US 12,141,672 B2
Delayed responses by computational assistant
Yariv Adan, Cham (CH); Vladimir Vuskovic, Zollikerberg (CH); and Behshad Behzadi, Freienbach (CH)
Assigned to GOOGLE LLC, Moutain View, CA (US)
Filed by GOOGLE LLC, Mountain View, CA (US)
Filed on Sep. 13, 2023, as Appl. No. 18/367,828.
Application 18/367,828 is a continuation of application No. 17/982,815, filed on Nov. 8, 2022, granted, now 11,790,207.
Application 17/982,815 is a continuation of application No. 17/330,892, filed on May 26, 2021, granted, now 11,521,037, issued on Dec. 6, 2022.
Application 17/330,892 is a continuation of application No. 15/847,341, filed on Dec. 19, 2017, granted, now 11,048,995, issued on Jun. 29, 2021.
Claims priority of provisional application 62/506,999, filed on May 16, 2017.
Prior Publication US 2024/0005125 A1, Jan. 4, 2024
Int. Cl. G06N 3/006 (2023.01); G06F 3/16 (2006.01); G06F 16/332 (2019.01); G06Q 10/02 (2012.01); G06Q 10/0631 (2023.01); G10L 13/00 (2006.01); G10L 15/22 (2006.01); H04M 3/493 (2006.01)
CPC G06N 3/006 (2013.01) [G06F 3/167 (2013.01); G06F 16/3329 (2019.01); G06Q 10/02 (2013.01); G06Q 10/063114 (2013.01); G10L 15/22 (2013.01); G10L 13/00 (2013.01); G10L 2015/223 (2013.01); H04M 3/4936 (2013.01); H04M 2203/355 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A system comprising:
at least one processor; and
memory storing instructions that, when executed, the at least one processor is operable to:
receive a representation of an utterance directed to a computing device;
identify, based on the utterance, a task to be completed by a computational assistant executing at least in part at the computing device;
determine whether the task to be completed by the computational assistant involves using extensive machine learning models;
in response to determining that the task to be completed by the computational assistant involves extensive computation using the extensive machine learning models:
cause, to be output for playback by one or more speakers operably connected to the computing device, synthesized voice data that informs the user of the computing device that completing performance of the task will not be immediate; and
subsequent to the computational assistant performing the extensive computation:
cause, to be output for playback by one or more of the speakers operably connected to the computing device, additional synthesized voice data that informs the user of the computing device that performance of the task is completed.