Patents by Inventor Rahul Kumar Jha

Rahul Kumar Jha 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: 20240038220
    Abstract: A computer-implemented technique is described herein for expediting a user's interaction with a digital assistant. In one implementation, the technique involves receiving a system prompt generated by a digital assistant in response to an input command provided by a user via an input device. The technique then generates a predicted response based on linguistic content of the system prompt, together with contextual features pertaining to a circumstance in which the system prompt was issued. The predicted response corresponds to a prediction of how the user will respond to the system prompt. The technique then selects one or more dialogue actions from a plurality of dialogue actions, based on a confidence value associated with the predicted response. The technique expedites the user's interaction with the digital assistant by reducing the number of system prompts that the user is asked to respond to.
    Type: Application
    Filed: October 9, 2023
    Publication date: February 1, 2024
    Inventors: Vipul AGARWAL, Rahul Kumar JHA, Soumya BATRA, Karthik TANGIRALA, Mohammad MAKARECHIAN, Imed ZITOUNI
  • Patent number: 11823661
    Abstract: A computer-implemented technique is described herein for expediting a user's interaction with a digital assistant. In one implementation, the technique involves receiving a system prompt generated by a digital assistant in response to an input command provided by a user via an input device. The technique then generates a predicted response based on linguistic content of the system prompt, together with contextual features pertaining to a circumstance in which the system prompt was issued. The predicted response corresponds to a prediction of how the user will respond to the system prompt. The technique then selects one or more dialogue actions from a plurality of dialogue actions, based on a confidence value associated with the predicted response. The technique expedites the user's interaction with the digital assistant by reducing the number of system prompts that the user is asked to respond to.
    Type: Grant
    Filed: November 24, 2020
    Date of Patent: November 21, 2023
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Vipul Agarwal, Rahul Kumar Jha, Soumya Batra, Karthik Tangirala, Mohammad Makarechian, Imed Zitouni
  • Publication number: 20210082403
    Abstract: A computer-implemented technique is described herein for expediting a user's interaction with a digital assistant. In one implementation, the technique involves receiving a system prompt generated by a digital assistant in response to an input command provided by a user via an input device. The technique then generates a predicted response based on linguistic content of the system prompt, together with contextual features pertaining to a circumstance in which the system prompt was issued. The predicted response corresponds to a prediction of how the user will respond to the system prompt. The technique then selects one or more dialogue actions from a plurality of dialogue actions, based on a confidence value associated with the predicted response. The technique expedites the user's interaction with the digital assistant by reducing the number of system prompts that the user is asked to respond to.
    Type: Application
    Filed: November 24, 2020
    Publication date: March 18, 2021
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Vipul AGARWAL, Rahul Kumar JHA, Soumya BATRA, Karthik TANGIRALA, Mohammad MAKARECHIAN, Imed ZITOUNI
  • Patent number: 10878805
    Abstract: A computer-implemented technique is described herein for expediting a user's interaction with a digital assistant. In one implementation, the technique involves receiving a system prompt generated by a digital assistant in response to an input command provided by a user via an input device. The technique then generates a predicted response based on linguistic content of the system prompt, together with contextual features pertaining to a circumstance in which the system prompt was issued. The predicted response corresponds to a prediction of how the user will respond to the system prompt. The technique then selects one or more dialogue actions from a plurality of dialogue actions, based on a confidence value associated with the predicted response. The technique expedites the user's interaction with the digital assistant by reducing the number of system prompts that the user is asked to respond to.
    Type: Grant
    Filed: December 6, 2018
    Date of Patent: December 29, 2020
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Vipul Agarwal, Rahul Kumar Jha, Soumya Batra, Karthik Tangirala, Mohammad Makarechian, Imed Zitouni
  • Publication number: 20200184956
    Abstract: A computer-implemented technique is described herein for expediting a user's interaction with a digital assistant. In one implementation, the technique involves receiving a system prompt generated by a digital assistant in response to an input command provided by a user via an input device. The technique then generates a predicted response based on linguistic content of the system prompt, together with contextual features pertaining to a circumstance in which the system prompt was issued. The predicted response corresponds to a prediction of how the user will respond to the system prompt. The technique then selects one or more dialogue actions from a plurality of dialogue actions, based on a confidence value associated with the predicted response. The technique expedites the user's interaction with the digital assistant by reducing the number of system prompts that the user is asked to respond to.
    Type: Application
    Filed: December 6, 2018
    Publication date: June 11, 2020
    Inventors: Vipul AGARWAL, Rahul Kumar JHA, Soumya BATRA, Karthik TANGIRALA, Mohammad MAKARECHIAN, Imed ZITOUNI
  • Patent number: 10268645
    Abstract: A user uploads date sets through a client to a database. The data sets are provisioned in the database for in-database searching. The data sets are evaluated and classifications for the columns of the tables that include the data set are detected. Columns content may be classified into different analysis types, aggregation types, formats, categories, hierarchies, etc. Metadata is generated based on the evaluation of the data sets. A schema is used to store the metadata that describes the detected classification of the columns. The schema is stored in the database and is used when a search in the database is performed.
    Type: Grant
    Filed: April 4, 2013
    Date of Patent: April 23, 2019
    Assignee: SAP SE
    Inventors: Ganesh Vaitheeswaran, Rahul Kumar Jha, Suraj Pai Airody, Anup Kumar Rai, Arindam Bhattacharjee
  • Patent number: 9092478
    Abstract: Methods, computer-readable media, and systems for managing business objects data sources. A search query that includes multiple query terms is received. Each query term at least partially represents metadata associated with one of multiple business objects data sources that each stores multiple data items. Multiple search index documents are searched to identify one or more business objects data sources that are each associated with metadata at least partially represented by each query term. Multiple metadata tables are searched to identify metadata associated with each identified business objects data source. The identified business objects data sources are searched for data items that satisfy the identified metadata. Representations of the data items and the metadata are provided in response to receiving the search query.
    Type: Grant
    Filed: December 27, 2011
    Date of Patent: July 28, 2015
    Assignee: SAP SE
    Inventors: Ganesh Vaitheeswaran, Manasa Ranjan Tripathy, Raghavendra Nagaraja, Arindam Bhattacharjee, Rahul Kumar Jha, Nithin Moolky Kamath
  • Patent number: 8938475
    Abstract: Methods, non-transitory computer-readable media, and systems for managing business objects data sources. Multiple business objects data sources, each storing multiple data items, are accessed. For each data source, multiple computer-searchable index documents and multiple metadata tables, including master tables and mapping tables, are generated. The multiple computer-searchable index documents and the multiple metadata tables are provided to perform a search for data items in the multiple business objects data sources.
    Type: Grant
    Filed: December 27, 2011
    Date of Patent: January 20, 2015
    Assignee: SAP SE
    Inventors: Ganesh Vaitheeswaran, Arindam Bhattacharjee, Raghavendra Nagaraja, Manasa Ranjan Tripathy, Nithin Moolky Kamath, Rahul Kumar Jha
  • Publication number: 20140304263
    Abstract: A user uploads date sets through a client to a database. The data sets are provisioned in the database for in-database searching. The data sets are evaluated and classifications for the columns of the tables that include the data set are detected. Columns content may be classified into different analysis types, aggregation types, formats, categories, hierarchies, etc. Metadata is generated based on the evaluation of the data sets. A schema is used to store the metadata that describes the detected classification of the columns. The schema is stored in the database and is used when a search in the database is performed.
    Type: Application
    Filed: April 4, 2013
    Publication date: October 9, 2014
    Inventors: Ganesh Vaitheeswaran, Rahul Kumar Jha, Suraj Pai Airody, Anup Kumar Rai, Arindam Bhattacharjee
  • Publication number: 20130166598
    Abstract: Methods, non-transitory computer-readable media, and systems for managing business objects data sources. Multiple business objects data sources, each storing multiple data items, are accessed. For each data source, multiple computer-searchable index documents and multiple metadata tables, including master tables and mapping tables, are generated. The multiple computer-searchable index documents and the multiple metadata tables are provided to perform a search for data items in the multiple business objects data sources.
    Type: Application
    Filed: December 27, 2011
    Publication date: June 27, 2013
    Applicant: Business Objects Software Ltd.
    Inventors: Ganesh Vaitheeswaran, Arindam Bhattacharjee, Raghavendra Nagaraja, Manasa Ranjan Tripathy, Nithin Moolky Kamath, Rahul Kumar Jha
  • Publication number: 20130166573
    Abstract: Methods, computer-readable media, and systems for managing business objects data sources. A search query that includes multiple query terms is received. Each query term at least partially represents metadata associated with one of multiple business objects data sources that each stores multiple data items. Multiple search index documents are searched to identify one or more business objects data sources that are each associated with metadata at least partially represented by each query term. Multiple metadata tables are searched to identify metadata associated with each identified business objects data source. The identified business objects data sources are searched for data items that satisfy the identified metadata. Representations of the data items and the metadata are provided in response to receiving the search query.
    Type: Application
    Filed: December 27, 2011
    Publication date: June 27, 2013
    Applicant: Business Objects Software Ltd.
    Inventors: Ganesh Vaitheeswaran, Manasa Ranjan Tripathy, Raghavendra Nagaraja, Arindam Bhattacharjee, Rahul Kumar Jha, Nithin Moolky Kamath