US 12,067,986 B2
Embedded instructions for voice user interface
Manoj Sindhwani, Seattle, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Mar. 17, 2023, as Appl. No. 18/185,485.
Application 18/185,485 is a continuation of application No. 16/909,431, filed on Jun. 23, 2020, granted, now 11,610,585.
Application 16/909,431 is a continuation of application No. 16/158,428, filed on Oct. 12, 2018, granted, now 10,720,159, issued on Jul. 21, 2020.
Application 16/158,428 is a continuation of application No. 15/473,818, filed on Mar. 30, 2017, granted, now 10,102,855, issued on Oct. 16, 2018.
Prior Publication US 2023/0290351 A1, Sep. 14, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/00 (2013.01); G06F 3/16 (2006.01); G06F 40/134 (2020.01); G06F 40/169 (2020.01); G06F 40/279 (2020.01); G06Q 10/087 (2023.01); G06Q 30/0601 (2023.01); G10L 15/22 (2006.01); G06F 16/951 (2019.01)
CPC G10L 15/22 (2013.01) [G06F 3/167 (2013.01); G06F 40/134 (2020.01); G06F 40/169 (2020.01); G06F 40/279 (2020.01); G06Q 10/087 (2013.01); G06Q 30/0635 (2013.01); G06F 16/951 (2019.01); G10L 2015/223 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving first input audio data representing an utterance;
performing speech processing on the first input audio data to determine a first request to output data corresponding to a plurality of steps of a first process, the plurality of steps including at least a first step, a second step, and a third step;
causing a first device to present first output data corresponding to the first step;
receiving input data corresponding to a second process corresponding to the second step;
determining second output data corresponding to the second process; and
after receiving the input data corresponding to the second process, causing the first device to present third output data corresponding to the third step.