Patents by Inventor Aravind BRAHMADEVARA

Aravind BRAHMADEVARA 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).

  • ATTENTION-BASED CLASSIFIER MACHINE LEARNING MODELS USING DUAL-POSITIONAL-MODE SEGMENT EMBEDDINGS
    Publication number: 20240070479
    Abstract: Various embodiments of the present invention use segment embeddings generated based at least in part on both intra-segment positional indicators for metadata labels within hierarchically-structured segments of a segment-ordered hierarchically-structured input data object as well as cross-segment position indicators for the noted hierarchically-structured segments.
    Type: Application
    Filed: August 24, 2022
    Publication date: February 29, 2024
    Inventors: Kartik B. Sharma, Aravind Brahmadevara
  • Apparatuses, methods, and computer program products for improved data format conversion for semi-structured data
    Patent number: 11709857
    Abstract: Embodiments of the present disclosure provide for improved mapping from sequential semi-structured data of a first custom data format to a second custom data format. The improved mechanism for mapping between custom data formats significantly reducing the amount of manual effort otherwise used for creating mapping rules. Example embodiments utilize a state extractor model that extracts an untrained modified finite state machine embodied by a skeleton set of extracted states from particular sequential semi-structured input data, and generate a trained modified finite state machine that maps the first custom data format to the second custom data format based at least in part on the untrained modified finite state machine, sequential semi-structured input data of the first custom data format, and database structured output data of the second custom data format. The trained modified finite state machine may be used for subsequent processing data of the first custom data format.
    Type: Grant
    Filed: April 26, 2021
    Date of Patent: July 25, 2023
    Assignee: OPTUM, INC.
    Inventors: Indranil Basu, Satishkumar Dontamsetty, Aravind Brahmadevara, Snigdha Sree Borra, Shubham Gupta
  • APPARATUSES, METHODS, AND COMPUTER PROGRAM PRODUCTS FOR IMPROVED DATA FORMAT CONVERSION FOR SEMI-STRUCTURED DATA
    Publication number: 20220342900
    Abstract: Embodiments of the present disclosure provide for improved mapping from sequential semi-structured data of a first custom data format to a second custom data format. The improved mechanism for mapping between custom data formats significantly reducing the amount of manual effort otherwise used for creating mapping rules. Example embodiments utilize a state extractor model that extracts an untrained modified finite state machine embodied by a skeleton set of extracted states from particular sequential semi-structured input data, and generate a trained modified finite state machine that maps the first custom data format to the second custom data format based at least in part on the untrained modified finite state machine, sequential semi-structured input data of the first custom data format, and database structured output data of the second custom data format. The trained modified finite state machine may be used for subsequent processing data of the first custom data format.
    Type: Application
    Filed: April 26, 2021
    Publication date: October 27, 2022
    Inventors: Indranil BASU, Satishkumar DONTAMSETTY, Aravind BRAHMADEVARA, Snigdha Sree BORRA, Shubham GUPTA