US 12,106,759 B2
Initializing non-assistant background actions, via an automated assistant, while accessing a non-assistant application
Denis Burakov, Zurich (CH); Behshad Behzadi, Freienbach (CH); Mario Bertschler, Zurich (CH); Bohdan Vlasyuk, Zurich (CH); Daniel Cotting, Islisberg (CH); Michael Golikov, Merlischachen (CH); Lucas Mirelmann, Zurich (CH); Steve Cheng, Los Altos, CA (US); Sergey Nazarov, Zurich (CH); Zaheed Sabur, Baar (CH); Marcin Nowak-Przygodzki, Bäch (CH); Mugurel Ionut Andreica, Adliswil (CH); and Radu Voroneanu, Zurich (CH)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Jan. 31, 2022, as Appl. No. 17/588,481.
Application 17/588,481 is a continuation of application No. 16/614,224, granted, now 11,238,868, previously published as PCT/US2019/036932, filed on Jun. 13, 2019.
Claims priority of provisional application 62/843,987, filed on May 6, 2019.
Prior Publication US 2022/0157317 A1, May 19, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/22 (2006.01); G06F 3/16 (2006.01); G10L 15/26 (2006.01)
CPC G10L 15/26 (2013.01) [G06F 3/167 (2013.01); G10L 15/22 (2013.01); G10L 2015/223 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method implemented by one or more processors, the method comprising:
receiving, at a third-party application and while another application is executing at a computing device, a request from an automated assistant to provide application data characterizing one or more actions capable of being performed by the third-party application,
wherein the request is provided by the automated assistant in response to a user providing one or more inputs to invoke the automated assistant while the other application is executing at the computing device;
providing, in response to receiving the request from the automated assistant, the application data to the automated assistant, wherein the application data identifies a particular action capable of being performed by the third-party application initialized via the automated assistant;
causing, based on providing the application to the automated assistant, the automated assistant to determine whether a spoken utterance provided by the user was directed at initializing performance of the particular action by the third-party application,
wherein the spoken utterance does not explicitly identify any application that is accessible via the computing device; and
when the automated assistant determines, based on the application data, that the spoken utterance was directed at the application:
causing, based on the action data, the automated assistant to initialize performance of the action via the application.