Patents by Inventor Thomas Benedict GUNTER

Thomas Benedict GUNTER 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).

  • Optimizing dialogue policy decisions for digital assistants using implicit feedback
    Patent number: 10810274
    Abstract: Systems and processes for optimizing dialogue policy decisions for digital assistants using implicit feedback are provided. In an example process, a user utterance is received. Based on a text representation of the user utterance, one or more user intents corresponding to the user utterance are determined. A policy action is selected from a plurality of candidate policy actions based on a belief state for the one or more user intents and a policy model. The policy action is performed, including outputting results of the policy action for presentation. A success score for the policy action is determined based on whether one or more predetermined types of implicit user feedback are detected after performing the policy action. A set of parameter values of the policy model is modified using the determined success score.
    Type: Grant
    Filed: August 15, 2017
    Date of Patent: October 20, 2020
    Assignee: Apple Inc.
    Inventors: Blaise Thomson, David J. Vandyke, Gennaro Frazzingaro, Silvia Frias Delgado, Thomas Benedict Gunter, Thomas David Voice, Thorvaldur Pall Helgason, Stephen J. Young, Diarmuid Ó Śeaghdha, Dain Kaplan
  • OPTIMIZING DIALOGUE POLICY DECISIONS FOR DIGITAL ASSISTANTS USING IMPLICIT FEEDBACK
    Publication number: 20180329998
    Abstract: Systems and processes for optimizing dialogue policy decisions for digital assistants using implicit feedback are provided. In an example process, a user utterance is received. Based on a text representation of the user utterance, one or more user intents corresponding to the user utterance are determined. A policy action is selected from a plurality of candidate policy actions based on a belief state for the one or more user intents and a policy model. The policy action is performed, including outputting results of the policy action for presentation. A success score for the policy action is determined based on whether one or more predetermined types of implicit user feedback are detected after performing the policy action. A set of parameter values of the policy model is modified using the determined success score.
    Type: Application
    Filed: August 15, 2017
    Publication date: November 15, 2018
    Inventors: Blaise THOMSON, David J. VANDYKE, Gennaro FRAZZINGARO, Silvia FRIAS DELGADO, Thomas Benedict GUNTER, Thomas David VOICE, Thorvaldur Pall HELGASON, Stephen J. YOUNG, Diarmuid Ó SEAGHDHA, Dain KAPLAN