Natural Language Patents (Class 704/9)
  • Patent number: 10095801
    Abstract: Interaction is provided between a first content set and a second content set, both of which are loaded into a data structure. When an event associated with loading of the second content set is detected, the second content set is parsed to identify at least one sub-set of the second content set. The identified sub-set is checked against a first data set associated with the first content set to determine whether the identified sub-set matches the first data set. If a match is found, an action associated with the least one identified sub-set is executed and the data structure is modified.
    Type: Grant
    Filed: August 17, 2015
    Date of Patent: October 9, 2018
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventor: Julian L. Friedman
  • Patent number: 10095692
    Abstract: The present invention relates to a system and method for bootstrapping templates for use in natural language sentence generation. More specifically, the present invention relates to identifying a set of candidate sentences from a large corpus based on a set of original templates by using a similarity measure. The set of candidate sentences are then processed or cleaned to generate a set of templates for use in natural language sentence generation.
    Type: Grant
    Filed: May 29, 2015
    Date of Patent: October 9, 2018
    Assignee: Thornson Reuters Global Resources Unlimited Company
    Inventors: Dezhao Song, Blake Howald, Frank Schilder
  • Patent number: 10095736
    Abstract: An approach is provided in which a knowledge manager analyzes a corpus of documents based upon relations corresponding to entities in a structured resource and constructs a natural language context associated with a set of the relations. The knowledge manager maps the natural language context to a database query and, in turn, invokes the database query when the knowledge manager matches a question to the natural language context.
    Type: Grant
    Filed: November 3, 2014
    Date of Patent: October 9, 2018
    Assignee: International Business Machines Corporation
    Inventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
  • Patent number: 10095691
    Abstract: First specification data defining a grammar corresponding to natural language, and second specification data defining a mapping between the grammar and one or more outputs to be generated, are received. An electronic object is generated using the first specification data and the second specification data, the electronic object being configured to, when executed by one or more processors, cause the one or more processors to map received natural language input to the one or more outputs. The one or more outputs may be used to control an electronically controllable machine.
    Type: Grant
    Filed: March 22, 2016
    Date of Patent: October 9, 2018
    Assignee: Wolfram Research, Inc.
    Inventor: Stephen Wolfram
  • Patent number: 10088972
    Abstract: Techniques and architectures for implementing a team of virtual assistants are described herein. The team may include multiple virtual assistants that are configured with different characteristics, such as different functionality, base language models, levels of training, visual appearances, personalities, and so on. The characteristics of the virtual assistants may be configured by trainers, end-users, and/or a virtual assistant service. The virtual assistants may be presented to end-users in conversation user interfaces to perform different tasks for the users in a conversational manner. The different virtual assistants may adapt to different contexts. The virtual assistants may additionally, or alternatively, interact with each other to carry out tasks for the users, which may be illustrated in conversation user interfaces.
    Type: Grant
    Filed: June 2, 2014
    Date of Patent: October 2, 2018
    Assignee: VERINT AMERICAS INC.
    Inventors: Fred A Brown, Tanya M Miller
  • Patent number: 10089983
    Abstract: Methods and systems for adding functionality to an account of a language processing system where the functionality is associated with a second account of a first application system is described herein. In a non-limiting embodiment, an individual may log into a first account of a language processing system and log into a second account of a first application system. While logged into both the first account and the second account, a button included within a webpage provided by the first application may be invoked. A request capable of being serviced using the first functionality may be received by the language processing system from a device associated with the first account. The language processing system may send first account data and the second account data to the first application system to facilitate an action associated with the request, thereby enabling the first functionality for the first account.
    Type: Grant
    Filed: June 8, 2017
    Date of Patent: October 2, 2018
    Assignee: Amazon Technologies, Inc.
    Inventors: Ganesh Kumar Gella, Venkata Abhinav Sidharth Bhagavatula, Robert William Serr, Yonnas Getahun Beyene
  • Patent number: 10089296
    Abstract: Systems and methods for sentiment lexicon expansion receive at least a domain specific corpus comprising a plurality of words, and a generic sentiment lexicon; parse the plurality of words in the domain specific corpus into a plurality of dependency relations; identify, using one or more syntactic dependency rules and at least one of the plurality of dependency relations, a set of one or more sentiment candidates in the domain specific corpus; filter from the set of one or more sentiment candidates any sentiment candidate having an expected performance below a predefined threshold; sample the filtered set of one or more sentiment candidates to be used in a qualitative evaluation; and, for each sentiment candidate that passes the qualitative evaluation, add the sentiment candidate to the generic sentiment lexicon.
    Type: Grant
    Filed: December 30, 2015
    Date of Patent: October 2, 2018
    Assignee: Nice Ltd.
    Inventors: Naomi Zeichner, Victor Shafran
  • Patent number: 10089301
    Abstract: A method and device for determining semantic similarity between two character strings are disclosed. The two character strings are segmented into sequences of words or phrases which represent the correlation between the characters. Edit distance from the first sequence to the second sequence is calculated based on a predetermined algorithm. A minimum semantic distance is then determined from the edit distance by considering the word/phrase pairs appearing in both sequences and the relationship between the cost of the various operations performed to convert the first sequence into the second sequence. The semantic similarity between the two character strings is then determined and normalized from the minimum semantic distance.
    Type: Grant
    Filed: November 10, 2016
    Date of Patent: October 2, 2018
    Assignee: Xiaomi Inc.
    Inventors: Pingze Wang, Tao Zhang, Fei Long
  • Patent number: 10083229
    Abstract: A computer-implemented method for pairing a new document to a document from a plurality of documents. Embodiments include, for each of the new document and the plurality of documents, generating a vector of terms of interest uniquely associated with a document of the new document and the plurality of documents. For each term of interest, an associated element value of the vector is assigned as zero if the term of interest does not occur in the document and one otherwise. The method also includes, for each document from the plurality of documents, determining a similarity between the vectors. The method also includes selecting a document from the plurality of documents as related to the new document if the similarity between the vector for the new document and the vector for the document from the plurality of documents is greater than or equal to a threshold value.
    Type: Grant
    Filed: October 9, 2009
    Date of Patent: September 25, 2018
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Greg Eyres, Vahit Hakan Hacigumus, Tobin J. Lehman, H. Raymond Strong, Jr.
  • Patent number: 10083173
    Abstract: A system, computer program product, and process are provided for artificial intelligence based language interpretation. A storage device has a terminology database that stores a plurality of terms utilized in a previous communication requesting a product and/or a service in a first spoken language, a plurality of responses in a second spoken language to the communication, and (a plurality of outcomes based upon the plurality of responses. The second spoken language being distinct from the first spoken language. Further, a processor learns to generate responses associated with corresponding terms in a request based upon an analysis of the plurality of outcomes from the terminology database, receives a request for a product and/or service in the first spoken language in a current communication, and generates a message having a response that is associated with a term present in the request.
    Type: Grant
    Filed: May 4, 2015
    Date of Patent: September 25, 2018
    Assignee: Language Line Services, Inc.
    Inventors: James Boutcher, Scott Swanson
  • Patent number: 10083451
    Abstract: A third-party company may assist other companies in providing customer support to their customers. The third-party company may provide software to a computer of a customer service representative to present a user interface to assist the customer service representative in responding to customer requests. Third-party company may also send update data to the computer of the customer service representative to cause a portion of the user interface to be updated, where the update data is determined using an intent of a message received from a customer. A message received from the customer may be processed to determine the intent of the message, a template may be obtained using the intent, and the update data may be generated by rendering the selected template. The update data may then be transmitted to the computer of the customer service representative to cause a portion of the user interface to be updated.
    Type: Grant
    Filed: June 30, 2017
    Date of Patent: September 25, 2018
    Assignee: ASAPP, INC.
    Inventors: Vicky Sehrawat, Jason Shaev, Punyashloka Biswal, Brian Dillmann, Joseph Hackman, Shawn Henry, Gustavo Sapoznik
  • Patent number: 10078725
    Abstract: Provided is a method of collecting and managing information relating to medical diagnostic procedures which includes collecting objective information about a plurality of procedures and subjective information about the results of those procedures. The objective information provides information about the parameters of the procedure and the patient who underwent the procedure while the subjective information includes an assessment of the quality of the results of the procedure. This information can be stored in a database. The database can be accessed and the information therein used in connection with understanding the results of past procedures and planning for future procedures.
    Type: Grant
    Filed: November 19, 2012
    Date of Patent: September 18, 2018
    Assignee: BAYER HEALTHCARE LLC
    Inventors: John F. Kalafut, David A. Mishler, Sridhar R. Balasubramanian, John A. Brosovich, Frederick P. Windham
  • Patent number: 10078632
    Abstract: An approach is provided in which an information handling system detects a multi-entity co-occurrence anomaly within a set of documents that corresponds to an amount of times that a first entity and a second entity co-occur in the set of documents. The information handling system then determines that at least one of the documents includes a title having a verb that grammatically connects the first entity to the second entity. As such, the information handling system collects document segments from the set of documents that have the first entity, the second entity, and the connecting verb. In turn, the information handling system uses the collected document segments to train a relation-based classifier.
    Type: Grant
    Filed: March 12, 2016
    Date of Patent: September 18, 2018
    Assignee: International Business Machines Corporation
    Inventors: Devin R. Harper, Pawan K. Lakshmanan, Gregory W. Schoeninger, Elliot B. Turner
  • Patent number: 10074200
    Abstract: Imagery may be generated for a written work based on textual descriptions in the written work using an automated or partially automated process. The imagery may be used to create a trailer for the written work, for insertion into a digital version of the written work, to visually represent the written work, and/or for other reasons. Descriptive text from the written work may be identified and associated with a catalog of imagery, which include image objects that are discrete images of subjects. The image objects may be compiled with other image objects to create an initial image. The initial image may be edited by a user or other person to add more detail, modify subjects, add an additional subject, remove subjects, change attributes, and/or make other changes to the initial image.
    Type: Grant
    Filed: April 22, 2015
    Date of Patent: September 11, 2018
    Assignee: Amazon Technologies, Inc.
    Inventor: Kalidas Yeturu
  • Patent number: 10073838
    Abstract: The present disclosure relates to a method and a system for enabling verifiable semantic rule building for semantic data. In one embodiment, the system enables verification of a semantic rule associated with semantic data based on natural language interpretation of the semantic rule. The system determines the natural language interpretation of the input semantic rule based on a predetermined semantic rule structure stored in a semantic data repository. Upon determining the natural language interpretation, the user may provide one or more inputs to modify the natural language interpretation. Based on the inputs, the system generates a modified natural language interpretation and modified semantic rule thus enabling user verified semantic rule building thereby improving interoperability of decision making processes.
    Type: Grant
    Filed: March 28, 2016
    Date of Patent: September 11, 2018
    Assignee: WIPRO LIMITED
    Inventor: Shishir Kumar
  • Patent number: 10073841
    Abstract: A system comprising a computer-readable storage medium storing at least one program and a computer-implemented method for creating messages using generative grammar models is presented. Consistent with some embodiments, the method may include receiving a request to generate a message, which in an example embodiment is to be published to a social network platform. In response to receiving the request, a generative grammar model defining the structure of the message is accessed. The generative grammar model may include a number of blanks and may specify a source along with a grammatical constraint for a term to populate each blank. The method may further include generating the message in accordance with the generative grammar model, and causing the generated message to be published.
    Type: Grant
    Filed: May 15, 2017
    Date of Patent: September 11, 2018
    Assignee: EBAY INC.
    Inventors: Elizabeth Churchill, Atish Das Sarma, Corinne Elizabeth Sherman, Gyanit Singh
  • Patent number: 10074135
    Abstract: Mechanisms are provided for performing an analysis of content based on a flow of property between entities. The mechanisms analyze a corpus of unstructured documents to identify one or more asset transfer flow relationships between entities. The mechanisms generate an asset transfer flow model defining a flow of an asset between entities based on the one or more asset transfer flow relationships between entities. The mechanisms input the asset transfer flow model into an analysis engine for use in analyzing content. The mechanisms analyze the content using the asset transfer flow model to generate results of the analysis and output the results of the analysis based on the asset transfer flow model.
    Type: Grant
    Filed: March 7, 2016
    Date of Patent: September 11, 2018
    Assignee: International Business Machines Corporation
    Inventors: Donna K. Byron, Duke C. Chang, Leanne N. LeBlanc, Alexander Pikovsky
  • Patent number: 10073827
    Abstract: A method to generate a process flow diagram is disclosed. The method includes receiving a textual description of a process at a remote terminal from an originating user, where the textual description includes one or more activities. The method also includes transmitting the textual description of the process to network servers using a network and analyzing the textual description at the network servers using an analysis module to detect whether there is an error in the textual description of the process. In addition, the method includes generating an annotated textual description according to a set of predefined rules that corrects any known errors that were detected in the textual description and generating a process flow diagram from the annotated textual description using a graph generation module. Further, the method includes transmitting the process flow diagram to the originating user using the network.
    Type: Grant
    Filed: June 7, 2012
    Date of Patent: September 11, 2018
    Inventor: Robert Kevin Houston
  • Patent number: 10073834
    Abstract: There is provided a computer-implemented method for outputting one or more cross-layer patterns to identify a target semantic phenomenon in text, the method comprising: extracting, for each word of at least some words of each training text fragment of training text fragments designated as representing a target semantic phenomenon, feature-values defined by respective layers; statistically analyzing the feature-values identified for the training text fragments to identify one or more cross-layer patterns comprising layers representing a common pattern for the training text fragments, the common cross-layer pattern defining one or more feature-values of a respective layer of one or more words and at least another feature-value of another respective layer of another word; and outputting the identified cross-layer pattern(s) for identifying a text fragment representing the target semantic phenomenon.
    Type: Grant
    Filed: February 9, 2016
    Date of Patent: September 11, 2018
    Assignee: International Business Machines Corporation
    Inventors: Ran Levy, Eyal Shnarch, Noam Slonim
  • Patent number: 10068016
    Abstract: A natural language query is received, and an answer to the natural language query is determined. A message is formatted such that the message includes the answer, and metadata corresponding to the answer, the metadata including information to enable construction, using the metadata, of a sentence that rephrases the query and recites the answer.
    Type: Grant
    Filed: October 17, 2014
    Date of Patent: September 4, 2018
    Assignee: Wolfram Alpha LLC
    Inventors: Stephen Wolfram, Oyvind Tafjord
  • Patent number: 10068104
    Abstract: A facility for performing contingent redaction of one or more portions of a document is described. The facility receives a request to materialize an identified document that identifies an entity for which the identified document is to be materialized. For a portion of the document identified by the request, the facility retrieves a criterion that must be satisfied to include the portion in a materialization of the document identified by the request. The facility evaluates the criterion for the entity identified by the request with respect to a present time. The facility causes the document identified by the request to be materialized for the entity identified by the request in a manner consistent with the result of the evaluation.
    Type: Grant
    Filed: January 29, 2016
    Date of Patent: September 4, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Christopher Lee Mullins, Jonathan Edgar Fay, Robert Earl Standefer, III
  • Patent number: 10067935
    Abstract: Embodiments are directed to a computer implemented counterproductive interaction identification system. The system includes an electronic tool configured to hold data of a user, and an analyzer circuit configured to derive a cognitive trait of the user based at least in part on the data of the user. The system further includes a decision engine configured to determine, based at least in part on the derived cognitive trait of the user, that the user is a target or a source of an actual or an impending counterproductive interaction.
    Type: Grant
    Filed: December 1, 2015
    Date of Patent: September 4, 2018
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Aaron K. Baughman, James R. Kozloski, Timothy M. Lynar, Suraj Pandey, John M. Wagner
  • Patent number: 10061748
    Abstract: According to some embodiments, matrix A data may be loaded into a temporary, unordered starting representation that contains coordinates and values for each element of matrix A. Z-curve ordering of matrix A may be performed to create a two-dimensional density map of matrix A by counting matrix elements that are contained in logical two-dimensional block cells of a given size. A quad-tree recursion may be executed on the two-dimensional density map structure in reduced Z-space to identify areas of different densities in the two dimensional matrix space. An adaptive tile matrix representation of input matrix A may then be created. According to some embodiments, an adaptive tile matrix multiplication operation may perform dynamic tile-granular optimization based on density estimates and a cost model.
    Type: Grant
    Filed: December 11, 2015
    Date of Patent: August 28, 2018
    Assignee: SAP SE
    Inventors: David Kernert, Wolfgang Lehner, Frank Koehler
  • Patent number: 10061838
    Abstract: In an approach to faceted classification, a computer receives a search query. The computer creates a first table of facet value ranges, based on the search query. The computer fetches a first search result corresponding to the search query. The computer retrieves a first facet value associated with the first search result. The computer maps the first facet value to a first facet value range. The computer determines whether the first facet value range is in the first table of facet value ranges. The computer inserts the first facet value range into the first table of facet value ranges. The computer determines whether a number of facet value ranges in the first table of facet value ranges is below a pre-defined threshold. The computer creates a second table of facet value ranges. The computer identifies a second facet value range that includes the first facet value range.
    Type: Grant
    Filed: April 29, 2015
    Date of Patent: August 28, 2018
    Assignee: International Business Machines Corporation
    Inventors: Marta Breno, Roberto Ragusa
  • Patent number: 10063576
    Abstract: Systems, methods, and media for detecting network anomalies are provided. In some embodiments, a training dataset of communication protocol messages having argument strings is received. The content and structure associated with each of the argument strings is determined and a probabilistic model is trained using the determined content and structure of each of the argument strings. A communication protocol message having an argument string that is transmitted from a first processor to a second processor across a computer network is received. The received communication protocol message is compared to the probabilistic model and then it is determined whether the communication protocol message is anomalous.
    Type: Grant
    Filed: December 29, 2015
    Date of Patent: August 28, 2018
    Assignee: The Trustees of Columbia University in the City of New York
    Inventors: Yingbo Song, Angelos D. Keromytis, Salvatore J. Stolfo
  • Patent number: 10055511
    Abstract: According to an embodiment, a search device searches paths of a digraph and includes a retriever, and an expander. The retriever is configured to, from among hypotheses stored in a storage, retrieve, as a target hypothesis, a single hypothesis for which a weight obtained by addition of a weight of an already-searched path corresponding to each hypothesis and a weight of the best path from a state of the head of concerned path to a final state is the best weight. The expander is configured to, when the retrieved target hypothesis is not a final hypothesis for which the search has been completed up to a final state, generate new hypotheses each holding an input symbol string that is present in a path in which the search has been performed from states held by the target hypothesis until finding a single input symbol, and write the generated hypotheses in the storage.
    Type: Grant
    Filed: December 18, 2014
    Date of Patent: August 21, 2018
    Assignee: KABUSHIKI KAISHA TOSHIBA
    Inventor: Manabu Nagao
  • Patent number: 10055410
    Abstract: Corpus-scoped annotation and analysis. Enrichment analysis data is generated including annotations and metadata for a plurality of documents that are part of a corpus. Whether to generate a second set of annotations is determined, based on a correlation of the annotations and metadata. A relational database is populated with the enrichment analysis data. A corpus-scoped query is resolved, initiated by an application, using the enrichment analysis data and content of the corpus.
    Type: Grant
    Filed: September 14, 2017
    Date of Patent: August 21, 2018
    Assignee: International Business Machines Corporation
    Inventors: Joel C. Dubbels, Mark G. Megerian, William C. Rapp
  • Patent number: 10055686
    Abstract: A deep structured semantic module (DSSM) is described herein which uses a model that is discriminatively trained based on click-through data, e.g., such that a conditional likelihood of clicked documents, given respective queries, is maximized, and a condition likelihood of non-clicked documents, given the queries, is reduced. In operation, after training is complete, the DSSM maps an input item into an output item expressed in a semantic space, using the trained model. To facilitate training and runtime operation, a dimensionality-reduction module (DRM) can reduce the dimensionality of the input item that is fed to the DSSM. A search engine may use the above-summarized functionality to convert a query and a plurality of documents into the common semantic space, and then determine the similarity between the query and documents in the semantic space. The search engine may then rank the documents based, at least in part, on the similarity measures.
    Type: Grant
    Filed: July 12, 2016
    Date of Patent: August 21, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Po-Sen Huang, Xiaodong He, Jianfeng Gao, Li Deng, Alejandro Acero, Larry P. Heck
  • Patent number: 10055399
    Abstract: A computer system and method of grammar analysis to generate code for runtime recognition to produce a list or graph representation of multiple lists of directions to be followed for a given sentence during a subsequent parse. The computer system implementing the method to parse grammar to create an intermediate representation, construct a graph for analysis that represents all features of a grammar, including recursion, alternation, grouping of alternatives, and looping, process each decision point in the graph to generate the intermediate representation, generate code for recognition functions that return lists of directions for use in runtime parse decisions, and patch each decision point token to reference or inline a top level recognition code for each decision point.
    Type: Grant
    Filed: July 10, 2015
    Date of Patent: August 21, 2018
    Inventor: Loring G. Craymer, III
  • Patent number: 10057364
    Abstract: A method for remotely running an application program. A client acquires an application program from a server, runs the application program on the client, and detects whether the application program triggers an application programming interface (API) invocation request. If the application program triggers the API invocation request, the client determines that the client or the server executes API invocation according to a preset invocation policy. A device resource of the client can be used to execute a part of the API invocation, which enhances efficiency in remote running of the application program and improves user experience. In addition, the latest data obtained according to a result of application program running can be saved onto the server, which ensures data access security.
    Type: Grant
    Filed: December 7, 2015
    Date of Patent: August 21, 2018
    Assignee: HUAWEI TECHNOLOGIES CO., LTD.
    Inventors: Pu Chen, Kaizhi Wei
  • Patent number: 10055402
    Abstract: A device may obtain text to be analyzed to determine semantic connections between sections of the text. The device may identify subject-verb-object (SVO) units included in the text, and may determine SVO unit information that describes the SVO units. The device may analyze the SVO unit information to determine semantic connection information that identifies one or more semantic connections between two or more of the SVO units. The one or more semantic connections may identify relationships between verbs associated with the two or more of the SVO units. The device may generate a semantic network based on the SVO unit information and the semantic connection information, and may provide information regarding the semantic network.
    Type: Grant
    Filed: March 16, 2015
    Date of Patent: August 21, 2018
    Assignee: Accenture Global Services Limited
    Inventors: Shubhashis Sengupta, Roshni Ramesh Ramnani, Subhabrata Das, Anitha Chandran
  • Patent number: 10049184
    Abstract: A method for communicating data from wearable devices, the method includes sensing data with a wearable sensor worn by an individual and communicating the data from the wearable sensor to an earpiece worn by the individual. The method may further include communicating software instructions for analyzing the data sensed with the wearable sensor from the wearable sensor to the earpiece. An earpiece includes an ear piece housing, a processor disposed within the ear piece housing, a speaker operatively connected to the processor, and a microphone operatively connected to the processor. The earpiece is configured to receive at the processor the software instructions for processing data collected from one or more remotely located sensor devices from the one or more remotely located sensor devices and to process the data according to the software instructions.
    Type: Grant
    Filed: September 29, 2017
    Date of Patent: August 14, 2018
    Inventors: Veniamin Milevski, Peter Vincent Boesen
  • Patent number: 10049666
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for voice recognition. In one aspect, a method includes the actions of receiving a voice input; determining a transcription for the voice input, wherein determining the transcription for the voice input includes, for a plurality of segments of the voice input: obtaining a first candidate transcription for a first segment of the voice input; determining one or more contexts associated with the first candidate transcription; adjusting a respective weight for each of the one or more contexts; and determining a second candidate transcription for a second segment of the voice input based in part on the adjusted weights; and providing the transcription of the plurality of segments of the voice input for output.
    Type: Grant
    Filed: January 6, 2016
    Date of Patent: August 14, 2018
    Assignee: Google LLC
    Inventors: Petar Aleksic, Pedro J. Moreno Mengibar
  • Patent number: 10042921
    Abstract: An embodiment of the invention provides a method for including receiving a natural language query from a user with an interface, and generating multiple dependency parses of the natural language query with a parser device connected to the interface. The generating of the multiple dependency parses includes dividing the natural language query into multiple components, and creating a single dependency parse by connecting each component of the components with at least one other component of the components. A processor connected to the parser device applies rules to all of the multiple dependency parses to identify entities and relations in the natural language query.
    Type: Grant
    Filed: September 18, 2015
    Date of Patent: August 7, 2018
    Assignee: International Business Machines Corporation
    Inventors: Branimir K. Boguraev, Elahe Khorasani, Vadim Sheinin, Siddharth A. Patwardhan, Petros Zerfos
  • Patent number: 10037377
    Abstract: A system for implementing a method that provides information to a user in response to a received user query. A natural language analysis generates substrings relevant to the user query. An ontology analysis outputs: terms of an ontology matching the relevant generated substrings; and relationships between the terms. A query analysis analyzes the user query regarding the outputted terms and relationships, including ascertaining whether the user query is more suitable for service than for an information search. If it is so ascertained, then service actions for the user to perform are identified to the user. If it is not so ascertained, then: the user query is refined based on the outputted terms and relationships; a search query is generated based on the refined user query, a search is initiated based on the search query, and results of the search are provided to the user.
    Type: Grant
    Filed: April 30, 2012
    Date of Patent: July 31, 2018
    Assignee: International Business Machines Corporation
    Inventors: Currie P. Boyle, Homa Javahery, Eniko I. Rozsa, Paul A. Yamamoto
  • Patent number: 10037319
    Abstract: A system for inputting text into an electronic device. The system comprises a candidate generator (2) configured to generate one or more candidates from an input sequence (20). The input sequence (20) comprises a contiguous sequence of characters. Each candidate comprises two or more terms separated by one or more term boundaries. The candidate generator (2) is configured to assign a first probability estimate to each candidate by: searching for one or more terms of that candidate in a context language model, wherein the context language model comprises sequences of terms, each sequence of terms having a corresponding probability of occurring; and assigning the probability corresponding to the one or more terms of that candidate from the context language model to the candidate. The candidate generator (2) is configured to discard one or more candidates on the basis of the corresponding first probability estimates. There is provided a corresponding method of inferring term boundaries in a user input sequence.
    Type: Grant
    Filed: July 25, 2014
    Date of Patent: July 31, 2018
    Assignee: TOUCHTYPE LIMITED
    Inventors: Benjamin William Medlock, Joseph Hayyim Benedict Osbourne
  • Patent number: 10031953
    Abstract: A server receives a query identifying one or more attributes of an entity. The server accesses a set of candidate templates for answering the query based on the one or more attributes of the entity, each candidate template having one or more fields, wherein each field is associated with at least one constraint. The server obtains a set of information that answers the query and selects a template from the set of candidate templates, where the selected template has a maximum number of fields with constraints that are satisfied by the set of information. The server then generates a phrase by adding the set of information to the one or more fields of the selected template, such that the phrase comprises an answer to the query. Finally, the server communicates the phrase to a client device.
    Type: Grant
    Filed: March 14, 2013
    Date of Patent: July 24, 2018
    Assignee: Google LLC
    Inventors: Engin Cinar Sahin, Vinicius J. Fortuna, Emma S. Persky
  • Patent number: 10032448
    Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: determining that one or more word of a feature vector more supports than negates a language model corresponding to the domain based on a sensitivity of respective word. Words having acceptable sensitivities are added to the language model, and the language model is enhanced by use of machine learning in order to accurately and comprehensively model the language specific for the domain.
    Type: Grant
    Filed: January 6, 2017
    Date of Patent: July 24, 2018
    Assignee: International Business Machines Corporation
    Inventors: Aaron K. Baughman, Stephen C. Hammer, Christopher Eythan Holladay, David A. Provan
  • Patent number: 10031952
    Abstract: An approach is provided for automatically ingesting additional corpus based on an interaction history that is mined to identify a question that meets specified answer deficiency criteria, and then generate a second question which is correlated to the first question by requesting additional answer information for answering the first question, where the second question is posted to a forum using a selected persona so that forum responses can be monitored and ingested as additional content in the knowledge base.
    Type: Grant
    Filed: February 24, 2016
    Date of Patent: July 24, 2018
    Assignee: International Business Machines Corporation
    Inventors: Paul R. Bastide, Matthew E. Broomhall, Aaron M. Cohen, Christopher W. Desforges, Carl J. Kraenzel, Robert E. Loredo
  • Patent number: 10026037
    Abstract: Systems and methods for configuring AI algorithms and knowledge sets within an automated messaging system are providing. In some embodiments, a message is received. A subsection of text from the training message is selected. Likewise, a knowledge set is selected. The knowledge set includes probabilistic associations between a term and a category. The terms in the selected subsection of text are compared to the knowledge sets to generate insights and contexts. The insights enable the categorization of the training message. This categorization has an associated confidence value based upon how strongly the terms in the text subsection are associated with the category (per the selected knowledge set). A low confidence value causes the message to be a candidate for training (a training message). Once identified as a training message, it may be displayed to an AI developer for approval or rejection of the categorization.
    Type: Grant
    Filed: January 23, 2015
    Date of Patent: July 17, 2018
    Assignee: CONVERSICA, INC.
    Inventor: Benjamin P. Brigham
  • Patent number: 10027611
    Abstract: Systems and methods for processing a message are provided. A message may be processed to generate a message summary by removing or replacing certain words, phrases, sentences, punctuation, and the like. Message signatures based upon the message summary may be generated and stored in a signature database, which may be used to identify and/or classify spam messages. Subsequently received messages may be classified by signature and processed based on classification.
    Type: Grant
    Filed: March 18, 2016
    Date of Patent: July 17, 2018
    Assignee: SonicWALL Inc.
    Inventors: Jonathan J. Oliver, David A. Koblas, Brian K. Wilson
  • Patent number: 10025774
    Abstract: Methods for developing an ontology of pharmacogenomics (PGx) relationships starting from a lexicon of key pharmacogenomic entities and a syntactic parse is described. The syntactic structure of PGx statements is used to systematically extract commonly occurring relationships and to map them to a common schema. In an embodiment, extracted relationships have a 70-87.7% precision and involve not only key PGx entities such as genes, drugs, and phenotypes (e.g., VKORC1, warfarin, clotting disorder), but also critical entities that are frequently modified by these key entities (e.g., VKORC1 polymorphism, warfarin response, clotting disorder treatment).
    Type: Grant
    Filed: May 26, 2012
    Date of Patent: July 17, 2018
    Assignee: The Board of Trustees of the Leland Stanford Junior University
    Inventors: Adrien Coulet, Nigam H. Shah, Yael Garten, Mark Musen, Russ B. Altman
  • Patent number: 10025878
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for analyzing lineage data. One of the methods includes obtaining data access event information; generating a lineage graph from the data access event information; receiving a data lineage request, wherein the data lineage request is a request for lineage data for a specified data set or a specified software process; traversing the lineage graph to identify nodes and edges in the lineage graph that satisfy the data lineage request; and providing data identifying the nodes and edges that satisfy the data lineage request in response to the request.
    Type: Grant
    Filed: November 11, 2014
    Date of Patent: July 17, 2018
    Assignee: Google LLC
    Inventors: Ryan Michael Lefever, Robbie Alan Haertel, Deborah Weisser, Long Fei, William Eric Province
  • Patent number: 10019512
    Abstract: A method for providing information to a user in response to a received user query. A natural language analysis generates substrings relevant to the user query. An ontology analysis outputs: terms of an ontology matching the relevant generated substrings; and relationships between the terms. A query analysis analyzes the user query regarding the outputted terms and relationships, including ascertaining whether the user query is more suitable for service than for an information search. If it is so ascertained, then service actions for the user to perform are identified to the user. If it is not so ascertained, then: the user query is refined based on the outputted terms and relationships; a search query is generated based on the refined user query, a search is initiated based on the search query, and results of the search are provided to the user.
    Type: Grant
    Filed: April 30, 2012
    Date of Patent: July 10, 2018
    Assignee: International Business Machines Corporation
    Inventors: Currie P. Boyle, Homa Javahery, Eniko I. Rozsa, Paul A. Yamamoto
  • Patent number: 10019437
    Abstract: A method includes receiving one or more natural language dependency parse trees as input. A hardware processor is used for processing the dependency parse trees by creating a mapping from nodes of the one or more dependency parse trees into actions, roles and contextual predicates. The mapping is used for information extraction. The actions include the verbs along with attributes of the verbs. The roles include arguments for the verbs. The contextual predicates include modifiers for the verbs.
    Type: Grant
    Filed: February 23, 2015
    Date of Patent: July 10, 2018
    Assignee: International Business Machines Corporation
    Inventors: Ching-Tien Ho, Benny Kimelfeld, Yunyao Li, Shivakumar Vaithyanathan
  • Patent number: 10019434
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for resolving ambiguity in received voice queries. An original voice query is received following one or more earlier voice queries, wherein the original voice query includes a pronoun or phrase. In one implementation, a plurality of acoustic parameters is identified for one or more words in the original voice query. A concept represented by the pronoun is identified based on the plurality of acoustic parameters, wherein the concept is associated with a particular query of the one or more earlier queries. The concept is associated with the pronoun. Alternatively, a concept may be associated with a phrase by using grammatical analysis of the query to relate the phrase to a concept derived from a prior query.
    Type: Grant
    Filed: December 21, 2016
    Date of Patent: July 10, 2018
    Assignee: Google LLC
    Inventors: Gabriel Taubman, John J. Lee
  • Patent number: 10019435
    Abstract: An example method includes displaying, at a presence-sensitive device, a virtual keyboard, receiving an indication of input entered at a presence-sensitive device indicating a plurality of characters, determining a sequence of at least three character strings in the plurality such that the sequence does not include any space characters, modifying the characters by inserting at least two space characters to demarcate the at least three character strings, and determining at least two suggested character strings based on first, second, and third character strings of the sequence. The method further includes outputting, for display at the presence-sensitive device and at a text-suggestion area of the GUI, the at least two suggested character strings, receiving a selection that indicates a selected character string of the at least two suggested character strings, and outputting, for display at the presence-sensitive device and at the text-entry area of the GUI, the selected character string.
    Type: Grant
    Filed: August 5, 2014
    Date of Patent: July 10, 2018
    Assignee: Google LLC
    Inventors: Yu Ouyang, Shumin Zhai
  • Patent number: 10013410
    Abstract: The present disclosure discloses methods and systems for managing one or more annotations for a host application through an annotation tool. The annotation tool implements a user interface for users to create, store, access, share or display one or more annotations corresponding to a page of the host application. The annotation tool also implements a back-end interface for processing the one or more annotations created by the user. The annotation tool stores the one or more annotations, associates the one or more annotations with the page of the host application, and allows further retrieval of the one or more annotations from any user device.
    Type: Grant
    Filed: July 22, 2016
    Date of Patent: July 3, 2018
    Assignee: CONDUENT BUSINESS SERVICES, LLC
    Inventors: Jayaprakash Ramakrishnan, Jithu Chathukutty, Manoj Rajgarhia
  • Patent number: 10013536
    Abstract: A software license management system may include an activation server that provides permission to activate a software product. The activation server may receive receiving a request to validate activation of the software and refreshing license information for the software in response to the request to validate. The server may additionally receive a request to re-designate the license information for the software product and may update license information for the software in response to the request to re-designate the software product.
    Type: Grant
    Filed: October 7, 2008
    Date of Patent: July 3, 2018
    Assignee: The MathWorks, Inc.
    Inventors: Loren Dean, Linda Cotter, Leslie Mehrez, Gerard McElhinney, John N. Little
  • Patent number: 10013077
    Abstract: Systems, devices, and methods for filtering a plurality of data items according to user input are presented. Each of the data items, such as media content files, is identified via a multiple-character identifier. A collection of individual characters is presented to a user for selection. A character sequence is received from the user, wherein the character sequence includes at least one character selection selected from the collection of individual characters. For each character selection in the sequence, more than one character from the collection is associated with the character selection. The data items are then filtered based on the associated characters corresponding to each character selection.
    Type: Grant
    Filed: May 18, 2011
    Date of Patent: July 3, 2018
    Assignee: DISH Technologies L.L.C.
    Inventors: Luke VanDuyn, Henry Gregg Martch, Morgan Haden Kirby