公开(公告)号：US20210216384A1

公开(公告)日：2021-07-15

申请号：US17049696

申请日：2019-08-06

Applicant: GOOGLE LLC

Inventor： Bohdan Vlasyuk ,  Behshad Behzadi ,  Mario Bertschler ,  Denis Burakov ,  Daniel Cotting ,  Michael Golikov ,  Lucas Mirelmann ,  Steve CHENG ,  Sergey NAZAROV ,  Zaheed Sabur ,  Jonathan Lee ,  Lucia Terrenghi ,  Adrian Zumbrunnen

IPC: G06F9/54 ,  G10L15/26 ,  G06F3/16 ,  G06F40/35 ,  G06F40/166 ,  G10L15/22

Abstract: Implementations set forth herein relate to an automated assistant that can be invoked while a user is interfacing with a foreground application in order to retrieve data from one or more different applications, and then provide the retrieved data to the foreground application. A user can invoke the automated assistant while operating the foreground application by providing a spoken utterance, and the automated assistant can select one or more other applications to query based on content of the spoken utterance. Application data collected by the automated assistant from the one or more other applications can then be used to provide an input to the foreground application. In this way, the user can bypass switching between applications in the foreground in order to retrieve data that has been generated by other applications.

公开(公告)号：US20220130385A1

公开(公告)日：2022-04-28

申请号：US17569811

申请日：2022-01-06

Applicant: GOOGLE LLC

Inventor： Lucas Mirelmann ,  Zaheed Sabur ,  Bohdan Vlasyuk ,  Marie Patriarche Bledowski ,  Sergey NAZAROV ,  Denis Burakov ,  Behshad Behzadi ,  Michael Golikov ,  Steve CHENG ,  Daniel Cotting ,  Mario Bertschler

IPC: G10L15/22 ,  G10L15/08

Abstract: Implementations herein relate to pre-caching data, corresponding to predicted interactions between a user and an automated assistant, using data characterizing previous interactions between the user and the automated assistant. An interaction can be predicted based on details of a current interaction between the user and an automated assistant. One or more predicted interactions can be initialized, and/or any corresponding data pre-cached, prior to the user commanding the automated assistant in furtherance of the predicted interaction. Interaction predictions can be generated using a user-parameterized machine learning model, which can be used when processing input(s) that characterize a recent user interaction with the automated assistant. Should the user command the automated assistant in a way that is aligned with a pre-cached, predicted interaction, the automated assistant will exhibit instant fulfillment of the command, thereby eliminating any latency that the user would have otherwise experienced interacting with the automated assistant.