	US 12,277,931 B2
	Predictive query execution
Raphael Tang, Washington, DC (US); Karun Kumar, Hyattsville, MD (US); Kendra Chalkley, Portland, OR (US); Wenyan Li, Arlington, VA (US); Liming Zhang, Reston, VA (US); Gefei Yang, Annadale, VA (US); Yajie Mao, Arlington, VA (US); Jun Ho Shin, Gaithersburg, MD (US); and Geoffrey Murray, Bethesda, MD (US)
Assigned to Comcast Cable Communications, LLC, Philadelphia, PA (US)
Filed by Comcast Cable Communications, LLC, Philadelphia, PA (US)
Filed on Nov. 9, 2021, as Appl. No. 17/454,234.
Prior Publication US 2023/0142836 A1, May 11, 2023
Int. Cl. G10L 15/00 (2013.01); G06F 16/432 (2019.01); G06F 16/683 (2019.01); G10L 15/16 (2006.01); G10L 15/197 (2013.01); G10L 15/22 (2006.01); G10L 15/30 (2013.01)

CPC G10L 15/197 (2013.01) [G06F 16/433 (2019.01); G06F 16/685 (2019.01); G10L 15/16 (2013.01); G10L 15/22 (2013.01); G10L 15/30 (2013.01)]

24 Claims

1. A method comprising:

receiving first audio data associated with a first portion of a voice query;

determining, based on the first audio data, a first transcript of the first audio data;

determining, based on the first transcript, a plurality of predicted queries;

determining, based on the plurality of the predicted queries, a response for each of the plurality of predicted queries;

receiving second audio data associated with a second portion of the voice query;

determining, based on the second audio data, a second transcript of the second audio data; and

causing output, based on comparing the second transcript of the second audio data to one of the plurality of predicted queries, of a response corresponding to the one of the plurality of predicted queries.