US 12,079,576 B2
Unsupervised extraction of trends from call center transcripts
Yonatan Ben-Simhon, Tel Aviv (IL); Nitzan Gado, Tel Aviv (IL); Ido Farhi, Tel Aviv (IL); and Alexander Zhicharevich, Tel Aviv (IL)
Assigned to INTUIT INC., Mountain View, CA (US)
Filed by INTUIT INC., Mountain View, CA (US)
Filed on Sep. 30, 2021, as Appl. No. 17/491,191.
Prior Publication US 2023/0107118 A1, Apr. 6, 2023
Int. Cl. G06F 16/35 (2019.01); G06F 40/284 (2020.01)
CPC G06F 40/284 (2020.01) [G06F 16/35 (2019.01)] 18 Claims
OG exemplary drawing
 
1. A method performed by a processor, said method comprising:
for a set of phone call transcripts generated over a time period, discretizing the time period into a plurality of time spans;
generating a subset of the plurality of time spans by filtering out time spans with less than a threshold number of phone call transcripts;
extracting n-grams from the phone call transcripts corresponding to the subset of the plurality of time spans;
contextually clustering the extracted n-grams, wherein the contextual clustering generates clusters of similar n-grams;
determining normalized occurrences of the generated clusters in the subset of the plurality of time spans; and
based on the normalized occurrences and historical occurrences, determining whether a cluster is trending.