US 12,243,527 B2
Display mode dependent response generation with latency considerations
Jian Wei Leong, San Francisco, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by GOOGLE LLC, Mountain View, CA (US)
Filed on Oct. 11, 2023, as Appl. No. 18/378,800.
Application 18/378,800 is a continuation of application No. 17/471,695, filed on Sep. 10, 2021, granted, now 11,823,675.
Application 17/471,695 is a continuation of application No. 16/461,424, granted, now 11,120,796, issued on Sep. 14, 2021, previously published as PCT/US2017/054931, filed on Oct. 3, 2017.
Prior Publication US 2024/0038232 A1, Feb. 1, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/22 (2006.01); G06F 3/16 (2006.01); G10L 15/18 (2013.01)
CPC G10L 15/22 (2013.01) [G06F 3/165 (2013.01); G06F 3/167 (2013.01); G10L 15/1822 (2013.01); G10L 2015/223 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, the method comprising:
receiving, at a client device, a first input audio signal from a user;
transmitting, over a network and to a data processing system, data packets corresponding to the first input audio signal and first client device configuration data corresponding to the client device, wherein the first client device configuration data reflects that a display of the client device corresponds with an OFF state;
receiving, over the network, based on the data processing system processing the first data packets, a first response data structure including audio data and not including video data, wherein the data processing system:
determines, based on the first client configuration data, that the display associated with the client device is in the OFF state,
processes, using natural language understanding, the first input audio signal to identify a first request and a first trigger keyword corresponding to the first request, and
generates, responsive to the first request, and based on the first trigger keyword and the OFF state of the display, the first response data structure; and
providing, at the client device and based on the audio data of first response data structure, output to the user, wherein the output is audible.