Patents by Inventor Alan Wayne Gilchrest

Alan Wayne Gilchrest 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).

  • Evaluating the performance of a large language model
    Patent number: 12705219
    Abstract: A query is received. A performance of a large language model that generated a query response based on the received query is evaluated. Evaluating the performance of the large language model includes determining a reference dependent evaluator score and/or a reference free evaluator score. One or more documents used to generate the received query are requested to be updated based on the reference dependent evaluator score associated with the query response. The one or more updated documents are received and stored. The one or more updated documents are utilized by the large language model to generate one or more subsequent query responses for one or more subsequent queries.
    Type: Grant
    Filed: October 11, 2024
    Date of Patent: August 11, 2026
    Assignee: Palo Alto Networks, Inc.
    Inventors: Spandan Mishra, Danielle Hyunwon Sim, Alexander Michael Margaris, Nandan Gautam Thor, Alan Wayne Gilchrest
  • Agentic approach to multilingual text-to-SQL conversion with intent detection and self-correction
    Patent number: 12705235
    Abstract: An intent associated with a user input is determined. An augmented prompt for generating a Standard Query Language (SQL) code snippet is generated. An SQL code snippet is generated by using the augmented prompt on a machine learning (ML) model. Results are generated by executing the SQL code snippet on a data lake.
    Type: Grant
    Filed: January 28, 2025
    Date of Patent: August 11, 2026
    Assignee: Palo Alto Networks, Inc.
    Inventors: Spandan Mishra, Danielle Hyunwon Sim, Nandan Gautam Thor, Katherine Chiang Lam, Jarod Matthew Hillerman, Alan Wayne Gilchrest, Alexander Michael Margaris, Taylor Yoojin Lee, Stefan Schlotter
  • AGENTIC APPROACH TO MULTILINGUAL TEXT-TO-SQL CONVERSION WITH INTENT DETECTION AND SELF-CORRECTION
    Publication number: 20260220129
    Abstract: An intent associated with a user input is determined. An augmented prompt for generating a Standard Query Language (SQL) code snippet is generated. An SQL code snippet is generated by using the augmented prompt on a machine learning (ML) model. Results are generated by executing the SQL code snippet on a data lake.
    Type: Application
    Filed: January 28, 2025
    Publication date: July 30, 2026
    Inventors: Spandan Mishra, Danielle Hyunwon Sim, Nandan Gautam Thor, Katherine Chiang Lam, Jarod Matthew Hillerman, Alan Wayne Gilchrest, Alexander Michael Margaris, Taylor Yoojin Lee, Stefan Schlotter
  • EVALUATING THE PERFORMANCE OF A LARGE LANGUAGE MODEL
    Publication number: 20260105034
    Abstract: A query is received. A performance of a large language model that generated a query response based on the received query is evaluated. Evaluating the performance of the large language model includes determining a reference dependent evaluator score and/or a reference free evaluator score. One or more documents used to generate the received query are requested to be updated based on the reference dependent evaluator score associated with the query response. The one or more updated documents are received and stored. The one or more updated documents are utilized by the large language model to generate one or more subsequent query responses for one or more subsequent queries.
    Type: Application
    Filed: October 11, 2024
    Publication date: April 16, 2026
    Inventors: Spandan Mishra, Danielle Hyunwon Sim, Alexander Michael Margaris, Nandan Gautam Thor, Alan Wayne Gilchrest