Настройки

Укажите год
-

Небесная энциклопедия

Космические корабли и станции, автоматические КА и методы их проектирования, бортовые комплексы управления, системы и средства жизнеобеспечения, особенности технологии производства ракетно-космических систем

Подробнее
-

Мониторинг СМИ

Мониторинг СМИ и социальных сетей. Сканирование интернета, новостных сайтов, специализированных контентных площадок на базе мессенджеров. Гибкие настройки фильтров и первоначальных источников.

Подробнее

Форма поиска

Поддерживает ввод нескольких поисковых фраз (по одной на строку). При поиске обеспечивает поддержку морфологии русского и английского языка
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Укажите год
Укажите год
Применить Всего найдено 1410. Отображено 100.
04-07-2013 дата публикации

METHOD FOR SHARING AND SEARCHING PLAYLISTS

Номер: US20130173656A1
Автор: Baird Daniel, Brown David E., III Alexander Stephen, Korman Adam, Ramachandra Poorna Chandra Gowda Bannikuppe, Sahay Siddhartha S., Schiro Pierre, Spiegelman Michael, Stelzmuller Christa Maria, Suresh Bipin, Sutton Lori Ann, Toth
Принадлежит: Yahoo! Inc.

The present disclosure provides a method for making a playlist available to the public. In another embodiment, the present disclosure provides a method for creating a playlist comprising user-defined descriptor information. In another embodiment, the present disclosure provides a method for searching for such public playlists. 146-. (canceled)47. A method , comprising:receiving an indication of a desire to identify a playlist at a computing platform, wherein the indication includes one or more search criteria; andsearching a playlist storage utilizing a processor of the computing platform to identify a desired playlist result set comprising one or more user-published playlists, the one or more user-published playlists individually comprising user-provided text describing one or more of a user's understanding, perception, and/or feelings toward the playlist, wherein said searching the playlist storage comprises searching the user-provided text according to the one or more search criteria.48. The method of claim 47 , wherein the one or more search criteria comprise a mood associated with the desired playlist result.49. The method of claim 47 , wherein the one or more search criteria comprise an event associated with the desired playlist result.50. The method of claim 47 , wherein the one or more search criteria comprise a situation associated with the desired playlist result.51. The method of claim 47 , wherein said receiving the indication of the desire to identify a playlist comprises receiving the indication at a server computing device.52. The method of claim 47 , wherein said receiving the indication of the desire to identify a playlist comprises receiving the indication from a user computing device.53. The method of claim 52 , further comprising transmitting the desired playlist result to the user computing device at least in part in response to said searching the playlist storage.54. An apparatus claim 52 , comprising:means for receiving an indication of a ...

Подробнее
Номер записи: 1
03-10-2013 дата публикации

USING OBSERVATIONS OF A PERSON TO DETERMINE IF DATA CORRESPONDS TO THE PERSON

Номер: US20130262477A1
Автор: III Richard Earle, Monaco Peter, Seeger
Принадлежит: XOBNI CORPORATION

Systems and methods to store data obtained from observations and to determine a correspondence of certain data to a particular person. In one approach, a method includes: receiving or making a plurality of observations for a person (e.g., data extracted from e-mails sent to the person); storing the observations in a repository (e.g., a database on a server); and determining whether data in a first observation of the observations corresponds to the person, wherein the determining is based on the plurality of observations. 1. A method , comprising:receiving or making, via a computing device, a plurality of observations for a person;storing the observations in a repository; anddetermining, via a computing device, whether data in a first observation of the observations corresponds to the person, the determining based on the plurality of observations.2. The method of claim 1 , wherein the person is associated with an address claim 1 , and each of the plurality of observations is a message from the person to a respective recipient of a plurality of recipients.3. The method of claim 2 , further comprising storing profile data for each of the plurality of recipients as a plurality of person profiles claim 2 , and wherein the determining comprises calculating a confidence based on the observations stored in the repository.4. The method of claim 3 , further comprising determining whether the confidence is equal to or greater than a threshold value.5. The method of claim 3 , further comprising receiving claim 3 , from another computing device claim 3 , a query requesting at least one confidence for ranking a list of data items to be presented on a display for one of the plurality of recipients.6. The method of claim 2 , further comprising using a result from the determining for caller identification.7. A non-transitory computer-storage medium storing instructions configured to instruct a computing apparatus to:receive or make, via a computer, a plurality of observations for a ...

Подробнее
Номер записи: 2
21-11-2013 дата публикации

Method and system relating to sentiment analysis of electronic content

Номер: US20130311485A1
Автор: Shahzad KHAN
Принадлежит: WHYZ Tech Ltd

Users receive information which must be filtered, processed, analysed, reviewed, consolidated and distributed or acted upon. Prior art tools automatically processing content to assign sentiment to the content are ineffective as essential aspects such as context are not considered. Embodiments of the invention provide automatic contextual based sentiment classification of content in terms of both sentiments expressed and their intensity. Further a content set is analysed to rapidly establish an “at-a-glance” type assessment of the key topics/themes present within the content set and sentimentally annotate each. Importantly embodiments of the invention also provide for a user to establish the basis for the sentiment associated with an item of or set of content, i.e. make it explainable. Further embodiments of the invention provide for the establishment of psychological tone to sentiments where the sentiments and psychological tones to be tuned from the context or domain of the content.

Подробнее
Номер записи: 3
12-12-2013 дата публикации

RECORD CREATING SUPPORT APPARATUS AND METHOD

Номер: US20130332477A1
Автор: NAGAI Kohta, Ohzaki Hiroki
Принадлежит: RICOH COMPANY, LTD.

A record creating support apparatus to support creation of a record may include an extracting unit that extracts a special word from a record that is being created, a searching unit that searches a special word dictionary in order to determine whether the special word extracted by the extracting unit is registered in the special word dictionary, and a notifying unit that notifies the special word when the searching unit determines that the special word is not registered in the special word dictionary. 1. A record creating support apparatus to support creation of a record , comprising:a storage unit configured to store a program; and an extracting unit configured to extract a special word from a record that is being created;', 'a searching unit configured to search a special word dictionary in order to determine whether the special word extracted by the extracting unit is registered in the special word dictionary; and', 'a notifying unit configured to notify the special word when the searching unit determines that the special word is not registered in the special word dictionary., 'a processor configured to execute the program, wherein the processor includes'}2. The record creating support apparatus as claimed in claim 1 , wherein the processor further comprises:a creating unit configured to create the special word dictionary based on special words, included in a record that is created in past, and extracted by the extracting unit.3. The record creating support apparatus as claimed in claim 2 , wherein the extracting unit extracts the special word that appears at least a predetermined number of times in the record.4. The record creating support apparatus as claimed in claim 2 , whereinthe extracting unit extracts the special word included the record that includes identification information identifying a participant who participated in a conference corresponding to the record, and the special word included in the record of the conference to which the participant ...

Подробнее
Номер записи: 4
05-01-2017 дата публикации

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

Номер: US20170003937A1
Автор: Huebra Nadia Analia
Принадлежит:

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 ...

Подробнее
Номер записи: 5
05-01-2017 дата публикации

Natural Language Relatedness Tool using Mined Semantic Analysis

Номер: US20170004129A1
Автор: Rajshekhar Kripa, Shalaby Walid A., Zadrozny Wlodek W.
Принадлежит:

Mined semantic analysis techniques (MSA) include generating a first subset of concepts, from a NL corpus, that are latently associated with an NL candidate term based on (i) a second subset of concepts from the corpus that are explicitly or implicitly associated with the candidate term and (ii) a set of concept association rules. The concept association rules are mined from a transaction dictionary constructed from the corpus and defining discovered latent associations between corpus concepts. A concept space of the candidate term includes at least portions of both the first and second subset of concepts, and includes indications of relationships between latently-associated concepts and the explicitly/implicitly-associated concepts from which the latently-associated concepts were derived. Measures of relatedness between candidate terms are deterministically determined based on their respective concept spaces. Example corpora include digital corpora such as encyclopedias, journals, intellectual property datasets, health-care related datasets/records, financial-sector related datasets/records, etc. 1. A natural language-relatedness (NLR) tool , comprising:an input interface via which an initial subset of a set of concepts of a corpus is received, each concept of the initial subset of concepts being semantically associated with a candidate term, the candidate term comprising one or more natural language words, the corpus comprising natural language, and the semantic associations of the initial subset of concepts with the candidate term determined based on a first semantic analysis of the corpus;a concept expander comprising first computer-executable instructions that are stored on one or more memories and that, when executed by one or more processors, cause the NLR tool to mine, based on the initial subset of concepts, a set of concept association rules of the corpus to discover an expansion subset of concepts of the corpus, each concept of the expansion subset of ...

Подробнее
Номер записи: 6
05-01-2017 дата публикации

UTILIZING SEMANTIC HIERARCHIES TO PROCESS FREE-FORM TEXT

Номер: US20170004205A1
Автор: Betz Adam J., Dao Huy P.M., DUBEY Rajeev, Haase Bill A., Jain Navendu
Принадлежит:

User feedback may be analyzed with semantic hierarchies. In some instances, the user feedback includes free-form text. The user feedback may be mapped to one or more semantic hierarchies that include multiple levels of nodes, where each node corresponds to a class. Information of the one or more semantic hierarchies may be mapped to an ontology model. The mapped information of the ontology model may be used to identify an actionable item for the user feedback, such as a problem, suggestion, question, or other issue. Information regarding the actionable item may be made available to an individual for evaluation of the actionable item. 1. A system comprising:one or more processors;memory communicatively coupled to the one or more processors and storing data regarding a semantic hierarchy having one or more levels of nodes, with each node representing a class;an interface communicatively coupled to the one or more processors and configured to receive data including free-form text;a mapping module stored in the memory and executable by the one or more processors to map at least one word or phrase of the data to one or more levels of the semantic hierarchy; anda feedback routing module stored in the memory and executable by the one or more processors to utilize the mapped at least one word or phrase of the data to send information regarding the data to a device associated with an individual for evaluation of the actionable item.2. The system of claim 1 , wherein the semantic hierarchy includes:a first level having at least one node representing customer terms; anda second level having at least one node representing at least one of morphological forms of the customer terms or technical terms for the customer terms.3. The system of claim 1 , wherein the actionable item includes at least one of a problem with a software or hardware entity claim 1 , a suggestion for improvement of the software or hardware entity claim 1 , or a question regarding a software or hardware entity ...

Подробнее
Номер записи: 7
05-01-2017 дата публикации

Natural language interpretation of hierarchical data

Номер: US20170004206A1
Автор: David M. Doran, James P. Boland, Junaid Y.A. Mohammed, Niketh J. Kala
Принадлежит: International Business Machines Corp

A computer-implemented method includes receiving a search label and accessing a hierarchical data source comprising a plurality of nodes. One node may be a context node. The method further includes determining a similarity score between the search label and a node label of each node, determining a contextual score between the context node and each node, combining, for each node, the similarity score with the contextual score to yield a combined score, and returning a result. The result may be based on ordering the plurality of nodes according to each node's combined score. A corresponding computer program product and computer system are also disclosed.

Подробнее
Номер записи: 8
07-01-2016 дата публикации

SECURITY TRIMMING OF SEARCH SUGGESTIONS

Номер: US20160004706A1
Автор: Baumgartner Patrick J., Faghihi Rezaei Pedram, Hays Chris A., Netz Amir, Petculescu Cristian
Принадлежит:

Search suggestions are generated in manner that takes into account access-control information. A query can be received from a user of a search engine prior to initiating execution of the query. Data that is accessible to the user can be determined based on access information associated with the user and data. Subsequently, query suggestions can be generated dynamically based on data accessible to the user. 1. A method , comprising:employing at least one processor configured to execute computer-executable instructions stored in memory to perform the following acts:receiving a query specified by a user of a search engine prior to initiating execution of the query;determining data that is accessible to the user based on access information associated with the user and the data; andgenerating one or more query suggestions dynamically based on the data that is accessible to the user.2. The method of claim 1 , generating one or more query suggestions comprises:generating a set of related queries based on the data that is accessible to the user; andselecting at least a subset of the set of related queries.3. The method of further comprises selecting at least a subset of the set of related queries based on frequency of use.4. The method of further comprises generating the set of related queries comprises:identifying a template that matches the query specified by the user;detecting at least one unspecified template parameter; andconstructing one or more queries by setting a value for the at least one unspecified template parameter with data that is accessible to the user.5. The method of further comprises receiving a natural language query.6. The method of further comprises ordering the one or more query suggestions based on user context.7. The method of further comprising presenting the one or more query suggestions on a display device.8. A system claim 1 , comprising:a processor coupled to a memory, the processor configured to execute the following computer-executable ...

Подробнее
Номер записи: 9
07-01-2016 дата публикации

INFORMATION PROVIDING DEVICE, INFORMATION PROVIDING PROGRAM, INFORMATION PROVIDING SERVER, AND INFORMATION PROVIDING METHOD

Номер: US20160004755A1
Автор: Sempuku Tsuyoshi
Принадлежит: Mitsubishi Electric Corporation

An information providing device includes: a device management unit acquiring information of a connected device; a history database storing the information acquired by the device management unit as a history; a function estimation unit estimating a function to be presented to a user, based on the information of the connected device and the history stored in the history database; an availability determination unit determining availability of the function estimated by the function estimation unit; and an output unit outputting the function to be presented to the user, based on an indication of the function estimation unit. The function estimation unit confirms that the estimated function is a function to be presented to the user and causes the output unit to output the function when the availability determination unit determines that the estimated function is available. 1. An information providing device comprising:a device manager that acquires information of a connected device;a history database that stores the information acquired by the device manager as a history;a function estimator that estimates a function to be presented to a user, based on the information of the connected device and the history stored in the history database;an availability determinator that determines availability of the function based on a determination condition of the availability corresponding to the function estimated by the function estimator; andan output processor that presents the estimated function to the user when the availability determinator determines that the function estimated by the function estimator is available.2. The information providing device according to claim 1 , wherein the availability determinator determines the availability claim 1 , based on only information relating to the function estimated by the function estimator.3. (canceled)4. The information providing device according to claim 1 , wherein the function estimator includes:a purpose estimator that ...

Подробнее
Номер записи: 10
07-01-2016 дата публикации

Search technology using synonims and paraphrasing

Номер: US20160004766A1
Автор: Evgeny Indenbom, Tatiana Danielyan
Принадлежит: ABBYY InfoPoisk LLC

The present invention is a method and a system of organizing information searches in electronic text corpora and displaying the search results in the user interface. The system and the method enable searches not just for words or word combinations, but also for specific lexical meanings of words, where a lexical meaning is a realization of a word's semantic meaning in a particular language. The completeness of search results is bases on incorporation synonyms and paraphrases in the search. The method also includes searching for fragments matching the query in electronic text corpora, estimating the results and the displaying the results ranked to the user.

Подробнее
Номер записи: 11
07-01-2016 дата публикации

METHOD AND SYSTEM FOR PROBABILISTICALLY QUANTIFYING AND VISUALIZING RELEVANCE BETWEEN TWO OR MORE CITATIONALLY OR CONTEXTUALLY RELATED DATA OBJECTS

Номер: US20160004768A1
Автор: Barney Jonathan A.
Принадлежит:

In one embodiment a method for probabilistically quantifying a degree of relevance between two or more citationally or contextually related data objects, such as patent documents, non-patent documents, web pages, personal and corporate contacts information, product information, consumer to behavior, technical or scientific information, address information, and the like is provided. In another embodiment a method for visualizing and displaying relevance between two or more citationally or contextually related data objects is provided. In another embodiment a search input/output interface that utilizes an iterative self-organizing mapping technique to automatically generate a visual map of relevant patents and/or other related documents desired to be explored, searched or analyzed is provided. In another embodiment, a search input/output interface that displays and/or communicates search input criteria and corresponding search results in a way that facilitates intuitive understanding and visualization of the logical relationships between two or more related concepts being searched is provided. 1. (canceled)2. A computer-implemented method for identifying relevant documents from a corpus comprising multiple millions of citationally-related source documents , said computer-implemented method comprising:storing on a computer-readable storage device a search index comprising a first set of identification information identifying potential input documents selected from said source documents and, for each said potential input document, a second set of identification information identifying a selected number of citationally-related potential output documents selected from said source documents;calculating, via one or more computer-processors coupled to said computer-readable storage device, a first numerical score that is statistically correlated to the probability that a direct citation exists between each corresponding pair of citationally-related potential input document ...

Подробнее
Номер записи: 12
04-01-2018 дата публикации

DECISION TABLE DECOMPOSITION USING SEMANTIC RELATIONS

Номер: US20180004837A1
Автор: Balasubramanian Swaminathan, Berlandier Pierre C.
Принадлежит:

A computer-implemented method for decomposing a decision table includes decomposing, by a computer processor, a decision table into a first sub-table and a second sub-table. The decision table includes two or more columns, and the decomposition is based on a semantic model describing relations among the two or more columns of the decision table. The first sub-table and the second sub-table together represent the decision table. 1. A computer-implemented method for decomposing a decision table , comprising: one or more condition columns together indicating, for each row of the decision table, a condition upon which an action is to be taken; and', 'one or more action columns together indicating, for each row of the decision table, the action to be taken given the condition specified in the one or more condition columns;, 'determining that invocation criteria are met for a decision table, wherein the decision table comprises two or more columns, and wherein the two or more columns of the decision table comprise dividing the decision table into two or more groups of rows, wherein each group of rows comprises one or more action sub-tuples representing values of the one or more action columns, and wherein the one or more action sub-tuples have equivalent values in the one or more action columns within each group of rows;', 'selecting a first subset of condition columns from the one or more condition columns of the decision table, wherein the first subset of condition columns meets selection criteria requiring that values of the sub-tuples from a complementary subset of condition columns to the first subset of condition columns are identical within each group of rows;', 'populating in the first sub-table the first subset of condition columns selected from the one or more condition columns of the decision table; and', 'populating in the second sub-table a second subset of condition columns from the one or more condition columns of the decision table, wherein the second set ...

Подробнее
Номер записи: 13
02-01-2020 дата публикации

CONVERSATIONAL QUERY ANSWERING SYSTEM

Номер: US20200004873A1
Автор: Brandt Jonathan, Chang Walter W., KIM Doo Soon
Принадлежит:

Techniques of directing a user to content based on a semantic interpretation of a query input by the user involves generating links to specific content in a collection of documents in response to user string query, the links being generated based on an answer suggestion lookahead index. The answer suggestion lookahead index references a mapping between a plurality of groups of semantically equivalent terms and a respective link to specific content of the collection of documents. These techniques are useful for the generalized task of natural language question answering. 1. A computer-implemented method , comprising:receiving document data representing a collection of documents, each document of the collection of documents including a respective topic and content pertaining to the topic;generating answer suggestion lookahead index data based on the collection of documents, the answer suggestion lookahead index data representing a plurality of term/link pairs, each term/link pair of the plurality of term/link pairs including a semantically equivalent term and a corresponding link to content of the collection of documents;receiving a user query string;in response to receiving the user query string, locating a semantically equivalent term of a term/link pair of the plurality of term/link pairs, the semantically equivalent term being located based a semantic equivalence to the user query string; andoutputting a representation of the link of the located term/link pair to an output device.2. The method of claim 1 , wherein generating the answer suggestion lookahead index data includes:generating topic knowledge graph data based on the collection of documents, the topic knowledge graph data representing a topic knowledge graph that includes (i) a respective topic and a set of subtopics of each of the collection of documents, and (ii) links to the content of the collection of documents, each of the links corresponding to one of a respective topic or subtopic of the set of ...

Подробнее
Номер записи: 14
02-01-2020 дата публикации

SYSTEMS AND METHODS FOR CONTEXTUAL RANKING OF SEARCH RESULTS

Номер: US20200004876A1
Автор: Sagar Nilabh, Singh Sanjay Kumar, SINHA Anshuman
Принадлежит:

Systems, apparatuses, methods, and computer program products are disclosed for searching electronic documents. An example method includes receiving a set of electronic documents, wherein each electronic document in the set of electronic documents comprises a set of sentences. The example method further includes generating a contextual index that associates each sentence with one or more of contexts. The example method further includes receiving an electronic search query comprising a plurality of search terms. Subsequently, the example method includes generating a contextual search ranking for a subset of the set of electronic documents based on the search terms and the contextual index. 1. A computing system for searching electronic documents , the computing system comprising: receive a set of electronic documents, wherein each electronic document in the set of electronic documents comprises a set of sentences,', 'identify a set of terms for each sentence, wherein each term in the set of terms is associated with one or more contexts in a set of contexts,', 'generate, based on the set of terms, a context score for each sentence with respect to each context in the set of contexts, and', 'generate a contextual index that associates each sentence with one or more of the contexts in the set of contexts based on the context score; and, 'preprocessing circuitry configured to'} receive an electronic search query provided by a user, wherein the electronic search query comprises a plurality of search terms, and', 'generate a contextual search ranking for a subset of the set of electronic documents based on the search terms and the contextual index., 'query processing circuitry in communication with the preprocessing circuitry and configured to'}2. The computing system of claim 1 , wherein the preprocessing circuitry is further configured to identify the set of terms for each sentence based on natural language processing.3. The computing system of claim 1 , wherein (a) the ...

Подробнее
Номер записи: 15
01-01-2015 дата публикации

COUNTING DEVICE, COUNTING PROGRAM, MEMORY MEDIUM, AND COUNTING METHOD

Номер: US20150006533A1
Автор: Shinzato Keiji
Принадлежит: RAKUTEN, INC.

A counting device () provided with a subtree generating part () for generating first subtree comprising a first sentence and a second subtree comprising a second sentence. The counting device () is provided with: a categorizing part () for categorizing the first subtree in the same group as the second subtree when it is determined that a first expression represented by the first subtree and a second expression represented by a second subtree represent a matching content; and an output part () for outputting the number of subtrees categorized in the group, or an expression represented by a plurality of syntax trees or one of the subtrees categorized in the aforementioned group. 1. A counting device for counting input sentences , comprising:an input part for inputting a first sentence and a second sentence;a syntax analyzing part for generating a syntax tree of the first sentence and a syntax tree of the second sentence by accomplishing syntax analysis on the first sentence and the second sentence;a subtree generating part for generating one or multiple first subtrees that are subtrees comprising the first sentence, from the generated syntax tree of the first sentence, and generating one or multiple second subtrees that are subtrees comprising the second sentence, from the generated syntax tree of the second sentence;a match determination part for determining whether or not a first expression represented by a first subtree comprising a subtree combination and a second expression represented by a second subtree comprising the subtree combination represent matching content, for one or multiple subtree combinations that are combinations or any one of the one or multiple first subtrees generated and one or multiple of the second subtrees generated;a categorizing part for categorizing a first subtree representing a first expression and a second subtree representing a second expression into the same group for one combination of the first expression and the second expression ...

Подробнее
Номер записи: 16
03-01-2019 дата публикации

SYSTEMS, METHODS, AND COMPUTER-READABLE MEDIUM FOR VALIDATION OF IDIOMATIC EXPRESSIONS

Номер: US20190005028A1
Автор: Mago Rishi
Принадлежит:

A method for validation of idiomatic expressions may include the steps of receiving an input text string; performing a search of a database based on the input text string, in which the database stores a plurality of idiomatic expressions; identifying a first set of idiomatic expressions, in which the first set includes at least one of the plurality of idiomatic expressions stored in the database, in which each idiomatic expression in the first set has an associated concordance score that meets or exceeds a predetermined concordance threshold value, in which the associated concordance score indicates a degree of similarity between the respective idiomatic expression in the first set and the input text string; and outputting the first set of idiomatic expressions. A computing device configured to implement the method and a non-transitory computer-readable medium configured to store instructions that define the method are also disclosed. 1. A computing device configured to perform validation of idiomatic expressions , the computing device comprising:one or more processors; and receive an input text string;', 'perform a search of a database based on the input text string, the database storing a plurality of idiomatic expressions;', 'identify a first set of idiomatic expressions, the first set including at least one of the plurality of idiomatic expressions stored in the database, each idiomatic expression in the first set having an associated concordance score that meets or exceeds a predetermined concordance threshold value, the associated concordance score indicating a degree of similarity between the respective idiomatic expression in the first set and the input text string; and', 'output the first set of idiomatic expressions., 'a memory storing computer-readable instructions that, when executed by the one or more processors, cause the computing device to2. The computing device of claim 1 , wherein:the associated concordance score is determined based on a comparison ...

Подробнее
Номер записи: 17
01-01-2015 дата публикации

INFORMATION PROCESSING TERMINAL AND METHOD, AND INFORMATION MANAGEMENT APPARATUS AND METHOD

Номер: US20150006573A1
Автор: FUSUME Kosei, MORITA Masahiro, SUZUKI Masaru
Принадлежит:

According to one embodiment, an information processing terminal includes a generator, an acquisition unit, and an output unit. The generator analyzes an electronic document to generate a metadata item including text information in an electronic document and structure information on the electronic document. The acquisition unit transmits the metadata item to an information management apparatus, causes the information management apparatus to estimate a similar metadata item similar to the metadata item and acquires an annotation information item corresponding to the similar metadata item. The output unit outputs the annotation information item in association with the electronic document. 1. An information processing terminal permitted to be connected to an information management apparatus for managing metadata items on electronic documents and annotation information items corresponding to the metadata items , the annotation information items on the electronic documents being generated by users , comprising:a generator configured to analyze an electronic document to generate a metadata item including text information in the electronic document and structure information on the electronic document;an acquisition unit configured to transmit the metadata item to the information management apparatus, to cause the information management apparatus to estimate a similar metadata item similar to the metadata item and to acquire a certain annotation information item corresponding to the similar metadata item, the certain annotation information item being included in the annotation information items; andan output unit configured to output the annotation information item in association with the electronic document.2. The terminal according to claim 1 , wherein the annotation information item is comment information indicating comments added by the users to the electronic document claim 1 , or is audio information corresponding to the electronic document.3. The terminal according to ...

Подробнее
Номер записи: 18
03-01-2019 дата публикации

Recommendation Engine using Inferred Deep Similarities for Works of Literature

Номер: US20190005097A1
Автор: Allen Corville O., Carrier Scott R., Woods Eric
Принадлежит:

A recommendation engine for works of literature uses patterns of flow and element similarities for scoring a first user-rated work of literature against one or more recommendation candidate works of literature. Cluster models are created using meta-data modeling the works of literature, the meta-data having literary element categories and instances within each category. Each instance is described by an index value (position in the literature) and significance value (e.g. weight or significance). Cluster finding process(es) invoked for each instance in each category find Similarity Concept clusters and Consistency Trend clusters, which are recorded into the cluster models representing each work of literature. The cluster model can be printed or displayed so that a user can visually understand the ebb and flow of each literary element in the literature, and may be digitally compared to other cluster models of other works of literature for potential recommendation to a user. 1. A method comprising:determining, by a computer, a degree of similarity between the first digital cluster model for a first work of digital literature and a second digital cluster model for a second work of digital literature; andproducing, by a computer, via a user interface device, a recommendation to a user for the second work of digital literature according to the degree of similarity.2. The method as set forth in wherein the first and second cluster models each comprise one or more clusters selected from the group consisting of abstracted concepts claim 1 , abstracted longitudinal patterns claim 1 , and abstracted consistency trends of elements in the clusters across multiple segments of each respective work of digital literature claim 1 , and which contain at least one cluster limited within a range of significance values for one or more instances within one or more literary element categories3. The method as set forth in wherein the first cluster model comprises at least one cluster model ...

Подробнее
Номер записи: 19
03-01-2019 дата публикации

SYSTEM FOR DETERMINATION OF AUTOMATED RESPONSE FOLLOW-UP

Номер: US20190005122A1
Автор: "OConnor Dan", "OKeeffe William G.", Barbosa Jose, Kumar Ashok T., Taieb David D.
Принадлежит:

Aspects include generation of automated response follow-up. A response to a question from a user is received at a response follow-up system. The response follow-up system analyzes the response using natural language processing to identify one or more response terms. The response follow-up system generates one or more follow-up questions based on the one or more response terms. Based on the response, one or more follow-up responses to the one or more follow-up questions are pre-fetched from one or more content provider systems including one or more content servers, where a question answering system including the response follow-up system is communicatively coupled to the one or more content provider systems through a network. The response follow-up system modifies an aspect of a user interface displayed to the user based on the one or more follow-up questions and the one or more follow-up responses. 1. A method , comprising:receiving, from a user, a response to a question at a response follow-up system;analyzing, by the response follow-up system, the response using natural language processing to identify one or more response terms;generating, by the response follow-up system, one or more follow-up questions based on the one or more response terms;pre-fetching, based on the response, one or more follow-up responses to the one or more follow-up questions from one or more content provider systems comprising one or more content servers, wherein a question answering system comprising the response follow-up system is communicatively coupled to the one or more content provider systems through a network; andmodifying an aspect of a user interface displayed to the user based on the one or more follow-up questions and the one or more follow-up responses.2. The method of claim 1 , further comprising:determining one or more variants of the one or more response terms;generating the one or more follow-up questions based on the one or more variants of the one or more response terms ...

Подробнее
Номер записи: 20
03-01-2019 дата публикации

TOPIC SHIFT DETECTOR

Номер: US20190005123A1
Автор: Byron Donna K., Emanuel Barton W., MAHDAD SAMIR, Rakshit Sarbajit K., Trim Craig M.
Принадлежит:

Aspects detect or recognize shifts in topics in computer implemented speech recognition processes as a function of mapping keywords to non-verbal cues. An initial topic is mapped to one or more keywords extracted from a first spoken query within a user keyword ontology mapping. A query spoken subsequent in time to the first query is identified and distinguished by recognizing one or more non-verbal cues associated with the audio data input that include a time elapsed between the queries, and in some aspects a user's facial expression or motion activity. Aspects determine whether the second spoken query is directed to the initial topic or to a new topic that is different from the initial topic, as a function of mappings of the keyword(s) extracted from the first query to one or more keywords extracted from the second query and to the non-verbal cue(s) within the user ontology mapping. 1. A computer-implemented method for detecting shifts in topics in computer implemented speech recognition processes as a function of mapping keywords to non-verbal cues , the method comprising executing on a computer processor:identifying an initial topic of a first spoken query within an audio data input from a user that is mapped to at least one keyword extracted from the first spoken query within a user keyword ontology mapping;identifying a second spoken query within the audio data input that is subsequent in time to the first spoken query and is distinguished from the first query by recognizing at least one non-verbal cue associated with the audio data input, wherein the at least one non-verbal cue comprises a time elapsed between the first spoken query and the second spoken query, and a user's motion activity relative to a programmable device comprising the processor during a time between the first spoken query and the second spoken query;determining whether the second spoken query is directed to the initial topic or to a new topic that is different from the initial topic, as a ...

Подробнее
Номер записи: 21
03-01-2019 дата публикации

Analyzing Concepts Over Time

Номер: US20190005141A1
Автор: Ho Tin Kam, Lastras-Montano Luis A., Shmueli Oded
Принадлежит:

A method and apparatus are provided for automatically generating and processing first and second concept vector sets extracted, respectively, from a first set of concept sequences and from a second, temporally separated, concept sequences by performing a natural language processing (NLP) analysis of the first concept vector set and second concept vector set to detect changes in the corpus over time by identifying changes for one or more concepts included in the first and/or second set of concept sequences. 120-. (canceled)21. A method , in an information handling system comprising a processor and a memory , for analyzing concept vectors over time to detect changes in a corpus , the method comprising:detecting one or more disruptive concepts in a second set of concept sequences that are effectively collected after collection of a first set of concept sequences by analyzing relationship strengths between concepts to identify market trends for answering questions submitted to the information handling system, wherein analyzing relationship strengths comprises (a) computing cosine distances between each of a first concept vector set V′k+1, . . . , V′k+b derived from a concatenation of a first set of concept sequences and the second set of concept sequences over k concepts that are shared by the first and second sets of concept sequences and each of a second concept vector set VL1, . . . , VLh, derived from a third set of concept sequences identified in the concatenation of the first and second sets of concept sequences as being central to a specified technology area T over h concepts and (b) sorting vectors V′k+1, . . . , V′k+b to identify one or more disruptive concepts based on the computed cosine distances.22. The method of claim 21 , wherein sorting vectors V′k+1 claim 21 , . . . claim 21 , V′k+b comprises sorting the vectors V′k+1 claim 21 , . . . claim 21 , V′k+b by a highest cosine distance to any of VL1 claim 21 , . . . claim 21 , VLh in the second concept vector ...

Подробнее
Номер записи: 22
03-01-2019 дата публикации

Threat intelligence system

Номер: US20190007425A1
Автор: Blake Butler, Bradley Wardman, Jakub Burgis, Kevin Tyers, Nate Robert Pratt, Nicole Harris
Принадлежит: PayPal Inc

Systems and methods for providing a threat intelligence system include a system provider device that downloads, through communication over a network and from one or more targeted websites, a plurality of images of a first environment. Based on an OCR process, the system provider device may extract a set of textual data corresponding to a subset of images of the plurality of images, where the subset of images depict text. The system provider device stores the set of textual data in an indexed and searchable database. The system provider device assigns a threat assessment score to each image based on the set of textual data, and the threat assessment score may be updated based on comparison of the set of textual data with other sets of textual data. Based on the threat assessment score being greater than a threshold value, the system provider device may generate a security alert.

Подробнее
Номер записи: 23
03-01-2019 дата публикации

PATTERN CREATION IN ENTERPRISE THREAT DETECTION

Номер: US20190007435A1
Автор: Bohn Joscha Philipp, Chrosziel Florian, Dinkova Hristina, Kartmann Daniel, Kunz Thomas, Luo Lin, Mehta Harish, Merkel Rita, Peng Wei-Guo, Pritzkau Eugen, Rodeck Marco, Seifert Hartwig, Zhang Nan
Принадлежит:

Search results are received from an initiated free text search of log data from one or more logs, where the free text is performed using search terms entered into a free text search graphical user interface. A set of at least one search result is selected from the search results containing an event desired to be identified in a completed enterprise threat detection (ETD) pattern. A forensic lab application is rendered to complete an ETD pattern. An event filter is added for an event type based on normalized log data to a path. A relative ETD pattern time range is set and an ETD pattern is completed based on the added event filter. 1. A computer-implemented method , comprising:receiving search results from an initiated free text search of log data from one or more logs, the free text performed using search terms entered into a free text search graphical user interface;selecting a set of at least one search result from the search results containing an event desired to be identified in a completed enterprise threat detection (ETD) pattern;rendering a forensic lab application to complete an ETD pattern;adding an event filter for an event type based on normalized log data to a path;setting a relative ETD pattern time range; andcompleting an ETD pattern based on the added event filter.2. The computer-implemented method of claim 1 , further comprising:analyzing the search results of the free text search to determine that the search result corresponds to a user expectation;refining the search terms; andreinitiating the free text search using the refined search terms.3. The computer-implemented method of claim 1 , wherein the event filter based on normalized log data is added to the path by selecting a bubble corresponding to the event type in a bubblegram view rendered in the forensic lab application.4. The computer-implemented method of claim 1 , further comprising analyzing a search result based on the added event filter to determine whether there has been a change in the ...

Подробнее
Номер записи: 24
08-01-2015 дата публикации

PRESENTING REAL-TIME SEARCH RESULTS

Номер: US20150012518A1
Автор: Burns Brendan D., Huelsbergen Lorenz, Hylton Jeremy, Leavitt Laramie, Menzel Jack W., Ngan Addy
Принадлежит:

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for presenting real-time search results. In one aspect, a method includes presenting real-time search results in response to a query; and automatically updating the real-time search results. 1presenting real-time search results in response to a query; andautomatically updating the real-time search results.. A computer-implemented method, comprising: This is a continuation of U.S. application Ser. No. 12/960,448, filed on Dec. 3, 2010, which claims the benefit of priority of U.S. Provisional Application No. 61/267,416, filed on Dec. 7, 2009, and U.S. Provisional Application No. 61/267,011, filed on Dec. 4, 2009. The disclosure of each prior application is considered part of and is incorporated by reference in the disclosure of this application.This specification relates to presenting search results. Search engines aim to identify resources (e.g., images, audio, video, web pages, text, documents) that are relevant to a user's needs and to present information about the resources in a manner that is most useful to the user. Search engines return a set of search results in response to a user submitted query.In general, one innovative aspect of the subject matter described in this specification can be embodied in methods that include the actions of presenting real-time search results in response to a query; and automatically updating the real-time search results. Other embodiments of this aspect include corresponding systems, apparatus, and computer programs recorded on computer storage devices, each configured to perform the actions of the methods.These and other embodiments can each optionally include one or more of the following features, alone or in combination. Presenting the real-time search results includes presenting the real-time search results along with other search results. Updating the real-time search results includes requesting new search results from a search ...

Подробнее
Номер записи: 25
12-01-2017 дата публикации

COMMON DATA REPOSITORY FOR IMPROVING TRANSACTIONAL EFFICIENCIES OF USER INTERACTIONS WITH A COMPUTING DEVICE

Номер: US20170011114A1
Автор: Naressi Alexandre, Souche Christian, Vidal Richard, Yang Junmin
Принадлежит:

Examples of the disclosure enable an information processing system to automatically generate a common data repository including a plurality of documents. In some examples, the information processing system is configured to analyze the documents to identify a plurality of topics. Based on the identified topics, the documents are classified into a plurality of sets. A set is associated with a corresponding topic. One or more correlations between the documents are identified and, based on the identified correlations, one or more user interaction tools are generated including an interaction script. 1. An information processing system comprising:a memory area storing computer-executable instructions for generating a common data repository including a plurality of documents; and analyze the plurality of documents to identify a plurality of topics;', 'based on the plurality of identified topics, classify the plurality of documents into a plurality of sets, a first set of the plurality of sets associated with a first topic of the plurality of topics;', 'identify one or more correlations between a first document classified into the first set and another document of the plurality of classified documents;', 'based on the one or more identified correlations, generate a taxonomy tree;', 'based on the generated taxonomy tree, generate one or more tools including an interaction script associated with the first topic of the plurality of topics to improve a transactional efficiency of a user interaction., 'a processor configured to execute the computer-executable instructions to2. The information processing system of claim 1 , wherein the processor is configured to execute the computer-executable instructions to retrieve the plurality of documents from a plurality of data sources.3. The information processing system of claim 1 , wherein the processor is configured to execute the computer-executable instructions to determine a language associated with one or more documents of the ...

Подробнее
Номер записи: 26
12-01-2017 дата публикации

Help Processing Method and Device Based on Semantic Recognition

Номер: US20170011117A1
Автор: He Shan, JIANG Qiang, Li Hang
Принадлежит:

A help processing method and device based on semantic recognition are presented. The method includes receiving, by user equipment, a search request entered by a user, where the search request includes information about a problem statement described in a natural language; performing semantic recognition processing on the information about the problem statement, to obtain information about a search intention of the user; and searching a database using the information about the search intention as a search term, to obtain help content needed by the user. 1. A help processing method based on semantic recognition , comprising:receiving a search request entered by a user, wherein the search request comprises information about a problem statement described in a natural language;performing semantic recognition processing on the information about the problem statement in order to obtain information about a search intention of the user; andsearching a database using the information about the search intention as a search term in order to obtain help content needed by the user.2. The method according to claim 1 , wherein performing the semantic recognition processing on the information about the problem statement in order to obtain the information about the search intention of the user comprises:sending the information about the problem statement to a network server, so that the network server performs semantic recognition processing on the information about the problem statement in order to obtain the information about the search intention; andreceiving the information about the search intention, which is fed back by the network server.3. The method according to claim 1 , wherein searching the database using the information about the search intention as the search term in order to obtain help content needed by the user comprises at least one of:searching, using the information about the search intention as the search term, a help database pre-stored in user equipment in order ...

Подробнее
Номер записи: 27
12-01-2017 дата публикации

LANGUAGE LEARNING EXCHANGE

Номер: US20170011654A1
Автор: Elchik Michael E.
Принадлежит:

Systems and methods to enable users to communicate via a language learning exchange are provided herein. One aspect includes registering through a computing device one or more users in a user community of an online language learning platform, the one or more users associated with profile information comprising user name, native language, and language of interest elements; accessing language content for use by the one or more users; matching the one or more users with one or more complementary users; and making the language content available to the users via a language learning exchange interface. 120-. (canceled)21. A system for enabling communication by complementary users of a language learning exchange , the system comprising:at least one processor; identify a first user in a user community of a language learning platform,', 'identify, for the first user, associated profile information comprising a native language and a language of interest,', 'use the profile information to automatically identify a complementary user in the user community who has (i) a native language that matches the language of interest of the first user, and (ii) a language of interest that matches the native language of the first user,', 'cause a first local computing device of the first user and a second local computing device of the complementary user to each output a learning exchange interface through which the first user and the complementary user may communicate in the language learning exchange,', "receive a source, a category, or a topic from the first user or the complementary user via a topic profile interface of that user's learning exchange interface,", 'retrieve, from a set of language learning content, content that corresponds to the received source, category or topic, and', 'present the retrieved content to the first user and the complementary user in either of the languages via the language learning interfaces., 'a computer readable storage medium containing programming ...

Подробнее
Номер записи: 28
14-01-2016 дата публикации

METHODS OF EVALUATING SEMANTIC DIFFERENCES, METHODS OF IDENTIFYING RELATED SETS OF ITEMS IN SEMANTIC SPACES, AND SYSTEMS AND COMPUTER PROGRAM PRODUCTS FOR IMPLEMENTING THE SAME

Номер: US20160012123A1
Автор: Cai Zhiqiang, Craig Scotty, GRAESSER ARTHUR C., Hu Xiangen
Принадлежит:

One aspect of the invention provides a method of evaluating semantic differences between a first item in a first semantic space and a second item in a second semantic space. Thee method includes: calculating a first ordered list of N nearest neighbors of the first item within the first semantic space; calculating a second ordered list of N nearest neighbors of the second item within the second semantic space; and computing a plurality of similarity measures between the first n nearest neighbors of the first item and the first n nearest neighbors of the second item, wherein n and N are positive integers and 1≦n≦N. 1. A method of evaluating semantic differences between a first item in a first semantic space and a second item in a second semantic space , the method comprising:calculating a first ordered list of N nearest neighbors of the first item within the first semantic space;calculating a second ordered list of N nearest neighbors of the second item within the second semantic space; andcomputing a plurality of similarity measures between the first n nearest neighbors of the first item and the first n nearest neighbors of the second item, wherein n and N are positive integers and 1≦n≦N.2. The method of claim 1 , wherein the plurality of similarity measures include one or more selected from the group consisting of: combinatorial similarity claim 1 , permutational similarity claim 1 , and quantitative similarity.3. The method of claim 1 , wherein the plurality of similarity measures are each selected from a uniform type of similarity measure.4. The method of claim 1 , wherein the plurality of similarity measures are selected from different types of similarity measures.5. The method of claim 1 , wherein the plurality of similarity measures is equal to N.6. The method of claim 5 , wherein a similarity measure is computed for each iteration of n for 1≦n≦N.7. The method of claim 1 , wherein the first item is selected from the group consisting of:words, phrases, and ...

Подробнее
Номер записи: 29
14-01-2016 дата публикации

INVERTED TABLE FOR STORING AND QUERYING CONCEPTUAL INDICES

Номер: US20160012125A1
Автор: Franceschini Michele M., Lastras-Montano Luis A., Soares Livio B., Wegman Mark N.
Принадлежит:

According to an aspect, storing and querying conceptual indices (CIs) includes creating a conceptual inverted index (CII) from the CIs. The CII includes CII entries, each of which corresponds to a concept in a concept graph. Creating the CII includes populating each entry with pointers to documents selected from the CIs having likelihoods of being related to the concept that are greater than a threshold value, and the corresponding likelihoods. An aspect also includes receiving a query that includes a concept in the concept graph, and generating query results from a search that include at least a subset of the pointers to documents. Each of the CIs is associated with a corresponding document and includes a CI entry for each concept in the concept graph, and each of the CI entries specifies a value indicating a likelihood that the document is related to the concept in the concept graph. 1. A method , comprising: with respect to the concept corresponding to the CII entry, populating the CII entry with:', 'pointers to documents selected from the CIs having likelihoods of being related to the concept that are greater than a threshold value; and', 'the corresponding likelihoods of the documents;, 'creating a conceptual inverted index (CII) based on conceptual indices (CIs), the CII including CII entries, each of which corresponds to a separate concept in a concept graph, the creating including for each CII entryreceiving a query that includes one of the concepts in the concept graph as a search term;searching the CII for the search term; andgenerating query results from the searching, the query results including at least a subset of the pointers to documents;wherein each of the CIs is associated with a corresponding one of the documents and includes a CI entry for each concept in the concept graph, and each of the CI entries specifies a value indicating a likelihood that the one of the documents is related to the concept in the concept graph.2. The method of claim 1 , ...

Подробнее
Номер записи: 30
14-01-2016 дата публикации

System for searching, recommending, and exploring documents through conceptual associations

Номер: US20160012126A1
Автор: John T. Richards, Livio B. Soares, Luis A. Lastras-Montano, Mark N. Wegman, Michele M. Franceschini
Принадлежит: International Business Machines Corp

According to an aspect, searching, recommending, and exploring documents through conceptual associations includes a method for receiving a plurality of documents and extracting concepts from each of the documents. A degree of relation between each of the documents and concepts in a knowledge base is calculated. The method also includes, in response to receiving a query, determining one or more concepts from the query. For each of the concepts, a list of documents having a highest degree of relation to the concept is retrieved. The method also includes outputting a list that is responsive to the one or more retrieved lists.

Подробнее
Номер записи: 31
11-01-2018 дата публикации

Type-Specific Rule-Based Generation of Semantic Variants of Natural Language Expression

Номер: US20180011837A1
Автор: Beller Charles E., Katz Edward G., Tonetti Alexander C.
Принадлежит:

A mechanism is provided in a data processing system having a processor and a memory storing a store of semantic types and instructions for implementing a natural language processing engine for generating semantically equivalent variants of a natural language term. The mechanism receives an input term for variant analysis. The natural language processing engine executing on the data processing system identifies a semantic type of the input term based on a store of semantic types. The natural language processing engine performs a type-specific series of rule-based expansions of the input term based on the identified semantic type of the input term to form a set of semantically equivalent variants of the input term. The natural language processing engine performs a natural language processing operation using the input term and the set of semantically equivalent variants of the input term. 1. A method , in a data processing system having a processor and a memory storing a store of semantic types and instructions for implementing a natural language processing engine for generating semantically equivalent variants of a natural language term , wherein the data processing system configured with the natural language processing engine comprises a question answering system , the method comprising:receiving, by the natural language processing engine, an input term for variant analysis, wherein the input term is an answer to a question forming a question and answer pair for an answer key of the question answering system;identifying, by the natural language processing engine executing on the data processing system, a semantic type of the input term based on a store of semantic types;performing, by the natural language processing engine, a type-specific series of rule-based expansions of the input term based on the identified semantic type of the input term to form a set of semantically equivalent variants of the input term;generating, by the natural language processing engine, a ...

Подробнее
Номер записи: 32
14-01-2016 дата публикации

AUTOMATICALLY LINKING TEXT TO CONCEPTS IN A KNOWLEDGE BASE

Номер: US20160012336A1
Автор: Franceschini Michele M., Lastras-Montano Luis A., Soares Livio B., Wegman Mark N.
Принадлежит:

According to an aspect, automatically linking text to concepts in a knowledge base using differential analysis includes receiving a text string and selecting, based on contents of the text string, a plurality of data sources that correspond to concepts in the knowledge base. In a further aspect, automatically linking the text to the concepts includes calculating, for each of the selected data sources, a probability that the text string is output by a language model built using the selected data source, calculating a probability that the text string is output by a generic language model, calculating link confidence scores for each concept based on a differential analysis of the probabilities, and creating a link from the text string to one of the concepts in the knowledge base. The creating is based on a link confidence score of the concept being more than a threshold value away from a prescribed threshold. 1. A method for automatically linking text to concepts in a knowledge base using a differential analysis , the method comprising:receiving a text string;selecting a plurality of data sources that correspond to concepts in the knowledge base, the selecting based on contents of the text string;calculating, for each of the selected data sources, a probability that the text string is output by a language model built using the selected data source;calculating a probability that the text string is output by a generic language model;calculating link confidence scores for each concept based on a differential analysis of the probabilities; andcreating a link from the text string to one of the concepts in the knowledge base, the creating based on a link confidence score of the concept being more than a threshold value away from a prescribed threshold.2. The method of claim 1 , wherein the differential analysis compares the probability that the text string is output by a language model built using a data source to the probability that the text string is output by a generic ...

Подробнее
Номер записи: 33
11-01-2018 дата публикации

HYBRID REASONING-BASED NATURAL LANGUAGE QUERY ANSWERING SYSTEM AND METHOD

Номер: US20180011927A1
Автор: BAE Yong Jin, CHOI Mi Ran, HEO Jeong, JANG Myung Gil, KIM Hyun Ki, LEE Chung Hee, LEE Hyung Jik, LIM Joon Ho, LIM Soo Jong, Park Sang Kyu
Принадлежит:

Provided is a natural language query answering method. The natural language query answering method includes generating a query axiom from an input query, generating answer candidates from the input query, filtering the answer candidates based on a similarity between the query axiom and the answer candidates, reasoning out the answer candidates by using at least one of an inductive reasoning method, a deductive reasoning method, and an abductive reasoning method, calculating reliability of the answer candidates, determining ranks of the answer candidates based on the calculated reliability, and comparing a threshold value with a reliability ratio of reliability of an answer candidate determined as No. 1 rank to reliability of an answer candidate determined as No. 2 rank, readjusting the determined ranks according to a result of the comparison, and detecting a No. 1 rank answer candidate, determined through the readjustment, as a final answer. 1. A natural language query answering method comprising:generating a query axiom from an input query through a textual entailment recognition process;generating answer candidates from the input query, based on a structured knowledge base and an unstructured knowledge base;filtering the answer candidates, based on a similarity between the query axiom and the answer candidates;reasoning out the answer candidates by using at least one of an inductive reasoning method, a deductive reasoning method, and an abductive reasoning method;calculating reliability of the answer candidates by using the query axiom, the filtered answer candidates, the reasoned answer candidates as features to determine ranks of the answer candidates, based on the calculated reliability; andcomparing a threshold value with a reliability ratio of reliability of an answer candidate determined as No. 1 rank to reliability of an answer candidate determined as No. 2 rank, readjusting the determined ranks according to a result of the comparison, and detecting a No. 1 ...

Подробнее
Номер записи: 34
11-01-2018 дата публикации

CONCEPT-BASED SEARCH AND CATEGORIZATION

Номер: US20180011929A1
Автор: Unitt Ashley
Принадлежит:

A system and method for concept-based search and categorization that uses a lexical database to take a search term and from this to build a set of concepts and related terms and then searches stemmed or lemmatized text from a call transcription, email or chat message to perform categorization based on these concepts. 1. A system for concept-based search and categorization , comprising: receive an interaction via a network,', "produce a full-text transcript of the interaction's content, and", 'store the full-text transcript in a searchable database;, 'a network-connected media server computer comprising at least a processor, a memory, and a plurality of programming instructions stored in the memory, the programming instructions, when executed by the processor, cause the processor to create a plurality of search terms from the full-text transcript retrieved from the searchable database;', 'perform a plurality of stemming or lemmatizing operations on the plurality of search terms;', 'query a lexical database via the network using the plurality of search terms to find a plurality of additional search terms, the plurality of additional search terms related and similar to the plurality of search terms;', 'expand, using the plurality of additional search terms, the plurality of search terms into an expanded search query;', 'search at least a portion of the searchable database based at least in part on the expanded search query to create a plurality of search results; and', 'produce a stemmed or lemmatized transcript based on at least a portion of the plurality of search results;', 'store the stemmed or lemmatized transcript in the searchable database., 'a network-connected concept-based search engine comprising at least another processor, another memory, and another plurality of programming instructions stored in the another its memory, the another plurality of programming instructions, when executed by the another processor, cause the another processor to2. A method for ...

Подробнее
Номер записи: 35
11-01-2018 дата публикации

SYSTEM AND METHOD FOR PROVIDING AN ENRICHED SENSORY RESPONSE TO ANALYTICS QUERIES

Номер: US20180011930A1
Автор: AZARIA Adi, BOYANGU Guy, FARKASH Eldad, LEVY YURISTA Guy, MARKO Ophir, Orad Amir
Принадлежит: Sisense Ltd.

A system and method for providing sensory analytics responses. The method comprises collecting raw data from a plurality of data sources; extracting, from the collected raw data, a subset of the raw data to be analyzed; generating, based on the extracted subset of the raw data, an analytics dataset, wherein the analytics dataset includes a performance indicator; determining, based on at least one received input, at least one query; determining, based on the generated analytics dataset, a response to the at least one query, wherein the response includes at least one sensory output; and causing projection of the determined at least one sensory output. 1. A method for providing sensory analytics responses , comprising:collecting raw data from a plurality of data sources;extracting, from the collected raw data, a subset of the raw data to be analyzed;generating, based on the extracted subset of the raw data, an analytics dataset, wherein the analytics dataset includes a performance indicator;determining, based on at least one received input, at least one query;determining, based on the analytics dataset, a response to the at least one query, wherein the response includes at least one sensory output; andcausing projection of the determined at least one sensory output.2. The method of claim 1 , wherein the analytics dataset is generated based on a subset of the collected raw data.3. The method of claim 1 , wherein determining the at least one query further comprises:parsing at least one textual input, wherein the at least one textual input is based on the at least one received input.4. The method of claim 3 , further comprising:determining, based on the at least one received input, the at least one textual input, wherein determining the at least one textual input includes at least one of: speech-to-text processing, and machine imaging.5. The method of claim 1 , further comprising:identifying, for each query, a user account providing the query, wherein the response is ...

Подробнее
Номер записи: 36
11-01-2018 дата публикации

Method and system for providing sales information and insights through a conversational interface

Номер: US20180012163A1
Автор: Adam Kenneth Hosp, Andrew J. Smith, Michael K. FORBIS, Siddique HAMEED, Stewart BOLING, Ted P. SANDERS, JR.
Принадлежит: Mastercard International Inc

A method and system are described that provide responses to natural language queries regarding the performance of a business. The method and system processes data from multiple data sources including information generated by the business and analyzes the data to provide actionable suggestions as to how to determine how to improve the performance of the business. The use of natural language queries allows for a merchant without a business intelligence background obtain these insights easily.

Подробнее
Номер записи: 37
11-01-2018 дата публикации

TEXT TRANSLATION USING CONTEXTUAL INFORMATION RELATED TO TEXT OBJECTS IN TRANSLATED LANGUAGE

Номер: US20180012278A1
Автор: Chelly Yan
Принадлежит:

In an example embodiment, input is received from a first user of a computer system. A text object relating to a first item from the input is created, and translated from a first language to a second language. A plurality of text objects, in the second language, having text similar to the translated text object, are located in a database, each text object comprising textual information pertaining to the first item. The plurality of text objects having text similar to the translated text are then ranked based on a comparison of the contextual information about the first item and the contextual information stored in the database for the plurality of text objects having text similar to the translated text object. At least one of the ranked text objects is translated to the first language. 1. (canceled)2. An apparatus comprising:a memory storing a database of text objects pertaining to items, the database further including contextual information about the items;a translation module executable by a processor and configured to translate a text object created from input received from a first user about a first item from a first language to a second language;a context ranking module configured to locate, in the database, a plurality of text objects, in the second language, having text similar to the translated text object, and to rank the plurality of text objects having text similar to the translated text object based on a comparison of contextual information about the first item and the contextual information stored in the database for the plurality of text objects having text similar to the translated text object;the translation module further configured to translate at least one of the ranked text objects to the first language; anda display module presenting the translated at least one of the ranked text objects.3. The apparatus of claim 2 , further comprising a feedback module configured to receive feedback from the first user used to select one of the at least one ...

Подробнее
Номер записи: 38
10-01-2019 дата публикации

Conversational/multi-turn question understanding using web intelligence

Номер: US20190012373A1
Автор: Jiarui Ren, Manish Malik, Qifa Ke
Принадлежит: Microsoft Technology Licensing LLC

Conversational or multi-turn question understanding using web intelligence is provided. An intelligent query understanding system is provided for receiving a context-dependent query from a user, obtaining contextual information related to the context-dependent query, and reformatting the context-dependent query as one or more reformulations based on the contextual information. The intelligent query understanding system is further operative to query a search engine with the one or more reformulations, receive one or more candidate results, and select a highest ranked reformulation based on the candidate results. The system can provide the highest ranked reformulation of the highest ranked reformulation as a response.

Подробнее
Номер записи: 39
10-01-2019 дата публикации

SYSTEMS AND METHODS FOR CROSS-MEDIA EVENT DETECTION AND COREFERENCING

Номер: US20190012374A1
Автор: Carstens Lucas, Duprey John, Leidner Jochen, Nourbakhsh Armineh, Nugent Tim, Panic Zarko, Petroni Fabio, RAMAN Natraj, Shah Sameena
Принадлежит:

A method of providing cross-media event linking may include: receiving, at a first input of an event coreferencing system, a stream of social media postings, and at a second input, a stream of news articles; generating, by the event coreferencing system, a first set of event representations representing events referenced by the social media postings, and a second set of event representations representing events referenced by the news articles; determining, by the event coreferencing system, that at least one of the social media postings references a same event referenced by at least one of the news articles, the determining including determining at least one similarity using data of at least one of the first set of event representations corresponding to the at least one of the social media postings and data of at least one of the second set of event representations corresponding to the at least one of the news articles; and transmitting, by an output of the event resolution system to the user system, an alert including at least one coreferenced event representation representing the event referenced by the at least one of the social media postings and the at least one of the news articles. 1. A method of providing cross-media event linking , the method comprising:receiving, at a first input of an event coreferencing system, a stream of social media postings, and at a second input of the event coreferencing system, a stream of news articles;generating, by the event coreferencing system, a first set of event representations representing events referenced by the social media postings, and a second set of event representations representing events referenced by the news articles;determining, by the event coreferencing system, that at least one of the social media postings references a same event referenced by at least one of the news articles, the determining including determining at least one similarity using data of at least one of the first set of event representations ...

Подробнее
Номер записи: 40
11-01-2018 дата публикации

FOLLOW-UP VOICE QUERY PREDICTION

Номер: US20180012594A1
Автор: Baeuml Martin, BEHZADI Behshad, Osmakov Dmitry, Skobeltsyn Gleb
Принадлежит:

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting follow-up queries to an initial transcription of an utterance. In some implementations, one or more follow-up queries that are pre-associated with a transcription of an initial utterance of a user are identified. A new or modified language model in which a respective probability associated with one or more of the follow-up queries is increased with respect to an initial language model is obtained. Subsequent audio data corresponding to a subsequent utterance of the user is then received. The subsequent audio data is processed using the new or modified language model to generate a transcription of the subsequent utterance. The transcription of the subsequent utterance is then provided for output to the user. 1. A computer-implemented method comprising:identifying one or more follow-up queries that are pre-associated with a term that matches a transcription of an initial utterance of a user, wherein the follow-up queries are (i) different than the term, and (ii) are pre-associated with the term based on query log data indicating that other users of a search engine have previously submitted the follow-up queries after submitting an initial query that includes the term;adjusting an initial language model to generate a modified language model, the modified language model specifying a respective probability associated with one or more of the follow-up queries that is increased with respect to the initial language model;receiving subsequent audio data corresponding to a subsequent utterance of the user;processing the subsequent audio data using the modified language model to generate a transcription of the subsequent utterance; andproviding the transcription of the subsequent utterance for output to the user.2. The method of claim 1 , further comprising:receiving initial audio data corresponding to an initial utterance of a user; andprocessing the audio data ...

Подробнее
Номер записи: 41
15-01-2015 дата публикации

AUTOMATED CONFIRMATION AND DISAMBIGUATION MODULES IN VOICE APPLICATIONS

Номер: US20150019228A1
Автор: AKOLKAR RAHUL P., Kleindienst Jan, Moore Victor S., Nahamoo David, Wiecha Charles F.
Принадлежит:

A method for providing a voice application includes executing control flow logic modeling a dialog flow with a user via a voice browser. The control flow logic produces a disambiguation requirement. A disambiguation module is initiated and a set of at least two candidates and partitioning criteria is sent from the control flow logic to the module. Attributes of the candidates are analyzed to determine a partitioning score for each attribute indicative of ability to distinguish between candidates based on the partitioning criteria. The attributes are sorted based on the partitioning scores. The user is queried based on a top-sorted attribute and results of the query are used to reduce the set of candidates. The steps of analyzing, sorting, and querying are repeated until the set of candidates is reduced to a single candidate. The single candidate is returned to the control flow logic for continued execution. 1. A method for providing a voice application , comprising:executing control flow logic modeling a dialog flow with a user via a voice browser, the control flow logic producing a disambiguation/confirmation requirement;initiating a disambiguation/confirmation module in response to the disambiguation/confirmation requirement;sending a set of at least two candidates and partitioning criteria from the control flow logic to the disambiguation/confirmation module;analyzing attributes of the set of candidates to determine a partitioning score for each attribute indicative of that attribute's ability to distinguish between the at least two candidates based on the partitioning criteria;sorting the attributes based on their corresponding partitioning scores;querying the user based on a top-sorted attribute and use results of the query to at least reduce the set of candidates;repeat the steps of analyzing, sorting, and querying until the set of candidates is reduced to a single candidate; andreturn the single candidate from the disambiguation/confirmation module to the ...

Подробнее
Номер записи: 42
19-01-2017 дата публикации

TERMINAL, SYSTEM, METHOD, AND PROGRAM FOR PRESENTING SENTENCE CANDIDATE

Номер: US20170017718A1
Автор: NAKAYAMA Yoshiharu, Saito Satoru
Принадлежит:

The present invention is to provide a terminal for presenting a sentence candidate that presents a candidate to improve the work efficiency and to standardize a sentence, when a report is generated. The terminal for presenting a sentence candidate is capable of presenting a more appropriate sentence candidate by including a report data base that stores a report including a plurality of sentences, searching the report data base by an input character, generating a report group including a plurality of reports as a search result, extracting a sentence containing a character input from the report group to generate a sentence group, and preferentially outputting a predetermined sentence based on a priority. 1. A terminal for presenting a sentence candidate , comprising:a report data base that stores a report including a plurality of sentences;a character input unit that receives an input of a character from a user;a report group generation unit that searches the report data base by the input character and generates a report group including a plurality of reports as a search result;a sentence group generation unit that extracts a sentence containing the character from each report included in the report group and generates a sentence group from a plurality of sentences extracted from the each report; anda sentence output unit that preferentially outputs a predetermined sentence from the sentence group based on a frequency of using the character.2. A terminal for presenting a sentence candidate , comprising:a report data base that stores a report including a plurality of sentences;a sentence selection unit that receives a selection of a sentence from a user;a report group generation unit that searches the report data base by the selected sentence and generates a report group including a plurality of reports as a search result;a sentence group generation unit that extracts a sentence right after the selected sentence from each report included in the report group and ...

Подробнее
Номер записи: 43
15-01-2015 дата публикации

Assignment of designations for measurement signals and devices from a first identification system to a second identification system within project planning for a technical installation

Номер: US20150019524A1
Автор: Andreas Geiger, Klaus Wendelberger, Thorsten Fuhring
Принадлежит: SIEMENS AG

A method and device for assigning measurement signal and device designations from a first to a second classification system within a projection of a technical system is provided. The process is implemented in an automated manner by a search engine. A measurement signal or device designation from the first classification system is entered into the search engine and converted into a search query. The text elements of the search query are processed, wherein text elements are semantically analyzed using terminology and compared with those of a list which contains all the designations from the second classification system. The text elements from the list which best match those of the search query are evaluated with respect to relevance and outputted as search results of the search engine. The search result with the maximum relevance corresponds to the designation from the second classification system and replaces designation from the first classification system.

Подробнее
Номер записи: 44
15-01-2015 дата публикации

Methods and devices for providing a text prediction

Номер: US20150019539A1
Автор: Andrew Douglas Bocking, Christopher Wormald, Conrad Delbert Seaman, Gerald Beard, William Alexander Cheung
Принадлежит: BlackBerry Ltd

A method for use in an electronic device including a display and a keyboard, the method including: receiving input reflecting selection of one or more characters through the keyboard; generating a predicted string of one or more characters based on the received input; determining a confidence value for the predicted string, based on a determination that the received input associated with a first one of the one or more selected characters reflects more than a single tap on a key of the keyboard; and displaying the predicted string on the display based on the determined confidence value.

Подробнее
Номер записи: 45
21-01-2016 дата публикации

Observation-based query interpretation model modification

Номер: US20160019292A1
Автор: Amir M. Netz, Christopher A. Hays, Patrick J. Baumgartner, Pedram Faghihi Rezaei
Принадлежит: Microsoft Technology Licensing LLC

The modifying of a natural language interpretation model for interpreting natural language queries. The system discovers modifications that one or more queriers made to one or more original query results of one or more natural language queries to generate one or more modified query results. The system then uses the discoveries to identify one or more changes to a natural language interpretation model that would result (given the same natural language queries) in one or more query results that more accurately reflect the one or more modified query results. The system the causes the natural language interpretation model to be modified with at least one of the one or more identified changes. Accordingly, over time, the natural language interpretation model may learn from observations of its own performance.

Подробнее
Номер записи: 46
21-01-2016 дата публикации

Interpreting and Distinguishing Lack of an Answer in a Question Answering System

Номер: US20160019293A1
Автор: Anand B. Bhagwat, John P. Bufe, III, Timothy P. Winkler
Принадлежит: International Business Machines Corp

A mechanism is provided in a computing system for interpreting and distinguishing a lack of an answer to an input question. The mechanism receives an input question from a user. The mechanism generates one or more hypotheses based on a corpus of source information. The mechanism injects a no-answer response into the one or more hypotheses to form a plurality of candidate answers. The mechanism ranks the plurality of candidate answers based on evidence scoring and confidence scoring to form a candidate answer ranking. Responsive to determining the no-answer response is the top candidate answer in the candidate answer ranking, the mechanism presents the no-answer response to the user.

Подробнее
Номер записи: 47
18-01-2018 дата публикации

AUTOMATIC ONTOLOGY GENERATION FOR INTERNET OF THINGS APPLICATIONS

Номер: US20180018393A1
Автор: Fenoglio Enzo, Friel Joseph T., Latapie Hugo, Rai Pete, Surcouf Andre
Принадлежит:

A method comprises collecting, by a computing device located at an edge of a network, data items corresponding to information transmitted by endpoints using the network, generating, by the computing device, a probabilistic hierarchy using the data items, generating, by the computing device using the probabilistic hierarchy and natural language data, a similarity metric, generating, by the computing device using the probabilistic hierarchy, the natural language data, and the similarity metric, an ontology, detecting, by the computing device using the ontology, an anomaly, and in response to detecting the anomaly, sending a notification. 1. A method comprising:collecting, by a computing device located at an edge of a network, a plurality of data items corresponding to information transmitted by a plurality of endpoints using the network;generating, by the computing device, a probabilistic hierarchy using the plurality of data items;generating, by the computing device using the probabilistic hierarchy and natural language data, a similarity metric;generating, by the computing device using the probabilistic hierarchy, the natural language data, and the similarity metric, an ontology;detecting, by the computing device using the ontology, an anomaly;in response to detecting the anomaly, sending a notification.2. The method of claim 1 , further comprising:sending, by the computing device, the ontology to a server;combining, by the server, the ontology with a plurality of other ontologies received from other computing devices within the network, to generate a complete ontology for the network.3. The method of claim 2 , wherein the ontology is compressed prior to sending the ontology to the server.4. The method of claim 1 , wherein the computing device is a network infrastructure device.5. The method of claim 1 , wherein the network comprises a smart building.6. The method of claim 1 , wherein the plurality of endpoints comprise one or more of: a motion detector claim 1 , a ...

Подробнее
Номер записи: 48
17-01-2019 дата публикации

KNOWLEDGE MAP-BASED QUESTION-ANSWER METHOD, DEVICE, AND STORAGE MEDIUM

Номер: US20190018839A1
Автор: GE Canhui, HUA NENGWEI, JIANG Xiaoxi, Yang Feng, ZHU Hangcheng
Принадлежит:

Knowledge map-based question-answer method, server, and storage medium are provided. The method includes obtaining a natural query sentence inputted by a user, and identifying a globally unique identifier, with respect to the knowledge map, of an entity in the natural query sentence. The knowledge map includes attributes and attribute values of entities and relationships thereof. The method also includes according to a context-free grammar rule, parsing the natural query sentence into a syntax tree, and according to the syntax tree, obtaining a logical expression corresponding to the natural query sentence. Moreover, the method includes according to the logical expression and the globally unique identifier of the entity, generating a machine query sentence corresponding to the knowledge map. Further, the method includes according to the machine query sentence, querying a question-answer result corresponding to the machine query sentence in the knowledge map, and feeding back the question-answer result to the user. 1. A knowledge map-based question-answer method , comprising:obtaining a natural query sentence inputted by a user, and identifying a globally unique identifier, with respect to the knowledge map, of an entity in the natural query sentence, wherein the knowledge map includes attributes and attribute values of entities and relationships between the entities;according to a context-free grammar rule, parsing the natural query sentence into a syntax tree, and according to the syntax tree, obtaining a logical expression corresponding to the natural query sentence;according to the logical expression and the globally unique identifier of the entity, generating a machine query sentence corresponding to the knowledge map; andaccording to the machine query sentence, querying a question-answer result corresponding to the machine query sentence in the knowledge map, and feeding back the question-answer result to the user.2. The method according to claim 1 , wherein ...

Подробнее
Номер записи: 49
17-01-2019 дата публикации

DYNAMIC MANAGEMENT OF RELATIVE TIME REFERENCES IN DOCUMENTS

Номер: US20190018840A1
Автор: Baroni Alessandro, Fionchetti Emanuela, Ghezzi Alessandro, SGRO ANTONIO M., Usai Marta
Принадлежит:

A method, computer system, and computer program product for accessing documents is provided. The method includes providing a document having one or more original time references having corresponding meanings depending on one or more time bases, identifying the original time references in the document, generating corresponding time artifacts for the original time references, the time artifacts including corresponding time values being calculated from the corresponding original time references according to the time bases and/or corresponding calculation instructions for calculating the corresponding time values from the corresponding original time references according to the time bases, and associating the corresponding time artifacts with the original time references for outputting the corresponding time values. 1. A method for accessing documents , the method comprising:identifying, by the processor, at least one original time reference in a document;generating, by the processor, a corresponding time artifact for the at least one original time reference;associating, by the processor, the corresponding time artifacts with the at least one original time reference for outputting the corresponding time values;generating, by the processor, the corresponding time artifacts to comprise corresponding translated time references, each translated time reference comprising the corresponding time values and a text corresponding to the meaning of the corresponding at least one original time reference, which changes the meaning of the at least one original time reference to a user accessing the document, independently of a time at which the document is accessed;generating, by the processor, a translated document from the document by replacing the at least one original time reference with the corresponding translated time references; andoutputting, by the processor, the translated document in place of the document.2. The method according to claim 1 , wherein the at least one ...

Подробнее
Номер записи: 50
17-01-2019 дата публикации

DETERMINING TONE DIFFERENTIAL OF A SEGMENT

Номер: US20190018893A1
Автор: "DSilva Charmaine Cynthia Rose", Chen Jindong, Chia Chih-Chun, Davidson James, Mengle Advay, Noble Isaac, Patterson Anna, Weiss Tania Bedrax
Принадлежит:

Methods and apparatus for determining a tone differential between a given segment of a document and a larger segment of the document. The tone differential may be based on comparison of a first tone associated with the given segment and a second tone associated with the larger segment. The tone differential is indicative of the variance between the tone of the given segment and the tone of the larger segment. 1. A computer-implemented method , comprising:identifying a message trail utilizing one or more processors;determining, utilizing one or more of the processors, a first tone associated with a given segment of the message trail based at least in part on one or more segment terms of the given segment, wherein the given segment is typed by a user via an application executing on a client device of the user;determining, utilizing one or more of the processors, a second tone associated with at least one or more additional segments of the message trail, wherein the at least one or more additional segments represent a larger portion of the message trail than the given segment, and wherein the one or more additional segments include at least one additional segment, from the message trail, that is from an additional user, that is directed to at least the user, and that precedes, in time, the given segment typed by the user; the first tone associated with the given segment, and', 'the second tone associated with the one or more additional segments; and, 'determining, utilizing one or more of the processors, a tone differential between the given segment and the at least one or more additional segments based on comparison ofproviding, for presentation by the client device via the application via which the user typed the given segment, output that is based on the determined tone differential and that indicates variance of the given segment of the message trail from the one or more additional segments of the message trail.2. (canceled)3. (canceled)4. The computer-implemented ...

Подробнее
Номер записи: 51
17-01-2019 дата публикации

AUTOMATIC CONFIGURATION OF COGNITIVE ASSISTANT

Номер: US20190019077A1
Автор: Griffin Keith, Lepore Michael P.
Принадлежит:

The present technology is an automatically configuring virtual assistant. The virtual assistant is assigned to an existing conversation space and, based on analyzing the existing conversation space the virtual assistant has been assigned to, is associated with at least one contextual cue of an existing conversation space. The analysis includes natural language processing of a title, a topic, or a past conversation of the existing conversation space in order to determine the at least one contextual cue. 1. A method of automatically configuring a virtual assistant comprising:receiving an assignment of the first virtual assistant to an existing conversation space, wherein the assignment includes the first virtual assistant as a participant in the existing conversation space;analyzing the existing conversation space to determine at least one contextual cue of the existing conversation space, wherein the analyzing includes natural language processing of a title, a topic, or a past conversation of the existing conversation space; andassociating the first virtual assistant with the at least one contextual cue.2. The method of claim 1 , comprising:receiving a request for assistance with a topic;determining that the topic relates to the at least one contextual cue associated with the first virtual assistant; andsending the topic to the first virtual assistant for submission to the conversation space by the first virtual assistant.3. The method of claim 1 , wherein the first virtual assistant is assigned to multiple existing conversation spaces claim 1 , each existing conversation space associated with a functional chat room comprised of expert participants.4. The method of claim 1 , wherein the first virtual assistant analyzes the existing conversation space by using natural language understanding to parse at least a portion of past content of the existing conversation space.5. The method of claim 4 , wherein the first virtual assistant parses the past content to determine ...

Подробнее
Номер записи: 52
22-01-2015 дата публикации

PROVIDING ANSWERS TO QUESTIONS USING LOGICAL SYNTHESIS OF CANDIDATE ANSWERS

Номер: US20150026169A1
Автор: Brown Eric W., Chu-Carroll Jennifer, Ferrucci David A., Lally Adam P., Murdock James W., Prager John M.
Принадлежит:

A method, system and computer program product for generating answers to questions. In one embodiment, the method comprises receiving an input query, decomposing the input query into a plurality of different subqueries, and conducting a search in one or more data sources to identify at least one candidate answer to each of the subqueries. A ranking function is applied to each of the candidate answers to determine a ranking for each of these candidate answers; and for each of the subqueries, one of the candidate answers to the subquery is selected based on this ranking. A logical synthesis component is applied to synthesize a candidate answer for the input query from the selected the candidate answers to the subqueries. In one embodiment, the procedure applied by the logical synthesis component to synthesize the candidate answer for the input query is determined from the input query. 1. A method of generating an answer to a question , comprising:receiving an input query;using the input query to determine a plurality of sub-queries, wherein each of the subqueries has an associated answer, and the answers to the subqueries are used to determine an answer to the input query;conducting a search in one or more data sources to identify at least one candidate answer to each of the subqueries;for each of the subqueries, selecting one of the candidate answers to the subquery;using the input query to determine a procedure for using the selected ones of the candidate answers to determine a candidate answer to the input query; andusing said determined procedure to use the selected ones of the candidate answers to determine a candidate answer to the input query.2. The method according to claim 1 , wherein the using said determined procedure includes applying a logical synthesis component for synthesizing the candidate answer for the input query from the selected candidate answers to the subqueries.3. The method according to claim 1 , wherein the determining the procedure for using ...

Подробнее
Номер записи: 53
26-01-2017 дата публикации

Personal knowledge graph population from declarative user utterances

Номер: US20170024375A1
Автор: Dilek Hakkani-Tur, Gokhan Tur, QI Li, Xiang Li
Принадлежит: Microsoft Technology Licensing LLC

An “Utterance-Based Knowledge Tool” monitors user utterances (e.g., user speech or text inputs) to identify relevant statements of facts in declarative utterances of a user. A semantic parser is applied to each statement of facts to parse assertions comprising instances of two or more entities and relations between those entities. As such, each assertion explicitly delimits a relation between two particular entities (one of which may be the user) that are relevant to the particular user. The Utterance-Based Knowledge Tool places or categorizes the identified assertions (which each include entities and relations) into one or more of a plurality of predefined classes. These classified assertions are then applied to construct and/or update a personal knowledge graph for the user. This personal knowledge graph is then applied to respond to user queries, thereby improving personal relevancy of query responses provided to the user.

Подробнее
Номер записи: 54
26-01-2017 дата публикации

CONTEXT SENSITIVE QUERY EXPANSION

Номер: US20170024461A1
Автор: Mac an tSaoir Seamus R., McCloskey Daniel J., Salem Ahmed M.M.R, Sogrin Mikhail
Принадлежит:

A processor expands a search expression. The processor determines nodes representing query terms of a search expression. The nodes have associated text for search term expansion, and represent at least one concept in a semantic graph of nodes that represents a domain of semantically related concepts. The processor determines i) a center of focus within the semantic graph for the two or more nodes based, at least in part, on a spreading activation in the graph and ii) a contextual relevance for the two or more nodes with respect to node the center of focus. The processor selects, for a query term, a node based on contextual relevance between that node and the query term and expands the search expression using an associated text of that node. 19-. (canceled)10. A computer program product for expanding a search expression , the computer program product comprising: program instructions to determine two or more nodes representing two or more query terms of a search expression, wherein the two or more nodes each have an associated text for search term expansion and represent at least one concept in a semantic graph of nodes that represents a domain of semantically related concepts;', 'program instructions to determine a center of focus within the semantic graph for the two or more nodes based, at least in part, on a spreading activation in the semantic graph;', 'program instructions to determine a contextual relevance for the two or more nodes with respect to node the center of focus;', 'program instructions to select for a query term, which is included in the two or more query terms of the search expression, at least one node from the two or more nodes based, at least in part, on a contextual relevance between the at least one node and the query term; and', 'program instructions to expand the search expression using an associated text of the at least one node., 'one or more computer-readable storage media and program instructions stored on the one or more computer- ...

Подробнее
Номер записи: 55
26-01-2017 дата публикации

ASSOCIATING A TEXT MESSAGE CONTAINING AN ANSWER WITH A TEXT MESSAGE CONTAINING A QUESTION

Номер: US20170024462A1
Автор: Allen Corville O., Maldari Mario A., Senior Monica A., Smith Paul A.
Принадлежит:

A first text message containing a first question can be received from a first user. A second text message containing a second question can be received from the first user or a second user. A third text message containing an answer can be received from a third user. Whether the third user begins typing the third text message after the first text message is received and before the second text message is received can be determined. Responsive to determining that the second user begins typing the third text message after the first text message is received and before the second text message is received, a determination can be made that the answer pertains to the first question. Responsive to determining that the answer pertains to the first question, the third text message can be configured for presentation in a manner indicating that the answer pertains to first question. 1. A method comprising:receiving from a first user a first text message containing a first question;receiving from the first user or a second user a second text message containing a second question;receiving from a third user a third text message containing an answer;automatically determining whether the third user begins typing the third text message after the first text message is received and before the second text message is received;responsive to determining that the second user begins typing the third text message after the first text message is received and before the second text message is received, automatically determining, using a processor, that the answer pertains to the first question; andresponsive to determining that the answer pertains to the first question, configuring the third text message for presentation to the third user, and the first user or the second user, on respective displays in a manner indicating that answer contained in the third text message pertains to first question contained in the first text message and does not pertain to the second question contained in the ...

Подробнее
Номер записи: 56
26-01-2017 дата публикации

Authorship Enhanced Corpus Ingestion for Natural Language Processing

Номер: US20170024463A1
Автор: Bastide Paul R., Broomhall Matthew E., Loredo Robert E., Lu Fang
Принадлежит:

Mechanisms for processing a corpus of information in a natural language processing system are provided. A corpus of information to process is identified and a set of author profiles associated with the corpus of information is retrieved. A content profile is generated for a portion of content of the corpus of information and the content profile is compared to the set of author profiles to generate an association of the content profile with at least one author profile in the set of author profiles. In addition, a processing operation of the natural language processing (NLP) system is controlled based on the association of the content profile with the at least one author profile. 1. A method , in a data processing system comprising a processor and a memory , for processing a corpus of information in a natural language processing system , the method comprising:identifying, by the data processing system, a corpus of information to process;retrieving, by the data processing system, a set of author profiles associated with the corpus of information;presenting, by the data processing system, a user interface that comprises the set of author profiles, through which a user input is received specifying a user selection of at least one user selected author profile in the set of author profiles;generating, by the data processing system, a content profile for a portion of content of the corpus of information;comparing, by the data processing system, the content profile to the set of author profiles to generate an association of the content profile with at least one author profile in the set of author profiles; andcontrolling a processing operation of the natural language processing (NLP) system based on the association of the content profile with the at least one author profile and a determined level of correspondence of the at least one author profile with the at least one user selected author profile, wherein the processing operation is an ingestion operation that ingests ...

Подробнее
Номер записи: 57
26-01-2017 дата публикации

CONDITIONAL STRING SEARCH

Номер: US20170024464A1
Автор: BOYCE Kevin Gerard
Принадлежит: TREND MICRO INCORPORATED

A method and a system for efficient search of string patterns characterized by positional relationships in a character stream are disclosed. The method is based on grouping string patterns of a dictionary into at least two string sets and performing string search processes of a text of the character stream based on individual string sets with the outcome of a search process influencing a subsequent search process. A system implementing the method comprises a dictionary processor for generating string sets with corresponding text actions and search actions, a conditional search engine for locating string patterns belonging to at least one string set in a text according to a current search state, a text operator for producing an output text according to search results, and a search operator for determining a subsequent search state. 1. A method of ascertaining presence , within a text , of a set of string patterns of a dictionary , the method comprising:sorting said string patterns into a set of string categories according to known interrelationships among the string patterns; a respective search domain within said text;', 'a respective search method; and', 'respective rules for transition to other search states;, 'defining each search state of a set of search states according to repeatedly perform a search procedure with successive search states, starting with an initial search state of said set of search states and an initial string category of said set of string categories; and', 'terminate said search procedure upon ascertaining that a current search state has no successor search state., 'executing software instructions to cause a processor to2. The method of further comprising associating with each string pattern of said set of string patterns a respective text action comprising at least one of: marking claim 1 , altering claim 1 , substitution claim 1 , and deletion of a string pattern found in said text.3. The method of wherein said interrelationships include a ...

Подробнее
Номер записи: 58
26-01-2017 дата публикации

SYSTEM AND METHOD FOR NATURAL LANGUAGE DRIVEN SEARCH AND DISCOVERY IN LARGE DATA SOURCES

Номер: US20170024465A1
Автор: Douglas Benjamin, Jarrold William, Patel-Schneider Peter, Ramachandran Deepak, Ratnaparkhi Adwait, Yeh Peter
Принадлежит:

In some natural language understanding (NLU) applications, results may not be tailored to the user's query. In an embodiment of the present invention, a method includes tagging elements of automated speech recognition (ASR) data based on an ontology stored in a memory. The method further includes indexing tagged elements to an entity of the ontology. The method further includes generating a logical form of the ASR data based on the tagged elements and the indexed entities. The method further includes mapping the logical form to a query to a respective corresponding database stored in the memory. The method further includes issuing the query to the respective corresponding databases. The method further includes presenting results of the query to the user via a display or a voice response system. 1. A computer-implemented method comprising:in response to automated speech recognition (ASR) data, sending at least one coordinated request to a plurality of processing modules or plurality of data sources, each coordinated request based on an ontology common to the plurality of processing modules and the plurality of data sources;based on at least one response to the at least one coordinated request from one of the plurality of processing modules or the plurality of data sources, dynamically determining (a) a result or (b) a next coordinated request, including data of the request and which of the plurality of processing modules or the plurality of data sources is the destination.2. The computer-implemented method of claim 1 , wherein the dynamically determined requests include:tagging elements of the ASR data based on the ontology stored in a memory;indexing tagged elements to an entity of the ontology;generating a logical form of the ASR data based on the tagged elements corresponding to the entities of the ontology and the indexed entities;mapping the logical form to at least one query to at least one respective corresponding database stored in the memory;issuing the at ...

Подробнее
Номер записи: 59
25-01-2018 дата публикации

ENCODING APPARATUS, SEARCH APPARATUS, ENCODING METHOD, AND SEARCH METHOD

Номер: US20180024990A1
Автор: IDEUCHI Masao, Kataoka Masahiro, NAKAMURA Fumiaki, Okura Seiji
Принадлежит: FUJITSU LIMITED

A computer generates semantic structure information from a document. The semantic structure information includes a plurality of semantic structures in a plurality of sentences in the document and a plurality of morphemes included in each of the plurality of sentences belong to a corresponding semantic structure. The computer generates a plurality of codes by encoding the plurality of morphemes for each of the plurality of sentences. The computer specifies a specific code that corresponds to a specific morpheme from among the plurality of morphemes included in each of the plurality of sentences, wherein at least one morpheme is potentially missing in a semantic structure that the specific morpheme belongs to. The computer adds missing-portion information to the specific code for each of the plurality of sentences. 1. A non-transitory computer-readable recording medium having stored therein an encoding program that causes a computer to execute a process comprising:generating semantic structure information from a document, the semantic structure information including a plurality of semantic structures in a plurality of sentences in the document, a plurality of morphemes included in each of the plurality of sentences belonging to a corresponding semantic structure;generating a plurality of codes by encoding the plurality of morphemes for each of the plurality of sentences;specifying a specific code that corresponds to a specific morpheme from among the plurality of morphemes included in each of the plurality of sentences, wherein at least one morpheme is potentially missing in a semantic structure that the specific morpheme belongs to; andadding missing-portion information to the specific code for each of the plurality of sentences.2. The non-transitory computer-readable recording medium according to claim 1 , whereinthe semantic structure that the plurality of morphemes belong to is expressed by using a plurality of semantic codes that respectively correspond to the ...

Подробнее
Номер записи: 60
25-01-2018 дата публикации

Collaborative Question Interceptor

Номер: US20180025076A1
Автор: Bastide Paul R., DeLuca Lisa Seacat, Price Dana L., SMITH-EIGENBRODE SHELBEE D.
Принадлежит:

Question interception is provided. It is determined that a first user corresponding to a data processing system is composing a message to be transmitted to a second data processing system corresponding to a second user. It is determined whether a question for the second user is identified in the message prior to transmitting the message to the second data processing system. In response to determining that a question is identified in the message, an answer to the question is retrieved from a plurality of data sources. A confidence score is calculated for the answer. It is determined whether the confidence score is greater than or equal to a confidence level threshold value. In response to determining that the confidence score is greater than or equal to the confidence level threshold value, the answer is displayed to the first user prior to transmitting the message to the second data processing system. 1. A computer-implemented method for question interception , the computer-implemented method comprising:determining, by a data processing system, that a first user corresponding to the data processing system is composing an electronic message to be transmitted via a network to a second data processing system corresponding to a second user;determining, by the data processing system, whether a question for the second user is identified in the electronic message prior to transmitting the electronic message to the second data processing system;responsive to the data processing system determining that a question for the second user is identified in the electronic message prior to transmitting the electronic message to the second data processing system, retrieving, by the data processing system, an answer to the question from at least one of a plurality of data sources;calculating, by the data processing system, a confidence score for the answer to the question;determining, by the data processing system, whether the confidence score for the answer to the question is greater ...

Подробнее
Номер записи: 61
26-01-2017 дата публикации

Resource management in a presentation environment

Номер: US20170026377A1
Автор: Adam T. Clark, Aspen L. Payton, John E. Petri, John S. Mysak, Michael D. Pfeifer
Принадлежит: International Business Machines Corp

Aspects of the present disclosure are directed toward managing resources in a presentation environment. Aspects are directed toward collecting, using a set of monitoring devices, context information with respect to a presentation. Aspects are also directed toward determining, based on the context information for the presentation, a subject matter group and a set of access rules for the set of network devices. Aspects are also directed toward identifying, based on the subject matter group, a first set of resources. Aspects are also directed toward establishing, based on the set of access rules and the first set of resources, a first subset of the first set of resources for the set of network devices of the presentation environment.

Подробнее
Номер записи: 62
24-01-2019 дата публикации

Analyzing Concepts Over Time

Номер: US20190026376A1
Автор: Ho Tin Kam, Lastras-Montano Luis A., Shmueli Oded
Принадлежит:

A method and apparatus are provided for automatically generating and processing first and second concept vector sets extracted, respectively, from a first set of concept sequences and from a second, temporally separated, concept sequences by performing a natural language processing (NLP) analysis of the first concept vector set and second concept vector set to detect changes in the corpus over time by identifying changes for one or more concepts included in the first and/or second set of concept sequences. 124-. (canceled)25. A method , in an information handling system comprising a processor and a memory , for analyzing concept vectors to detect changes in a corpus over time , the method comprising:analyzing relationship strengths between concepts that persist in a first set of concept sequences and a second set of concept sequences to identify market trends for answering questions submitted to the information handling system by identifying vector changes for one or more concepts included in the first and/or second set of concept sequences, wherein analyzing relationship strengths comprises:{'b': '1', 'computing, by the system, a first cosine distance between each vector pair Vi, Vj from a first concept vector set V, . . . , Vk derived from the first set of concept sequences over k concepts for all i≠j, 1≤i, j≤k;'}{'b': '1', 'computing, by the system, a second cosine distance between each vector pair V′i, V′j from a second concept vector set V′, . . . , V′k+b derived from the second set of concept sequences over k old and b new concepts for all i≠j, 1≤i, j≤k; and'}identifying concept pairs from the first set of concept sequences whose interrelationship has changed by reporting each concept pair Vi, Vj whereby a subtraction of the second cosine distance from the first cosine distance exceeds a first specified reporting threshold.261. The method of claim 25 , further comprising generating claim 25 , by the system claim 25 , the first concept vector set V claim 25 , . ...

Подробнее
Номер записи: 63
24-01-2019 дата публикации

Analyzing Concepts Over Time

Номер: US20190026379A1
Автор: Luis A. Lastras-Montano, Oded Shmueli, Tin Kam Ho
Принадлежит: International Business Machines Corp

A method and apparatus are provided for automatically generating and processing first and second concept vector sets extracted, respectively, from a first set of concept sequences and from a second, temporally separated, concept sequences by performing a natural language processing (NLP) analysis of the first concept vector set and second concept vector set to detect changes in the corpus over time by identifying changes for one or more concepts included in the first and/or second set of concept sequences.

Подробнее
Номер записи: 64
24-01-2019 дата публикации

IMAGE DATA CAPTURE AND CONVERSION

Номер: US20190026577A1
Автор: Hall John B., JR. Michael J., Pepe, Santhanam Murali, Simpkins Kerry Kurt
Принадлежит:

Embodiments of the present invention provide a system for image capture and conversion. The system receives or captures an image of a resource document comprising image coordinates. The system can then cause a user interface of a computing device to display the image of the resource document and request that a specialist provide an input of an image coordinate area associated with a data field of the resource document. The specialist then provides a selection of boundaries for the coordinate area that encloses a value of the data field within the image of the resource document. The system then applies a data field-specific OCR process to the provided image coordinate area to extract a value of the data field. The extracted value can be presented on the display along with an enlarged view of the image coordinate area to allow the specialist to verify the accuracy of the extracted value. 1. A system for image data capture and conversion , the system comprising:a memory device; and receive an image of a resource document comprising image coordinates associated with the resource document;', 'cause a user interface of a computing device to display the image of the resource document;', 'receive, from the user interface of the computing device, a user input of an expected image coordinate area for a data field;', 'apply a data field-specific optical character recognition process to the expected image coordinate area for the data field to extract a value of the data field; and', 'transmit the extracted value of the data field to a resource processing system., 'a processing device operatively coupled to the memory device, wherein the processing device is configured to execute computer-readable program code to2. The system of claim 1 , wherein the processing device is further configured to execute the computer-readable program code to:store the expected image coordinate data for the data field in a database associated with a source of the resource document or a type of the ...

Подробнее
Номер записи: 65
24-01-2019 дата публикации

METHOD TO LEVERAGE SIMILARITY AND HIERARCHY OF DOCUMENTS IN NN TRAINING

Номер: US20190026646A1
Автор: Kurata Gakuto
Принадлежит:

A computer-implemented method for training a natural language-based classifier, includes obtaining a query and a first label which is a binary vector, each of a plurality of elements of the binary vector being associated with one of a plurality of instances, the first label indicating that the query is classified into a specific instance of the plurality of instances by a value set to a specific element associated with the specific instance, estimating relationships between the specific instance and instances other than the specific instance of the plurality of instances, generating a second label which is a continuous-valued vector from the first label by distributing the value set to the specific element to elements other than the specific element of the plurality of elements according to the relationships, and training the natural language-based classifier using the query and the second label. 1. A computer-implemented method for training a natural language-based classifier , the method comprising:obtaining a query and a first label represented by a binary vector, each of a plurality of elements of the binary vector being associated with at least instance from a plurality of instances, the first label indicating that the query is classified into a specific instance from the plurality of instances by a value set to a specific element associated with the specific instance;estimating relationships between the specific instance and instances other than the specific instance from the plurality of instances;generating a second label represented by a continuous-valued vector from the first label by distributing the value set to the specific element to elements other than the specific element from the plurality of elements according to the relationships; andtraining the natural language-based classifier using the query and the second label.2. The method of claim 1 , wherein the relationships are similarities.3. The method of claim 1 , wherein training includes training ...

Подробнее
Номер записи: 66
29-01-2015 дата публикации

Method of creating classification pattern, apparatus, and recording medium

Номер: US20150032749A1
Автор: Atsushi Kubota, Hirokazu Iwakura, Junichi Higuchi, Masazumi Matsubara, Yasuhiko Kanemasa
Принадлежит: Fujitsu Ltd

A method includes: extracting a partial character string including a reserved word and a character string immediately previous or subsequent to the reserved word from each of a plurality of pieces of target data, the plurality of pieces of target data conforming to a first pattern character string including the reserved word defined by a protocol; detecting target data including the partial character string among the plurality of pieces of target data; specifying a first partial character string from the extracted partial character string based on the detected target data; and creating, by a processor, a second pattern character string for classifying the plurality of pieces of target data based on the first pattern character string and the first partial character string.

Подробнее
Номер записи: 67
02-02-2017 дата публикации

PROTOCOL FOR COMMUNICATION OF DATA STRUCTURES

Номер: US20170031739A1
Автор: Donovan Alan A., Fink Stephen J., Reimer Darrell C., Wegman Mark N.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A system and method are provided for communicating information in a data structure between applications. According to the method, a description of a data structure is sent from a first application to a second application, and there is received from the second application an identification of at least one portion of the data structure that is requested by the second application. The first application marshals a subset of the data structure consisting of the at least one portion that was identified, and there is sent from the first application to the second application the marshalled subset of the data structure. 1. An information processing system comprising:an interface adapted to receive messages from other nodes; anda processor, [ 'a first message from the first node to the second node, wherein the first message comprising a first metadata abstraction identifying a set of data fields and a type of each of the set of data fields for a data structure that comprises a body of the second message to be sent from the first node to the second node, wherein the first metadata abstraction is absent a value for each of the set of data fields;', 'send a request from the first node to the second node, wherein the request allows the first node and the second node to agree upon a meta-data format and describes a structure of at least a second message to be sent from the first node to the second node, wherein the second message comprises at least one query to be serviced by the second node, the request comprising'}, 'after sending the first message comprising the first metadata abstraction, receive, at the first node, a second metadata abstraction from the second node, the second metadata abstraction having been generated based on the first metadata abstraction and identifying which of the data subset of the fields of the data structure are required by the second node to satisfy the query within the second message to be sent from the first node to the second node, where the ...

Подробнее
Номер записи: 68
02-02-2017 дата публикации

Information query

Номер: US20170032024A1
Автор: Haifeng Zhu, Liang Ye, Yuejun Hu
Принадлежит: Alibaba Group Holding Ltd

An example information query method including receiving a query parameter including keyword information and one or more pieces of language feature information; generating one or more query request strings corresponding to the one or more pieces of language feature information respectively according to the keyword information; determining corresponding position intervals of the one or more pieces of language feature information in a second index according to a pre-established first index, the first index including a mapping relationship between the language feature information and the position intervals of the second index, the second index including a mapping relationship between keywords and information pages; and acquiring query results corresponding to the one or more query request strings respectively according to the determined corresponding position intervals of the one or more pieces of language feature information in the second index. The techniques of the present disclosure reduce the cost of multi-language query.

Подробнее
Номер записи: 69
02-02-2017 дата публикации

System and method for performing verifiable query on semantic data

Номер: US20170032025A1
Автор: Shishir Kumar
Принадлежит: Wipro Ltd

This disclosure relates generally to information retrieval, and more particularly to a system and method for verifiable query of semantic data. In one embodiment, a method is provided for performing verifiable query on semantic data. The method comprises rendering a visualization of an ontology of the semantic data, acquiring one or more user interactions with the visualization, generating a semantic query and a natural language interpretation based on the one or more user interactions, and presenting the semantic query and the natural language interpretation to a user for validation.

Подробнее
Номер записи: 70
02-02-2017 дата публикации

INTERACTIVE VISUALIZATION OF BIG DATA SETS AND MODELS INCLUDING TEXTUAL DATA

Номер: US20170032026A1
Автор: Ashenfelter Adam, Parker Charles
Принадлежит: BigML, Inc.

Systems and processes are disclosed for advanced text analysis in the field of big data analytics and visualization: Users can now factor text into their predictive models, alongside regression, time/date and categorical information. This is ideal for building models where text content may play a prominent role (e.g., social media or customer service logs). Multiple data types, including text fields, may be combined together in datasets and models, and may be presented in various interactive visualization displays. 1. A method comprising:accessing a set of sample data instances, each instance comprising a corresponding value for each one of a plurality of data fields;processing the sample data instances so as to form a dataset; andgenerating a visual summary of the dataset on a computing device, the visual representation comprising a generally tabular presentation, the presentation including a series of rows and columns of information, each row corresponding to one of the data fields of the sample data, and each column displaying a corresponding parameter in each of the rows;wherein at least one of the columns displays, in each row of the presentation, an indication to identify a data type of the corresponding row; and whereinthe single data type is detected from a set of data types that includes at least a text data type.2. The method of wherein processing the sample data includes tokenizing the text fields.3. The method of wherein:at least one of the columns displays, in each row, an indication of a corresponding number of instances of the sample data that include the corresponding data field;at least one of the columns displays, in each row, a corresponding number of instances of the sample data that are missing the corresponding data field; andat least one of the columns displays, in each row, a corresponding number of instances of the sample data that have an error in the corresponding data field.4. The method of :wherein at least one of the columns displays, ...

Подробнее
Номер записи: 71
02-02-2017 дата публикации

SYSTEM AND METHOD FOR IMPROVING INCIDENT TICKET CLASSIFICATION

Номер: US20170032029A1
Автор: VENKATARAMAN Arthi
Принадлежит:

This disclosure relates generally to automatic classification of incident ticket, and more particularly to a system and method for improving the incident ticket classification. An incident ticket classification system to update an incident ticket classification, the system comprising: a memory; and a processor coupled to the memory storing processor executable instructions which when executed by the processor causes the processor to perform operations comprising: identifying one or more user-defined classes from one or more classes assigned to one or more incident tickets; determining, divergence of the one or more user-defined classes from one or more pre-defined classes associated with the incident ticket classification; and updating, the incident ticket classification based on the divergence. 1. A method to update an incident ticket classification , the method comprising:identifying, by an incident ticket classification system, one or more user-defined classes from one or more classes assigned to one or more incident tickets;determining, by the incident ticket classification system, divergence of the one or more user-defined classes from one or more pre-defined classes associated with the incident ticket classification; andupdating, by the incident ticket classification system, the incident ticket classification based on the divergence.2. The method of claim 1 , wherein the divergence of one or more user-defined classes from the one or more pre-defined classes is determined based on dampening parameter β claim 1 , pre-defined weight assigned to the one or more class and number of one or more incident tickets.3. The method of claim 2 , wherein the dampening parameter β is used to reduce the pre-defined weight of the one or more classes to save training time and to reduce error oscillations.4. The method of claim 1 , wherein updating the incident ticket classification based on the divergence further comprises:generating a negative classification based on the one or ...

Подробнее
Номер записи: 72
02-02-2017 дата публикации

Discovery and communication of team dynamics

Номер: US20170032308A1
Автор: Asima Silva, Hernan A. Cunico
Принадлежит: International Business Machines Corp

Electronic communications of team members of a team are monitored over time. Individual repeating patterns of interactions between team members and associated repeating subject matter topics of the interactions are identified. The identified individual repeating patterns and the associated repeating subject matter topics of the interactions are aggregated into a set of group interaction patterns of the team. Routine availability of a team member for additional interactions is determined in accordance with the set of group interaction patterns of the team.

Подробнее
Номер записи: 73
04-02-2016 дата публикации

Managing credibility for a question answering system

Номер: US20160034565A1
Автор: Fang Lu, Matthew E. Broomhall, Paul R. Bastide, Robert E. Loredo
Принадлежит: International Business Machines Corp

A method and system for managing credibility of a set of search results for a search query is disclosed. The method can include determining, by a natural language processing technique configured to analyze a portion of the set of search results and a portion of the search query, a credibility factor configured to indicate similarity to a subject matter of the search query. The method can also include establishing a relevance relationship between the credibility factor and source information of a first search result of the set of search results, wherein the source information is based on the credibility factor. The method may also include computing a credibility score for the first search result of the set of search results based on the relevance relationship between the credibility factor and the source information of the set of search results.

Подробнее
Номер записи: 74
04-02-2016 дата публикации

Computer-Based Method of Processing of Machine-Readable Information

Номер: US20160034568A1
Автор: KISELEV Oleg Mikhailovich, Vasiljev Vladimir Yaroslavovich, ZILBERMAN Mark Sholemovich
Принадлежит:

The invention relates to processing of machine-readable data. The invention can be used for processing of data specially intended for a wide range of specific functions. The invention can be used in computers, for composing of computer programs, as well as for building systems of processing of information. Particular cases of using the invention include information search, processing of information in databases, data selection and its statistics. The invention can be used for receiving a visualized representation of data being processed, including data in the form of electronic documents. A computer-based method of processing of machine-readable data comprises: calling for a set of electronic documents; defining a search query; matching of search attributes to a search query; determining of matching of search attributes of electronic documents to specified search queries; attributing of electronic documents relevant to specified search queries to corresponding subject subsets of electronic documents. 176-. (canceled)77. A computer-based method of processing of machine-readable data which are represented as electronic documents , comprising:Calling for at least one set of electronic documents;Specifying at least one search query;Matching of search attributes of electronic documents to at least one specified search query;Determining of the presence of search attributes in these electronic documents that correspond to each specified search query;Matching of each search query to its own unique subject subset of electronic documents given that only one search query is biunique to each of these subject subsets of electronic documents;Attributing of the electronic documents relevant to any specified search query to such subject subsets of electronic documents, to search queries of which these electronic documents are relevant.78. The method of claim 77 , wherein the electronic documents relevant to more than one search query are attributed to each subject subset of ...

Подробнее
Номер записи: 75
01-02-2018 дата публикации

Systems and methods for determining an execution path for a natural language query

Номер: US20180032514A1
Автор: Ahmed Nizam Mohaideen P., Sashikumar Venkataraman
Принадлежит: Rovi Guides Inc

Systems and methods are described to address shortcomings in conventional conversation systems by determining an execution path for a natural language query using questions and answers and selecting the path in a knowledge graph based on the entities in the questions and answers and the user's feedback. In some aspects, the systems and methods described provide for determining an execution path for a natural language query presented to an interactive media guidance application. The interactive media guidance application receives, from a user, a query including an input entity and an unknown term. The interactive media guidance application retrieves, from a knowledge graph, a plurality of possible responses for the query. The interactive media guidance application determines a correct response of the plurality of possible responses based on feedback from the user. The interactive media guidance application selects an execution path for the query based on the correct response.

Подробнее
Номер записи: 76
04-02-2016 дата публикации

DETERMINING A USER'S LATENT PREFERENCE

Номер: US20160034853A1
Автор: Hardtke David, WANG Jian
Принадлежит:

Generally discussed herein are methods, systems, and apparatuses for determining a latent preference of a user. One or more embodiments, discussed herein regard determining a latent preference of a user's propensity to relocate for a job. According to an example, a method can include receiving one or more characteristics of a user of a web service, estimating a probability corresponding to a latent preference of the user, and/or determining whether the probability indicates the user has the latent preference. 1. A non-transitory computer readable medium comprising instructions stored thereon , which when executed by a machine cause the machine to:receive one or more characteristics of a user of a web service;estimate a probability corresponding to a propensity of the user to relocate for a job using the one or more received characteristics of the user; anddetermine whether to present a user with a job recommendation associated with a job opportunity local to the user using the estimated probability.2. The computer readable medium of claim 1 , wherein the instructions for estimating the probability include instructions claim 1 , which when executed by the machine claim 1 , cause the machine to estimate the probability using a multinomial regression model of a plurality of users that include a characteristic that matches a characteristic of the user.3. The computer readable medium of claim 2 , wherein the multinomial regression model is one of a plurality of multinomial regression models each corresponding to a segment of users claim 2 , wherein each segment includes only users with a specific characteristic claim 2 , and wherein a parameter of a multinomial regression model associated with the characteristic of a particular segment is different from the parameter of a multinomial regression model associated with another segment.4. The computer readable medium of claim 3 , wherein the instructions for estimating the probability include instructions claim 3 , which ...

Подробнее
Номер записи: 77
01-02-2018 дата публикации

Determining Temporal Categories for a Domain of Content for Natural Language Processing

Номер: US20180032589A1
Автор: Allen Corville O., Chung Albert A., Freed Andrew R., Miller Dorian B.
Принадлежит:

Mechanisms are provided for processing sources of content in a corpus of information associated with a domain. The mechanisms ingest a plurality of sources of content in the corpus of information associated with the domain and determine at least one temporal category for the domain based on identification of frequently occurring references to at least one of temporal terms or time spans specified in the plurality of sources of content in the corpus of information associated with the domain. The mechanisms store the at least one temporal category for the domain in association with the domain and process queries applied to the plurality of sources of content in the corpus of information associated with the domain based on the stored at least one temporal category for the domain. 1. A method , in a data processing system comprising a processor and a memory , for processing an input question based on one or more sources of content in a corpus of information associated with a domain , comprising:determining, by the data processing system, at least one temporal category for the domain based on identification of frequently occurring references to at least one of temporal terms or time spans specified in the one or more sources of content in the corpus of information associated with the domain;storing, by the data processing system, the at least one temporal category for the domain in association with the domain; andprocessing, by the data processing system, an input question directed to the domain at least by retrieving the at least one temporal category associated with the domain and determining a temporal category for the input question based on the retrieved at least one temporal category associated with the domain.2. The method of claim 1 , wherein determining the at least one temporal category for the domain comprises:determining at least one of key terms or key concepts referenced in the one or more sources of content;determining, for each key term or key concept ...

Подробнее
Номер записи: 78
01-02-2018 дата публикации

Platform support clusters from computer application metadata

Номер: US20180032607A1
Автор: Aman Singhal, Marcelo M. De Barros, Siddharth S. Shenoy
Принадлежит: Microsoft Technology Licensing LLC

Application metadata for computer applications can be retrieved, with the metadata corresponding to metadata for an online application store from which the applications are available. Computer-readable application clusters can be generated. Each of the application clusters can indicate that applications in the cluster are supported by an associated set of one or more platforms for the cluster. The generating of the clusters can include analyzing the application metadata, such as by performing pattern matching on natural language data. Results for application queries for applications supported by a specified computer platform can be limited to listings of applications in one or more of the clusters whose associated set of one or more platforms includes the specified platform.

Подробнее
Номер записи: 79
01-02-2018 дата публикации

Generating Training Data For A Conversational Query Response System

Номер: US20180032902A1
Автор: Charette Francois, Han Kyu Jeong, Krishnan Lakshmi, Puskorius Gintaras Vincent
Принадлежит:

Training tuples including text and a question and answer corresponding to the text are input to a machine learning algorithm, such as a deep neural network. A Q&A model is obtained that outputs questions and answers given an input text. The training tuples may be obtained from standardized test such that the text is a question prompt and the questions and answers are based on the prompt. Raw text is input to the Q&A model to obtain second training tuples including a question and an answer. An NLU model is trained according to the second training tuples. The NLU model may then be installed on a consumer device, which will then use the model to respond to conversational queries and provide an appropriate response. 1. A method for training a query-response model for use in a vehicle , the method comprising , by a computer system:training a first model using a first plurality of tuples each including text, a question, and an answer;processing unstructured data using the first model to obtain a second plurality of tuples each including a question and an answer; andtraining a second model using the second plurality of tuples.2. The method of claim 1 , further comprising loading the second model onto a consumer computing device.3. The method of claim 2 , wherein the consumer computing device is an in-vehicle infotainment (IVI) system mounted in a vehicle.4. The method of claim 3 , further comprising:programming the IVI system to receive a query, input the query to the second model, and output a response according to the second model.5. The method of claim 3 , further comprising:programming the IVI system to input voice queries to the second model and output a response to the query according to the second model.6. The method of claim 1 , wherein the first model is a deep neural network (DNN) model.7. The method of claim 1 , wherein the second model is a deep neural network (DNN) model.8. The method of claim 1 , wherein processing the unstructured data using the first model ...

Подробнее
Номер записи: 80
01-02-2018 дата публикации

System and method to Generate Queries for a Business Database

Номер: US20180032930A1
Автор: HAMDI Maziyar, JAHANBAKHSH Kazem, KOLB Kurt Robert
Принадлежит: 0934781 B.C. Ltd

A method and system are provided for analyzing data in an online professional social network to identify and rank organizations with regard to providing professional services. A graph structure provides an efficient structure for accessing and processing data about service providers. The method and system provide a means to convert an unstructured query from a user into a graph query to return search results that provide a context for past provisions of services. An organization may be connected in the graph to problem and solution nodes to indicate that the organization can provide a solution to a given problem entered by a user. 1. A computer-implemented method comprising:providing a graph comprising problem nodes representing business problems, solution nodes representing business solutions, and organization nodes representing organizations;receiving a search query about a business problem from a user device;matching the query to one or more problem nodes in the graph;identifying solution nodes connected in the graph to matched problem nodes;identifying organization nodes connected in the graph to identified solution nodes; andcommunicating data about certain of the identified organization nodes to the user device, as query results.2. The method of claim 1 , wherein the search query is an unstructured text query.3. The method of claim 2 , further comprising creating one or more structured queries from the unstructured text query claim 2 , the one or more structured queries comprising identifiers of problem nodes and solution nodes.4. The method of claim 1 , further comprising communicating to the user device a set of Natural Language Generated suggestions from candidate problem and/or solution nodes identified from the query.5. The method of claim 1 , further comprising receiving a selection of one or more of the Natural Language Generated suggestions from the user device to indicate a user preference for corresponding business problems or business solutions.6. ...

Подробнее
Номер записи: 81
31-01-2019 дата публикации

Correcting Input Based on User Context

Номер: US20190034405A1
Автор: Davidson Douglas R., Ivan Jason J., Linn Christopher S.
Принадлежит:

In some implementations, a computing device can generate user input correction suggestions based on the user's context. For example, the user's context can include content that the user has open or has recently opened on the computing device or another computing device. For example, when the user opens an item of content, the computing device can generate a context dictionary that includes words, phrases, etc., that describe the opened content. When the user provides input (e.g., text, speech, etc.) the computing device can use the context dictionary to generate input correction suggestions. The computing device can synchronize the context dictionary with other computing devices that the user may be using so that the user's context on one device can be used by another device to generate input correction suggestions. 1. A method comprising:receiving, by a computing device, a first user input selecting a content item;generating, by the computing device, context entries in a context dictionary based on the selected content item;receiving, by the computing device, a second user input specifying a word;generating, by the computing device, a correction suggestion for the specified word based on the context entries in the context dictionary; andcausing, by the computing device, the correction suggestion to be presented on a display of the computing device.2. The method of claim 1 , further comprising:parsing the content item to determine one or more words included in the content item; andgenerating one or more context entries based on the one or more words in the content item.3. The method of claim 1 , further comprising:determining that a particular content item corresponding to a particular context entry in the context dictionary has been closed;determining whether a period of time has elapsed since the particular content item was closed;determining that the particular context entry is an active context entry when the period of time has not elapsed since the particular ...

Подробнее
Номер записи: 82
31-01-2019 дата публикации

METHODS AND SYSTEMS FOR PLAYING BACK INDEXED CONVERSATIONS BASED ON THE PRESENCE OF OTHER PEOPLE

Номер: US20190034524A1
Автор: McCarty Michael, Roe Glen E.
Принадлежит:

Methods and systems are provided herein for playing back indexed conversations based on the presence of other people. When a user asks a query, the system monitors the area, determines the other users in the area, and searches its database for a conversation that addresses the query in consideration of the other users present in the area. The system filters the indexed conversations to find conversations that included all the users present and determines the best matching conversation based on the words of the query as well as the keywords from the conversation. Once the system has determined the best match conversation, the system plays back the conversation to the user. 1. (canceled)2. A method of providing portions of portion indexed conversations based on the presence of other people , the method comprising:receiving from the user a query;monitoring an area around the user;detecting other users within the area around the user;parsing the query into a set of words;accessing a database of indexed conversations, wherein each entry in the database of indexed conversations includes a portion of a conversation, a record of users participating in the conversation, and a set of keywords associated with the conversation;searching the database of indexed conversations for a set of entries associated with a corresponding record of users for each entry that includes the user;filtering the set of entries so that each entry in the set of entries has a corresponding record of users that includes the other users within the area around the user in the corresponding record of users;comparing, for each entry in the set of entries, the corresponding set of keywords to the set of words from the parsed query;determining, based on the comparison, for each entry, an amount of the corresponding keywords that match the set of words;determining an entry in the set of entries with a best match based on the amount;selecting the determined entry of the database of indexed conversations; ...

Подробнее
Номер записи: 83
31-01-2019 дата публикации

METHODS AND SYSTEMS FOR REPLYING TO QUERIES BASED ON INDEXED CONVERSATIONS AND CONTEXT

Номер: US20190034525A1
Автор: McCarty Michael, Roe Glen E.
Принадлежит:

Methods and systems are provided herein for replying to queries based on indexed conversations and context. When a user asks a query, the system monitors the area, determines the other users in the area, and searches its database for a conversation that addresses the query in consideration of the other users present in the area. The system filters the indexed conversations to find conversations with the best matching conversation based on the words of the query as well as the keywords from the conversation. Once the system has determined the best match conversation, the system generates a response to the query based on the indexed conversation and query and then filters out segments of the response based on the other users in the area and other privacy concerns. The system then plays back generated response to the user. 1. (canceled)2. A method of replying to queries based on indexed conversations and context , the method comprising:receiving from the user a query;monitoring an area around the user;detecting other users within the area around the user;parsing the query into a set of words;accessing a database of indexed conversations, wherein each entry in the database of indexed conversations includes a portion of a conversation, a record of users participating in the conversation, and a set of keywords associated with the conversation;retrieving, from the database of indexed conversations, a set of entries from the database of indexed conversations, wherein the corresponding record of users for each entry in the set of entries includes the user;searching each set of keywords associated with each entry in the set of entries for a set of keywords that matches the set of words from the parsed query;identifying an entry with the matching set of keywords;processing the relevant portion of the conversation from the identified entry to determine context clues related to the query;generating a response to the query based on the determined context clues related to the ...

Подробнее
Номер записи: 84
31-01-2019 дата публикации

INTELLIGENT AGENT SYSTEM AND METHOD OF ACCESSING AND DELIVERING DIGITAL FILES

Номер: US20190034542A1
Автор: FINKEL Mike, MING Al
Принадлежит:

A system incorporates a speech recognition device that receives user audio signals, including speech, to automatically deliver content related to an audio or video transmission. The system performs speech recognition to identify speech recognition results and identifies tasks and actions based on the speech recognition results and on contextual information associated with the speech or the user. The system determines an intent of the speech and performs identified actions based upon the intent. In response to a user requesting a recipe detailed in video content, the system identifies the user request, identifies the video content, identifies a portion of the content from the video transmission, and delivers the content to the user. The content includes video, audio, and/or textual content and can also include setting reminders for the user, purchasing items on behalf of the user, making reservations for the user or launching applications for the user. 1. A content provider computer comprising:at least one processor;a memory; receiving a JSON package from a speech and language processing computer, wherein the JSON package includes a messaging intent determined by performing natural language processing on text data, and the text data is generated from an audio file by performing automated speech recognition;', 'decoding the JSON package to identify the messaging intent, wherein the messaging intent corresponds to an action to be taken by the content provider computer;', 'determining at least one digital content item that satisfies the action of the messaging intent;', 'appending the JSON package to include the at least one digital content item; and', 'providing the appended JSON package with the at least one digital content item to the speech and language computer over a communications network., 'one or more computer programs, wherein the one or more computer programs are stored in the memory and configured to be executed by the at least one processor, the one or more ...

Подробнее
Номер записи: 85
31-01-2019 дата публикации

Analyzing Concepts Over Time

Номер: US20190034543A1
Автор: Ho Tin Kam, Lastras-Montano Luis A., Shmueli Oded
Принадлежит:

A method and apparatus are provided for automatically generating and processing first and second concept vector sets extracted, respectively, from a first set of concept sequences and from a second, temporally separated, concept sequences by performing a natural language processing (NLP) analysis of the first concept vector set and second concept vector set to detect changes in the corpus over time by identifying changes for one or more concepts included in the first and/or second set of concept sequences.

Подробнее
Номер записи: 86
31-01-2019 дата публикации

Searching for Ideograms in an Online Social Network

Номер: US20190034545A1
Автор: Davis Stephen Moore, Goldsmid Aaron Payne, Sa Brian Paihan, Tan Jireh Yiwei, Vilimonovic Nikola
Принадлежит:

In one embodiment, a method includes receiving a first query comprising one or more n-grams inputted by the first user at the client system, accessing by the client system a plurality of ideograms each being associated with one or more tags matching at least one of the n-grams of the first query, where the one or more ideograms are ranked in an order based on their respective user-probabilities each being calculated based at least in part on a frequency of use associated with the respective ideogram, presenting one or more of the ideograms at the client system in ranked order where each ideogram is selectable by the first user, and receiving a selection of one of the presented ideograms at the client system. 1. A method comprising , by a client system of a first user:receiving, at the client system, a first query inputted by the first user, wherein the first query comprising one or more n-grams;accessing, by the client system, a plurality of ideograms, wherein each ideogram is associated with one or more tags matching at least one of the n-grams of the first query, wherein the one or more ideograms are ranked in an order based on their respective user-probabilities, and wherein each user-probability is calculated based at least in part on a frequency of use associated with the respective ideogram;presenting, at the client system, one or more of the ideograms, wherein the ideograms are presented in ranked order, each ideogram being selectable by the first user; andreceiving, at the client system, a selection of one of the presented ideograms.2. The method of claim 1 , wherein at least one of the one or more n-grams corresponds to an emoticon.3. The method of claim 1 , wherein the first user is a user of an online social network and wherein the frequency of use is determined for a plurality of users of the online social network.4. The method of claim 1 , wherein the frequency of use is determined with respect to the first user.6. The method of claim 1 , wherein the ...

Подробнее
Номер записи: 87
31-01-2019 дата публикации

DATA PROCESSING METHOD, MEDICAL TERM PROCESSING SYSTEM AND MEDICAL DIAGNOSTIC SYSTEM

Номер: US20190034810A1
Автор: Zhang Zhenzhong
Принадлежит:

The present disclosure relates to a data processing method, a medical term processing system, a medical diagnostic system, a medical intelligent triage apparatus and a computer readable storage medium. The method comprises: acquiring statement information inputted by a user; dividing the statement information into a plurality of information segments by means of a predetermined algorithm, the plurality of information segments comprising a first information segment; establishing a Gaussian distribution of each of the information segments; calculating the similarity between the first information segment and words in a database by means of a similarity model; and obtaining, from words in the database, at least one second information segment for describing the first information segment based on the calculated similarity. The present disclosure can provide professional terms, such as medical terms, corresponding to colloquial expressions, to facilitate users' diagnosis and treatment. 1. A data processing method , comprising:acquiring statement information inputted by a user;dividing the statement information into a plurality of information segments by means of a predetermined algorithm, the plurality of information segments comprising a first information segment;establishing a Gaussian distribution of each of the information segments;calculating the similarity between the first information segment and words in a database by means of a similarity model; andobtaining, from words in the database, at least one second information segment for describing the first information segment based on the calculated similarity.2. The method according to claim 1 , wherein the dividing the statement information into a plurality of information segments by means of a predetermined algorithm comprises:dividing the statement information into a plurality of information segments according to part of speech by means of a natural language processing algorithm.3. The method according to claim 1 , ...

Подробнее
Номер записи: 88
30-01-2020 дата публикации

INCREASING THE ACCURACY OF A STATEMENT BY ANALYZING THE RELATIONSHIPS BETWEEN ENTITIES IN A KNOWLEDGE GRAPH

Номер: US20200034465A1
Автор: BOXWELL STEPHEN A., BRAKE KYLE M., FROST KEITH G., VERNIER STANLEY J.
Принадлежит:

A cognitive system improves the accuracy of a natural language statement by analyzing relationships between entities in a knowledge graph for the statement. A natural language processing engine extracts entities and relationships in the statement, and a yes/no pipeline gauges the accuracy of the statement. If a statement is deemed inaccurate, the knowledge graph is used to identify a predominant relationship between certain entities, and a candidate phrase representing the predominant relationship is generated and presented to the user as a suggested replacement for a target phrase in the statement representing the relationship. The yes/no pipeline computes an accuracy score for the statement, and the statement is deemed inaccurate when the score is below a programmable threshold. The assertiveness of the system can be tuned by requiring the accuracy score of a proposed modified statement to be greater than the score of the original statement plus some tuning factor. 1. A method of improving the accuracy of a natural language statement comprising:receiving the natural language statement from a user in computer-readable form, by executing first instructions in a computer system;extracting from the natural language statement a plurality of entities and at least one stated relationship using natural language processing wherein the stated relationship is between at least a first one of the entities and a second one of the entities and is based on a target phrase in the statement, by executing instructions in the computer system;determining that the natural language statement is inaccurate, by executing third instructions in the computer system;identifying a predominant relationship between the first and second entities using a knowledge base wherein the predominant relationship is different from the stated relationship, by executing fourth instructions in the computer system;generating a candidate phrase representing the predominant relationship using natural language ...

Подробнее
Номер записи: 89
30-01-2020 дата публикации

AGILE SEMANTIC FRAMEWORK

Номер: US20200034480A1
Автор: Hoehmann Tobias, KAZMAIER GERRIT SIMON, Said Bare, Teichmann Jan
Принадлежит:

A computer-implemented method for defining queries based on agile semantic objects (ASOs) is provided. Data definitions defining data structures are acquired from a plurality of data sources. The data definitions include information for fields, semantics, and data relationships and semantics for use in analytical environments. Using the data definitions, metadata is defined for ASOs representing data objects in the data definitions. The metadata and the ASOs are stored in an ASO repository. A request for creating a query is received. Metadata representing the ASOs is provided in response to the request for use in a query designer interface. A query based on selected ones of the ASOs is received from the query designer interface. The query is stored in a query repository. A runtime object for executing the query is provided. 1. A computer-implemented method , comprising:acquiring, from a plurality of data sources, data definitions defining data structures, the data definitions including information for fields, semantics, and data relationships and semantics for use in analytical environments;defining, using the data definitions, metadata for agile semantic objects (ASOs) representing data objects in the data definitions;storing the metadata and the ASOs in an ASO repository;receiving a request for creating a query;providing, in response to the request and for use in a query designer interface, metadata representing the ASOs;receiving, from the query designer interface, a query based on selected ones of the ASOs;storing the query in a query repository; andproviding a runtime object for executing the query.2. The computer-implemented method of claim 1 , wherein the data definitions are stored in JAVASCRIPT OBJECT NOTATION (JSON) or extensible markup language (XML) format.3. The computer-implemented method of claim 1 , wherein the metadata is provided in a visual claim 1 , hierarchal format.4. The computer-implemented method of claim 1 , wherein storing the metadata and ...

Подробнее
Номер записи: 90
11-02-2016 дата публикации

System for Natural Language Understanding

Номер: US20160041967A1
Автор: GHANNAM Maan, GHANNAM Rima
Принадлежит:

A general-purpose apparatus for analyzing natural language text that allows for the implementation of a broad range of natural language understanding applications. The apparatus for natural language understanding analyzes a source text and transforms the source text into a semantically-interpretable syntactic representation (SISR), comprising a syntax template and semantic clause annotations. The general-purpose apparatus for natural language understanding is adaptable to various source text natural languages and is adaptable to various natural language understanding applications, such as query answering, translation, summarization, information extraction, disambiguation, and parsing. A natural language query answering apparatus for answering questions about a source text, whereby the query answering apparatus utilizes the general-purpose apparatus for transforming the natural language query into SISR format. 2. The method according to further comprising a lexicon database claim 1 , the lexicon database comprisinga plurality of lexicons and a plurality of lists.3. The method according to claim 2 , wherein the lexicon database further comprises a noun-categories lexicon where each left side entry is a noun corresponding to a right side entry that lists the possible semantic categories proper to the noun.4. The method according to claim 2 , wherein the lexicon database further comprises a semantic non-copula verb clauses lexicon where each left side entry of non copula category template clauses corresponds to one or more right side representations.5. The method according to claim 4 , wherein the right side entry of the semantic non-copula verb clauses lexicon contains an equal or less number of end-terms than the number of end-terms in the corresponding left side entry.6. The method according to claim 4 , wherein the right side entry of the semantic non-copula verb clauses lexicon comprises:a clause that describes the status of the subject or object before the ...

Подробнее
Номер записи: 91
11-02-2016 дата публикации

Processing Natural-Language Documents and Queries

Номер: US20160042058A1
Автор: Nguyen Cuong Duc
Принадлежит:

The subject disclosure presents a natural language processing engine for analyzing an input sentence comprising one or more clauses, and generating a plurality of semantic structures for the sentence and the component clauses, based on statistically parsing an input sentence to generate a syntactic structure of the input sentence, examining the syntactic structure of phrases and subordinate clauses within the input sentence, and generating tuples representing a subject, verb, object, indirect object, supplement, type, etc. Each part of the tuple is a reference to an entity in an external knowledge base. Disclosed operations include linking a plurality of entities identified in the syntactic structure with corresponding entities found in an external knowledge base, operating a co-reference resolution, filtering the references from mentioned entities to external entities by semantic relations, and exporting the set of output tuples. 1. A system for parsing a natural-language sentence , the system comprising:a server; and creating a phrase-level syntactic structure based on a syntactic structure of an input query comprising one or more phrases;', 'constructing an entity-level syntactic structure based on the phrase-level syntactic structure;', 'constructing a sentence-level semantic structure based on the entity-level syntactic structure; and', 'returning a set of tuples in the sentence-level semantic structure as an output., 'a memory coupled to the server, the memory to store logical instructions that are executed by the processor to perform operations comprising2. The system of claim 1 , wherein the creation of the phrase-level syntactic structure further comprises recognizing one or more clauses in the input query and parsing one or more verb phrases in each clause.3. The system of claim 2 , wherein recognizing the one or more clauses comprises matching the syntactic structure of the input query with one or more sentence templates to determine one or more main ...

Подробнее
Номер записи: 92
11-02-2016 дата публикации

CONFIGURABLE CHARACTER VARIANT UNIFICATION

Номер: US20160042059A1
Автор: "Staff K. Rene", Liu Su, Xu Cheng, Yan Shunguo
Принадлежит:

A method for configurable character variant unification is provided in the illustrative embodiments. A determination is made that a unification profile is applicable to a circumstance in which a character variant has been selected. The character variant is a variation of a character in a set of variations of the character such that each variation of the character in the set is represented by a unique Unicode code point. A unification repository is identified according to the profile. A determination is made whether the character variant satisfies a unification rule. Responsive to the character variant not satisfying the unification rule, a different variation of the character is selected from the unification repository, the different variation forming a replacement character variant. The replacement character variant is used in place of the character variant. 1. A method for configurable character variant unification , the method comprising:determining that a unification profile is applicable to a circumstance in which a character variant has been selected, wherein the character variant is a variation of a character in a set of variations of the character such that each variation of the character in the set is represented by a unique Unicode code point;identifying a unification repository according to the profile;determining whether the character variant satisfies a unification rule;selecting, responsive to the character variant not satisfying the unification rule, a different variation of the character from the unification repository, the different variation forming a replacement character variant; andusing the replacement character variant in place of the character variant.2. The method of claim 1 , further comprising:receiving a Unicode code point of the character variant; andoutputting a different Unicode code point corresponding to the replacement character variant.3. The method of claim 1 , further comprising:determining that the circumstance relates to a ...

Подробнее
Номер записи: 93
09-02-2017 дата публикации

Processing Text with Domain-Specific Spreading Activation Methods

Номер: US20170039186A1
Автор: Duch Wlodzislaw, Glauser Tracy A., Grupp-Phelan Jacqueline M., Kowatch Robert A., Matykiewicz Pawel, Pestian John P., Sorter Michael
Принадлежит:

A method for performing natural language processing of free text using domain-specific spreading activation. Embodiments of the present invention ontologize free text using an algorithm based on neurocognitive theory by simulating human recognition, semantic, and episodic memory approaches. Embodiments of the invention may be used to process clinical text for assignment of billing codes, analyze suicide notes or legal discovery materials, and for processing other collections of text. Further, embodiments of the invention may be used to more effectively search large databases, such as a database containing a large number of medical publications. 119-. (canceled)21. A method comprising using a using a central processing unit (CPU) to create , from a text of one or more documents containing natural language stored in a non-transitory electronic memory device , a semantic network having a plurality of nodes corresponding to sets of semantic and episodic concepts and weighted links between the sets of semantic and episodic concepts ,the sets of semantic concepts consisting of a plurality of semantic concepts associated with a plurality of known words;the sets of episodic concepts consisting of a plurality of episodic concepts associated with the semantic concepts; andutilizing, using the CPU, spreading activation algorithms to refine the weighted links in the semantic network.22. The method of claim 21 , further comprising claim 21 , prior to the step of creating a semantic network claim 21 , the steps ofidentifying, using the CPU, one or more of a plurality of groups of characters of the text as corresponding to at least one of the plurality of known words;querying a first database comprising associations between known words and semantic concepts to obtain the sets of one or more semantic concepts associated with each of the known words;querying a second database comprising associations between episodic concepts, known words, and semantic concepts to obtain the sets of ...

Подробнее
Номер записи: 94
09-02-2017 дата публикации

Scoring Automatically Generated Language Patterns for Questions using Synthetic Events

Номер: US20170039271A1
Автор: Bishop Timothy A., BOXWELL STEPHEN A., Brumfield Benjamin L., Desai Nirav P., VERNIER STANLEY J.
Принадлежит:

An approach is provided in which a knowledge manager identifies training entities in a training question answer pair and identifies multiple database paths a database that link the training entities. The knowledge manager then generates multiple generalized queries based upon the identified multiple database paths and assigns query scores to the multiple generalized queries. In addition, the knowledge manager generates a generalized syntactic pattern based upon syntactic relationships between the training entities in the training question answer pair. When the knowledge manager receives a question and matches the syntactic pattern of the received question to the generalized syntactic pattern, the knowledge manager generates custom queries from the generalized queries and queries the database using the custom queries. The knowledge manager, in turn, scores answers generated from the custom queries based upon the custom queries' corresponding query scores. 1. A method implemented by an information handling system that includes a memory and a processor , the method comprising:creating a plurality of generalized queries corresponding to a plurality of training entities included in a training question answer pair, wherein each of the plurality of generalized queries is assigned one of a plurality of query scores;formulating a generalized syntactic pattern based upon one or more syntactic relationships between the plurality of training entities in the training question answer pair;constructing a plurality of custom queries, from the plurality of generalized queries, in response to matching the generalized syntactic pattern to a syntactic pattern of a question, wherein each of the plurality of custom queries is assigned the query score of its corresponding generalized query; andgenerating a plurality of answers to the question in response to querying the database using the plurality of custom queries, wherein each of the plurality of answers is scored based upon the ...

Подробнее
Номер записи: 95
09-02-2017 дата публикации

NLP-BASED CONTENT RECOMMENDER

Номер: US20170039272A1
Автор: Dhillon Navdeep S., Hernando Jose, Koperski Krzysztof, Liang Jisheng, Roseman Neil, Schwend Diana, Stark Korina J.
Принадлежит:

Methods, techniques, and systems for using natural language processing to recommend related content to an associated text segment or document. Example embodiments provide a NLP-based content recommender (“NCR”) which uses NLP-based search techniques, potentially in conjunction with context or other related information, to locate and provide content related to entities that are recognized in the associated material. NCRs may be embedded as widgets, for example on Web pages to assist users in their perusal and search for information, provided by means of browser plug-ins or other application plug-ins, provided in libraries or in standalone environments, or otherwise integrated into other code, programs, or devices. This abstract is provided to comply with rules requiring an abstract, and it is submitted with the intention that it will not be used to interpret or limit the scope or meaning of the claims. 113-. (canceled)14. A computer-implemented NLP-based content recommendation system , comprising:a memory; and receive a text segment for processing;', 'identify one or more named entities to which the received text segment refers based, at least in part, upon a natural language processing (NLP) parsing and linguistic analysis of the text segment;', 'derive related content based at least in part upon a natural language processing parsing and linguistic analysis of entity based information of the identified one or more named entities and based upon context information associated with the named entities or from the received text segment, wherein the related content includes at least one named entity that is connected to at least one of the one or more named entities; and', 'cause the derived related content to be presented., 'a content recommender module, stored in the memory, and having instructions that are configured, when executed by a computer processor, to15. The system of claim 14 , wherein the module is further configured claim 14 , when executed claim 14 , to ...

Подробнее
Номер записи: 96
09-02-2017 дата публикации

Extracting facts from unstructured data

Номер: US20170039341A1
Автор: Amy Abernethy, Andrew Dilling, Benjamin Birnbaum, Caitlin Keenan, Catherine Miller, Cynthia Revol, Daniel Eisenberg, Dennis Lee, Dominique Connolly, Elijah Meerson, Geoffrey Calkins, Gil Shklarski, James Dura, Jeremy Feinstein, Jeremy Kohansimeh, Joseph Delgado, Joseph DiLallo, Joseph Mou, Katherine Larrabee, Lauren Ellsworth, Maayan Roth, Melisa Tucker, Nathan Nussbaum, Nathaniel Turner, Paul Richardson, Paul You, Ross Feinstein, Zachary Weinberg
Принадлежит: Flatiron Health Inc

Methods, systems, and apparatus, including computer programs encoded on computer storage media, to present a video. One of the methods includes obtaining one or more unstructured documents. The method includes obtaining, by a computer system, a data model, the data model identifying a type of fact that can be determined from the one or more unstructured documents. The method includes determining, by the computer system, a channel to extract facts from the document based on the type of fact. The method includes distributing, by the computer system, the one or more unstructured documents to the channel. The method includes extracting, by the channel, facts from the one or more unstructured documents. The method also includes storing the facts in a data model.

Подробнее
Номер записи: 97
11-02-2016 дата публикации

SYSTEM AND METHOD FOR FINANCIAL TRANSACTION MANAGEMENT

Номер: US20160042469A1
Автор: DUTHOIT Nathan, LIMEBACK Dieter, Lochrie James, WARKENTIN Michael
Принадлежит:

A system and method providing a financial transaction management tool operable to provide contextual information relating to particular financial transactions is provided. The financial transaction management tool is operable to highlight associations between bank data, source documents and manual or automated financial data. The financial transaction management tool is further operable to organize accounting information and contextual information into an easy to read format and that operates to assemble and thereby bring together sources relating to a financial transaction so that such sources are easily viewable. In some embodiments of the present invention the multiple sources may be viewable in a single view. The financial transaction management tool is also operable to organize multiple transactions in a single transaction stream. 1. A financial transaction management tool , comprising:a. a server computer;b. one or more databases linked to the server computer;c. an internet connection whereby one or more records are transferred to the server computer; i. apply a transaction detection element to capture information from a loaded record;', 'ii. apply a transaction matching element operable to access additional records and to determine matches between records to identify records corresponding to a single financial transaction; and to store information derived from the loaded record and the additional records, as well as copies of the loaded record and the additional records in the one or more databases; and, 'd. a transaction processing application operable by one or more processors of the server computer toe. a user interface operable by one or more processors of the server computer to interactively display the information derived from the loaded record and the additional records to the user.2. A system for financial transaction management , comprising:a. a server computer;b. one or more databases linked to the server computer;c. an internet connection whereby ...

Подробнее
Номер записи: 98
09-02-2017 дата публикации

SYSTEMS, METHODS, AND COMPUTER PROGRAM PRODUCTS FOR IMPLEMENTING A FREE-TEXT SEARCH DATABASE

Номер: US20170039619A1
Автор: Barraud Romain, Pauchet David, Tanasescu Teodor-Vlad
Принадлежит:

Systems, methods, and computer program products for implementing a dynamic free-text search database. First data is generated for the dynamic free-text search database that represents a first relationship including a first keyword, a first trip, and a first weight value. A plurality of free-text search requests are received, and a second weight value for the first relationship is calculated based on the free-text search requests. The second weight value differs from the first weight value. The first data is transformed into second by inserting the second weight value into the first data such that the first relationship includes the second weight value. 1. A method for implementing a dynamic free-text search database , the method comprising:generating, by at least one processor, first data for the dynamic free-text search database that represents a first relationship including a first keyword, a first trip, and a first weight value;receiving, by the at least one processor, a plurality of free-text search requests;calculating, by the at least one processor, a second weight value for the first relationship based on the free-text search requests, wherein the second weight value differs from the first weight value; andtransforming, by the at least one processor, the first data into second data by inserting the second weight value into the first data such that the first relationship includes the second weight value.2. The method of claim 1 , further comprising:establishing a connection for data communication between at least one data storage device and a travel proposal system that includes the at least one processor, wherein the at least one data storage device hosts the dynamic free-text search database; andtransmitting the first data from the pricing system to the at least one data storage device via the connection.3. The method of claim 1 , wherein the first trip comprises a destination location claim 1 , a point-of-sale claim 1 , and one or more contextual parameters ...

Подробнее
Номер записи: 99
09-02-2017 дата публикации

System and method for evaluating text to support multiple insurance applications

Номер: US20170039656A1
Автор: Arthur Paul Drennan, III
Принадлежит: Hartford Fire Insurance Co

A system for evaluating text data to support multiple applications is disclosed. In some embodiments, text input data is received from multiple sources. The text input data may then be aggregated and mapped to create composite text input data. A semantic event in the composite text input data may be automatically detected, such as by being triggered by a semantic rule and associated semantic tag. A text mining result database may be updated by adding an entry to the database identifying the detected semantic event and the triggering semantic rule. An indication associated with the text mining result database may then be transmitted to a plurality of applications.

Подробнее
Номер записи: 100