| CPC G06F 40/40 (2020.01) [G06F 16/355 (2019.01); G06F 40/131 (2020.01); G06F 40/289 (2020.01)] | 18 Claims |
|
1. A method comprising:
training a language model to output a predicted word of an utterance, using training utterances from a set of training transcripts, wherein training the language model comprises:
converting, by an encoder layer of the language model, the training utterances to encoder values,
generating, by an attention layer of the language model, attention values using the encoder values, and
generating the predicted word for the utterance based on the attention values to obtain a trained language model;
selecting a set of selected transcripts from the set of training transcripts based on training transcript scores;
filtering the training utterances of the set of selected transcripts using the attention values obtained from the trained language model to obtain filtered training utterances;
clustering the filtered training utterances using the encoder values obtained from the trained language model to obtain clusters of training utterances;
grouping the clusters of training utterances into topics;
assigning topic labels to the topics to generate topic label-training utterance pairs;
training a classifier model with the topic label-training utterance pairs to output a predicted topic label for a training utterance;
receiving an utterance from a transcript from a communication session;
processing the utterance with the trained classifier model to identify a topic label for the utterance;
and
routing the communication session using the topic label for the utterance.
|