Patents by Inventor Andrew Michael Bradfield

Andrew Michael Bradfield 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: 11726803
    Abstract: Artificial intelligence (AI) based computer systems and methods are disclosed for autonomously creating customer service help guides via a graphic user interface (GUI). Computing instructions operating on processor(s) are configured to automatically crawl digital product categorie(s) and create action script(s) derived therefrom. The action script(s) comprise user directive(s) for completing user task(s) on a computing device and software application configured to render a GUI. A natural language understanding (NLU) model associates the action script(s) with text of the user task(s). The action script(s) are tested against completion criteria to output success result(s). An AI model is trained on the action script(s), the text of the user tasks, and the completion criteria. A client device of user may request assistance with a given task, and may render, in response, graphic-and-text display(s) associated with a relevant action script (as determined by the AI model) on a GUI of the client device.
    Type: Grant
    Filed: March 1, 2022
    Date of Patent: August 15, 2023
    Assignee: ORANGE MANAGEMENT INC.
    Inventor: Andrew Michael Bradfield
  • Publication number: 20220276882
    Abstract: Artificial intelligence (AI) based computer systems and methods are disclosed for autonomously creating customer service help guides via a graphic user interface (GUI). Computing instructions operating on processor(s) are configured to automatically crawl digital product categorie(s) and create action script(s) derived therefrom. The action script(s) comprise user directive(s) for completing user task(s) on a computing device and software application configured to render a GUI. A natural language understanding (NLU) model associates the action script(s) with text of the user task(s). The action script(s) are tested against completion criteria to output success result(s). An AI model is trained on the action script(s), the text of the user tasks, and the completion criteria. A client device of user may request assistance with a given task, and may render, in response, graphic-and-text display(s) associated with a relevant action script (as determined by the AI model) on a GUI of the client device.
    Type: Application
    Filed: March 1, 2022
    Publication date: September 1, 2022
    Inventor: Andrew Michael Bradfield