Patents by Inventor Abhishek Sanghavi

Abhishek Sanghavi 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).

  • Patent number: 11907650
    Abstract: Methods and systems for artificial intelligence (AI)-assisted document annotation and training of machine learning-based models for document data extraction are described. The methods and systems described herein take advantage of a continuous machine learning approach to create document processing pipelines that provide accurate and efficient data extraction from documents that include structured text, semi-structured text, unstructured text, or any combination thereof.
    Type: Grant
    Filed: July 11, 2022
    Date of Patent: February 20, 2024
    Assignee: PwC Product Sales LLC
    Inventors: Jacob T. Wilson, Joseph D. Harrington, Vinston Sundara Pandiyan Sigamani, Abhishek Sanghavi, Jayakumar Pillai, Benjamin Cunningham, Lindsey P. Lewis
  • Patent number: 11645462
    Abstract: Methods and systems for artificial intelligence (AI)-assisted document annotation and training of machine learning-based models for document data extraction are described. The methods and systems described herein take advantage of a continuous machine learning approach to create document processing pipelines that provide accurate and efficient data extraction from documents that include structured text, semi-structured text, unstructured text, or any combination thereof.
    Type: Grant
    Filed: August 13, 2021
    Date of Patent: May 9, 2023
    Assignee: PricewaterhouseCoopers LLP
    Inventors: Jacob T. Wilson, Joseph D. Harrington, Vinston Sundara Pandiyan Sigamani, Abhishek Sanghavi, Jayakumar Pillai, Benjamin Cunningham, Lindsey P. Lewis
  • Publication number: 20230052372
    Abstract: Methods and systems for artificial intelligence (Al)-assisted document annotation and training of machine learning-based models for document data extraction are described. The methods and systems described herein take advantage of a continuous machine learning approach to create document processing pipelines that provide accurate and efficient data extraction from documents that include structured text, semi-structured text, unstructured text, or any combination thereof.
    Type: Application
    Filed: July 11, 2022
    Publication date: February 16, 2023
    Applicant: PricewaterhouseCoopers LLP
    Inventors: Jacob T. WILSON, Joseph D. HARRINGTON, Vinston Sundara Pandiyan SIGAMANI, Abhishek SANGHAVI, Jayakumar PILLAI, Benjamin CUNNINGHAM, Lindsey P. LEWIS
  • Publication number: 20230049167
    Abstract: Methods and systems for artificial intelligence (AI)-assisted document annotation and training of machine learning-based models for document data extraction are described. The methods and systems described herein take advantage of a continuous machine learning approach to create document processing pipelines that provide accurate and efficient data extraction from documents that include structured text, semi-structured text, unstructured text, or any combination thereof.
    Type: Application
    Filed: August 13, 2021
    Publication date: February 16, 2023
    Applicant: PricewaterhouseCoopers LLP
    Inventors: Jacob T. Wilson, Joseph D. Harrington, Vinston Sundara Pandiyan Sigamani, Abhishek Sanghavi, Jayakumar Pillai, Benjamin Cunningham, Lindsey P. Lewis
  • Patent number: 11443102
    Abstract: Methods and systems for artificial intelligence (AI)-assisted document annotation and training of machine learning-based models for document data extraction are described. The methods and systems described herein take advantage of a continuous machine learning approach to create document processing pipelines that provide accurate and efficient data extraction from documents that include structured text, semi-structured text, unstructured text, or any combination thereof.
    Type: Grant
    Filed: August 13, 2021
    Date of Patent: September 13, 2022
    Assignee: PricewaterhouseCoopers LLP
    Inventors: Jacob T. Wilson, Joseph D. Harrington, Vinston Sundara Pandiyan Sigamani, Abhishek Sanghavi, Jayakumar Pillai, Benjamin Cunningham, Lindsey P. Lewis
  • Publication number: 20200125630
    Abstract: Described are system, method, and computer-program product embodiments for performing language-agnostic page stream segmentation. In some embodiments, a method includes receiving a multi-page file associated with a plurality of documents. A plurality of characters present on each page of the set of consecutive pages, including a first page and a second page, of the multi-page file can be detected. A plurality of structural data for each page can be computed based on a position and a font format for one or more of the detected characters. The plurality of structural data between the first page and the second page can be compared to determine whether the second page corresponds to a boundary between two documents of the plurality of documents. The multi-page file can be segmented at the second page in response to determining that the second page corresponds to the boundary.
    Type: Application
    Filed: December 5, 2019
    Publication date: April 23, 2020
    Applicant: PricewaterhouseCoopers LLP
    Inventors: Abhishek SANGHAVI, Michael FLYNN, Joseph HARRINGTON, Michael BACCALA
  • Patent number: 10534846
    Abstract: Described are system, method, and computer-program product embodiments for performing language-agnostic page stream segmentation. In some embodiments, a method includes receiving a multi-page file associated with a plurality of documents. A plurality of characters present on each page of the set of consecutive pages, including a first page and a second page, of the multi-page file can be detected. A plurality of structural data for each page can be computed based on a position and a font format for one or more of the detected characters. The plurality of structural data between the first page and the second page can be compared to determine whether the second page corresponds to a boundary between two documents of the plurality of documents. The multi-page file can be segmented at the second page in response to determining that the second page corresponds to the boundary.
    Type: Grant
    Filed: June 7, 2019
    Date of Patent: January 14, 2020
    Assignee: PricewaterhouseCoopers LLP
    Inventors: Abhishek Sanghavi, Michael Flynn, Joseph Harrington, Michael Baccala