Dictionary Building, Modification, Or Prioritization Patents (Class 704/10)
  • Patent number: 10706230
    Abstract: Systems for inputting text into an electronic device are provided. The systems are configured to receive a sequence of characters input into the device. The systems comprise a means configured to generate from the sequence of characters a sequence of word-segments. The systems also comprise a text prediction engine comprising a language model having stored sequences of word-segments. The text prediction engine is configured to receive the sequence of word-segments. In a first embodiment, the text prediction engine is configured to determine whether each word-segment of the sequence of word-segments corresponds to a stored word-segment of the language model and output the sequence of word-segments as a candidate prediction when each of the word-segments of the sequence of word-segments corresponds to a stored word-segment of the language model, regardless of whether the sequence of word-segments corresponds to a stored sequence of word-segments. Various other systems and corresponding methods are provided.
    Type: Grant
    Filed: December 11, 2014
    Date of Patent: July 7, 2020
    Assignee: TOUCHTYPE LIMITED
    Inventors: Juha Iso-Sipilä, Hwasung Lee, Julien Baley, Joseph Osborne
  • Patent number: 10699707
    Abstract: Example aspects of the present disclosure are directed to processing voice commands or utterances. For instance, data indicative of a voice utterance can be received. A device topology representation can be accessed. The device topology representation can define a plurality of smart devices associated with one or more structures. The device topology representation can further define a location of each of the plurality of devices within the associated structures. A transcription of the voice utterance can be determined based at least in part on the device topology representation. One or more selected devices and one or more actions to be performed by the one or more selected devices can be determined based at least in part on the determined transcription and the device topology representation.
    Type: Grant
    Filed: September 29, 2017
    Date of Patent: June 30, 2020
    Assignee: GOOGLE LLC
    Inventors: Barnaby John James, David Roy Schairer, Amy Lynn Baldwin, Vincent Yanton Mo, Jun Yang, Mark Spates, IV, Lei Zhong
  • Patent number: 10691892
    Abstract: The language analysis method includes collecting an online document, performing coined word filtering on the collected document based on a predetermined coined word extraction pattern and a dictionary to extract a coined word candidate which corresponds to the coined word extraction pattern and is not registered in a coined stop word dictionary, performing morpheme analysis on the extracted coined word candidate to verify a coined word candidate which does not correspond to a predetermined part of speech and is not registered in a pre-stored morpheme dictionary, refining the coined word extraction pattern, based on a result of the verification and updating the verified coined word candidate in the coined stop word dictionary, and updating the verified coined word candidate in the morpheme dictionary, based on the result of the verification.
    Type: Grant
    Filed: September 14, 2017
    Date of Patent: June 23, 2020
    Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Chung Hee Lee, Hyun Ki Kim, Sang Kyu Park, Kyung Man Bae, Yong Jin Bae, Ji Hyun Wang, Hyung Jik Lee, Soo Jong Lim, Joon Ho Lim, Myung Gil Jang, Mi Ran Choi, Jeong Heo
  • Patent number: 10679134
    Abstract: Systems and methods of automated ontology development include a corpus of communication data. The corpus of communication data includes communication data from a plurality of interactions and is processed. A plurality of terms are extracted from the corpus. Each term of the plurality is a plurality of words that identify a single concept within the corpus. An ontology is automatedly generated from the extracted terms.
    Type: Grant
    Filed: July 1, 2019
    Date of Patent: June 9, 2020
    Assignee: VERINT SYSTEMS LTD.
    Inventors: Roni Romano, Yair Horesh, Jeremie Dreyfuss
  • Patent number: 10678572
    Abstract: Techniques provide a framework for dynamic globalization enablement for an application during software development. A globalization development operation information system (GDOIS) retrieves source code for the application, which is assigned to support specified globalization features. The GDOIS evaluates the source code for each of the plurality of specified globalization features. Upon determining that the source code does not include at least a first specified globalization feature, the GDOIS identifies an application programming interface (API) associated with the feature. The GDOIS inserts source code associated with the API into the source code for the application.
    Type: Grant
    Filed: January 24, 2017
    Date of Patent: June 9, 2020
    Assignee: International Business Machines Corporation
    Inventors: Syed Haiderzaidi, Su Liu, Boyi Tzen, Cheng Xu
  • Patent number: 10679011
    Abstract: Systems, devices, and methods of the present invention detect argumentation in text. In an example, an application executing on a computing device accesses text comprising fragments. The application creates a discourse tree from the text. The discourse tree includes nodes, each nonterminal node representing a rhetorical relationship between two of the fragments and each terminal node of the nodes of the discourse tree is associated with one of the fragments. The application matches each fragment that has a verb to a verb signature, thereby creating a communicative discourse tree. The application determines whether the communicative discourse tree represents text that includes argumentation by applying a classification model trained to detect argumentation to the communicative discourse tree.
    Type: Grant
    Filed: June 15, 2018
    Date of Patent: June 9, 2020
    Assignee: Oracle International Corporation
    Inventor: Boris Galitsky
  • Patent number: 10649971
    Abstract: A contextual index compendium that includes contextual index item generation rules that define document index entry generation transforms usable to transform text of the documents into embedded document index entries of document indexes within the documents is obtained by a processor. Using the document index entry generation transforms defined within the contextual index item generation rules in association with a document that includes embedded document index entries that are both embedded at locations of associated text distributed throughout the document and added as part of a document index within the document, new text of the document is programmatically transformed into at least one new document index entry in response to determining that at least one portion of the new text includes candidate text that is not already indexed within the existing embedded document index entries and the document index within the document.
    Type: Grant
    Filed: November 17, 2015
    Date of Patent: May 12, 2020
    Assignee: International Business Machines Corporation
    Inventor: Neil G. Bloomfield
  • Patent number: 10650801
    Abstract: Embodiments of the present disclosure provide a language recognition method and apparatus, a device and a computer storage medium. In an aspect, in the embodiments of the present disclosure, after the Nth speech segment included by the speech signal is received, language recognition is performed according to already-received previous N speech segments to obtain the score of each language in at least one language, N being 2, 3, 4 . . . ; therefore, if there exists a langue whose score reaches the designated threshold, the language whose score reaches the designated threshold is considered as the language matched with the speech signal. Therefore, the technical solutions according to embodiments of the present disclosure solve the problem in the prior art that the efficiency of language recognition is lower so that the language recognition cannot be applied to an application scenario in which the recognition result needs to be obtained quickly.
    Type: Grant
    Filed: June 20, 2016
    Date of Patent: May 12, 2020
    Assignee: Baidu Online Network Technology (Beijing) Co., Ltd.
    Inventors: Xiao Li, Chao Li, Yong Guan
  • Patent number: 10650099
    Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.
    Type: Grant
    Filed: March 20, 2017
    Date of Patent: May 12, 2020
    Assignee: ELMENTAL COGNITION LLC
    Inventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
  • Patent number: 10643036
    Abstract: A method of providing real-time translation for video chat is provided. The method includes: continuously receiving first-language voice data and at least one second-language word from a first terminal; continuously displaying the at least one second-language word at the same time as reproduction of the voice data; acquiring a second-language translation of an ended sentence included in a voice recognition result for the voice data; and substituting at least one word, which corresponds to the ended sentence in the displayed at least one second-language word, with the acquired translation. The at least one second-language word corresponds to respective words included in the voice recognition result for the voice data.
    Type: Grant
    Filed: August 18, 2017
    Date of Patent: May 5, 2020
    Assignee: Hyperconnect, Inc.
    Inventors: Sangil Ahn, Kangsik Jung, Hyountaek Yong, Hyeok Choi
  • Patent number: 10635754
    Abstract: Systems and methods for improved conversation translation are disclosed. The system receives a first portion of a conversation in a first language. The system translates the first portion of the conversation to a second language. The system generates a predicted second portion of the conversation. The first portion and the predicted second portion are sent to a second user device as a predictive translation. The system then receives an actual second portion of the conversation, translates it to the second language, and sends the first portion and the actual second portion to the second user device as a batch translation. The system compares the batch translation to the predictive translation to identity any differences and generates a color-coded translation highlighting any differences between the batch translation and the predictive translation. The system sends the color-coded translation to the second user device for display on the second user device.
    Type: Grant
    Filed: August 2, 2019
    Date of Patent: April 28, 2020
    Assignee: CAPITAL ONE SERVICES, LLC
    Inventors: Vincent Pham, Jeremy Edward Goodsitt, Austin Walters, Fardin Abdi Taghi Abad
  • Patent number: 10635852
    Abstract: The image processing apparatus includes an accepting unit, first and second storage units, and a controller. The first storage unit stores frequency order data for each language. The controller, using character image data in a font cache area, performs rasterization processing on PDL data. The controller sets first and second cache areas. The controller, based on frequency order data corresponding to a selected language, generates character image data in descending order of character use frequency. The controller has the character image data generated based on frequency order data stored in the first cache area.
    Type: Grant
    Filed: July 3, 2019
    Date of Patent: April 28, 2020
    Assignee: KYOCERA DOCUMENT SOLUTIONS INC.
    Inventor: Anthony Deiparine
  • Patent number: 10628129
    Abstract: Implementations directed to providing a computer-implemented method for automating analytical model building for code snippets, the method comprising receiving software instructions indicating functionality of a software component, analyzing the software instructions through natural language processing to identify tags to characterize the software instructions and the functionality, performing a search, based on the identified tags, of relevant Internet sites to identify code snippets that address the functionality, scoring one or more of the identified code snippets based on a respective relevance to the functionality, based on the scoring of the one or more of the identified code snippets, determining that at least one of the code snippets has a score that meets a relevance threshold, and providing the at least one of the code snippets based on the determination that the at least one of the code snippets has the score that meets the relevance threshold.
    Type: Grant
    Filed: October 2, 2017
    Date of Patent: April 21, 2020
    Assignee: Accenture Global Solutions Limited
    Inventors: Ashvin Gondalia, Sunjeet Gupta, Parikshit Maniar, Shridhar D. Rajgopalan, Prateek Shrivastav, Meghashyam Vishwanath Sawant, Kulshrestha Ashwani, Gade Sanjay Gaurav, Sumit Alawat
  • Patent number: 10628130
    Abstract: A code completion tool uses machine learning models generated for custom or proprietary classes associated with a custom library of classes of a programming language and for overlapping classes associated with a standard library of classes for the programming language. The machine learning models are trained with features from usage patterns of the custom classes and overlapping classes found in two different sources of training data. An n-order Markov chain model is trained for each custom class and each overlapping class from the usage patterns to generate probabilities to predict a method invocation more likely to follow a sequence of method invocations for a custom class and for an overlapping class.
    Type: Grant
    Filed: December 3, 2018
    Date of Patent: April 21, 2020
    Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC.
    Inventors: Shengyu Fu, Neelakantan Sundaresan, Ying Zhao
  • Patent number: 10616036
    Abstract: Implementations are directed to integrating a computer-executed service platform with multiple channels, and include actions of providing a transition layer as an application executed on a client-side device, which receives input from a channel of the multiple channels, and providing a unified input that is in a unified format for processing by the service platform, receiving, by the service platform, the unified input, identifying, by the service platform, a set of actions based on the unified input, the set of actions including to be executed by one or more back-end services, providing a service layer including a plurality of bots, each bot interacting with a back-end service based on an action to receive at least one result from the respective back-end service, receiving result data including data describing the at least one result, and transmitting an output based on the result data through the transition layer of the client-side device.
    Type: Grant
    Filed: June 7, 2017
    Date of Patent: April 7, 2020
    Assignee: Accenture Global Solutions Limited
    Inventors: Tariq Mohammad Salameh, Marco Intermite, Matteo Luca Maga, Federica Rossi
  • Patent number: 10606957
    Abstract: Natural language policy text is translated into logical access control policy code with a policy composer that receives natural language policy text, an attribute dictionary connected to the policy composer to define attributes and their logical access control policy equivalents. A natural language policy set is connected to the policy composer and includes samples of natural language policy rules and their logical access control policy equivalents. The policy composer uses natural language processing, the attribute dictionary and the natural language policy set to translate the natural language policy text into logical access control code.
    Type: Grant
    Filed: June 27, 2019
    Date of Patent: March 31, 2020
    Assignee: Raivana, Inc.
    Inventors: Michael Good, Benjamin Coffinberger
  • Patent number: 10600412
    Abstract: A system and means for recognising phrases of approval, questions and answers in speech conversations exchanged between communication devices such that the phrase recognition means is conditional upon detection of a non-speech event from the devices to denote a subject of interest, the phrase recognition means employing detection of non-speech events from the devices to identify and select speech recognition rules of relevance to the subject item, questions about the subject and answers to the questions. Speech recognition means logs detected speech and non-speech events to a repository for later analysis.
    Type: Grant
    Filed: October 27, 2016
    Date of Patent: March 24, 2020
    Assignee: Simple Matters Limited
    Inventor: Jonathan Peter Vincent Drazin
  • Patent number: 10592538
    Abstract: Aspects migrate an unstructured document to a specific document type definition Darwin Information Typing architecture wherein processors are configured to calculate a verb to noun ratio of an unstructured document by dividing a of plurality verbs of the unstructured document by a plurality of nouns of the unstructured document, assign a first weight to the unstructured document based on the calculated verb to noun ratio, and migrate the unstructured document to a specific document type definition Darwin Information Typing Architecture based on the first weight.
    Type: Grant
    Filed: January 4, 2018
    Date of Patent: March 17, 2020
    Assignee: International Business Machines Corporation
    Inventors: Palliyathu Vishal George, Michael J. Iantosca, John Kurian, Balaji Sankar
  • Patent number: 10575058
    Abstract: A method for enabling an user to consume a video or audio content understandable with respect to a preferred language. The method includes receiving a content selection input from an user for selecting a video or audio content for viewing from a set of contents, wherein the content is available in one or more languages, receiving a location related information of the user, identifying the preferred language for providing the content, fetching the content from the server based on the preferred language, if the content is not available in the preferred language, fetching a text content along with the video or audio content in relation to the preferred language, rendering the video or audio content alone or in synchronization with the text content.
    Type: Grant
    Filed: March 15, 2017
    Date of Patent: February 25, 2020
    Inventor: Mrityunjay Patil
  • Patent number: 10572935
    Abstract: During an analysis technique, information associated with two entities may be compared to determine a similarity metric. For example, a string distance between the information may be computed. Then, an association metric between financial-transaction histories for the two entities may be calculated. This calculation may involve comparing the nodes and branches in a commerce graph that represents financial interrelationships among a set of entities, including inputs received by the set of entities, outputs provided by the set of entities, and financial transactions among the set of entities. Next, a determination of whether the entities are likely to be a same entity may be based on the similarity metric and/or the association metric. If the entities are likely to be the same entity, the entities may be combined in a data structure. Alternatively, if the entities are not likely to be the same, they may remain separate.
    Type: Grant
    Filed: July 16, 2014
    Date of Patent: February 25, 2020
    Assignee: INTUIT, INC.
    Inventors: Calum G. Murray, Jeffrey A. Langston, John J. Tumminaro
  • Patent number: 10572585
    Abstract: This disclosure provides a computer-implemented method. The method may include extracting one or more features based on a first utterance from a first interlocutor in a dialog and a second utterance from a second interlocutor in the dialog. The method may further include inferring one or more personality traits of the first interlocutor based on the one or more extracted features from the dialog.
    Type: Grant
    Filed: November 30, 2017
    Date of Patent: February 25, 2020
    Assignee: International Business Machines Coporation
    Inventors: En Liang Xu, Chang Hua Sun, Shi Wan Zhao, Ke Ke Cai, Yue Chen, Li Zhang, Zhong Su
  • Patent number: 10559301
    Abstract: Speech recognition may be improved by generating and using a topic specific language model. A topic specific language model may be created by performing an initial pass on an audio signal using a generic or basis language model. A speech recognition device may then determine topics relating to the audio signal based on the words identified in the initial pass and retrieve a corpus of text relating to those topics. Using the retrieved corpus of text, the speech recognition device may create a topic specific language model. In one example, the speech recognition device may adapt or otherwise modify the generic language model based on the retrieved corpus of text.
    Type: Grant
    Filed: December 15, 2017
    Date of Patent: February 11, 2020
    Assignee: Comcast Interactive Media, LLC
    Inventors: David F. Houghton, Seth Michael Murray, Sibley Verbeck Simon
  • Patent number: 10552545
    Abstract: The present invention relates to a mathematical translator, a mathematical translation device and a mathematical translation platform, which especially allows a user to understand principle of mathematics of its own accord and express the principle in words by interpreting the meaning of the mathematical expression in a natural language when the specific mathematical expression is inputted.
    Type: Grant
    Filed: September 27, 2017
    Date of Patent: February 4, 2020
    Inventor: Bong Han Cho
  • Patent number: 10552541
    Abstract: According to an embodiment of the present invention, a natural language query including an ambiguous entity is received from a user. A meaning of the ambiguous entity is determined based on an extracted language context of the natural language query. The determined meaning, extracted language context, and contextual information of the user is applied to a machine learning model to determine a plurality of computer applications from amongst multiple computer applications to process the natural language query. The determined applications are executed to produce results for the natural language query tailored to an interest of the user in accordance with the contextual information.
    Type: Grant
    Filed: August 27, 2018
    Date of Patent: February 4, 2020
    Assignee: International Business Machines Corporation
    Inventors: Brian S. Dreher, Henry H. Chen, Sheng Hua Bao, William S. Spangler
  • Patent number: 10545966
    Abstract: A method, system, and non-transitory computer readable medium for identifying a relevant conversation. The method can include: identifying a conversation graph including identifiers of messages posted by a set of authoring accounts; identifying a relevance score for each authoring account; applying, by a computer processor, a first relevance filter to the conversation graph in order to modify the set of relevance scores; applying, by the computer processor and after applying the first relevance filter, a second relevance filter to the conversation graph in order to further modify the set of relevance scores; selecting, based on the set of relevance scores and after applying the second relevance filter, a subset of messages of the conversation graph for inclusion in the relevant conversation; and providing at least a portion of the relevant conversation to a client device.
    Type: Grant
    Filed: September 19, 2016
    Date of Patent: January 28, 2020
    Assignee: Twitter, Inc.
    Inventors: Marcel Molina, Ross Cohen, Kyle Maxwell, Stuart Hood, Cara Meverden, Coleen Baik
  • Patent number: 10542147
    Abstract: A virtual assistant application, system, and service that interacts with a caller over a telephone, cellular, or VoIP network as the called party's representative when the called party is unavailable, providing answers to queries and performing commands that were provisioned by the called party. The application includes a telephony interface, speech recognition and synthesis, a dialog manager, and knowledge domain. The application can also be configured to interact with a sender of SMS, MMS, or IM messages.
    Type: Grant
    Filed: December 28, 2018
    Date of Patent: January 21, 2020
    Assignee: Open Invention Network LLC
    Inventor: Gerald McCobb
  • Patent number: 10540424
    Abstract: Symbol recognition techniques may be applied to documents comprising various forms of content. Documents including both text and mathematical expressions may be problematic, as applying a recognizer that does not match the content may produce anomalous results. Instead, a parser may evaluate the document to classify respective regions as one of a text region or a mathematics region, based on the characteristics of each type of content. The recognizer corresponding to the content of each region may be applied to produce a composite document comprising both recognized text expressions and recognized mathematical expressions. Additional functionality may be presented based on the recognized content; e.g.
    Type: Grant
    Filed: June 13, 2017
    Date of Patent: January 21, 2020
    Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
    Inventors: Sheng Yi, Nikola Nikolic, Xiao Tu, Ivan Stojiljkovic, Jelena Mojasevic
  • Patent number: 10528662
    Abstract: An example method includes receiving text from a plurality of documents, segmenting text received text of the plurality of documents, calculating a frequency statistic for each segment of each document, determining segments of potential interest of each document based on calculated frequency statistic, calculating distances between each document of the plurality of documents based on a text metric, and storing segments of potential interest of each document and the distances in a search database. The method may further include receiving a search query and performing a search of information contained in the search database, partitioning documents of search results using the distances, for each partition, determining labels of segments of potential interest for documents of that particular partition, the labels being determined based on a plurality of frequency statistics, and providing determined labels of segments of potential interest for documents of each partition.
    Type: Grant
    Filed: February 13, 2018
    Date of Patent: January 7, 2020
    Assignee: Ayasdi AI LLC
    Inventors: Harlan Sexton, Jennifer Kloke
  • Patent number: 10521253
    Abstract: Techniques provide a framework for dynamic globalization enablement for an application during software development. A globalization development operation information system (GDOIS) retrieves source code for the application, which is assigned to support specified globalization features. The GDOIS evaluates the source code for each of the plurality of specified globalization features. Upon determining that the source code does not include at least a first specified globalization feature, the GDOIS identifies an application programming interface (API) associated with the feature. The GDOIS inserts source code associated with the API into the source code for the application.
    Type: Grant
    Filed: June 28, 2016
    Date of Patent: December 31, 2019
    Assignee: International Business Machines Corporation
    Inventors: Syed Haiderzaidi, Su Liu, Boyi Tzen, Cheng Xu
  • Patent number: 10515061
    Abstract: Methods and systems for generating a database index and searching the database index are described herein. In one aspect this may include receiving an item of database data, wherein the item of database data comprises a sequence of data elements. Groups of data elements may be identified within the received item of database data. If any one or more of the identified groups of data elements have not been previously identified within the item of database data and/or previous items database data then the one or more identified group may be stored as index entries in a database index. Information describing the sequence of the groups of neighbouring data elements may be recorded within the database index as they are located within the item of database data. The database index may be searched based on a received search term comprising a sequence of data elements.
    Type: Grant
    Filed: December 4, 2015
    Date of Patent: December 24, 2019
    Assignee: Business Partners Limited
    Inventor: Simon Ian Bain
  • Patent number: 10503828
    Abstract: Provided are a system and method for answering a natural language question which show improved information retrieval performance. The system includes an index unit configured to analyze text of previously stored irregular documents and classify and index the irregular documents according to meanings of sentences or paragraphs, a database configured to receive and store the irregular documents indexed according to the meanings and transmitted from the index unit, a retrieval unit configured to extract an index word by semantically analyzing an input question and search the database for documents related to the extracted index word, and a provision unit configured to generate a correct answer to the question by analyzing the documents searched by the retrieval unit and provide the search results and the correct answer.
    Type: Grant
    Filed: June 11, 2015
    Date of Patent: December 10, 2019
    Assignee: Electronics and Telecommunications Research Institute
    Inventors: Yong Jin Bae, Hyun Ki Kim, Pum Mo Ryu, Hyo Jung Oh, Chung Hee Lee, Soo Jong Lim, Joon Ho Lim, Myung Gil Jang, Mi Ran Choi, Jeong Heo
  • Patent number: 10503762
    Abstract: According to an aspect, searching, recommending, and exploring documents through conceptual associations includes a method for receiving a plurality of documents and extracting concepts from each of the documents. A degree of relation between each of the documents and concepts in a knowledge base is calculated. The method also includes, in response to receiving a query, determining one or more concepts from the query. For each of the concepts, a list of documents having a highest degree of relation to the concept is retrieved. The method also includes outputting a list that is responsive to the one or more retrieved lists.
    Type: Grant
    Filed: March 13, 2015
    Date of Patent: December 10, 2019
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Michele M. Franceschini, Luis A. Lastras-Montano, John T. Richards, Livio B. Soares, Mark N. Wegman
  • Patent number: 10503761
    Abstract: According to an aspect, searching, recommending, and exploring documents through conceptual associations includes receiving a plurality of documents and extracting concepts from each of the documents. A degree of relation between each of the documents and concepts in a knowledge base is calculated. An aspect also includes, in response to receiving a query, determining one or more concepts from the query. For each of the concepts, a list of documents having a highest degree of relation to the concept is retrieved. An aspect also includes outputting a list that is responsive to the one or more retrieved lists.
    Type: Grant
    Filed: July 14, 2014
    Date of Patent: December 10, 2019
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Michele M. Franceschini, Luis A. Lastras-Montano, John T. Richards, Livio B. Soares, Mark N. Wegman
  • Patent number: 10499121
    Abstract: A system for generating video clips includes a video processing system configured to receive a video file from a video capture system, and to create video clips based on significant moments identified in the video file. The video processing system includes a file storage and database system configured to store the video file, and storing an ontology and keywords associated with themes that are pertinent to the overall theme of the video file. The video processing system also includes a natural language processing (NLP) moments module configured to identify themes contained in the video file using the ontology and the keywords, and to identify time codes associated with the identified themes. The video processing system also includes a video clip generator configured to generate video clips based on the identified time codes.
    Type: Grant
    Filed: January 9, 2018
    Date of Patent: December 3, 2019
    Assignee: NBCUniversal Media, LLC
    Inventors: William Beckett, Gaurav Gupta, Milena Markova
  • Patent number: 10496744
    Abstract: A method includes obtaining an input text, identifying a first term in the input text, and accessing lexicon data to identify a first entry corresponding to the first term. The first entry includes core data corresponding to domain-independent lexical information for the first term, and non-core data corresponding to domain-specific lexical information for the first term. The method also includes determining that the non-core data of the first entry identifies a second term in the input text as a modifier of the first term. The method further includes generating a partially parsed and bracketed version of the input text. The partially parsed and bracketed version indicates that the second term modifies the first term in the input text. The method also includes generating a parsed version of the input text based on the partially parsed and bracketed version of the input text.
    Type: Grant
    Filed: November 3, 2017
    Date of Patent: December 3, 2019
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Branimir K. Boguraev, Esme Manandise, Benjamin P. Segal
  • Patent number: 10497366
    Abstract: An agent automation system includes a memory configured to store a natural language understanding (NLU) framework, and a processor configured to perform actions, including: generating a meaning representation from an annotated utterance tree of an utterance, wherein a structure of the meaning representation indicates a syntactic structure of the utterance and one or more subtree vectors of the meaning representation indicate a semantic meaning of one or more intent subtrees of the meaning representation; searching the meaning representation of the utterance against an understanding model to extract intents/entities of the utterance based on the one or more subtree vectors of the meaning representation, wherein the understanding model includes a plurality of meaning representations derived from the intent/entity model; and providing the intents/entities of the utterance to a reasoning agent/behavior engine (RA/BE) of the agent automation system that performs one or more actions in response to the intents/entit
    Type: Grant
    Filed: January 2, 2019
    Date of Patent: December 3, 2019
    Assignee: ServiceNow, Inc.
    Inventors: Edwin Sapugay, Anil Kumar Madamala, Maxim Naboka, Srinivas SatyaSai Sunkara, Lewis Savio Landry Santos, Murali B. Subbarao
  • Patent number: 10496756
    Abstract: A sentence creation system, which outputs an opinion sentence on an agenda, includes: an input unit into which the agenda is input; an agenda analyzing unit analyzing the agenda and judging the polarity of the agenda and a keyword used for searching; a searching unit searching for articles using the keyword and a disputed point word showing a disputed point in the discussion; a disputed point determining unit for determining the disputed point used for creating the opinion sentence; a sentence extracting unit for extracting sentences in which the disputed point is described among the articles output by the searching unit; a sentence sorting unit for creating sentences by sorting the extracted sentences; an evaluating unit for evaluating the sentences; a paraphrasing unit for inserting appropriate conjunctions into the sentences; and an output unit for outputting the most highly evaluated sentence among the plural sentences as the opinion sentence.
    Type: Grant
    Filed: October 1, 2014
    Date of Patent: December 3, 2019
    Assignee: HITACHI, LTD.
    Inventors: Kohsuke Yanai, Toshinori Miyoshi, Toshihiko Yanase, Misa Sato
  • Patent number: 10489516
    Abstract: A speech recognition terminal includes: a voice input unit to accept an input of a voice; a speech recognition command unit to command a speech recognition unit to convert voices of joined voice data acquired by the voice input unit joining the voice data of the voice accepted by the voice input unit to the voice data of the voice accepted previously into character information of a first language at an interval of predetermined time; a translation command unit to command a translation unit to translate first character information of a first language into a second language whenever receiving the first character information of the first language converted by the voice recognition unit; and a display unit to display the first character information of the second language translated by the translation unit together with the first character information of the first language.
    Type: Grant
    Filed: March 29, 2017
    Date of Patent: November 26, 2019
    Assignee: Fujitsu Social Science Laboratory Limited
    Inventor: Toshikazu Fukuoka
  • Patent number: 10482185
    Abstract: Logic may adjust communications between customers. Logic may cluster customers into a first group associated with a first subset of synonyms and a second group associated with a second subset of the synonyms. Logic may associate a first tag with the first group and with each of the synonyms of the first subset. Logic may associate a second tag with the second group and with each of the synonyms of the second subset. Logic may associate one or more models with pairs of the groups. A first pair may comprise the first group and the second group. The first model associated with the first pair may adjust words in communications between the first group and the second group, based on the synonyms associated with the first pair, by replacement of words in a communication between customers of the first subset and customers of the second sub set.
    Type: Grant
    Filed: February 27, 2019
    Date of Patent: November 19, 2019
    Assignee: Capital One Services, LLC
    Inventors: Fardin Abdi Taghi Abad, Austin Grant Walters, Jeremy Edward Goodsitt, Reza Farivar, Vincent Pham, Anh Truong
  • Patent number: 10482874
    Abstract: Systems and processes for operating a digital assistant using a hierarchical belief state are disclosed. In an example process, a user utterance of a dialog is received. A belief state for the dialog is determined. The belief state comprises a plurality of dialog slots. Each dialog slot of the plurality of dialog slots includes a respective marginal certainty for a concept or property represented by the respective dialog slot. A first dialog slot of the plurality of dialog slots further includes one or more joint certainties for one or more interpretations arising from the first dialog slot. Based on the marginal certainty of each dialog slot of the plurality of dialog slots and the one or more joint certainties of the first dialog slot, a policy action is selected from a plurality of candidate policy actions that correspond to the belief state. The selected policy action is performed.
    Type: Grant
    Filed: August 15, 2017
    Date of Patent: November 19, 2019
    Assignee: Apple Inc.
    Inventors: Blaise Thomson, Anders Johannsen, Diarmuid Ó Séaghdha, Federico Flego, Luca Simonelli, Stephen J. Young, Thomas David Voice, Thorvaldur Pall Helgason
  • Patent number: 10482175
    Abstract: A communication device is arranged to transmit a character string that identifies the device. The character string comprises a plurality of substrings, each of which comprises a sequence of characters. A property of the device is identified using a data structure having multiple nodes, wherein each of a plurality of nodes stores a respective hash value. Each hash value corresponds to the hash value that would be generated by performing a hash function on the sequence of characters of each substring. The data structure comprises references between the plurality of nodes, and the references define a path through the data structure that identifies the device. A node on the path is associated with a property of the device.
    Type: Grant
    Filed: August 24, 2017
    Date of Patent: November 19, 2019
    Assignee: 51 DEGREES MOBILE EXPERTS LIMITED
    Inventors: James William Rosewell, Jonathan Daniel Rabin, Benjamin James Shillito
  • Patent number: 10474969
    Abstract: Logic may adjust communications between customers. Logic may cluster customers into a first group associated with a first subset of synonyms and a second group associated with a second subset of the synonyms. Logic may associate a first tag with the first group and with each of the synonyms of the first subset. Logic may associate a second tag with the second group and with each of the synonyms of the second subset. Logic may associate one or more models with pairs of the groups. A first pair may comprise the first group and the second group. The first model associated with the first pair may adjust words in communications between the first group and the second group, based on the synonyms associated with the first pair, by replacement of words in a communication between customers of the first subset and customers of the second sub set.
    Type: Grant
    Filed: February 27, 2019
    Date of Patent: November 12, 2019
    Assignee: Capital One Services, LLC
    Inventors: Fardin Abdi Taghi Abad, Austin Grant Walters, Jeremy Edward Goodsitt, Reza Farivar, Vincent Pham, Anh Truong
  • Patent number: 10467290
    Abstract: A knowledge graph (KG) is generated and refined. The generated KG describes direct relationships between different words associated with a particular classification. Initially, a semantic data source, such as a lexical database, is accessed to identify words that are similarly grouped and express a distinct concept. A KG generator creates a sparse KG that provides a direct connection between a seed word and other words. The sparse KG is used by a dense KG generator to create a dense KG. The dense KG generator creates a dense KG that joins each of the different words directly with the seed word for the category. At different points during the creation and refinement of the KG, a user may add or remove one or more connections that affect the creation of the KG.
    Type: Grant
    Filed: December 29, 2015
    Date of Patent: November 5, 2019
    Assignee: Amazon Technologies, Inc.
    Inventors: Weixin Wu, Wei Xia, Ranju Das, Meng Wang
  • Patent number: 10460036
    Abstract: The disclosure relates to transferred learning from a first language (e.g., a source language for which a semantic parser has been defined) to a second language (e.g., a target language for which a semantic parser has not been defined). A system may use knowledge from a trained model in one language to model another language. For example, the system may transfer knowledge of a semantic parser from a first (e.g., source) language to a second (e.g., target) language. Such transfer of knowledge may occur and be useful when the first language has sufficient training data but the second language has insufficient training data. The foregoing transfer of knowledge may extend the semantic parser for multiple languages (e.g., the first language and the second language).
    Type: Grant
    Filed: April 23, 2018
    Date of Patent: October 29, 2019
    Assignee: Voicebox Technologies Corporation
    Inventors: Long Duong, Hadi Afshar, Dominique Estival, Glen Pink, Philip Cohen, Mark Edward Johnson
  • Patent number: 10452703
    Abstract: Ontologies are used to comprehend regular expressions, by selecting, based on a context relating to a domain of a regular expression, an ontology and an assertion base, parsing the regular expression to identify at least one fragment of the regular expression, identifying one or more assertions in the assertion base corresponding to one of the identified fragments, identifying, for each identified assertion, an associated node in the ontology, and returning, based on the associated nodes, a concept in the ontology as representing the associated fragment of the regular expression.
    Type: Grant
    Filed: September 6, 2016
    Date of Patent: October 22, 2019
    Assignee: International Business Machines Corporation
    Inventors: Brian P. Byrne, Ivan M. Milman, Martin A. Oberhofer, Sushain Pandit
  • Patent number: 10446055
    Abstract: A public speaking trainer has a computer system including a display monitor. A microphone is coupled to the computer system. A video capture device is coupled to the computer system. A biometric device is coupled to the computer system. A simulated environment including a simulated audience member is rendered on the display monitor using the computer system. A presentation is recorded onto the computer system using the microphone and video capture device. A first feature of the presentation is extracted based on data from the microphone and video capture device while recording the presentation. A metric is calculated based on the first feature. The simulated audience member is animated in response to a change in the metric. A score is generated based on the metric. The score is displayed on the display monitor of the computer system after recording the presentation. A training video is suggested based on the score.
    Type: Grant
    Filed: August 11, 2015
    Date of Patent: October 15, 2019
    Assignee: PitchVantage LLC
    Inventors: Anindya Gupta, Yegor Makhiboroda, Brad H. Story
  • Patent number: 10446136
    Abstract: A system and method for accent invariant speech recognition comprising: maintaining a database scoring a set of language units in a given language, and for each of the language units, scoring audio samples of pronunciation variations of the language unit pronounced by a plurality of speakers; extracting and storing m the database a feature vector for locating each of the audio samples in a feature space; identifying pronunciation variation distances, which are distances between locations of audio samples of the same language unit in the feature space, and inter-unit distances, which are distances between locations of audio samples of different language units in the feature space; calculating a transformation applicable on the feature space to reduce the pronunciation variation distances relative to the inter-unit distances; and based on the calculated transformation, training a processor to classify as a same language unit pronunciation variations of the same language unit.
    Type: Grant
    Filed: May 11, 2017
    Date of Patent: October 15, 2019
    Assignee: ANTS TECHNOLOGY (HK) LIMITED
    Inventors: Ron Fridental, Ilya Blayvas, Pavel Nosko
  • Patent number: 10438221
    Abstract: Techniques for generating matchups of sale and coupon deals are described. For example, deal data that pertains to a sale deal and a coupon deal is received. A sale brand identification and a coupon brand identification are identified based on the deal data. A first set of deal data including the sale brand identification and corresponding to the sale deal, and a second set of deal data including the coupon brand identification and corresponding to a coupon deal are determined based on the deal data. A matchup of the sale deal and the coupon deal is generated based on matching the sale brand identification and the coupon brand identification, detecting a sale deal type in the first set of deal data and a coupon deal type in the second set of data, and determining that a sale deal's and a coupon deal's validity periods overlap and have not expired.
    Type: Grant
    Filed: June 24, 2013
    Date of Patent: October 8, 2019
    Assignee: Circupon
    Inventors: Danielle Barbieri, Brian Lawler
  • Patent number: 10430042
    Abstract: Conversation-based context rules for altering virtual reality (VR) gaming and for switching between input languages based on heuristics related to past conversations between users.
    Type: Grant
    Filed: September 30, 2016
    Date of Patent: October 1, 2019
    Assignee: Sony Interactive Entertainment Inc.
    Inventors: Steven Osman, Jorge Arroyo Palacios
  • Patent number: 10430863
    Abstract: In certain implementations, a system for facilitating voice commerce is provided. A user input comprising a natural language utterance related to a product or service to be purchased may be received. A first product or service that is to be purchased may be determined based on the utterance. First payment information that is to be used to purchase the first product or service may be obtained. First shipping information that is to be used to deliver the first product or service may be obtained. A purchase transaction for the first product or service may completed based on the first payment information and the first shipping information without further user input, after the receipt of utterance, that identifies a product or service type or a product or service, seller information, payment information, shipping information, or other information related to purchasing the first product or service.
    Type: Grant
    Filed: April 11, 2017
    Date of Patent: October 1, 2019
    Assignee: VB Assets, LLC
    Inventor: Michael R. Kennewick, Sr.