Patents by Inventor Nirav P Desai
Nirav P Desai has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 10628413Abstract: An approach is provided in which a knowledge manager identifies training entities in a training question answer pair and identifies database paths a database that link the training entities. The knowledge manager then generates a generalized query based upon the identified database paths. In addition, the knowledge manager generates a generalized syntactic pattern based upon syntactic relationships between the training entities in the training question answer pair. When the knowledge manager receives a question and matches the syntactic pattern of the received question to the generalized syntactic pattern, the knowledge manager generates a custom query from the generalized query and queries the database using the custom query.Type: GrantFiled: August 3, 2015Date of Patent: April 21, 2020Assignee: International Business Machines CorporationInventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
-
Patent number: 10628521Abstract: An approach is provided in which a knowledge manager identifies training entities in a training question answer pair and identifies multiple database paths a database that link the training entities. The knowledge manager then generates multiple generalized queries based upon the identified multiple database paths and assigns query scores to the multiple generalized queries. In addition, the knowledge manager generates a generalized syntactic pattern based upon syntactic relationships between the training entities in the training question answer pair. When the knowledge manager receives a question and matches the syntactic pattern of the received question to the generalized syntactic pattern, the knowledge manager generates custom queries from the generalized queries and queries the database using the custom queries. The knowledge manager, in turn, scores answers generated from the custom queries based upon the custom queries' corresponding query scores.Type: GrantFiled: August 3, 2015Date of Patent: April 21, 2020Assignee: International Business Machines CorporationInventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
-
Patent number: 10229156Abstract: An approach is provided in which a knowledge manager matches a question to multiple natural language contexts that each correspond to relations associated with entities in a structured resource. The knowledge manager identifies database queries corresponding to the multiple natural language contexts and assigns priority scores to the database queries based upon their relative specificity. In turn, the knowledge manager invokes one of the database queries based upon the assigned priority scores.Type: GrantFiled: November 3, 2014Date of Patent: March 12, 2019Assignee: International Business Machines CorporationInventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
-
Patent number: 10176228Abstract: An approach is provided in which a knowledge manager receives a question and selects candidate answers based upon a lexical answer type included in the question. The knowledge manager evaluates the candidate answers against conditions detected in the question and generates condition fulfillment scores accordingly. In turn, the knowledge manager ranks the candidate answers based upon the corresponding condition fulfillment scores.Type: GrantFiled: December 10, 2014Date of Patent: January 8, 2019Assignee: International Business Machines CorporationInventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
-
Patent number: 10108661Abstract: 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: GrantFiled: September 20, 2015Date of Patent: October 23, 2018Assignee: International Business Machines CorporationInventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
-
Patent number: 10095736Abstract: 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: GrantFiled: November 3, 2014Date of Patent: October 9, 2018Assignee: International Business Machines CorporationInventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
-
Patent number: 9946708Abstract: One or more words are received. A set of frequency of occurrence values of the received word(s) within a set of domain tables is determined. A domain table in the set of domain tables is associated to the received word(s), based on the set of frequency of occurrence values meeting a threshold value. A word-sense of the received word(s) is determined based on a corresponding word-sense in the associated domain table and/or corresponding domain dictionary.Type: GrantFiled: January 12, 2017Date of Patent: April 17, 2018Assignee: International Business Machines CorporationInventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
-
Patent number: 9946709Abstract: One or more words are received. A set of frequency of occurrence values of the received word(s) within a set of domain tables is determined. A domain table in the set of domain tables is associated to the received word(s), based on the set of frequency of occurrence values meeting a threshold value. A word-sense of the received word(s) is determined based on a corresponding word-sense in the associated domain table and/or corresponding domain dictionary.Type: GrantFiled: January 12, 2017Date of Patent: April 17, 2018Assignee: International Business Machines CorporationInventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
-
Patent number: 9910890Abstract: An approach is provided in which a knowledge manager analyzes parent/child hierarchies between semi-structured items included in a semi-structured resource. The knowledge manager generates synthetic events based upon the parent/child hierarchy analysis and creates a structured resource utilizing the synthetic events. In one embodiment, the structured resource includes structured resource entries, which include a first semi-structured item, a second semi-structured item, and one of the synthetic events. In turn, the knowledge manager queries the structured resource based upon a question received from a user interface.Type: GrantFiled: June 15, 2015Date of Patent: March 6, 2018Assignee: International Business Machines CorporationInventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
-
Patent number: 9767000Abstract: An environment and techniques for intelligently selecting which tests of multiple different tests to run on a particular section or sections of code, such as one or more lines of code that a developer has altered, are described herein. In this manner, the techniques may allow developers to receive feedback on their software more quickly by running a subset of tests, rather than each test in a predefined set of tests.Type: GrantFiled: September 20, 2010Date of Patent: September 19, 2017Assignee: Amazon Technologies, Inc.Inventors: Suzuko Chida, Nirav P Desai, Ravikumar Makam, Kyung Deuk Park, Kyle Andrew Farrell, Michael C. Moore
-
Publication number: 20170139901Abstract: One or more words are received. A set of frequency of occurrence values of the received word(s) within a set of domain tables is determined. A domain table in the set of domain tables is associated to the received word(s), based on the set of frequency of occurrence values meeting a threshold value. A word-sense of the received word(s) is determined based on a corresponding word-sense in the associated domain table and/or corresponding domain dictionary.Type: ApplicationFiled: January 12, 2017Publication date: May 18, 2017Inventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
-
Publication number: 20170124068Abstract: One or more words are received. A set of frequency of occurrence values of the received word(s) within a set of domain tables is determined. A domain table in the set of domain tables is associated to the received word(s), based on the set of frequency of occurrence values meeting a threshold value. A word-sense of the received word(s) is determined based on a corresponding word-sense in the associated domain table and/or corresponding domain dictionary.Type: ApplicationFiled: January 12, 2017Publication date: May 4, 2017Inventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
-
Patent number: 9619850Abstract: One or more words are received. A set of frequency of occurrence values of the received word(s) within a set of domain tables is determined. A domain table in the set of domain tables is associated to the received word(s), based on the set of frequency of occurrence values meeting a threshold value. A word-sense of the received word(s) is determined based on a corresponding word-sense in the associated domain table and/or corresponding domain dictionary.Type: GrantFiled: September 13, 2016Date of Patent: April 11, 2017Assignee: International Business Machines CorporationInventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
-
Patent number: 9619460Abstract: One or more words are received. A set of frequency of occurrence values of the received word(s) within a set of domain tables is determined. A domain table in the set of domain tables is associated to the received word(s), based on the set of frequency of occurrence values meeting a threshold value. A word-sense of the received word(s) is determined based on a corresponding word-sense in the associated domain table and/or corresponding domain dictionary.Type: GrantFiled: September 23, 2016Date of Patent: April 11, 2017Assignee: International Business Machines CorporationInventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
-
Patent number: 9594746Abstract: One or more words are received. A set of frequency of occurrence values of the received word(s) within a set of domain tables is determined. A domain table in the set of domain tables is associated to the received word(s), based on the set of frequency of occurrence values meeting a threshold value. A word-sense of the received word(s) is determined based on a corresponding word-sense in the associated domain table and/or corresponding domain dictionary.Type: GrantFiled: February 13, 2015Date of Patent: March 14, 2017Assignee: International Business Machines CorporationInventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
-
Publication number: 20170039482Abstract: An approach is provided in which a knowledge manager identifies training entities in a training question answer pair and identifies database paths a database that link the training entities. The knowledge manager then generates a generalized query based upon the identified database paths. In addition, the knowledge manager generates a generalized syntactic pattern based upon syntactic relationships between the training entities in the training question answer pair. When the knowledge manager receives a question and matches the syntactic pattern of the received question to the generalized syntactic pattern, the knowledge manager generates a custom query from the generalized query and queries the database using the custom query.Type: ApplicationFiled: August 3, 2015Publication date: February 9, 2017Inventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
-
Publication number: 20170039271Abstract: An approach is provided in which a knowledge manager identifies training entities in a training question answer pair and identifies multiple database paths a database that link the training entities. The knowledge manager then generates multiple generalized queries based upon the identified multiple database paths and assigns query scores to the multiple generalized queries. In addition, the knowledge manager generates a generalized syntactic pattern based upon syntactic relationships between the training entities in the training question answer pair. When the knowledge manager receives a question and matches the syntactic pattern of the received question to the generalized syntactic pattern, the knowledge manager generates custom queries from the generalized queries and queries the database using the custom queries. The knowledge manager, in turn, scores answers generated from the custom queries based upon the custom queries' corresponding query scores.Type: ApplicationFiled: August 3, 2015Publication date: February 9, 2017Inventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
-
Publication number: 20170004130Abstract: One or more words are received. A set of frequency of occurrence values of the received word(s) within a set of domain tables is determined. A domain table in the set of domain tables is associated to the received word(s), based on the set of frequency of occurrence values meeting a threshold value. A word-sense of the received word(s) is determined based on a corresponding word-sense in the associated domain table and/or corresponding domain dictionary.Type: ApplicationFiled: September 23, 2016Publication date: January 5, 2017Inventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
-
Publication number: 20160371806Abstract: One or more words are received. A set of frequency of occurrence values of the received word(s) within a set of domain tables is determined. A domain table in the set of domain tables is associated to the received word(s), based on the set of frequency of occurrence values meeting a threshold value. A word-sense of the received word(s) is determined based on a corresponding word-sense in the associated domain table and/or corresponding domain dictionary.Type: ApplicationFiled: September 13, 2016Publication date: December 22, 2016Inventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier
-
Publication number: 20160364500Abstract: An approach is provided in which a knowledge manager analyzes parent/child hierarchies between semi-structured items included in a semi-structured resource. The knowledge manager generates synthetic events based upon the parent/child hierarchy analysis and creates a structured resource utilizing the synthetic events. In one embodiment, the structured resource includes structured resource entries, which include a first semi-structured item, a second semi-structured item, and one of the synthetic events. In turn, the knowledge manager queries the structured resource based upon a question received from a user interface.Type: ApplicationFiled: June 15, 2015Publication date: December 15, 2016Inventors: Timothy A. Bishop, Stephen A. Boxwell, Benjamin L. Brumfield, Nirav P. Desai, Stanley J. Vernier