Patents by Inventor Manish U. GARG

Manish U. GARG 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).

  • System and method for analysis of structured and unstructured data
    Patent number: 10922358
    Abstract: The invention relates to a computer-implemented system and method for analyzing unstructured data from a plurality of input files, and standardizing the data to a format that can be consumed by downstream systems. The method may comprise the steps of: receiving at least one input file to be analyzed, wherein the at least one input file includes the structured and unstructured data, splitting the at least one input file into a plurality of documents, classifying each page of the plurality of documents as one of structured or unstructured data, parsing the pages of the plurality of documents classified as unstructured data, extracting relevant data from the parsed pages, mapping each of the extracted relevant data to standardized output; and generating canonical data sets based on the standardized outputs.
    Type: Grant
    Filed: October 12, 2018
    Date of Patent: February 16, 2021
    Assignee: KPMG LLP
    Inventors: Manish U. Garg, Kallol K. Ghosh, Elliott A. Torres, Nikhil S. Dharap, Steve Rainey, Timothy J. Cerino, John Hyung Lee, Nader Karimi
  • SYSTEM AND METHOD FOR ANALYSIS OF STRUCTURED AND UNSTRUCTURED DATA
    Publication number: 20190114360
    Abstract: The invention relates to a computer-implemented system and method for analyzing unstructured data from a plurality of input files, and standardizing the data to a format that can be consumed by downstream systems. The method may comprise the steps of: receiving at least one input file to be analyzed, wherein the at least one input file includes the structured and unstructured data, splitting the at least one input file into a plurality of documents, classifying each page of the plurality of documents as one of structured or unstructured data, parsing the pages of the plurality of documents classified as unstructured data, extracting relevant data from the parsed pages, mapping each of the extracted relevant data to standardized output; and generating canonical data sets based on the standardized outputs.
    Type: Application
    Filed: October 12, 2018
    Publication date: April 18, 2019
    Inventors: Manish U. GARG, Kallol K. GHOSH, Elliott A. TORRES, Nikhil S. DHARAP, Steve RAINEY, Timothy J. CERINO, John Hyung LEE, Nader KARIMI