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 29197. Отображено 100.
05-01-2012 дата публикации

Method and system for scoring articles in an on-demand services environment

Номер: US20120005218A1
Автор: Vinodh Rajagopal
Принадлежит: Salesforce com Inc

A method for scoring and ranking knowledge articles in an on-demand service environment in a database network system. The scoring allows users to have input into the scoring to determine relevancy and authenticity to solve particular problems.

Подробнее
Номер записи: 1
19-01-2012 дата публикации

Intelligent Automated Assistant

Номер: US20120016678A1
Автор: Adam John Cheyer, Christopher Dean Brigham, Dag Kittlaus, Didier Rene Guzzoni, Harry Joseph Saddler, Marcello Bastea-Forte, Richard Donald Giuli, Thomas Robert Gruber
Принадлежит: Apple Inc

An intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions. The system can be implemented using any of a number of different platforms, such as the web, email, smartphone, and the like, or any combination thereof. In one embodiment, the system is based on sets of interrelated domains and tasks, and employs additional functionally powered by external services with which the system can interact.

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

Systems and Methods for Remote Deletion of Contact Information

Номер: US20120066177A1
Автор: Andre Okada, Chris Young, Paul Hanson, Scott Swanburg
Принадлежит: AT&T MOBILITY II LLC

An exemplary system for providing remote deletion of contact information includes a first device associated with a first user. The first device is configured to generate and send a delete request message to a second device. In some embodiments, the delete request message includes a request to delete contact information for the first user from the second device. The second device can be configured to receive the delete request message and delete the first user's contact information. A method for providing remote deletion of contact information includes a delete request message being generated at a first device, associated with a first user. The delete request message can include a request to delete contact information for the first user. The first device can send the delete request message to a second device. The delete request message can instruct the second device to delete the first user's contact information.

Подробнее
Номер записи: 3
19-04-2012 дата публикации

System and method for identifying a stored response to a subject query

Номер: US20120095999A1
Автор: Maxim Donde, Yoav Gelbfish
Принадлежит: Individual

A system and method of identifying stored responses that may be relevant to a subject query, by identifying relevant phrases in the query that express a topic of the query. A list of the relevant phrases is indexed, and a set of stored responses is reviewed to find a response that includes one or more of the relevant phrases. Relevant phrases may be ranked so that matches of particular phrases in a subject query and stored response may be given more weight in determining a relevance of a stored response. Stored responses may be ranked by the relevance of the terms that they include, where such terms are also relevant to the subject query.

Подробнее
Номер записи: 4
10-05-2012 дата публикации

System and method for providing distributed intelligent assistance

Номер: US20120117005A1
Автор: Nova T. Spivack
Принадлежит: Individual

A system and a method for a service engine providing distributed intelligent assistance to a user are described herein. The method comprising steps of receiving and displaying a user inquiry from the user, the user inquiry having a linguistic pattern including a verb; generating and displaying a follow up question based on the user inquiry; receiving and displaying a follow up answer from the user; and generating and displaying a response based on the user inquiry and the follow up answer.

Подробнее
Номер записи: 5
24-05-2012 дата публикации

Query suggestions from documents

Номер: US20120130978A1
Автор: Goang-Tay Hsu, Linda Lin Lin, Youlin Li
Принадлежит: Google LLC

Methods, systems, and apparatus, including computer program products, for presenting search query suggestions. In an aspect, query triggers in a resource are identified at a client device. For each query trigger identified in the resource, a rank score for the query trigger based on query trigger attributes is calculated at the client device. The query triggers are ranked at the client device based on the rank scores. Search query suggestions are generated at the client device from the query triggers identified in the resource. The search query suggestions include terms of the query triggers, expansion terms of the query triggers, and search query suggestions generated from templates applied to the terms of the query triggers and expansion terms of the query triggers. The search query suggestions are presented at the client device according to the rank of the corresponding query triggers.

Подробнее
Номер записи: 6
18-10-2012 дата публикации

Identifying query formulation suggestions for low-match queries

Номер: US20120265787A1
Автор: Bo-June Hsu, Chao-Chia Liu, Heung-Yeung Shum, Kuansan Wang, Yu-Ting Kuo
Принадлежит: Microsoft Corp

Systems, methods and computer-storage media are provided for identifying low-match search queries and determining comparable item matches to suggest to the user in response to a low-match query. “Low-match queries” are queries for which an insufficient number of exact item matches are available. In embodiments, exact and/or comparable item matches may be determined via semantic analysis. Also provided are systems, methods and computer-storage media for informing the user, by way of a presented indicator, or the like, that a presented item was selected for presentation based upon a similarity metric rather than being determined an exact match for the input query.

Подробнее
Номер записи: 7
22-11-2012 дата публикации

Method and system for quickly recognizing and responding to user intents and questions from natural language input using intelligent hierarchical processing and personalized adaptive semantic interface

Номер: US20120296638A1
Автор: Ashish Patwa
Принадлежит: Individual

In embodiments of the present invention, capabilities are described for understanding and responding to the user intent and questions quickly wherein the understanding is based on supervised system learning, Intelligent layered semantic and syntactic information processing and personalized adaptive semantic interface. Supervised system learning creates reference pattern set for the intent repository and possible question categories. Each layer in the layered processing increases the probability of the intent/question recognition. Personalized adaptive voice interface learns from user's interactions over time by enriching the pattern sets and personal index for successfully resolved user intents and questions. Collectively, all these technologies improve the response time for correctly recognizing and responding to user's intents and questions.

Подробнее
Номер записи: 8
27-12-2012 дата публикации

Using ontological information in open domain type coercion

Номер: US20120330921A1
Автор: Aditya A. Kalyanpur, Christopher A. Welty, David A. Ferrucci, James W. Murdock, IV, Wlodek W. Zadrozny
Принадлежит: International Business Machines Corp

A computer-implemented system, method and program product generates answers to questions in an input query text string. The method includes determining, by a programmed processor unit, a lexical answer type (LAT) string associated with an input query; automatically obtaining a candidate answer string to the input query from a data corpus; mapping the query LAT string to a first type string in a structured resource; mapping the candidate answer string to a second type string in the structured resource; and determining if the first type string and the second type string are disjointed; and scoring the candidate answer string based on the determination of the types being disjointed wherein the structured resource includes a semantic database providing ontological content.

Подробнее
Номер записи: 9
17-01-2013 дата публикации

Providing answers to questions using hypothesis pruning

Номер: US20130018876A1
Автор: Adam P. Lally, David A. Ferrucci, David C. Gondek, 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 a query, conducting a search through one or more data sources to identify candidate answers to the query, and providing each of the candidate answers with a preliminary score. The method further comprises filtering out any of the candidate answers with a preliminary score that does not satisfy a defined condition. The candidate answers having preliminary scores that satisfy this condition form a subset of the candidate answers. Each of the candidate answers in this subset is processed to produce further scores. A ranking function is applied to these further scores to determine a ranking for each of the candidate answers in the subset; and after this ranking function is applied, one or more of the candidate answers are selected as one or more final answers to the query.

Подробнее
Номер записи: 10
28-03-2013 дата публикации

Semantic questioning mechanism to enable analysis of information architectures

Номер: US20130080461A1
Автор: Brian P. Byrne, Sushain Pandit
Принадлежит: International Business Machines Corp

Methods, computer program products and systems are directed to receiving a query regarding an information architecture, selecting a set of nodes based on the query, from a plurality of nodes in a weighted linked graph, the weighted linked graph comprising the plurality of nodes and a plurality of pathways, each of the plurality of nodes comprising a source of information regarding the information architecture, each of the plurality of pathways connecting one of the plurality of nodes to another of the plurality of nodes, each of the plurality of pathways comprising a weight, determining a path from the plurality of pathways that passes through all of selected nodes, and presenting the path in response to the query.

Подробнее
Номер записи: 11
11-04-2013 дата публикации

System for organizing and fast searching of massive amounts of data

Номер: US20130091266A1
Автор: Ajit Bhave, Arun Ramachandran, Sai Krishnam Raju Nadimpalli, Sandeep Bele
Принадлежит: Ajit Bhave, Arun Ramachandran, Sai Krishnam Raju Nadimpalli, Sandeep Bele

A system to collect and analyze performance metric data recorded in time-series measurements, converted into unicode, and arranged into a special data structure. The performance metric data is collected by one or more probes running on machines about which data is being collected. The performance metric data is also organized into a special data structure. The data structure at the server where analysis is done has a directory for every day of performance metric data collected with a subdirectory for every resource type. Each subdirectory contain text files of performance metric data values measured for attributes in a group of attributes to which said text file is dedicated. Each attribute has its own section and the performance metric data values are recorded in time series as unicode hex numbers as a comma delimited list. Analysis of the performance metric data is done using regular expressions.

Подробнее
Номер записи: 12
09-05-2013 дата публикации

Personalized Vocabulary for Digital Assistant

Номер: US20130117022A1
Автор: Adam John Cheyer, Didier Rene Guzzoni, Lik Harry Chen, Thomas Robert Gruber
Принадлежит: Apple Inc

Methods, systems, and computer readable storage medium related to operating an intelligent digital assistant are disclosed. A text string is obtained from a speech input received from a user. The received text string is interpreted to derive a representation of user intent based at least in part on a plurality of words associated with a user and stored in memory associated with the user, the plurality of words including words from a plurality of user interactions with an automated assistant. At least one domain, a task, and at least one parameter for the task, are identified based at least in part on the representation of user intent. The identified task is performed. An output is provided to the user, where the output is related to the performance of the task.

Подробнее
Номер записи: 13
13-06-2013 дата публикации

Structured Questions in a Social Networking System

Номер: US20130151347A1
Автор: Adrian A. Graham, Drew W. Hamlin, Robert Michael Baldwin
Принадлежит: Individual

A social networking system includes a question and answer system that allows questions to be associated with social networking system objects. A question is received from a questioning user. A question term is identified, and an object associated with the question term is identified. The identified object is then associated with the question, and this association is stored. Question terms can be identified by the questioning user, or automatically, using contextual information. Question objects may also be identified by using template questions or sample questions provided by the social networking system. The stored association may be used to collection information about answering users, to auto-populate answers, and to generate social networking system stories. The stored association may also be used to collect information about the object of the stored association, to recommend an object to a user, to target advertising to users, and to recommend answers to users.

Подробнее
Номер записи: 14
18-07-2013 дата публикации

Converting data into natural language form

Номер: US20130185050A1
Автор: Doyle J. McCoy, John J. Bird
Принадлежит: International Business Machines Corp

Converting technical data from field oriented electronic data sources into natural language form is disclosed. An approach includes obtaining document data from an input document, wherein the document data is in a non-natural language form. The approach includes determining a data type of the document data from one of a plurality of data types defined in a detection and conversion database. The approach includes translating the document data to a natural language form based on the determined data type. The approach additionally includes outputting the translated document data in natural language form to an output data stream.

Подробнее
Номер записи: 15
15-08-2013 дата публикации

Apparatus and method for interpreting korean keyword search phrase

Номер: US20130211820A1
Автор: Joon Myun CHO, Moo Hun Lee
Принадлежит: Electronics and Telecommunications Research Institute ETRI

An apparatus and method for interpreting a Korean keyword search phrase is provided. The apparatus for interpreting the Korean keyword search phrase may include an interface to receive a search phrase and to extract keywords from the search phrase, and a processor to classify the extracted keywords into at least one of a class, an instance, a property, and an attribute, based on a Korean sentence structure, and to obtain semantic information associated with the search phrase from a database, based on a result of the classifying.

Подробнее
Номер записи: 16
22-08-2013 дата публикации

System and method for providing recommendations based on information extracted from reviewers' comments

Номер: US20130218914A1
Автор: Anna Stavrianou, Caroline Brun
Принадлежит: Xerox Corp

A recommendation method includes receiving a user's review of an item that includes a textual comment. Deficient features of the reviewed item are identified from the text by applying a set of extraction patterns. Each pattern is satisfied when a term in the text, which is associated in a structured terminology with one of a predefined set of features, is in a syntactic relation with another term in the text, such as a polar adjective or expression of a wish or a lack. When such a pattern is satisfied, the corresponding feature is considered a deficient feature. Feature attributes of the reviewed item are compared with corresponding feature attributes of a set of items to identify any improved items whose attribute for the deficient feature is better than that for the reviewed item. The improved item or items can be recommended to the user or to others reading the review.

Подробнее
Номер записи: 17
05-09-2013 дата публикации

Determination of a service description most closely matching a specified service name

Номер: US20130232141A1
Автор: Waseem A. Roshen
Принадлежит: International Business Machines Corp

A method and system for determining a service description that most closely matches a service name. A ranked service name list is generated by use of a name parser, a dictionary, and a name composer, wherein the ranked service name list comprises at least one alternative service name and a respective rank of each alternative service name of the at least one alternative service name, and wherein the respective rank indicates how closely the alternative service name associated with the respective rank resembles the service name provided by the user. It is ascertained that the service description matches the highest ranked alternative service name in the service name list. The service description matching the highest ranked alternative service name is communicated to the user.

Подробнее
Номер записи: 18
07-11-2013 дата публикации

Systems and methods for responding to natural language speech utterance

Номер: US20130297293A1
Автор: Lynn Elise Armstrong, Min Ke, Philippe Di Cristo, Robert A. Kennewick
Принадлежит: VoiceBox Technologies Corp

Systems and methods are provided for receiving speech and non-speech communications of natural language questions and/or commands, transcribing the speech and non-speech communications to textual messages, and executing the questions and/or commands. The invention applies context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users presenting questions or commands across multiple domains. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context of the speech and non-speech communications and presenting the expected results for a particular question or command.

Подробнее
Номер записи: 19
06-03-2014 дата публикации

Surfacing entity attributes with search results

Номер: US20140067816A1
Автор: Ashok Ponnuswami, Tapas Kanungo
Принадлежит: Microsoft Corp

In an effort to enhance computer user engagement with a search results page, systems and methods are presented which are configured to identify an entity as being the subject matter of a user's search query. If the entity is a known entity, i.e., entity information is stored in an entity store for the identified entity, a subset of entity attributes are identified and a representative entity attribute question is obtained for each of the attributes in the subset of entity attributes. The representative entity attribute questions are identified according to the probability that they are formed linguistically correct. The representative entity attribute questions are included in a search results page that is generated in response to the user's search query.

Подробнее
Номер записи: 20
06-03-2014 дата публикации

Establishing "is a" relationships for a taxonomy

Номер: US20140067832A1
Автор: Digvijay Singh Lamba, Xiaoyong Chai
Принадлежит: Wal Mart Stores Inc

Disclosed are methods for returning to a user an answer to the question “what is <string>.” Concepts and classes to which the concepts belong are determined from a corpus, such as taxonomy. The concepts are mapped to categories according to the structure of the taxonomy. Homonyms for words are collected and scored according to likeliness of use. Concept vectors are assembled for the identified concepts based on articles in the corpus and social media usage. Words are evaluated for generic-ness and a generic score is associated therewith. In responding to a query, the generic-ness of the terms of the query is evaluated and additional context solicited if the terms are generic. Candidate homonym concepts for a string in the query are selected according to context vectors for the homonym concepts. One or more homonym concepts are selected and the one or more categories corresponding to these concepts are returned.

Подробнее
Номер записи: 21
06-01-2022 дата публикации

Document search method, document search system, program, and non-transitory computer readable storage medium

Номер: US20220004570A1
Автор: Shoko SAITO, Tatsuya Okano
Принадлежит: Semiconductor Energy Laboratory Co Ltd

A similar document is retrieved in units of blocks of a document. Highly accurate document search is performed. A specific text block is searched for in a plurality of text blocks created by dividing each of a plurality of search target documents. A first search text block, which is a part of a search document, is prepared; full-text search is performed by using at least some of the plurality of text blocks as a first target and using the first search text block as a search criterion to calculate first relevance of each text block included in the first target to the first search text block; a second target is determined from the first target depending on a level of the first relevance; first similarities of each sentence included in the first search text block to sentences included in the second target are calculated; and at least one text block similar to the first search text block is retrieved using the first similarities.

Подробнее
Номер записи: 22
06-01-2022 дата публикации

Information processing apparatus, information processing method, and non-transitory storage medium

Номер: US20220005365A1
Автор: Daiki Yokoyama, Genshi Kuno, Shin Sakurada, Shuichi Sawada, Takaharu Ueno, Yurika Tanaka
Принадлежит: Toyota Motor Corp

There is provided a technology that can improve the convenience of users who are reading books. An information processing apparatus has a controller that determines a focus sentence in a subject book that a user is reading. The focus sentence is a sentence on which the user is focusing attention. The controller analyzes what the focus sentence describes and obtains related information relating to what the focus sentence describes. Moreover, the controller executes the processing for causing a user's terminal that the user is using to display the related information.

Подробнее
Номер записи: 23
06-01-2022 дата публикации

CROSS-CONTEXT NATURAL LANGUAGE MODEL GENERATION

Номер: US20220005463A1
Автор: Bender Walter, Fernández Musoles Carlos, Garay Maestre Unai, Tomkins Adam
Принадлежит:

Provided is a method including obtaining a corpus and an associated set of domain indicators. The method includes learning a set of vectors in an embedding space based on n-grams of the corpus. The method includes updating ontology graphs comprising a set of vertices and edges associating the set of vertices with each other. The method also includes determining a vector cluster using hierarchical clustering based on distances of the set of vectors with respect to each other in the embedding space and determining a hierarchy of the ontology graphs based on a set of domain indicators of a respective set of vertices corresponding to vectors of the vector cluster. The method also includes updating an index based on the ontology graphs. 1. A computer-implemented method of using domain-specific ontologies to of providing summaries of documents in a corpora of natural-language text documents , the method comprising:obtaining, with a computer system, a set of user-specific context parameters and a natural-language text document;determining, with the computer system, a first domain of knowledge based on the set of user-specific context parameters, wherein the first domain of knowledge maps to a first ontology amongst a plurality of ontologies, and wherein ontologies in the plurality of ontologies map n-grams onto a set of concepts to which the n-grams refer;scoring, with the computer system, a first set of n-grams of the natural-language text document using a scoring model based on relations between members of the first set of n-grams;selecting, with the computer system, text sections of the natural-language text based on n-gram scores provided by the scoring model;determining, with the computer system, an initial set of n-grams of the n-grams, wherein each respective n-gram of the initial set of n-grams maps to a respective concept of the set of concepts, and wherein each respective n-gram is identified by an ontology other than the first ontology;determining, with the ...

Подробнее
Номер записи: 24
05-01-2017 дата публикации

Monitoring a Corpus for Changes to Previously Provided Answers to Questions

Номер: US20170004204A1
Автор: Aaron M. Cohen, Paul R. Bastide
Принадлежит: International Business Machines Corp

Mechanisms are provided for identifying changes, within a corpus of information, to answers to questions provided within the corpus of information. A mapping of a question and a previously provided answer to the question in a question/answer data structure is generated. A transaction referencing the previously provided answer, and having an update to the previously provided answer, is received and correlated with the question/answer data structure, which is updated based on the transaction. A determination is made as to whether the strength of the mapping of the first question to the previously provided answer based on the update to the question/answer data structure has fallen equal to or below a predetermined threshold. In response to this being the case, a change to the previously provided answer is propagated throughout the corpus of information.

Подробнее
Номер записи: 25
02-01-2020 дата публикации

METHOD FOR PROCESSING LANGUAGE INFORMATION AND ELECTRONIC DEVICE THEREFOR

Номер: US20200004768A1
Автор: BEKSA Katarzyna, BUJNOWSKI Pawel, JEON Hee Sik, MARHULA Joanna Ewa, WISNIEWSKI Dawid, ZEMBRZUSKI Maciej
Принадлежит:

The disclosure relates to an artificial intelligence (AI) system for simulating human brain functions such as perception and judgement by using a machine learning algorithm such as deep learning, and an application thereof. An operation method of an electronic device comprises the steps of: receiving an input message; determining a user's language information included in the input message; determining language information for a response corresponding to the user's language information; and outputting the response on the basis of the language information for the response. 1. A method for operating an electronic device , the method comprising:receiving an input message;determining language information of a user included in the input message;determining language information for a response corresponding to the language information of the user; andoutputting the response, based on the language information for the response.2. The method of claim 1 , wherein determining the language information for the response corresponding to the language information of the user comprises:determining a value indicating a language proficiency of the user, based on the language information of the user; anddetermining the language information for the response corresponding to the value indicating the language proficiency of the user.3. The method of claim 2 , wherein the determining the value indicating the language proficiency of the user claim 2 , based on the language information of the user claim 2 , comprises determining the value indicating the language proficiency of the user according to a number of words included in the language information of the user.4. The method of claim 2 , wherein the outputting the response claim 2 , based on the language information for the response claim 2 , comprises:outputting a response comprised of photographs if the value indicating the language proficiency of the user is a first value; andoutputting a response comprised of moving pictures if the ...

Подробнее
Номер записи: 26
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: 27
07-01-2021 дата публикации

SYSTEMS AND METHODS TO EXTRACT THE CONTEXT OF SCIENTIFIC MEASUREMENTS USING TARGETED QUESTION ANSWERING

Номер: US20210004540A1
Автор: Cox Jessica Rose, Daniel, Harper Corey A., JR. Ronald E., Scerri Antony Jason
Принадлежит: Elsevier, Inc

A method for performing a search for a result set of documents comprises receiving, at a computing device, an electronic document, identifying a numerical value in the document, extracting the numerical value and a portion of text surrounding the numerical value from the document to obtain extracted text, creating a vector representation of the extracted text, generating a series of questions associated with the extracted text, generating answers to the series of questions based on the vector representation of the extracted text, determining a context associated with the numerical value based on the answers to the plurality of questions, and storing the numerical value and the context associated with the numerical value in a database. 1. A method comprising:receiving, at a computing device, an electronic document;identifying a numerical value in the document;extracting the numerical value and a portion of text surrounding the numerical value from the document to obtain extracted text;creating a vector representation of the extracted text;generating a series of questions associated with the extracted text;generating answers to the series of questions based on the vector representation of the extracted text;determining a context associated with the numerical value based on the answers to the series of questions; andstoring the numerical value and the context associated with the numerical value in a database.2. The method of claim 1 , wherein the numerical value is associated with a scientific measurement.3. The method of claim 2 , wherein the context associated with the scientific measurement comprises a property of an entity that was measured claim 2 , the entity whose property was measured claim 2 , and conditions under which the scientific measurement was taken.4. The method of claim 3 , further comprising:storing the numerical value and the context associated with the numerical value in a data structure comprising a quantity to hold the numerical value, a measured ...

Подробнее
Номер записи: 28
13-01-2022 дата публикации

Dialog interaction method, graphical user interface, terminal device, and network device

Номер: US20220012432A1
Автор: Li Qian, Xiao Chen
Принадлежит: Huawei Technologies Co Ltd

This application relates to the field of artificial intelligence. A dialog interaction method, a graphical user interface, a terminal device, and a network device are provided in this application. The disclosed terminal device displays a dialog view in a first region of a target dialog user interface, and displays a conceptual view in a second region of the target dialog user interface. The dialog view is used to display dialog data of the target dialog. The conceptual view is used to display a knowledge subgraph corresponding to the target dialog. The knowledge subgraph includes a plurality of semantic entities and a semantic relationship between semantic entities in the plurality of semantic entities. The plurality of semantic entities include a first semantic entity. The first semantic entity is a semantic entity existing in the dialog data. The technical solution can improve dialog interaction experience of a user.

Подробнее
Номер записи: 29
07-01-2021 дата публикации

System and method for generating information for interaction with a user

Номер: US20210004702A1
Автор: Jonghyun Kim, Miyoung Kim, Musik Kwon
Принадлежит: SAMSUNG ELECTRONICS CO LTD

A method for generating, by a first interactive electronic device of a first user, information for interaction with the first user includes: receiving, from a second interactive electronic device, information about an interaction between a second user and the second interactive electronic device; and generating interactive information to be provided to the first user, by applying the interactive information provided from the second interactive electronic device to a first AI learning model. At least a part of the method for generating interactive information may use a rule-based model, or an AI model trained according to at least one of a machine learning algorithm, a neural network algorithm, and a deep learning algorithm.

Подробнее
Номер записи: 30
20-01-2022 дата публикации

DETECTION OF MISSION CHANGE IN CONVERSATION

Номер: US20220020375A1
Автор: Colagiovanni Lawrence William, Hewavitharana Sanjika, Kale Ajinkya Gorakhnath, Khuc Vinh, Schoenmackers Stefan, Srivastava Amit
Принадлежит:

Methods, systems, and computer programs are presented for detecting a mission changes in a conversation. A user utterance from a user device is received. The user utterance is part of a conversation with an intelligent assistant. The conversation includes preceding user utterances in pursuit of a first mission. It is determined that the user utterance indicates a mission change from the first mission to a second mission based on an application of a machine-learned model to the user utterance and the preceding user utterances. The machine-learned model has been trained repeatedly with past utterances of other users over a time period, the determining based on a certainty of the indication satisfying a certainty threshold. Responsive to the determining that the user utterance indicates the mission change from the first mission to a second mission, a reply to the user utterance is generated to further the second mission rather than the first mission. 1. A computer-implemented method comprising:receiving, from a user device, user input as part of a conversation with an intelligent assistant, the conversation corresponding to a first product search mission for a product of a network-based marketplace;determining, by one or more hardware processors, that the user input contains information related to continuing the first product search mission instead of changing to a second product search mission based at least in part on the user input and a context of the conversation; andgenerating a reply to the user input to further the first product search mission based at least in part on the user input and the context.2. The method of claim 1 , further comprising:identifying a plurality of preceding user inputs included in the conversation corresponding to the first product search mission for the product of the network-based marketplace, wherein determining that the user input contains information related to continuing the first product search mission is based at least in part on ...

Подробнее
Номер записи: 31
27-01-2022 дата публикации

CLUSTER BASED SEARCH AND RECOMMENDATION METHOD TO RAPIDLY ON-BOARD COMMANDS IN PERSONAL ASSISTANTS

Номер: US20220027398A1
Автор: Dobrynin Vladimir, PATTERSON David, Rooney Niall
Принадлежит:

The present invention provides assistance to a user that is on-boarding an action for a virtual assistant. Methods and systems provide, based on an initial command group, recommendations for additional commands, actions, and applications that are relevant to commands included in the initial command group. The initial command group includes commands that include a sequence of natural language words or tokens. Additional commands are determined. The additional commands are relevant to the initial commands and provided to the user as recommended commands to include in the command group. The additional commands are determined by employing the initial commands as search queries to search preprocessed document clusters. Each document included in the document clusters relates to a potential command to include in the command group. In response to receiving a selection of a recommended command, the command group is updated to include the selected recommended command. 120-. (canceled)21. A non-transitory computer storage medium storing computer-usable instructions that , when used by at least one processor , cause the at least one processor to perform operations , comprising:obtaining a command set associated with an action, each command of the command set being recognizable by a digital assistant to execute the action;generating a search query based on the command set;searching a language model utilizing the search query;identifying a ranked set of additional commands that are each relevant to the command set based on the search, wherein each additional command of the ranked set of additional commands is unrecognizable by the digital assistant; andgenerating an association between a first ranked command of the ranked set of additional commands and the action such that the digital assistant can recognize the first ranked command to execute the action.22. The medium of claim 21 , wherein the first ranked command is recognized within a speech command.23. The medium of claim 21 ...

Подробнее
Номер записи: 32
14-01-2021 дата публикации

KNOWLEDGE-BASED INFORMATION RETRIEVAL SYSTEM EVALUATION

Номер: US20210011933A1
Автор: Akkiraju Rama Kalyani T., Guo Yufan, Liu Zhe, Mahmud Jalal, Yin Peifeng
Принадлежит:

Embodiments provide a computer implemented method of evaluating one or more IR systems, the method including: providing, by a processor, a pre-indexed knowledge-based document to a pre-trained sentence identification model; identifying, by the sentence identification model, a predetermined number of query-worthy sentences from the pre-indexed knowledge-based document, wherein the query-worthy sentences are ranked based on a prediction probability value of each query-worthy sentence; providing, by the sentence identification model, the query-worthy sentences to a pre-trained query generation model; generating, by the query generation model, a query for each query-worthy sentence; and evaluating, by the processor, the one or more IR systems using the generated queries, wherein one or more searches are performed via the one or more IR systems, and the one or more searches are performed in a set of knowledge-based documents including the pre-indexed knowledge-based document. 1. A computer implemented method in a data processing system comprising a processor and a memory comprising instructions , which are executed by the processor to cause the processor to implement the method of evaluating one or more IR systems , the method comprising:providing, by the processor, a pre-indexed knowledge-based document to a pre-trained sentence identification model;identifying, by the sentence identification model, a predetermined number of query-worthy sentences from the pre-indexed knowledge-based document, wherein the query-worthy sentences are ranked based on a prediction probability value of each query-worthy sentence;providing, by the sentence identification model, the query-worthy sentences to a pre-trained query generation model;generating, by the query generation model, a query for each query-worthy sentence; andevaluating, by the processor, the one or more IR systems using the generated queries, wherein one or more searches are performed via the one or more IR systems, and ...

Подробнее
Номер записи: 33
14-01-2021 дата публикации

EFFICIENT CORPUS SEARCH AND ANNOTATION MANAGEMENT FOR A QUESTION ANSWERING SYSTEM

Номер: US20210011934A1
Автор: BOXWELL STEPHEN A., BRAKE KYLE M., FROST KEITH G., VERNIER STANLEY J.
Принадлежит:

A computer converts a question received in a natural language format into a string of text elements. The computer searches a corpus comprising unstructured passages with the string of the text elements as search terms to identify a selection of unstructured passages from the corpus relevant to the text elements. The computer annotates the selection of relevant unstructured passages with one or more annotations according to at least one natural language annotation type to generate an annotated selection knowledge base. The computer modifies the string of text elements by annotating at least one of the text elements according to the at least one natural language annotation type. The computer searches the annotated selection knowledge base using the modified string of text elements to generate a selection of ranked passages. The computer identifies an answer to the question based on the selection of ranked passages. 1. A method comprising:converting, by a computing device, a question received in a natural language format into a string of a plurality of text elements;searching, by the computing device, a corpus comprising a plurality of unstructured passages with the string of the plurality of text elements as search terms to identify a selection of unstructured passages from the corpus relevant to the plurality of text elements;annotating, by the computing device, the selection of relevant unstructured passages with one or more annotations according to at least one natural language annotation type to generate an annotated selection knowledge base;modifying, by the computing device, the string of the plurality of text elements by annotating at least one text element within the plurality of text elements according to the at least one natural language annotation type;searching, by the computing device, the annotated selection knowledge base using the modified string of the plurality of text elements to generate a selection of ranked passages; andidentifying, by the ...

Подробнее
Номер записи: 34
14-01-2021 дата публикации

SELECTIVELY GENERATING WORD VECTOR AND PARAGRAPH VECTOR REPRESENTATIONS OF FIELDS FOR MACHINE LEARNING

Номер: US20210011936A1
Автор: Ganapathy ChitraBharathi, Govindarajan Kannan, Jayaraman Baskar, Ramanna Shiva Shankar, Thakur Aniruddha Madhusudan
Принадлежит:

Word vectors are multi-dimensional vectors that represent words in a corpus of text and that are embedded in a semantically-encoded vector space; paragraph vectors extend word vectors to represent, in the same semantically-encoded space, the overall semantic content and context of a phrase, sentence, paragraph, or other multi-word sample of text. Word and paragraph vectors can be used for sentiment analysis, comparison of the topic or content of samples of text, or other natural language processing tasks. However, the generation of word and paragraph vectors can be computationally expensive. Accordingly, word and paragraph vectors can be determined only for user-specified subsets of fields of incident reports in a database. 1. A system , comprising:a processor; and receiving an incident report comprising a plurality of input fields associated with an information technology (IT) issue;', 'identifying a first subset of input fields of the plurality of input fields;', 'identifying a second subset of input fields of the plurality of input fields;', 'generating a word vector representation of the first subset of input fields using a trained artificial neural network (ANN);', 'generating a paragraph vector representation of the second subset of input fields using the trained ANN;', 'generating an aggregate vector representation of the incident report by combining the word vector representation and the paragraph vector representation;', 'comparing the aggregate vector representation of the incident report with a plurality of additional aggregate vector representations for a plurality of additional incident reports relating to a managed network, wherein the plurality of additional aggregate vector representations are stored in a database;', 'identifying one or more similar aggregate vector representations of the plurality of additional aggregate vector representations based on the comparison; and', 'returning one or more incident reports of the plurality of additional ...

Подробнее
Номер записи: 35
14-01-2021 дата публикации

Expanding knowledge graphs using external data source

Номер: US20210012218A1
Автор: Kyle Croutwater, Le Zhang, Vikrant Verma, Zhe Zhang
Принадлежит: International Business Machines Corp

An approach is provided that selects an original entity from an original knowledge graph. The approach then accesses a data source that is external to the original knowledge graph, such as an online encyclopedia. An entity in the data source is identified based on the entity matching the original entity. A new relation is then identified in the data source between the identified entity and a new entity with the new entity being absent from the original knowledge graph. An expanded knowledge graph is then generated with the expanded knowledge graph formed by adding the new entity to the original knowledge graph.

Подробнее
Номер записи: 36
14-01-2021 дата публикации

Customer service assistance system and customer service assistance method

Номер: US20210012352A1
Автор: Takashi Yamagishi
Принадлежит: HITACHI LTD

A customer service assistance system includes: storage device that stores an address of an automated response device accumulating knowledge of a provided business in the output screen; and an arithmetic device that, when an inquiry specifying the address is received from a customer terminal, checks identification information of the output screen and an inquiry sentence indicated by the inquiry against questions-and-answers information held for each output screen of the provided business in the automated response device associated with the address, estimates a question matching an intention of the inquiry out of questions in the questions-and-answers information according to whether a screen associated with each question included in the questions-and-answers information matches the output screen and a degree of similarity between a sentence of each question included in the questions-and-answers information and the inquiry sentence, and extracts an answer to the question, and returns the answer to the customer terminal.

Подробнее
Номер записи: 37
09-01-2020 дата публикации

Context-based autocompletion suggestion

Номер: US20200012718A1
Автор: Cheng-Lun Yang, Chih-Hsiung Liu, Joanne Kuei-Chen HO, Norman Kung
Принадлежит: International Business Machines Corp

A process for context-based autocompletion suggestion includes, based on initiating an online chat by a user of a computer system, the chat having as participants the user and a target participant, providing participant information that identifies the participants. The process maintains at the computer system a relation-based autocompletion model for use in word autocompletion suggesting. The maintained relation-based autocompletion model is initially a template model based on to relationship between chat participants, and is updated over time via training. The process suggests to the user words for autocompletion in the user's composition of chat messages, the suggested words being selected as suggestions based on the maintained relation-based autocompletion model. Maintaining the relation-based autocompletion model includes sending chat messages as training data to further train the autocompletion model.

Подробнее
Номер записи: 38
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: 39
03-02-2022 дата публикации

Apparatuses, Methods and Computer Programs for a User Device and for a Server

Номер: US20220035596A1
Автор: HU Wangsu, TCHOI Won, Tian Jilei, WERNER Marko
Принадлежит:

Examples relate to apparatuses, methods and computer programs for a user device and for a server, e.g. to provide a personalized service enabled by converting human language to processing logic. An apparatus for a user device comprises processing circuitry configured to obtain a user command from the user via a user interface of the user device, the user command being obtained in natural language. The processing circuitry is configured to provide the user command in natural language to the server via an interface. The processing circuitry is configured to obtain a response to the user command from the server via the interface, the response to the user command comprising an identifier that is assigned to the user command by the server. The processing circuitry is configured to assign the user command to an element of a graphical user interface of an application being executed by the user device, and to link the identifier to the element of the graphical user interface. For example, the element of the graphical user interface may be linked with processing logic generated by the server, which may be executed by the server (e.g. on data that is available on the server) or by the user device itself (e.g. on data available at the user device, or using data from a third-party service). 1. An apparatus for a user device , the apparatus comprising processing circuitry configured to:obtain a user command from a user via a user interface of the user device, the user command being obtained in natural language;provide the user command in natural language to the server via an interface;obtain a response to the user command from the server via the interface, the response to the user command comprising an identifier that is assigned to the user command by the server; andassign the user command to an element of a graphical user interface of an application being executed by the user device, and to link the identifier to the element of the graphical user interface.2. The apparatus ...

Подробнее
Номер записи: 40
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: 41
03-02-2022 дата публикации

Computer-readable recording medium storing response processing program, response processing method, and information processing apparatus

Номер: US20220035849A1
Автор: Masaki Ohashi, Shinichi Kawakami
Принадлежит: Fujitsu Ltd

A non-transitory computer-readable recording medium stores a response processing program for causing a computer to execute processing including: receiving a question from a user input to a terminal; extracting, in a case where a plurality of pieces of answer candidate data that corresponds to the received question is retrieved, keywords or key phrases from the plurality of pieces of answer candidate data; classifying the extracted keywords or key phrases on the basis of words included in the keywords or key phrases; and outputting a classification result of the keywords or key phrases to the terminal in a state selectable by a user, together with a response text to the question.

Подробнее
Номер записи: 42
15-01-2015 дата публикации

Systems and methods for responding to natural language speech utterance

Номер: US20150019217A1
Автор: Lynn Elise Armstrong, Min Ke, Philippe Di Cristo, Robert A. Kennewick
Принадлежит: VoiceBox Technologies Corp

Systems and methods are provided for receiving speech and non-speech communications of natural language questions and/or commands, transcribing the speech and non-speech communications to textual messages, and executing the questions and/or commands. The invention applies context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users presenting questions or commands across multiple domains. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context of the speech and non-speech communications and presenting the expected results for a particular question or command.

Подробнее
Номер записи: 43
21-01-2016 дата публикации

Identifying question answerers in a question asking system

Номер: US20160019280A1
Автор: Alexander Ketner Unger, Frances Bordwell Haugen
Принадлежит: Google LLC

Methods and systems are provided for a question answering. In some implementations, a question is received from a question asker. A complexity metric associated with the question is determined. One or more potential question answerers to answer the question are identified. For each of the one or more potential question answerers, a sophistication metric is determined. At least the sophistication metric and the complexity metric are analyzed to generate a metric analysis. A question answerer to answer the question is selected from the potential question answerers based at least in part on the metric analysis.

Подробнее
Номер записи: 44
21-01-2016 дата публикации

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

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

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

Подробнее
Номер записи: 45
03-02-2022 дата публикации

Multi-modal conversational agent platform

Номер: US20220036899A1
Автор: Evgeny Stepanov, Giuliano Tortoreto, Giuseppe Di Fabbrizio, Mehool Patel, Phil C. Frank
Принадлежит: Vui Inc

A method includes receiving data characterizing an utterance of a query associated with a tenant; providing, to an automated speech recognition engine, the received data and a profile selected from a plurality of profiles based on the tenant, the profile configuring the automated speech recognition engine to process the received data; receiving, from the automated speech recognition engine, a text string characterizing the query; and processing, via an ensemble of natural language agents configured based on the tenant, the text string characterizing the query to determine a textual response to the query, the textual response including at least one word from a first lexicon associated with the tenant. Related systems, methods, apparatus, and computer readable mediums are also described.

Подробнее
Номер записи: 46
17-01-2019 дата публикации

Electronic content insertion systems and methods

Номер: US20190018827A1
Автор: Alexander Friedrich Kuscher, Jennifer Chen, Trond Thomas Wuellner, Zachary Daniel ALCORN
Принадлежит: Google LLC

Aspects of the subject technology relate to systems and methods for instant insert of external content into a content-editor application. An assistant application is provided, separate from the content-editor application, that can identify, obtain, and insert the external content into the content-editor application. The assistant application can identify the external content responsive to a user request while the user is inputting or editing content in the content-editor application and/or the assistant can provide predictive options for insertion of content based on the already input content by the user. As one example, the assistant can insert a photo related to text the user has recently typed into the content-editor application. The assistant may obtain the photo from a public source such a public web server or from a local database for the user.

Подробнее
Номер записи: 47
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: 48
21-01-2021 дата публикации

MACHINE LEARNING CLASSIFIER FOR CONTENT ANALYSIS

Номер: US20210019339A1
Автор: GHULATI Dhruv, SHUKLA Rishabh, WASEEM Zeerak
Принадлежит:

The present invention relates to a series of methods and systems in respect of online media content. More specifically, the present invention relates to aspects of fact checking of online media content. 188.-. (canceled)89. A method comprising:receiving an input content item, the input content item including a set of words;generating, using natural language processing, a set of answers to a set of content questions based on the set of words included in the input content item, the set of answers indicating sentiment of the input content item;determining, based on the set of answers, a confidence score indicating a confidence level that the input content items includes contentions content;comparing the confidence score to a threshold confidence score; andin response to determining that the confidence score meets or exceeds the threshold confidence score, labeling the input content item as contentions content, yielding a labeled content item.90. The method of claim 89 , further comprising:receiving a second input content item including a second set of words;generating, using natural language processing, a second set of answers to the set of content questions based on the second set of words included in the second input content item, the second set of answers indicating sentiment of the second input content item;determining, based on the second set of answers, a second confidence score indicating a confidence level that the second input content items includes contentions content;comparing the second confidence score to the threshold confidence score; andin response to determining that the second confidence score is less than the threshold confidence score, assigning the second input content item to an annotator for review.91. The method of claim 90 , further comprising:receiving, from the annotator, data indicating that the second input content item does not include contentious content; andlabeling the second input content item as not being contentions content, yielding ...

Подробнее
Номер записи: 49
21-01-2021 дата публикации

Method and device for processing untagged data, and storage medium

Номер: US20210019372A1
Автор: Xiaotong PAN, Zuopeng LIU
Принадлежит: Beijing Xiaomi Intelligent Technology Co Ltd

A method for processing untagged data includes: similarity comparison is performed on a semantic vector of untagged data and a semantic vector of each piece of tagged data to obtain similarities corresponding to respective pieces of tagged data; a preset number of similarities are selected according to a preset selection rule; the untagged data is predicted with a tagging model obtained by training through the tagged data, to obtain a prediction result of the untagged data; and the untagged data is divided into untagged data that can be tagged by a device or untagged data that cannot be tagged by the device according to the preset number of similarities and the prediction result.

Подробнее
Номер записи: 50
16-01-2020 дата публикации

Communication Methods and Apparatuses

Номер: US20200021542A1
Автор: He Weinan, Pan Yongqiang, Zhang Daping, ZHANG Di, Zhang Lili, Zhao Jianjun
Принадлежит:

Communication methods and apparatuses are provided. A method may include: obtaining at least a part of a communication message in a communication session page of a communication application, the communication session page being used for conducting communications between an end user and at least one peer user; performing content recognition of the communication message; and configuring a to-be-sent message corresponding to a message sending control in the communication session page, so that the to-be-sent message matches a content recognition result for the communication message. Using the technical solutions of the present disclosure, the efficiency of communications can be improved. 1. A method implemented by a computing device , the method comprising:obtaining at least a part of a communication message in a communication session page of a communication application;performing content recognition of the communication message; andconfiguring a to-be-sent message for a message sending control in the communication session page, wherein the to-be-sent message matches a content recognition result for the communication message.2. The method of claim 1 , wherein the message sending control comprises a quick sending control in the communication session page claim 1 , and the to-be-sent message is sent to at least one peer user when the quick sending control is triggered.3. The method of claim 1 , wherein:performing the content recognition of the communication message comprises identifying a described topic of the communication message; andconfiguring the to-be-sent message for the message sending control in the communication session page comprises selecting a to-be-sent message matching the described topic, and associating the selected to-be-sent message to the message sending control.4. The method of claim 1 , wherein:performing the content recognition of the communication message comprises identifying a sender of the communication message as a separate notification object ...

Подробнее
Номер записи: 51
22-01-2015 дата публикации

Correlating Corpus/Corpora Value from Answered Questions

Номер: US20150026163A1
Автор: Dane A. Johnson, Peter F. Haggar, Richard L. Stillwell, Stephan J. Roorda
Принадлежит: International Business Machines Corp

Mechanisms are provided for dynamically selecting a subset of candidate answer sources for use by a question and answer (QA) system. The QA system receives an input question for which an answer is sought and generates one or more queries based on the input question. The QA system selects a subset of candidate answer sources, from a group of candidate answer sources, based on a ranked listing of candidate answer sources. The ranked listing of candidate answer sources is generated based on characteristics of previous candidate answers generated by the QA system for previously input questions. The QA system applies the one or more queries to the subset of candidate answer sources and generates at least one candidate answer for the input question based on results of applying the one or more queries to the subset of candidate answer sources.

Подробнее
Номер записи: 52
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: 53
10-02-2022 дата публикации

TEMPLATE-BASED AUTOMATIC SOFTWARE BUG QUESTION AND ANSWER METHOD

Номер: US20220043845A1
Автор: Li Bin, LU Jinting, Sun Xiaobing
Принадлежит: Yangzhou University

Disclosed is a template-based automatic question and answer method for software bug. An entity relationship triple is extracted from a bug corpus and a natural language pattern is acquired; an entity relationship in the triple is determined; a query template corresponding to the natural language pattern is acquired; an entity in a question q proposed by a user is replaced with an entity type to acquire a question q′; then, the entity type in q′ and an entity type in the natural language pattern are compared and searched for and a similarity is calculated; then, a SPARQL query pattern of the question q is acquired according to the similarity and the entity in the question q; and finally, the SPARQL query pattern of the question q is executed so as to acquire an answer to the question q. 1. A template-based automatic question and answer method for software bug , comprising:step 1: extracting, from a bug report, an entity relationship triple set E, and acquiring, according to the entity relationship triple set E, a natural language pattern set S, a supported instance set I and a predicate set R;step 2: determining, according to the natural language pattern set S acquired in step 1, an entity relationship in the entity relationship triple set E;step 3: acquiring, according to the natural language pattern set S and an entity relationship triple, a query template corresponding to each natural language pattern in the natural language pattern set S;step 4: identifying an entity in a question q proposed by a user, and replacing the entity in q with an entity type to obtain a question q′;step 5: acquiring, according to an entity type in the question q′ acquired in step 4 and an entity type in the natural language pattern set S acquired in step 1, candidate query patterns for the question q, and calculating a similarity between each candidate query pattern and the question q′;step 6: acquiring, in combination with a SPARQL query language and according to the query template ...

Подробнее
Номер записи: 54
10-02-2022 дата публикации

Conversational graph structures

Номер: US20220043973A1
Автор: Carlos Ruiz Moreno, Guillermo Infante, Sinuhé Arroyo
Принадлежит: Capricorn Holding Pte Ltd, Capricorn Holdings Pte Ltd

A system and method for executing a node within the conversation graph model by receiving from a client device, a user input, and executing a first software instruction in the node, based on the user input. A server may identify at least one token within the user input, and if it matches a conversation context data associated in a database with the at least one token: suspend execution of the first software instruction; identify an abstract node associated in the database with the conversation context data; identify a specialized node associated in the database with conversation context data and the abstract node; and execute a second software instruction within the specialized node.

Подробнее
Номер записи: 55
28-01-2021 дата публикации

SYSTEMS AND METHODS FOR IDENTIFYING DYNAMIC TYPES IN VOICE QUERIES

Номер: US20210026878A1
Автор: Malhotra Manik, Robert Jose Jeffry Copps
Принадлежит:

The system receives a voice query at an audio interface and converts the voice query to text. The system identifies entities included in the query based on comparison to an information graph, as well as dynamic types based on the structure and format of the query. The system can determine dynamic types by analyzing parts of speech, articles, parts of speech combinations, parts of speech order, influential features, and comparisons of these aspects to references. The system combines tags associated with the identified entities and tags associated with the dynamic types to generate query interpretations. The system compares the interpretations to reference templates, and selects among the query interpretations using predetermined criteria. A search query is generated based on the selected interpretation. The system retrieves content or associated identifiers, updates metadata, updates reference information, or a combination thereof. Accordingly, the system responds to queries that include non-static types. 2. The method of claim 1 , wherein identifying the content based on the resultant tags comprises:generating a query interpretation based on the resultant tags;generating one or more comparison metrics based on comparing the query interpretation to one or more reference templates; andselecting a reference template from the one or more reference templates based on the one or more comparison metrics.3. The method of claim 2 , further comprising generating a tag associated with the reference template that is selected claim 2 , wherein the tag is indicative of the query interpretation.4. The method of claim 1 , further comprising:generating a tag based on the resultant tags and on the content, wherein the tag is indicative of a dynamic categorization of the one or more dynamic categorizations most closely associated with the content; andstoring the tag in memory.5. The method of claim 1 , wherein identifying the one or more dynamic categorizations comprises:identifying a ...

Подробнее
Номер записи: 56
24-01-2019 дата публикации

System and method for integrated virtual assistant-enhanced customer service

Номер: US20190028587A1
Автор: Ashley Unitt, Brian R. Galvin
Принадлежит: NewVoiceMedia Ltd

A system for integrated virtual assistant and contact center end-to-end functionality, which allows users to use their personal virtual assistant (such as SIRI, Amazon Alexa, Google Assistant, Cortana, and others) to extend functionality and communicate with other VA's and with contact centers through an interface, for services and functionality to be improved and automated.

Подробнее
Номер записи: 57
29-01-2015 дата публикации

System and method for auto-suggesting responses based on social conversational contents in customer care services

Номер: US20150032724A1
Автор: Arun Bakthavachalu, David R. Vandervort, Tong Sun, Veerasundaravel THIRUGNANASUNDARAM
Принадлежит: Xerox Corp

A first embodiment of the disclosure relates to a method for responding to a message posted in a social media stream. The method includes monitoring a social media site for at least one message including select subject matter. In response to identifying a message, the method includes collecting a series of exchanges that form a conversational thread including the message. The method includes determining at least one content attribute of the message. The method includes classifying the message using at least one key attribute. The method includes searching a database for a reference message using a combination of the at least one content and key attributes. The method includes determining a previous outcome of a reference thread including the reference message. The method includes using the previous outcome for determining a course of action.

Подробнее
Номер записи: 58
17-02-2022 дата публикации

Auto-completion for Gesture-input in Assistant Systems

Номер: US20220050696A1
Автор: Kumar Anuj, Penov Francislav P., Presant William Crosby
Принадлежит:

In one embodiment, a method includes receiving an initial input in a first modality from a first user from a client system associated with the first user, determining one or more intents corresponding to the initial input by an intent-understanding module, generating one or more candidate continuation-inputs based on the one or more intents, where the one or more candidate continuation-inputs are in one or more candidate modalities, respectively, and wherein the candidate modalities are different from the first modality, and sending instructions for presenting one or more suggested inputs corresponding to one or more of the candidate continuation-inputs to the client system. 1. A method comprising , by one or more computing systems:receiving, from a client system associated with a first user, an initial input from the first user, wherein the initial input is in a first modality;determining, by an intent-understanding module, one or more intents corresponding to the initial input;generating, based on the one or more intents, one or more candidate continuation-inputs, where the one or more candidate continuation-inputs are in one or more candidate modalities, respectively, and wherein the candidate modalities are different from the first modality; andsending, to the client system, instructions for presenting one or more suggested inputs corresponding to one or more of the candidate continuation-inputs.2. The method of claim 1 , wherein the first modality comprises one of audio claim 1 , text claim 1 , image claim 1 , video claim 1 , motion claim 1 , or orientation.3. The method of claim 2 , wherein the first modality comprises motion claim 2 , and wherein the initial input comprises a gesture.4. The method of claim 2 , wherein the first modality comprises orientation claim 2 , and wherein the initial input comprises a gaze on an object.5. The method of claim 1 , further comprising:determining that the first user needs one or more suggested inputs.6. The method of ...

Подробнее
Номер записи: 59
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: 60
17-02-2022 дата публикации

HYBRID APPROACH TO APPROXIMATE STRING MATCHING USING MACHINE LEARNING

Номер: US20220050879A1
Автор: Banerjee Soumyajyoti, Singh Pranjal
Принадлежит:

Systems, apparatuses, and methods are provided for identifying a corresponding string stored in memory based on an incomplete input string. A system can analyze and produce phonetic and distance metrics for a plurality of strings stored in memory by comparing the plurality of strings to an incomplete input string. These similarity metrics can be used as the input to a machine learning model, which can quickly and accurately provide a classification. This classification can be used to identify a string stored in memory that corresponds to the incomplete input string. 1. A method comprising performing , by a computer system:retrieving, in response to receiving a search query including an incomplete input string, a plurality of stored strings from a database; comparing the incomplete input string to the stored string to determine a plurality of similarity metrics that measure a difference between the incomplete input string and the stored string, the plurality of similarity metrics including at least one distance metric measuring a difference between characters in the incomplete input string and the stored string and at least one phonetic metric measuring a difference in phonemes between the incomplete input string and the stored string; and', 'providing the plurality of similarity metrics as input features to a machine learning model to obtain a similarity score including a probability that the stored string matches the incomplete input string; and, 'performing a first filtering comprising, for each stored string of the plurality of stored stringsreturning a first stored string as a response to the search query, the first stored string corresponding to a highest similarity score of a plurality of similarity scores obtained during the first filtering.2. The method of claim 1 , wherein the search query further comprises location information that identifies a geographical region corresponding to the incomplete input string claim 1 , the method further comprising ...

Подробнее
Номер записи: 61
17-02-2022 дата публикации

CONTROLLING CONVERSATIONAL DIGITAL ASSISTANT INTERACTIVITY

Номер: US20220051072A1
Автор: JESWANI Sapna Daryanomal, NANDI Ajoy
Принадлежит: Microsoft Technology Licensing, LLC

Interaction between a user and a conversational digital assistant executing on a computing device is controlled. Multiple interaction pairs are stored in one or more datastores accessible by the conversational digital assistant. Each interaction pair includes an interaction query and an associated assistance operation. An interactive engagement event is detected between the user and the conversational digital assistant, responsive to the storing operation. An interaction pair is selected from the one or more datastores, responsive to the operation of detecting an interactive engagement event. The interaction query of the selected interaction pair is communicated to the user. The assistance operation associated with the communicated interaction query is executed, responsive to receipt of a response from the user to the interaction query. 120.-. (canceled)21. A system comprising:a processor; and detecting an interactive engagement event between a user and a conversational digital assistant executing on a computing device;', 'in response to detecting the interactive engagement event, selecting an interaction pair from one or more datastores accessible by the conversational digital assistant, wherein the interaction pair includes an interaction query and an assistance operation associated with the interaction query;', 'causing the interaction query to be provided to the user by the conversational digital assistant; and', 'based on a response by the user to the interaction query, executing the assistance operation, wherein executing the assistance operation exposes new or undiscovered functionality of the conversational digital assistant to the user., 'memory coupled to the processor, the memory comprising computer executable instructions that, when executed by the processor, perform a method comprising22. The system of claim 21 , wherein the computer executable instructions perform the method further comprising:monitoring, by the conversational digital assistant, one or ...

Подробнее
Номер записи: 62
17-02-2022 дата публикации

CLAIM ANALYSIS BASED ON CANDIDATE FUNCTIONS

Номер: US20220051164A1
Автор: Devore Justin, Dickerson Jeremy David, King Garren, Marsh Matthew
Принадлежит:

Candidate function data can include data for multiple candidate functions that may indicate whether insurance claims are likely to involve certain issues, such as comparative negligence issues. A real-time claim identifier can use the candidate function data to determine, in near real-time, if claim data for a new insurance claim submitted to an insurance company satisfies at least one of the candidate functions. If the claim data satisfies at least one of the candidate functions, the insurance claim can be assigned to a corresponding destination in the insurance company, such as a department that processes comparative negligence claims, for further processing. 1. A method , comprising:obtaining, by a claim identification system, claim data associated with an insurance claim; a plurality of string sets associated with the particular candidate function; and', 'at least one logical operator that relates two or more of the plurality of string sets;, 'identifying, by the claim identification system, candidate function data associated with one or more candidate functions, wherein the one or more candidate functions are associated with a particular destination for the insurance claim, and the candidate function data for a particular candidate function includesdetermining, by the claim identification system, that the claim data satisfies at least one of the one or more candidate functions; andassigning, by the claim identification system, the insurance claim to the particular destination, in response to the claim data satisfying the at least one of the one or more candidate functions.2. The method of claim 1 , wherein the identifying claim 1 , the determining claim 1 , and the assigning are performed by a real-time claim identifier of the claim identification system.3. The method of claim 1 , wherein the candidate function data defines the one or more candidate functions based in part on a plurality of corresponding string sets generated by a batch claim identifier of the ...

Подробнее
Номер записи: 63
31-01-2019 дата публикации

Method for providing chatting service with chatbot assisted by human counselor

Номер: US20190034522A1
Автор: Bong Won NAH, Byung Jae Park, Chang Pil KIM, Jean Su BYUN, Ji Hun Kim, Jin Soo Lee, Jin Woon KIM, Joo Hee AHN, Joon Won Lee, Keum Sik IM, Seul Gi Kang, Young Min Park
Принадлежит: Samsung SDS Co Ltd

Provided is a method of providing an unmanned dialogue service according to an embodiment of the inventive concept. The method includes transmitting or receiving text message data constituting a dialogue to or from a user terminal in an unmanned dialogue model, analyzing the dialogue to determine whether a counselor switching situation has occurred, transmitting a dialogue handover request including information regarding the dialogue to a counselor management apparatus when it is determined that the counselor switching situation has occurred, and automatically switching into a mode for relaying transmission or reception of messages between the user terminal and a counselor terminal that receives a task for processing the dialogue handover request allocated by the counselor management apparatus.

Подробнее
Номер записи: 64
30-01-2020 дата публикации

USING USER INPUT TO ADAPT SEARCH RESULTS PROVIDED FOR PRESENTATION TO THE USER

Номер: US20200034116A1
Автор: Horling Bryan, Kogan David
Принадлежит:

Methods, apparatus, and computer readable media related to interaction between a user and an automated assistant during a dialog between the user and the automated assistant. Some implementations are directed to adapting a graphical and/or audible presentation of search results provided by the automated assistant for presentation to the user. The adaptation may be in response to attribute(s), of one or more of the search results, referenced in spoken and/or typed textual input provided by the user during the dialog. Some of those implementations may enable a user to provide textual input to navigate the search results within the dialog and within resource and/or interface constraints associated with the dialog. Some of those implementations may additionally and/or alternatively enable adapting, based on textual input provided by a user to the automated assistant, when and/or whether search results having certain attributes are provided to the user by the automated assistant. 1. A method implemented by one or more processors , comprising: receiving a spoken input of the user;', 'obtaining a search result that is responsive to the spoken input;', 'providing the search result for presentation to the user;', 'in response to providing the search result, receiving further spoken input of the user;', an attribute of the search result, and', 'a sentiment expressed by the user towards the attribute;, 'determining, based on processing the further spoken input, that the further spoken input references, 'determining, based on the attribute and the sentiment expressed by the user towards that attribute, whether or when to provide, as part of the dialog, an additional search result that is also responsive to the spoken input and that also has the attribute.', 'in response to determining that the further spoken input references the attribute of the search result and the sentiment expressed by the user towards the attribute], 'as part of a dialog between a user and an automated ...

Подробнее
Номер записи: 65
30-01-2020 дата публикации

DIALOG SYSTEM FOR TRANSITIONING BETWEEN STATE DIAGRAMS

Номер: US20200034360A1
Автор: Clark Mitchell, Hsu Kevin, Khaitan Priyanka, Wei Haichao
Принадлежит:

Systems and methods are provided for receiving and processing a query to determine an intent of the query, and analyzing the intent of the query to determine that the intent of the query is associated with a use case state diagram. Systems and methods further provide for traversing a plurality of nodes in the user case state diagram to generate a value for each relevant node, performing an operation associated with the query using the generated values, and providing the results of the operation to a computing device. 1. A method comprising:determining, by a server computer, that an intent of a first query received from a user via a computing device is associated with a first use case state diagram of a plurality of predetermined use case state diagrams, wherein the first use case state diagram comprises a plurality of nodes to traverse to satisfy a query;traversing the first use case state diagram by generating and storing a value for each node traversed in the first use case state diagram based on available data or data requested from the computing device;during traversal of the first use case state diagram, receiving response data in response to data requested from the computing device;determining that the response data is a second query with an intent associated with a second use case state diagram of the plurality of predetermined use case state diagrams;traversing the second use case state diagram to provide a response to the second query;receiving a third query from the computing device;processing the third query to determine an intent of the third query;determining that the intent of the third query is associated with the first use case state diagram, wherein generated values for a plurality of nodes of the first use case state diagram continue to persist in memory;determining a node where the user left off in the first use case diagram based on the generated values; andcontinuing traversing the first user case diagram from the node where the user left off in ...

Подробнее
Номер записи: 66
30-01-2020 дата публикации

ACTIVE LISTENING TO MANAGE ADAPTIVE CONTENT ITEMS

Номер: US20200034369A1
Автор: Bohannon John, Gourley Sean
Принадлежит:

Systems, methods, and software described herein provide improvements for dynamically modifying the presentation of content items to end users. In one example, a summary service determines first content items associated with an end user and determines a first sequence for the first content items. The summary service further monitors user interactions with one or more secondary services and determines content of interest for the end user based on the user interactions. As the content of interest is identified, the summary service determines second content items to be presented to the end user and determines a second sequence for the second content items based on the content of interest. 1. A method of managing content items for end users , the method comprisingdetermining first content items to be presented to an end user;determining a first sequence for the first content items;monitoring user interactions with one or more secondary services;determining content of interest for the end user based on the user interactions;determining second content items to be presented to the end user based on the content of interest; anddetermining a second sequence for the second content items based on the content of interest.2. The method of claim 1 , wherein the user interactions comprise voice and text communications using the one or more secondary services.3. The method of claim 1 , wherein the first content items comprise first summaries of a first plurality of events claim 1 , and wherein the second content items comprise second summaries of a second plurality of events.4. The method of claim 3 , wherein determining the first content items to be presented to the end user comprises:obtaining data objects from a plurality of data sources;generating the first summaries of the first plurality of events based at least on content of the data objects.5. The method of claim 4 , wherein generating the first summaries of the first plurality of events based at least on content of the data ...

Подробнее
Номер записи: 67
30-01-2020 дата публикации

RECOMMENDING DOCUMENTS SETS BASED ON A SIMILAR SET OF CORRELATED FEATURES

Номер: US20200034379A1
Автор: Kikuchi Hiroaki, Terui Fumihiko
Принадлежит:

A method for recommending a plurality of alternate search keywords is provided. The method may include executing a first search query using a plurality of user-entered search text. The method may also include identifying a highest contribution keyword to a plurality of search results of the executed first search query. The method may further include identifying a highest correlation alternate keyword to the identified highest contribution keyword. The method may also include creating an alternate keyword group by replacing the identified highest contribution keyword with the identified highest correlation alternate keyword. The method may further include executing a second search query using the created alternate keyword group. The method may also include displaying the plurality of search results associated with the executed first search query with a plurality of statistics associated with the executed second search query. 1. A processor-implemented method for improving data processing of a plurality of user-entered search text by recommending a plurality of alternate search keywords , the method comprising:executing, by a processor, a first search query using the plurality of user-entered search text;identifying a highest contribution keyword from the keyword group based on a plurality of search results of the executed first search query, wherein identifying the highest contribution keyword based on calculating a contribution value of each keyword from the executed first search query to a plurality of search results, wherein the contribution value is calculated using a number of total search result hits and a number of documents within the search results within which a particular keyword appears;identifying a highest correlation alternate keyword to the identified highest contribution keyword; andcreating an alternate keyword group from the keyword group by replacing the identified highest contribution keyword with the identified highest correlation alternate ...

Подробнее
Номер записи: 68
30-01-2020 дата публикации

NON-FACTOID QUESTION-ANSWERING SYSTEM AND METHOD AND COMPUTER PROGRAM THEREFOR

Номер: US20200034722A1
Автор: IIDA Ryu, KLOETZER Julien, KRUENGKRAI Canasai, OH Jonghoon, TORISAWA Kentaro
Принадлежит:

A question-answering system includes a storage unit storing expressions representing causality; an answer receiving unit receiving a question and answer passages each including an answer candidate to the question; a causality expression extracting unit extracting a causality expression from each of the answer passages; a relevant causality expression extracting unit selecting, for a combination of the question and an answer passage, an expression most relevant to the combination, from the storage unit; and a neural network receiving the question, the answer passages, semantic relation expressions related to the answer passages, and one of the relevant expressions for the combination of the question and the answer passages, and selecting an answer to the question from the answer passages. 1. A non-factoid question-answering system generating an answer to a non-factoid question by focusing on an expression representing a first semantic relation appearing in text , comprising:a first expression storage means for storing a plurality of expressions representing said first semantic relation;a question/answer receiving means for receiving a question and a plurality of answer passages including an answer candidate to the question;a first expression extracting means for extracting a semantic relation expression representing said first semantic relation from each of the plurality of answer passages;a relevant expression selecting means for selecting, for each of the combinations of said question and said plurality of answer passages, a relevant expression that is an expression most relevant to said combination, from said plurality of expressions stored in said first expression storage means; andan answer selecting means trained in advance by machine learning to receive, as inputs, each combination of said question, said plurality of answer passages, said semantic relation expressions for the answer passages, and one of said relevant expressions for a combination of said ...

Подробнее
Номер записи: 69
17-02-2022 дата публикации

Answer text processing methods and apparatuses, and key text determination methods

Номер: US20220052976A1
Автор: Hengbin CUI, Shuang PENG, Weifeng Lou, Yangyi Xie, Ze Zhan
Принадлежит: Alipay Hangzhou Information Technology Co Ltd

The present specification provides answer text processing methods and apparatuses and key text determination methods. In some embodiments, based on the previously described data processing methods, a piece of answer text that corresponds to a target question is determined from a predetermined knowledge base as a piece of target answer text at first; then one or more key texts that are closely associated with the target question and corresponds to a relatively high user attention measure is recognized and determined from the piece of target answer text, and the previously described key text in the piece of target answer text is labeled; and furthermore, the previously described key text can be identified in the piece of target answer text displayed to a user. Therefore, the user can read relatively valuable key information that the user needs in the piece of target answer text conveniently and efficiently.

Подробнее
Номер записи: 70
04-02-2021 дата публикации

Method and device for natural language processing and storage medium

Номер: US20210034966A1
Автор: Zhuang Qian
Принадлежит: Beijing Xiaomi Intelligent Technology Co Ltd

A method for natural language, includes: determining a slot tagging result output by a Bi-directional Long Short-Term Memory-Conditional Random Field algorithm (BiLSTM-CRF) model after slot tagging on conversation data input by a user; determining reward information based on the slot tagging result and a reward of the user for the slot tagging result; and performing reinforcement learning on the BiLSTM-CRF model according to the reward information.

Подробнее
Номер записи: 71
30-01-2020 дата публикации

PROVIDING NEW RECOMMENDATION IN AUTOMATED CHATTING

Номер: US20200036659A1
Автор: Wu Xianchao
Принадлежит:

The present disclosure provides method and apparatus for providing news recommendation in automated chatting. A first message may be obtained in a chat flow. Recommended news may be determined based at least on the first message, a user preference list including sentiment labels, and a news dataset including sentiment labels. At least one of title, summarization and content of the recommended news may be provided based on the first message. 1. A method for providing news recommendation in automated chatting , comprising:obtaining a first message in a chat flow;determining recommended news based at least on the first message, a user preference list including sentiment labels, and a news dataset including sentiment labels; andproviding at least one of title, summarization and content of the recommended news based on the first message.2. The method of claim 1 , whereinthe first message is expressed by natural language, and the first message and the at least one of title, summarization and content of the recommended news are in a form of text or voice.3. The method of claim 1 , further comprising:determining that the first message indicates an intention of obtaining news recommendation.4. The method of claim 1 , whereinthe user preference list comprises keywords and/or categories of news that a user is interested in, and sentiment labels of the keywords and/or categories, andthe news dataset comprises a plurality of candidate news items, each item corresponding to a piece of candidate news and including at least one of: title of the candidate news, summarization of the candidate news, content of the candidate news, comments to the candidate news, a sentiment label of the candidate news, and a sentiment label of the comments.5. The method of claim 1 , further comprising:obtaining a second message in the chat flow;determining that the second message includes sentimental comment to the recommended news; andupdating the user preference list based on the sentimental comment ...

Подробнее
Номер записи: 72
24-02-2022 дата публикации

SYSTEMS AND METHODS FOR IDENTIFYING DYNAMIC TYPES IN VOICE QUERIES

Номер: US20220058213A1
Автор: Malhotra Manik, Robert Jose Jeffry Copps
Принадлежит:

The system receives a voice query at an audio interface and converts the voice query to text. The system identifies entities included in the query based on comparison to an information graph, as well as dynamic types based on the structure and format of the query. The system can determine dynamic types by analyzing parts of speech, articles, parts of speech combinations, parts of speech order, influential features, and comparisons of these aspects to references. The system combines tags associated with the identified entities and tags associated with the dynamic types to generate query interpretations. The system compares the interpretations to reference templates, and selects among the query interpretations using predetermined criteria. A search query is generated based on the selected interpretation. The system retrieves content or associated identifiers, updates metadata, updates reference information, or a combination thereof. Accordingly, the system responds to queries that include non-static types. 150-. (canceled)51. A method for identifying content based on a query , the method comprising:receiving data that indicates a query;identifying, from one or more databases, keywords based on the data and the query;determining that a portion of the query cannot be categorized based on the keywords;identifying a dynamic categorization associated with the portion of the query by comparing at least one of words, phrases, or parts of speech of the query to tags associated with dynamic categorizations;generating search tags based on the keywords and the dynamic categorization;determining content items based on the search tags; andcausing to be outputted the content items.52. The method of claim 51 , wherein the keywords are stored in metadata from the one or more databases claim 51 , and wherein the dynamic categorization is not stored in the metadata.53. The method of claim 51 , wherein identifying the dynamic categorization comprises:determining, based on comparing the ...

Подробнее
Номер записи: 73
24-02-2022 дата публикации

SYSTEMS AND METHODS FOR UNIFIED EXTRACTION OF ATTRIBUTES

Номер: US20220058717A1
Автор: Bhattacharya Tuhin, Mondal Sakib Abdul
Принадлежит:

Systems and methods for unified attribute extraction are disclosed. A set of product data including at least one text-based description of each of the products in the set of products is received and at least one closed list attribute is extracted from the at least one text-based description of each of the products. The at least one closed list attribute is extracted by an attribute extraction model configured to implement an extended conditional random field (XCRF) process. A set of attributes including each of the at least one closed list attributes extracted from the at least one text-based description of each of the products in the set of products is output. 1. A system , comprising:a memory having instructions stored thereon and a processor configured to read the instructions to:receive a set of product data including at least one text-based description of each of the products in the set of products;extract at least one closed list attribute from the at least one text-based description of each of the products, wherein the at least one closed list attribute is extracted by an attribute extraction model configured to implement an extended conditional random field (XCRF) process; andoutput a set of attributes including each of the at least one closed list attributes extracted from the at least one text-based description of each of the products in the set of products.2. The system of claim 1 , wherein the attribute extraction model includes a set of hidden variables representative of one or more states associated with each of the at least one closed list attributes.3. The system of claim 1 , wherein the processor is configured to extract at least one open list attribute from the at least one text-based description of each of the products claim 1 , wherein the at least one open list attribute is extracted by the attributed extraction model using a conditional random field (CRF) process.5. The system of claim 1 , wherein the XCRF process is implemented using a limited ...

Подробнее
Номер записи: 74
24-02-2022 дата публикации

Electronic device and control method therefor

Номер: US20220059088A1
Автор: Hyonsok Lee, Jaehun Lee, Mirae Jeong, Taeho HWANG, Yunsu Lee
Принадлежит: SAMSUNG ELECTRONICS CO LTD

An electronic device is disclosed. The electronic device of the present disclosure comprises a microphone, a memory including at least one command, and a processor which is connected to the microphone and the memory and controls the electronic device, wherein the processor, by executing the at least one command extracts a keyword from a user voice received as an input when the user voice is input through the microphone, acquires context information at the time when the user voice is input, acquires an object related to the user voice and knowledge information relating to the object, on the basis of the extracted keyword and the context information, and updates a stored knowledge database on the basis of the knowledge information relating to the object. In particular, at least a part of a method for providing a response to a user query by an electronic device may use an artificial intelligence model learned in accordance with at least one of machine learning, a neural network, and a deep-learning algorithm.

Подробнее
Номер записи: 75
07-02-2019 дата публикации

System and method for querying questions and answers

Номер: US20190042572A1
Автор: Carlos Ruiz Moreno, Sinuhé Arroyo
Принадлежит: Capricorn Holdings Pte Ltd

A system and method for information retrieval are presented. A client computer receives a natural language query comprising an array of tokens. A query processing server analyzes the natural language query (interpreted as a question) to identify a plurality of terms and a relationship between one or more pairs of the terms according to a knowledge model defining interrelationships between a plurality of entities. A set of assertions is constructed using the relationship between the pair of terms, and a query is executed against a knowledge base of frequently asked questions, corresponding answers, documents and/or data using the set of assertions to generate a set of results. The knowledge base identifies a plurality of items, each of the plurality of items is associated with at least one annotation identifying at least one of the entities in the knowledge model. The set of results are transmitted to the client computer.

Подробнее
Номер записи: 76
07-02-2019 дата публикации

Capturing and managing knowledge from social networking interactions

Номер: US20190042658A1
Автор: David A. Brooks, Joseph A. Russo, Mustansir Banatwala
Принадлежит: International Business Machines Corp

Presenting a marking element in a social networking interaction where the marking element includes a question specifier and an answer specifier, creating a knowledge element in response to a user activating the marking element on the social networking interaction or a portion thereof, and presenting a knowledge element indicator in the social networking interaction.

Подробнее
Номер записи: 77
06-02-2020 дата публикации

APPLICATION INTEGRATION WITH A DIGITAL ASSISTANT

Номер: US20200042334A1
Автор: DASARI Rohit, KHOSLA Vineet, NEWENDORP Brandon J., PETERSON Corey J., RADEBAUGH Carey E., TRAN Trungtin
Принадлежит:

Systems and processes for application integration with a digital assistant are provided. In accordance with one example, a method includes receiving an audio input including a natural-language user input and identifying an intent object of a set of intent objects. The intent object may be derived from the natural-language user input. The method further includes identifying a software application associated with the intent object of the set of intent objects, providing the intent object to the software application to cause the software application to perform a task associated with the intent object, receiving a result response indicating whether the task was successfully performed, and providing an output indicating whether the task was performed. 1. A non-transitory computer-readable storage medium storing one or more programs , the one or more programs including instructions , which when executed by one or more processors of an electronic device having a display , cause the electronic device to:receive an audio input including a natural-language user input;identify an intent object of a set of intent objects, wherein the intent object is derived from the natural-language user input;identify a software application associated with the intent object of the set of intent objects;provide the intent object to the software application to cause the software application to perform a task associated with the intent object;receive; from the software application, a response indicating whether the task was successfully performed; andprovide an output indicating whether the task was performed.2. The non-transitory computer-readable storage medium of claim 1 , wherein:identifying a software application associated with the intent object of the set of intent objects comprises identifying a first parameter associated with the intent object, andproviding the intent object to the software application to cause the software application to perform a task associated with the intent object ...

Подробнее
Номер записи: 78
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: 79
06-02-2020 дата публикации

GENERATING QUESTION-ANSWER PAIRS FOR AUTOMATED CHATTING

Номер: US20200042597A1
Автор: Wu Xianchao
Принадлежит:

The present disclosure provides method and apparatus for generating question-answer (QA) pairs for automated chatting. A plain text may be obtained. A question may be determined based on the plain text through a deep learning model. A QA pair may be formed based on the question and the plain text. 1. A method for generating question-answer (QA) pairs for automated chatting , comprising:obtaining a plain text;determining a question based on the plain text through a deep learning model; andforming a QA pair based on the question and the plain text.2. The method of claim 1 , whereinthe deep learning model comprises a Learning-to-Rank (LTR) model, andthe LTR model is for computing a similarity score between the plain text and a reference QA pair through at least one of word matching and latent semantic matching.3. The method of claim 2 , wherein the similarity score is computed through:computing a first matching score between the plain text and a reference question in the reference QA pair,computing a second matching score between the plain text and a reference answer in the reference QA pair; andcombining the first matching score and the second matching score to obtain the similarity score.4. The method of claim 3 , wherein the first matching score and the second matching score are computed through Gradient Boosting Decision Tree (GBDT).5. The method of claim 1 , wherein the deep learning model comprises a Learning-to-Rank (LTR) model claim 1 , and the determining the question comprises:computing similarity scores of a plurality of reference QA pairs compared to the plain text through the LTR model; andselecting a reference question in an reference QA pair having the highest similarity score as the question.6. The method of claim 1 , whereinthe deep learning model comprises a Neutral Machine Translation (NMT) model, andthe NMT model is for generating the question based on the plain text in a sequence-to-sequence approach, the plain text being as an input sequence, the ...

Подробнее
Номер записи: 80
24-02-2022 дата публикации

Configuring a chatbot with remote language processing

Номер: US20220060435A1
Автор: Andrew Stephen Brown, Benjamin Abraham Russell BROWN, Christopher WHITTEN, Marieke Watson IWEMA, Sangwoo Han, Vishwac Sena Kannan, Yochay KIRIATY
Принадлежит: Microsoft Technology Licensing LLC

A chatbot designer user interface (UI) has a visual authoring canvas that shows visual elements indicative of a logical flow of processing in a chatbot application. The designer UI receives an authoring input identifying a language processing system that is to be used during runtime. The chatbot application is configured to use the identified language processing system.

Подробнее
Номер записи: 81
18-02-2021 дата публикации

DOMAIN ASSISTANT SYSTEM AND METHOD

Номер: US20210049194A1
Автор: Arcienega Mijail, Boudett Josselyn, Brown Stephen, Carta Elisabetta, Lefkowitz Lawrence Seth, Taneva Bilyana
Принадлежит:

A method, computer program product, and computer system identifying, by a computing device, an intent relating to a query associated with an object. A plurality of informational items associated with the object may be identified. At least a first informational item of the plurality of informational items associated with the object for which a first portion of information is already known may be identified. At least a second informational item of the plurality of informational items associated with the object for which a second portion of information is unknown may be identified. A question may be generated to determine the second portion of information based upon, at least in part, the second portion of information being unknown. An answer may be received for the question generated to determine the second portion of information. A response to the intent relating to the query may be provided based upon, at least in part, at least the first informational item for which the first portion of information is already known and the answer for the question generated to determine the second portion of information. 1. A computer-implemented method comprising:identifying, by a computing device, an intent relating to a query associated with an object;identifying a plurality of informational items associated with the object;identifying at least a first informational item of the plurality of informational items associated with the object for which a first portion of information is already known;identifying at least a second informational item of the plurality of informational items associated with the object for which a second portion of information is unknown;generating a question to determine the second portion of information based upon, at least in part, the second portion of information being unknown;receiving an answer for the question generated to determine the second portion of information; andproviding a response to the intent relating to the query based upon, at least in ...

Подробнее
Номер записи: 82
18-02-2021 дата публикации

Computer-readable recording medium recording answering program, answering method, and answering device

Номер: US20210049195A1
Автор: Miyuki Yamada, Shinichi Kawakami
Принадлежит: Fujitsu Ltd

A non-transitory computer-readable recording medium stores therein an answering program for causing a computer to execute a process including: receiving an inquiry from a terminal; referring to a memory that stores a content of an inquiry and an answer candidate for the inquiry in association with each other, and judging whether or not an answer candidate for the received inquiry is present; referring to a past inquiry history and determining information to be outputted to the terminal when it is judged that the answer candidate is absent; and outputting the determined information.

Подробнее
Номер записи: 83
24-02-2022 дата публикации

INTENT-DRIVEN CONTACT CENTER

Номер: US20220060580A1
Автор: Bradley Joe, Dunn Matthew, Onu Laura
Принадлежит: LIVEPERSON, INC.

The present disclosure relates generally to providing an intent-driven contact center. The contact center according to some embodiments analyzes intents to determine to which device or agent to route a communication. The analyzed intent information can also be used to formulate reports and analyze the accuracy of the identified intents with respect to the received communication. 1. (canceled)2. A computer-implemented method , comprising:routing a communication, wherein the communication is associated with a pre-defined intent that defines an action corresponding to a user device, and wherein when the communication is received at a terminal device associated with an agent, a communication session is established between the terminal device and the user device to facilitate execution of the action;generating a set of metrics during the communication session, wherein the set of metrics correspond to ongoing performance of the agent;generating an updated set of metrics, wherein the updated set of metrics are generated by aggregating the set of metrics with other metrics corresponding to previous communication sessions associated with the pre-defined intent, and wherein the set of metrics are aggregated with the other metrics as intents are ascertained from ongoing communications;determining a quality of an association between the communication and the pre-defined intent based on the updated set of metrics; andupdating a dashboard to provide the updated set of metrics and the determined quality of the association.3. The computer-implemented method of claim 2 , further comprising:aggregating the set of metrics corresponding to the performance of the agent with other metrics corresponding to previous communications associated with the agent to generate an aggregated set of metrics; andupdating the dashboard to present a ranking of the agent against a set of other agents, wherein the agent is ranked against the set of other agents based on the aggregated set of metrics and ...

Подробнее
Номер записи: 84
18-02-2021 дата публикации

Temporal context-aware representation learning for question routing

Номер: US20210049213A1
Автор: BO Zong, Haifeng Chen, Wei Cheng, Xuchao Zhang
Принадлежит: NEC Laboratories America Inc

A method for employing a temporal context-aware question routing model (TCQR) in multiple granularities of temporal dynamics in community-based question answering (CQA) systems is presented. The method includes encoding answerers into temporal context-aware representations based on semantic and temporal information of questions, measuring answerers expertise in one or more of the questions as a coherence between the temporal context-aware representations of the answerers and encodings of the questions, modeling the temporal dynamics of answering behaviors of the answerers in different levels of time granularities by using multi-shift and multi-resolution extensions, and outputting answers of select answerers to a visualization device.

Подробнее
Номер записи: 85
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: 86
06-02-2020 дата публикации

EXTRACTED CONCEPT NORMALIZATION USING EXTERNAL EVIDENCE

Номер: US20200043610A1
Автор: AL HASAN SHEIKH SADID, DATLA Vivek Varma, FARRI OLADIMEJI FEYISETAN, Ling Yuan
Принадлежит:

Various embodiments described herein relate to a method, system, and non-transitory machine-readable medium including one or more of the following: extracting a first concept from input data presented for processing by a downstream function; identifying external data from an external resource based on the first concept; extracting a second concept from the external data; revising the first concept based on the second concept to produce a revised concept, wherein revising includes: applying a machine learning agent to determine whether to keep the first concept or adopt the second concept, and adopting the second concept in place of the first concept for use as the revised concept based on a decision by the machine learning agent to adopt the second concept; and further processing the revised concept according to the downstream function to generate an output. 1. A method for normalizing input data against external data , the method comprising:extracting a first concept from input data presented for processing by a downstream function;identifying external data from an external resource based on the first concept;extracting a second concept from the external data; applying a machine learning agent to determine whether to keep the first concept or adopt the second concept, and', 'adopting the second concept in place of the first concept for use as the revised concept based on a decision by the machine learning agent to adopt the second concept; and, 'revising the first concept based on the second concept to produce a revised concept, wherein revising comprisesfurther processing the revised concept according to the downstream function to generate an output.2. The method of claim 1 , wherein the input data is free text and the first concept is at least one of a term and a phrase extracted from the free text.3. The method of claim 1 , wherein identifying external data from an external resource based on the first concept comprises executing a query comprising the first ...

Подробнее
Номер записи: 87
06-02-2020 дата публикации

VOICE FORWARDING IN AUTOMATED CHATTING

Номер: US20200044999A1
Автор: Ito Kazushige, Wu Xianchao
Принадлежит:

The present disclosure provides method and apparatus for voice forwarding in automated chatting. A first request for transmitting a voice segment may be received from a first entity in a service group. The voice segment may be received from the first entity. A voice message may be generated based on the voice segment. The voice message may be transmitted based on the first request. 1. A method for voice forwarding in automated chatting , comprising:receiving, from a first entity in a service group, a first request for transmitting a voice segment;receiving the voice segment from the first entity;generating a voice message based on the voice segment; andtransmitting the voice message based on the first request.2. The method of claim 1 , further comprising:determining at least one second entity in the service group based on the first request,wherein the transmitting the voice message comprises: transmitting the voice message to the at least one second entity.3. The method of claim 1 , further comprising:determining that the first request indicates transmitting the voice segment randomly; andreceiving, from a second entity in the service group, a second request for obtaining a randomly-transmitted voice message,wherein the transmitting the voice message comprises: transmitting the voice message to the second entity.4. The method of claim 1 , further comprising:determining that the first request indicates transmitting the voice segment in a way not denoting the first entity,wherein the transmitting the voice message comprises: transmitting the voice message in the way not denoting the first entity.5. The method of claim 1 , wherein the generating the voice message comprises:including the voice segment in the voice message.6. The method of claim 1 , wherein the generating the voice message comprises:detecting an indication of voice preference from the first request;converting the voice segment into a target voice segment based on the voice preference; andincluding the ...

Подробнее
Номер записи: 88
15-02-2018 дата публикации

Dynamic Voicemail Receptionist System

Номер: US20180048765A1
Автор: Andre Okada, Chris Young, Paul Hanson, Scott Swanburg
Принадлежит: AT&T MOBILITY II LLC

A voicemail receptionist system includes a memory and a processor. The memory can store data relating to one or more users. An incoming communication can be handled by the voicemail receptionist system and provided with functionality based upon a user's preferences, for example. The data stored by the voicemail receptionist system can be updated at any time, or automatically updated upon updating of the data, or upon occurrence of a trigger event. Voicemail receptionist functionality can include standard voicemail system functionality as well as functionality relating to email, text messaging, MMS messaging, calendar features, schedule announcements, location data, as well as other features.

Подробнее
Номер записи: 89
03-03-2022 дата публикации

TEXT PROCESSING APPARATUS AND METHOD

Номер: US20220067074A1
Автор: "ONEIL Alison", FALIS Matus
Принадлежит: Canon Medical Systems Corporation

An apparatus for medical text processing comprises processing circuitry configured to: obtain a trained model, wherein the trained model is trained to classify medical text documents with a medical classification code; apply the trained model to at least one medical text document to obtain weightings for text terms included in the at least one medical text document, wherein the weightings are associated with the medical classification code; and use the weightings to perform a searching or indexing process.

Подробнее
Номер записи: 90
03-03-2022 дата публикации

METHOD AND SYSTEM FOR RETRIEVAL OF PRIOR COURT CASES USING WITNESS TESTIMONIES

Номер: US20220067076A1
Автор: Bhattacharyya Pushpak, GHOSH Kripabandhu, KALIDINDI Vasudeva Varma, PALSHIKAR Girish Keshav, PAWAR Sachin Sharad
Принадлежит: TATA CONSULTANCY SERVICES LIMITED

This disclosure relates generally to retrieval of prior court cases using witness testimonies. Conventional state-of-the-art methods use supervised techniques for answering basic questions in legal domain using numerous features and do not address interpretability of results and the performance and precision of retrieving prior court cases for these methods are less. Embodiments of the present disclosure obtains an embedded representation for an event structure of a user query and testimony sentences identified from prior court cases using a trained Bi-LSTM classifier and a set of linguistic rules. A similarity is estimated between the embedded representation for the event structure of the user query and the event structure of each testimony sentence from the prior court cases. Further a relevance score is assigned in accordance with the estimated similarity to retrieve the relevant prior court cases. The disclosed method is used to retrieve the relevant prior court cases using witness testimonies. 2. The processor implemented method as claimed in claim 1 , wherein the trained classifier is trained using a set of training data claim 1 , wherein the set of training data comprises of (i) the set of testimony sentences satisfying a set of predefined linguistic rules claim 1 , (ii) the set of non-testimony sentences satisfying a subset of the set of predefined linguistic rules and (iii) a set of sentences which are neither identified as testimony nor non-testimony by the linguistic rules.3. The processor implemented method as claimed in further comprising training the denoising auto-encoder claim 1 , the training comprising:(i) encoding the event structure by masking either the predicate or one or more arguments of the event structure of each of the one or more testimony sentences;(ii) reconstructing the embedded representation of the encoded event structure of each of the one or more testimony sentences; and(iii) storing the embedded representation of each of the one ...

Подробнее
Номер записи: 91
03-03-2022 дата публикации

CONVERSATIONAL SYNTAX USING CONSTRAINED NATURAL LANGUAGE PROCESSING FOR ACCESSING DATASETS

Номер: US20220067303A1
Автор: Bacon Dylan Paul, Chen Junda, Leo John Rogers Jeffrey, Li Jiatong, Patel Jignesh, Ramesh Ushmal
Принадлежит:

In general, techniques are described for various aspects of accessing datasets. A device comprising a memory configured to store the dataset, and a processor may be configured to perform the techniques. The processor may expose a language sub-surface specifying a natural language containment hierarchy defining a grammar for a natural language as a hierarchical arrangement of a plurality of language sub-surfaces. The processor may receive a query to access the dataset, the query conforming to a portion of the natural language provided by the exposed language sub-surface. The processor may transform the query into one or more statements that conform to a formal syntax associated with the dataset, access, based on the one or more statements, the dataset to obtain a query result, and output the query result.

Подробнее
Номер записи: 92
03-03-2022 дата публикации

METHOD AND DEVICE FOR GENERATING COLLECTION OF INCORRECTLY-ANSWERED QUESTIONS

Номер: US20220067416A1
Автор: CHEN Mingquan, HE Tao, LUO Huan, MAO Lihui
Принадлежит: Hangzhou Dana Technology Inc.

A method and a device for generating a collection of incorrectly-answered questions are provided. The method includes: acquiring an image of a marked test paper (S); recognizing regions of respective questions in the marked test paper according to a pre-trained first region recognition model (S); recognizing a question whose marking result is incorrect in the marked test paper as an incorrectly-answered question according to a pre-trained incorrectly-answered question recognition model (S); and storing the region of the incorrectly-answered question in an incorrectly-answered question database to generate the collection of incorrectly-answered questions (S). The above solution may solve the problem of low efficiency in generating the collection of incorrectly-answered questions in the prior art.

Подробнее
Номер записи: 93
14-02-2019 дата публикации

Tools and techniques for extracting knowledge from unstructured data retrieved from personal data sources

Номер: US20190050433A1
Автор: Corey Hulen, Kenneth C. Nitz, Madhu Yarlagadda, Rajan Singh, Thierry Donneau-Golencer, William Scott Mark
Принадлежит: Salesforce com Inc

A system may include multiple personal data sources and a machine-implemented data extractor and correlator configured to retrieve personal data from at least one of the personal data sources. The data extractor and correlator may extract information from unstructured data within the retrieved personal data and correlate the extracted information with previously stored structured data to generate additional structured data. The system may also include a storage device configured to store the previously stored structured data and the additional structured data. A natural language query module may be configured to receive a natural language query from a user and provide a response to the natural language query based at least in part on one or both of the previously stored structured data and the additional structured data.

Подробнее
Номер записи: 94
25-02-2021 дата публикации

UTILIZING REGULAR EXPRESSION EMBEDDINGS FOR NAMED ENTITY RECOGNITION SYSTEMS

Номер: US20210056099A1
Автор: Farivar Reza, GOODSITT Jeremy Edward, PHAM Vincent, RAFFERTY Galen, Truong Anh, WALTERS Austin Grant, WATSON Mark Louis
Принадлежит: Capital One Services, LLC

Various embodiments are directed to a system that utilizes regular expression (regex) to recognize at least portions of characters, words, text, numbers, etc. in a structured or unstructured dataset, any patterns associated therewith, and/or similarities between the determined patterns. In examples, a regex-based pattern recognition platform may receive a dataset and determine whether at least a first regex pattern and a second regex pattern can be identified. The occurrences of the first and second regex patterns and the frequency of those occurrences may reveal something about the dataset itself or any patterns contained therein. 1. A method comprising:determining, via one or more processors, whether a dataset contains a first regex pattern of a regex list;determining, via the one or more processors, a number of occurrences of the first regex pattern in the dataset;generating, via the one or more processors, a vector, the vector specifying a vector position and a regex value for at least the first regex pattern;incrementing, via the one or more processors, the regex value corresponding to the first regex pattern by a predefined value for each occurrence of the first regex pattern in the dataset;determining, via the one or more processors, any false matches between the first regex pattern of the regex list and the dataset;refining, based on any determined false matches, the regex list via a machine learning model or a classification model; andproviding, via the one or more processors, the vector to at least one entity recognition system.2. The method of claim 1 , further comprising:determining, via the one or more processors, whether the dataset contains a second regex pattern of the regex list;determining, via the one or more processors, a number of occurrences of the second regex pattern in the dataset; andincrementing, via the one or more processors, a regex value corresponding to the second regex pattern by the predefined value for each occurrence of the second ...

Подробнее
Номер записи: 95
25-02-2021 дата публикации

LIMITING A DICTIONARY USED BY A NATURAL LANGUAGE MODEL TO SUMMARIZE A DOCUMENT

Номер: US20210056170A1
Автор: Bohannon John, Grek Thomas Alexander, Vasilyev Oleg
Принадлежит:

The technology disclosed herein summarizes a document using a dictionary derived from tokens within the document itself. In a particular implementation, a method provides identifying a first document for summarization and inputting the first document into a natural language model. The natural language model is configured to summarize the first document using words from a first dictionary compiled based on tokens from the first document. The method further provides receiving a first summary output by the natural language model after the natural language model summarizes the first document. 1. A method for summarizing documents , the method comprising:identifying a first document for summarization;inputting the first document into a natural language model, wherein the natural language model is configured to summarize the first document using words from a first dictionary compiled based on tokens from the first document; andreceiving a first summary output by the natural language model after the natural language model summarizes the first document.2. The method of claim 1 , wherein the tokens comprise complete words and wherein the first dictionary compiled based on the tokens comprises a dictionary that includes only the words in the first document.3. The method of claim 1 , wherein the tokens comprise strings of characters of minimum length while still having meaning to the natural language model and wherein the first dictionary compiled based on the tokens comprises a dictionary that includes only words that can be derived from the tokens.4. The method of claim 3 , wherein the words that can be derived from the tokens include the words in the first document claim 3 , alternative forms of the words in the first documents claim 3 , synonyms of the words in the first document claim 3 , and aphorisms of the words in the first document.5. The method of claim 1 , further comprising:obtaining a plurality of documents, each including a respective summary thereof, and for ...

Подробнее
Номер записи: 96
25-02-2021 дата публикации

SYSTEMS AND METHODS FOR IMPROVING KBA IDENTITY AUTHENTICATION QUESTIONS

Номер: US20210056186A1
Автор: Nygate Tamir, Rotem Benny, Yaakobovich Elina
Принадлежит:

Certain implementations include systems and methods for improving knowledge-based-authentication (KBA) identity authentication questions. A method is provided that includes receiving a set of identity information associated with a subject; querying one or more databases; receiving personally identifiable information; determining, from the personally identifiable information, at least one subject characteristic; producing, with a predictive model and based on the personally identifiable information and on the at least one subject characteristic, at least one knowledge-based authentication (KBA) identity proofing question having a personally identifiable correct answer; sending, for display on a first computing device associated with the subject, the at least one KBA identity proofing question; receiving, responsive to the sending, a response answer; and responsive to a match between the response answer and the personally identifiable correct answer, sending, for display on the first computing device associated with the subject, a first indication of authentication. 1. A computer-implemented method comprising:receiving a set of identity information associated with a subject, the set of identity information comprising location information;querying one or more databases with at least a portion of the set of identity information;receiving, in response to the querying, personally identifiable information;determining, from the personally identifiable information, residence information of the subject;ranking, by a predictive model executing on one or more computer processors, a plurality of question topics based on the residence information of the subject;selecting, based on the ranking, at least one knowledge-based authentication (KBA) identity proofing question for presentation to the subject, the at least one KBA identity proofing question having a personally identifiable correct answer;sending, for display on a first computing device associated with the subject, the at ...

Подробнее
Номер записи: 97
25-02-2021 дата публикации

Electronic device and deep learning-based interactive messenger operation method

Номер: US20210056270A1
Автор: Analle Jamal ABUAMMAR, Ruba Waleed JAIKAT, Wael Younis FARHAN
Принадлежит: SAMSUNG ELECTRONICS CO LTD

An interactive messenger operation method may include: transferring a user's sentence or comment to an interactive messenger architecture; generating candidate responses by means of a response generator, based on a user language model and a context; and selecting one response from among the candidate responses through a ranking network by using a personal database and a user vector embedding.

Подробнее
Номер записи: 98
13-02-2020 дата публикации

INGESTION PLANNING FOR COMPLEX TABLES

Номер: US20200050643A1
Автор: Bastide Paul R., Broomhall Matthew E., Byron Donna K., Loredo Robert E.
Принадлежит:

Embodiments of the present invention disclose a method, computer program product, and system for generating a plan for document processing. A plurality of electronic documents are received, by a computer, using a network. The plurality of electronic documents are analyzed, using the computer, to identify a plurality of tabular data, based on the analyzed plurality of electronic documents. Textual data is identified within the identified tabular data, of the analyzed plurality of electronic documents. Textual hints are generated, based on the identified textual data within the identified tabular data. References are identified, wherein references are based on matching textual hints with textual data in the received plurality of electronic documents. A count of references is calculated, associated with one or more sets of tabular data. A priority score is calculated based on the count of references, and an ingestion plan is generated, based on the calculated priority score. 1. A computer-implemented method for generating a plan for document processing , the method comprising:receiving a plurality of electronic documents, by a computer using a network;analyzing one of the received plurality of electronic documents, using the computer, to identify a table containing tabular data;identifying textual data within the identified tabular data, by performing a first natural language search of the identified tabular data;generating textual hints, based on the identified textual data within the identified tabular data;identifying references, wherein the references are based on matching textual hints with textual data in non-tabular data of the one analyzed electronic document of the received plurality of electronic documents;calculating a priority score based on a calculated count of references;generating an ordered list of identified references and the associated tabular data, wherein the ordering of the ordered lists is based on generated list of identified references; ...

Подробнее
Номер записи: 99
13-02-2020 дата публикации

Dialogue method, dialogue system, and program

Номер: US20200050670A1
Автор: Makoto Iwayama, Yu Asano
Принадлежит: HITACHI LTD

Provided is a technique for easily using a dialogue service that reduces an effect of a change in a task of the dialogue service and provides a plurality of tasks. In the dialogue method, a computer including a processor and a memory executes a dialogue. The dialogue method includes: a text input step in which the computer receives text; a task execution step in which the computer causes the text to be separately executed by a plurality of types of tasks; an execution result obtaining step in which the computer separately obtains execution results from the plurality of types of tasks; a task selection step in which the computer selects one of the obtained execution results; and a response output step in which the computer outputs the selected execution result as an answer to the text.

Подробнее
Номер записи: 100