Patents by Inventor Andre R. Williams

Andre R. Williams 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).

  • Generating descriptive tags for images of utility assets
    Patent number: 12676017
    Abstract: An image caption generator analyzes a set of images of a region of an environment captured during or after environmental emergency event to provide a set of utility images selected from the set of images that include a utility asset. The image caption generator also generates descriptive tags for the set of utility images. The descriptive tags each characterize a type and a state of a respective utility asset included in a respective image of the set of utility images. A verification engine cross-references the set of utility images with information from an external data source to confirm an accuracy of the descriptive tags for the set of utility images and providing feedback to the image caption generator based on results of the cross-referencing. The image caption generator adjusts the parameters of the ML model based on the feedback to increase accuracy of the descriptive tags.
    Type: Grant
    Filed: March 26, 2024
    Date of Patent: July 7, 2026
    Assignee: Florida Power & Light Company
    Inventors: Mackenzie Vecchio, Andre R. Williams, Richard Bauder, Stephen S. Cross, Rohan N. Shah, Kyle A Bush, Paul R. Hynes, Eric D Schwartz, Dmitri Soroka, David J. Sunderman
  • GENERATING DESCRIPTIVE TAGS FOR IMAGES OF UTILITY ASSETS
    Publication number: 20250308269
    Abstract: An image caption generator analyzes a set of images of a region of an environment captured during or after environmental emergency event to provide a set of utility images selected from the set of images that include a utility asset. The image caption generator also generates descriptive tags for the set of utility images. The descriptive tags each characterize a type and a state of a respective utility asset included in a respective image of the set of utility images. A verification engine cross-references the set of utility images with information from an external data source to confirm an accuracy of the descriptive tags for the set of utility images and providing feedback to the image caption generator based on results of the cross-referencing. The image caption generator adjusts the parameters of the ML model based on the feedback to increase accuracy of the descriptive tags.
    Type: Application
    Filed: March 26, 2024
    Publication date: October 2, 2025
    Inventors: Mackenzie Vecchio, Andre R. Williams, Richard Bauder, Stephen S. Cross, Rohan N. Shah, Kyle A. Bush, Paul R. Hynes, Eric D. Schwartz, Dmitri Soroka, David J. Sunderman