US 11,875,790 B2
Dynamically adapting assistant responses
Tanya Kraljic, Ridgewood, NJ (US); Miranda Callahan, New York, NY (US); Yi Sing Alex Loh, New York, NY (US); and Darla Sharp, Alameda, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Appl. No. 16/621,371
Filed by Google LLC, Mountain View, CA (US)
PCT Filed Mar. 1, 2019, PCT No. PCT/US2019/020394
§ 371(c)(1), (2) Date Sep. 23, 2020,
PCT Pub. No. WO2020/180286, PCT Pub. Date Sep. 10, 2020.
Prior Publication US 2021/0082420 A1, Mar. 18, 2021
Int. Cl. G10L 15/22 (2006.01); G10L 13/02 (2013.01); G10L 15/18 (2013.01); G10L 15/30 (2013.01)
CPC G10L 15/22 (2013.01) [G10L 13/02 (2013.01); G10L 15/1815 (2013.01); G10L 15/30 (2013.01); G10L 2015/223 (2013.01); G10L 2015/228 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method implemented by one or more processors, the method comprising:
receiving user input, wherein the user input is provided by a user at an automated assistant interface of a client device, and wherein the automated assistant interface is an interface for interacting with an automated assistant executing on the client device and/or one or more remote computing devices;
processing the user input to determine at least one intent associated with the user input, wherein the at least one intent corresponds to controlling one or more connected smart devices;
generating a familiarity measure for the at least one intent, wherein generating the familiarity measure for the at least one intent comprises:
processing, using a machine learning model, a plurality of parameters to generate the familiarity measure,
wherein the plurality of parameters processed using the machine learning model to generate the familiarity measure include one or more intent specific parameters that are based on historical interactions, of the user with the automated assistant in controlling the one or more connected smart devices, for the at least one intent specified by the user input,
wherein the familiarity measure dynamically changes over time based on changes to the historical interactions, and
wherein the familiarity measure dynamically changing includes both increasing and decreasing over time based on changes to the historical interactions;
determining a response, of the automated assistant to the user input, based on the familiarity measure and based on the at least one intent; and
causing the client device to render the determined response.