Patents by Inventor Pranav Khaitan
Pranav Khaitan 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: 11714857Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining, for each of one or more categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active during processing of inputs by a machine learning model. In one aspect, a method comprises: generating a batch of output sequences, each output sequence in the batch specifying, for each of the categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active; for each output sequence in the batch, determining a performance metric of the machine learning model on a machine learning task after the machine learning model has been trained to perform the machine learning task with only the respective vocabulary of categorical feature values of each categorical feature specified by the output sequence being active.Type: GrantFiled: December 7, 2022Date of Patent: August 1, 2023Assignee: Google LLCInventors: Cong Li, Jay Adams, Manas Joglekar, Pranav Khaitan, Quoc V. Le, Mei Chen
-
Publication number: 20230146053Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining, for each of one or more categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active during processing of inputs by a machine learning model. In one aspect, a method comprises: generating a batch of output sequences, each output sequence in the batch specifying, for each of the categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active; for each output sequence in the batch, determining a performance metric of the machine learning model on a machine learning task after the machine learning model has been trained to perform the machine learning task with only the respective vocabulary of categorical feature values of each categorical feature specified by the output sequence being active.Type: ApplicationFiled: December 7, 2022Publication date: May 11, 2023Inventors: Cong Li, Jay Adams, Manas Joglekar, Pranav Khaitan, Quoc V. Le, Mei Chen
-
Patent number: 11551159Abstract: Generally, the present disclosure is directed to systems and methods for performing task-oriented response generation that can provide advantages for artificial intelligence systems or other computing systems that include natural language processing for interpreting user input. Example implementations can process natural language descriptions of various services that can be accessed by the system. In response to a natural language input, systems can identify relevant values for executing one of the service(s), based in part on comparing embedded representations of the natural language input and the natural language description using a machine learned model.Type: GrantFiled: December 23, 2019Date of Patent: January 10, 2023Assignee: GOOGLE LLCInventors: Abhinav Kumar Rastogi, Raghav Gupta, Xiaoxue Zang, Srinivas Kumar Sunkara, Pranav Khaitan
-
Patent number: 11537664Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining, for each of one or more categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active during processing of inputs by a machine learning model. In one aspect, a method comprises: generating a batch of output sequences, each output sequence in the batch specifying, for each of the categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active; for each output sequence in the batch, determining a performance metric of the machine learning model on a machine learning task after the machine learning model has been trained to perform the machine learning task with only the respective vocabulary of categorical feature values of each categorical feature specified by the output sequence being active.Type: GrantFiled: May 20, 2020Date of Patent: December 27, 2022Assignee: Google LLCInventors: Cong Li, Jay Adams, Manas Joglekar, Pranav Khaitan, Quoc V. Le, Mei Chen
-
Patent number: 11418471Abstract: A system and method for identifying an entity from a message exchange thread and generating a suggestion that is directed to the entity, such as a suggestion for a user to take an action on the entity. A suggestion application receives at least one electronic message from a message exchange thread, identifies an entity that can be actionable from the electronic message, determines contextual indicators of the entity, determines whether the entity is actionable based on the contextual indicators, and responsive to the entity being actionable, provides a suggestion that is directed to the entity to a participant(s) of the message exchange thread.Type: GrantFiled: November 22, 2019Date of Patent: August 16, 2022Assignee: Google LLCInventors: Timothy Seeds Milligan, Hila Shemer, Dennis Kiilerich, Gang Ji, Ori Gershony, Sergey Nazarov, Pranav Khaitan, Sushant Prakash, Anton Volkov, Ricardo Escutia, David Citron
-
Patent number: 11397784Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving user-specific content, the user-specific content being associated with a user of one or more computer-implemented services, processing the user-specific content using one or more parsers to identify one or more entities and one or more relationships between entities, a parser being specific to a schema, and the one or more entities and the one or more relationships between entities being identified based on the schema, providing one or more user-specific knowledge graphs, a user-specific knowledge graph being specific to the user and including nodes and edges between nodes to define relationships between entities based on the schema, and storing the one or more user-specific knowledge graphs.Type: GrantFiled: August 14, 2019Date of Patent: July 26, 2022Assignee: GOOGLE LLCInventors: Pranav Khaitan, Shobha Diwakar
-
Publication number: 20210192397Abstract: Generally, the present disclosure is directed to systems and methods for performing task-oriented response generation that can provide advantages for artificial intelligence systems or other computing systems that include natural language processing for interpreting user input. Example implementations can process natural language descriptions of various services that can be accessed by the system. In response to a natural language input, systems can identify relevant values for executing one of the service(s), based in part on comparing embedded representations of the natural language input and the natural language description using a machine learned model.Type: ApplicationFiled: December 23, 2019Publication date: June 24, 2021Inventors: Abhinav Kumar Rastogi, Raghav Gupta, Xiaoxue Zang, Srinivas Kumar Sunkara, Pranav Khaitan
-
Publication number: 20200372076Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining, for each of one or more categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active during processing of inputs by a machine learning model. In one aspect, a method comprises: generating a batch of output sequences, each output sequence in the batch specifying, for each of the categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active; for each output sequence in the batch, determining a performance metric of the machine learning model on a machine learning task after the machine learning model has been trained to perform the machine learning task with only the respective vocabulary of categorical feature values of each categorical feature specified by the output sequence being active.Type: ApplicationFiled: May 20, 2020Publication date: November 26, 2020Inventors: Cong Li, Jay Adams, Manas Joglekar, Pranav Khaitan, Quoc V. Le, Mei Chen
-
Patent number: 10803391Abstract: Systems and methods are provided for a personal entity modeling for computing devices. For example, a computing device comprises at least one processor and memory storing instructions that, when executed by the at least one processor, cause the mobile device to perform operations including identifying a personal entity in content generated for display on the mobile device, generating training examples for the personal entity from the content, and updating an embedding used to model the personal entity using the training examples. The embedding may be used to make predictions regarding the personal entity. For example, the operations may also include predicting an association between a first personal entity displayed on the computing device and a second entity based on the embedding, and providing a recommendation, to be displayed on the computing device, related to the second entity.Type: GrantFiled: July 29, 2015Date of Patent: October 13, 2020Assignee: GOOGLE LLCInventors: Matthew Sharifi, David Petrou, Pranav Khaitan
-
Publication number: 20200092243Abstract: A system and method for identifying an entity from a message exchange thread and generating a suggestion that is directed to the entity, such as a suggestion for a user to take an action on the entity. A suggestion application receives at least one electronic message from a message exchange thread, identifies an entity that can be actionable from the electronic message, determines contextual indicators of the entity, determines whether the entity is actionable based on the contextual indicators, and responsive to the entity being actionable, provides a suggestion that is directed to the entity to a participant(s) of the message exchange thread.Type: ApplicationFiled: November 22, 2019Publication date: March 19, 2020Applicant: Google LLCInventors: Timothy Seeds MILLIGAN, Hila SHEMER, Dennis KIILERICH, Gang JI, Ori GERSHONY, Sergey NAZAROV, Pranav KHAITAN, Sushant PRAKASH, Anton VOLKOV, Ricardo ESCUTIA, David CITRON
-
Patent number: 10530723Abstract: A system and method for identifying an entity from a message exchange thread and generating a suggestion that is directed to the entity, such as a suggestion for a user to take an action on the entity. A suggestion application receives at least one electronic message from a message exchange thread, identifies an entity that can be actionable from the electronic message, determines contextual indicators of the entity, determines whether the entity is actionable based on the contextual indicators, and responsive to the entity being actionable, provides a suggestion that is directed to the entity to a participant(s) of the message exchange thread.Type: GrantFiled: December 21, 2016Date of Patent: January 7, 2020Assignee: Google LLCInventors: Timothy Seeds Milligan, Hila Shemer, Dennis Kiilerich, Gang Ji, Ori Gershony, Sergey Nazarov, Pranav Khaitan, Sushant Prakash, Anton Volkov, Ricardo Escutia, David Citron
-
Publication number: 20190370302Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving user-specific content, the user-specific content being associated with a user of one or more computer-implemented services, processing the user-specific content using one or more parsers to identify one or more entities and one or more relationships between entities, a parser being specific to a schema, and the one or more entities and the one or more relationships between entities being identified based on the schema, providing one or more user-specific knowledge graphs, a user-specific knowledge graph being specific to the user and including nodes and edges between nodes to define relationships between entities based on the schema, and storing the one or more user-specific knowledge graphs.Type: ApplicationFiled: August 14, 2019Publication date: December 5, 2019Inventors: Pranav Khaitan, Shobha Diwakar
-
Patent number: 10482139Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving user-specific content, the user-specific content being associated with a user of one or more computer-implemented services, processing the user-specific content using one or more parsers to identify one or more entities and one or more relationships between entities, a parser being specific to a schema, and the one or more entities and the one or more relationships between entities being identified based on the schema, providing one or more user-specific knowledge graphs, a user-specific knowledge graph being specific to the user and including nodes and edges between nodes to define relationships between entities based on the schema, and storing the one or more user-specific knowledge graphs.Type: GrantFiled: November 5, 2013Date of Patent: November 19, 2019Assignee: Google LLCInventors: Pranav Khaitan, Shobha Diwakar
-
Publication number: 20170180294Abstract: A system and method for identifying an entity from a message exchange thread and generating a suggestion that is directed to the entity, such as a suggestion for a user to take an action on the entity. A suggestion application receives at least one electronic message from a message exchange thread, identifies an entity that can be actionable from the electronic message, determines contextual indicators of the entity, determines whether the entity is actionable based on the contextual indicators, and responsive to the entity being actionable, provides a suggestion that is directed to the entity to a participant(s) of the message exchange thread.Type: ApplicationFiled: December 21, 2016Publication date: June 22, 2017Inventors: Timothy Seeds Milligan, Hila Shemer, Dennis Kiilerich, Gang Ji, Ori Gershony, Sergey Nazarov, Pranav Khaitan, Sushant Prakash, Anton Volkov, Ricardo Escutia, David Citron
-
Publication number: 20170032257Abstract: Systems and methods are provided for a personal entity modeling for computing devices. For example, a computing device comprises at least one processor and memory storing instructions that, when executed by the at least one processor, cause the mobile device to perform operations including identifying a personal entity in content generated for display on the mobile device, generating training examples for the personal entity from the content, and updating an embedding used to model the personal entity using the training examples. The embedding may be used to make predictions regarding the personal entity. For example, the operations may also include predicting an association between a first personal entity displayed on the computing device and a second entity based on the embedding, and providing a recommendation, to be displayed on the computing device, related to the second entity.Type: ApplicationFiled: July 29, 2015Publication date: February 2, 2017Inventors: Matthew SHARIFI, David PETROU, Pranav KHAITAN
-
Publication number: 20160292299Abstract: Methods and apparatus for determining and inferring user attributes based on detected user activity are presented. A first user attribute may be determined based on first activity of a user. A second user attribute related to the first user attribute may be inferred. A third user attribute may be determined based on second activity of the user that occurs after the first activity. A confidence associated with the second user attribute may be altered in response to a determination that the third user attribute is related to the second user attribute.Type: ApplicationFiled: January 29, 2014Publication date: October 6, 2016Applicant: Google Inc.Inventors: Shobha Diwakar, Pranav Khaitan
-
Patent number: 9083696Abstract: A system for providing a trusted peer-based information verification system may include one or more processors and a memory. The one or more processors may facilitate steps of receiving an identification item from a server hosting a web site and providing a request for verification of the identification item to devices of trusted peers. The steps may further include receiving verification responses from the devices of the trusted peers. The verification responses may be indicative of whether identification items received by the devices of the trusted peers via the web site are different than the identification item received from the server hosting the web site. The steps may further include determining a validity of the identification item based on the verification responses received from the devices of the trusted peers. In one example the identification item may be a digital certificate, such as a public key certificate.Type: GrantFiled: May 30, 2012Date of Patent: July 14, 2015Assignee: Google Inc.Inventor: Pranav Khaitan
-
Publication number: 20150127632Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving user-specific content, the user-specific content being associated with a user of one or more computer-implemented services, processing the user-specific content using one or more parsers to identify one or more entities and one or more relationships between entities, a parser being specific to a schema, and the one or more entities and the one or more relationships between entities being identified based on the schema, providing one or more user-specific knowledge graphs, a user-specific knowledge graph being specific to the user and including nodes and edges between nodes to define relationships between entities based on the schema, and storing the one or more user-specific knowledge graphs.Type: ApplicationFiled: November 5, 2013Publication date: May 7, 2015Applicant: Google Inc.Inventors: Pranav Khaitan, Shobha Diwakar