US 12,086,168 B2
Contextual voice search suggestions
Vikram Aggarwal, Palo Alto, CA (US); and Aparna Rajan Ramchandran, San Francisco, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by GOOGLE LLC, Mountain View, CA (US)
Filed on Jan. 24, 2022, as Appl. No. 17/582,822.
Application 17/582,822 is a continuation of application No. 15/194,153, filed on Jun. 27, 2016, granted, now 11,232,136.
Prior Publication US 2022/0222282 A1, Jul. 14, 2022
Int. Cl. G06F 16/332 (2019.01); G06F 3/0484 (2022.01); G06F 3/16 (2006.01); G06F 9/451 (2018.01); G06F 16/31 (2019.01); G06F 16/33 (2019.01); G06F 16/35 (2019.01); G06F 40/279 (2020.01); G06F 40/30 (2020.01); G06V 30/224 (2022.01)
CPC G06F 16/3322 (2019.01) [G06F 3/0484 (2013.01); G06F 3/167 (2013.01); G06F 9/453 (2018.02); G06F 16/313 (2019.01); G06F 16/334 (2019.01); G06F 16/35 (2019.01); G06F 40/279 (2020.01); G06F 40/30 (2020.01); G06V 30/224 (2022.01)] 19 Claims
OG exemplary drawing
 
10. A system comprising:
one or more computing devices and one or more storage devices storing instructions that are operable, when executed by the one or more computing devices, to cause the one or more computing devices to perform operations comprising:
receiving screen data indicating content displayed on a screen of an electronic device of a user;
determining, based on processing the screen data, at least one entity referenced in the content;
determining a suggested voice request that includes at least one pronoun referring to the at least one entity based on:
determining one or more respective classifications for the at least one entity based on accessing a knowledge graph defining entity classifications, and
determining one or more types of request formats that correspond to the one or more respective classifications for the at least one entity; and
providing the suggested voice request for audible or visual output to the user in response to both:
receiving an indication that the user provided user input to initiate access to digital assistant functionality while the content is currently displayed on the electronic device of the user, and
determining that the content included in the screen data references only a single entity or only a single entity of a particular entity classification.