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 26886. Отображено 100.
19-01-2012 дата публикации

Parsing culturally diverse names

Номер: US20120016660A1
Автор: Frankie E. Patman Maguire, Leonard A. Shaefer, JR., Richard T. Gillam
Принадлежит: International Business Machines Corp

Provided are techniques for parsing a name. A name to be parsed is received. A culture of the name is identified. One or more name phrases from the name are identified. Statistics for the one or more name phrases are identified. It is determined whether to perform a first parsing technique that parses different types of name elements within at least one field of the name. In response to determining that the first parsing technique is to be performed, the name is parsed using the statistics and the first parsing technique. In response to determining that the first parsing technique is not to be performed, the name is parsed using the statistics and a second parsing technique.

Подробнее
Номер записи: 1
26-01-2012 дата публикации

Information processing apparatus, information processing method, and information processing program

Номер: US20120023399A1
Автор: Akihiro Watanabe, Kenichiro Kobayashi, Masaaki Hoshino, Shouichi Doi
Принадлежит: Sony Corp

An information processing apparatus includes a selection unit selecting at least a part of a text included in contents, an acquisition unit acquiring a processing result of natural language processing for the part of the text selected by the selection unit, a specifying unit specifying a predetermined part of the text based on the processing result acquired by the acquisition unit, a detection unit detecting a keyword from the predetermined part of the text based on the processing result acquired by the acquisition unit, a tag generation unit automatically generating a tag in accordance with the keyword detected by the detection unit, and an association unit associating the tag generated by the tag generation unit with the predetermined part of the text.

Подробнее
Номер записи: 2
15-03-2012 дата публикации

Generating parser combination by combining language processing parsers

Номер: US20120065960A1
Автор: Futoshi Iwama, Hironori Takeuchi, Taiga Nakamura
Принадлежит: International Business Machines Corp

A computer implemented method, a computer system, and a program for generating a parser combination. The method includes: generating a parser combination by combining parsers each associated with at least one grammar description, where the step is carried out using (i) at least one grammar description means and (ii) a computer device. The computer system includes: a processor, a memory connected to the processor, and a parser generator for generating a parser combination in the memory by combining parsers each associated with at least one grammar description, and at least one grammar description type means.

Подробнее
Номер записи: 3
03-05-2012 дата публикации

Extracting rich temporal context for business entities and events

Номер: US20120109637A1
Автор: Arup Kumar Choudhury, Sathiya Keerthi Selvaraj, Srujana Merugu, Vipul Agarwal
Принадлежит: Yahoo Inc until 2017

Methods and apparatus for performing computer-implemented extraction of temporal information for business entities and events are disclosed. In one embodiment, a sequence of text is obtained. A label is assigned to one or more of a plurality of segments of the text such that each of the one or more of the plurality of segments of the text is classified as temporal data in one of a plurality of classes of temporal data. One or more rules are applied to the one or more segments of the text that have been classified as temporal data to generate a structured representation of the temporal data, where the rules include one or more schematic rules. Each of the schematic rules pertains to one or more of the plurality of classes of temporal data and indicates a structure in which temporal data in the corresponding one or more of the plurality of classes is to be stored.

Подробнее
Номер записи: 4
12-07-2012 дата публикации

Word pair acquisition apparatus, word pair acquisition method, and program

Номер: US20120179682A1
Автор: Junichi Kazama, Kentaro Torisawa, Kow Kuroda, Masaki Murata, Stijn De Saeger
Принадлежит: Individual

Conventionally, it has been impossible to appropriately acquire word pairs having a prescribed relationship. Such word pairs can be appropriately acquired with a word pair acquisition apparatus including: a word class information storage unit in which word class information can be stored; a class pair favorableness degree storage unit in which a class pair favorableness can be stored; a seed pattern storage unit in which can be stored one or more seed patterns; a word pair acquisition unit that acquires one or more word pairs co-occurring with the seed pattern from sentence groups; a class pair favorableness degree acquisition unit that acquires a class pair favorableness degree; a score determination unit that uses the class pair favorableness degree to determine a score of each of the word pairs; and a word pair selection unit that acquires one or more word pairs having a high score.

Подробнее
Номер записи: 5
04-10-2012 дата публикации

Electronic brain model with neuron tables

Номер: US20120254087A1
Автор: Thomas A. Visel
Принадлежит: Neuric Tech LLC

A method of emulating the human brain with its thought and rationalization processes is presented here, as well as a method of storing human-like thought. The invention provides for inclusion of psychological profiles, experience and societal position in an electronic emulation of the human brain. This permits a realistic human-like response by that emulation to the people and the interactive environment around it.

Подробнее
Номер записи: 6
11-10-2012 дата публикации

Translating Texts Between Languages

Номер: US20120259621A1
Автор: Konstantin Anisimovich, Konstantin Zuev, Vladimir Selegey
Принадлежит: ABBYY InfoPoisk LLC

Methods and computer systems for translating sentences between languages from an intermediate language-independent semantic representation are provided. Based on a comprehensive understanding about languages and semantics, exhaustive linguistic descriptions are used to analyze sentences, build syntactic structures and language independent semantic structures and representations, and synthesize one or more sentences in a natural or artificial language. A computer system is also provided to analyze and synthesize various linguistic structures and perform translation of a wide spectrum of various sentence types. As result, a generalized data structure, such as a semantic structure, is generated from a sentence of an input language and can be transformed into a natural sentence expressing its meaning correctly in an output language. The methods and systems can be applied to automated abstracting, machine translation, natural language processing, control systems, Internet information retrieval, etc.

Подробнее
Номер записи: 7
10-01-2013 дата публикации

Providing answers to questions including assembling answers from multiple document segments

Номер: US20130013615A1
Автор: David A. Ferrucci, Eric W. Brown, James W. Murdock, IV, Jennifer Chu-Carroll
Принадлежит: International Business Machines Corp

A method, system and computer program product for generating answers to questions. In one embodiment, the method comprises receiving an input query, identifying a plurality of candidate answers to the query; and for at least one of these candidate answers, identifying at least one proof of the answer. This proof includes a series of premises, and a multitude of documents are identified that include references to the premises. A set of these documents is selected that include references to all of the premises. This set of documents is used to generate one or more scores for the one of the candidate answers. A defined procedure is applied to the candidate answers to determine a ranking for the answers, and this includes using the one or more scores for the at least one of the candidate answers in the defined procedure to determine the ranking for this one candidate answer.

Подробнее
Номер записи: 8
14-03-2013 дата публикации

Phone number recognition

Номер: US20130064359A1
Автор: Peter A. Kalmstrom
Принадлежит: Skype Ltd Ireland

Method and system for recognising a numeric or alphanumeric sequence of characters in a document, the sequence conforming to predetermined rules and representing user identifiers for identifying users in a communication system include identifying a country of origin of the document, recalling rules relating to the format of the sequence associated with the determined country of origin, searching the document to identify any sequence in the document satisfying the format and returning any such sequence.

Подробнее
Номер записи: 9
22-08-2013 дата публикации

Systems and methods for generating high-quality formal executable software feature requirements

Номер: US20130219354A1
Автор: Arun Chakrapani Rao, Manoj G. Dixit, Ramesh Sethu
Принадлежит: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Systems and methods for generating formal software requirements using an informal requirements document having informal requirements and annotations associated with the informal requirements. The systems and methods extract syntax from the annotations and generate artifacts as a function of the syntax.

Подробнее
Номер записи: 10
31-10-2013 дата публикации

Method and process for semantic or faceted search over unstructured and annotated data

Номер: US20130290370A1
Автор: Anthony Tom Levas, Branimir Konstantinov Boguraev, Dafna Sheinwald, David Angelo Ferrucci, Eric William Brown, Paul Turquand Keyser, Youssef Drissi
Принадлежит: International Business Machines Corp

A semantic query over a corpus of data is constructed using a graphical user interface to create an aggregation of graphical representations of annotations associated with a plurality of data elements contained within the corpus of data and graphical representations of search terms contained within the plurality of data elements. The aggregation includes at least one annotation and at least one search term. The relative positions of the graphical representations of the annotations and the search terms are manipulated within the aggregation within the graphical user interface to express relationships among the annotations and search terms, yielding a visual spatial representation of the semantic query. The annotations, search terms and expressed relationships define the semantic query that is used to search the corpus of data.

Подробнее
Номер записи: 11
06-02-2014 дата публикации

Systems and Methods for Semantic Information Retrieval

Номер: US20140039877A1
Автор: Azriel L. Chelst, Jordan Rhys Powell, Nicola J. Guenigault
Принадлежит: American Express Travel Related Services Co Inc

A semantic tagging method may add context to a sentence in order to increase search efficiency. Regardless of an author's writing style, translating semantic concepts into tags may increase search efficiency. Automatic semantic tagging of documents may allow semantic search and reasoning. Text for semantic tagging may include an email, a website chat room, an internet forum, or a text message, Additional texts may include aggregating general consensus of an emailed topic across multiple emails, whether in the same email chain or separate emails. To increase search efficiency, the analysis of prior communications within the body of text may comprise analyzing structured contextual information to facilitate with homophora resolution. The structured contextual information may include at least one of a sender email address, one or more recipient email addresses, a subject field, a message date and time stamp, and an attachment title.

Подробнее
Номер записи: 12
06-01-2022 дата публикации

METHODS AND APPARATUS TO IMPROVE DISAMBIGUATION AND INTERPRETATION IN AUTOMATED TEXT ANALYSIS USING STRUCTURED LANGUAGE SPACE AND TRANSDUCERS APPLIED ON AUTOMATONS

Номер: US20220004708A1
Автор: Roche Emmanuel
Принадлежит:

Methods and apparatus for automated processing of natural language text is described. Received text can be preprocessed to produce language-space data that includes descriptive data elements for words. Source code that includes linguistic constraints, and that may be written in a programming language that is user-friendly to linguists, can be compiled to produce finite-state transducers and bi-machine transducers that are used by a language-processing virtual machine to process the language-space data. The language-processing virtual machine selects and executes code segments in accordance with path transitions of the transducers when applied on automatons to disambiguate meanings of words in the received text. 1. A method of automated text analysis , the method comprising:receiving text;preprocessing the received text to generate a language space in which one or more descriptive data elements are associated with each word in the received text; and identifying a match between a first identifying element in the transducer and a first identifier of a first descriptive data element in the language space associated with a word in the sentence;', 'selecting a first code segment that is identified in the transducer to be associated with the first identifying element; and', 'executing the first code segment to produce a modified language space in which the meaning of the word in the sentence associated with the first descriptive data element is disambiguated., 'executing an operation with a transducer to process a sentence in the language space, wherein the operation comprises2. The method of claim 1 , wherein the transducer is a bi-machine transducer.3. The method of claim 1 , further comprising processing the modified language space to extract information from the received text.4. The method of claim 1 , wherein processing the modified language space comprises performing a search query on the modified languages space for all sentences containing words having the meaning ...

Подробнее
Номер записи: 13
06-01-2022 дата публикации

SYSTEM AND METHOD FOR DETECTING UNDESIRABLE AND POTENTIALLY HARMFUL ONLINE BEHAVIOR

Номер: US20220004710A1
Автор: LELIWA GNIEWOSZ, Wroczynski Michal
Принадлежит: Samurai Labs sp. z o.o.

Embodiments include computer-implemented methods and systems for detecting undesirable and potentially harmful online behavior. The embodiments described and claimed could also be applied to detecting any other type of online behavior to be detected, but the descriptions focuses on detecting online violence. More particularly, the embodiments disclosed relate to detecting online violence using symbolic methods of natural language processing (NLP) that utilize and govern the usage of: 1) syntactic parser for analyzing grammatical context of the input text data, 2) unsupervised learning methods for improving selected aspects of the system and adjusting the system to new data sources and guidelines, and 3) statistical classifiers for resolving specific well-defined sub-tasks, in which statistical approaches surpass the symbolic methods. 1. A system for detecting one or more predetermined online behaviors , the system comprising: the at least one processor receiving plain text input;', normalization comprises the process of transforming the plain text input into a single predetermined canonical form to generate normalized text;', 'correction comprises the process of revising the normalized text in order to correct misspellings and any other types of intentional and non-intentional errors to generate corrected text; and', 'transformation comprises the process of revising the corrected text in order to replace, remove or add specific text fragments to generate transformed text that is optimally phrased for detecting one or more predetermined online behaviors; and, 'the at least one processor performing a plurality of functional modules, the plurality of functional modules comprising one or more of a text preparation module, a normalization module, and a correction and transformation module, wherein,'}, each contextual model comprises a detection model for detecting a single well-defined type of online violence; and', 'each contextual model classifies text as containing or ...

Подробнее
Номер записи: 14
04-01-2018 дата публикации

System performance logging of complex remote query processor query operations

Номер: US20180004796A1
Автор: Charles Wright, David R. Kent, IV, Radu Teodorescu, Ryan CAUDY
Принадлежит: Illumon LLC

Described are methods, systems and computer readable media for performance logging of complex query operations.

Подробнее
Номер записи: 15
07-01-2021 дата публикации

METHODS AND APPARATUS FOR ANALYZING SEQUENCES OF APPLICATION PROGRAMMING INTERFACE TRAFFIC TO IDENTIFY POTENTIAL MALICIOUS ACTIONS

Номер: US20210004460A1
Автор: GUNUGANTI Aditya, HARGUINDEGUY Bernard, KUNDOTTIL Yasar, ROSENBLUM Isidore, SAHU Avinash Kumar, Sharma Amit Kumar, SUBBARAYAN Udayakumar
Принадлежит: Ping Identity Corporation

In some embodiments, a method includes receiving, at a processor of a server, a first application programming interface (API) call from a client device and providing an indication associated with the first API call as an input to a machine learning model such that the machine learning model identifies a set of parameters associated with a set of likely subsequent API calls. The method can further include receiving a second API call from the client device, identifying the second API call as an anomalous API call based on the second API call not meeting the set of parameters associated with the set of likely subsequent API calls, and sending a signal to perform a remedial action based on the identifying. 120.-. (canceled)21. A non-transitory processor-readable medium storing code representing instructions to be executed by a processor , the code comprising code to cause the processor to:receive, from a client device, a set of application programming interface (API) calls having a sequence;calculate a first consistency score for a pair of API calls from the set of API calls, the first consistency score being based on a first API call in the pair of API calls being within a first predetermined proximity in the sequence of a second API call in the pair of API calls;calculate a second consistency score for the pair of API calls, the second consistency score being based on the first API call in the pair of API calls being within a second predetermined proximity in the sequence of the second API call in the pair of API calls;generate a combined consistency score for the pair of API calls by combining the first consistency score and the second consistency score; andidentify, in response to determining that the combined consistency score for the pair of API calls meets a criterion, that the client device is operating in a malicious manner.22. The non-transitory processor-readable medium of claim 21 , further comprising code to cause the processor to:restrict API calls ...

Подробнее
Номер записи: 16
02-01-2020 дата публикации

Social autonomous agent implementation using lattice queries and relevancy detection

Номер: US20200004813A1
Автор: Boris Galitsky
Принадлежит: Oracle International Corp

Techniques for computer-generated conversation are disclosed. In an example, a method identifies text postings from a conversation. The method creates, for each text fragment of each text posting, a syntactic tree and a discourse tree. The method creates parse thickets, each parse thicket including the syntactic tree and discourse tree of a unique pair of text postings. The method extracts, from each parse thicket, a common text segment and obtains a set of candidate search results by providing the common text segments to a search engine. The candidate search results can be further refined for relevancy and mental state and posted as a response to a conversation.

Подробнее
Номер записи: 17
13-01-2022 дата публикации

MULTI-USER INTELLIGENT ASSISTANCE

Номер: US20220012470A1
Автор: Bathiche Steven Nabil, BATRICEVIC Uros, Koishida Kazuhito, POPOV Alexander A.
Принадлежит: Microsoft Technology Licensing, LLC

An intelligent assistant records speech spoken by a first user and determines a self-selection score for the first user. The intelligent assistant sends the self-selection score to another intelligent assistant, and receives a remote-selection score for the first user from the other intelligent assistant. The intelligent assistant compares the self-selection score to the remote-selection score. If the self-selection score is greater than the remote-selection score, the intelligent assistant responds to the first user and blocks subsequent responses to all other users until a disengagement metric of the first user exceeds a blocking threshold. If the self-selection score is less than the remote-selection score, the intelligent assistant does not respond to the first user. 1. An intelligent assistant computer , comprising:a logic machine; anda storage machine holding instructions executable by the logic machine to:recognize another intelligent assistant computer;record speech spoken by a first user;determine a self-selection score for the first user based on the speech spoken by the first user;receive a remote-selection score for the first user from the other intelligent assistant computer;if the self-selection score is greater than the remote-selection score, respond to the first user, determine a disengagement metric of the first user based on recorded speech spoken by the first user, and block subsequent responses to all other users until the disengagement metric of the first user exceeds a blocking threshold;if the self-selection score is less than the remote-selection score, do not respond to the first user; andstop blocking subsequent responses to another user responsive to a new self-selection score for the first user being less than a new remote-selection score for the first user.2. The intelligent assistant computer of claim 1 , wherein the self-selection score is determined based further on a signal-to-noise ratio of recorded speech spoken by the first user. ...

Подробнее
Номер записи: 18
07-01-2021 дата публикации

Revealing Content Reuse Using Fine Analysis

Номер: US20210004582A1
Автор: Christopher Miles WHITE, Darren Keith Edge, Jonathan Karl LARSON, Nathan Roy Evans
Принадлежит: Microsoft Technology Licensing LLC

Systems and methods for managing content provenance are provided. A network system accesses a document of a plurality of documents to be analyzed. The network system extracts text fragments from the document including a first fragment and a second fragment. A determination is made whether each of the text fragments match an entry in a hash table. Based on a first fragment not matching any entries in the hash table, the network system creates a new entry in the hash table, whereby the first fragment is used to generate a key in the hash table. Based on a second fragment matching an entry of the hash table, the network system associates the document with a key of the matching entry in the hash table, whereby the associating comprising updating the hash table with an identifier of the document.

Подробнее
Номер записи: 19
07-01-2021 дата публикации

HIERARCHICAL SELF-ATTENTION FOR MACHINE COMPREHENSION

Номер: US20210005195A1
Автор: AL HASAN SHEIKH SADID, DATLA Vivek Varma, FARRI OLADIMEJI FEYISETAN, Tao Li
Принадлежит:

A method for determining the answer to a query in a document, including: encoding, by an encoder, the query and the document; generating a query-aware context encodings G by a bidirectional attention system using the encoded query and the encoded document; performing a hierarchical self-attention on the query aware document by a hierarchical self-attention system by applying a word to word attention and a word to sentence attention mechanism resulting in a matrix M; and determining the starting word and the ending word of the answer in the document by a span detector based upon the matrix M. 1. A method for determining the answer to a query in a document , comprising:encoding, by an encoder, the query and the document;generating a query-aware context encodings G by a bidirectional attention system using the encoded query and the encoded document;performing a hierarchical self-attention on the query aware document by a hierarchical self-attention system by applying a word to word attention and a word to sentence attention mechanism resulting in a matrix M; anddetermining the starting word and the ending word of the answer in the document by a span detector based upon the matrix M.2. The method of claim 1 , wherein performing a hierarchical self-attention on the query aware document further includes:applying a bidirectional recurrent neural network (BiRNN) on the query-aware context encoding G to produce a matrix G′;extracting sentence-level encodings S′ from G′;producing a word-word self-attention matrix A_w by comparing each word in G′ with each other word in G′; andproducing a word-sentence self-attention matrix A_s by comparing each word in G′ to each sentence in the extracted sentence-level encodings S′,wherein the matrix M is based upon A_w and A_s.3. The method of claim 2 , wherein producing a word-word self-attention matrix A_w further includes using a trilinear function to compute similarity scores for each word-word comparison and normalizing the resulting ...

Подробнее
Номер записи: 20
27-01-2022 дата публикации

DOCUMENT TEXT EXTRACTION TO FIELD-SPECIFIC COMPUTER EXECUTABLE OPERATIONS

Номер: US20220027564A1
Автор: Manandise Esmé, Mukherjee Saikat, Patchirajan Karpaga Ganesh
Принадлежит: INTUIT INC.

This disclosure describes converting computer-executable predicate-argument structures for a specific field to field-specific predicated-argument structures to improve execution. In some implementations, a method can be performed by one or more processors of a computing device, and can include receiving one or more predicate-argument structures (PASs) associated with taxation-specific text and converting the one or more PASs into one or more tax-specific predicate-argument structures (TPASs). Converting the one or more PASs to one or more TPASs may include one or more of: defining terms in a segment based on a definition of the term from a different segment or line description (including from a different document); reordering nodes, replacing nodes, or removing nodes of a segment (such as based on one or more single segment tree traversal rules); or combining multiple PASs for multiple segments of a single line description based on one or more multiple segment tree traversal rules. 1. A method of generating one or more computer-executable tax-specific predicate-argument structures (TPASs) for text from one or more tax-specific documents , the method performed by one or more processors of a computing device and comprising:receiving one or more computer-executable predicate-argument structures (PASs) generated from the text from the one or more tax-specific documents; andconverting the one or more PASs to one or more TPASs.2. The method of claim 1 , further comprising deserializing the one or more PASs before converting the one or more PASs to one or more TPASs.3. The method of claim 2 , further comprising categorizing the content of the one or more deserialized PASs before converting the one or more deserialized PASs to one or more TPASs.4. The method of claim 3 , wherein categorizing the content of the one or more deserialized PASs includes defining an undefined term in the one or more deserialized PASs based on a defined reference for the undefined term in a label ...

Подробнее
Номер записи: 21
10-01-2019 дата публикации

Method and system for linear generalized ll recognition and context-aware parsing

Номер: US20190012309A1
Автор: Loring G. Craymer, III
Принадлежит: Individual

A computer system and method of grammar analysis to generate code for runtime recognition to produce a list or graph representation of multiple lists of directions to be followed for a given sentence during a subsequent parse. The computer system implementing the method to parse grammar to create an intermediate representation, construct a graph for analysis that represents all features of a grammar, including recursion, alternation, grouping of alternatives, and looping, process each decision point in the graph to generate the intermediate representation, generate code for recognition functions that return lists of directions for use in runtime parse decisions, and patch each decision point token to reference or inline a top level recognition code for each decision point.

Подробнее
Номер записи: 22
14-01-2021 дата публикации

System and method for the automated tracking of personal and emotional information of individuals

Номер: US20210011975A1
Автор: Pegah AARABI
Принадлежит: Individual

The present disclosure provides a system and method for collecting personal information about an individual. The system and method comprises memory for storing personal information schemas, personal data, emotional data, a communication interface to send a plurality of questions to a user interface and to receive a plurality of responses from the user interface, and a processor: to translate the personal information schemas into a plurality of questions, to translate the responses into personal data or emotional data mapped to the personal information schemas and to analyze the personal information schemas, personal data and emotional data to provide an action.

Подробнее
Номер записи: 23
10-01-2019 дата публикации

Natural language processing to merge related alert messages for accessibility

Номер: US20190013006A1
Автор: Keith G Frost, Kyle M Brake, Stanley J Vernier, Stephen A Boxwell
Принадлежит: International Business Machines Corp

A method, apparatus and computer program product for merging incoming alerts for accessibility are described. Two input alerts intended for presentation by a screen reader are received. If the two input alerts have arrived with a specified time interval, the two input alerts are combined into an output alert. The output alert is sent to a screen reader for presentation.

Подробнее
Номер записи: 24
11-01-2018 дата публикации

Assisting entities in responding to a request of a user

Номер: US20180013699A1
Автор: Gustavo Sapoznik, Hui Dai, Joseph Hackman
Принадлежит: ASAPP Inc

A third-party service may be used to assist entities in responding to requests of users. A third-party service may receive, directly or indirectly, a request of a first user for assistance from a first entity. The third-party service may request information about the first user by sending a request to a computer of the first entity. The third-party service may use the request of the first user and the information about the first user to automatically generate a response to the request of the first user. The third-party service may then transmit, directly or indirectly, the response to the first user.

Подробнее
Номер записи: 25
03-02-2022 дата публикации

SEARCH INDEXING USING DISCOURSE TREES

Номер: US20220035845A1
Автор: Galitsky Boris
Принадлежит: ORACLE INTERNATIONAL CORPORATION

Systems, devices, and methods of the present invention create a searchable index that includes informative portions of text. In an example, a computer-implemented method creates a discourse tree from a body of text. For each non-terminal node in the discourse tree, the method identifies a rhetorical relationship associated with the non-terminal node. The method labels each terminal node associated with the non-terminal node as either a nucleus or a satellite. The method further accesses a rule associated with the rhetorical relationship, and selects, based on the rule, selects the fragment associated with the nucleus. The method creates a searchable index including the selected fragments. 1. A system comprising:a non-transitory computer-readable medium storing computer-executable program instructions; and creating a discourse tree from fragments of text, wherein the discourse tree comprises a plurality of nodes, each non-terminal node representing a rhetorical relationship between two of the fragments of text, and each terminal node is associated with one or more fragments and is associated with a non-terminal node;', identifying, from the discourse tree, a rhetorical relationship associated with the non-terminal node,', 'accessing a rule corresponding to the identified rhetorical relationship, wherein the rule identifies for selection, based on the rhetorical relationship, one or more of (i) a corresponding nucleus elementary discourse unit or (ii) a corresponding satellite elementary discourse unit, and', 'selecting, based on the rule, one or more of (i) the fragment of text associated with the nucleus elementary discourse unit or the (ii) fragment of text associated with the satellite elementary discourse unit; and, 'for each non-terminal node of the discourse tree, 'creating a searchable index comprising multiple entries, each entry corresponding to a selected fragment., 'a processing device communicatively coupled to the non-transitory computer-readable medium ...

Подробнее
Номер записи: 26
03-02-2022 дата публикации

Computer-implemented presentation of synonyms based on syntactic dependency

Номер: US20220035994A1
Автор: Roman Guliak, Stanislav Levental, Yuriy Tanskiy
Принадлежит: Grammarly Inc

In an embodiment, the disclosed technologies are capable of identifying a target word within a text sequence; displaying a subset of candidate synonyms for the target word, determining a synonym selected from the subset of candidate synonyms, and replacing the target word with the selected synonym, where the subset of candidate synonyms has been created using syntactic dependency data for the target word.

Подробнее
Номер записи: 27
03-02-2022 дата публикации

DERIVING MULTIPLE MEANING REPRESENTATIONS FOR AN UTTERANCE IN A NATURAL LANGUAGE UNDERSTANDING (NLU) FRAMEWORK

Номер: US20220036012A1
Автор: Sapugay Edwin, Sarda Gopal
Принадлежит:

The present approaches are generally related to an agent automation framework that is capable of extracting meaning from user utterances, such as requests received by a virtual agent (e.g., a chat agent), and suitably responding to these user utterances. In certain aspects, the agent automation framework includes a NLU framework and an intent-entity model having defined intents and entities that are associated with sample utterances. The NLU framework may include a meaning extraction subsystem designed to generate meaning representations for the sample utterances of the intent-entity model to construct an understanding model, as well as generate meaning representations for a received user utterance to construct an utterance meaning model. The disclosed NLU framework may include a meaning search subsystem that is designed to search the meaning representations of the understanding model to locate matches for meaning representations of the utterance meaning model. 1. An agent automation system , comprising:a memory configured to store a natural language understanding (NLU) framework, wherein the NLU framework includes a part-of-speech (POS) component, a variability filter component, a parser component, and a final scoring and filtering component; and performing, via the POS component, part-of-speech (POS) tagging to generate a set of potential POS taggings for a set of utterances;', 'performing, via the variability filter component, variability filtering of the set of potential POS taggings to generate a set of final nominee POS taggings, wherein each of the set of final nominee POS taggings is distinct from one another;', 'parsing, via the parsing component, the set of final nominee POS taggings to generate a set of potential meaning representations for the set of final nominee POS taggings; and', 'selecting, via the final scoring and filtering component, a final set of meaning representations for the set of utterances from the set of potential meaning representations ...

Подробнее
Номер записи: 28
03-02-2022 дата публикации

AUTONOMOUS DETECTION OF COMPOUND ISSUE REQUESTS IN AN ISSUE TRACKING SYSTEM

Номер: US20220036014A1
Автор: Bar-on Noam, Chung Sukho
Принадлежит:

An issue tracking system configured to determine whether an issue request submitted by a user of the issue tracking system can, or should, be subdivided into two or more issue requests. In some implementations, the issue tracking system is configured to extract a content item of the issue request (e.g., title, description, and the like) in order to perform a semantic and/or syntactic analysis of that content item. Upon determining that the content item includes two or more clauses linked by a coordinating, subordinating, or correlative conjunction, the system can provide a recommendation to the user to submit discrete two or more issue requests, each one of which corresponds to a single linked clause of the content item. 1. An issue tracking system comprising:a client device executing a client application; and receive an issue request from the client application;', 'determine a divisibility score based on semantic content of a content item of the issue request; and', generate two or more issue request templates based on the semantic content of the content item, the issue request templates at least partially populated with data extracted from the issue request; and', 'transmit the two or more populated issue request templates to the client application., 'in response to a determination that the divisibility score satisfies a divisibility threshold], 'a host service operably coupled to the client application of the client device and comprising a processor configured to2. The issue tracking system of claim 1 , wherein:the content item is an issue request description;the semantic content of the issue request description is a set of lemmatized words extracted from the issue request description;the divisibility score is increased upon a first determination that the set of lemmatized words includes at least a threshold number of lemmatized words associated with compound issue requests; andthe divisibility score is decreased upon a second determination that the set of words ...

Подробнее
Номер записи: 29
17-01-2019 дата публикации

Method and system for providing real time search preview personalization in data management systems

Номер: US20190018899A1
Автор: Benjamin Indyk, Igor A. Podgorny, Ling Feng WEI
Принадлежит: Intuit Inc

A method and system provides personalized search results to users of a data management system. The method and system receives a search query from a user and generate initial search results including a plurality of assistance documents relevant to the query data. The method and system utilizes natural language analysis and machine learning processes to analyze the query data, user attributes data, and the assistance documents in order to generate personalized previews of the assistance documents for the user. The method and system output personalized search results to the user including the personalized previews of the assistance documents.

Подробнее
Номер записи: 30
21-01-2021 дата публикации

ANSWER MANAGEMENT IN A QUESTION-ANSWERING ENVIRONMENT

Номер: US20210019313A1
Автор: Barker Kevin S., EGGEBRAATEN THOMAS J., Megerian Mark G., Petri John E., Pfeifer Michael D.
Принадлежит:

Managing answers in a question-answering environment is disclosed. Managing answers in the question-answering environment can include sorting, based on a set of answer categories for a subject matter, a first set of answers into a first answer category and a second set of answers into a second answer category. Managing answers in the question-answering environment can include determining, using the subject matter, a first category sequence including the first answer category and the second answer category, and establishing, based on the first category sequence, a first answer sequence established from a portion of the first set of answers from the first answer category and a portion of the second set of answers from the second answer category. 1. A computer-implemented method , performed by a question-answering system having improved technical functioning such that it provides high-quality and complete responses to input queries , the method comprising:receiving, by the question-answering system, an input query, wherein the input query is a request for instructions to achieve a result;parsing, by the question-answering system using a natural language processing technique configured to analyze syntactic and semantic content, the input query;searching, by the question-answering system and based on the parsed input query, a set of corpora;generating, by the question-answering system and based on the searching, a plurality of answers;analyzing, by the question-answering system, the generated plurality of answers;generating, by the question-answering system and based on the analysis, a plurality of answer categories;sorting, by the question-answering system, the plurality of answers into the plurality of answer categories, wherein, upon the sorting, each answer is included in one answer category, there is at least one answer in at least two answer categories, and there is at least one answer category with at least two answers;generating, by the question-answering system ...

Подробнее
Номер записи: 31
21-01-2021 дата публикации

AUTOMATIC GENERATION OF STATEMENT-RESPONSE SETS FROM CONVERSATIONAL TEXT USING NATURAL LANGUAGE PROCESSING

Номер: US20210019475A1
Автор: Avedissian Narbeh
Принадлежит:

Systems and methods that access an online networked resource using a locator are disclosed. A first item of content on the networked resource is identified. A trigger rule comprising keywords and a sentiment classifier is accessed. A neural network, including input, hidden, and output layers, is used to assign a sentiment classification to the first item of content. The trigger rule, the sentiment classification, and identified keywords, are used to determine whether response content is to be posted to the online networked resource. In response to determining, using the trigger rule, the assigned sentiment classification, and keywords identified in the first item of content, that response content is to be posted to the online networked resource, the sentiment classification and identified keywords are used to select and/or generate a second item of content, and the second item of content is enabled to be posted to the online networked resource. 1. A content distribution system , the content distribution system comprising:a data repository configured to store uploads of a plurality of media files of media submitters, including one or more media files comprising performance data; and provide access to media files of media submitters stored on the media file data repository to a plurality of different types of user devices, including at least a phone, over a communication network;', 'obtain feedback from users with respect to the media files of media submitters;', 'determine that a selected media submitter meets a threshold value or condition;, 'a computer system configured to the determination that the selected media submitter meets the threshold value or condition, provide a first offer of services to the selected media submitter,', 'deliver media files associated with the selected media submitter and one or more advertisements to user devices;', 'monitor subsequent user interactions with the one or more advertisements associated with the media files associated with ...

Подробнее
Номер записи: 32
21-01-2021 дата публикации

METHODS AND APPARATUS TO IMPROVE DISAMBIGUATION AND INTERPRETATION IN AUTOMATED TEXT ANALYSIS USING TRANSDUCERS APPLIED ON A STRUCTURED LANGUAGE SPACE

Номер: US20210019476A1
Автор: Roche Emmanuel
Принадлежит: CLRV Technologies, LLC

Methods and apparatus for automated processing of natural language text is described. The text can be preprocessed to produce language-space data that includes descriptive data elements for words. Source code that includes linguistic expressions, and that may be written in a programming language that is user-friendly to linguists, can be compiled to produce finite-state transducers and bi-machine transducers that may be applied directly to the language-space data by a language-processing virtual machine. The language-processing virtual machine can select and execute code segments identified in the finite-state and/or bi-machine transducers to disambiguate meanings of words in the text. 1. A method of automated processing of text , the method comprising:processing the text to generate a language space having one or more descriptive data elements associated with one or more words in the text and for which a word has multiple meanings; and identifying a match between a first input element in the first finite-state transducer or first bi-machine transducer and a first identifier of a first descriptive data element in the language space associated with a word in the sentence;', 'identifying an expressive element in the first finite-state transducer or first bi-machine transducer following the first input element, wherein the expressive element indicates a relational aspect between the first descriptive data element and a second descriptive data element in the language space;', 'in response to identifying the expressive element, updating transition data that tracks relational aspects of descriptive data elements in the language space; and', 'executing a first code segment, based at least in part on the updated transition data, to produce a modified language space in which the meaning of the word in the sentence associated with the first descriptive data element is disambiguated., 'executing an operation with a first finite-state transducer or first bi-machine transducer ...

Подробнее
Номер записи: 33
16-01-2020 дата публикации

Generative Adversarial Network Based Modeling of Text for Natural Language Processing

Номер: US20200019863A1
Автор: Bowen Zhou, Cicero Nogueira Dos Santos, Dheeru Dua
Принадлежит: International Business Machines Corp

Mechanisms are provided to implement a generative adversarial network (GAN) for natural language processing. With these mechanisms, a generator neural network of the GAN is configured to generate a bag-of-ngrams (BoN) output based on a noise vector input and a discriminator neural network of the GAN is configured to receive a BoN input, where the BoN input is either the BoN output from the generator neural network or a BoN input associated with an actual portion of natural language text. The mechanisms further configure the discriminator neural network of the GAN to output an indication of a probability as to whether the input BoN is from the actual portion of natural language text or is the BoN output of the generator neural network. Moreover, the mechanisms train the generator neural network and discriminator neural network based on a feedback mechanism that compares the output indication from the discriminator neural network to an indicator of whether the input BoN is from the actual portion of natural language text of the BoN output of the generator neural network.

Подробнее
Номер записи: 34
26-01-2017 дата публикации

Identifying errors in medical data

Номер: US20170024517A1
Автор: Brendan C. Bull, David Contreras, Keith P. Biegert, Robert C. Sizemore, Sterling R. Smith
Принадлежит: International Business Machines Corp

A computer processor may receive medical data including a report and an image. The computer processor may analyze the report using natural language processing to identify a condition and a corresponding criterion. The computer processor may also analyze the image using an image processing model to generate an image analysis. The computer processor may determine whether the report has a potential problem by comparing the image analysis to the criterion.

Подробнее
Номер записи: 35
10-02-2022 дата публикации

METHOD AND SYSTEM FOR ONTOLOGY DRIVEN DATA COLLECTION AND PROCESSING

Номер: US20220043813A1
Автор: Mirhaji Parsa
Принадлежит:

Systems and method to aid in the collection, representation and mining of data are disclosed. More particularly, embodiments as disclosed may utilize a unifying format to represent data obtained or utilized by a system to facilitate linking between data from different sources and the commensurate ability to mine such data. Specifically, embodiments may represent data as graphs that comprise the concepts and relationships between those concepts. In this manner, concepts in graphs that represent distinct groupings of data may be mapped and knowledge mining with respect to these graphs facilitated. 1. A system for data mining , comprising:an informatics system, comprising a processor and a non-transitory computer readable medium comprising instructions for:receiving an input from one or more data sources;translating data of the input to a graph representation of the input based on a graph representation of a source ontology;obtaining a graph representation of a domain ontology, wherein the domain ontology comprises a set of concepts and a set of relationships;mapping the graph representation of the input to the graph representation of the domain ontology to create a unified graph comprising the graph representation of the input and the graph representation of the domain ontology;providing the ability to construct a query based on at least one of the set of concepts or at least one of the set of relationships of the domain ontology; andsearching the unified graph based on the query to obtain data of the input associated with at the at least one of the set of concepts or the at least one relationships on which the query is based.2. The system of claim 1 , wherein the domain ontology includes the unified medical language system (UMLS) or GALEN.3. The system of claim 2 , wherein the domain ontology is represented in Simple Knowledge Organization System representation (SKOS).4. The system of claim 1 , wherein the input is survey response.5. A survey system claim 1 , ...

Подробнее
Номер записи: 36
10-02-2022 дата публикации

Cluster analysis method, cluster analysis system, and cluster analysis program

Номер: US20220043851A1
Автор: Kunitoshi YAMASAKI, Ryuichi Hosoya
Принадлежит: Aixs Inc

A server 4 executes a similarity calculation step (S 2 ) of calculating similarity between content of one document and content of another document, a cluster classification step (S 3 ) of generating a network in which a document is set as a node based on calculated similarity and similar nodes are connected by an edge, and performing classification based on similar documents, a first index calculation step (S 4 ) of calculating a first index indicating centrality of a document in the network, a second index calculation step (S 5 ) of calculating a second index that is different from the first index in the network and indicates importance of a document, and a display data generation step (S 6 ) of generating, regarding a document, first display data indicating the network by an expression of a size of an object of a node according to the first index, an expression of a gauge having a shape corresponding to a shape of the object according to the second index and a length of the gauge, an expression according to a type of the cluster, and an expression according to magnitude of similarity between documents.

Подробнее
Номер записи: 37
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: 38
26-01-2017 дата публикации

Resource management in a presentation environment

Номер: US20170026471A1
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: 39
25-01-2018 дата публикации

Encoding device, encoding method and search method

Номер: US20180026650A1
Автор: Masahiro Kataoka, Masao Ideuchi, Seiji Okura
Принадлежит: Fujitsu Ltd

A recording medium having stored therein an encoding program that causes a computer to execute a process, the process including first generating a plurality of word codes by assigning a compression code to each of a plurality of words contained in a sentence in a compression target document, second generating a plurality of pieces of semantic structure information respectively corresponding to the plurality of words by performing a semantic analysis of the sentence, third generating a plurality of semantic structure codes by assigning each of the plurality of compression codes to corresponding semantic structure information, and outputting the plurality of word codes and the plurality of semantic structure codes with a specific order.

Подробнее
Номер записи: 40
24-01-2019 дата публикации

Miscategorized outlier detection using unsupervised slm-gbm approach and structured data

Номер: US20190026356A1
Автор: Mingkuan Liu
Принадлежит: eBay Inc

In an example, one or more leaf category specific unsupervised statistical language model (SLM) models are trained using sample item listings corresponding to each of one or more leaf categories and structured data about the one or more leaf categories, the training including calculating an expected perplexity and a standard deviation for item listing titles. A perplexity for a title of a particular item listing is calculated and a perplexity deviation signal is generated based on a difference between the perplexity for the title of the particular item listing and the expected perplexity for item listing titles in a leaf category of the particular item listing and based on the standard deviation for item listing titles in the leaf category of the particular item listing. A gradient boosting machine (GBM) fuses the perplexity deviation signal with one or more other signals to generate a miscategorization classification score corresponding to the particular item listing.

Подробнее
Номер записи: 41
28-01-2021 дата публикации

METHOD FOR DETECTING DECEPTIVE E-COMMERCE REVIEWS BASED ON SENTIMENT-TOPIC JOINT PROBABILITY

Номер: US20210027016A1
Автор: DONG Luyu, JI Shujuan, Li Da, ZHANG Chunjin, ZHANG Qi
Принадлежит:

Provided is a method for detecting deceptive e-commerce reviews based on a sentiment-topic joint probability, which belongs to the fields of natural language processing, data mining and machine learning. In the data of different fields, a STM model is superior to other reference models; compared with other models, the STM model belongs to a completely un-supervised (no label information) statistic learning method and shows great advantages in processing unbalanced large sample dataset. Thus, the STM model is more suitable for application in a real e-commerce environment. 1{'img': [{'@id': 'CUSTOM-CHARACTER-00041', '@he': '4.57mm', '@wi': '2.46mm', '@file': 'US20210027016A1-20210128-P00001.TIF', '@alt': 'custom-character', '@img-content': 'character', '@img-format': 'tif'}, {'@id': 'CUSTOM-CHARACTER-00042', '@he': '4.23mm', '@wi': '2.46mm', '@file': 'US20210027016A1-20210128-P00002.TIF', '@alt': 'custom-character', '@img-content': 'character', '@img-format': 'tif'}, {'@id': 'CUSTOM-CHARACTER-00043', '@he': '3.89mm', '@wi': '2.12mm', '@file': 'US20210027016A1-20210128-P00003.TIF', '@alt': 'custom-character', '@img-content': 'character', '@img-format': 'tif'}], 'sub': m,n', 'm,n', 'm,n, 'A STM model is a sentiment-topic joint probability model which is a 9-tuple, STM=(α, β, μ, , , , z, s, w), whereinα is a hyper parameter that reflects a relative strength hidden between topic and sentiment;μ is a hyper parameter that reflects a sentiment probability distribution over topic;β is a hyper parameter that reflects a word probability distribution;{'img': {'@id': 'CUSTOM-CHARACTER-00044', '@he': '4.57mm', '@wi': '2.46mm', '@file': 'US20210027016A1-20210128-P00001.TIF', '@alt': 'custom-character', '@img-content': 'character', '@img-format': 'tif'}, 'is a K-dimensional Dirichlet random variable, which is a topic probability distribution matrix;'}{'img': {'@id': 'CUSTOM-CHARACTER-00045', '@he': '4.23mm', '@wi': '2.46mm', '@file': 'US20210027016A1-20210128-P00002.TIF', '@alt': ' ...

Подробнее
Номер записи: 42
28-01-2021 дата публикации

DATA EXTRACTION AND DUPLICATE DETECTION

Номер: US20210027054A1
Автор: Bhatnagar Lokesh, Bhatt Himanshu Sharad, Bhokardole Manoj, Fitzgerald Gabriella P., Jain Vinit, Lohani Chetan, Pandey Shachindra, Panwar Gunjan, Roy Shourya, Xu Di
Принадлежит:

A system provides an end-to-end solution for invoice processing which includes reading invoices (both pdfs and images), extracting key relevant information from the face of invoices, organizing the relevant information in a structured template as a key-value pair, and comparing invoices based on the similarities between different invoice fields to identify potential duplicate invoices. 1. A computer-implemented method , comprising:receiving an invoice;identifying unstructured text in the invoice;converting the unstructured text in the invoice to structured text; andgenerating a structure preserved layout of the invoice that comprises the structured text.2. The computer-implemented method of claim 1 , whereinthe invoice is received in a first format; and converting the invoice to a second format in the form of an image file, and', 'wherein identifying the unstructured text in the invoice further comprises performing optical character recognition on the image file to identify the unstructured text in the invoice., 'the computer-implemented further comprises3. The computer-implemented method of claim 1 , further comprising:removing all spaces from the structured text to generate an intermediate text;segmenting non-space separated words in the intermediate text based at least in part on a reference dictionary to generate a clean text.4. The computer-implemented method of claim 1 , further comprising:identifying a plurality of bigrams in the structured text; andidentifying a plurality of similar bigrams based on a reference of the plurality of bigrams to a language model database; andreplacing the plurality of bigrams with the plurality of similar bigrams to generate a clean text.5. The computer-implemented method of claim 1 , wherein the invoice is a first invoice and the computer-implemented method further comprises comparing the structured text of the first invoice with structured text of a second invoice to determine that the first invoice and the second invoice are ...

Подробнее
Номер записи: 43
24-04-2014 дата публикации

Centering Mathematical Objects in Documents

Номер: US20140115447A1
Автор: Allison M. STYER, Christopher E. Rudolph, Donald R. Beaver, Ian J. Elseth, Martin J. Murrett
Принадлежит: Apple Inc

A content presentations editing application for editing a structured electronic document that includes mathematical objects is provided. The content presentation editing application selects a portion of the document, the selected portion including at least one mathematical object. The content presentation editing application centers the selected portion of the document by identifying an alignment symbol in the mathematical object and aligning the mathematical object to a particular position in the document at the identified alignment symbol. To align the mathematical object, some embodiments move the mathematical object such that the alignment symbol is at the center of the page. For mathematical objects that are located within cells of a table, the center alignment operation moves each mathematical object in the table such that the identified alignment symbol aligns with the center of the table column that contains the mathematical object.

Подробнее
Номер записи: 44
17-02-2022 дата публикации

Mapping natural language utterances to nodes in a knowledge graph

Номер: US20220050864A1
Автор: Cynthia Joann Osmon, Gregory Kenneth COULOMBE, Pavlo MALYNIN, Roger C. Meike, Sricharan Kallur Palli Kumar
Принадлежит: Intuit Inc

Certain aspects of the present disclosure provide techniques for mapping natural language to stored information. The method generally includes receiving a long-tail query comprising a natural language utterance from a user of an application associated with a set of topics and providing the natural language utterance to a natural language model configured to identify nodes of a knowledge graph. The method further includes, based on output of the natural language model, identifying a node of a knowledge graph associated with the natural language utterance, wherein the output of the natural language model includes a node identifier for the node of the knowledge graph and providing the node identifier to the knowledge engine. The method further includes receiving a response associated with the node of the knowledge graph from the knowledge engine and transmitting the response to the user in response to the long-tail query.

Подробнее
Номер записи: 45
17-02-2022 дата публикации

METHOD AND SYSTEM FOR ANALYZING TEXTUAL NARRATIVES USING QUALITY CRITERIA

Номер: US20220050969A1
Автор: ALI Reshmi, ARORA Gurkiran, AVHAD Yogesh, JADHAV Akshay Shantaram, SHAH Kenil Dinesh, SHINDE Prashant P.
Принадлежит: JPMORGAN CHASE BANK, N.A.

A system and method for analyzing a textual narrative are provided. The method includes: receiving, from a user, an input that includes a textual narrative; comparing the textual narrative to various types of quality criteria, including syntactical criteria, semantic criteria, and pragmatic criteria; determining, based on the comparison, whether the textual narrative satisfies the quality criteria; and providing an output that indicates a result of the determination. The textual narrative may be a JIRA user story or a JIRA epic. The comparison may be performed by using one or more Natural Language Processing techniques. 1. A method for analyzing a textual narrative , the method being implemented by at least one processor , the method comprising:receiving, by the at least one processor from a user, an input that includes the textual narrative;comparing, by the at least one processor, the textual narrative to at least one quality criterion;determining, by the at least one processor based on the comparing, whether the textual narrative satisfies the at least one quality criterion; andproviding an output that indicates a result of the determining.2. The method according to claim 1 ,wherein the textual narrative includes at least one from among a JIRA user story that relates to a feature of a software product and a JIRA epic that relates to a plurality of features of a software product.3. The method according to claim 1 ,wherein the comparing is performed by using at least one Natural Language Processing (NPL) technique.4. The method according to claim 1 ,wherein the at least one quality criterion includes at least one from among a syntactical criterion that relates to a syntax of the textual narrative, a semantic criterion that relates to a conceptual soundness of the textual narrative, and a pragmatic criterion that relates to a subjective interpretation of the textual narrative to an audience.5. The method according to claim 4 ,wherein the syntactical criterion ...

Подробнее
Номер записи: 46
17-02-2022 дата публикации

System, method, and computer program for transformer neural networks

Номер: US20220051080A1
Автор: Sanjeet Hajarnis, Tushar Makkar, Varun Kacholia, Xingjian WANG, Yi Ding
Принадлежит: Eightfold AI Inc

A system and method include one or more processing devices to implement a sequence of transformer neural networks, first and second sequence-to-sequence layers that each comprises a sequence of nodes, and an output layer to provide the first set and second set of score vectors to a downstream application of a natural language processing (NLP) task.

Подробнее
Номер записи: 47
04-02-2021 дата публикации

Question group extraction method, question group extraction device, and recording medium

Номер: US20210034815A1
Автор: Ayako HOSHINO
Принадлежит: NEC Corp

An addition unit 11, with regard to data indicating a conversation history including one or more sets of sentences formed from a problem sentence being a sentence indicating one problem, a question sentence being a sentence indicating a question for the one problem, and an answer sentence being a sentence indicating an answer to the question, adds a label indicating a problem state to the problem sentence within the data, a label indicating a question state to the question sentence within the data, and a label indicating an answer state to the answer sentence within the data. An extraction unit 12 extracts, from the data, a set of sentences with which the states indicated by the labels have been associated according to a state transition model that is a model configured from the one problem state, question state, and answer state, and that represents a transition of the states.

Подробнее
Номер записи: 48
11-02-2016 дата публикации

System and method for evaluating input based on dynamic grammars

Номер: US20160042442A1
Автор: Gunther Rademacher, Harald Schöning, Juliane Harbarth
Принадлежит: Software AG

A method and system for evaluating service definitions in a service-oriented architecture (SOA) system which provides service offerings categorized according to service categories using a taxonomy. A specification field receives a formal definition of a service. The formal definition is for inclusion to define one of service offerings of the SOA. A current grammar is determined which is currently in effect as a specification-requirement of acceptable definitions for a service category in which the service is categorized. The current grammar is a common grammar. The system determines whether the formal definition in the specification field is acceptable, by adhering to the current grammar determined to be currently in effect as the specification-requirement for the category of the service. The formal definition is accepted for the service when it is determined to be acceptable according to the current grammar. Otherwise, the formal definition is rejected.

Подробнее
Номер записи: 49
08-02-2018 дата публикации

Systems and methods for asymmetrical formatting of word spaces according to the uncertainty between words

Номер: US20180039617A1
Автор: Christopher D Nicholas, Kenneth R Brownfield
Принадлежит: Asymmetrica Labs Inc

Asymmetrical formatting of word spaces according to the uncertainty between words includes an initial filtering process and subsequent text formatting process. An equivocation filter generates a mapping of keys and values (output) from a corpus or word sequence frequency data (input). Text formatting process for asymmetrically adjusts the width of spaces adjacent to keys using the values. The filtering process, which generates a mapping of keys and values can be performed once to analyze a corpus and once generated, the key-value mapping can be used multiple times by a subsequent text processing process.

Подробнее
Номер записи: 50
24-02-2022 дата публикации

DATA ACCURACY USING NATURAL LANGUAGE PROCESSING

Номер: US20220058172A1
Автор: BHATTACHARYA Satyaki, DAS Priya, JOHN Rajeev, Joshi Sanjaykumar, KUMAR PANDEY Vivek, Kumar Sameer, RAMASWAMY Srinivasan, RAY Aniruddha, Swamy Jayant, VYAS Vismay
Принадлежит: Accenture Global Solutions Limited

Examples for enhancing veracity of data are described herein. Data from a repository may be received based on a data receiving rule. From the received data, a first dataset may be generated using statistical modeling. Also, a first data veracity score for the first dataset is generated which is indicative of a degree of usability of the dataset. Another aspect relates to identifying an anomaly in the first dataset, the corrector, for each anomaly, to identify a correction technique from amongst a plurality of correction techniques. Further, a second dataset is generated using the identified correction technique having second data veracity score higher than the first data veracity score. 1. A system comprising:a processor;a retriever coupled to the processor to receive data from a repository, wherein the retriever receives the data based on a data receiving rule;a profiler coupled to the processor to generate a first dataset from the received data, wherein the profiler creates a first dataset of data using statistical modeling;a veracity generator coupled to the processor to generate a first data veracity score for the first dataset of the data, wherein the first data veracity score is indicative of a degree of usability of the first dataset;a corrector coupled to the processor to identify an anomaly in the first dataset, wherein the corrector is to identify an optimal correction technique from amongst a plurality of correction techniques to substantially remove the anomaly, wherein, based on a type of the received data, the corrector is to identify one of a machine learning model from amongst a plurality of machine learning models and a statistical data analysis technique from amongst a plurality of statistical data analysis techniques as the optimal correction technique; anda recommender coupled to the processor to generate a second dataset using the optimal correction technique, wherein the veracity generator generates a second data veracity score for the second ...

Подробнее
Номер записи: 51
12-02-2015 дата публикации

Method and Apparatus for a Multi I/O Modality Language Independent User-Interaction Platform

Номер: US20150046168A1
Автор: Alireza Salimi, Andrei Dragoi, Eric Buist, Simona Gandrabur
Принадлежит: Nuance Communications Inc

Automated user-machine interaction is gaining attraction in many applications and services. However, implementing and offering smart automated user-machine interaction services still present technical challenges. According to at least one example embodiment, a dialogue manager is configured to handle multiple dialogue applications independent of the language, the input modalities, or output modalities used. The dialogue manager employs generic semantic representation of user-input data. At a step of a dialogue, the dialogue manager determines whether the user-input data is indicative of a new request or a refinement request based on the generic semantic representation and at least one of a maintained state of the dialogue, general knowledge data representing one or more concepts, and data representing history of the dialogue. The dialogue manager then responds to determined user-request with multi-facet output data to a client dialogue application indicating action(s) to be performed.

Подробнее
Номер записи: 52
24-02-2022 дата публикации

SEMANTIC LANGUAGE FEATURE DEFINITION LANGUAGE FOR USE IN FRAUD DETECTION

Номер: US20220058341A1
Автор: JR. Willie Robert, Kelton Eugene Irving, Lambert Russell Gregory, McPherson Jacob, Patten
Принадлежит:

A semantic, machine readable language part that supports the specification of features is used by an engine that interprets that language to produce the features based on the raw data. In this way, the model developer can specify the measurement columns (for example, data fields), to obtain the dimensions from which the engine can compute the multiple combinations of features possible based on this set of input fields. This computation of features can be used to perform machine learning (ML) training and/or scoring algorithms (for example, ML algorithms for fraud detection). 1. A computer-implemented method (CIM) comprising:receiving a piece of coded syntax including machine readable information indicative of at least the following: (i) an identification of document(s) making up an input corpus, (ii) an identification of a set of focal object(s), (iii) an identification of a set of measurement(s), (iv) an identification of a set of dimension(s), and (v) an identification of set of feature(s) to compute; and retrieve the input corpus, and', 'analyze the corpus with respect to the set of focal object(s), the set of measurement(s) to determine a set of feature value(s) corresponding to the set of feature(s) to compute., 'parsing the piece of coded syntax to2. The CIM of further comprising:using the set of feature value(s) to perform a scoring function on a machine learning algorithm.3. The CIM of further comprising:using the set of feature value(s) to perform training for a machine learning algorithm.4. The CIM of wherein:the piece of coded syntax further includes an identification of a set of aggregation attribute(s); andthe analysis of the corpus to determine the set of feature value(s) is further based on the aggregation attribute(s).5. The CIM of wherein the piece of coded syntax is formed and formatted according to a semantic language part that supports the specification of features.6. The CIM of wherein the input corpus is in OWL/RDF (web ontology language/ ...

Подробнее
Номер записи: 53
24-02-2022 дата публикации

WRITTEN-MODALITY PROSODY SUBSYSTEM IN A NATURAL LANGUAGE UNDERSTANDING (NLU) FRAMEWORK

Номер: US20220058343A1
Автор: Madamala Anil Kumar, Naboka Maxim, Santos Lewis Savio Landry, Sapugay Edwin, Subbarao Murali B., Sunkara Srinivas SatyaSai
Принадлежит:

Present embodiment include a prosody subsystem of a natural language understanding (NLU) framework that is designed to analyze collections of written messages for various prosodic cues to break down the collection into a suitable level of granularity (e.g., into episodes, sessions, segments, utterances, and/or intent segments) for consumption by other components of the NLU framework, enabling operation of the NLU framework. These prosodic cues may include, for example, source prosodic cues that are based on the author and the conversation channel associated with each message, temporal prosodic cues that are based on a respective time associated with each message, and/or written prosodic cues that are based on the content of each message. For example, to improve the domain specificity of the agent automation system, intent segments extracted by the prosody subsystem may be consumed by a training process for a ML-based structure subsystem of the NLU framework. 1. A method of operating a natural language understanding (NLU) framework , comprising:receiving, via a prosody subsystem of the NLU framework, a conversation log comprising a plurality of written messages;dividing, via the prosody subsystem, a subset of the conversation log into a plurality of sessions based at least in part on temporal prosodic cues of the plurality of written messages, written prosodic cues of the plurality of written messages, or any combination thereof;dividing, via the prosody subsystem, each of the plurality of sessions into a plurality of conversation segments based at least in part on the temporal prosodic cues of the plurality of written messages, the written prosodic cues of the plurality of written messages, or any combination thereof andproviding the plurality of sessions, the plurality of conversation segments, or any combination thereof, to a behavior engine of the NLU framework, wherein the behavior engine is configured to generate episodic context information based on the ...

Подробнее
Номер записи: 54
24-02-2022 дата публикации

Data processing method, device, and storage medium

Номер: US20220058349A1
Автор: Haijiang Wu, Songling YUAN, Xiaoli Wang, Xinjie WEN
Принадлежит: Tencent Technology Shenzhen Co Ltd

A data processing method is described. The method includes acquiring a to-be-filtered dataset, the to-be-filtered dataset including a plurality of pieces of to-be-filtered source language data; filtering all source language data in the to-be-filtered dataset based on a target data filtering model to obtain target source language data remaining after the filtering, the target data filtering model being obtained through training performed by using a reinforcement learning algorithm; and acquiring markup language data corresponding to the obtained target source language data, and acquiring a machine translation model based on the target source language data and the acquired markup language data. In such a data processing process, a filtering rule in the target data filtering model is automatically learned by a machine in a reinforcement learning process. Apparatus and non-transitory computer-readable storage medium counterpart embodiments are also provided.

Подробнее
Номер записи: 55
06-02-2020 дата публикации

Method and system for text understanding in an ontology driven platform

Номер: US20200042523A1
Автор: Parsa Mirhaji
Принадлежит: University of Texas System

Embodiments of methods and systems for informatics systems are disclosed. Such informatics systems may utilize a unifying format to represent text to facilitate linking between data from the text and one or more ontologies, and the commensurate ability to mine such data.

Подробнее
Номер записи: 56
07-02-2019 дата публикации

Speech endpointing based on word comparisons

Номер: US20190043480A1
Автор: Christopher Bo Tandiono, Michael Buchanan, Pravir Kumar Gupta
Принадлежит: Google LLC

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech endpointing based on word comparisons are described. In one aspect, a method includes the actions of obtaining a transcription of an utterance. The actions further include determining, as a first value, a quantity of text samples in a collection of text samples that (i) include terms that match the transcription, and (ii) do not include any additional terms. The actions further include determining, as a second value, a quantity of text samples in the collection of text samples that (i) include terms that match the transcription, and (ii) include one or more additional terms. The actions further include classifying the utterance as a likely incomplete utterance or not a likely incomplete utterance based at least on comparing the first value and the second value.

Подробнее
Номер записи: 57
18-02-2021 дата публикации

Enabling rhetorical analysis via the use of communicative discourse trees

Номер: US20210049329A1
Автор: Boris Galitsky
Принадлежит: Oracle International Corp

Systems, devices, and methods of the present invention calculate a rhetorical relationship between one or more sentences. In an example, a computer-implemented method accesses a sentence comprising a plurality of fragments. At least one fragment includes a verb and a words. Each word includes a role of the words within the fragment. Each fragment is an elementary discourse unit. The method generates a discourse tree that represents rhetorical relationships between the sentence fragments. The discourse tree includes nodes including nonterminal and terminal nodes, each nonterminal node representing a rhetorical relationship between two of the sentence fragments, and each terminal node of the nodes of the discourse tree is associated with one of the sentence fragments. The method matches each fragment that has a verb to a verb signature, thereby creating communicative discourse tree.

Подробнее
Номер записи: 58
16-02-2017 дата публикации

Parsing and Interpretation of Logical Statements

Номер: US20170046139A1
Автор: Xiaohua Yi
Принадлежит: Individual

Methods, systems, and devices are described that enable parsing and interpretation of logical statements in “native style” with syntax that is very similar to that of first-order-logic (FOL) and “prose style” with which logical statements are expressed in English prose, or a mixture of both English prose and FOL.

Подробнее
Номер записи: 59
03-03-2022 дата публикации

Reasoning based natural language interpretation

Номер: US20220067102A1
Автор: Ayushi Dalmia, Jaydeep Sen, Karthik Sankaranarayanan, Sumit Bhatia
Принадлежит: International Business Machines Corp

A natural language processing approach for generating domain specific reasoning-based meaning representations. The approach may include receiving a user query via structured or unstructured data. The approach may also include generating a structured query from the user query using domain specific ontology and universal facts. Further, the approach many include the structured query may be analyzed to determine if the structured query has been assigned consistent concepts, properties and actions. Additionally, the approach may involve correcting the structured query if it is determined the structured query is inconsistent with the domain ontology and the universal facts.

Подробнее
Номер записи: 60
03-03-2022 дата публикации

METHODS, APPARATUSES AND COMPUTER PROGRAM PRODUCTS FOR PARSING TEMPORAL EXPRESSIONS IN A CONVERSATIONAL DATA-TO-TEXT SYSTEM

Номер: US20220067276A1
Автор: Alexander John William, De Oliveira Rodrigo Gomes
Принадлежит:

Embodiments provide for a temporal expression parser in a conversational data-to-text system are described herein. An example method may include receiving user query data comprising an input text string; generating, based at least in part on the input text string, a n-gram set comprising a plurality of n-gram elements; traversing each n-gram element in the n-gram set to generate a parse tree list comprising one or more parse trees based on a grammar template associated with the input text string; and generating, based at least in part on a last parse tree of the parse tree list, one or more semantic frames indicating a temporal expression associated with the input text string.

Подробнее
Номер записи: 61
03-03-2022 дата публикации

Determining topics and action items from conversations

Номер: US20220067299A1
Автор: Ansup Babu, Sekhar Vallath, Toshish Arun Jawale
Принадлежит: Rammer Technologies Inc

Embodiments are directed to organizing conversation information. Two or more machine learning (ML) models and a plurality of sentences provided from a conversation may be employed to generate insight scores for each sentence such that each insight score correlates to a probability that its sentence includes one or more of an action or a question. In response to one or more sentences having insight scores that exceed a threshold value an information score and a definiteness score may be determined for the one or more sentences. And one or more insights associated with the conversation may be generated based on the one or more sentences. A report may be generated that associates the one or more insights with one or more portions of the conversation that include the one or more sentences that are associated with the insights.

Подробнее
Номер записи: 62
03-03-2022 дата публикации

Semantic clustering of messages

Номер: US20220070630A1
Автор: Alec RUBIN, Barry Steinglass, Josh ROSENHECK, Lars PERKINS, Matthew PELTIER, Nate Saletan, Skylar KERZNER, Tomas KOCI
Принадлежит: Community com Inc

Example systems, methods, and computer-readable media are disclosed. In an example method, a first outbound text message is transmitted via a message broker of a messaging platform from a client to a plurality of recipients. In response to the first outbound message, a plurality of inbound text messages is received, via the message broker, from the plurality of recipients. A first grouping of the plurality of inbound text messages is determined, the first grouping associated with one or more recipients of the plurality of recipients. The first grouping is presented to the client. A second outbound text message is transmitted, via the message broker, from the client to the one or more recipients of the plurality of recipients. The second outbound text message is generated based on the first grouping. The message broker is in communication with a first messaging service and a second messaging service different from the first messaging service. The first outbound text message is transmitted via the first messaging service. A first inbound text message of the plurality of inbound text messages is received via the second messaging service. Each inbound text message of the plurality of inbound text message is addressed to a long-code telephone number generated by the messaging platform and uniquely associated with the client by the messaging platform.

Подробнее
Номер записи: 63
25-02-2021 дата публикации

Document information evaluating device, document information evaluating method, and document information evaluating program

Номер: US20210056304A1
Автор: Hajime Shirasaka, Takashi Mikami, Yuki Adachi
Принадлежит: AI Samurai Inc, Al Samurai Inc

An information acquiring unit configured to acquire input information input from a user terminal that is able to be operated by a user from the user terminal, a storage unit configured to store a plurality of pieces of document information, a calculation unit configured to decompose the input information into predetermined constituent units and calculate a matching condition with one piece of document information among the plurality of pieces of document information stored in the storage unit as a score for each decomposed constituent unit, an output unit configured to output a comparison table representing a degree of difference between the input information and the document information for each constituent unit on the basis of the score, and an input unit configured to input a self-evaluation of the document information that is performed by the user to the comparison table are included.

Подробнее
Номер записи: 64
22-02-2018 дата публикации

Computer assisted completion of hyperlink command segments

Номер: US20180052879A1
Автор: Charles Wright
Принадлежит: Illumon LLC

Described are methods, systems and computer readable media for computer assisted completion of hyperlink command segments.

Подробнее
Номер записи: 65
25-02-2021 дата публикации

Modification of audio-based computer program output

Номер: US20210058347A1
Автор: Alex Jacobson, Laura Eidem
Принадлежит: Google LLC

Modifying computer program output in a voice or non-text input activated environment is provided. A system can receive audio signals detected by a microphone of a device. The system can parse the audio signal to identify a computer program to invoke. The computer program can identify a dialog data structure. The system can modify the identified dialog data structure to include a content item. The system can provide the modified dialog data structure to a computing device for presentation.

Подробнее
Номер записи: 66
10-03-2022 дата публикации

Text-Based News Significance Evaluation Method, Apparatus, and Electronic Device

Номер: US20220075938A1
Автор: CHEN He, Lu Wenxi, Wu Ying, ZHANG Qingquan
Принадлежит: Business Management Advisory LLC

The present invention provides text-based news significance evaluation methods, apparatuses, and electronic devices for improving efficiency and accuracy of news significance evaluation, and implementing real-time dynamic evaluation on text news. The method comprises: reading text news; preprocessing the text news to obtain original data; extracting feature values from the original data, which comprises metadata, a keyword, and a probability model feature value; and obtaining a score of each feature value according to a weight ratio corresponding to each feature value. The apparatus comprises: a text news reading module, a text news preprocessing module, a feature value extraction module, a feature value weight determining module, and a text news significance evaluation module. The electronic device comprises a memory and a processor. The memory stores a computer program that can run on the processor. When executing the computer program, the processor implements the text-based news significance evaluation method. 1. A text-based news significance evaluation method , comprising:reading text news;preprocessing the text news to obtain original data;extracting feature values from the original data, wherein the feature values comprise metadata, a keyword, and a probability model feature value;obtaining a score of each feature value according to a weight ratio corresponding to each feature value; andevaluating significance of the text news according to the score of each feature value.2. The text-based news significance evaluation method of claim 1 , wherein the text news comprises a news text in a txt or pdf format.3. The text-based news significance evaluation method of claim 1 , wherein the preprocessing comprises converting a character sequence to a lowercase character claim 1 , selecting a word within a specific length range claim 1 , deleting an invalid character claim 1 , deleting a numeral claim 1 , deleting a stop word claim 1 , or extracting a stem and restoring ...

Подробнее
Номер записи: 67
10-03-2022 дата публикации

NATURAL LANGUAGE PROCESSING OF UNSTRUCTURED DATA

Номер: US20220075939A1
Автор: Andrews Joshua N., JR. Thomas C., Wisehart
Принадлежит:

A computer system for processing unstructured data, the computer system comprising a computer processor, a computer memory operatively coupled to the computer processor and the computer memory having disposed within it computer program instructions that, when executed by the processor, cause the computer system to carry out the steps of receiving unstructured data input from a client device, analyzing the unstructured data for features that satisfy logical segment criteria by using natural language processing (NLP), and partitioning the unstructured data into logical segments based on satisfaction of the logical segment criteria. 1. A method , in a data processing system comprising a processor and a memory , for processing unstructured data , the method comprising:receiving, by the data processing system, the unstructured data input from a client device;analyzing, by the data processing system, the unstructured data for features that satisfy logical segment criteria by using natural language processing (NLP); andpartitioning, by the data processing system, the unstructured data into logical segments based on satisfaction of the logical segment criteria, whereinthe satisfaction of the logical segment criteria includes comparing scores respectively assigned to text fragments within the logical segments to the logical segment criteria, andthe unstructured data is partitioned into the logical segments in accordance with the scores.2. The method of whereinthe unstructured data comprise text includes topics and/or content.3. The method of whereinthe analyzing the unstructured data for features further comprises using the NLP to identify text that satisfy the logical segment criteria.4. The method of whereinthe unstructured data includes compliance obligations.5. The method of whereinthe logical segment criteria include features associated with a plurality of industries or companies.6. The method of whereinthe logical segment criteria include features associated with ...

Подробнее
Номер записи: 68
10-03-2022 дата публикации

INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND STORAGE MEDIUM STORING INFORMATION PROCESSING PROGRAM

Номер: US20220075943A1
Автор: Kokojima Yoshiyuki, Takeyama Yasutoyo
Принадлежит: KABUSHIKI KAISHA TOSHIBA

An information processing apparatus includes a processor. The processor receives an input of a graph structure. The graph structure has nodes including text and edge. The processor assigns the nodes to one or more clusters. The processor partitions the text into words. The processor classifies the words into 1) a word representing a subject or target of an operation, 2) a word representing a content or state of the operation, and 3) other words. The processor extracts a frequent word by counting a frequency of occurrence of one or more words classified as the words representing the subject or target of the operation and extracts a frequent word by counting a frequency of occurrence of one or more words classified as the words representing the content or state of the operation, for the respective clusters. 1. An information processing apparatus , comprising: receive an input of a graph structure having a plurality of nodes including text and edge interconnecting the nodes;', 'assign the nodes of the graph structure to one or more clusters;', 'partition the text included in the nodes assigned to the respective clusters into words;', 'classify the words into 1) a word representing a subject or target of an operation, 2) a word representing a content or state of the operation, and 3) other words; and,', 'for the respective clusters, extract a first frequent word by counting a frequency of occurrence of one or more first words classified as the words representing the subject or target of the operation and extract a second frequent word by counting a frequency of occurrence of one or more second words classified as the words representing the content or state of the operation., 'a processor configured to2. The information processing apparatus according to claim 1 ,wherein the processor generates a summarized graph structure by substituting, for the clusters, nodes including text that lists the extracted first frequent words and second frequent words.3. The information ...

Подробнее
Номер записи: 69
10-03-2022 дата публикации

Dynamic detection of cross-document associations

Номер: US20220076007A1
Автор: Akshaya D. N, Kartik Chaudhary, Sharlene L. Tan, Swapna Sourav Rout, Vamsi Bhandaru, Vineet Shukla
Принадлежит: Optum Technology LLC

Systems and methods are configured to generate a set of related document objects for a predictive entity and/or to generate an optimal document sequence for a set of related document objects. In one embodiment, a set of related document objects for a predictive entity is generated by processing entity metadata features associated with the predictive entity using an entity-document correlation machine learning model, and an optimal document sequence is generated for the set of related document objects by processing the set of related document objects using a document sequence optimization machine learning model.

Подробнее
Номер записи: 70
03-03-2016 дата публикации

Systems and methods for analyzing document coverage

Номер: US20160062986A1
Автор: C. David Seuss
Принадлежит: NORTHERN LIGHT GROUP LLC

A system including a memory storing a meaning taxonomy is provided. The meaning taxonomy includes meaning loaded entities and associations between meaning loaded entities and syntactic structures. Each association links a meaning loaded entity to a syntactic structure. The system includes a processor coupled with the memory and components executable by the processor configured to receive content generated by a source, the content including syntactic structures, identify meaning loaded entities that are linked to the syntactic structures by associations, calculate a content summary indicating a level of coverage of the meaning loaded entities within the content, and provide a representation of the summary to an external entity.

Подробнее
Номер записи: 71
01-03-2018 дата публикации

Predicate Parses Using Semantic Knowledge

Номер: US20180060304A1
Автор: Brendan C. Bull, David Contreras, Paul L. Felt
Принадлежит: International Business Machines Corp

A mechanism is provided for improving predicate parses (or logical representations of a passage) using semantic knowledge. In response to encountering an ambiguous decision point during a syntactic analysis of a portion of natural language content, a candidate meaning of the ambiguous decision point is generated. Characteristics of the ambiguous decision point are evaluated based on a semantic knowledge base to determine a semantic meaning associated with the ambiguous decision point. A determination is made as to whether the semantic meaning supports or refutes the candidate meaning. In response to determining that the semantic meaning refutes the candidate meaning, the candidate meaning of the ambiguous decision point is overridden based on the semantic meaning to include the semantic meaning as a final meaning for the ambiguous decision point. The portion of natural language content is then processed based on the final meaning for the ambiguous decision point.

Подробнее
Номер записи: 72
01-03-2018 дата публикации

Extracting facts from natural language texts

Номер: US20180060306A1
Автор: Anatoly Sergeevich Starostin, Ivan Mikhailovich Smurov, Stanislav Sergeevich Dzhumaev
Принадлежит: ABBYY Production LLC

Systems and methods for extracting facts from natural language texts. An example method comprises: receiving an identifier of a token comprised by a natural language text, wherein the token comprising at least one natural language word references a first information object; receiving identifiers of a first plurality of words representing a first fact of a specified category of facts, wherein the first fact is associated with the first information object of a specified category of information objects; identifying, within the natural language text, a second plurality of words; and responsive to receiving a confirmation that the second plurality of words represents a second fact associated with a second information object of the specified category of information objects, modifying a parameter of a classifier function that produces a value reflecting a degree of association of a given semantic structure with a fact of the specified category of facts.

Подробнее
Номер записи: 73
10-03-2022 дата публикации

METHOD AND SYSTEM FOR GENERATING INVESTIGATION CASES IN THE CONTEXT OF CYBERSECURITY

Номер: US20220078198A1
Автор: GINGRAS Eric, HAMELIN Benoit, LALONDE LEVESQUE Fanny, Michaud Frédéric, MORIN Louis Philip, PARADIS Mickael, PIQUETTE Patrick, THEBERGE Marc
Принадлежит: ELEMENT AI INC.

A system for generating a cybersecurity investigation case that comprises: an event parser for receiving an event and identifying at least one empty entity from the received event; a case investigator for determining a value to the at least one empty entity to obtain at least one enriched entity; a case correlator for associating at least one existing investigation case to the received event; and a case manager for generating and outputting the cybersecurity investigation case. 1. A system for generating a cybersecurity investigation case , comprising:an event parser for receiving an event and identifying at least one empty entity from the received event;a case investigator for determining a value to the at least one empty entity to obtain at least one enriched entity;a case correlator for associating at least one existing investigation case to the received event; anda case manager for generating and outputting the cybersecurity investigation case.2. The system of claim 1 , wherein the event parser is configured for identifying the at least one empty entity using a previously statically defined parsing method.3. The system of claim 1 , wherein the event parser is configured for identifying the at least one empty entity by searching for regular expressions matching on known patterns.4. The system of claim 1 , wherein the event parser is configured for identifying the at least one empty entity using one of a natural language processing and a statistical Named-Entity Recognition method.5. (canceled)6. The system of any one of to claim 1 , wherein the received event is represented by at least one vectorized feature.7. The system of claim 6 , wherein the case correlator is configured for determining the at least one vectorized feature using a machine learning model and a neural network.8. The system of or claim 6 , wherein the case correlator is configured for determining a measure of one of similarity and distance between the received event and the at least one existing ...

Подробнее
Номер записи: 74
20-02-2020 дата публикации

Systems and methods providing a cognitive augmented memory network

Номер: US20200057807A1
Автор: Ajay Baranwal, Ajay Kapur, Deepak Jain
Принадлежит: Nirveda Cognition Inc

A system to electronically generate original content may include a Cognitive Memory Augmented Network (“CAMN”) that ingests data from structured and unstructured sources and organizes it in a neural network. Generic and/or custom decomposition may ensure that the data sources are broken down inside the CAMN to individual elements of reusable data. A Cognitive Gateway Interface (“CGI”) may make data available inside the CAMN accessible to processes such as cognitive search, content extraction, and/or summarization. A feedback mechanism may ingest human thought and convert the feedback to introduce original content into an output. With an enriched CAMN built upon substantial digital content, the system may learn deep semantic meaning and understanding based on content. The system may create and curate new articles, and an assistant system may work as interpreter of content. The system may help with complex research on advanced topics and provide personalized and/or customized reports.

Подробнее
Номер записи: 75
20-02-2020 дата публикации

Apparatuses and methods for signing a legal document

Номер: US20200057871A1
Автор: Robin P. Hartley
Принадлежит: Individual

Provided is a server, for use in digitally signing writing in a legal document, wherein a signee has an associated public/private key pair, the server comprising: one or more processors; a communication module, to communicate with a signee device; memory comprising instructions which when executed by one or more of the processors configure the server to: process a document based on a set of rules to extract writing from the document, for signing, from other document data; and generate, on the server, or receive, from the signee device: a hash of the extracted writing; a signee security stamp based on a private key associated with the signee and the hash.

Подробнее
Номер записи: 76
02-03-2017 дата публикации

Providing answers to questions including assembling answers from multiple document segments

Номер: US20170060990A1
Автор: David A. Ferrucci, Eric W. Brown, James W. Murdock, IV, Jennifer Chu-Carroll
Принадлежит: International Business Machines Corp

A method, system and computer program product for generating answers to questions. In one embodiment, the method comprises receiving an input query, identifying a plurality of candidate answers to the query; and for at least one of these candidate answers, identifying at least one proof of the answer. This proof includes a series of premises, and a multitude of documents are identified that include references to the premises. A set of these documents is selected that include references to all of the premises. This set of documents is used to generate one or more scores for the one of the candidate answers. A defined procedure is applied to the candidate answers to determine a ranking for the answers, and this includes using the one or more scores for the at least one of the candidate answers in the defined procedure to determine the ranking for this one candidate answer.

Подробнее
Номер записи: 77
04-03-2021 дата публикации

Method and System for Refactoring Document Content and Deriving Relationships Therefrom

Номер: US20210064672A1
Автор: Richard V. Rifredi, Sanjay G. Mahadi
Принадлежит: Individual

A method and system for refactoring document content and deriving relationships therefrom are described. For each page of a document to be processed, a processing engine processes a page of the document to create a summary and metadata relating to the page, determines a keyphrase relating to the summary, generates links to other content based on the keyphrase, and stores the summary, the keyphrase, the links, and the metadata. A search engine processes a search term, retrieves a page of a document containing the search term, and returns only the page that contains the search term and not the entire document that contains the search term.

Подробнее
Номер записи: 78
02-03-2017 дата публикации

Temporal based word segmentation

Номер: US20170061291A1
Автор: Abraham Murray, Daniel Martin Keysers, Shumin Zhai, Thomas Deselaers
Принадлежит: Google LLC

A computing device is described that receives first input, at an initial time, of a first textual character and a second input, at a subsequent time, of a second textual character. The computing device determines, based on the first and second textual characters, a first character sequence that does not include a space character between the first and second textual characters and a second character sequence that includes the space character between the first and second textual characters. The computing device determines a first score associated with the first character sequence and a second score associated with the second character sequence. The computing device adjusts, based on a duration of time between the initial and subsequent times, the second score to determine a third score, and responsive to determining that the third score exceeds the first score, the computing device outputs the second character sequence.

Подробнее
Номер записи: 79
04-03-2021 дата публикации

APPARATUS FOR EXTRACTING SYNTAX AND ELECTRONIC APPARATUS INCLUDING THE SAME

Номер: US20210064818A1
Автор: KIM HyeYoung, KIM YOUNGWOOK, SUN Hangyeol
Принадлежит: LG ELECTRONICS INC.

Provided are an apparatus for extracting a syntax and an electronic apparatus including the same. The apparatus for extracting a syntax and the electronic apparatus including the same according to embodiments of the present disclosure include a communicator to receive data or transmit data through an external network and a processor to collect text data through the communicator and extract a core syntax based on the collected text data, and the processor collects the text data from a server to provide a social network service through the external network, extracts a sentence from the collected text, and extracts a core syntax based the extracted sentence and a prestored syntax rule. As a result, the text is collected from the server of the social network service to extract effectively extract the core syntax from the collected text. 1. An apparatus for extracting a syntax , the apparatus comprising:a communicator to receive data or transmit data through an external network; anda processor to collect text data through the communicator and extract a core syntax based on the collected text data,wherein the processor collects the text data from a server to provide a social network service through the external network, extracts a sentence from the collected text, and extracts the core syntax based on the extracted sentence and a prestored syntax rule.2. The apparatus for extracting a syntax of claim 1 , wherein in case in which the processor extracts the sentence from the collected text and a small sentence is included in the extracted sentence claim 1 , the processor extracts the small sentence and extracts the core syntax based on the extracted small sentence.3. The apparatus for extracting a syntax of claim 2 , wherein in case in which the text is English claim 2 , the processor extracts an adjective or noun phrase following a verb in the small sentence as the core syntax based on the stored syntax rule.4. The apparatus for extracting a syntax of claim 2 , wherein in ...

Подробнее
Номер записи: 80
04-03-2021 дата публикации

SERVER

Номер: US20210064819A1
Автор: KIM Dongho, Kim Youngsik, KIM YOUNGWOOK, KWAK Yonghoon, SUN Hangyeol
Принадлежит: LG ELECTRONICS INC.

The present disclosure relates to a server. The server includes a communicator to receive and transmit data from and to an external network, and a processor to detect and monitor an online issue in the external network through the communicator, wherein the processor collects text from a plurality of external servers, performs learning on the collected text, performs an issue detection, and monitors text corresponding to a confirmed issue. Accordingly, an online issue in a network is effectively detected and monitored. 1. A server comprising:a communicator to receive and transmit data from and to an external network; anda processor to detect and monitor an online issue in the external network through the communicator,wherein the processor collects text from a plurality of external servers, performs learning on the collected text, performs an issue detection, and monitors text corresponding to a confirmed issue.2. The server of claim 1 , wherein the processor performs issue scoring for calculating an issue score of the confirmed issue.3. The server of claim 1 , wherein the processor collects text from the plurality of external servers during a first set period.4. The server of claim 1 , wherein the processor collects text corresponding to a set related word from the plurality of external servers during a first set period.5. The server of claim 1 , wherein the processor performs learning on text corresponding to the confirmed issue.6. The server of claim 1 , wherein the processor performs learning and primary filtering on the collected text through a plurality of issue detection models and performs secondary filtering thereon through a garbage-filtering model.7. The server of claim 1 , wherein the processor classifies the collected text into formal text and informal text through a plurality of issue detection models and performs formal-text-based learning and informal-text-based learning.8. The server of claim 1 , wherein the processor collects text related to the ...

Подробнее
Номер записи: 81
04-03-2021 дата публикации

Processing transactional feedback

Номер: US20210064824A1
Автор: Brandon An Lai, Canran XU, Don Kumudu Janaka RANATUNGA, Jason DIRAN, Marie Michelle Rhea FOSTER, Sanjika HEWAVITHARANA
Принадлежит: eBay Inc

Disclosed are systems and methods for receiving a plurality of comments at a particular phase of a transaction with a member of a networked system, classifying one or more of the plurality of comments into one of a set of predetermined sentiment classifications, applying a trained machine learning system to select a category from a set of predefined categories for each of the one or more comments, applying a natural language processing module to generate a sub-category for each of the one or more comments, associating the generated sub-categories with their respective categories for the one or more comments, and generating a display of the determined categories for the particular transaction with the generated sub-categories, each generated sub-category being graphically connected to their respective categories.

Подробнее
Номер записи: 82
05-03-2015 дата публикации

System and method for processing natural language

Номер: US20150066477A1
Автор: Shangfeng Hu
Принадлежит: Individual

A method for processing natural language includes generating a first layer of a multi-layer knowledge network including a plurality of word nodes arranged to represent a word or an entity name, generating a second layer of the multi-layer knowledge network with a natural language dataset, the second layer including one or more instance nodes arranged to represent a word or an entity of the natural language dataset, each of the instance nodes being linked by one or more semantic or syntactic relations to form one or more sub-graphs, and, referencing the first layer of the multi-layer knowledge network with the second layer of the multi-layer knowledge network by establishing a reference between each of the word nodes and each of the instance nodes when the word or the entity name represented by each word node is associated with the word or the entity represented by the instance node.

Подробнее
Номер записи: 83
05-03-2015 дата публикации

Sytem and method for use of semantic understanding in storage, searching, and providing of data or other content information

Номер: US20150066482A1
Автор: Gil Fuchs
Принадлежит: Individual

A system and method for using semantic understanding in storing and searching data and other information. A linearized tuple-based version of a conceptual graph can be created from a user input. A plurality of conceptual graphs, or portions thereof, can be compared to determine matches. An associative database can be created and/or searched using a hierarchy of conceptual graphs in tuple format, so that the data storage and searching of such database is optimized. The associative database can be used to integrate data from multiple different sources; form part of an Internet or other search engine; or used in other implementations. Also disclosed herein is a system and method for use of semantic understanding in searching and providing of content is described herein. In accordance with an embodiment, the system comprises a Syntactic Parser (SP) or statistical word tokenizer for data retrieval and parsing; a Syntax To Semantics (STS) transformational algebra-based semantic rule set, and an Associative Database (ADB) of linearized tuple conceptual graphs (TCG), utilizing a conceptual graph formalism. Data can be represented within the ADB, enabling both fast data retrieval in the form of semantic objects and a broad ranging taxonomy of content.

Подробнее
Номер записи: 84
17-03-2022 дата публикации

Methods and systems for assisting document editing

Номер: US20220083724A1
Автор: Yan Li
Принадлежит: Qixingtian Beijing Consulting Co Ltd

The present disclosure discloses a method of assisting document editing which is applied to a client. The method may include receiving and displaying a text structure of a second text obtained by a server based on a first text. The first text may include at least one discussion, each of the at least one discussion including at least one key point. The text structure of the second text may be a tree structure, and may include at least one structure node corresponding to the at least one discussion or the at least one key point. The second text may include at least one text unit corresponding to the at least one structure node, the at least one text unit being configured to illustrate the first text. The method may also include generating a request of acquiring a target text unit corresponding to the at least one structure node when the at least one structure node is detected to be triggered, and sending the request to the server; and receiving and displaying the target text unit obtained by the server.

Подробнее
Номер записи: 85
17-03-2022 дата публикации

GENERATING CONTROL COMMANDS FROM SCHEMATIZED RULE SETS

Номер: US20220083740A1
Автор: Goebel Matthias, von der Heyde Markus
Принадлежит:

A method for generating control commands includes providing a document that includes at least one declaration that formulates a rule set, parsing the at least one declaration to generate a plurality of syntactical blocks, constructing terms and symbols from the syntactical blocks to generate a semantic representation, validating the semantic representation, and generating at least one control command based on the validated semantic representation, wherein the at least one control command corresponds to the rule set formulated by the at least one declaration. The at least one control command can advantageously be converted into a plurality of platform-specific instructions for driving a target platform. There is further defined a device for generating control commands and a corresponding system. 1. A computer-implemented method for generating control commands , comprising:providing, to a processor or a processing unit of a computer, a document that includes at least one declaration that formulates a rule set; and parsing the at least one declaration to generate a plurality of syntactical blocks;', 'constructing terms and symbols from the syntactical blocks, to generate a semantic representation;', 'validating the semantic representation; and', 'generating at least one control command based on the validated semantic representation,, 'automatically, by the processor or processing unitwherein the at least one control command corresponds to the rule set formulated by the at least one declaration.2. The method according to claim 1 , wherein the at least one declaration includes a textual formulation of the rule set.3. The method according to claim 1 , wherein the at least one control command is a target-system-dependent control command.4. The method according to claim 1 , further comprising converting the at least one control command into a plurality of platform-specific instructions for driving a target platform.5. The method according to claim 4 , wherein the plurality ...

Подробнее
Номер записи: 86
17-03-2022 дата публикации

GENERATING WORD EMBEDDINGS WITH A WORD EMBEDDER AND A CHARACTER EMBEDDER NEURAL NETWORK MODELS

Номер: US20220083837A1
Автор: Hashimoto Kazuma, Socher Richard, Xiong Caiming
Принадлежит:

The technology disclosed provides a so-called “joint many-task neural network model” to solve a variety of increasingly complex natural language processing (NLP) tasks using growing depth of layers in a single end-to-end model. The model is successively trained by considering linguistic hierarchies, directly connecting word representations to all model layers, explicitly using predictions in lower tasks, and applying a so-called “successive regularization” technique to prevent catastrophic forgetting. Three examples of lower level model layers are part-of-speech (POS) tagging layer, chunking layer, and dependency parsing layer. Two examples of higher level model layers are semantic relatedness layer and textual entailment layer. The model achieves the state-of-the-art results on chunking, dependency parsing, semantic relatedness and textual entailment. 1. A method for encoding words , the method comprising:receiving, at a word embedder implemented on a processor and trained to create a word embedding space, input words;mapping, by the word embedder, a word from the input words into a word embedding space, to produce a word embedding vector;processing, by a character embedder implemented on the processor, character substrings of the word in the input words, the character substrings having multiple substring lengths;mapping, by the character embedder, the character substrings into corresponding intermediate vectors, the intermediate vectors representing positions of the character substrings in a character embedding space;identifying unique character substrings from the character substrings;combining, by the character embedder, intermediate vectors from the unique character substrings to produce a character embedding vector; andgenerating, using a word embedding processor, an embedding vector for the word by combining the word embedding vector and the character embedding vector, wherein the word that was previously mapped into the word embedding space is represented by ...

Подробнее
Номер записи: 87
28-02-2019 дата публикации

Non-transitory computer readable recording medium, specifying method, and information processing apparatus

Номер: US20190065466A1
Автор: Junya Hiramatsu, Masahiro Kataoka, Tomonori Ota, Toshiyuki Fujishima
Принадлежит: Fujitsu Ltd

An information processing apparatus accepts information corresponding to a text. The information processing apparatus refers to a storage unit that stores therein co-occurrence information on other texts with respect to the text and information corresponding to the other texts by associating both the information with the text. The information processing apparatus specifies, from among the pieces of information corresponding to the other texts, the text associated with the information corresponding to the other texts that is associated with the co-occurrence information that meets the standard.

Подробнее
Номер записи: 88
28-02-2019 дата публикации

Adaptive, interactive, and cognitive reasoner of an autonomous robotic system utilizing an advanced memory graph structure

Номер: US20190065625A1
Автор: Byoung-Kwon Lim, Cheongan Lee, Eunmi HONG, Hong Shik SHINN, Inhyuk Lee, Yeongju KIM
Принадлежит: Aibrain Corp

An autonomous robotic system using an adaptive, interactive, and cognitive reasoner utilizing an advanced memory graph structure receives a natural language input. The natural language input is processed to identify components. At least a portion of the components of the natural language input is stored in a short-term artificial intelligence memory graph data structure. A long-term artificial intelligence memory graph data structure includes data that was previously stored in the short-term artificial intelligence memory graph data structure but is no longer stored in the short-term artificial intelligence memory graph data structure.

Подробнее
Номер записи: 89
11-03-2021 дата публикации

Using Natural Language Expressions to Define Data Visualization Calculations that Span Across Multiple Rows of Data from a Database

Номер: US20210073279A1
Автор: Djalali Alex, Duan Suyang, Ericson Jeffrey, Leite Goldner Eliana, Setlur Vidya Raghavan
Принадлежит:

A method executes at a computing device that includes a display, one or more processors, and memory. The method includes receiving user input to specify a data source. The method includes receiving a first user input in a first region of a graphical user interface to specify a natural language command related to the data source. The device determines, based on the first user input, that the natural language command includes a table calculation expression. In accordance with the determination, the method identifies a second data field in the data source, Values of the first data field are aggregated for each of the time periods in a range of dates according to the second data field. A respective difference between the aggregated values for each consecutive pair of time periods is computed. A data visualization is generated and displayed. 1. A method of using natural language for visual analysis of datasets , comprising: receiving user input to specify a data source;', 'receiving a first user input in a first region of a graphical user interface to specify a natural language command related to the data source;', 'determining, based on the first user input, that the natural language command includes a table calculation expression, wherein the table calculation expression specifies a change in aggregated values of a first data field from the data source over consecutive time periods, and each of the time periods represents a same amount of time;', identifying a second data field in the data source, wherein the second data field is distinct from the first data field and the second data field spans a range of dates that includes the time periods;', 'aggregating values of the first data field for each of the time periods in the range of dates according to the second data field;', 'computing a respective difference between the aggregated values for each consecutive pair of time periods;', 'generating a data visualization that includes a plurality of data marks, each of the ...

Подробнее
Номер записи: 90
11-03-2021 дата публикации

SEMANTIC VECTOR RULE DISCOVERY

Номер: US20210073466A1
Автор: ROBERTS Gregory F., SORAH Michael Allen
Принадлежит:

Various data or document processing systems may benefit from an improved machine learning process for information extraction. For example, certain data or document processing systems may benefit from enhanced Semantic Vector Rules and a lexical knowledge base used to extract information from the text. A method may include analyzing a set of documents including a plurality of text. The method may also include extracting information from the plurality of text based on one or more semantic vector rules. In addition, the method may include updating the one or more semantic vector rules to include at least one new semantic vector rule based on a semantic rule state evaluation. 1. A method , comprising:analyzing a set of documents comprising a plurality of text;extracting information from the plurality of text based on one or more semantic vector rules; andupdating the one or more semantic vector rules to include at least one new semantic vector rule based on a semantic rule state evaluation.2. The method according to claim 1 , wherein the semantic rule state evaluation is based on shared context.3. The method according to or claim 1 , further comprising providing a report comprising the extracted information to a user claim 1 , wherein the report comprises at least one new semantic vector rule.4. The method according to claim 3 , further comprising displaying the report comprising the extracted information to the user.5. The method according to claim 4 , wherein the displaying of the report occurs after the analyzing of the plurality of text.6. The method according to any of - claim 4 , wherein the at least one new semantic vector rule is discovered by the user upon reviewing of the report or the plurality of the text.7. The method according to any one of - claim 4 , wherein the user uses a rule discovery tool to discover the at least one new semantic vector rule.8. The method according to claim 3 , wherein the report comprises a trace back illustrating the one or more ...

Подробнее
Номер записи: 91
11-03-2021 дата публикации

Natural language processing using hybrid document embedding

Номер: US20210073471A1
Автор: Shashi Kumar, Suman Roy, Vishal Pathak
Принадлежит: Optum Technology LLC

There is a need for more effective and efficient natural language processing. This need can be addressed by, for example, solutions for performing/executing natural language processing using hybrid document embedding. In one example, a method includes identifying a natural language document associated with one or more document attributes, wherein the natural language document comprises one or more natural language words; determining an attribute-based document embedding for the natural language document, wherein the attribute-based document embedding is generated based on a document vector for the natural language document and a word vector for each natural language word of the one or more natural language words; processing the attribute-based document embedding using a predictive inference model to determine one or more document-related predictions for the natural language document; and performing one or more prediction-based actions based on the one or more document-related predictions.

Подробнее
Номер записи: 92
07-03-2019 дата публикации

Turbine disk

Номер: US20190071969A1
Автор: Brian J. Burke, Fabian D. Betancourt, Jeffrey Leon, Kimberly Caruso, Kurt Leach, William Indoe
Принадлежит: United Technologies Corp

A turbine rotor for a gas turbine engine includes a disk rotationally disposed about a central axis. The disk includes an annular bore portion, an annular rim portion and an annular web portion disposed radially between the bore portion and the rim portion. The annular web portion includes an aft surface. A cylindrical arm is disposed on the aft surface and has a first portion extending axially from the aft surface and a second portion extending radially outward from a distal end of the first portion. The intersection of the first portion and the aft surface defines a fillet, radially inward of the first portion. The fillet is defined by a compound radius.

Подробнее
Номер записи: 93
15-03-2018 дата публикации

Information processing device, method and program

Номер: US20180075556A1
Автор: Masayuki SHOBAYASHI
Принадлежит: Individual

The purpose of the present invention is to achieve a suitable evaluation method for the quality of a patent publication such as a specification. In this information processing device, a claim term frequency distribution generation unit separates the content of the claims of a patent published in a patent publication into individual terms and generates a claim term frequency distribution indicating the frequency distribution of each separated term. A description term frequency distribution generation unit separates the content of the specification of the patent published in a patent publication into individual terms and generates a description term frequency distribution indicating the frequency distribution of each separated term. A description synonym frequency distribution generation unit classifies each term extracted from the specification into a plurality of groups respectively corresponding to the plurality of terms in the claims, and generates a description synonym frequency distribution indicating a frequency distribution in which each of the classified plurality of groups serves as a unit. An evaluation information generation unit generates evaluation information on the basis of the claim term frequency distribution and the description term synonym frequency distribution.

Подробнее
Номер записи: 94
16-03-2017 дата публикации

Model-based identification of relevant content

Номер: US20170075978A1
Автор: Chi-Yi Kuan, Yi Zheng, Yongzheng Zhang
Принадлежит: LinkedIn Corp

The disclosed embodiments provide a system for processing data. During operation, the system obtains validated training data containing a first set of content items and a first set of relevance tags, wherein the first set of relevance tags is used by one or more domain experts to identify the first set of content items as relevant to one or more topics. Next, the system uses the validated training data to produce a statistical model for classifying a relevance of content to the one or more topics. The system then uses the statistical model to generate a second set of relevance tags for a second set of content items. Finally, the system outputs one or more groupings of the second set of content items by the second set of relevance tags to improve understanding of content related to the one or more topics without requiring a user to manually analyze the second set of content items.

Подробнее
Номер записи: 95
24-03-2022 дата публикации

AUTOMATED MACHINE LEARNING TOOL FOR EXPLAINING THE EFFECTS OF COMPLEX TEXT ON PREDICTIVE RESULTS

Номер: US20220092452A1
Автор: "OConnell Michael", HSU Tun-Chieh, HUSSEINI Noora, PAOLINI Gaia Valeria, ROPE Daniel
Принадлежит:

An apparatus comprising feature engineering and text explanation modules for explaining text from predictive results of an algorithmic model. The feature engineering module creates vectors for string variables, each string variable comprising identified text, each vector created comprising a numeric combination, each numeric combination identifying a variable name and a value having a word or a phrase. The feature engineering module causes a predictive engine to generate predictive results using the algorithmic model, the data set, and the vectors created. The predictive results comprising the string variable or a modified version of the string variable and a confidence score. The text explanation module maps words and phrases from qualified text of the string variable, or modified version, to the numeric combinations of the vectors and determines a probability score for each word and each phrase. The most influential words and phrases are plotted on a chart. 1. An apparatus for explaining text from predictive results generated by at least one algorithmic model , the apparatus comprising: create a plurality of vectors for at least one string variable, with each string variable comprising identified text, each vector created comprising a numeric combination, each numeric combination identifying a variable name and at least one selected from a group comprising a value having a word and another value having a phrase; and', 'cause a predictive engine to generate predictive results using the at least one algorithmic model, the data set, and the vectors created, the predictive results comprising the at least one string variable or a modified version of the at least one string variable and at least one confidence score associated with the at least one string variable or the modified version of the at least one string variable;, 'a feature engineering module configured by a processor to map at least one selected from a group comprising words and at least one phrase from ...

Подробнее
Номер записи: 96
24-03-2022 дата публикации

Contextual sentence embeddings for natural language processing applications

Номер: US20220093088A1
Автор: Barada Prasanna Acharya, Douglas Ross Davidson, Vivek Kumar Rangarajan Sridhar, Xingwen XU
Принадлежит: Apple Inc

Methods and systems for embedding natural language sentences within a highly-dimensional vector space are provided. Additionally, various applications relating to natural language processing, are provided. Such applications include digital assistants and search engines, as well as systems for classifying, sorting, organizing, and/or pairing content that are associated with natural language objects. The sentence vector embeddings encode various semantic features of the sentence. Two separate language models, arranged in a serial architecture are employed to generate a sentence vector. The first language model generates token vectors for each of the tokens included in the sentence. The token vectors are employed as inputs to the second language model. The second language model generates the sentence vector for the sentence. A sentence vector embeds the semantic context of the corresponding natural language object within the vector space. The second language model may be trained via supervised learning on multiple semantic-related tasks.

Подробнее
Номер записи: 97
05-03-2020 дата публикации

Systems, devices, and methods for facilitating website remediation and promoting assistive technologies

Номер: US20200073921A1
Автор: Adam Finkelstein, Charlie E. Blevins, Damien M. Carrillo, David C. Pinckney, Douglas J. Gilormo, Helena Laymon, Jeffrey O. Jones, Kenny P. Hefner, Mark D. Baker, Sean D. Bradley, Taylor R. Bodnar, Trevor C. Jones
Принадлежит: AudioEye Inc

Systems and methods are disclosed for manually and programmatically remediating websites to thereby facilitate website navigation by people with diverse abilities. For example, an administrator portal is provided for simplified, form-based creation and deployment of remediation code, and a machine learning system is utilized to create and suggest remediations based on past remediation history. Voice command systems and portable document format (PDF) remediation techniques are also provided for improving the accessibility of such websites.

Подробнее
Номер записи: 98
18-03-2021 дата публикации

Web Experience Augmentation Based On Local And Global Content Preferences

Номер: US20210081467A1
Автор: Aarushi Agrawal, Aman Deep Singh, Kushal Chawla, Niyati Himanshu Chhaya, Soumya Vadlamannati
Принадлежит: Adobe Inc

A web experience augmentation system predicts, during a web browsing session of a user, augmentation data that the user is likely to want to view during the web browsing session. This prediction is based on both local content preferences for the user and global content preferences. The local content preferences for the user refer to an indication of the webpages accessed during the current web browsing session of the user. The global content preferences refer to analytics for webpages on a website obtained over an extended period of time that extends prior to the web browsing session of the user. The web experience augmentation system also modifies a webpage to which the user navigates to include the predicted augmentation data.

Подробнее
Номер записи: 99
18-03-2021 дата публикации

Tag assignment model generation apparatus, tag assignment apparatus, methods and programs therefor

Номер: US20210081597A1
Автор: Hiroaki Sugiyama, Hiromi NARIMATSU, Masahiro Mizukami
Принадлежит: Nippon Telegraph and Telephone Corp

Provided is a technique for generating a tagging model for attaching a tag in consideration of a phrase based on dependency between words. A tagging model generation apparatus includes a learning section 2 which generates, by using inputted learning data, a tagging model including probability-related information serving as information related to the probability that each tag is associated with each word-related information, and joint probability-related information serving as information related to a joint probability which serves as the probability of appearance of each tag in which appearance frequencies of a plurality of consecutive tags associated with pieces of word-related information of a plurality of consecutive words in each text are taken into consideration, and a storage section 3 which stores the generated tagging model.

Подробнее
Номер записи: 100