СИСТЕМА И СПОСОБ ОБНАРУЖЕНИЯ ОРФАННЫХ ВЫСКАЗЫВАНИЙ

Изобретение относится к средствам для обнаружения орфанных высказываний. Технический результат заключается в повышении эффективности обнаружения орфанных высказываний. Принимают внедоменное высказывание, отклоненное доменным классификатором системы целенаправленного понимания языка. Оценивают внедоменное высказывание по одному или более признакам семантики, синтаксиса, тега части речи или лексики, определяющим, является ли внедоменное высказывание запросом веб-поиска или орфаном диалоговой системы целенаправленного понимания языка. Определяют, что внедоменное высказывание является орфаном, посредством: проверки оцененного внедоменного высказывания на существование семантического признака, причем семантический признак является сказуемым и/или аргументом; и классификации внедоменного высказывания как орфана, когда сказуемое и аргумент существуют. Генерируют ответ, указывающий, что внедоменное высказывание понято как запрос на выполнение некоторого действия, адресованный диалоговой системе ...

СИСТЕМА ДЛЯ СОЗДАНИЯ ДОКУМЕНТОВ НА ОСНОВЕ АНАЛИЗА ТЕКСТА НА ЕСТЕСТВЕННОМ ЯЗЫКЕ

Изобретение относится к системам и способам обработки естественного языка. Технический результат заключается в расширении арсенала средств построения составного текстового документа. Способ построения составного текстового документа включает получение устройством обработки данных текста на естественном языке, выполнение устройством обработки данных анализа текста с целью определения одной или более семантической связи в пределах одной или более области текста, создание устройством обработки данных поискового запроса с целью поиска дополнительного контента, передачу устройством обработки данных поискового запроса в один или более доступный информационный ресурс данного объекта с соответствующим концептом онтологии, получение в ответ множества дополнительных единиц контента, создание устройством обработки данных составного документа, в который входит множество разделов и в каждом разделе содержится одна область текста из множества областей текста, которая содержит одну или более дополнительную ...

РАСПОЗНАВАНИЕ СИМВОЛОВ С ИСПОЛЬЗОВАНИЕМ ИЕРАРХИЧЕСКОЙ КЛАССИФИКАЦИИ

Изобретения относятся к средствам распознавания символов с использованием нейронных сетей. Техническим результатом является обеспечение эффективного и точного распознавания символов для языков с большим алфавитом и мультиязычных текстов. Способ содержит: отнесение входного изображения графемы к первому кластеру графем из множества кластеров графем, где первый кластер графем содержит первое множество графем, выбор обрабатывающим устройством классификатора из множества классификаторов второго уровня, классификатора графем исходя из первого кластера графем, такого что выбранный классификатор был обучен распознавать первое множество графем, и обработку входного изображения графемы с помощью выбранного классификатора для распознавания по меньшей мере одного символа на выходном изображении графемы. Системы обеспечивают работу способа. 3 н. и 17 з.п. ф-лы, 9 ил.

NETWORK-INTERACTIVE USER INTERFACE OF MEANS SPEECH RECOGNITION AND PROCESSING OF NATURAL SPEECH

Systems and methods of applying pragmatics principles for interaction with visual analytics

A method uses natural language processing for visual analysis of a dataset by a computer. The computer displays a data visualization based on a dataset retrieved from a database using a first set of one or more database queries. The computer receives user input (e.g., keyboard or voice) to specify a natural language command related to the displayed data visualization. Based on the displayed data visualization, the computer extracts one or more independent analytic phrases from the natural language command. The computer further computes a set of one or more conversation centers associated with the natural language command based on the set of one or more analytic phrases. The computer then computes a set of analytical functions associated with the set of one or more conversation centers, thereby creating a set of one or more functional phrases. The device then updates the data visualization based on the set of one or more functional phrases.

SYSTEMS AND METHODS FOR IDENTIFYING AND SUGGESTING EMOTICONS

Various embodiments provide a method that comprises receiving a set of segments from a text field, analysing the set of segments to determine at least one of a target subtext or a target meaning associated with the set of segments, and identifying a set of candidate emoticons where each candidate emoticon in the set of candidate emoticons has an association between the candidate emoticon and at least one of the target subtext or the target meaning. The method may further comprise presenting the set of candidate emoticons for entry selection at a current position of an input cursor, receiving an entry selection for a set of selected emoticons from the set of candidate emoticons, and inserting the set of selected emoticons into the text field at the current position of the input cursor. WO 2013/096482 PCT/US2012/070677 Q0 m Cd: UJO) z md 0 C:U 0-i ...

Method of and system for inferring user intent in search input in a conversational interaction system

A method of inferring user intent in search input in a conversational interaction system is disclosed. A method of inferring user intent in a search input includes providing a user preference signature that describes preferences of the user, receiving search input from the user intended by the user to identify at least one desired item, and determining that a portion of the search input contains an ambiguous identifier. The ambiguous identifier is intended by the user to identify, at least in part, a desired item. The method further includes inferring a meaning for the ambiguous identifier based on matching portions of the search input to the preferences of the user described by the user preference signature and selecting items from a set of content items based on comparing the search input and the inferred meaning of the ambiguous identifier with metadata associated with the content items.

MOBILE WIRELESS COMMUNICATIONS DEVICE PROVIDING ENHANCED TEXT NAVIGATION INDICATORS AND RELATED METHODS

A mobile wireless communications device may include a portable, handheld housing, and a display and keypad carried by the housing. In particular, the keypad may include a plurality of symbol keys each having indicia of at least one respective symbol thereon, and an alternate function key. A user input device and a controller may also be carried by the portable, handheld housing. The controller may be connected to the display and the keypad, and it may generate a menu of possible desired words based upon actuation of the symbol keys, and generate a word cursor in the menu for scrolling through the possible desired words based upon the user input device. The controller may also change the word cursor to a symbol cursor based upon actuation of the alternate function key for scrolling through symbols in the possible desired words based upon the user input device.

Document searching method and document indexing method, which use multi-byte encoding

Animation display method and man-machine interaction device

Illegal outgoing mailbox identification system, method, device and storage medium

Computer executing method and systems and devices for searching using queries

CONTROL PUBLICATION OF MESSAGE RELATING TO A USER

Knowledge base for tennis, has interrogative knowledge base with lexical unit database having key words associated to classes of interrogation syntax structures of request in natural language and to interrogation object concepts and roles

La présente invention concerne une base de connaissances relative à un domaine prédéterminé de connaissances, cette base de connaissances comprenant au moins une base d'ontologie (12) constituée de concepts et de rôles formalisés soumis à un ensemble de contraintes sémantiques et une base d'instances (14) relatives aux concepts. Cette base de connaissances comprend en outre une base de connaissances (11) relative au domaine de connaissances comprenant au moins une base d'unités lexicales du type constructeur d'interrogation constituée de mots-clefs représentatifs de types de questions et de motifs syntaxiques, les mots-clefs représentatifs de types de question étant associés à un ensemble prédéterminé de classes de structures syntaxiques d'interrogation et à un ensemble prédéterminé de concepts et de rôles objets d'interrogation. Application à tout type de langage naturel.

SYSTEMS AND METHODS FOR SEARCHING USING QUERIES WRITTEN IN A DIFFERENT CHARACTER-SET AND/OR LANGUAGE FROM THE TARGET PAGES

LANGUAGE MODEL ADAPTATION USING SEMANTIC SUPERVISION

MESSENGER ADVERTISEMENT SERVICE METHOD THROUGH DIALOG ANALYSIS AND APPARATUS THEREOF

Disclosed are a messenger advertisement service method through dialog analysis and an apparatus thereof. The messenger advertisement service method according to an embodiment of the present invention comprises the steps of: analyzing dialog contents input in a messenger chat room; determining a keyword through analysis of the dialog contents; and exposing an advertisement related to the determined keyword to the messenger chat room. COPYRIGHT KIPO 2018 (AA) Start (BB) End (S210) Analyzing dialog contents in a messenger chat room (S220) Determining an advertisement exposure keyword (S230) Searching an advertisement corresponding to the determined keyword (S240) Exposing the searched advertisement to the messenger chat room (S250) Setting a link to a corresponding advertisement page and highlighting in the determined keyword in the dialog contents (S260) Providing a reward due to advertisement exposure to participants of the messenger chat room ...

미디어 체험과 링크된 실시간 토픽 관련의 표적 광고

... 방법 및 시스템은 미디어 콘텐츠와 연관된 실시간 키워드를 수신하고, 미디어 콘텐츠를 대면하는 사용자와 연관된 수식어 데이터(modifier data)를 식별하는 것과 관련되어 있다. 또한, 실시간 키워드 및 수식어 데이터는 광고 서비스(advertising service)로 전송될 수 있고, 이것은 실시간 키워드 및 수식어 데이터를 기반으로 토픽 관련(topic-relevant) 및 사용자 특정(user-specific)의 광고를 선택할 수 있다.

DIGITAL DEVICE FOR PROVIDING TEXT MESSAGING SERVICE AND THE METHOD FOR CONTROLLING THE SAME

일관된 텍스트 제안 출력

... 일 예시에서, 방법은 컴퓨팅 디바이스에 의해서 그리고 디스플레이를 위해서, 복수 개의 텍스트 제안 영역들을 포함하는 그래픽 사용자 인터페이스를 출력하는 것을 포함한다. 상기 방법은 컴퓨팅 디바이스에 의해서 프레즌스-감응 입력 디바이스에서 검출되는 제스처 입력의 지시를 수신하는 것과, 그리고, 상기 제스처 입력의 지시에 적어도 부분적으로 기초해서, 복수 개의 후보 문자열들로부터 후보 문자열을 선택하는 것을 더 포함한다. 상기 방법은 상기 복수 개의 텍스트 제안 영역들로부터의 특정한 텍스트 제안 영역 내에 디스플레이되는 동안 상기 후보 문자열이 이전에 선택되었음을 결정하는 것과, 그리고 디스플레이를 위해서 그리고 상기 특정한 텍스트 제안 영역 내에 디스플레이되는 동안 상기 후보 문자열이 이전에 선택되었음을 결정함에 적어도 부분적으로 기초해서, 상기 특정한 텍스트 제안 영역 내에 상기 후보 문자열을 출력하는 것을 더 포함한다.

음성 데이터 처리 방법 및 이를 지원하는 시스템

... 시스템에 있어서, 통신 회로, 상기 통신 회로와 기능적으로 연결된 적어도 하나의 프로세서, 및 상기 프로세서와 기능적으로 연결된 적어도 하나의 메모리를 포함하고, 상기 메모리는, 실행 시에, 상기 프로세서가, 상기 통신 회로를 통해 외부 장치로부터 음성 데이터를 획득하고, 상기 음성 데이터를 텍스트 데이터로 변환하고, 상기 텍스트 데이터에 포함된 적어도 하나의 표현을 분류하고, 상기 적어도 하나의 표현이 상기 외부 장치를 이용한 제1 태스크의 수행을 요청하는 제1 표현을 포함하면, 상기 통신 회로를 통해 상기 제1 태스크의 수행과 관련한 상기 외부 장치의 상태들의 시퀀스에 관한 제1 정보를 상기 외부 장치로 전송하고, 상기 적어도 하나의 표현이 상기 제1 표현을 포함하지 않고 상기 제1 표현과 다른 제2 표현을 포함하며, 데이터베이스에 상기 제2 표현과 매핑된 상기 제1 표현이 존재하면, 상기 통신 회로를 통해 상기 제1 정보를 상기 외부 장치로 전송하도록 하는 인스트럭션들을 저장하는 것을 특징으로 하는 시스템이 개시된다. 이 외에도 명세서를 통해 파악되는 다양한 실시 예가 가능하다.

METHOD FOR SELECTING REPRESENTATIVE WORD OF ELECTRONIC DOCUMENT, METHOD FOR PROVIDING ELECTRONIC DOCUMENT, AND COMPUTING SYSTEM PERFORMING METHODS

Disclosed are a method for selecting a representative word capable of representing an electronic document from among respective words included in the electronic document, a method for providing an electronic document requested by a user terminal and information on the electronic document related thereto by using the selected representative word of each electronic document, and a computing system performing the methods. According to an aspect of the present invention, a method for selecting a representative word of an electronic document performed by a predetermined computing system comprises the following steps of: obtaining an electronic document to be analyzed belonging to a predetermined electronic document group including a plurality of electronic documents; extracting at least one candidate word from the electronic document to be analyzed by predetermined extraction standards; obtaining a weight value of each of the at least one candidate word; and selecting at least a portion of the ...

APPARATUS AND METHOD FOR EXTRACTING SOCIAL RELATION BETWEEN ENTITIES

Disclosed area an apparatus and a method for extracting the social relation between entities. The apparatus for extracting the social relation between entities includes a processor and a calculation unit. The processor divides syntactic words in a first sentence into a ruling element and depending elements, places the syntactic word serving as the ruling element at the center of the first sentence, and places the syntactic words serving as the depending elements at both ends of the center to create a first dependency trigram. The calculation unit compares the first dependency trigram with a second dependency trigram created in relation to a second sentence to be compared with the first sentence and selects the first and second sentences as sentences having a similar relation according to the comparison result. COPYRIGHT KIPO 2016 (101) Processor (103) Calculation unit (105) Output unit ...

INFORMATION PROCESSING SYSTEM AND INFORMATION PROCESSING METHOD FOR CHARACTER INPUT PREDICTION

The present invention relates to an information processing system which displays candidates of displayed character strings of phrases corresponding to input character strings set to correspond to operation of inputting characters in a terminal device (1). The terminal device obtains internal candidates (list (A)) by performing search by the input character strings and transmits a candidate transmission request signal, including the input character strings and identification information of a dictionary for the terminal device stored in the equipment, to a server (2). The server (2) performs search by using the dictionary for the terminal device and a dictionary for the sever dedicated to the equipment to correspond to the identification information in the received candidate transmission request signal. The server (2) transmits dictionary data (list (B)), different from dictionary data (list (D)) extracted from the dictionary for the terminal device in dictionary data (list (E)) extracted ...

LANGUAGE INDEPENDENT PROBABILISTIC CONTENT MATCHING

Content is received and compared against rules for identifying a type of content. Each rule has both segmented and unsegmented patterns. The content is matched against the patterns and assigned a confidence score that is higher if the content matches a segmented pattern and lower if the content matches an unsegmented pattern.

SYSTEM AND METHOD FOR GENERATING NATURAL LANGUAGE PHRASES FROM USER UTTERANCES IN DIALOG SYSTEMS

Embodiments of a dialog system that employs a corpus-based appioach to generate responses based on a given number of semantic constraint-value pairs are described. The system makes full use of the data from the user input to produce dialog system responses in combination with a template generator The system primarily utilizes constraint values in order to realize efficiencies based on the more frequent tasks performed in real dialog systems although rhetorical or discourse aspects of the dialog could also be included in a similar way, that is, labeling the data with such information and performing a training process. The benefits of this system include higher quality user-aligned responses, broader coverage, faster response time, and shorter development cycles ...

INTELLIGENT PRESENTATION OF DOCUMENTS

In some implementations, documents can be presented on a display of a computing device based on a context of the computing device. The context can include a current time and/or current location associated with the computing device. The documents can be presented based on a time and/or location associated with the documents. Documents can be downloaded and shared between devices. Documents can be dynamically updated based on document vendor provided information and/or other network based resources. In some implementations, the various graphical interfaces described herein provide access to a variety of document types in an organized and efficient manner.

DOCUMENT STRUCTURE IDENTIFIER

A method of automated document structure identification based on visual cues is disclosed herein. The two dimensional layout of the document is analyzed to discern visual cues related to the structure of the document, and the text of the document is tokenized so that similarly structured elements are treated similarly. The method can be applied in the generation of extensible mark-up language files, natural language parsing and search engine ranking mechanisms.

SYSTEM AND METHOD FOR CONDUCTING ELECTRONIC COMMERCE

A method of processing data exchanged between a first trading partner and a second trading partner includes receiving a first data file from the first trading partner, the first data file having a first file format and being an electronic representation of at least one document. The method further includes translating the received first data file into at least one second data file having an XML file format and transforming each of the at least one second data files into a normalized third data file having an XML file format, wherein the third data file is normalized according to a data format associated with the second trading partner.

VISUAL DISPLAY OF SEMANTIC INFORMATION

Techniques involving visual display of information related to matching user utterances against graph patterns are described. In one or more implementations, an utterance of a user is obtained that has been indicated as corresponding to a graph pattern through linguistic analysis. The utterance is displayed in a user interface as a representation of the graph pattern.

METHOD AND DEVICE FOR AUTOMATICALLY ESTABLISHING A SERVICE FORM

Disclosed is a method for automatically establishing a service form from a natural-language service request. Said method comprises the following steps: the language data that is contained in a language data stream representing a natural-language service request is analyzed regarding information included therein by means of a language recognition system (5); the information contained in the language data stream is classified into a number of predefined classes based on information features that are characteristic of the classes, said classes representing a variety of information linked to filling-in options of the service form; and the service form is established by selecting the options of the service form corresponding to the classes into which the information has been classified.

Method and apparatus for computer-implemented processing of payment entries

Method and apparatus for the computer-implemented processing of payment entries which are intended to move money in an account, wherein a payment entry is automatically checked for errors as it is received and if at least one error occurs an error sequence is decided upon from a list of error routines by means of an error routine, all the errors occurring in a given payment entry being supplied collectively to the error routine, and within the scope of the error routine the errors which have occurred are weighted and appropriate error follow-up measures are initiated depending on the results of the error weighting.

Attorney terminal having outline preparation capabilities for managing trial proceedings

The present invention provides attorney terminals which operate using an outline for storing, associating and managing case evidence, case law and work product for a given lawsuit at issue. Accessed through attorney terminals, the outline is structured based on a hierarchical categorization of the lawsuit into the law and fact at issue. Associated with each categorization entry in the hierarchical outline are groupings of case law, case evidence, relevance and draft discovery information for rapid access by the attorney. Each categorization entry in the tailored outline provides instant access to case law via headnotes, treatise selections, seminal cases, and preset searches. The disclosed invention also automatically: 1) tracks the use of Exhibits in a proceeding; 2) generates draft portions of a pretrial order including jury instructions; and 3) generates time-lines for analysis and use during a proceeding. Draft interrogatories, document requests and deposition or trial questions are ...

Basic poetry generation

A method of analyzing an author's work, including reading a text file, generating an analysis model from the text file and storing the analysis model. The text file may be a poem, the poem containing ASCII text. The analysis model is a linked data structure. The linked data structure includes n-gram data structures, the n-gram structures including combinations of 1-gram data structures, bigram data structures, trigram data structures and quadrigram data structures.

Text summarization using relevance measures and latent semantic analysis

Text summarizers using relevance measurement technologies and latent semantic analysis techniques provide accurate and useful summarization of the contents of text documents. Generic text summaries may be produced by ranking and extracting sentences from original documents; broad coverage of document content and decreased redundancy may simultaneously be achieved by constructing summaries from sentences that are highly ranked and different from each other. In one embodiment, conventional Information Retrieval (IR) technologies may be applied in a unique way to perform the summarization; relevance measurement, sentence selection, and term elimination may be repeated in successive iterations. In another embodiment, a singular value decomposition technique may be applied to a terms-by-sentences matrix such that all the sentences from the document may be projected into the singular vector space; a text summarizer may then select sentences having the largest index values with the most important ...

METHODS AND SYSTEMS FOR AUTOMATICALLY IDENTIFYING KEYWORDS OF VERY LARGE TEXT DATASETS

Methods and systems for automatically generating a list of keywords for an end user from very large amounts of text data. In an embodiment, a computer-implemented method includes a processor receiving a request from an end user device to generate a key word list, reading text data of a corpus of at least one domain, performing pre-processing of the text data of the corpus, and removing stop words. The process also includes generating, by the processor, a term document matrix, removing rare words, and identifying unigrams, bigrams and trigrams. The processor then performs a stemming process on the unigrams, bigrams and trigrams to form stem words, replaces each stem word with its highest frequency unigram to generate normalized unigrams, generates normalized bigrams and normalized trigrams based on the normalized unigrams, and generates a list of keywords comprising the normalized unigrams, the normalized bigrams, and the normalized trigrams.

Common interface for ink trees

A system, method, and data structure are described that permit a function to be operable at a designated node or sub nodes. An instruction that designates one or more nodes is processed to perform the instruction on each of the nodes. If the instruction is not performable on a current node, the data structure relating to the current node is navigated to obtain one or more sub nodes. The instruction is then performed on the sub nodes.

Method and apparatus for providing information by using messenger

A user device which can provide information related to text, which is input into a messenger, on a background screen (10) of the messenger, and a method for providing information in the user device are provided. The method includes displaying a conversation exchanged through a messenger,detecting text related to a content in the conversation (707), displaying a content image matched to the content on a background of the conversation (711), and providing information related to the content in response to selection of the content image.

PREDICATE TEMPLATE GATHERING DEVICE, SPECIFIED PHRASE PAIR GATHERING DEVICE AND COMPUTER PROGRAM FOR SAID DEVICES

INTERACTIVE USER INTERFACE USING SPEECH RECOGNITION AND NATURAL LANGUAGE PROCESSING

A system and method for interacting with objects, via a computer using utterances, speech processing and natural language processing. A Data Definition File relates networked objects and a speech processor. The Data Definition File encompasses a memory structure relating the objects, including grammar files, a context-specific dictation model, and a natural language processor. The speech processor searches a first grammar file for a matching phrase for the utterance, and for searching a second grammar file for the matching phrase if the matching phrase is not found in the first grammar file. The system also includes a natural language processor for searching a database for a matching entry for the matching phrase; and an application interface for performing an action associated with the matching entry if the matching entry is found in the database. The system utilizes context-specific grammars and dictation models, thereby enhancing speech recognition and natural language processing efficiency ...

検査報告書を生成する装置、システム、方法およびプログラム

文書閲覧装置およびプログラム

АВТОМАТИЗИРОВАННЫЕ СПОСОБЫ И СИСТЕМЫ ВЫЯВЛЕНИЯ НА ИЗОБРАЖЕНИЯХ, СОДЕРЖАЩИХ ДОКУМЕНТЫ, ФРАГМЕНТОВ ИЗОБРАЖЕНИЙ ДЛЯ ОБЛЕГЧЕНИЯ ИЗВЛЕЧЕНИЯ ИНФОРМАЦИИ ИЗ ВЫЯВЛЕННЫХ СОДЕРЖАЩИХ ДОКУМЕНТЫ ФРАГМЕНТОВ ИЗОБРАЖЕНИЙ

Изобретение относится к области обработки изображений и оптическому распознаванию символов. Технический результат – обеспечение выявления содержащих документ фрагментов на изображении. Система обработки содержащих документы изображений предназначена для: получения изображения, применения к полученному изображению детекторов признаков, причем каждый детектор признаков создает из изображения связанный с детектором набор признаков, для каждой из одной или более моделей типа документа; применения модели типа документа к полученному изображению, причем модель документа содержит набор признаков модели, для создания набора итоговых пар признаков; применения одной или более проверок к набору итоговых пар признаков и в случае установления наличия в изображении фрагмента изображения, содержащего соответствующий модели тип документа, применение преобразования, которое преобразует положения признаков модели в положения на изображении для создания и сохранения положений одной или более точек содержащего ...

СПОСОБ ЛИНГВО-ЛОГИЧЕСКОГО ПРЕОБРАЗОВАНИЯ СТРУКТУРИРОВАННОГО МАССИВА ДАННЫХ, СОДЕРЖАЩЕГО ЛИНГВИСТИЧЕСКОЕ ПРЕДЛОЖЕНИЕ

Изобретение относится к области вычислительной техники для обработки массивов данных. Технический результат заключается в повышении точности предварительной обработки текста на естественном языке для его последующей индексации и обработки. Технический результат достигается за счет формирования первой структуры данных, на котором формируют первую структуру данных СМД, содержащую элементы упомянутой первой структуры данных, формирования базы данных лингвистических признаков (БДЛП), на котором выявляют лингвистические признаки текстовых элементов (ТЭ) лингвистического предложения, из которых формируют базу данных, представляющую собой БДЛП текстовых элементов лингвистического предложения; формирования второй структуры данных, на котором формируют вторую структуру данных СМД, содержащую элементы упомянутой второй структуры данных; формирования третьей структуры данных, на котором формируют третью структуру данных СМД, содержащую элементы упомянутой третьей структуры данных; и формирования четвертой ...

ИСПОЛЬЗОВАНИЕ АВТОЭНКОДЕРОВ ДЛЯ ОБУЧЕНИЯ КЛАССИФИКАТОРОВ ТЕКСТОВ НА ЕСТЕСТВЕННОМ ЯЗЫКЕ

Группа изобретений относится к вычислительным системам и способам обработки естественного языка. Технический результат состоит в достижении высокой точности классификации при обучении классификатора на обучающих выборках относительно небольшого объема посредством использования результата скрытого слоя автоэнкодера для дообучения классификатора. Для достижения технического результата предложен способ, который включает создание, с помощью вычислительной системы, множества векторов признаков, обучение, с использованием множества векторов признаков, автоэнкодера, представленного искусственной нейронной сетью, создание, с использованием автоэнкодера, результата скрытого слоя и обучение, с использованием обучающей выборки данных, классификатора текста. Также предложена система, включающая память и процессор, соединенный с запоминающим устройством. И предложен постоянный машиночитаемый носитель данных, включающий исполняемые команды, которые при исполнении их вычислительным устройством приводят ...

INTERACTIVE USER INTERFACE WITH SPEECH RECOGNITION AND NATURE LANGUAGE PROCESSING SYSTEM

TEXT CLASSIFICATION OF MEANS OF EXTERNAL KNOWLEDGE

PRODUCTION PICTURES MOVED BY SUB-TITLES FOR

Automated system and method for creating machine-generated advertisements

A system and process provide a novel methodology to improve advertising performance by creating and testing new ad copy within advertisements more effectively and efficiently. The system includes an automated technology that produces a virtually unlimited number of predictably high-quality machine-generated advertisements, by combining and recombining the words and phrases (e.g., ad copy) that have proven to be most effective in previous advertisements with new words and phrases that are determined as likely to be effective based on the motivations of the target audience that will be viewing the advertisements. The novel technology is a combined order of specific rules that renders information into a specific format that is then used and applied to create desired results in the form of top performing ad copy and top performing machine-generated advertisements.

Intelligent presentation of documents

In some implementations, documents can be presented on a display of a computing device based on a context of the computing device. The context can include a current time and/or current location associated with the computing device. The documents can be presented based on a time and/or location associated with the documents. Documents can be downloaded and shared between devices. Documents can be dynamically updated based on document vendor provided information and/or other network based resources. In some implementations, the various graphical interfaces described herein provide access to a variety of document types in an organized and efficient manner.

SYSTEM AND METHOD FOR MANAGING CONTRACTS USING TEXT MINING

A method of managing contracts is provided. The method includes storing a plurality of electronic contracts including unstructured textual data. The method further includes determining one or more linguistic patterns associated with a business parameter and generating linguistic rules based on the one or more linguistic patterns. The method further includes using text mining tools to extract information regarding the business parameter from the unstructured textual data using one or more of the linguistic rules. The method further includes generating a visual output based on at least a portion of the extracted information.

SYSTEMS AND METHODS OF APPLYING PRAGMATICS PRINCIPLES FOR INTERACTION WITH VISUAL ANALYTICS

A method uses natural language processing for visual analysis of a dataset by a computer. The computer displays a data visualization based on a dataset retrieved from a database using a first set of one or more database queries. The computer receives user input (e.g., keyboard or voice) to specify a natural language command related to the displayed data visualization. Based on the displayed data visualization, the computer extracts one or more independent analytic phrases from the natural language command. The computer further computes a set of one or more conversation centers associated with the natural language command based on the set of one or more analytic phrases. The computer then computes a set of analytical functions associated with the set of one or more conversation centers, thereby creating a set of one or more functional phrases. The device then updates the data visualization based on the set of one or more functional phrases.

METHOD AND SYSTEM FOR DETECTING AND CLASSIFICATION OF CAUSES OF CLAIMS USERS IN SELF-SERVICE DEVICES

CONTROL PUBLICATION OF MESSAGE RELATING TO A USER

Pour contrôler la publication de message dans un serveur de réseau social (SRS) depuis un terminal de communication (TC), un serveur (SC) apte à communiquer avec le serveur de réseau social (SRS) intercepte un message (Mes) contenant des données textuelles (DonT), le message étant fourni par un utilisateur inscrit auprès du serveur de réseau social (SRS) et destiné à être publié par le serveur de réseau social (SRS). Le serveur (SC) extrait des mots-clés associés aux données textuelles (DonT) en fonction d'une analyse sémantique des données textuelles, et pour bloque la publication du message (Mes) si au moins un mot-clé extrait est inclus dans un ensemble de mots-clés (EnsMC) associé à un autre utilisateur inscrit auprès du serveur de réseau social (SRS), ledit utilisateur étant inclus dans une liste (LC) initialement définie par ledit autre utilisateur.

SALES PROMOTION SYSTEM BASED ON VOICE INFORMATION AND METHOD USING SAME

A sales promotion system based on voice information is disclosed. The sales promotion system includes: a user terminal for outputting event information on a sales promotion activity and collecting voice information on the sales promotion activity; and a server for generating performance information on the sales promotion activity using the collected voice information. Accordingly, the present invention can provide the sales promotion system based on voice information, capable of contributing to the sales promotion of products by transmitting the product information of products included in a product list to a customer by providing the product list about products to be promoted to employees, analyzing the performance of the sales promotion activities of the employees who recommend the products, and rewarding for the analyzed performance. COPYRIGHT KIPO 2018 (100) User terminal (200) Server (300) Manager terminal ...

가중치에 의한 다수 분야별 검색 기능을 구비한 지식관리 시스템

... 분야별 대표 색인어를 이용하여 해당 문서의 각 분야의 유사도를 산출하고, 검색된 문서에 대한 분야 정보를 각 분야별 유사도를 이용하여 검색결과를 제공하는, 가중치에 의한 다수 분야별 검색 기능을 구비한 지식관리 시스템에 관한 것으로서, 샘플 문서들로부터 대표 단어들을 추출하여 저장하는 대표단어 관리부; 각 문서에 대하여, 각 분야별 대표 색인어와 해당 문서 간의 유사도를 이용하여 해당 문서의 각 분야별 유사도를 산출하여 저장하는 유사도 연산부; 및, 문서 검색 요청에 따라 문서를 검색하고, 검색된 문서를 표시하여 제공하되, 검색된 문서의 각 분야별 유사도를 표시하는 검색부를 포함하는 구성을 마련한다. 상기와 같은 지식관리 시스템에 의하여, 분야별 대표 색인어를 추출하고 이를 이용하여 각 분야별 문서와의 유사도로 해당 분야의 소속 정도를 구함으로써. 문서나 산출물들을 보다 정확하게 분야별로 속하는 정도를 분석할 수 있고, 이를 통해, 보다 정확한 분야별 검색을 제공할 수 있다.

스토리텔링 저작지원 장치 및 그 방법

... 본 발명은 스토리텔링 저작지원 장치 및 그 방법에 관한 것으로, 서사정보 전처리모듈을 통해 데이터 수집모듈로부터 수집된 스토리 데이터에서 명사들을 추출하고, 서사정보 선정모듈을 통해 추출된 명사들 중 중요명사들을 서사정보로 선정하며, 관계형성모듈을 통해 서사정보 관계도를 형성하고, 이를 바탕으로 토픽맵으로 구축하여 시각화시키며, 캐릭터 관리모듈을 통해 서사정보 관계도 중 인물정보에 해당하는 적어도 하나의 캐릭터 이미지를 관리함으로써, 스토리 데이터를 수집할 수 있을 뿐만 아니라 수집된 스토리 데이터의 구조를 체계적이고 정확하게 분석할 수 있어, 스토리텔링의 스토리를 저작하는 저작자에게 시간적 및 비용적 부담을 줄일 수 있을 뿐만 아니라 스토리텔링의 스토리 저작 효율을 극대화시킬 수 있는 효과가 있다.

글에 반영된 사용자의 심리 상태 정보 제공 장치 및 그 방법

... 글에 반영된 사용자의 심리 상태 정보 제공 장치 및 그 방법이 개시된다. 본 발명의 일 실시 예에 따른 정보 제공 장치는, 사용자가 작성한 글들을 시간 단위로 정리하고, 글에 포함된 단어들을 카테고리 별로 분류된 워드 그래프에 투영시켜 워드 그래프 내에 투영된 단어들의 분포를 분석하여 글에 반영된 사용자의 심리 상태를 판단하는 제어부와, 사용자의 심리 상태 판단 결과를 글 작성 시간 정보와 연관 지어 제공하는 출력부를 포함한다.

DEVICE FOR EXTRACTING A DESCRIPTIVE CONCEPT EXPRESSION ABOUT TERMS FROM LITERATURE BY USING A PREDICATE-ARGUMENT TUPLE AND A METHOD THEREOF

PURPOSE: A device for extracting a descriptive concept expression about terms from literature and a method thereof are provided to actually enable an conceptual approach to the literature by performing a sentence search based on a PAT(Predicate Argument Tuble) for extracting a sentence corresponding to an inputted term. CONSTITUTION: A conversion processing unit(100) designates a correlation about words included in each paragraph of a sentence based on a grammatical relation between the words composing the sentence to extract a PAT corresponding to the sentence. The conversion processing unit reforms a structure of the PAT for grouping the PAT. An information storage unit(200) stores the reformed PAT so that the PAT corresponds to the sentence. An information search unit(300) extracts the stored sentence to include the PAT extracted from a sentence corresponding to a query. COPYRIGHT KIPO 2013 [Reference numerals] (100) Conversion processing unit; (200) Information storage unit; (300) Information ...

유사군 DB를 이용한 임의명칭의 특정 국가용 후보명칭 추천 시스템 및 방법

... 본 발명은 유사군 DB를 이용한 임의명칭의 특정 국가용 후보명칭 추천 시스템 및 방법을 개시한다. 상기 시스템은, 임의의 특정명칭을 획득하는 ETL 모듈과; 빅데이터로부터 특정명칭과 관련있는 다수의 유사명칭을 획득하는 정보처리 모듈과; 특정명칭 및 다수의 유사명칭이 서로 관련지어 저장되어 있는 유사군 DB를 구비한 DB 모듈과, 임의의 문의명칭을 입력받는 인터페이스 모듈과; 문의명칭과 발음 또는 표음이 유사한 로컬명칭을 생성하고, 문의명칭 또는 로컬명칭이 유사군 DB에 저장된 특정명칭 또는 유사명칭에 존재하는지 검색하고 결과를 출력하는 부가기능 모듈을 포함한다.

SYSTEMS AND METHODS FOR SEARCHING USING QUERIES WRITTEN IN A DIFFERENT CHARACTER-SET AND/OR LANGUAGE FROM THE TARGET PAGES

유니버셜 번역

... 미디어 아이템의 가능성이 높은 소스 언어가 내인성 또는 외인성 인자, 가령 미디어 아이템 내의 단어 및 미디어 아이템 작성자에 의해 알려진 언어에 기반하여 미디어 아이템의 초기 언어 식별을 시도함으로써 식별될 수 있다. 이러한 초기 식별은 대응하는 가능성 인자를 갖는 가장 가능성이 높은 소스 언어들의 리스트를 생성할 수 있다. 번역이 이후 각각의 가장 가능성이 높은 소스 언어를 추정하여 수행될 수 있다. 번역은 다수의 출력 언어들에 대해 수행될 수 있다. 각각의 발생된 번역은 다수의 인자에 기반하여 대응하는 점수를 수신할 수 있다. 점수는 그들이 공통의 소스 언어를 가지는 경우 조합될 수 있다. 이러한 조합된 점수가 미디어 아이템의 소스 언어에 대해 이전에 식별된 가능성 인자에 가중치를 부여하는데 사용될 수 있다.

회의 관리 방법, 장치 및 시스템

... 본 발명은 회의 관리 방법 및 장치에 관한 것으로, 제1 단말로부터 수신된 회의 예약 정보에 대한 키워드 분석을 수행하는 단계, 기저장된 과거의 회의 중 키워드와 관련된 과거 회의 내역에 포함된 참여자 리스트를 제1 단말로 전송하는 단계, 제1 단말로부터 참여자 리스트에 포함된 참여자 중 적어도 하나의 참여자에 대한 권한을 수신하는 단계 및 적어도 하나의 참여자에 권한을 부여하고 회의 예약 정보를 기반으로 회의 예약을 수행하는 단계를 포함할 수 있고, 다른 실시 예로도 적용이 가능하다.

METHOD FOR PERFORMING SEARCH, INTERPRETATION, INPUT AND LIKE OF DATA BY OPERATING ONLY KEYS WITHOUT MARKING LETTERS ON KEYBOARD CONNECTED TO PC

The present invention relates to a method for performing search, interpretation, input, and the like of data by operating only keys without marking letters on a keyboard connected to a PC. Natural words are displayed and stored in a three-dimensional space (a pop-up window firstly replacing a function of the three-dimensional space on the Internet) for the first time in human history. Morphemes forming the words are moved in the directions of upwards, downwards, left, and light or the direction of the height (thickness) of the pop-up window replacing a function of a three-dimensional space. (Refer to a web source file, a database file, and a program backup file to be submitted as an appendix afterwards.) So-called artificial intelligence words, performing a globally common (commonly used) word function, are developed. A base on which human beings and robots apply artificial intelligence words is prepared. A base on which robots read Internet data of computers and communicate with human ...

음성 입력의 워드-레벨 수정

... 본 명세서의 내용은 여러 가지 중에서, 모바일 컴퓨팅 디바이스에 있는 마이크로폰으로부터 음성 오디오 데이터를 수신하는 단계를 포함하는 전사된 텍스트에 있는 워드들을 수정하기 위한 컴퓨터-구현 방법으로 구현될 수 있다. 본 발명은 상기 음성 오디오 데이터를 전사 시스템에 송신하는 단계를 더 포함한다. 본 발명은 상기 모바일 컴퓨팅 디바이스에서, 상기 전사 시스템이 상기 음성 오디오 데이터로부터 전사한 워드 래티스를 수신하는 단계를 더 포함한다. 본 발명은 상기 워드 래티스로부터 하나 이상의 전사된 워드를 제시하는 단계를 더 포함한다. 본 발명은 상기 제시된 전사된 워드들 중 적어도 하나에 대한 사용자 선택을 수신하는 단계를 더 포함한다. 본 발명은 상기 선택된 전사된 워드에 대한 상기 워드 래티스로부터 하나 이상의 대체 워드를 제시하는 단계를 더 포함한다. 본 발명은 상기 대체 워드들 중 적어도 하나에 대한 사용자 선택을 수신하는 단계를 더 포함한다. 본 발명은 상기 제시된 전사된 워드들에 있는 상기 선택된 전사된 워드를 상기 선택된 대체 워드로 교체하는 단계를 더 포함한다.

SYSTEMS AND METHODS FOR SEARCHING USING QUERIES WRITTEN IN A DIFFERENT CHARACTER-SET AND/OR LANGUAGE FROM THE TARGET PAGES

SPEECH RECOGNITION DEVICE, SPEECH RECOGNITION METHOD THEREOF, MODEL GENERATION DEVICE AND MODEL GENERATION METHOD FOR SAME

The present invention relates to a speech recognition device, a speech recognition method thereof, a model generation device and a model generation method for the same. According to an aspect, the speech recognition device comprises: a speech model; a pronunciation dictionary consisting of basic words; and a word spacing correcting unit for collecting a spacing blank. COPYRIGHT KIPO 2017 (100) Model generation device (200) Speech recognition device ...

CLASSIFICATION OF AMBIGUOUS GEOGRAPHIC REFERENCES

A location classifier generates location information based on textual strings in input text. The location information defines potential geographical relevance of the input text. In determining the location information, the location classifier may receive at least one geo-relevance profile associated with at least one string in the input text, obtain a combined geo-relevance profile for the document from the at least one geo-relevance profile, and determine geographical relevance of the input text based on the combined geo-relevance profile. © KIPO & WIPO 2007 ...

병렬 처리용 하이브리드 클라이언트/서버 아키텍처

... 본 발명은 원격 및 로컬 서비스의 모두의 고유 능력을 레버리징 이용할 수 있는 예시적인 하이브리드 클라이언트/서버 아키텍처를 설명한다. 데이터는 원격 및 로컬 프로세스에 의해 병렬 처리될 수 있다. 병렬 처리 중에 생성된 결과는 원격 및 로컬 서비스 사이에 교환되고 개별 서비스에 의해 생성된 결과를 업데이트하는데 사용될 수 있다. 하이브리드 클라이언트/서버 아키텍처는 향상된 추론, 로컬 및 원격 구독에 기초하는 하이브리드 구독을 생성하고, 자연 언어 표현 평가 서비스를 향상시키는데 이용될 수 있다.

사례기반 추론 및 형태소 유사도를 기반으로 하는 자동 상담 장치 및 방법

... 본 발명의 일 실시 예에 따른 자동 상담 장치는 사용자 질의를 수신하는 대화 인터페이스부 및 사용자 질의와 데이터베이스에 저장된 모든 예상 질의를 비교하여, 유사도가 미리 지정된 임계값 이상인 예상 질의가 존재하는지 판단하는 사례기반추론 엔진부를 포함하되, 사례기반추론 엔진부는, 유사도가 임계값 이상인 예상 질의가 존재하는 경우, 모든 예상 질의 중 유사도가 가장 높은 예상 질의에 대응하는 의도를 검출하고, 의도에 대응하는 답변을 대화 인터페이스부를 통해 사용자에게 제공하는 것을 특징으로 한다.

TEXT CATEGORIZATION USING EXTERNAL KNOWLEDGE

A method of providing weighted concepts related to a sequence of one or more words, including: providing on a computer an encyclopedia with concepts and a document explaining each concept, forming a vector, which contains the frequency of the word for each concept, for each word in the encyclopedia, arranging the vector according to the frequency of appearance of the word for each concept, selecting the concepts with the highest frequencies for each word from the vector, truncating the rest of the vector, inducing a feature generator using the truncated vectors; wherein the feature generator is adapted to receive as input one or more words and provide a list of weighted concepts, which are most related to the one or more words provided as input.

INFORMATION GIVING SYSTEM, INFORMATION GIVING METHOD, INFORMATION GIVING PROGRAM, AND INFORMATION GIVING PROGRAM RECORDING MEDIUM

An information giving system for giving attribute information to a part adequate in context as well as to a word unit including a specific character string expression. The system comprises analyzing means (21) for dividing a language expression into predetermined language units, a dictionary (31) for extracting vocabularies determining attribute information and selecting a language unit to which the attribute information is given, attribute information determining means (first attribute information determining means) (22) for extracting predetermined vocabularies from the language unit by using the dictionary and determining the attribute information, and attribute information giving language unit selecting means (second attribute information determining means) (23) for determining the attribute information of an adjacent language unit according to the determined attribute information and the relation of connection between language units.

SYSTEM AND METHOD FOR MANAGING SPENDING

A method of managing spending is provided. The method includes collecting procurement data from a plurality of data sources which may have associated source-specific product catalogs. The method further includes storing a global catalog specifying mapping relationships between source-specific product attributes specified by the source-specific product catalogs and generic attributes specified by the global catalog. The method further includes mapping the source-specific attributes associated with particular products to corresponding generic attributes based on the mapping relationships. The method further includes analyzing a portion of the collected procurement data, including identifying information regarding products associated with the particular procurement events based on the generic attributes associated with the products. The method further includes automatically generating a visual output based on the analysis of the collected procurement data.

Methods and systems for incrementally changing text representation

To reduce required display space, a text segment is reduced in size by successively eliminating portions of the text segment and by reducing a size of text of the text segment and/or a spacing between characters of the text segment. The reduction is thus visually represented in a step-wise manner, and recognizability of the text segment is maintained, even if the final representation of the text does not carry a full meaning and/or is not independently comprehensible, because of the impression left in the mind of the user by the step-wise reduction of the text segment. The reduction may be animated.

Unsupervised learning of paraphrase/translation alternations and selective application thereof

A computer-implemented method is disclosed for applying a given paraphrase alternation pattern to an input string. The method includes generating a language model and applying the language model to determine how to apply the given paraphrase alternation pattern to the input string.

APPARATUS AND METHOD FOR SEARCHING FOR RESOURCES OF E-BOOK

An apparatus and a method for searching for resources in an e-book are provided. The apparatus includes a memory having a resource-to-location mapping table in which information about resources of the e-book is mapped to location information that matches the resources of the e-book, and a controller for creating the resource-to-location mapping table and for controlling a search for a resource of the e-book that matches a location in the resource-to-location mapping table and a display of the detected resource of the e-book.

Context Based Online Advertising

A software and/or hardware facility for inferring user context and delivering advertisements, such as coupons, using natural language and/or sentiment analysis is disclosed. The facility may infer context information based on a user's emotional state, attitude, needs, or intent from the user's interaction with or through a mobile device. The facility may then determine whether it is appropriate to deliver an advertisement to the user and select an advertisement for delivery. The facility may also determine an appropriate expiration time and/or discount amount for the advertisement.

IDENTIFYING RELEVANT INFORMATION WITHIN A DOCUMENT HOSTING SYSTEM

This disclosure generally covers systems and methods that identify relevant information for a user based on an object graph for documents and other files hosted by a document hosting system. In particular, certain embodiments of the disclosed systems and methods generate an object graph comprising interconnected nodes representing relationships among documents and other files on the document hosting system. Using the object graph, the disclosed systems and methods can identify relevant information and provide results or recommendations corresponding to that information based on a query or on user input, respectively.

DOCUMENT PROCESSOR AND ASSOCIATED METHOD

Drag handle for applying image filters in picture editor

The present disclosure provides for dynamic application of image filters in picture editor applications. A selected filter is dynamically applied to a portion of an image displayed on a screen as a drag handle is moved across the image, the portion of the image to which the selected filter is applied being changeable in size with motion of handle across the image and determined by a position of the handle on the screen. Changes to the portion of the image caused by application of the selected filter are dynamically displayed as the handle is moved across the image displayed on the screen.

A method of copying a marked portion of a structured document

METHOD AND APPARATUS FOR CONVERTING DOCUMENTS BETWEEN PAPER MEDIUM AND ELECTRONIC MEDIA

An apparatus and method for providing access to computerized information services for users unequipped with computers, particularly information services related to commercial transactions. Images of hardcopy forms are used as means for conveying transactional information. Each image contains character and data fields with information for a particular transaction. The system captures the image (22) and converts the character and data fields (24) into computer readable form. The system enhances each image (221) and performs several levels of feature extraction, including character recognition techniques (241). The system optimizes database lookup (2411) and human operator manual keying (245) to assist character recognition techniques in developing accurate coded text from the features of the image. The system produces accurate coded text strings for transmission (26) over telecommunications networks to independent computer systems. Additionally, user services provides processing of data received ...

CHARACTER INPUT DEVICE

PURPOSE: To automatically calculate and output the designated number of characters by providing a means to store a designation range, a discrimination means for a character targeted to be calculated, a means to calculate the num ber of characters, and a means to output a calculation result. CONSTITUTION: When key data inputted by a key discrimination means 1 shows calculation method designation of type1, a character number calculation means 5 calculates character data within a range designated by a calculation range designation means 3 by a calculation character discrimination means 4 and a character number output means 6, and outputs a result. When the key data inputted by the means 1 shows calculation method designation of type2, the means 5 calculates the number of characters at every input of the character data by the means 4 and 6, and outputs the calculation result representing the inputted number of characters at present, etc. Also, when the key data inputted by the means 1 shows ...

СПОСОБ ВЫЯВЛЕНИЯ НЕОБХОДИМОСТИ ОБУЧЕНИЯ ЭТАЛОНА ПРИ ВЕРИФИКАЦИИ РАСПОЗНАННОГО ТЕКСТА

Изобретение относится к области обработки изображений. Технический результат – повышение общей точности распознавания документов. Способ анализа текста включает: анализ выполняемой пользователем верификации распознанного текста, полученного в процессе распознавания изображения документа, где верификация включает в себя изменение определенного пользователем неправильного символа на определенный пользователем правильный символ; выявление однотипных изменений первого неправильного символа на первый правильный символ; и инициирование процесса обучения эталона распознавания на основе выявленных однотипных изменений, где эталон распознавания обучается для распознавания определенного символа и используется при распознавании символов в изображении документа для получения распознанного текста. 3 н. и 15 з.п. ф-лы, 6 ил.

СПОСОБ ПРЕДВАРИТЕЛЬНОГО ПРЕОБРАЗОВАНИЯ СТРУКТУРИРОВАННОГО МАССИВА ДАННЫХ, СОДЕРЖАЩЕГО ЛИНГВИСТИЧЕСКОЕ ПРЕДЛОЖЕНИЕ

Изобретение относится к области вычислительной техники для обработки массивов данных. Технический результат заключается в повышении точности предварительной обработки текста на естественном языке. Технический результат достигается за счет того, что способ преобразования структурированного массива данных (СМД) содержит этап формирования первой структуры данных, на котором формируют первую структуру данных СМД, содержащую элементы упомянутой первой структуры данных, причем упомянутые элементы первой структуры данных представляют собой текстовые элементы (ТЭ) лингвистического предложения, а также идентификационные данные ТЭ, представляющие собой для каждого ТЭ, по меньшей мере: значение ТЭ и порядковый номер ТЭ в лингвистическом предложении; и этап формирования второй структуры данных, на котором формируют вторую структуру данных СМД, содержащую элементы упомянутой второй структуры данных, причем упомянутые элементы второй структуры данных представляют собой синтаксические единицы (СЕ) лингвистического ...

СПОСОБ ПРЕОБРАЗОВАНИЯ СТРУКТУРИРОВАННОГО МАССИВА ДАННЫХ, СОДЕРЖАЩЕГО СИНТАКСИЧЕСКИЕ ЕДИНИЦЫ

Изобретение относится к области обработки структурированных массивов данных. Технический результат заключается в точности поиска в структурированном массиве данных. Технический результат достигается за счет формирования итоговой структуры данных структурированного массива данных (СМД), на котором формируют итоговую структуру данных СМД, содержащую элементы упомянутой итоговой структуры данных СМД, причем упомянутые элементы итоговой структуры данных СМД представляют собой основные лингво-логические объекты (ОЛЛО) лингвистического предложения, сформированные из групп лингво-логической единицы (ЛЛЕ) путем устранения однородностей в группах ЛЛЕ, также представляют собой идентификационные данные ОЛЛО, представляющие собой для каждого ОЛЛО по меньшей мере значение ОЛЛО и порядковый (порядковые) номер (номера) текстовых элементов (ТЭ) лингвистического предложения, составляющего (составляющих) ОЛЛО. 4 н. и 17 з.п. ф-лы, 45 ил.

TRANSFER OF GRAPHIC DATA

PROCEDURE AND DEVICE FOR COMPUTER-IMPLEMENTED PROCESSING OF ELECTRONIC ORDERS TO PAY

Universal translation

A likely source language of a media item can be identified by attempting an initial language identification of the media item based on intrinsic or extrinsic factors, such as words in the media item and languages known by the media item author. This initial identification can generate a list of most likely source languages with corresponding likelihood factors. Translations can then be performed presuming each of the most likely source languages. The translations can be performed for multiple output languages. Each resulting translation can receive a corresponding score based on a number of factors. The scores can be combined where they have a common source language. These combined scores can be used to weight the previously identified likelihood factors for the source languages of the meAdia item.

AUTOMATED ESSAY ANNOTATION SYSTEM AND METHOD

An automatic discourse analysis application (ADAA) (180) is used to automatically annotate an essay. The ADAA (180) includes a user interface (300), which receives and essays and forwards the essay to feature extractor (302) and receives the annotated essay from a discourse analysis modeler (318). The feature extractor (302) includes a position identifier (304), lexical item identifier (306), punctuation identifier (314), and a rhetorical relation identifier (316).

MOBILE WIRELESS COMMUNICATIONS DEVICE PROVIDING ENHANCED TEXT NAVIGATION INDICATORS AND RELATED METHODS

A mobile wireless communications device may include a portable, handheld housing, and a display and keypad carried by the housing. In particular, the keypad may include a plurality of symbol keys each having indicia of at least one respective symbol thereon, and an alternate function key. A user input device and a controller may also be carried by the portable, handheld housing. The controller may be connected to the display and the keypad, and it may generate a menu of possible desired words based upon actuation of the symbol keys, and generate a word cursor in the menu for scrolling through the possible desired words based upon the user input device. The controller may also change the word cursor to a symbol cursor based upon actuation of the alternate function key for scrolling through symbols in the possible desired words based upon the user input device.

METHODS AND SYSTEMS FOR GENERATING AND TRAVERSING DISCOURSE GRAPHS USING ARTIFICIAL NEURAL NETWORKS

A system for generating and performing inference over graphs of sentences standing in directed discourse relations to one another, comprising a computer process, and a computer readable medium having computer executable instructions for providing: tree-structured encoder networks that convert an input sentence or a query into a vector representation; tree-structured decoder networks that convert a vector representation into a predicted sentence standing in a specified discourse relation to the input sentence; couplings of encoder and decoder networks that permit an input sentence and a "query" sentence to constrain a decoder network to predict a novel sentence that satisfies a specific discourse relation and thereby implements an instance of graph traversal; couplings of encoder and decoder networks that implement traversal over graphs of multiple linguistic relations, including entailment, contradiction, explanation, elaboration, contrast, and parallelism, for the purposes of answering ...

METHODS AND APPARATUS FOR SELECTING SEMANTICALLY SIGNIFICANT IMAGES IN A DOCUMENT IMAGE WITHOUT DECODING IMAGE CONTENT

A method and apparatus for processing a document image, using a programmed general or special purpose computer, includes forming the image into image units, and at least one image unit classifier of at least one of the image units is determined, without decoding the content of the at least one of the image units. The classifier of the at least one of the image units is then compared with a classifier of another image unit. The classifier may be image unit length, width, location in the document, font, typeface, cross-section, the number of ascenders, the number of descenders, the average pixel density, the length of the top line contour, the length of the base contour, the location of image units with respect to neighboring image units, vertical position, horizontal inter-image unit spacing, and so forth. The classifier comparison can be a comparison with classifiers of image units of words in a reference table, or with classifiers of other image units in the document. Equivalent classes ...

An advertisement putting method and platform

The use of the complex system of physical embodiments on the location of the complex system is the component of the panoramic visualization

Network technique for malfunction countermeasure

Feature word extraction method and device

System and method for analyzing patient electronic receipt file

The invention relates to a system and method for analyzing a patient electronic receipt file. The method comprises the following steps: downloading the patient electronic receipt file from the website of the state intellectual property office of P.R. China according to a downloading instruction inputted from a client computer by a user; converting the patient electronic receipt file in a PDF (portable document format) into an image file in a TIF (tagged image file format) by utilizing a file conversion function; recognizing the image character information from the image file in the TIF by utilizing a character recognition function; carrying out fault-tolerant processing on the image character information; acquiring patient information from the fault-tolerant processed image character information by utilizing a regular expression; comparing the acquired patient information with the patient basic information of a database; and transmitting the comparison result to the client computer. By ...

Automatic generation of N-grams and concept relations from linguistic input data

NATURAL LANGUAGE PROCESSING FOR SOFTWARE COMMANDS

A system and method for facilitating user access to software functionality. An example method includes receiving natural language input; determining an identify of a user providing the input; employing the identity to facilitate selecting a software command to associate with the received natural language input; and employing software to act on the command. In a more specific embodiment, the method further includes determining an initial set of available software commands, and narrowing the initial set of available software commands based on the identity of a user and enterprise data associated with the identity of the user, resulting in a narrowed set of software commands in response thereto. Example enterprise data includes enterprise organizational chart information (e.g., corporate hierarchy information) and user access privilege information maintained by an ERP system. 1. A method for facilitating user access to software functionality , the method comprising:receiving natural language input;determining an identity of a user;processing the natural language input with reference to the identity to associate a software command with the received natural language input; andemploying software to act on the command.2. The method of claim 1 , wherein the software includes enterprise software.3. The method of claim 2 , further including determining an initial set of available software commands claim 2 , and narrowing the initial set of available software commands based on the identity of a user and enterprise data associated with the identity of the user claim 2 , resulting in a narrowed set of software commands in response thereto.4. The method of claim 3 , wherein the enterprise data includes enterprise organizational chart information.5. The method of claim 4 , wherein the enterprise data includes a measurement of a strength of a relationship between first object associated with a user and a second object.6. The method of claim 5 , further including determining when a ...

APPARATUS AND METHOD FOR RECOGNIZING EMOTION BASED ON EMOTIONAL SEGMENTS

An apparatus and method to recognize a user's emotion based on emotional segments are provided. An emotion recognition apparatus includes a sampling unit configured to extract sampling data from input data for emotion recognition. The emotion recognition apparatus further includes a data segment creator configured to segment the sampling data into a plurality of data segments. The emotion recognition apparatus further includes an emotional segment creator configured to create a plurality of emotional segments that include a plurality of emotions corresponding to each of the respective data segments. 1. An emotion recognition apparatus comprising:a sampling unit configured to extract sampling data from input data for emotion recognition;a data segment creator configured to segment the sampling data into a plurality of data segments; andan emotional segment creator configured to create a plurality of emotional segments that comprise a plurality of emotions corresponding to each of the respective data segments.2. The emotion recognition apparatus of claim 1 , wherein the data segment creator is further configured to segment the sampling data at regular intervals based on a predetermined time-domain window.3. The emotion recognition apparatus of claim 1 , wherein the data segment creator is further configured to segment the sampling data at different intervals based on two or more predetermined time-domain windows.4. The emotion recognition apparatus of claim 1 , wherein the data segment creator is further configured to reconfigure the sampling data based on a predetermined time-domain window such that a portion of the sampling data is shared by at least two of the data segments.5. The emotion recognition apparatus of claim 1 , further comprising an emotion deciding unit configured to decide at least one of a user's representative emotion claim 1 , a user's complex emotion claim 1 , and a user's changed emotion based on the emotional segments.6. The emotion recognition ...

System and method for parsing, summarizing and reporting log data

A system and method is disclosed which enables network administrators and the like to quickly analyze the data produced by log-producing devices such as network firewalls and routers. Unlike systems of the prior art, the system disclosed herein automatically parses and summarizes log data before inserting it into one or more databases. This greatly reduces the volume of data stored in the database and permits database queries to be run and reports generated while many types of attempted breaches of network security are still in progress. Database maintenance may also be accomplished automatically by the system to delete or archive old log data. 1. A data processing system comprising:one or more computers;a log-producing device connected to the one or more computers through a network; and, receiving, by a log receiver, a log message from the log-producing device;', 'determining, by the log receiver, a property of the log message;', 'copying, by the log receiver, the log message into a first storage buffer;', extracting data fields from the log message in the first storage buffer; and', 'converting the extracted data fields into one or more structured query language statements;, 'parsing, by a log parser, content of the first storage buffer, including, 'copying, by the log parser, the one or more structured query language statements into a second buffer;', 'reading, by a database inserter, the one or more structured query language statements in the second storage buffer;', 'inserting, by the database inserter, the one or more structured query language statements into one or more database tables; and', 'summarizing, by a message collection engine, the one or more structured query language statements in the one or more database tables into summarized statements for storing on the non-transitory storage device., 'a non-transitory storage device storing computer instructions operable to cause the one or more computers to perform operations comprising2. The data processing ...

Method and Apparatus For Retrieving and Combining Summarized Log Data In a Distributed Log Data Processing System

A system can receive raw log data from log-producing devices. The system can parse the raw log data to generate parsed log data, including extracting fields from the raw log data, generating structured query language (SQL) statements from the extracted fields, and inserting the SQL statements in a database. The system can summarize the parsed log data, including identifying one or more SQL statements based on fields of commonality and fields of uniqueness, and creating summarized data that include a new statement condensed from the identified SQL statements. The system can then generate a report based on the summarized data. 1. A method for processing log data , the method comprising:receiving raw log data in a log data analyzer; extracting fields from the raw log data based on a log data message type;', 'generating structured query language (SQL) statements from the extracted fields; and', 'inserting the SQL statements into a database table;, 'parsing the raw log data to generate parsed log data, including identifying, from the SQL statements inserted into the database table, a set of one or more SQL statements based on one or more fields of commonality and one or more fields of uniqueness; and', 'creating summarized data, the summarized data including a new statement condensed from the identified set of one or more SQL statements based on the one or more fields of commonality and one or more fields of uniqueness; and, 'summarizing the parsed log data, includinggenerating a report based on the summarized data, wherein the method is performed by one or more computers.2. The method of claim 1 , where the one or more fields of commonality include at least one of an identical source Internet protocol (IP) address claim 1 , an identical destination IP address claim 1 , or an identical destination port number.3. The method of claim 1 , where the one or more fields of uniqueness includes a source port number.4. The method as recited in claim 1 , where inserting the SQL ...

System and Method for Using Data and Angles to Automatically Generate a Narrative Story

A system and method for automatically generating a narrative story receives data and information pertaining to a domain event. The received data and information and/or one or more derived features are then used to identify a plurality of angles for the narrative story. The plurality of angles is then filtered, for example through use of parameters that specify a focus for the narrative story, length of the narrative story, etc. Points associated with the filtered plurality of angles are then assembled and the narrative story is rendered using the filtered plurality of angles and the assembled points. 1. A computer program product for automatically generating a narrative story , the narrative story comprising text arranged in a narrative format , the computer program product comprising:a plurality of instructions that are resident on a non-transitory computer-readable storage medium and executable by a processor to (1) receive domain related data and information, (2) determine an angle data structure, from among a plurality of angle data structures, that is applicable to the received domain related data and information based on a plurality of predetermined criteria, each of the plurality of angle data structures comprising a plurality of data representations that connect a plurality of events, circumstances, and/or entities as an abstract model of a thematic nature, and (3) automatically generate the text for the narrative story using the determined angle data structure and the received domain related data and information.2. The computer program product of claim 1 , wherein the domain related data and information is representative of at least one member of the group consisting of (1) an actual event claim 1 , (2) an actual circumstance claim 1 , and (3) an actual entity claim 1 , and wherein the instructions are further configured to automatically generate the text for the narrative story such that the generated text is descriptive of the at least one member as ...

HANDHELD ELECTRONIC DEVICE AND METHOD FOR PERFORMING OPTIMIZED SPELL CHECKING DURING TEXT ENTRY BY PROVIDING A SEQUENTIALLY ORDERED SPELL-CHECK ALGORITHMS

A handheld electronic device includes a reduced QWERTY keyboard and is enabled with a disambiguation routine that is operable to disambiguate text input. In addition to identifying and outputting representations of language objects that are stored in the memory and that correspond with a text input, the device is able to perform a spell check routine during input of a text entry. The spell check routine subjects a text entry to a sequentially ordered series of spell-check algorithms and ceases subjecting the text entry to further spell-check algorithms upon identification of a predetermined quantity of spell-check language objects. 149.-. (canceled)50. A method of enabling a spell-check operation on a handheld electronic device having stored for execution thereon a number of spell-check algorithms , the method comprising:on the handheld electronic device, subjecting a text entry to a spell-check algorithm to obtain a resultant expression, and generating a list including any language object determined to be inconsistent with the resultant expression;subjecting the text entry to a first spell-check algorithm related to misspelling when a quantity of language objects in the list has not reached a predetermined quantity; andsubsequent to said subjecting the text entry to the first spell-check algorithm related to misspelling, and when the quantity of language objects in the list has not reached the predetermined quantity, subjecting the text entry to a first spell-check algorithm related to a predetermined affixation rule.51. The method of claim 50 , further comprising subjecting the text entry to a first spell-check algorithm related to character configuration.52. The method of claim 51 , wherein the first spell-check algorithm related to character configuration comprises a first spell-check algorithm related to ignoring at least one of capitalization and accenting.53. The method of claim 50 , further comprising:ceasing said subjecting the text entry to the spell-check ...

ORTHOGRAPHICAL VARIANT DETECTION APPARATUS AND ORTHOGRAPHICAL VARIANT DETECTION PROGRAM

Provided is an orthographical variant detection apparatus which detects orthographical variant candidates with a high precision. The orthographical variant detection apparatus includes a term extraction unit that extracts terms from document data, a similarity computation unit that computes similarity of an arbitrary pair of the extracted terms, an orthographical variant candidate determination unit that determines, based on the similarity, whether or not the terms in the pair of terms are orthographical variant candidates, and a group classification unit that groups the orthographical variant candidates based on a character string commonly included in pair of terms as the orthographical variant candidates. 1. An orthographical variant detection apparatus comprising:a term extraction unit that extract terms from document data;a similarity computation unit that computes similarity of an arbitrary pair of the extracted terms;an orthographical variant candidate determination unit that determines, based on the similarity, whether or not the pair of terms are orthographical variant candidates; anda group classification unit that groups the orthographical variant candidates based on a character string commonly included in the pair of terms as the orthographical variant candidates.2. An orthographical variant detection apparatus comprising:a term extraction unit that extracts terms from document data;a similarity computation unit that performs operations including character type replacing on an arbitrary pair of the extracted terms, computes an edit distance based on the number of times of the operations, and computes similarity based on the edit distance; andan orthographical variant candidate determination unit that determines, based on the similarity, whether or not the pair of terms are orthographical variant candidates.3. The orthographical variant detection apparatus according to claim 1 , wherein the similarity computation unit obtains the edit distance by ...

Method and system for buying and renting real properties

In accordance with a computer-implemented approach and computer system, user conducts a search for real estate properties using natural language and has the ability to buy or rent real property online using unique functionalities not available in prior art. A “Natural Search” approach allows user to conduct an online search of real estate properties using natural language as opposed to standardized pre-determined search terms. Based on user's natural search, the system administrator generates a series of results using the “Interactive Results” approach, which enables the apparatus to analyze users' preferences to create a list of matching real estate properties and provide interactive features allowing user to act on generated results. According to “Live Offer” approach, the computer system generates an offer history and unique data for each property and allows user to act on the data by submitting an offer and, otherwise, completing the buying and renting process online. All three approaches may be used together or separately to streamline, simplify and improve the process of buying and renting real property.

Method and apparatus for rating documents and authors

Methods and apparatus for determining a competence rating of an author relating to one or more topics is disclosed. An exemplary method comprises determining semantic information associated with one or more documents related to the one or more topics, determining amplification information associated with the one or more documents, determining occurrence information associated with the author; and determining a competence rating for the author based at least in part on the semantic information associated with the one or more documents, the amplification information associated with the one or more documents, and the occurrence information associated with the author. A document rating for at least one of the one or more documents may also be determined based at least in part on the one or more weighted semantic features and the amplification information.

METHOD AND APPARATUS FOR GENERATING PHONEME RULE

A phoneme rule generating apparatus includes a spectrum analyzer configured to analyze pronunciation patterns of voices included in a plurality of voice data, a clusterer configured to cluster the plurality of voice data based on the analyzed pronunciation patterns, a voice group generator configured to generate voice groups from the clustered voice data, a phoneme rule generator configured to generate a phoneme rule corresponding to each respective voice group from among the generated voice groups and a group mapping DB configured to store the generated voice groups and the generated phoneme rules for an accurate voice recognition. 1. A phoneme rule generating apparatus comprising:a spectrum analyzer configured to analyze pronunciation patterns of a plurality of voice data;a clusterer configured to cluster the plurality of voice data based on the analyzed pronunciation patterns;a voice group generator configured to generate voice groups based on the clustered voice data;a phoneme rule generator configured to generate a phoneme rule corresponding to each respective voice group from among the generated voice groups.2. The apparatus of claim 1 , wherein the plurality of voice data comprises voices and information about respective user devices that transmitted the voices.3. The apparatus of claim 2 , wherein the plurality of voice data is clustered based on the information about the respective user devices.4. A phoneme rule generating method comprising:analyzing pronunciation patterns of a plurality of voice data;clustering the plurality of voice data based on the analyzed pronunciation patterns;generating voice groups based on the clustered voice data;generating a phoneme rule corresponding to each respective voice group from among the generated voice groups.5. The method of claim 4 , wherein the plurality of voice data comprises voices and information about respective user devices that transmitted the voices.6. The method of claim 5 , wherein the plurality of voice ...

System and Method of Spoken Language Understanding in Human Computer Dialogs

A system and method are disclosed that improve automatic speech recognition in a spoken dialog system. The method comprises partitioning speech recognizer output into self-contained clauses, identifying a dialog act in each of the self-contained clauses, qualifying dialog acts by identifying a current domain object and/or a current domain action, and determining whether further qualification is possible for the current domain object and/or current domain action. If further qualification is possible, then the method comprises identifying another domain action and/or another domain object associated with the current domain object and/or current domain action, reassigning the another domain action and/or another domain object as the current domain action and/or current domain object and then recursively qualifying the new current domain action and/or current object. This process continues until nothing is left to qualify. 1. A method comprising:partitioning, via a processor, a speech recognizer output into independent clauses;identifying, independent of domain, a dialog act for each of the independent clauses;identifying, dependent on domain, an object within each of the independent clauses; andrecursively generating, for each independent clause in the independent clauses, a semantic representation using the dialog act and the object of each independent clause.2. The method of claim 1 , wherein the semantic representation is used by a dialog manager in a spoken dialog system to determine a response to a user input.3. The method of claim 1 , further comprising:identifying, dependent on domain, an action within each of the independent clauses, wherein recursively generating the semantic representation further comprises using the action.4. The method of claim 1 , wherein while recursively generating the semantic representation claim 1 , additional objects are extracted from each of the independent clauses.5. The method of claim 1 , wherein identifying the object comprises ...

Methods for Creating A Phrase Thesaurus

The invention enables creation of grammar networks that can regulate, control, and define the content and scope of human-machine interaction in natural language voice user interfaces (NLVUI). More specifically, the invention concerns a phrase-based modeling of generic structures of verbal interaction and use of these models for the purpose of automating part of the design of such grammar networks. 169-. (canceled)70. A phrase analysis system comprising:a phrase database configured to store phrases; and obtain a corpus comprising a plurality of phrases;', 'extract phrases from the corpus;, 'a phrase analysis computer coupled with the phrase database and configured to 'cluster the phrases into classes within the phrase database based on based on the degree of similarity among the phrase.', 'determine a degree of similarity among the phrases based on phrase contexts associated with the phrases and on overlaps among phrase contexts determined by surrounding phrases in the corpus proximate to the phrases; and'}71. The system of claim 70 , wherein the corpus comprises a text corpus.72. The system of claim 70 , wherein the corpus comprises a speech corpus.73. The system of claim 70 , wherein the corpus comprises a conversational corpus.74. The system of claim 70 , wherein the corpus comprises a machine-readable corpus.75. The system of claim 70 , wherein the corpus comprises a specialized corpus that is specific to a domain.76. The system of claim 75 , wherein the domain comprises an interactive discourse.77. The system of claim 76 , wherein the interactive discourse comprises at least one of the following: a task oriented interactive discourse claim 76 , a verbal discourse claim 76 , a simulated discourse claim 76 , and a scripted discourse.78. The system of claim 70 , wherein the classes comprises equivalence classes.79. The system of claim 70 , wherein the classes comprises tags denoting abstract conceptual representations.80. The system of claim 79 , wherein the ...

Systems and Processes for Identifying Features and Determining Feature Associations in Groups of Documents

Systems and computer-implemented processes for identification of features and determination of feature associations in a group of documents can involve providing a plurality of keywords identified among the terms of at least some of the documents. A value measure can be calculated for each keyword. High-value keywords are defined as those keywords having value measures that exceed a threshold. For each high-value keyword, term-document associations (TDA) are accessed. The TDA characterize measures of association between each term and at least some documents in the group. A processor quantifies similarities between unique pairs of high-value keywords based on the TDA for each respective high-value keyword and generates a similarity matrix that indicates one or more sets that each comprise highly associated high-value keywords. 1. A computer-implemented process for identifying features and determining feature associations within a group of documents that comprise terms in unstructured text , which is maintained in a storage device and/or received through communications hardware , the process comprising:Providing a plurality of keywords identified among the terms of at least some of the documents;Calculating a value measure for each keyword, wherein the value measure of a particular keyword is a function of the number of documents, within the group, in which the particular keyword occurs and of the number of documents for which it is a keyword;Defining high-value keywords as those keywords having value measures that exceed a threshold;Accessing term-document associations (TDA) for each high-value keyword, wherein the TDA are stored in a storage device and characterize measures of association between each term and at least some documents in the group;Quantifying by a processor similarities between unique pairs of high-value keywords based on the TDA for each respective high-value keyword; andGenerating a similarity matrix that indicates one or more sets each comprising ...

METHOD AND APPARATUS FOR CONSENT DOCUMENT MANAGEMENT

An approach is provided for consent document management. The consent platform causes, at least in part, a creation of one or more consent document objects representing one or more consent documents, metadata associated with the consent documents, or a combination thereof. Next, the consent platform processes and/or facilitates a processing of one or more responses to the one or more consent documents to cause, at least in part, a creation of one or more user response objects, wherein the one or more user response objects record the one or more responses on a per user basis. 1. A method comprising facilitating a processing of and/or processing (1) data and/or (2) information and/or (3) at least one signal , the (1) data and/or (2) information and/or (3) at least one signal based , at least in part , on the following:a creation of one or more consent document objects representing one or more consent documents, metadata associated with the one or more consent documents, or a combination thereof; anda processing of one or more responses to the one or more consent documents to cause, at least in part, a creation of one or more user response objects,wherein the one or more user response objects record the one or more responses on a per user basis.2. A method of claim 1 , wherein the (1) data and/or (2) information and/or (3) at least one signal are further based claim 1 , at least in part claim 1 , on the following:at least one determination of one or user interface capabilities of one or more applications, one or more devices, or a combination thereof; anda presentation of the one or more consent document objects, the one or more user response objects, or a combination thereof based, at least in part, on the one or more user interface capabilities.3. A method of claim 1 , wherein the (1) data and/or (2) information and/or (3) at least one signal are further based claim 1 , at least in part claim 1 , on the following:at least one determination to query the one or more ...

SYSTEM AND METHOD FOR ENHANCED LOOKUP IN AN ONLINE DICTIONARY

A system and method predictively generates words based on a user input, according to a frequency of lookup of each of the generated words. The system and method also allows for a user to add predictively generated words to a word list that assists in the facilitation of word and vocabulary comprehension for a user. Words in the online dictionary are grouped in word families where a user can navigate between different forms of a root word. 113-. (canceled)14. A computer-implemented method for outputting a hierarchically structured word family , the method comprising:assigning, by a computer processor, a selected word as a main word represented by a portion of a bar of a first hierarchical level; assigning, by the computer processor, a word that is an immediate parent of the main word of the respective hierarchical level as a main word represented by a portion of a bar of an immediately lower hierarchical level; and', 'assigning, by the computer processor, to remaining portions of the bar of the immediately lower hierarchical level, children of the word that is the immediate parent; and, 'for each hierarchical level, beginning with the first hierarchical level until a root word is assigned to a respective bardisplaying, by the computer processor, the bars according to the assignments.15. The method of claim 14 , wherein claim 14 , for each of the bars to which more than one word is assigned claim 14 , sizes of the respective portions of the bar to which the more than one word is assigned are based on a differences in respective frequencies of occurrence of respective ones of the more than one word in a corpus of text.16. The method of claim 14 , wherein the corpus of text includes text received from at least one online source.17. The method of claim 14 , wherein the portions of the bars are selectable for changing which word is the selected word.18. The method of claim 17 , further comprising claim 17 , responsive to a selection of the selected word:if a definition is ...

Format for displaying text analytics results

A system can receive text. The text can be divided into various portions. One or more significance indicators can be associated with each portion of text: these significance indicators can also be received by the system. The system can then display a portion of text and the associated significance indicators to the user.

PHRASE BASED DOCUMENT CLUSTERING WITH AUTOMATIC PHRASE EXTRACTION

Meaningful phrases are distinguished from chance word sequences statistically, by analyzing a large number of documents and using a statistical metric such as a mutual information metric to distinguish meaningful phrases from groups of words that co-occur by chance. In some embodiments, multiple lists of candidate phrases are maintained to optimize the storage requirement of the phrase-identification algorithm. After phrase identification, a combination of words and meaningful phrases can be used to construct clusters of documents. 1. A method of extracting phrases from a corpus of documents , the method comprising:generating, by at least one processor, a set of candidate phrases from the documents in the corpus, wherein each candidate phrase corresponds to a group of two or more words that occur consecutively in at least one of the documents in the corpus, each candidate phrase having an occurrence count associated therewith;computing, by the at least one processor, a statistical metric for each candidate phrase based at least in part on the occurrence count, wherein the statistical metric indicates a likelihood of the words within the candidate phrase occurring consecutively by chance;selecting, by the at least one processor, a plurality of the candidate phrases as meaningful phrases, the selection being based on the statistical metric;computing, by the at least one processor, a phrase weight for each meaningful phrase, the phrase weight being based on a number of documents in the corpus that contain the meaningful phrase; andforming, by the at least one processor, clusters of the documents using the phrase weights.2. The method of claim 1 , wherein the statistical metric is a mutual information metric.3. The method of claim 1 , wherein generating the set of candidate phrases includes:extracting a group of consecutive words from one of the documents in the corpus;determining whether the group of consecutive words appears as one of the candidate phrases in a first ...

SYSTEMS AND METHODS FOR AN AUTOMATED PERSONALIZED DICTIONARY GENERATOR FOR PORTABLE DEVICES

A system and method for automated dictionary population is provided to facilitate the entry of textual material in dictionaries for enhancing word prediction. The automated dictionary population system is useful in association with a mobile device including at least one dictionary which includes entries. The device receives a communication which is parsed and textual data extracted. The text is compared to the entries of the dictionaries to identify new words. Statistical information for the parsed words, including word usage frequency, recency, or likelihood of use, is generated. Profanities may be processed by identifying profanities, modifying the profanities, and asking the user to provide feedback. Phrases are identified by phrase markers. Lastly, the new words are stored in a supplementary word list as single words or by linking the words of the identified phrases to preserve any phrase relationships. Likewise, the statistical information may be stored. 1. A computer implemented method for automated dictionary population , useful in association with a personal appliance including at least one dictionary , which includes entries , the method for automated dictionary population comprising:retrieving a message containing words, wherein the message is received by the personal appliance;parsing the words of the message;identifying phrases from the parsed words by identifying phrase markers, wherein the phrase markers include at least one of italicized word groups, quoted word groups, bolded word groups, capitalized word groups, and word groups containing more than one new word;linking the words of the identified phrases and storing the linking of the words of the identified phrases with additional information that allows them to remain linked without storing the entire identified phrases.2. The method of automated dictionary population claim 1 , as recited in claim 1 , further comprising processing profanities claim 1 , wherein the processing profanities comprises: ...

Method and system for formation of electronic documents

A method and system for creation of customized documents over a network as well as for negotiation of contents for documents over a network (e.g., Internet) are disclosed. In one aspect, professional documents can be created in an automated manner. In another aspect, negotiation of documents (or their contents) can be performed in an automated manner. In either case, the customization and/or negotiation is efficient, cost-effective and useful.

INFORMATION PROCESSING DEVICE AND INFORMATION PROCESSING METHOD

An information processing device comprises a word string acquirer which acquires a word string that is a target of analysis; a partial string extractor which extracts, using two words on either side of each space in the word string, a partial string containing one word but not the other, a partial string not containing the one word but containing the other, and a partial string containing both words from the word string; a division coefficient acquirer which acquires, for each partial string, division coefficients indicating degree of reliability in dividing the partial string by respective division patterns that divide the partial string into words; a probability coefficient acquirer which calculates a coefficient indicating probability that the word string is divided at the space based on the division coefficients; and an ouputter which determines division of the word string based on the coefficient, and divides and outputs the word string. 1. An information processing device , comprising:a word string acquirer which acquires a word string that is a target of analysis;a partial string extractor which extracts, using two words on either side of each space in the word string acquired by the word string acquirer, a partial string containing one word but not the other, a partial string not containing the one word but containing the other, and a partial string containing both words from the acquired word string;a division coefficient acquirer which acquires, for each partial string extracted by the partial string extractor, division coefficients indicating degree of reliability in dividing the partial string by respective division patterns that divide the partial string into words;a probability coefficient acquirer which calculates a coefficient indicating probability that the word string is divided at the space, based on the division coefficients acquired by the division coefficient acquirer; andan ouputter which determines division of the word string that is the ...

METHOD FOR LABELING SEMANTIC ROLE OF BILINGUAL PARALLEL SENTENCE PAIR

Methods for Semantic Role Labeling (SRL) of bilingual sentence pairs. Steps in this invention include tokenizing and part-of-speech tagging a bilingual sentence pair, performing word alignments on the bilingual sentence pair, finding word-aligned predicate pairs in the bilingual sentence pair, generating argument candidates for each predicate using monolingual SRL system, and performing joint inference to obtain the SRL results and argument alignment for each predicate pair. This method produces more accurate SRL results on both sides of bilingual sentence pairs. Furthermore, this method also aligns the predicate-argument structures between the sentence pairs. 1. A method of bilingual Semantic Role Labeling (SRL) , the method comprising:Step 1: Tokenizing bilingual sentence pair and finding word-aligned predicate pairs in a bilingual sentence pair;Step 2: For each predicate, using monolingual SRL method to generate argument candidates;Step 3: For each predicate, merging its duplicate argument candidates into one; andStep 4: For each word-aligned predicate pair, performing joint inference to obtain their arguments and the alignment between these arguments.2. The method of claim 1 , wherein the step 1 further comprises tokenizing each sentence in bilingual sentence pair and performing part-of-speech tagging and word-alignment for the bilingual sentence pair.3. The method of claim 1 , wherein the step 1 further comprises finding the verb pairs that align to each other claim 1 , wherein the word-aligned word pairs are examined one by one and all word-aligned verb pairs are identified.4. The method of claim 1 , wherein the step 2 further comprises:Step 2.1: For each sentence, using multiple parsing models to produce several parse trees; andStep 2.2: For each predicate, performing monolingual SRL multiple times to obtain several argument candidates, each time using one parse tree generated in Step 2.1.5. The method of claim 4 , wherein in Step 2.1 claim 4 , multiple ...

REQUEST ACQUISITION SUPPORT SYSTEM IN SYSTEM DEVELOPMENT, REQUEST ACQUISITION SUPPORT METHOD AND RECORDING MEDIUM

A request pick-up assisting system includes: a question information registering unit registering a question item and attributes of a questionee; a basic connection word candidate extracting unit referring to information that includes words of the question, and extracting words that coexist with the words of the question; an attribute connection word candidate extracting unit referring to information including words of the question, and information that includes words constituting attributes of the questionee, and extracting, for each attribute, words in which the words of the question and the attributes coexist; an attribute specificity calculating unit calculating an attribute specificity based on dissimilarity between groups of words; an effective attribute extracting unit comparing attribute specificity for each attribute, and extracting a suitable attribute; a connection word extracting unit extracting a connection word about the effective attribute; and an association chart creating unit generating an association chart, by referencing the extracted connection word. 1. A request pick-up assisting system , comprising:a question information registering unit for registering a question item and attributes of a questionee as question information;a basic connection word candidate extracting unit for referring to information that includes words constituting the question item and that is obtained from a database that collects and accumulates arbitrary text information, and to extract as basic connection word candidates a group of words that coexist with the words of the question item;an attribute connection word candidate extracting unit for referring to information that includes words constituting the question item and that is obtained from the database, and information that includes words constituting the attributes of the questionee and that is obtained from the database, and to extract for each attribute, as attribute connection word candidates a group of words in ...

ATTRIBUTION USING SEMANTIC ANALYISIS

A method, system, and computer program product for semantic attribution of a request. Source data statements for the request are received. A selection of a domain for the received source data statements is received. The received source data statements are semantically analyzed, which includes matching elements in the received source data statements to respective one or more entries in an ontology associated with the selected domain. The ontology includes items and relationships that define the selected domain. Each element in the received source data statements is a word or a phrase. The one or more entries are assigned to the matched elements, respectively, to annotate each matched element with a respective annotation consisting of the respective one or more entries. The annotated elements are saved with the respective annotations. 1. A method for semantic attribution of a request , said method implemented by a processor of a computer system , said method comprising:said processor receiving source data statements for the request;said processor receiving a selection of a domain for the received source data statements;said processor semantically analyzing the received source data statements, said semantically analyzing comprising matching elements in the received source data statements to respective one or more entries in an ontology associated with the selected domain, wherein the ontology comprises items and relationships that define the selected domain, and wherein each element in the received source data statements is a word or a phrase;said processor assigning the one or more entries to the matched elements, respectively, to annotate each matched element with a respective annotation consisting of the respective one or more entries; andsaid processor saving the annotated elements with the respective annotations.2. The method of claim 1 , wherein the method further comprises:said processor using the annotations to generate a search query for the request.3. The ...

Multi-Concept Latent Semantic Analysis Queries

A method includes accessing text, identifying a plurality of terms from the text, determining a plurality of term vectors associated with the identified plurality of terms, and clustering the determined plurality of term vectors into a plurality of clusters, the plurality of clusters comprising a first and a second cluster, the first and second clusters each comprising two or more of the determined term vectors. The method further includes creating a first pseudo-document according to the first cluster, creating a second pseudo-document according to the second cluster, identifying a first set of terms associated with the first cluster using latent semantic analysis (LSA) of the first pseudo-document, identifying a second set of terms associated with the second cluster using LSA of the second pseudo-document, and combining the first and second sets of terms into a list of output terms.

APPARATUS AND METHOD FOR PROVIDING INTERNET DOCUMENTS BASED ON SUBJECT OF INTEREST TO USER

The present invention provides an apparatus for providing Internet documents based on a subject of interest to a user, including an subject reception unit configured to receive information on a subject from a user terminal; a relevant document collection unit configured to collect relevant documents related to the information on the subject of interest using search engines; a similar sentence classification unit configured to extract a core sentence from the relevant documents, calculate similarity of sentences peripheral to the core sentence, and classify sentences similar to the core sentence into similar sentence sets based on the calculated similarity; and a similar sentence providing unit configured to provide the core sentence and the similar sentence sets to the user terminal. 1. An apparatus for providing Internet documents based on a subject of interest to a user , the apparatus comprising:a subject reception unit configured to receive information on a subject of interest from a user terminal;a relevant document collection unit configured to collect relevant documents related to the information on the subject using search engines;a similar sentence classification unit configured to extract a core sentence from the relevant documents, calculate similarity of sentences peripheral to the core sentence, and classify sentences similar to the core sentence into similar sentence sets based on the calculated similarity; anda similar sentence providing unit configured to provide the core sentence and the similar sentence sets to the user terminal.2. The apparatus of claim 1 , wherein the information on the subject of interest is information corresponding to a search word claim 1 , a query word claim 1 , or a keyword related to the subject of interest.3. The apparatus of claim 1 , wherein the relevant document collection unit collects the relevant documents by using a meta-search method using an open API provided by the search engines.4. The apparatus of claim 1 , ...

SYSTEM AND METHOD FOR DISCOVERING STORY TRENDS IN REAL TIME FROM USER GENERATED CONTENT

A method for identifying story trends includes identifying a set of words in a fixed size data stream based on a subword cache, and electronically determining at least one story trend associated with the set of words and electronically generating a story hash associated with the set of words. The method also includes storing the story hash in a story trend cache and updating the story trend cache according to the story hash, and retrieving one or more popular story topics according to the story trend cache. Machine readable media including program code that causes execution of a method for generating search results also are described. 1. A computer-implemented method for identifying story trends , the method comprising:identifying a set of words in a fixed size data stream based on a subword cache;electronically determining at least one story trend associated with the set of words and electronically generating a story hash associated with the set of words;storing the story hash in a story trend cache and updating the story trend cache according to the story hash; andretrieving one or more popular story topics according to the story trend cache for presentation to a user.2. The method of claim 1 , wherein the data stream is a user-generated data stream.3. The method of claim 1 , wherein generating a story hash associated with the set of words comprises generating a SimHash based on the set of words.4. The method of claim 1 , further comprising:receiving a request for stories from a user;using the story hash to calculate a hamming distance between the story hash and another story hash; andproviding a story to the user based on a merger of the story hashes, if the hamming distance indicates that the story hashes are proximate.5. The method of claim 4 , wherein the merger occurs at run time.6. Non-transitory machine readable media comprising program code that when executed by a programmable processor causes execution of a method for generating search results claim 4 , ...

INTELLIGENT EMOTION-INFERRING APPARATUS, AND INFERRING METHOD THEREFOR

The present disclosure provides an intelligent emotion-inferring apparatus and inferring method therefor. The intelligent emotion-inferring apparatus includes: an emotional-word-storing unit, which classifies emotional words into items including at least one among similarity, positivity or negativity, and emotional intensity, using classes of emotion comprising a basic emotion group which classifies human emotions and a detailed emotion group which classifies the basic emotion group, and stores the words in an emotional-word dictionary; a sentence-converting unit which ascertains the words and phrases of sentence logged by a user and converts the words and phrases into a basic format; a match-checking unit which checks the converted words and phrases for words and phrases matching those in the emotional-word dictionary; and an emotion-inferring unit, which applies a probabilistic model on the basis of co-occurrence of the converted words and phrases, and infers emotions on the basis of the probabilistic model. 1. An intelligent emotion-inferring apparatus , comprising:an emotional-word-storing unit configured to classify emotional words into items including at least one among similarity, positivity or negativity, and emotional intensity, using classes of emotion comprising a basic emotion group which classifies human motions and a detailed emotion group which classifies the basic emotion group, and to store the words in an emotional-word dictionary;a sentence-converting unit configured to ascertain words and phrases of a sentence logged by a user and convert the words and phrases into a basic format;a match-checking unit configured to check words or phrases among the converted words and phrases, which match with the emotional-word dictionary; andan emotion-inferring unit configured to apply a probabilistic model on the basis of co-occurrence of the converted words and phrases, and to infer emotions on the basis of the applied probabilistic model.2. The intelligent ...

SYSTEM AND METHOD FOR SEARCHING FUNCTIONS HAVING SYMBOLS

A system and method for searching through functions and expressions with symbols. Moreover, the system can be used to recognize and further analyze the notations of this nature and use this in order to translate, transform into audio, or solve the mathematical problems. According to at least some embodiments, the functions comprise mathematic equations which are defined by symbols and mathematic notation. The system and method enable a user to enter a mathematical equation in a WYSIWYG environment to a search engine, and to find similar or identical equations, first and foremost according to theoretical similarity, and secondly, according to visual similarity. The engine does this be understanding the meaning behind the visual symbols of the equation using a Dynamic Hidden Markov Model (hereon DHMM). The system enables the user to insert the equation with no prior knowledge of LaTeX, or any computing language, and with no need to follow a predefined generic protocol in order to insert the query. 150-. (canceled)51. A method for analyzing a function comprising a plurality of symbols , wherein the function comprises a scientific equation , said equation comprising at least one operator and at least one variable , the method being performed by a computer , the method comprising:providing the function in a visual format to the computer;decomposing the function into the plurality of symbols by the computer;labeling each symbol with a label by determining each character of the function;determining a plurality of possible labels for each character or combinations of characters;selecting a symbol label for each symbol according to said probabilistic model, wherein each symbol comprises a character or a plurality of characters;forming said one or more semantic connections according to each symbol label;determining a degree of probability for said one or more semantic connections and said symbol labels according to a probabilistic dynamic mathematical model by said computer, ...

INTELLIGENT EMOTIONAL WORD EXPANDING APPARATUS AND EXPANDING METHOD THEREFOR

The present disclosure provides an intelligent emotional word expanding apparatus and an expanding method therefor. The intelligent emotional word expanding apparatus includes word dictionary storing module, emotion inferring module and word expanding module. The word dictionary storing module classifies emotional words into similarity, positivity or negativity, and emotional intensity using emotion classes including a basic emotion group classifying human emotions and a detailed emotion group classifying the basic emotion group, storing the classified emotional words in emotional word dictionary, and storing neutral words together with the number of calls thereof in neutral word dictionary. Emotion inferring module captures words and phrases of a sentence logged by a user, converting the words and phrases into basic formats, and inferring emotions. Word expanding module determines whether a word or a phrase is neutral on the basis of the neutral word dictionary when emotions are not inferred by the emotion inferring module. 1. An intelligent emotional word expanding apparatus , comprising:a word dictionary storing module configured to classify emotional words into items including at least one of similarity, positivity or negativity, and emotional intensity using emotion classes including a basic emotion group which classifies human emotions and a detailed emotion group which classifies the basic emotion group, to store the classified emotional words in an emotional word dictionary, and to store neutral words together with the number of calls thereof in a neutral word dictionary;an emotion inferring module configured to capture words and phrases of a sentence logged by a user, to convert the words and phrases into basic formats, and to infer emotions on the basis of the converted words or phrases and the emotional word dictionary; anda word expanding module configured to determine whether a word or a phrase is neutral on the basis of the neutral word dictionary when ...

Method, apparatus and system for finding synonyms

A method and system are provided for finding synonyms which are more contextually relevant to the intended use of a particular word. The system finds a list of synonyms for the input word and also finds a list of synonyms for an additional word entered by the user to approximate the intended usage of the input word. These two lists of synonyms are compared to find words common to both lists, and the common words are presented to the user as potential synonyms which are appropriate for the intended use.

DIALOG TEXT ANALYSIS DEVICE, METHOD AND PROGRAM

A dialog text analysis device generates data for text processing from a dialog text. A negative judging means decides whether or not an event of a first utterance in a dialog text which is a text including content of a plurality of utterances is negated by a second utterance which exists subsequent to the first utterance. When the event of the first utterance is negated by the second utterance, the data for text processing generation means generates data for text processing which is data in which the negated event of the first utterance is eliminated from the dialog text. 1. A dialog text analysis device comprising:a negative judging unit which judges whether or not an event of a first utterance in a dialog text which is a text including content of a plurality of utterances is negated by a second utterance which exists subsequent to the first utterance; anda data for text processing generation unit which, when the event of the first utterance is negated by the second utterance, generates data for text processing which is data in which the negated event of the first utterance is eliminated from the dialog text.2. The dialog text analysis device according to claim 1 , further comprising an inquiry/response pair identifying unit which identifies from each utterance in an inputted dialog text an inquiry/response pair which is a pair of the first utterance which indicates content to ask to a speaker and a second utterance which exists subsequent to the first utterance and is a response to the first utterance claim 1 ,wherein the negative judging unit judges whether or not the event of the first utterance in the inquiry/response pair is negated by the second utterance.3. The dialog text analysis device according to claim 1 , wherein claim 1 , when content of the event of the first utterance negated by the second utterance indicates an affirmative fact claim 1 , the data for text processing generation unit changes the event which indicates the affirmative fact to an event ...

System and method for using information from intuitive multimodal interactions for media tagging

System and method for using information extracted from intuitive multimodal interactions in the context of media for media tagging are disclosed. In one embodiment, multimodal information related to media is captured during multimodal interactions of a plurality of users. The multimodal information includes speech information and gesture information. Further, the multimodal information is analyzed to identify speech portions of interest. Furthermore, relevant tags for tagging the media are extracted from the speech portions of interest. 1. A method of using multimodal information for media tagging comprising:capturing multimodal information, related to media, during multimodal interactions of a plurality of users, wherein the multimodal information comprises speech information and gesture information;analyzing the multimodal information to identify speech portions of interest; andextracting relevant tags, from the speech portions of interest, for tagging the media.2. The method of claim 1 , wherein analyzing the multimodal information to identify the speech portions of interest comprises:analyzing the multimodal information to identify co-occurrence of the gesture information and the speech information; andidentifying the speech portions of interest based on the identified co-occurrence of the gesture information and the speech information.3. The method of claim 1 , wherein extracting the relevant tags for tagging the media comprises: if so, converting the speech portions of interest to text in a natural language understanding format; and', 'if so, extracting the relevant tags from the text in the natural language understanding format based on nouns, verbs, subject and object.', 'determining whether the relevant tags can be extracted from the text in the natural language understanding format;'}], 'determining whether the speech portions of interest can be recognized using a speech recognition software;'}4. The method of claim 3 , wherein if the relevant tags cannot ...

METHOD AND SYSTEM FOR TEXT UNDERSTANDING IN AN ONTOLOGY DRIVEN PLATFORM

Embodiments of methods and systems for informatics systems are disclosed. Such informatics systems may utilize a unifying format to represent text to facilitate linking between data from the text and one or more ontologies, and the commensurate ability to mine such data. 1. A system , comprising:an informatics system coupled to one or more data sources, the informatics system comprising a processor and a non-transitory computer readable medium comprising instructions for:receiving a clinical text as input from a data source;creating a parse graph of the input, wherein creating the parse graph comprises parsing the input to create the parse graph by segmenting the input into a set of evidence spaces based on one or more identifiers within the input;obtaining a graph representation of a domain ontology, wherein the domain ontology comprises a set of concepts and a set of relationships; andmapping the parse graph to the graph representation of the domain ontology to create a unified graph comprising the graph representation of the input and the graph of the domain ontology.2. The system of claim 1 , wherein the input is parsed based on a graph representation of a syntax ontology and the syntax ontology comprises the one or more identifiers.3. The system of claim 1 , wherein the instructions are further for chunking each of the set of evidence spaces into one or more chunks claim 1 , each chunk comprising a permutation of tokens of the evidence space within a distance of one another in the evidence space.4. The system of claim 3 , wherein the distance is five plus or minus two.5. The system of claim 3 , wherein creating the parse graph further comprises ordering the set of evidence spaces.6. The system of claim 5 , wherein mapping the parse graph to the graph representation of the domain ontology comprises matching a set of concepts represented by the parse graph to one or more of the set of concepts of the domain ontology.7. The system of claim 1 , wherein the ...

SYSTEM AND METHOD FOR INPUTTING TEXT INTO ELECTRONIC DEVICES

A text prediction engine, a system comprising a text prediction engine, and a method for generating sequence predictions. The text prediction engine, system and method generate a final set of sequence predictions, each with an associated probability value. 136-. (canceled)37. A text prediction engine comprising:at least one model configured to generate from an evidence source a first set of sequences with associated probability estimates;a probability generator configured to receive the set of first sequences with associated probability estimates and to generate a set of sequence predictions with associated probability values,wherein the probability values are approximately normalised over all possible sequence predictions generated by the probability generator given all of the possible sequences received by the probability generator.38. The text prediction engine according to claim 37 , further comprising a prior model configured to generate a second set of sequences with associated probability estimates.39. The text prediction engine according to claim 38 , wherein:the at least one model comprises a context model and an input model, each of which is configured to receive text input by a user and to generate a set of sequences and associated probability estimates; andthe prior model comprises a target prior model configured to generate a set of sequences and associated probability estimates.40. The text prediction engine according to claim 39 , wherein:the input model comprises a candidate model and a language model;the context model comprises a candidate model and a prefix match model; and the target prior model comprises a character model and a unigram model.41. The text prediction engine according to claim 37 , wherein the at least one model is configured to generate a first set of sequences based on the evidence source and an uncertainty in the evidence source.42. The text prediction engine according to claim 37 , wherein the probability generator is configured ...

KNOWLEDGE STORAGE AND RETRIEVAL SYSTEM AND METHOD

A system and method for representing, storing and retrieving real-world knowledge on a computer or network of computers is disclosed. Knowledge is broken down into permanent atomic “facts” which can be stored in a standard relational database and processed very efficiently. It also provides for the efficient querying of a knowledge base, efficient inference of new knowledge and translation into and out of natural language. Queries can also be processed with full natural language explanations of where the answers came from. The method can also be used in a distributed fashion enabling the system to be a large network of computers and the technology can be integrated into a web browser adding to the browser's functionality. 1. A computer-implemented method , comprising:receiving text, wherein the text was entered as input in a field in a web browser configured to receive uniform resource locators (URLs) as input;determining that the text comprises a natural language question;generating a query for use with a knowledge base using the text;generating a result by processing the query with reference to the knowledge base; andgenerating a natural language answer to the natural language question for presentation in the web browser, the natural language answer corresponding to the result.2. The method of claim 1 , further comprising identifying an object associated with the result claim 1 , and generating profile information describing the object for presentation in the web browser.3. The method of claim 1 , further comprising generating an explanation representing how the result was generated claim 1 , the explanation including a natural language translation of the query and one or more processing steps of the query.4. The method of claim 1 , wherein the text corresponds to a plurality of possible results claim 1 , the method further comprising generating a request for further information for presentation in the web browser.5. The method of claim 1 , wherein the text ...

PROCESSING STRUCTURED DATA

The present invention provides a fast and efficient way of processing structured data by utilizing an intermediate file to store the structural information. The structured data may be processed into a Binary mask Format (BMF) file which may serve as a starting point for post-processing. A tree structure built on top of the BMF file may be constructed very quickly, and also takes up less space than a DOM tree. Additionally, BMF records may reside entirely in the memory and contain structural information, allowing SAX-like sequential data access. 120.-. (canceled)21. A method for efficiently processing a structured data file , the method comprising:receiving the structured data file;creating an intermediate file, wherein the intermediate file is a binary file having a plurality of cells organized into groupings, wherein each of the groupings of cells constitutes a record; creating a first record in an intermediate file for an element in the structured data file, wherein the first record further contains one or more descriptors including an offset value identifying a location, within the structured data file, of the element;', 'creating a second record in the intermediate file for an attribute name in the structured data file, wherein the second record further contains one or more descriptors including an offset value identifying a location, within the structured data file, of the attribute name; and', 'creating a third record in the intermediate file for an attribute value in the structured data file, wherein the third record further contains one or more descriptors including an offset value identifying a location, within the structured data file, of the attribute value; and, 'parsing the structured data file bytransmitting the intermediate file and the structured data file to a component so that the component accesses data from the structured data file using both the intermediate file and the structured data file together.22. The method of claim 21 , wherein the ...

Computer-Implemented Method, Program, and System for Identifying Non-Self-Descriptive Terms in Electronic Documents

A computer-implemented method, program, and system for identifying non-self-descriptive terms in electronic documents. The computer-implemented method for identifying a non-self-descriptive term in an electronic document, includes a memory and a processor communicatively coupled to the memory and configured to execute the steps of a method. The method includes acquiring a noun included in the corpus data. The method further includes calculating a qualifying level and a qualified level in the corpus data related to each known in the corpus data. The method further includes identifying one or more nouns included in the corpus data as having a qualifying level and/or qualified level satisfying a predetermined condition. The method further includes presenting a term related to one or more of the nouns in the electronic document as a candidate for the non-self-descriptive term in the electronic document. 1. A computer-implemented method for identifying a non-self-descriptive term in an electronic document , including a memory and a processor communicatively coupled to the memory , wherein the processor is configured to execute the steps of a method comprising:acquiring a noun included in corpus data;calculating a qualifying level and qualified level in the corpus data related to each noun included in the corpus data;identifying one or more nouns included in the corpus data having a qualifying level and/or qualified level satisfying a predetermined condition; andpresenting a term related to one or more of the nouns in the electronic document as a candidate for the non-self-descriptive term in the electronic document.2. The method of further comprising a step for analyzing the qualification relationships of each noun included in the corpus data.3. The method of claim 2 , wherein the analyzing step includes a step for identifying words qualifying and words qualified by each noun included in the corpus data.4. The method of further comprising:breaking down compound nouns ...

NAMED ENTITY EXTRACTION FROM A BLOCK OF TEXT

A data processing method, program, and apparatus for identifying a document within a block of text. A block of text is tokenized into a plurality of text tokens according to at least one rule parser. Each of the plurality of text tokens is sequentially compared to a plurality of document tokens to determine if the text token matches one of the plurality of document tokens. The plurality of document tokens correspond to a plurality of documents which have been tokenized according to the one or more rule parsers. Each matched text token is filtered according to predetermined filtering criteria to generate one or more candidate text tokens. It is then determined whether sequence of candidate text tokens that occur in sequential order within the block of text match sequence of document tokens. If so, then it is determined that the document has been identified within the block of text. The document can correspond to an artist, a song names, and misspellings and aliases thereof. 1. A data processing method of identifying a document within a block of text , comprising:tokenizing a block of text into a plurality of text tokens according to at least one rule parser;comparing each of the plurality of text tokens to a plurality of document tokens sequentially and determining if the text token matches one of the plurality of document tokens, wherein the plurality of document tokens correspond to a plurality of documents which have been tokenized according to the at least one rule parser;filtering each matched text token according to predetermined filtering criteria to generate one or more candidate text tokens; andmatching a sequence of candidate text tokens from the one or more candidate text tokens to a sequence of document tokens, wherein the sequence of candidate text tokens occurs in sequential order within the block of text.2. A data processing method according to claim 1 , wherein the predetermined filtering criteria includes a plurality of stop words and a plurality of ...

Handheld electronic device including indication of a selected data source, and associated method

A method of enabling input into a handheld electronic device having stored therein a number of language objects includes detecting a selection of a languages, making a determination that the language is a default language or a non-default language, detecting as an ambiguous input an actuation of one or more input members, outputting at least a portion of a number of the language objects that corresponds to the ambiguous input, and outputting an indication representative of the language.

KNOWLEDGE REPOSITORY

A knowledge storage system is described. A specific embodiment is a computer system comprising a knowledge base of general knowledge in structured form which can be added to and queried by untrained users. Various embodiments include the facility for remote computers to access the knowledge stored in the system, natural language questions to be answered, profile screens giving general knowledge about an object in the system, and methods for distinguishing between reliable and unreliable facts. 1. A computer-implemented method , comprising:receiving a natural language question;determining that the natural language question relates to a first fictional context of a plurality of fictional contexts represented in the knowledge base;generating a query compatible with structured knowledge of a knowledge base using the natural language question;generating a result by processing the query with reference to the knowledge base and the first fictional context; andgenerating a response to the natural language question using the result.2. The method of claim 1 , wherein determining that the natural language question relates to the first fictional context comprises:determining that the natural language question refers to an object; anddetermining that the object is associated with the first fictional context in the knowledge base.3. The method of claim 1 , wherein determining that the natural language question relates to the first fictional context comprises identifying a reference to the first fictional context in the natural language question.4. The method of claim 1 , wherein the natural language question is received from a user of the knowledge base claim 1 , and wherein determining that the natural language question relates to the first fictional context comprises determining that the first fictional context is associated with the user in the knowledge base.5. The method of claim 4 , further comprising associating the first fictional context with the user in response to ...

APPARATUS AND METHOD FOR EFFICIENTLY REVIEWING PATENT DOCUMENTS

Apparatuses and methods are provided for efficiently and effectively reviewing patent documents that can include, e.g., issued patent documents, patent applications, patent file histories, and the like. Different aspects of/patent data associated with patent documents may be identified, parsed, and/or extracted from patent documents. These different aspects/patent data may be used to create an interactive patent document. Through a user interface, a user can interact with the interactive patent document to review, analyze, or otherwise peruse a patent document, e.g., determine claim dependencies, correlate figure elements to specification text, determine antecedent basis of claim terms, etc. 1. An apparatus , comprising:a parser for parsing textual components of a patent document; andan interactive patent document creator operatively connected to the parser for creating an interactive document based upon the parsed patent document.2. The apparatus of further comprising claim 1 , a local database for storing at least one of the patent document claim 1 , additional documents related to the patent document claim 1 , and information relevant to the patent document.3. The apparatus of claim 2 , wherein the local database is operatively connected to at least one remote patent database from which the patent document claim 2 , the additional documents related to the patent document claim 2 , and the information relevant to the patent document is received.4. The apparatus of further comprising claim 1 , an image processor for performing optical character recognition to identify the textual components claim 1 , wherein the textual components are included within at least one figure of the patent document.5. The apparatus of claim 4 , wherein the image processor further performs at least one of the following:extracting at least one figure from the patent document;cropping the at least one figure;rotating the at least one figure;enhancing the at least one figure;linking textual ...

SEMANTIC ENRICHMENT BY EXPLOITING TOP-K PROCESSING

Proper representation of the meaning of texts is crucial to enhancing many data mining and information retrieval tasks, including clustering, computing semantic relatedness between texts, and searching. Representing of texts in the concept-space derived from Wikipedia has received growing attention recently, due to its comprehensiveness and expertise. This concept-based representation is capable of extracting semantic relatedness between texts that cannot be deduced with the bag of words model. A key obstacle, however, for using Wikipedia as a semantic interpreter is that the sheer size of the concepts derived from Wikipedia makes it hard to efficiently map texts into concept-space. An efficient algorithm is proved which is able to represent the meaning of a text by using the concepts that best match it. In particular, this approach first computes the approximate top- concepts that are most relevant to the given text. These concepts are then leverage to represent the meaning of the given text. 1. A method for performing semantic interpretation for keywords , the method comprising:obtaining one or more keywords for semantic interpretation;computing top-k concepts in a knowledge database for the one or more keywords; andmapping the one or keywords into a concept space using the top-k concepts.2. The method of claim 1 , wherein the step of computing top-k concepts comprises the steps of:estimating the bounds on the number of input lines; andcomputing an expected score for a fully or partially unseen object.3. The method of claim 1 , wherein the step of obtaining one or more keywords for semantic interpretation comprises extracting keywords from close captioning data included with content.4. The method of claim 1 , further comprising processing concepts resulting from the mapping of the one or more keywords into the concept space.5. The method of claim 4 , wherein the processing comprises ranking the concepts6. The method of claim 4 , wherein the processing comprises ...

METHOD FOR PROCESSING NATURAL LANGUAGE AND MATHEMATICAL FORMULA AND APPARATUS THEREFOR

The present disclosure provides an apparatus and method for processing a natural language and a mathematical formula. The apparatus includes a natural language and mathematical formula input unit configured to receive a natural language and a mathematical formula inputted; an information generation unit configured to generate parsing semantic information of the mathematical formula from combined data composed of the natural language combined with the mathematical formula; an operation information extraction unit configured to extract operation information generated by using a logical condition from the combined data; a natural language and mathematical formula structuralizing unit configured to analyze, classify in terms of specific meaning and recombine the combined data; an operation structuralizing unit configured to structuralize the operation information; and a natural language and mathematical formula indexing unit configured to index the combined data. 1. An apparatus for processing a natural language and a mathematical formula , the apparatus comprising:a natural language and mathematical formula input unit configured to receive a natural language and a mathematical formula inputted;an information generation unit configured to generate parsing semantic information of the mathematical formula from combined data including the natural language combined with the mathematical formula;an operation information extraction unit configured to extract operation information generated by using a logical condition from the combined data;a natural language and mathematical formula structuralizing unit configured to analyze, classify in terms of specific meaning and recombine the combined data;an operation structuralizing unit configured to structuralize the operation information; anda natural language and mathematical formula indexing unit configured to index the combined data.2. The apparatus of claim 1 , wherein the natural language and mathematical formula input unit ...

Method and Apparatus for Identifying a Conversation in Multiple Strings

Techniques for identifying conversations in multiple short strings include determining from a first plurality of strings associated with a first contact of a user, based on time separations between successive strings, a first conversation portion and a different second conversation portion. The first conversation portion (snippet) comprises a plurality of strings of the first plurality; and the second snippet comprises a different pluralty of strings of the first plurality. A first semantic content for the first snippet and a second semantic content for the second snippet are determined. It is determined whether to merge the first snippet and the second snippet into a first conversation that includes the first snippet based, at least in part, on a similarity of the first semantic content to the second semantic content. 128-. (canceled)29. A method comprising:determining from a first plurality of strings associated at least in part with a first contact of a user, based at least in part on time separations between successive strings, a first conversation portion that comprises a plurality of strings of the first plurality and a different second conversation portion that comprises a different plurality of strings of the first plurality;determining a first semantic content for the first conversation portion and a second semantic content for the second conversation portion; anddetermining whether to merge the first conversation portion and the second conversation portion into a first conversation that includes the first conversation portion based, at least in part, on a similarity of the first semantic content to the second semantic content.30. A method of claim 29 , wherein determining whether to merge the first conversation portion and the second conversation portion further comprises combining the first conversation portion and the second conversation portion into the first conversation claim 29 , if the similarity is determined to exceed a similarity threshold.31. A ...

DOCUMENT VIEWING APPARATUS AND TANGIBLE COMPUTER-READABLE RECORDING MEDIUM

Disclosed is a document viewing apparatus including: a display unit to display a page designation object for receiving designation of a document or designation of any page in one document; an operating unit to receive a page designating operation for the page designation object; and a control unit; wherein in case that there are a plurality of documents to be displayed, the control unit instructs the display unit to display the page designation objects corresponding to the plurality of documents to be displayed, respectively, and when the operating unit receives the page designating operation for any one of the page designation objects which are currently displayed, the control unit instructs the display unit to display a page designated by the page designating operation, the displayed page being contained in a document corresponding to the page designation object for which the page designating operation is received. 1. A document viewing apparatus comprising:a display unit to display a page designation object for receiving designation of a document or designation of any page in one document;an operating unit to receive a page designating operation for the page designation object; anda control unit;wherein in case that there are a plurality of documents to be displayed, the control unit instructs the display unit to display the page designation objects corresponding to the plurality of documents to be displayed, respectively, and when the operating unit receives the page designating operation for any one of the page designation objects which are currently displayed, the control unit instructs the display unit to display a page designated by the page designating operation, the designated page being contained in a document corresponding to the page designation object for which the page designating operation is received.2. The document viewing apparatus of claim 1 , wherein the entire page designation object corresponds to one document claim 1 , and a page position in ...

ADAPTING LANGUAGE USE IN A DEVICE

In several non-English languages and cultures, such as Dutch and German, there is a formal and informal language form used to address a person. A device having a user interface is adapted for use with both formal and informal language. A user's preferred language form can change over time, and is determined directly or indirectly from characteristics of the user based on their use of the device, including how long the device has been used, a role of the user and/or his or her location. Another way of determining the characteristics of the user is to monitor the user's online behavior, including such data as social networking traffic, web sites visited, email and chat use, and the like. An application's user interface can be dynamically changed to use the current preferred language form. 1. A method comprising:adapting a language form used in a device to one of an informal or formal form based on data related to a user's interaction with the device;updating a preferred language form with the adapted language form; andgenerating a user interface on the device to reflect the preferred language form.2. The method of claim 1 , wherein adapting the language form used in the device to one of an informal or formal form based on data related to the user's interaction with the device includes:accumulating the data related to the user's interaction with a device; and an amount of time the user spends using the device over a period of time;', 'a number of interactions between the user and the device via a user interface on the device;', 'a number of days that the device has been in use;', 'a number of times the user interacted with the device using an informal language form; and', 'a number of times the user interacted with the device using a formal language form., "measuring the accumulated data against a criteria for determining whether to adapt the language form to the informal or formal form, the criteria including meeting at least one threshold related to the user's ...

INTELLIGENT HIGHLIGHTING SYSTEM

An intelligent highlighting system for automatically determining where the author has marked a manuscript for insertion of multimedia, and then inserting the multimedia into digital publications is provided. In the system, digital publication are parsed to identify multimedia references, such as footnotes, comments and hyperlinks. A database table index containing the parsed results is generated and stored in a projected identification database. Next, metadata specific to the parsing results are also stored in the project identification database and a pre-determined highlighting method is identified. The metadata and highlighting method are compiled into an intelligent highlighting object, which is used to embed a hidden multimedia path within the keywords. The keywords with the embedded multimedia are then stored as a binary file. Using the data stored in the project identification database, the binary file and e-reader specifications, the multimedia files are converted to the appropriate format compatible with the e-readers. 1. A method of automatically inserting multimedia files into a digital publication comprising:parsing the digital publication to identify multimedia references within the digital publication;indexing locations and reference data associated with the multimedia references identified in the digital publication;identifying and categorizing the indexed locations and the indexed reference data, the indexed, identified and categorized locations and reference data used to identify and capture multimedia; andstoring the indexed, identified and categorized locations and reference data in a project identification database.2. The method of claim 1 , further comprising:locating metadata stored in a metadata database; andstoring the metadata in the project identification database.3. The method of claim 2 , further comprising:located a pre-determined highlighting method used to highlight one or more keywords, the one or more keywords identified by the ...

METHOD FOR CLASSIFYING PIECES OF TEXT ON BASIS OF EVALUATION POLARITY, COMPUTER PROGRAM PRODUCT, AND COMPUTER

A computer-implemented method, program product, and system, for extracting pieces of text from a plurality of pieces of text. The method includes: primarily evaluating a measure of positive expressions and a measure of negative expressions included in each of pieces of text; secondarily evaluating each of the pieces of text on the basis of a plurality of evaluation functions, where certain evaluation functions among the plurality of evaluation functions include, as variables, the measure of positive expressions and the measure of negative expressions; and extracting a piece of text having an evaluation result with a higher rating in preference to a piece of text having an evaluation result with a lower rating, where the individual evaluation results are based on the same evaluation function among the plurality of evaluation functions. 1. A computer-implemented method for extracting pieces of text from a plurality of pieces of text , said method comprising the steps of:primarily evaluating a measure of positive expressions and a measure of negative expressions included in each of pieces of text;secondarily evaluating each of said pieces of text on the basis of a plurality of evaluation functions, wherein certain evaluation functions among said plurality of evaluation functions include, as variables, said measure of positive expressions and said measure of negative expressions; andextracting a piece of text having an evaluation result with a higher rating in preference to a piece of text having an evaluation result with a lower rating, wherein said individual evaluation results are based on said same evaluation function among said plurality of evaluation functions.2. The method of claim 1 , wherein one evaluation function among said certain evaluation functions is a function outputting an evaluation result with a higher rating for a piece of text having an average measure of positive expressions and an average measure of negative expressions.3. The method of claim 1 , ...

LITERARY GENRE MAP AND METHODS OF USE THEREOF

A method of displaying an electronic book includes techniques for allowing a person to self-publish an electronic book by employing tones of the electronic book and displaying the book on a two-dimensional graphical book map in which the location of the book on the map is based on the identified tones and degrees of those tones. A genre map including various book genres and subgenres also are employed. A person desiring to find a book having desired tones/characteristics uses the genre map and then the displayed graphical book map. 1. A method of displaying an electronic book , comprising:receiving a degree of an identified tone of a book to be electronically received and placed on a graphical book map;receiving an electronic copy of the book via an electronic communication;providing a graphical book map for display on an electronic device, the graphical book map having a graphical representation of the received book disposed at a location on the graphical book map based on the received degree of the identified tone of the book.2. The method of claim 1 , wherein the graphical book map includes graphical representations of other electronic books received via electronic communication claim 1 , the respective locations of the graphical representations of the other electronic books being based on respective identified degrees of tones of the other electronic books.3. The method of claim 1 , wherein the graphical book map further includes a graphical representation of a well-known book at a location on the graphical book map that is based on a degree of a tone of the well-known book claim 1 , the graphical representation of the well-known book being different than the graphical representation of the received electronic book.4. The method of claim 1 , comprising receiving an identification of a plurality of tones of the received book and receiving a degree for each of the identified tones of the received book claim 1 , and wherein the graphical representation of the ...

EVENT VISUALIZATION

Displaying a preference by a first user of a content contribution submitted by a second user is disclosed. A preference event by the first user is detected. A plurality of detected events is stored. In response to a query from a client, at least a portion of the stored detected events is produced. At least a portion of the received events is caused to be rendered graphically. 1. A method of presentation of preference events , the method comprising:receiving, at an automated preference system from multiple users, multiple preference events regarding purchasable products; and present to a first user of the preference system a visualization interface displaying a subset of the multiple preference events;', if the first user has submitted a positive preference event regarding the product, a first indicator configured to indicate that the first user submitted a positive preference event regarding the product; and', 'if at least one friend of the first user has submitted a positive preference event regarding the product, a second indicator configured to indicate that at least one friend of the first user has submitted a positive preference event regarding the product;, 'for each product represented in the visualization interface, display in the visualization interface, 'offer to the first user an option to view in the visualization interface only preference events regarding products for which at least a threshold number of friends of the first user have submitted positive preference events; and', 'as additional preference events are received at the preference system, update the visualization interface to reflect the additional preference events., 'operating one or more processors of the preference system to2. The method of claim 1 , further comprising operating the one or more processors to: 'if the first user has not submitted a positive preference event regarding the product, the first indicator configured to solicit from the first user a positive preference event ...

Script Detection Service

Script detection service techniques are described. In an implementation, a corpora of text is analyzed to determine which strings in the corpora of text are to be included in a targeted dictionary that is usable for language detection services. The targeted dictionary is populated with strings that are individually associated with a human language. The strings include individual text characters associated with values that correspond to a particular subset of values in a table that associates subsets of values with individual human writing systems. 1. A method implemented by one or more computing devices , the method comprising:analyzing a corpora of text to determine which strings in the corpora of text are to be included in a targeted dictionary that is usable for language detection services; andpopulating the targeted dictionary with a plurality of strings that are individually associated with a human language, the plurality of strings including individual text characters associated with values that correspond to a particular subset of values in a table that associates subsets of values with individual human writing systems.2. The method of claim 1 , wherein the populating of the targeted dictionary further comprises populating the targeted dictionary with one or more strings that frequently occur in the human language.3. The method of claim 1 , wherein the populating of the targeted dictionary further comprises populating the targeted dictionary with one or more strings that are indicative of the human language.4. The method of claim 1 , wherein the populating of the targeted dictionary further comprises populating the targeted dictionary with one or more strings that serve a function in the human language.5. The method of claim 1 , further comprising assigning a weight to respective strings in the plurality of strings based on a frequency with which the respective strings appear in the corpora of text.6. The method of claim 1 , further comprising weighing the ...

METHOD AND SYSTEM RELATING TO SALIENT CONTENT EXTRACTION FOR ELECTRONIC CONTENT

Individuals receive overwhelming barrage of information which must be filtered, processed, analysed, reviewed, consolidated and distributed or acted upon. Automatic approaches to “scraping” salient content from sources of content are provided allowing the salient content to be provided to the user or subjected to further processing such as clustering or sentiment analysis for example. 1. A method comprising:a) receiving an item of content;b) identifying within the item of content using a microprocessor a set of lexical pattern cues for core content of the item of content and selecting a segment of the item of content having a highest likelihood as being the core content based upon a structural analysis of the item of content in dependence upon at least the set of lexical pattern cues;c) parsing the item of content to generate a hierarchy of content within the item of content;d) ranking the hierarchy of content in dependence upon at least the lexical pattern cues and sorting the resulting ranking;e) identifying a gap when searching down the ranking meeting a predetermined threshold and removing those portions of the hierarchy of content below the gap to generate truncated content;f) find all occurrences for portions of the hierarchy of content with closest match to the lexical pattern cues closest to the start of the item of content;g) determining whether multiple matches to the lexical pattern cues exist and establishing an action in dependence upon at least whether multiple matches exist or not; establishing the occurrence for the portion of the hierarchy of content as the core content of the item of content when the determination of multiple matches is negative; and', 'establishing the occurrence for the portion of the hierarchy of content that at least one of contains the largest portion of the item of content and is the first occurrence as the core content of the item of content when the determination of multiple matches is positive., 'h) performing the action, ...

HANDHELD ELECTRONIC DEVICE AND METHOD EMPLOYING LOGICAL PROXIMITY OF CHARACTERS IN SPELL CHECKING

An improved handheld electronic device and associated method employing an improved spell checking routine enable proposed spelling corrections having a close logical proximity to an active input to be output at a position of preference for easy selection by the user. By way of example, a base character and the various accented forms thereof can be said to have a logical proximity to one another that is closer than their logical proximity to any character having a different base character, whether additionally having a diacritical element or not. 114-. (canceled)15. A method of enabling input on an electronic device , the method comprising:receiving an input reflecting a set of characters;identifying proposed spelling corrections based on the input; andoutputting at least two of the proposed spelling corrections such that spelling corrections of a first type are distinguishable from spelling corrections of a second type.16. The method of claim 15 , wherein outputting at least two of the proposed spelling corrections comprises:ordering the output proposed spelling corrections with the spelling corrections of the first type prioritized in the order over spelling corrections of the second type.17. The method of claim 15 , wherein the first type of spelling correction is a correction that contains base characters matching the input claim 15 , but that has at least one diacritical difference.18. The method of claim 15 , wherein the second type of spelling correction is a correction that contains at least one base character different from the base characters of the input.19. The method of claim 15 , further comprising accessing a dictionary to determine whether any words exist in the dictionary that are of the first type of spelling correction.20. The method of claim 19 , further comprising identifying claim 19 , as a first proposed spelling correction claim 19 , a word that is of the first type of spelling correction.21. The method of claim 20 , further comprising ...

Intelligent and robust context based XML data parsing from spreadsheets

This invention is for a method to make sense of XML (Extensible Markable Language) data when it is imported into spreadsheets without the use of a stylesheet and to accurately capture that data automatically into the appropriate fields. When it is imported into spreadsheets without a stylesheet, the rows and columns are unspecifiable, and even for similar XML files having different sets of data, the rows and columns may not always correspond exactly, as it would with form data where each data field always has a place holder. The method developed by this claim uniquely addresses the issue of absorbing this data by cross indexing all descendant elements and attributes pillared around a mandatory element and attribute for one direction, and keeping an open spring like data sensing mechanism in the vertical direction, with resulting data read being instantly captured accurately, associated with the proper data field and validated. 1. Intelligent and robust context based XML data parsing from spreadsheets using an unique indexing scheme and iterative spring like vertical data explorer. The illustration in attached drawing (captioned ) shows the typical problem that is encountered in opening an XML in a spreadsheet that can parse and bring in the the XML in a read only mode into a spreadsheet format with column headers showing the full node address including traced parentage, current element and attribute.A description of this drawing is attached that shows the challenge in obtaining a value of a data parameter from the cell location alone in terms of row or column numbers.The claim addresses this issue uniquely. The method developed is far superior to any general XML parsing because it combines apriori information about the DOM structure, while allowing for extreme flexibility in terms of allowing mandatory as well as optional fields. For complex XML data which is not 2-dimensional in hierarchy, this causes an asynchronous structure in the planar spreadsheet view when ...

Methods and Systems for Automated Text Correction

The present embodiments demonstrate systems and methods for automated text correction. In certain embodiments, the methods and systems may be implemented through analysis according to a single text correction model. In a particular embodiment, the single text correction model may be generated through analysis of both a corpus of learner text and a corpus of non-learner text. 1. An apparatus , comprising: to identify words of an input utterance;', 'to place the words in a plurality of first nodes stored in the memory device;', 'to assign a word-layer tag to each of the plurality of first nodes based, in part, on neighboring nodes of the plurality of first nodes; and', 'to generate an output sentence by combining words from the plurality of first nodes with punctuation marks selected, in part, on the word-layer tags assigned to each of the first nodes., 'at least one processor and a memory device coupled to the at least one processor, in which the at least one processor is configured2. The apparatus of claim 1 , in which the word-layer tag is at least one of none claim 1 , comma claim 1 , period claim 1 , question mark claim 1 , and exclamation mark.3. The apparatus of claim 1 , in which the plurality of first nodes is a first-order linear chain of conditional random fields.4. The apparatus of claim 1 , in which each of the word-layer tags is placed in a node of a plurality of second nodes stored in the memory device claim 1 , each of the second nodes coupled to at least one of the first nodes.5. The apparatus of claim 1 , in which the at least one processor is further configured to assign a sentence-layer tag to each of the nodes in the plurality of first nodes based claim 1 , in part claim 1 , on boundaries of the input utterance claim 1 , in which punctuation marks selected for the output sentence are selected claim 1 , in part claim 1 , on the sentence-layer tag claim 1 , in which the sentence-layer tag is at least one of a declaration beginning claim 1 , ...

METHOD FOR GENERATING TEXT THAT MEETS SPECIFIED CHARACTERISTICS IN A HANDHELD ELECTRONIC DEVICE AND A HANDHELD ELECTRONIC DEVICE INCORPORATING THE SAME

Incoming e-mails, instant messages, SMS, and MMS, are scanned for new language objects such as words, abbreviations, text shortcuts and, in appropriate languages, ideograms, that are placed in a list for use by a text input process of a handheld electronic device to facilitate the generation of text. 18.-. (canceled)9. A method , comprising:receiving a text file in an electronic device, the text file containing a plurality of language objects;identifying, by a processor in the electronic device, from the plurality of language objects in the text file one or more new language objects for which a storage unit in the electronic device does not contain a match;determining, by the processor, that a ratio reflecting a quantity of the new language objects in at least a segment of the text file to a quantity of the language objects in the at least a segment of the text file exceeds a first predetermined threshold;identifying, by the processor, one or more particular ones of the new language objects each containing at least one linguistic element different from a plurality of predetermined linguistic elements stored in the storage unit;determining, by the processor, that a ratio reflecting a quantity of the one or more particular ones of the new language objects to the quantity of the new language objects is below a second predetermined threshold; andignoring the one or more particular ones of the new language objects and adding the new language objects that are not ignored to the storage unit.10. The method of claim 9 , wherein the electronic device is a handheld electronic device.11. The method of claim 9 , wherein the text file is an email message.12. The method of claim 9 , wherein the text file is an instant message.13. The method of claim 9 , further comprising claim 9 , before adding the new language objects that are not ignored to the storage unit claim 9 , removing one or more of existing language objects from the storage unit.14. An electronic device claim 9 , ...

SYSTEMS AND METHODS FOR AUTOMATICALLY GENERATING A RÉSUMÉ

A résumé of a developer working with a parallel processing development environment is, at least in part, automatically generated by the parallel processing development environment based upon information of the developers work experience within the development environment. 1. A method for automatically generating a résumé of a developer using a development environment , comprising:retrieving, from a database and using a processor of the development environment, information including work completed by the developer, and associated start and end dates of the completed work; andgenerating, using the processor, a description of developer experience within the development environment based upon the completed work and the associated start and end dates.2. The method of claim 1 , wherein a first date when the developer is given edit privileges to the completed work within the development environment defines the associated start date.3. The method of claim 5 , wherein a second date when an administrator of the development environment submits that the work is completed defines the associated end date.4. The method of claim 1 , further comprising:(a) receiving a skill pass notification defining a developer skill from a training institution;(b) adding the developer skill to the résumé;(c) determining whether the training institution is trusted based upon an institution list within the database; and(d) adding a certified indication to the résumé in association with the developer skill when the training institution is trusted.5. The method of claim 1 , further comprising:(a) receiving a developer skill training request from the developer;(b) providing a training program associated with the developer skill to the developer;(c) adding the developer skill to the résumé if the developer completes the training program above a threshold of acceptability.6. The method of claim 1 , further comprising:(a) determining a developer fee associated with a developer skill of the developer;(b) ...

Intelligent Presentation of Documents

In some implementations, documents can be presented on a display of a computing device based on a context of the computing device. The context can include a current time and/or current location associated with the computing device. The documents can be presented based on a time and/or location associated with the documents. Documents can be downloaded and shared between devices. Documents can be dynamically updated based on document vendor provided information and/or other network based resources. In some implementations, the various graphical interfaces described herein provide access to a variety of document types in an organized and efficient manner. 1. A method comprising:storing one or more documents on a computing device;determining a context of the computing device;based on the context, identifying at least one of the one or more documents to present on a display of the computing device; andpresenting the at least one identified document on a display of the computing device.2. The method of claim 1 , wherein determining a context of the computing device comprises determining a current time and further comprising:comparing the current time to one or more preconfigured times associated with the one or more documents, where each document is associated with at least one preconfigured time; andidentifying the at least one identified document based on the comparison.3. The method of claim 1 , wherein determining a context of the computing device comprises determining a current location of the computing device and further comprising:comparing the current location to one or more preconfigured locations associated with the one or more documents, where each document is associated with at least one preconfigured location; andidentifying the at least one identified document based on the comparison.4. The method of claim 1 , wherein presenting the at least one identified document comprises presenting the at least one identified document on a display of the computing ...

Image processing device, image processing method and non-transitory computer readable recording medium

An image processing device, comprises: an input part for inputting image data; a word extracting part for extracting a word from texts contained in the image data; a synonym obtaining part for obtaining a synonym corresponds to the word, and for associating the obtained synonym with the word; a position identifying part for identifying a display position on the image data of the word with which the synonym is associated; a layer creating part for creating an accompanying layer to add to an original layer, which is the image data containing the word, and for embedding the synonym associated with the word within a position on the accompanying layer the same as the display position identified by the position identifying part; and an output image generating part for generating output image data including the original layer containing the word and the accompanying layer within which the synonym is embedded.

Assisted Free Form Decision Definition Using Rules Vocabulary

A method of decision definition using a rules vocabulary includes: receiving free form input; identifying terms contained within the free form input; searching the rules vocabulary objects for terms; responsive to the term being found, obtaining input from a user as to whether to use the found term; responsive to the term not being found; searching the rules vocabulary attributes for terms having attributes corresponding to the term; responsive to the term being found, obtaining input from a user as to whether to use the found term; and refactoring the free form input with the found term accepted by the user. The method also includes updating the rules vocabulary with the term identified in the free form input as a synonym for the term found in said rules vocabulary. One embodiment further provides a method of determining semantic equivalence between a plurality of rules using a rules database having preferred terms. 1. A computer-implemented method of decision definition using a rules vocabulary , the method comprising the steps of:receiving free form input;a data processing system identifying terms contained within the free form input;searching the rules vocabulary objects for terms;{'b': '518', 'responsive to the term being found, obtaining () input from a user as to whether to use the found term;'} searching the rules vocabulary attributes for other terms having attributes corresponding to the term that is not found;', 'responsive to another term being found, obtaining input from a user as to whether to use the found similar term; and, 'responsive to the term not being foundrefactoring the free form input with the found term or the other term accepted by the user.2. The method of claim 1 , wherein said terms include one of objects claim 1 , attributes claim 1 , values claim 1 , relationships claim 1 , and verbs.3. The method of claim 1 , further comprising updating said rules vocabulary with said term identified in said free form input.4. The method of claim 1 , ...

Automatic Language Identification for Dynamic Text Processing

Methods and systems which utilize, in one embodiment, automatic language identification, including automatic language identification for dynamic text processing. In at least certain embodiments, automatic language identification can be applied to spellchecking in real time as the user types. 1. A machine-implemented method , comprising:at an electronic device with one or more processors and memory:receiving a first language identification for a document;performing a modifying operation on the document in accordance with the first language identification; anddetermining based at least in part on results from the modifying operation, whether the first language identification for the document is correct.2. The method of claim 1 , wherein the modifying operation is a spellchecking function.3. The method of claim 1 , wherein the results of the modifying operation include a count of errors detected by the modifying function.4. The method of claim 1 , wherein the results of the modifying operation include one or more types of errors detected by the modifying function.5. The method as in claim 1 , wherein the first language identification of the document is automatically determined by an automatic language identifier service claim 1 , without user intervention.6. The method as in claim 1 , further comprising claim 1 , receiving an accuracy confidence ranking associated with the first language identification; andwherein the determining is based on the results from the modifying operation and the accuracy confidence ranking.7. The method as in claim 1 , further comprising claim 1 , in accordance with a determination that the first language identification is incorrect claim 1 , determining a second language identification of the document.8. The method of claim 7 , further comprising claim 7 , performing a modifying function on the document in accordance with one or more alternate languages different from the first language; andwherein the second language identification of the ...

INVENTIVE CONCEPTS ENABLED SEMI-AUTOMATIC TESTS OF PATENTS

This patent (application) discloses for a claimed invention 10 tests (+their 5 controls) enabled by its inventive concepts, automatically prompting their user through exploratively checking its meeting the requirements stated by 10) A computer-implemented method for updating a given data structure PTR-DS in a BAD-KR , both in given formats , by a set of Binary Elementary Disclosed (“BED”) inventive concepts of PTR's TT.0 , called BED-TT.0 , input to it by the user and by appendices to it and to BAD-KR for controlling an Innovation Expert System IES—the method (performing , for a claimed invention of PTR , its refined claim construction by here first disaggregating its compound inventive concepts , if these are not yet elementary) using a memory for storing the so updated PTR-DS , generated by executing this method on TT.0's compound inventive concepts BAD-X..n of TT.0 representing their mirror predicates BAD-.0.n of its X.0.n , 1≦n≦N—which:{'sup': 'CT', '(a) writes the PTR-DS in a given BAD-KR into the memory'} (b).1 either given by the IES as a default KR_R&S_S for both strategies, based on the BAD-KR of (a),', '(b).2 or a KR_R&S_S input, in a given notation, by the user additionally to the BAD-KR of (a);, '(b) automatically prompts the user to determine the KR_R&S_S to be obeyed during its execution, being'}{'sup': 'CT', 'claim-text': ["(c).1 for a given 0≦I≦IRSI, all document.i's and all their doc.i-MUIs, 0≦i≦l, and", '(c).2 the document.CT in doc.0 and all its doc.CT-MUIs, and', {'u': {'@style': 'single', 'X'}, '(c).3 all elements X.0.n and their predicates BAD-.0.n, 1≦n≦N, for any BAD-KR in KR_R&S_S;'}], '(c) automatically identifies in said PTR-DS and said KR_R&S_S, in given formats,'} ["(d).1 prompt the user to input a set of BED-cr-C.0.k's—in a given notation—of TT.0, 1≦k≦K, and", {'u': [{'@style': 'single', 'X'}, {'@style': 'single', 'C'}, {'@style': 'single', '⊂'}, {'@style': 'single', 'C'}, {'@style': 'single', 'X'}, {'@style': 'single', 'C'}, {'@style': ...

Retrieving Electronic Documents by Converting Them to Synthetic Text

The present invention relies on the two-dimensional information in documents and encodes two-dimensional structures into a one-dimensional synthetic language such that two-dimensional documents can be searched at text search speed. The system comprises: an indexing module, a retrieval module, an encoder, a quantization module, a retrieval engine and a control module coupled by a bus. Electronic documents are first indexed by the indexing module and stored as a synthetic text library. The retrieval module then converts an input image to synthetic text and searches for matches to the synthetic text in the synthetic text library. The matches can be in turn used to retrieve the corresponding electronic documents. In one or more embodiments, the present invention includes a method for comparing the synthetic text to documents that have been converted to synthetic text for a match. 1an indexing module for receiving an electronic document and generating a synthetic representation of the electronic document, the indexing module also producing an association between the electronic document and the synthetic representation; anda data storage for storing the electronic document, the synthetic representation of the electronic document, and an association between the electronic document, a page of the electronic document and the synthetic representation.. A system for converting documents to synthetic text, the system comprising: This application is a continuation of U.S. patent application Ser. No. 13/415,228, titled “Retrieving Electronic Documents by Converting them to Synthetic Text,” filed Mar. 8, 2012, which is a divisional of U.S. patent application Ser. No. 11/777,142, titled “Retrieving Electronic Documents by Converting them to Synthetic Text,” filed Jul. 12, 2007, which is incorporated by reference herein in its entirety.1. Field of the InventionThis invention relates generally to systems and methods for retrieving electronic documents using an image or portion of the ...

APPARATUS AND METHOD FOR GENERATING INSPECTION REPORT(S)

In one embodiment, an apparatus for generating inspection report(s) includes a report input unit for receiving input from a user for an inspection report and displaying contents of the inspection report which currently has been inputted, a context feature identifying unit for identifying, in a real-time manner, one or more context features from the displayed contents of the inspection report, a processing unit for processing inspection data for the object based on one or more of the identified context features, and an input assistant unit configured to cause the report input unit to display a list of items of the inspection data processed by the processing unit, upon detection of a specific user input, to be selected by the user, and to insert, when an item in the list is selected by the user, processed inspection data corresponding to the selected item into the inspection report. 1. An apparatus for generating inspection report(s) , comprising:a report input unit for receiving input from a user for an inspection report relating to an object which has been subjected to one or more inspections and displaying contents of the inspection report which currently has been inputted;a context feature identifying unit for identifying, in a real-time manner, one or more context features from the displayed contents of the inspection report which currently has been inputted;a processing unit for processing inspection data for the object based on one or more of the identified context features, the inspection data resultant from the one or more inspections subjected to by the object; andan input assistant unit configured to cause the report input unit to display a list of items of the inspection data processed by the processing unit, upon detection of a specific user input, to be selected by the user, and to insert, when an item in the list is selected by the user, processed inspection data corresponding to the selected item into the inspection report.2. The apparatus according to ...

LIST DISPLAY APPARATUS AND LIST DISPLAY METHOD

A list display apparatus that displays multiple pieces of character string data in a list on a display unit includes a storage unit that stores the multiple pieces of character string data; a sorting unit that sorts the multiple pieces of character string data stored in the storage unit in a character code order; a ligature decomposing unit that decomposes a ligature included in the multiple pieces of character string data into multiple original letters on which the ligature is based in the sorting by the sorting unit; and a sorting control unit that controls the sorting unit so that the multiple letters resulting from the decomposition by the ligature decomposing unit is used in the sorting, instead of the ligature. 1. A list display apparatus that displays multiple pieces of character string data in a list on a display unit , the list display apparatus comprising:a storage unit configured to store the multiple pieces of character string data;a sorting unit configured to sort the multiple pieces of character string data stored in the storage unit in a character code order;a ligature decomposing unit configured to decompose a ligature included in the multiple pieces of character string data into multiple original letters on which the ligature is based in the sorting by the sorting unit; anda sorting control unit configured to control the sorting unit so that the multiple letters resulting from the decomposition by the ligature decomposing unit is used in the sorting instead of the ligature,wherein the multiple pieces of character string data are displayed in the list according to an order of the sorting by the sorting unit under the control of the sorting control unit.2. The list display apparatus according to claim 1 , further comprising:a first replacement unit configured to replace a part of the ligature in each piece of character string data including the ligature with all of the multiple letters resulting from the decomposition,wherein the sorting control unit ...

DATA PROCESSING METHOD, PRESENTATION METHOD, AND CORRESPONDING APPARATUSES

A data processing method includes obtaining text information corresponding to a presented content, the presented content comprising a plurality of areas; performing text analysis on the text information to obtain a first keyword sequence, the first keyword sequence including area keywords associated with at least one area of the plurality of areas; obtaining speech information related to the presented content, the speech information at least comprising a current speech segment; and using a first model network to perform analysis on the current speech segment to determine the area corresponding to the current speech segment, wherein the first model network comprises the first keyword sequence. 1. An apparatus for data processing , comprising:a text obtaining module configured to obtain text information corresponding to a presented content, the presented content comprising a plurality of areas;a text analysis module configured to perform text analysis on the text information to obtain a first keyword sequence, the first keyword sequence including area keywords associated with at least one area of the plurality of areas;a speech obtaining module configured to obtain speech information related to the presented content, the speech information at least comprising a current speech segment;a first speech analysis module configured to use a first model network to perform analysis on the current speech segment to determine the area corresponding to the current speech segment, wherein the first model network comprises the first keyword sequence.2. The apparatus according to claim 1 , wherein the first speech analysis module comprises:a first confidence submodule configured to obtain a confidence degree of at least one area keyword in the first keyword sequence, wherein the higher similarity an area keyword has with respect to the current speech segment, the higher confidence degree is obtained for the area keyword;an area determining submodule configured to determine, if a ...

Method for Parsing Natural Language Text

A parser for natural language text is provided. The parser is trained by accessing a corpus of labeled utterances. The parser extracts details of the syntactic tree structures and part of speech tags from the labeled utterances. The details extracted from the tree structures include Simple Links which are the key to the improved efficiency of this new approach. The parser creates a language model using the details that were extracted from the corpus. The parser then uses the language model to parse utterances. 1. A method for using a parser to parse natural language text , said method comprising:(a) training said parser by accessing a corpus of labeled utterances;(b) using said parser to extract details from said corpus, where said details include at least one simple link;(c) using said parser to create a language model using said details;(d) using said language model to generate at least one new simple link for at least one additional utterance; and(e) using said new simple links to generate a new syntactic tree structure for said additional utterance.2. The method of claim 1 , wherein said details also include syntactic tree structures.3. The method of claim 1 , wherein said details also include part of speech tags.4. The method of claim 1 , further including the step of outputting the results of said parsing of said new utterance.5. A computer-readable storage medium having instructions that develop a parser for use in natural language processing claim 1 , the instructions comprising:(a) training said parser by accessing a corpus of labeled utterances;(b) using said parser to extract details from said corpus, where said details include at least one simple link;(c) using said parser to create a language model using said details;(d) using said language model to generate at least one new simple link for at least one additional utterance; and(e) using said new simple links to generate a new syntactic tree structure for said additional utterance.6. A method of claim 5 ...

USING INFORMATION BANNERS TO COMMUNICATE WITH USERS OF ELECTRONIC DICTIONARIES

In one embodiment, computer-implemented systems and methods related to electronic dictionary systems are provided including: storing statistical information representing user interactions with the dictionary system over a period of time and electronically analyzing the statistical information so as to determine a customized message to a user. The customized message may be provided for display as part of a user interface comprising at least one field for entering a dictionary query, at least one field for providing dictionary results, and at least one field for customized user messages. 120.-. (canceled)21. A dictionary system , comprising: store, in a memory, query information representing a plurality of queries issued by a user to the dictionary system over a period of time;', 'analyze the query information to determine a subject of interest to the user;', 'identify a product or service consistent with the subject of interest; and', a field for entering a dictionary query;', 'a field for providing dictionary results;', 'a field for providing customized messages; and', 'a representation of a collection of dictionaries where the user may perform a search., 'provide an advertising message advertising the product or service, wherein the advertising message is configured to be part of a user interface comprising], 'a processor configured to22. The system of claim 21 , wherein the product or service is an electronic dictionary.23. The system of claim 21 , wherein the processor is further configured to store claim 21 , in the memory claim 21 , interface information representing a plurality of user interactions with the dictionary system over a period of time.24. The system of claim 23 , wherein the processor is further configured to:analyze the stored interface information to determine whether there is an interface feature that could be better utilized; andresponsive to determining the interface feature that could be better utilized, provide information for the user ...

SYSTEM AND METHOD FOR PHRASE MATCHING WITH ARBITRARY TEXT

A system and method for matching phrases having arbitrary text. A first data structure stores a list of common phrases having multiple words. Each unique word is indexed in a hash table and mapped to one or more values that describe attributes of using the word in one or more of the common phrases. Using the hash table and the list of common phrases, a temporary array is defined to keep track of possible matches between words in an input string and the list of common phrases. 1. A method for phrase matching in database operations , comprising:storing a plurality of expressions in a first data structure, each expression having a plurality of words;storing each word from the plurality of expressions as a key in a second data structure along with at least one associated value, each associated value representing a first set of attributes relating to use of the word in one of the expressions in the first data structure;receiving an input sentence having a string of words; 'evaluating, for each word that matches a key, the first set of attributes associated with the matched key and storing a second set of attributes in a third data structure, the second set of attributes indicating how the matching word from the input sentence compares with use of the same word in one of the expressions in the first data structure;', 'comparing a word from the input sentence with each key of the second data structurerepeating the comparing step for each word from the input sentence; anddetermining based on the first set of attributes and the second set of attributes if one or more expressions from the first data structure are present in the input sentence.2. The method of claim 1 , further comprising:updating the second set of attributes when use of the word from the input sentence is consistent with use of the word in an expression of the first data structure.3. The method of claim 1 , wherein the first set of attributes include: (i) the number of the expression in the first data ...

DATA DETECTION

A method for detecting data in a sequence of characters or text using both a statistical engine and a pattern engine. The statistical engine is trained to recognize certain types of data and the pattern engine is programmed to recognize the grammatical pattern of certain types of data. The statistical engine may scan the sequence of characters to output first data, and the pattern engine may break down the first data into subsets of data. Alternatively, the statistical engine may output items that have a predetermined probability or greater of being a certain type of data and the pattern engine may then detect the data from the output items and/or remove incorrect information from the output items. 1. A machine-implemented method of detecting data of a plurality of types in a sequence of characters , the method comprising:combining the use of a pattern detection method and a statistical learning method to detect the data.2. The method of claim 1 , comprising:scanning the sequence of characters using the statistical learning method, the statistical learning method detecting and outputting data of at least one of said plurality of types;using the pattern detection method to decompose the output data into data of a subset of types.3. The method of claim 2 , wherein the at least one type is an address and the subset of types comprises at least one of a street claim 2 , a town claim 2 , a county claim 2 , a state claim 2 , a country and a postal code.4. The method of claim 1 , comprising:scanning the sequence of characters using the statistical learning method, the statistical learning method outputting items, each in combination with a probability that the output item is data of one of said types;scanning only output items having at least a predetermined probability using the pattern detection method to detect and output the data of said types.5. The method of claim 1 , comprising:scanning the sequence of characters using the statistical learning method, the statistical ...

METHOD AND APPARATUS FOR RECOMMENDING TEXTS

A text recommendation for offering a next text recommendations that may be entered by a user is performed by executing a communication application; collecting context information associated with the communication application; predicting a user's intention by analyzing the context information; retrieving recommended texts corresponding to the user's intention; and displaying the recommended texts. 1. A method for recommending a text transmission , the method comprising:collecting context information associated with a particular contact while a communication application is being executed;predicting user's intention by analyzing the context information;retrieving recommended texts corresponding to the user's intention; anddisplaying the recommended texts.2. The method of claim 1 , wherein collecting step comprises acquiring at least one of an outbound text transmitted to the contact and an inbound text received from the contact.3. The method of claim 2 , wherein predicting step comprises:recognizing context of the outbound text or the inbound text; andpredicting the user's intention by mapping the recognized context from a previously stored prediction table.4. The method of claim 3 , wherein retrieving step comprises:acquiring the recommended texts related to the user's intention from an internal memory storing the previously stored prediction table; andaccessing the recommended text from an exterior source when there are no recommended text from the internal memory.5. The method of claim 4 , further comprising inserting claim 4 , when a user input for selecting one of the recommended texts is detected claim 4 , the selected recommended text into the outbound text.6. The method of claim 1 , wherein collecting step comprises acquiring at least one of an outbound text transmitted to the contact claim 1 , an inbound text received from the contact claim 1 , and data related to location claim 1 , weather claim 1 , time claim 1 , date claim 1 , day of week claim 1 , country ...

Information Classification Based on Product Recognition

The present disclosure provides an example information classification method and system based on product recognition. When a request for product recognition is received, one or more candidate product words of product profile information for recognition are determined. One or more characteristics of the product profile information are extracted based on the determined candidate product words respectively. Based on the candidate product words and their corresponding characteristics, the learning sub-model and the comprehensive learning model determine a product word corresponding to the product profile information. The product profile information is classified based on the product word. The present techniques implement automatic classification of the product profile information and improve an efficiency of information classification. 1. A method comprising:receiving a request for product recognition, the request for product recognition including product profile information for recognition;determining one or more candidate product words of the product profile information for recognition;extracting one or more respective characteristics from the product profile information for recognition according to the determined one or more candidate product words respectively;determining a product word corresponding to the product profile information for recognition at least based on the determined one or more candidate product words and their corresponding respective characteristics; andclassifying the product profile information for recognition according to the determined product word.2. The method as recited in claim 1 , wherein the determining the one or more candidate product words comprises:applying a lexical categorization to a title of the product profile information for recognition; andusing a word or phrase included in one or more character strings segmented by a conjunction, a preposition, or a punctuation as a respective candidate product word.3. The method as recited ...

Labeling Context Slices To Produce a Storyline from Mobile Device Data

Embodiments create and label context slices from observation data that together define a storyline of a user's movements. A context is a (possibly partial) specification of what a user was doing in the dimensions of time, place, and activity. Contexts can vary in their specificity, their semantic content, and their likelihood. A storyline is composed of a time-ordered sequence of contexts that partition a given span of time. A storyline is created through a process of data collection, slicing and labeling. Raw context data can be collected from a variety of observation sources with various error characteristics. Slicing refines the chaotic collection of contexts produced by data collection into a single consistent storyline composed of a sequence of contexts representing homogeneous time intervals. Labeling adds more specific and semantically meaningful data (e.g., geography, venue, activity) to the storyline produced by slicing. 1. A method of labeling context slices of a storyline of a user's movements , the method comprising:receiving a plurality of context slices derived from associated context data collected from a plurality of observation sources; identifying a set of candidate labels based on context data associated with the context slice, the candidate labels each comprising semantic data describing the context data associated with the context slice, the semantic data selected from a group consisting of geography, venue, and activity;', 'ranking the set of candidate labels by likelihood;', 'applying one or more of the candidate labels to the context slice; and', 'storing a correspondence between the applied one or more labels and the context slice., 'for each of the plurality of context slices2. The method of claim 1 , wherein the set of candidate labels are from public venue records claim 1 , a user-specified database of places claim 1 , a database of descriptions of activities commonly applicable to venue categories claim 1 , calendar data claim 1 , and ...

Open information extraction

A system for identifying relational tuples is provided. The system extracts a relation phrase from a sentence by identifying a verb in the sentence and then identifying a relation phrase of the sentence as a phrase in the sentence starting with the identified verb that satisfies both a syntactic constraint and a lexical constraint. The system also identifies arguments for a relation phrase. To extract the arguments, the system applies a left-argument-left-bound classifier, a left-argument-right-bound classifier, and a right-argument-right-bound classifier to identify a left argument and right argument for the relation phrase such that the left argument, the relation phrase, and the right argument form a relational tuple.

APPARATUS, METHOD AND COMPUTER READABLE MEDIUM FOR A MULTIFUNCTIONAL INTERACTIVE DICTIONARY DATABASE FOR REFERENCING POLYSEMOUS SYMBOL SEQUENCES

An embodiment of the present application is directed to an apparatus, method, and or computer readable medium for effectively storing an interactive dictionary database in a memory. The interactive dictionary database includes a plurality of symbol sequences, each of the plurality of symbol sequences including at least one polysemous symbol and each of the plurality of symbol sequences being stored in association with at least one word, sentence, phoneme, message, letter, number, morpheme, command and/or phrase. The method includes providing, in the interactive dictionary database, information useable to assign at least a subset of the plurality of symbol sequences at least one of an active and an inactive status. 1. A method , comprising:storing an interactive dictionary database in a memory, the interactive dictionary database including a plurality of symbol sequences, each of the plurality of symbol sequences including at least one polysemous symbol and each of the plurality of symbol sequences being stored in association with at least one word, sentence, phoneme, message, letter, number, morpheme, command and/or phrase; and providing, in the interactive dictionary database, information useable to assign at least a subset of the plurality of symbol sequences at least one of an active and an inactive status.2. The method of claim 1 , wherein at least portions of the interactive dictionary database are displayable to a user claim 1 , and wherein the information is displayable to the user in a selectable manner.3. The method of claim 1 , wherein the interactive dictionary database is searchable.4. The method of claim 1 , wherein when an inactive status is assigned claim 1 , a corresponding symbol sequence is rendered unselectable by a user.5. The method of claim 1 , wherein the interactive dictionary database includes a plurality of rationales claim 1 , each respectively relating a respective one of the plurality of symbol sequences to a respective associated at ...

VISUAL ANALYSIS OF PHRASE EXTRACTION FROM A CONTENT STREAM

A system may include an extraction engine to extract candidate phrases from a content stream, and an analysis engine to assign the candidate phrases visual cues and display the visual cues to an operator. 1. A method comprising:extracting candidate phrases from a content stream;calculating an importance value of the extracted candidate phrases based on frequency of the extracted phrases in the content stream;thresholding the extracted candidate phases based on the calculated importance value;calculating an average sentiment value for the thresholded candidate phrases using term-association;assigning a visual cue to the thresholded candidate phrases; andgraphically displaying the visual cue representative of the thresholded candidate phrases in statistical clusters.2. The method of claim 1 , wherein calculating an importance value of the extracted candidate phrases comprises determining the temporal proximity of the extracted candidate phrases to an event or predetermined period.3. The method of claim 1 , wherein assigning the thresholded candidate phrases a visual cue further comprises using color and color intensity.4. The method of claim 1 , wherein assigning the thresholded candidate phrases a visual cue further comprises using the calculated importance to determine at least one property of the visual cue.5. The method of claim 1 , wherein assigning the thresholded candidate phrases a visual cue further comprises using the calculated average sentiment to determine at least one property of the visual cue.6. The method of claim 1 , wherein calculating the average sentiment further comprises altering the calculated importance of the extracted candidate phrases.7. The method of claim 6 , wherein altering the calculated importance comprises increasing the importance of the extracted candidate phrases in response to a negative average sentiment in the thresholded candidate phrases.8. The method of claim 6 , wherein altering the calculated importance of the extracted ...

EXTRACTING RELATED CONCEPTS FROM A CONTENT STREAM USING TEMPORAL DISTRIBUTION

A system may include an analysis engine to generate a set of candidate phrases from a content stream based on the temporal resolution, the interestingness, and/or the correlation of the candidate phrases. 1. A method comprisingextracting candidate phrases from a content stream;thresholding the candidate phrases below a minimum frequency for each candidate phrase;determining a temporal distribution of the candidate phrases; 'wherein determining interestingness of the candidate phrases comprises statistically analyzing the temporal distribution of a candidate phrase; and', 'determining interestingness of the candidate phrases,'}displaying the candidate phrases.2. The method of claim 1 , wherein determining the temporal distribution comprises separating the candidate phrases into groups based on a time stamp.3. The method of claim 2 , wherein separating the candidate phrases into groups claim 2 , comprises groups having a uniform number of candidate phrases.4. The method of claim 1 , wherein determining interestingness of each candidate phrase comprises:scaling each candidate phrase frequency across the temporal distribution and computing the average of those scaled values or,determining a coefficient of variation of the temporal distribution for each candidate phrase.5. The method of claim 1 , further comprising simplifying the candidate phrases by removing excess words after determining interestingness of the candidate phrases.6. The method of claim 1 , further comprising:determining the correlation of the candidate phrases; andmerging the correlated candidate phrases.7. The method of claim 6 , further comprising removing merged candidate phrases below a predetermined threshold.8. The method of claim 1 , wherein displaying the candidate phrases further comprises providing the candidate phrases to an operator by an interface having at least one control for at least one metric of the candidate phrases.9. The method of claim 8 , further comprising determining the ...

Applying Service Levels to Transcripts

Speech is transcribed to produce a draft transcript of the speech. Portions of the transcript having a high priority are identified. For example, particular sections of the transcript may be identified as high-priority sections. As another example, portions of the transcript requiring human verification may be identified as high-priority sections. High-priority portions of the transcript are verified at a first time, without verifying other portions of the transcript. Such other portions may or may not be verified at a later time. Limiting verification, either initially or entirely, to high-priority portions of the transcript limits the time required to perform such verification, thereby making it feasible to verify the most important portions of the transcript at an early stage without introducing an undue delay into the transcription process. Verifying the other portions of the transcript later ensures that early verification of the high-priority portions does not sacrifice overall verification accuracy. 1(A) identifying a first semantic meaning of a first portion of a first transcript of speech;(B) assigning a first service level to the first portion of the transcript based on the first semantic meaning;(C) identifying a second semantic meaning of a second portion of the first transcript;(D) assigning a second service level to the second portion of the transcript based on the second semantic meaning; and(E) at a processor, verifying the transcript in accordance with the first and second service levels.. A computer-implemented method comprising: This application is related to U.S. patent application Ser. No. 10/923,517, filed on Aug. 20, 2004, entitled “Automated Extraction of Semantic Content and Generation of a Structured Document from Speech,” now U.S. Pat. No. 7,584,103, which is hereby incorporated by reference herein.It is desirable in many contexts to generate a structured textual document based on human speech. In the legal profession, for example, ...

INFORMATION PROCESSING SYSTEM, INFORMATION PROCESSING APPARATUS AND METHOD FOR UPDATING DATA

An information processing system comprises a plurality of information processing apparatus and a dictionary server (server). Each of the scanners includes a local storage device, a determination module and a local update module. The server includes a master storage device, a master update module and a master transmitting module. The determination module determines the commodity category to which a commodity belongs by comparing the feature amount extracted from the image showing the appearance of the commodity with the feature amount described in a local dictionary data stored in the local storage device. The master update module updates a master dictionary data stored in the master storage device. The master transmitting module transmits the master dictionary data updated by the master update module to the scanners. The local update module updates the local dictionary data according to the master dictionary data transmitted by the transmitting module. 2. The information processing system according to claim 1 , whereinthe information processing apparatus further includes:a learning module configured to update the local dictionary data, using the feature amount extracted from the image, anda local transmitting module configured to transmit the local dictionary data updated by the learning module to the dictionary server, andwhereinthe master update module updates the master dictionary data, using the local dictionary data transmitted by the local transmitting module.3. The information processing system according to claim 2 , whereinthe master dictionary data and the local dictionary data include a plurality of data records in which a commodity code for identifying the commodity categories is associated with the feature amount,the master update module updates the master dictionary table by updating the data records,the master transmitting module transmits the data record updated by the master update module to the information processing apparatus andthe local update ...

Information management apparatus, data processing method and computer program

An information management apparatus receives position data from each terminal device. The position data contains position measurement data showing its positions at multiple clock times and its user identification data. The apparatus creates action history for every user based on the position data, and abstracts the position data in the action history. The apparatus includes an abstracting section and a testing section. The abstracting section abstracts arbitrary position data in the action history of a certain user. The testing section extracts another action history of another user. The other action history includes position data of the other user which shows a position same as or included in a position of the abstracted position data of the certain user, but excludes position data of the other user which shows positions same as remaining position of the certain user. The testing section outputs the abstracted position data as anonymity data.

SYSTEMS AND METHODS FOR STORAGE OF DECLARATIVE KNOWLEDGE ACCESSIBLE BY NATURAL LANGUAGE IN A COMPUTER CAPABLE OF APPROPRIATELY RESPONDING

Systems and methods for natural language communication with a computer. A builder module constructs tables in a database by generating concept symbols for each language element in an expression to form a string of ordered concept symbols, and, in a series of rounds, combining pairs of concept symbols into newly generated concept symbols to form shortened strings of concept symbols until a single concept symbol remains. Each generated concept symbol is stored in a row in the database. A parser module may then utilize the database to parse an input expression by identifying rows in the database that correspond to language elements of the input expression to generate a string of concept symbols, and, in a series of rounds, replacing pairs of concept symbols in the string of concept symbols by identifying rows in the database that comprise the pairs of concept symbols until a single concept symbol remains. 1. A system for parsing text in a natural language communication with a computer , the system comprising:at least one hardware processor;a database; for each language element in the string of language elements of the model expression, including at least one punctuation mark, generating a concept symbol that represents a meaning of the language element, to form a string of concept symbols in a same order as the string of language elements,', 'in a series of one or more rounds, combining one or more pairs of concept symbols in the string of concept symbols into a newly generated concept symbol that represents a meaning of the combined pair of concept symbols, to form one or more shortened strings of concept symbols until a single concept symbol remains that represents a meaning of the entire model expression, and,', 'for each generated concept symbol, storing the concept symbol in its own row in the database; and, 'a builder module, interfaced with the database, that, when executed by the at least one hardware processor, constructs at least one table that represents ...

METHOD AND SYSTEM FOR DISCOVERING SUSPICIOUS ACCOUNT GROUPS

In one exemplary embodiment, a system for discovering suspicious account groups establishes a language model according to the post contents from each account of a first group of accounts during a first time interval, to describe the speech of the account, and compares the similarity among a plurality of language models of the first group of accounts to cluster the first group of accounts; and for a plurality of newly added data during a second time interval, discovers near-synonyms of at least a monitored vocabulary set, and updates the near-synonyms to a plurality of language models of a second group of accounts. The system further integrates the first and the second groups of accounts, and re-clusters an integrated group of accounts. 1. A method for discovering suspicious account groups , comprising:under a control of at least one hardware processor,establishing a language model according to one or more post contents from each account of a first group of accounts during a first time interval, to describe a linguistic fashion of the account, and comparing a similarity among a first group of language models of the first group of accounts to cluster the first group of accounts; andfor a plurality of newly added data during a second time interval, discovering one or more near-synonyms of at least one monitored vocabulary set, and updating the one or more near-synonyms to a second group of language models of a second group of accounts, further integrating the first and the second groups of accounts, and re-clustering an integrated group of accounts.2. The method as claimed in claim 1 , said method further includes:for the plurality of newly added data during each updated time interval of a plurality of updated time intervals, discovering a plurality of near-synonyms of at least a monitored vocabulary set, and updates or reconstructs said plurality of near-synonyms to a plurality of language models of a different group of accounts, and further integrating said different ...

AUTOMATIC SENTENCE EVALUATION DEVICE USING SHALLOW PARSER TO AUTOMATICALLY EVALUATE SENTENCE, AND ERROR DETECTION APPARATUS AND METHOD OF THE SAME

An automatic sentence evaluating device using a shallow parser. A simple grammatical error and an error in sentence structure are detected by generating a string of parts of speech using n-gram for a composed input sentence and parsing the generated string of parts of speech on the basis of a rule (shallow parsing) defined according to a connective relationship between adjacent parts of speech, and a corrected draft is proposed for the detected errors to thereby increase accuracy of sentence evaluation, and an error detection apparatus and a method for the same. 1. An apparatus for automatically evaluating sentences , the apparatus comprising:an input sentence divider configured to divide a composed input sentence into morphemes which are the smallest units of a sentence;a part-of-speech tagging section configured to tag parts of speech to the divided morphemes;a syntax analyzer configured to analyze a syntax structure of the sentence based on the parts of speech and to output a syntax tree as an analysis result;a sentence evaluating section configured to evaluate whether the sentence is grammatically correct by using the syntax tree output by the syntax analyzer; andan error detector configured to generate a part-of-speech string by using an n-gram with respect to each part of speech tagged by the part-of-speech tagging section, to analyze the generated part-of-speech string based on a regular grammar rule and a context free grammar rule which are defined in accordance with connection relationship between the parts of speech adjacent to each other to detect an error of syntax analysis, and to provide a corrected draft for the detected error.2. An error detection apparatus using a shallow parser for automatically evaluating composition of a sentence , the apparatus comprising:a part-of-speech string generator configured to generate a part-of-speech string by a predetermined window unit by using an n-gram with respect to each of parts of speech tagged to an input ...

METHOD AND APPARATUS FOR OPTIMIZING HANDWRITING INPUT METHOD

Embodiments of the present invention provide a method and an apparatus for optimizing a handwriting input method, A position in which a cursor is located and a first content and a second content of the position in which the cursor is located are obtained. The first content is a character related to the foregoing text of the position in which the cursor is located and the second content is a character related to the following text of the position in which the cursor is located. A candidate character is determined according to the first content and/or the second content, an input method dictionary, and a character handwritten and input by a user and the candidate character is displayed. 115-. (canceled)16. A handwriting input method , comprising:obtaining a position at which a cursor is located;obtaining a first content and a second content of the position at which the cursor is located, wherein the first content is a character related to foregoing text, if any, of the position at which the cursor is located and the second content is a character related to the following text, if any, of the position in which the cursor is located;determining a candidate character according to the first content and/or the second content, an input method dictionary, and a character handwritten and input by a user; anddisplaying the candidate character.17. The method according to claim 16 , wherein obtaining the first content and the second content of the position at which the cursor is located comprises:using a method for registering an application programming interface API hook to obtain the first content and the second content of the position at which the cursor is located.18. The method according to claim 16 , wherein if the first content is empty and the second content is not empty claim 16 , wherein and determining the candidate character comprises determining the candidate character according to the second content claim 16 , the input method dictionary claim 16 , and the input ...

System and Method of Spoken Language Understanding in Human Computer Dialogs

A system and method are disclosed that improve automatic speech recognition in a spoken dialog system. The method comprises partitioning speech recognizer output into self-contained clauses, identifying a dialog act in each of the self-contained clauses, qualifying dialog acts by identifying a current domain object and/or a current domain action, and determining whether further qualification is possible for the current domain object and/or current domain action. If further qualification is possible, then the method comprises identifying another domain action and/or another domain object associated with the current domain object and/or current domain action, reassigning the another domain action and/or another domain object as the current domain action and/or current domain object and then recursively qualifying the new current domain action and/or current object. This process continues until nothing is left to qualify. 1. A method comprising:identifying, in a domain-independent manner, a dialog act for an independent clause of a speech recognizer output;identifying, in a domain-dependent manner, an object within the independent clause; andrecursively generating, via a processor, for each sub-independent clause within the independent clause, a semantic representation using the dialog act and the object of the independent clause.2. The method of claim 1 , wherein the semantic representation is used by a dialog manager in a spoken dialog system to determine a response to a user input.3. The method of claim 1 , further comprising:identifying, in the domain-dependent manner, an action within each of the independent clause, wherein recursively generating the semantic representation further comprises using the action.4. The method of claim 1 , wherein while recursively generating the semantic representation claim 1 , additional objects are extracted from the independent clause.5. The method of claim 1 , wherein identifying the object comprises using a domain specific ...

RECIPIENT BASED CUSTOMIZATION CARD GROUPS

A method for creating and sending customized cards to members on a list can include steps for designing a first card, creating a member list and dividing the member list into at least two groups. The first card can initially be associated with all members included in the member list. A second card can be designed and can be based, at least in part, on the first card. The second card can be associated with at least one member group. A data file can be created that can include the first and second card designs and association information regarding the card designs and the member groups. 1. An electronic device comprising:a memory circuit configured to store a plurality of commands;a user interface; and the processor circuit is configured to create a printer ready document associated to a member list stored in the memory circuit;', 'the processor circuit is configured to form a plurality of member groups from the member list according to the user command, and store the plurality of groups in the memory circuit;', 'the processor circuit is configured to provide common features to the printer ready document according to the member groups formed from the member list;', 'and the processor circuit is configured to provide a second plurality of common features to the printer ready document according to a theme., 'a processor circuit configured to execute the plurality of commands stored in the memory circuit and a user command provided by a user via the user interface; wherein'}2. The electronic device of further comprising a display configured to show an editable version of the printer ready document according to the user command.3. The electronic device of wherein the display is configured to show a plurality of editable versions of the printer ready document according to the plurality of member groups.4. The electronic device of wherein the display is configured to show a tree diagram including a theme layer claim 2 , a group layer claim 2 , and a recipient layer; the ...

Natural Language Image Spatial and Tonal Localization

Natural language image spatial and tonal localization techniques are described. In one or more implementations, a natural language input is processed to determine spatial and tonal localization of one or more image editing operations specified by the natural language input. Performance is initiated of the one or more image editing operations on image data using the determined spatial and tonal localization. 1. A method comprising:processing a natural language input to determine spatial and tonal localization of one or more image editing operations specified by the natural language input; andinitiating performance of the one or more image editing operations on image data using the determined spatial and tonal localization.2. A method as described in claim 1 , wherein the performance of the one or more image editing operations includes forming one or more localization masks.3. A method as described in claim 2 , wherein the one or more localization masks are a combination of a spatial localization mask with a tonal region localization mask.4. A method as described in claim 3 , wherein the spatial localization mask has spatial components that define a shape to convey a local operation claim 3 , a spatial gradient function claim 3 , or a border function.5. A method as described in claim 3 , wherein the tonal region localization mask has components configured to modulate tonal shapes.6. A method as described in claim 2 , wherein at least one said localization mask is formed for each filter used to perform a respective said image editing operation.7. A method as described in claim 2 , wherein a single said localization mask is formed for a composite filter operation involved in performance of a plurality of said image editing operations.8. A method as described in claim 1 , wherein the spatial localization of the natural language input is specified using at least two directions.9. A method as described in claim 8 , wherein the at least two directions include top claim 8 , ...

EXAMPLE-BASED ERROR DETECTION SYSTEM FOR AUTOMATIC EVALUATION OF WRITING, METHOD FOR SAME, AND ERROR DETECTION APPARATUS FOR SAME

An error detection system for automatically evaluating writing includes: an example construction apparatus to collect example sentences including various literary styles, to break up the collected example sentences in units of morphemes, and to construct the example sentences in an example-based index database (DB); and an error detection apparatus to break up an input sentence in units of morphemes, to generate one or more morpheme sequences bound in arbitrary window sizes based on one or more of morphemes of the broken-up input sentence, to search the example-based index DB for each of the generated morpheme sequences, and to detect an error according to a frequency at which said each morpheme is arranged in a corresponding morpheme sequence among morpheme sequences searched for through the example-based index DB. 1. An error detection system for automatically evaluating writing , the system comprising: to collect example sentences including various literary styles,', 'to break up the collected example sentences in units of morphemes, and', 'to construct the example sentences in an example-based index database (DB); and, 'an example construction apparatus configured'} to break up an input sentence in units of morphemes,', 'to generate one or more morpheme sequences bound in arbitrary window sizes based on one or more of the morphemes of the broken-up input sentence,', 'to search the example-based index DB for each of the generated morpheme sequences, and', 'to detect an error according to a frequency at which each morpheme of the broken-up input sentence is arranged in a corresponding morpheme sequence among morpheme sequences searched for through the example-based index DB., 'an error detection apparatus configured'}2. An error detection apparatus , comprising:an input sentence break-up unit configured to break up an input sentence in units of morphemes;a part-of-speech tagging unit configured to tag a part of speech to each of the morphemes of the broken up ...

EMOTION IDENTIFICATION SYSTEM AND METHOD

A system and method for identifying emotion in text that connotes authentic human expression, and training an engine that produces emotional analysis at various levels of granularity and numerical distribution across a set of emotions at each level of granularity. The method may include classifying textual data as emotional textual data or non-emotional textual data, and determining duration of an emotional state. 1. A method of classifying textual data as emotional textual data or non-emotional textual data comprising:providing, with a processor, a database of data indicators that each define emotional content of textual data;receiving, at a processor, first textual data authored by an individual;processing, with a processor, the first textual data to produce a first data indicator defining emotional content of the first textual data;inputting, with a processor, the first data indicator into an emotion similarity model and the data indicators of the database into the emotion similarity model to determine at least one similarity between the first data indicator and the data indicators of the database; andclassifying, with a processor, the first textual data as emotional textual data or non-emotional textual data based on the at least one similarity.2. The method of claim 1 , wherein the textual data of the database has been authored by at least one individual on a webpage of an online forum system.3. The method of claim 2 , wherein the textual data of the database has been tagged with at least one tag by an author of the textual data claim 2 , the at least one tag being associated with at least one emotion and associating at least a portion of the textual data of the database with the at least one emotion.4. The method of claim 1 , wherein the first data indicator is produced using textual analysis selected from a group consisting of latent semantic analysis claim 1 , and positive pointwise mutual information.5. The method of claim 1 , wherein the emotion similarity ...

System and Method for a Digital Therapeutic Delivery of Generalized Clinician Tips (GCT)

This invention relates generally to the field of electronic communications and the transmittance of such communications. More specifically, the invention discloses a new and useful method for delivering a therapeutic through an eco-system of digital content based on a user-mapped EMS. The method comprises: receiving a text input comprising message content from an electronic computing device associated with a user; parsing the message content comprised in the text input for emotionally-charged language; assigning a sentiment value, based on the emotionally-charged language, from a dynamic sentiment value spectrum to the text input; and, based on the sentiment value, imposing a sentiment vector, corresponding to the assigned sentiment value, to the text input, the imposed sentiment vector rendering a sensory effect on the message content designed to convey a corresponding sentiment. 1. A method for delivering generalized clinician tips (GCT) , specific to a users emotional or mental state (EMS) , said method comprising the steps of:fast-capturing of at least one EMS for the user based on at least one of a user-plotted point on at least one of a displayed mood map or mood wheel or user-selected from a menu, said EMS indicating an assessment of at least one of a feeling, sensation, mood, mental state, emotional condition, or physical status of the user;delivering said GCT to at least one of a user's device (mobile device, wearable, smart watch, tablet, desktop, laptop, headphones, speaker, or smart speaker) or home entertainment system in communication with at least one of the user's device or a voice-activated Internet-of-Things (IoT) hub; andwherein the GCT is selected from a store of EMS-specific GCT and is at least one of a suggestion or recommendation for the user to perform a task with clinical-consensus benefits to address at least one of the EMS.2. The method of claim 1 , wherein the EMS is defined based on at least one of a stored or previous user-plotted or ...

SYSTEM AND METHOD FOR SEMANTIC PROCESSING OF NATURAL LANGUAGE COMMANDS

A system, method and computer-readable storage devices are for processing natural language commands, such as commands to a robotic arm, using a Tag & Parse approach to semantic parsing. The system first assigns semantic tags to each word in a sentence and then parses the tag sequence into a semantic tree. The system can use statistical approach for tagging, parsing, and reference resolution. Each stage can produce multiple hypotheses, which are re-ranked using spatial validation. Then the system selects a most likely hypothesis after spatial validation, and generates or outputs a command. In the case of a robotic arm, the command is output in Robot Control Language (RCL). 1. A method comprising:assigning, via a sequence tagger, a part of speech, a semantic tag and a label to each word in a natural language command addressed to a robotic arm to yield a tagged natural language command;semantically parsing, via a processor and a semantic parsor, the tagged natural language command to yield a parsed natural language command, wherein a data set used to train the semantic parsor does not include any tag from which the sequence tagger selects for assigning the semantic tag; andmoving the robotic arm according to a spatial validation of a physical context of the natural language command when applied to the robotic arm.2. The method of claim 1 , further comprising:receiving the natural language command.3. The method of claim 1 , further comprising:identifying a command type for the parsed natural language command and wherein moving the robotic arm is according to the command type.4. The method of claim 1 , wherein the semantic tag identifies entity types and event types in the natural language command.5. The method of claim 3 , further comprising claim 3 , after identifying the command type:performing the spatial validation, based on the command type, for the physical context of the natural language command when applied to the robotic arm; andif the spatial validation ...

INCREMENTAL MULTI-WORD RECOGNITION

In one example, a computing device includes at least one processor that is operatively coupled to a presence-sensitive display and a gesture module operable by the at least one processor. The gesture module may be operable by the at least one processor to output, for display at the presence-sensitive display, a graphical keyboard comprising a plurality of keys and receive an indication of a continuous gesture detected at the presence-sensitive display, the continuous gesture to select a group of keys of the plurality of keys. The gesture module may be further operable to determine, in response to receiving the indication of the continuous gesture and based at least in part on the group of keys of the plurality of keys, a candidate phrase comprising a group of candidate words. 120-. (canceled)21. A method comprising:outputting, by a computing device, for display at a display device, a graphical user interface including a committed-text region, a text-suggestion region, and a graphical keyboard comprising a plurality of keys;determining, by the computing device, a first single-touch gesture detected at a first region of a presence-sensitive input device that corresponds to a first location of the display device at which a first key of the plurality of keys is displayed and a second single-touch gesture detected at a second region of the presence-sensitive input device that corresponds to a second location of the display device at which a second key of the plurality of keys is displayed, wherein a first character is associated with the first key and a second character is associated with the second key;determining, by the computing device, based on the first single-touch gesture and the second single-touch gesture, a first candidate word of a candidate phrase and a second candidate word of the candidate phrase, wherein the first candidate word comprises the first character and the second candidate word comprises the second character;outputting, by the computing device, ...

Systems and Methods for Adaptively Presenting a Keyboard on a Touch- Sensitive Display

Systems and methods for adaptively presenting a keyboard on a touch-sensitive display are disclosed herein. In one aspect, a method includes: monitoring typing inputs received from a user at a touch-sensitive display of an electronic device. The method also includes: determining whether the typing inputs are converging towards a midpoint of the touch-sensitive display or diverging away from the midpoint of the touch-sensitive display. In accordance with a determination that the typing inputs are converging towards the midpoint of the touch-sensitive display, the method includes: providing a first feedback to the user to indicate that the typing inputs are converging. In accordance with a determination that the typing inputs are diverging away from the midpoint of the touch-sensitive display, the method includes: providing a second feedback to the user to indicate that the typing inputs are diverging. 1. A non-transitory computer-readable storage medium storing one or more programs configured for execution by one or more processors of an electronic device with a touch-sensitive display , the one or more programs comprising instructions for:monitoring typing inputs received from a user at the touch-sensitive display;determining whether the typing inputs are converging towards a midpoint of the touch-sensitive display or diverging away from the midpoint of the touch-sensitive display;in accordance with a determination that the typing inputs are converging towards the midpoint of the touch-sensitive display, providing a first feedback to the user to indicate that the typing inputs are converging; andin accordance with a determination that the typing inputs are diverging away from the midpoint of the touch-sensitive display, providing a second feedback to the user to indicate that the typing inputs are diverging.2. The non-transitory computer-readable storage medium of claim 1 , wherein the typing inputs are received at a virtual keyboard with a plurality of keys ...

Process and system for automatic generation of functional architecture documents and software design and analysis specification documents from natural language

The present invention is a computer-implemented system and method for automatic generation of Functional Architecture, business, analysis and software design documents based on phrases expressed in natural language. 1130. A computer-implemented method for generating Functional Architecture documents from phrases expressed in natural language that describe a case , which are stored in a database memory , characterized by the following stages:{'b': 120', '130, 'A. using an Input/Output Device to upload the MAS Metamodel into the Database Memory .'}{'b': 121', '120', '130, 'B. using the Language User Interface (of the Input/Output Device ) to input the eligible languages, the grammatical and syntactic features of each eligible language and storing those data in the Database Memory ;'}{'b': 122', '120', '130, 'C. using the Case User Interface (of the display device ) to input the description of “the case” as text in one of the natural languages selected from the list of eligible languages from Stage B and then storing them in the Database Memory ;'}{'b': 122', '120', '130, 'D. identifying the simple sentences of the case that correspond to the steps from Stage C and using the Case User Interface (of the Input/Output Device ) to upload them so they can then be stored in the Database Memory ;'}{'b': 150', '151', '130, 'E. automatically identifying the functional components based on the simple sentences from Stage D, by means of a Processor configured as an Automatic Sentence Analyzer and storing them in the Database Memory ;'}{'b': 150', '153, 'F. automatically generating the functional architecture documents based on the functional components from Stage E, by means of a Processor configured as a Document Generator , using the graphical notation defined specifically for this type of Document.'}2. The method in accordance with claim 1 , characterized in that stage A consists of the following substages:{'b': 1', '130', '150, 'A. Storing the MAS Metamodel in the Database ...

TASK MANAGEMENT BASED ON SEMANTIC ANALYSIS

Example implementations relate to managing tasks for a user. In example implementations, semantic tags may be detected in electronic documents that are accessed by a user. Models of the accessed electronic documents may be generated based on semantic analysis. A priority of a task for the user may be determined based on the detected semantic tags and the generated models. 1. A method for task management , the method comprising:detecting semantic tags in electronic documents accessed by a first user;generating, based on semantic analysis, models of the electronic documents accessed by the first user;inferring, based on the generated models, user collaboration patterns of the first user; anddetermining, based on the detected semantic tags and the inferred user collaboration patterns, a priority of a task for the first user, wherein the task is associated with one of the accessed electronic documents.2. The method of claim 1 , further comprising receiving a user request for task management services.3. The method of claim 2 , wherein the user request is received via a text message.4. The method of claim 2 , wherein:the user request specifies a task type to manage; andsemantic tags are detected in, and models are generated of, accessed electronic documents associated with the specified task type.5. The method of claim 1 , wherein determining the priority of the task comprises ranking a plurality of tasks in a task list claim 1 , the method further comprising allowing the first user to modify the ranking of the plurality of tasks.6. The method of claim 1 , wherein the one of the accessed electronic documents is initially accessed on a first user device claim 1 , the method further comprising:generating a first electronic calendar appointment, in an electronic calendar associated with the first user, for a time when the task is to be performed; anddisplaying the one of the accessed electronic documents on a second user device during the time when the task is to be ...

MONITORING DEVICE AND INPUT OPERATION SUPPORT DEVICE

A monitoring device included a processor. The processor is configured to monitor a state of a first device. The processor is configured to receive an operation command input partway. The operation command is for operating the first device. The processor is configured to select, depending on the state of the first device, a prioritized completion candidate from among a plurality of completion candidates likely to be included in the operation command. The prioritized completion candidate is to be displayed in a display unit in priority to other completion candidates among the plurality of completion candidates. The processor is configured to output information regarding the prioritized completion candidate. 1. A monitoring device , comprising: monitor a state of a first device,', 'receive an operation command input partway, the operation command being for operating the first device,', 'select, depending on the state of the first device, a prioritized completion candidate from among a plurality of completion candidates likely to be included in the operation command, the prioritized completion candidate being to be displayed in a display unit in priority to other completion candidates among the plurality of completion candidates, and', 'output information regarding the prioritized completion candidate., 'a processor configured to'}2. The monitoring device according to claim 1 , wherein monitor states of parts included in the first device for respective part types of the parts, and', 'select depending on an operation type of the operation command and the monitored states, when the operation type has been input and a subsequent input of a part type of a target part is not yet performed, the prioritized completion candidate from among first part types likely to be input subsequent to the operation type., 'the processor is configured to'}3. The monitoring device according to claim 2 , wherein 'select the prioritized completion candidate in accordance with a completion rule ...

CORRECTIONS FOR NATURAL LANGUAGE PROCESSING

Technology is disclosed for correcting items containing natural language words that match qualified corrections. Qualified corrections can be identified from language snippet sets, which can include, for example, a post to a social media website and one or more updates to that post. Qualified corrections can be word pairs identified in one of these language snippet sets by aligning words between the language snippets according to a minimum word edit distance and computing that the word edit distance is below a first threshold. Based on this word alignment, word pairs can be selected and analyzed to identify qualified corrections as the word pairs that have a minimum character edit distance below a second threshold. In some cases, such as where both words in the qualified correction word pair are known words, a context can be associated with the qualified correction to control when the qualified correction should be applied. 1. A method for generating a natural language correction module , comprising:receiving one or more sets of language snippets, each received set of language snippets comprising a sequence of an initial language snippet and one or more updates to either the initial language snippet or a previous language snippet in the sequence; computing that a minimum word edit distance between at least two of the language snippets of the selected set is below a word difference threshold;', 'creating word pairs by aligning words between the at least two of the language snippets of the selected set according to the minimum word edit distance; and', 'identifying qualified corrections as the created word pairs that have a minimum character edit distance that is below a character difference threshold; and, 'for at least one selected set of the one or more sets of language snippets, identifying at least one qualified correction byincorporating the identified qualified corrections into the natural language correction module.2. The method of further comprising claim 1 , ...

MACHINE-TRANSLATION BASED CORRECTIONS

Technology is disclosed for building correction models that correct natural language snippets. Correction models can include rules comprising pairs of word sequences identified from viable correction snippet pairs, where a first sequence of words in the pair should be replaced with a second sequence of words in the pair. Viable correction snippet pairs can be identified from among pairs of language snippets, such as a post to a social media website and a subsequent update to that post. Viable corrections can be the snippet pairs that both have no more unaligned words than a word alignment threshold and have no aligned word pair with a character edit difference above an edit distance threshold. In some implementations, word alignments can be found by aligning all the characters between a pair of language snippets, and identifying aligned words as those that have at least one aligned letter in common. 1. A method for generating a natural language correction model comprising:obtaining one or more language snippet pairs comprising an initial language snippet and a subsequent language snippet; aligning words between the initial language snippet and the subsequent language snippet of the selected language snippet pair to obtain an aligned version of the selected language snippet pair;', 'computing a word alignment score for the aligned version of the selected language snippet pair;', 'determining that the computed word alignment score for the aligned version of the selected language snippet pair is below a word alignment threshold value;', 'computing a character edit distance for one or more of the aligned words within the aligned version of the selected language snippet pair; and', 'determining that each computed character edit distance for the one or more of the aligned words within the selected language snippet pair is below a character distance threshold value;, 'for at least one selected language snippet pair of the one or more language snippet pairs, identifying the ...