US 12,462,801 B2
Processing complex utterances for natural language understanding
Cengiz Erbas, Acton, MA (US); Thomas Kollar, San Jose, CA (US); Avnish Sikka, Acton, MA (US); Spyridon Matsoukas, Hopkinton, MA (US); and Simon Peter Reavely, Lexington, MA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Aug. 8, 2022, as Appl. No. 17/882,874.
Application 16/368,399 is a division of application No. 15/280,430, filed on Sep. 29, 2016, abandoned.
Application 17/882,874 is a continuation of application No. 16/368,399, filed on Mar. 28, 2019, granted, now 11,410,646.
Prior Publication US 2023/0032575 A1, Feb. 2, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/22 (2006.01); G10L 15/02 (2006.01); G10L 15/06 (2013.01); G10L 15/18 (2013.01)
CPC G10L 15/22 (2013.01) [G10L 15/02 (2013.01); G10L 15/063 (2013.01); G10L 15/1822 (2013.01); G10L 2015/223 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
determining, by a computing system, that an input utterance includes a first portion corresponding to a command and a second portion corresponding to a condition;
based at least in part on the command, sending, via a network, a first signal that causes a first component to transition from a first state to a second state, wherein the condition is initially not satisfied when the first component is in the second state;
after the first component has transitioned to the second state, determining, by the computing system, that the condition has become satisfied; and
based at least in part on the condition having become satisfied, sending, via the network, a second signal that causes the first component to transition from the second state to the first state.