US 12,437,760 B2
Generating and/or causing rendering of video playback-based assistant suggestion(s) that link to other application(s)
Wendy Look, Zurich (CH); Evgeny Cherepanov, Adliswil (CH); Olga Kapralova, Bern (CH); Dan Vallejo, New York, NY (US); and Mikhail Reutov, Zug (CH)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by GOOGLE LLC, Mountain View, CA (US)
Filed on Aug. 18, 2023, as Appl. No. 18/235,707.
Claims priority of provisional application 63/399,105, filed on Aug. 18, 2022.
Prior Publication US 2024/0062757 A1, Feb. 22, 2024
Int. Cl. G10L 15/00 (2013.01); G06F 3/0482 (2013.01); G06Q 10/1093 (2023.01); G10L 15/22 (2006.01); H04N 21/431 (2011.01); H04N 21/472 (2011.01)
CPC G10L 15/22 (2013.01) [G06F 3/0482 (2013.01); G06Q 10/1095 (2013.01); H04N 21/4316 (2013.01); H04N 21/47217 (2013.01); G10L 2015/223 (2013.01)] 20 Claims
OG exemplary drawing
 
9. A method implemented by one or more processors, the method comprising:
causing, by a video application, a first portion of an application interface of the video application to provide playback of video content,
wherein the video content is rendered at a display interface of a computing device;
receiving, based on the playback of the video content, assistant data that characterizes an action that can be initialized by an automated assistant, which is separate from the video application,
wherein the action is associated with the video content, and a user who is associated with the automated assistant;
causing a second portion of the application interface of the video application to render a selectable element that, when selected, causes the automated assistant to initialize performance of the action,
wherein the automated assistant is accessible separately from the video application;
receiving, by the video application, a selection of the selectable element,
wherein the selection is received via an interface of the computing device, which provides access to the video application and the automated assistant; and
causing, based on the selection of the selectable element, the automated assistant to initialize performance of the action,
wherein performance of the action involves the automated assistant communicating with an additional application that is separate from the automated assistant and that is also separate from the video application.
 
14. A method implemented by one or more processors, the method comprising:
determining, by an automated assistant, that video content is being rendered at a display interface of a computing device for a user,
wherein the video content is rendered by a video application that is a separate application from the automated assistant;
generating, based on the video content, relevance data that characterizes relevance of the video content to assistant data that is associated with the user,
wherein the assistant data includes multiple different instances of data that are associated with the user, and the relevance data indicates a relevance of at least one instance of data, of the multiple different instances of data, to the video content;
determining whether the relevance of the at least one instance of data to the video content satisfies a relevance threshold; and
when the relevance of the at least one instance of data satisfies the relevance threshold:
causing a portion of a graphical user interface (GUI) of the video application to render one or more selectable elements based on the at least one instance of data,
wherein a selection of a particular selectable element of the one or more selectable elements causes the automated assistant to initialize performance of one or more actions using the at least one instance of data.