US 11,694,682 B1
Triggering voice control disambiguation
Julia Reinspach, Seattle, WA (US); Oleg Rokhlenko, Kirkland, WA (US); Ramakanthachary Gottumukkala, Sammamish, WA (US); Giovanni Clemente, Seattle, WA (US); Ankit Agrawal, Bellevue, WA (US); Swayam Bhardwaj, Seattle, WA (US); Guy Michaeli, Seattle, WA (US); Vaidyanathan Puthucode Krishnamoorthy, Seattle, WA (US); Costantino Vlachos, Seattle, WA (US); Nalledath P. Vinodkrishnan, Bellevue, WA (US); Shaun M. Vickers, Seattle, WA (US); Sethuraman Ramachandran, Issaquah, WA (US); and Charles C. Moore, Mercer Island, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Reno, NV (US)
Filed on Dec. 11, 2019, as Appl. No. 16/711,043.
Int. Cl. G10L 15/22 (2006.01); G10L 15/30 (2013.01); G06F 3/16 (2006.01); G06F 3/0484 (2022.01); G06Q 30/06 (2012.01); G06F 3/0481 (2022.01); G10L 15/19 (2013.01); G10L 15/18 (2013.01); G06Q 30/0601 (2023.01)
CPC G10L 15/22 (2013.01) [G06F 3/0481 (2013.01); G06F 3/0484 (2013.01); G06F 3/167 (2013.01); G06Q 30/0625 (2013.01); G10L 15/1815 (2013.01); G10L 15/19 (2013.01); G10L 15/222 (2013.01); G10L 15/30 (2013.01); G10L 2015/223 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving utterance data associated with a voice request;
determining a type of request that the utterance data is directed to, the type of request associated with an action to be performed for information or control using a plurality of processing steps;
perform at least one of the plurality of processing steps;
detecting an error based at least in part on one or more of the plurality of processing steps;
determining, based on a model, to request additional user input associated with the error; and
causing the voice-enabled device or a second client device to output a request for the additional user input.