US 11,783,814 B2
Efficient and low latency automated assistant control of smart devices
David Roy Schairer, San Jose, CA (US); Di Lin, Sunnyvale, CA (US); and Lucas Palmer, Windsor (CA)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by GOOGLE LLC, Mountain View, CA (US)
Filed on Oct. 21, 2021, as Appl. No. 17/506,809.
Application 17/506,809 is a continuation of application No. 16/973,392, granted, now 11,176,928, previously published as PCT/US2019/065808, filed on Dec. 11, 2019.
Claims priority of provisional application 62/915,158, filed on Oct. 15, 2019.
Prior Publication US 2022/0044677 A1, Feb. 10, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/18 (2013.01); G10L 15/22 (2006.01); G10L 15/30 (2013.01)
CPC G10L 15/1815 (2013.01) [G10L 15/22 (2013.01); G10L 15/30 (2013.01); G10L 2015/223 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method implemented by one or more processors of a client device, the method comprising:
storing, in a cache on the client device: a cache entry that includes a mapping of text to a semantic representation, wherein the semantic representation includes a locally interpretable semantic representation that is locally interpretable by the client device;
capturing, at the client device, audio data that captures a spoken utterance;
processing, using a voice-to-text model stored locally on the client device, the audio data to generate current text that corresponds to the spoken utterance;
determining that the current text matches the text of the cache entry; and
in response to determining that the current text matches the text of the cache entry, and in response to the cache entry including the mapping of the text to the semantic representation:
processing, at the client device, the locally interpretable semantic representation to generate a given control command, the given control command differing from the locally interpretable semantic representation,
wherein the given control command is generated responsive to a determination that the locally interpretable semantic representation is not locally interpretable by a given smart device; and
transmitting, via a local channel, the given control command to cause the altering of at least the given state of the given smart device.