Patents by Inventor Peter Frick

Peter Frick 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).

  • Entity extraction with encoder decoder machine learning model
    Patent number: 12394233
    Abstract: A method includes executing an encoder machine learning model on multiple token values contained in a document to create an encoder hidden state vector. A decoder machine learning model executing on the encoder hidden state vector generates raw text comprising an entity value and an entity label for each of multiple entities. The method further includes generating a structural representation of the entities directly from the raw text and outputting the structural representation of the entities of the document.
    Type: Grant
    Filed: November 30, 2022
    Date of Patent: August 19, 2025
    Assignee: Intuit Inc.
    Inventors: Tharathorn Rimchala, Peter Frick
  • ENTITY EXTRACTION WITH ENCODER DECODER MACHINE LEARNING MODEL
    Publication number: 20230386236
    Abstract: A method includes executing an encoder machine learning model on multiple token values contained in a document to create an encoder hidden state vector. A decoder machine learning model executing on the encoder hidden state vector generates raw text comprising an entity value and an entity label for each of multiple entities. The method further includes generating a structural representation of the entities directly from the raw text and outputting the structural representation of the entities of the document.
    Type: Application
    Filed: November 30, 2022
    Publication date: November 30, 2023
    Applicant: Intuit Inc.
    Inventors: Tharathorn Rimchala, Peter Frick
  • Entity extraction with encoder decoder machine learning model
    Patent number: 11544943
    Abstract: A method includes executing an encoder machine learning model on multiple token values contained in a document to create an encoder hidden state vector. A decoder machine learning model executing on the encoder hidden state vector generates raw text comprising an entity value and an entity label for each of multiple entities. The method further includes generating a structural representation of the entities directly from the raw text and outputting the structural representation of the entities of the document.
    Type: Grant
    Filed: May 31, 2022
    Date of Patent: January 3, 2023
    Assignee: Intuit Inc.
    Inventors: Tharathorn Rimchala, Peter Frick
  • Memory structure and method making
    Publication number: 20040151016
    Abstract: A memory structure has a plurality of row conductors intersecting a plurality of column conductors at a plurality of intersections. Each intersection includes an electrically linear resistive element in series with a voltage breakdown element.
    Type: Application
    Filed: January 22, 2004
    Publication date: August 5, 2004
    Inventors: Andrew L. Van Brocklin, Peter Frick