US 11,893,526 B2
Customer contact service with real-time supervisor assistance
Swaminathan Sivasubramanian, Sammamish, WA (US); Vasanth Philomin, Seattle, WA (US); Vikram Anbazhagan, Issaquah, WA (US); Ashish Singh, Sammamish, WA (US); Atul Deo, Kirkland, WA (US); Anuroop Arora, Seattle, WA (US); Colin Thomas Davidson, Bellevue, WA (US); Jessie Young, Seattle, WA (US); and Yasser El-Haggan, Columbia, MD (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Nov. 27, 2019, as Appl. No. 16/698,470.
Prior Publication US 2021/0158235 A1, May 27, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/00 (2013.01); G10L 15/26 (2006.01); G06Q 10/0633 (2023.01); G06F 16/683 (2019.01); H04M 3/51 (2006.01); G10L 15/18 (2013.01); G06F 40/16 (2020.01); G10L 15/08 (2006.01)
CPC G06Q 10/0633 (2013.01) [G06F 16/685 (2019.01); G06F 40/16 (2020.01); G10L 15/1815 (2013.01); G10L 15/26 (2013.01); H04M 3/5191 (2013.01); G10L 2015/088 (2013.01); H04M 2203/357 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
connecting a first service to a plurality of audio streams of calls between agents and customers;
obtaining a plurality of audio data for the calls at the first service;
using a second service to generate transcripts for a plurality of audio data, wherein a turn of the transcripts is reconstructed based at least in part on a first fragment of the transcripts and a second fragment of the transcripts that correspond to each of the plurality of audio that that was obtained at a different time;
as a result of determining that the turn of the transcripts is reconstructed, analyzing the transcripts with a third service to generate a set of natural language processing (NLP) outputs encoding audio characteristics associated with the transcripts;
tagging the transcripts with categories based at least in part on the set of NLP outputs, wherein the categories are defined based at least in part on rules that evaluate content and audio characteristics, and at least one of the rules is determined by a supervisor of the agents;
generating a notification for the plurality of audio streams based on the categories, where the notification identifies a new pattern from at least two of the plurality of audio streams during a specified period; and
providing the notification to the supervisor.