Patents by Inventor Jayant Madhavan
Jayant Madhavan 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).
-
Publication number: 20240119047Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.Type: ApplicationFiled: October 16, 2023Publication date: April 11, 2024Inventors: Jayant Madhavan, Hongrae Lee, Sreeram Viswanath Balakrishnan, Warren H.Y. Shen
-
Patent number: 11900068Abstract: At least selectively utilizing a large language model (LLM) in generating a natural language (NL) based summary to be rendered in response to a query. In some implementations, in generating the NL based summary additional content is processed using the LLM. The additional content is in addition to query content of the query itself and, in generating the NL based summary, can be processed using the LLM and along with the query content—or even independent of the query content. Processing the additional content can, for example, mitigate occurrences of the NL based summary including inaccuracies and/or can mitigate occurrences of the NL based summary being over-specified and/or under-specified.Type: GrantFiled: August 9, 2023Date of Patent: February 13, 2024Assignee: GOOGLE LLCInventors: Matthew K. Gray, John Blitzer, Corinn Herrick, Srinivasan Venkatachary, Jayant Madhavan, Sam Oates, Phiroze Parakh, Aditya Shah, Mahsan Rofouei, Ibrahim Badr
-
Patent number: 11886828Abstract: At least selectively utilizing a large language model (LLM) in generating a natural language (NL) based summary to be rendered in response to a query. In some implementations, in generating the NL based summary additional content is processed using the LLM. The additional content is in addition to query content of the query itself and, in generating the NL based summary, can be processed using the LLM and along with the query content—or even independent of the query content. Processing the additional content can, for example, mitigate occurrences of the NL based summary including inaccuracies and/or can mitigate occurrences of the NL based summary being over-specified and/or under-specified.Type: GrantFiled: August 22, 2023Date of Patent: January 30, 2024Assignee: GOOGLE LLCInventors: Matthew K. Gray, John Blitzer, Corinn Herrick, Srinivasan Venkatachary, Jayant Madhavan, Sam Oates, Phiroze Parakh, Aditya Shah, Mahsan Rofouei, Ibrahim Badr
-
Publication number: 20230342411Abstract: Techniques of generating short answers for queries by a search engine include performing a training operation on a corpus of training data to train the score prediction engine, the corpus of training data including candidate passages providing short answers for display in callouts and remaining respective passages, from which a top scoring short answer is generated. In such implementations, the corpus of training data further includes the remaining respective passages and the respective titles of the candidate passage and remaining respective passages.Type: ApplicationFiled: March 9, 2022Publication date: October 26, 2023Inventors: Preyas Dalsukhbhai Popat, Gaurav Bhaskar Gite, John Blitzer, Jayant Madhavan, Aliaksei Severyn
-
Patent number: 11789946Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.Type: GrantFiled: February 14, 2022Date of Patent: October 17, 2023Assignee: GOOGLE LLCInventors: Jayant Madhavan, Hongrae Lee, Sreeram Viswanath Balakrishnan, Warren H. Y. Shen
-
Patent number: 11769017Abstract: At least selectively utilizing a large language model (LLM) in generating a natural language (NL) based summary to be rendered in response to a query. In some implementations, in generating the NL based summary additional content is processed using the LLM. The additional content is in addition to query content of the query itself and, in generating the NL based summary, can be processed using the LLM and along with the query content—or even independent of the query content. Processing the additional content can, for example, mitigate occurrences of the NL based summary including inaccuracies and/or can mitigate occurrences of the NL based summary being over-specified and/or under-specified.Type: GrantFiled: March 20, 2023Date of Patent: September 26, 2023Assignee: GOOGLE LLCInventors: Matthew K. Gray, John Blitzer, Corinn Herrick, Srinivasan Venkatachary, Jayant Madhavan, Sam Oates, Phiroze Parakh, Aditya Shah, Mahsan Rofouei, Ibrahim Badr
-
Publication number: 20220171779Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.Type: ApplicationFiled: February 14, 2022Publication date: June 2, 2022Inventors: Jayant Madhavan, Hongrae Lee, Sreeram Viswanath Balakrishnan, Warren H.Y. Shen
-
Patent number: 11249993Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.Type: GrantFiled: May 22, 2020Date of Patent: February 15, 2022Assignee: GOOGLE LLCInventors: Jayant Madhavan, Hongrae Lee, Warren H. Y. Shen, Sreeram Viswanath Balakrishnan
-
Publication number: 20200293529Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.Type: ApplicationFiled: May 22, 2020Publication date: September 17, 2020Inventors: Jayant Madhavan, Hongrae Lee, Warren H. Y. Shen, Sreeram Viswanath Balakrishnan
-
Patent number: 10698888Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.Type: GrantFiled: January 26, 2018Date of Patent: June 30, 2020Assignee: Google LLCInventors: Jayant Madhavan, Hongrae Lee, Warren H. Y. Shen, Sreeram Viswanath Balakrishnan
-
Publication number: 20190065502Abstract: Methods and apparatus determining features related to a table of a document and/or providing information related to a table of a document in response to a search query. Some implementations are directed generally to determining an ordered collection of information that is responsive to search query terms, wherein the ordered collection of information is based at least in part on content of a table of a document that is responsive to the search query terms. Some implementations are directed generally to determining a table of a document includes an ordered collection of information and determining one or more features of the table.Type: ApplicationFiled: April 21, 2015Publication date: February 28, 2019Inventors: Hongrae Lee, Jayant Madhavan, Yuliang Li
-
Patent number: 9916348Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.Type: GrantFiled: August 12, 2015Date of Patent: March 13, 2018Assignee: Google LLCInventors: Jayant Madhavan, Hongrae Lee, Warren H. Y. Shen, Sreeram Viswanath Balakrishnan
-
Patent number: 9582766Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for clustering query refinements. One method includes building a representation of a graph for a first query, wherein the graph has a node for the first query, a node for each of a plurality of refinements for the first query, and a node for each document in the document sets of the refinements, and wherein the graph has edges from the first query node to each of the refinement nodes, edges from the first query to each document in the respective document set of the first query, edges from each refinement to each document in the respective document set of the refinement, and edges from each refinement to each co-occurring query of the refinement. The method further includes clustering the refinements into refinement clusters by partitioning the refinement nodes in the graph into proper subsets.Type: GrantFiled: March 21, 2016Date of Patent: February 28, 2017Assignee: Google Inc.Inventors: Eldar Sadikov, Jayant Madhavan, Alon Yitzchak Halevy
-
Publication number: 20160203411Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for clustering query refinements. One method includes building a representation of a graph for a first query, wherein the graph has a node for the first query, a node for each of a plurality of refinements for the first query, and a node for each document in the document sets of the refinements, and wherein the graph has edges from the first query node to each of the refinement nodes, edges from the first query to each document in the respective document set of the first query, edges from each refinement to each document in the respective document set of the refinement, and edges from each refinement to each co-occurring query of the refinement. The method further includes clustering the refinements into refinement clusters by partitioning the refinement nodes in the graph into proper subsets.Type: ApplicationFiled: March 21, 2016Publication date: July 14, 2016Inventors: Eldar Sadikov, Jayant Madhavan, Alon Yitzchak Halevy
-
Patent number: 9323806Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for clustering query refinements. One method includes building a representation of a graph for a first query, wherein the graph has a node for the first query, a node for each of a plurality of refinements for the first query, and a node for each document in the document sets of the refinements, and wherein the graph has edges from the first query node to each of the refinement nodes, edges from the first query to each document in the respective document set of the first query, edges from each refinement to each document in the respective document set of the refinement, and edges from each refinement to each co-occurring query of the refinement. The method further includes clustering the refinements into refinement clusters by partitioning the refinement nodes in the graph into proper subsets.Type: GrantFiled: April 1, 2013Date of Patent: April 26, 2016Assignee: Google Inc.Inventors: Eldar Sadikov, Jayant Madhavan, Alon Halevy
-
Publication number: 20160026696Abstract: Methods, systems, and apparatus, including computer program products, for generating aspects associated with entities. In some implementations, a method includes receiving data identifying an entity; generating a group of candidate aspects for the entity; modifying the group of candidate aspects to generate a group of modified candidate aspects comprising combining similar candidate aspects and grouping candidate aspects using one or more aspect classes each associated with one or more candidate aspects; ranking one or more modified candidate aspects in the group of modified candidate aspects based on a diversity score and a popularity score; and storing an association between one or more highest ranked modified candidate aspects and the entity. The aspects can be used to organize and present search results in response to queries for the entity.Type: ApplicationFiled: October 5, 2015Publication date: January 28, 2016Inventors: Jayant Madhavan, Fei Wu, Alon Yitzchak Halevy
-
Patent number: 9152676Abstract: Methods, systems, and apparatus, including computer program products, for generating aspects associated with entities. In some implementations, a method includes receiving data identifying an entity; generating a group of candidate aspects for the entity; modifying the group of candidate aspects to generate a group of modified candidate aspects comprising combining similar candidate aspects and grouping candidate aspects using one or more aspect classes each associated with one or more candidate aspects; ranking one or more modified candidate aspects in the group of modified candidate aspects based on a diversity score and a popularity score; and storing an association between one or more highest ranked modified candidate aspects and the entity. The aspects can be used to organize and present search results in response to queries for the entity.Type: GrantFiled: June 3, 2013Date of Patent: October 6, 2015Assignee: GOOGLE INC.Inventors: Jayant Madhavan, Fei Wu, Alon Yitzchak Halevy
-
Patent number: 9116940Abstract: Systems and techniques are provided for receiving an input column and a search keyword and providing one or more suggested columns with which to merge the input column. A coverage score and a refinity score are calculated for potential columns based on the input column as well as a search score based on the search keyword. The one or more suggested columns may be determined based on the coverage score, refinity score, and/or the search score. The input column and/or a potential column may be modified based on a function and the modification may result in a plurality of modified input and/or potential columns. Coverage, refinity, and search scores may be calculated based on the modified columns.Type: GrantFiled: April 15, 2013Date of Patent: August 25, 2015Assignee: Google Inc.Inventors: Nitin Gupta, Alon Yitzchak Halevy, Jayant Madhavan, Tuan Anh Cao, Sreeram Balakrishnan
-
Patent number: 9098530Abstract: Aspects of the invention provide a service for data management and integration across a wide range of applications. Clustered computers may be arranged in a cloud-type configuration for storing and handling large amounts of user data under the control of a front-end management server. Communities of distributed users may collaborate on the data across multiple enterprises. Very large tabular data files are uploaded to the storage facilities. The data files are maintained as tables, and a composite table of related information is created and maintained in response to user queries. Different ways of visualizing the data are provided. Depending on the amount of information that can be displayed, features in a spatial index may the thinned for presentation. Spatial and structured queries are processing and results are intersected to obtain information for display.Type: GrantFiled: November 14, 2013Date of Patent: August 4, 2015Assignee: Google Inc.Inventors: Hector Gonzalez, Jayant Madhavan, Andrin Von Rechenberg, Anno Langen, Alon Halevy
-
Publication number: 20150161201Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for clustering query refinements. One method includes building a representation of a graph for a first query, wherein the graph has a node for the first query, a node for each of a plurality of refinements for the first query, and a node for each document in the document sets of the refinements, and wherein the graph has edges from the first query node to each of the refinement nodes, edges from the first query to each document in the respective document set of the first query, edges from each refinement to each document in the respective document set of the refinement, and edges from each refinement to each co-occurring query of the refinement. The method further includes clustering the refinements into refinement clusters by partitioning the refinement nodes in the graph into proper subsets.Type: ApplicationFiled: April 1, 2013Publication date: June 11, 2015Applicant: Google Inc.Inventors: Eldar Sadikov, Jayant Madhavan, Alon Halevy