公开(公告)号：US11783827B2

公开(公告)日：2023-10-10

申请号：US17224627

申请日：2021-04-07

Applicant: Apple Inc.

Inventor： Jamie Harry Drummie ,  Silvia Frias Delgado ,  Andrew J. Haines ,  Samuel E. Turnbull ,  Johan D. Forsell

IPC: G10L15/22

CPC classification number: G10L15/22 ,  G10L2015/221

Abstract: Systems and processes for operating an intelligent automated assistant are provided. An example process includes receiving an utterance including a user request, determining, based on the user request, a domain associated with the user request, determining, based on the domain, a first subsequent user action and a second subsequent user action, determining, based on the domain, a first parameter for the first subsequent user action and a second parameter for the second subsequent user action, in accordance with a determination that a first score associated with the first subsequent user action is higher than a score associated with the second subsequent user action, selecting the first subsequent user action as a suggested subsequent user action, and providing the suggested subsequent user action.

公开(公告)号：US10810274B2

公开(公告)日：2020-10-20

申请号：US15678059

申请日：2017-08-15

Applicant: Apple Inc.

Inventor： 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

IPC: G06F16/9535 ,  H04N21/466 ,  H04N21/233 ,  G10L15/18 ,  G10L15/22 ,  H04N21/482 ,  H04N21/414 ,  H04N21/422 ,  H04N21/239 ,  G10L15/08 ,  G10L13/02 ,  G10L15/02 ,  G10L15/30 ,  G10L13/00

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.