Patents by Inventor Graham Sheldon

Graham Sheldon 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).

  • Publication number: 20250104458
    Abstract: Using a cognitive artificial intelligence (AI) layer (e.g., a generative AI model and one or more other AI/ML models) to perform robotic process automation (RPA) robot repair is disclosed. Computer vision (CV) and/or optical character recognition (OCR) models may be called by RPA robots when performing activities in RPA workflows to identify graphical elements and text, respectively, in a user interface (UI). However, the CV or OCR model may not find a graphical element or text targeted by the activity of the RPA workflow, or the RPA robot may encounter an exception and otherwise fail when performing the activity. In such cases, a cognitive AI layer including a generative AI model may be used to find the target graphical element or text, or to address the robot failure.
    Type: Application
    Filed: September 26, 2023
    Publication date: March 27, 2025
    Applicant: UiPath, Inc.
    Inventors: Daniel DINES, Graham SHELDON, Mircea GRIGORE, Gerd WEISHAAR, Justin GRINDAL
  • Publication number: 20160063394
    Abstract: Discrete sets of data are divided into collections in accordance with strata delineated along multiple dimensions of data. Each dimension of data represents criteria to be evaluated and the stratification of a dimension is based on a distribution of the discrete sets of data along such a dimension. Once divided into the multidimensional strata, one or more discrete sets of data are randomly selected from each stratum and are provided to human judges to generate corresponding classifications of such a discrete set of data. Such human-generated classifications are compared with computer-generated classifications associated with the same discrete sets of data for purposes of evaluating the computer-implemented functionality generating such classifications. Such human-generated classifications are also associated with the corresponding discrete sets of data for purposes of training, and thereby improving, computer-implemented functionality.
    Type: Application
    Filed: August 27, 2014
    Publication date: March 3, 2016
    Inventors: Sedat Gokalp, Graham Sheldon, Salem Haykal
  • Publication number: 20060167725
    Abstract: A method and apparatus for scheduling is disclosed. The method may include g a service for which a scheduling strategy is to be applied, selecting the scheduling to be applied to the service selected, selecting an action to be applied to the selected accessing a calendar related to the selected service, in view of the service selected, g the constraints to be applied as required by the scheduling strategy and returning a applying the constraints.
    Type: Application
    Filed: January 25, 2005
    Publication date: July 27, 2006
    Applicant: MICROSOFT CORPORATION
    Inventors: Dan Grunspan, Graham Sheldon, Michael Ott, Naveen Garg, Ilya Baimetov, Tsvi Reiter
  • Publication number: 20060150077
    Abstract: In a user interface method, an electronic form is displayed to a user, the electronic form to allow the user to gather information. An event associated with the electronic form is detected. A context is determined based on the detected event. Information relevant to the context is retrieved from a database, and the displayed electronic form is modified to allow the electronic form to display to the user the information relevant to the context.
    Type: Application
    Filed: December 30, 2004
    Publication date: July 6, 2006
    Applicant: MICROSOFT CORPORATION
    Inventors: Graham Sheldon, Tobin Zerba