Patents by Inventor Deepak Dilipkumar

Deepak Dilipkumar 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).

  • Machine learned language model based natural language interface for querying databases
    Patent number: 12645718
    Abstract: A system, such as an online system, allows users to ask natural language questions requesting information stored in a database. The system receives a natural language question. The system determines database tables and database queries associated with the natural language question. The system generates a prompt for input to a machine learned language model. The prompt specifies the natural language question, information describing database tables, and the example database queries. The system sends the prompt to the machine learned language model for execution and receives a response generated by the machine learned language model. The response includes a database query corresponding to the natural language question. The system sends the database query for execution on a database system and provides the result of execution of the database query to the client device.
    Type: Grant
    Filed: September 10, 2024
    Date of Patent: June 2, 2026
    Assignee: Maplebear Inc.
    Inventors: Deepak Dilipkumar, Wahhaj Ali, Karthik Ravishankar
  • MACHINE LEARNED LANGUAGE MODEL BASED NATURAL LANGUAGE INTERFACE FOR QUERYING DATABASES
    Publication number: 20250086213
    Abstract: A system, such as an online system, allows users to ask natural language questions requesting information stored in a database. The system receives a natural language question. The system determines database tables and database queries associated with the natural language question. The system generates a prompt for input to a machine learned language model. The prompt specifies the natural language question, information describing database tables, and the example database queries. The system sends the prompt to the machine learned language model for execution and receives a response generated by the machine learned language model. The response includes a database query corresponding to the natural language question. The system sends the database query for execution on a database system and provides the result of execution of the database query to the client device.
    Type: Application
    Filed: September 10, 2024
    Publication date: March 13, 2025
    Inventors: Deepak Dilipkumar, Wahhaj Ali, Karthik Ravishankar