US 11,817,095 B2
Ambient cooperative intelligence system and method
Paul Joseph Vozila, Arlington, MA (US); and Neal Snider, Belmont, MA (US)
Assigned to Nuance Communications, Inc., Burlington, MA (US)
Filed by Nuance Communications, Inc., Burlington, MA (US)
Filed on Feb. 3, 2022, as Appl. No. 17/592,353.
Application 17/592,353 is a continuation of application No. 17/133,199, filed on Dec. 23, 2020, granted, now 11,250,855.
Prior Publication US 2022/0199082 A1, Jun. 23, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/22 (2006.01); G06N 20/00 (2019.01); G10L 15/18 (2013.01); G10L 15/08 (2006.01)
CPC G10L 15/22 (2013.01) [G06N 20/00 (2019.01); G10L 15/1815 (2013.01); G10L 2015/088 (2013.01); G10L 2015/223 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method, executed on a computing device, comprising:
monitoring a plurality of conversations to generate a conversation data set;
processing the conversation data set to:
define a system-directed command, and
associate one or more conversational contexts with the system-directed command, wherein associating one or more conversational contexts with the system-directed command includes identifying a subject matter of a conversation preceding an occurrence of a wake-up word/phrase and defining at least one of the conversational contexts based, at least in part, upon the subject matter of the conversation preceding the occurrence of the wake-up word/phrase;
detecting the occurrence of a specific conversational context, wherein the specific conversational context is included in the one or more conversational contexts associated with the system-directed command, and wherein the system-directed command is determined based, at least in part, upon the at least one of the conversational contexts defined based, at least in part, upon the subject matter of the conversation preceding the occurrence of the wake-up word/phrase; and
automatically executing, in whole or in part, functionality associated with the system-directed command in response to detecting the occurrence of the specific conversational context without requiring the utterance of the system-directed command and/or the wake-up word/phrase, including processing the conversational context to yield a confidence level with respect to the system-directed command, and automatically executing functionality associated with the system-directed command when the confidence level exceeds a confidence level threshold.