Patents by Inventor Sandip Mandlecha

Sandip Mandlecha 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).

  • TEXT-BASED MACHINE LEARNING EXTRACTION OF TABLE DATA FROM A READ-ONLY DOCUMENT
    Publication number: 20240160616
    Abstract: Embodiments of the disclosed technologies provide solutions for automatically reading digital electronic documents that contain tables and correctly extracting table data, rows and columns from the documents with high accuracy and high throughput. Embodiments are capable of converting a table portion of a read-only document to a searchable, editable data record using text rectangle (TR)-level numerical data that indicates probabilities of TRs belonging to canonicals and at least one convolutional neural network (CNN) that processes the TR-level numerical data to produce table-level numerical data.
    Type: Application
    Filed: January 17, 2024
    Publication date: May 16, 2024
    Inventors: Hongyang Yu, Hanieh Borhanazad, Sandip Mandlecha
  • Text-based machine learning extraction of table data from a read-only document
    Patent number: 11914567
    Abstract: Embodiments of the disclosed technologies provide solutions for automatically reading digital electronic documents that contain tables and correctly extracting table data, rows and columns from the documents with high accuracy and high throughput. Embodiments are capable of converting a table portion of a read-only document to a searchable, editable data record using text rectangle (TR)-level numerical data that indicates probabilities of TRs belonging to canonicals and at least one convolutional neural network (CNN) that processes the TR-level numerical data to produce table-level numerical data.
    Type: Grant
    Filed: October 25, 2022
    Date of Patent: February 27, 2024
    Assignee: Coupa Software Incorporated
    Inventors: Hongyang Yu, Hanieh Borhanazad, Sandip Mandlecha
  • TEXT-BASED MACHINE LEARNING EXTRACTION OF TABLE DATA FROM A READ-ONLY DOCUMENT
    Publication number: 20230049389
    Abstract: Embodiments of the disclosed technologies provide solutions for automatically reading digital electronic documents that contain tables and correctly extracting table data, rows and columns from the documents with high accuracy and high throughput.
    Type: Application
    Filed: October 25, 2022
    Publication date: February 16, 2023
    Inventors: Hongyang Yu, Hanieh Borhanazad, Sandip Mandlecha
  • Text-based machine learning extraction of table data from a read-only document
    Patent number: 11500843
    Abstract: Embodiments of the disclosed technologies provide solutions for automatically reading digital electronic documents that contain tables and correctly extracting table data, rows and columns from the documents with high accuracy and high throughput. Embodiments are capable of converting a table portion of a read-only document to a searchable, editable data record using text rectangle (TR)-level numerical data that indicates probabilities of TRs belonging to canonicals and at least one convolutional neural network (CNN) that processes the TR-level numerical data to produce table-level numerical data.
    Type: Grant
    Filed: October 20, 2020
    Date of Patent: November 15, 2022
    Assignee: COUPA SOFTWARE INCORPORATED
    Inventors: Hongyang Yu, Hanieh Borhanazad, Sandip Mandlecha
  • TEXT-BASED MACHINE LEARNING EXTRACTION OF TABLE DATA FROM A READ-ONLY DOCUMENT
    Publication number: 20220067014
    Abstract: Embodiments of the disclosed technologies provide solutions for automatically reading digital electronic documents that contain tables and correctly extracting table data, rows and columns from the documents with high accuracy and high throughput. Embodiments are capable of converting a table portion of a read-only document to a searchable, editable data record using text rectangle (TR)-level numerical data that indicates probabilities of TRs belonging to canonicals and at least one convolutional neural network (CNN) that processes the TR-level numerical data to produce table-level numerical data.
    Type: Application
    Filed: October 20, 2020
    Publication date: March 3, 2022
    Inventors: Hongyang Yu, Hanieh Borhanazad, Sandip Mandlecha