US 11,934,443 B2
Media consumption context for personalized instant query suggest
Dhruv Bakshi, Zurich (CH); and Jakob Nicolaus Foerster, Zurich (CH)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by GOOGLE LLC, Mountain View, CA (US)
Filed on Aug. 23, 2021, as Appl. No. 17/409,549.
Application 17/409,549 is a continuation of application No. 15/970,230, filed on May 3, 2018, abandoned.
Application 15/970,230 is a continuation of application No. 14/875,855, filed on Oct. 6, 2015, granted, now 9,984,075, issued on May 29, 2018.
Prior Publication US 2021/0382930 A1, Dec. 9, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 7/00 (2006.01); G06F 16/435 (2019.01); G06F 16/951 (2019.01); G06F 16/9535 (2019.01); G06F 16/9538 (2019.01)
CPC G06F 16/435 (2019.01) [G06F 16/951 (2019.01); G06F 16/9535 (2019.01); G06F 16/9538 (2019.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving, by a digital assistant device, a spoken request that includes one or more terms, the spoken request being spoken by a user of the digital assistant device; and
in response to determining that an autocompletion, of the one or more terms included in the spoken request, includes a trigger term, the autocompletion including an additional term that is not included in the spoken request:
obtaining background audio data captured by a microphone of the digital assistant device during a time window that is associated with the trigger term, wherein the time window is prior to the spoken request and has a particular length that is based on the trigger term, the background audio data capturing playback of media content during the time window;
providing the background audio data and the trigger term to an entity search system that searches an entity database based on the background audio data to identify an entity associated with an item of media content;
generating a prompt based at least on (i) the autocompletion of the one or more terms and (ii) the entity identified by the entity search system, wherein the prompt comprises at least two suggested search queries based on the spoken request that includes the one or more terms, each of the at least two suggested search queries being based on one or more entities that are associated with the item of media content; and
providing, by the digital assistant device, a synthesized audio representation of the prompt for output.