CPC H04L 12/1831 (2013.01) [G10L 15/04 (2013.01); G10L 15/08 (2013.01); G10L 15/1815 (2013.01); G10L 15/26 (2013.01); H04L 12/1818 (2013.01); G10L 2015/088 (2013.01)] | 20 Claims |
1. A method, comprising:
receiving a list of topics;
receiving a conversation transcript that includes one or more transcriptions of utterances transmitted between a plurality of participant user accounts during a communication session comprising an online virtual meeting, the transcript comprising at least one timestamp corresponding to a time within a time duration of the online virtual meeting at which a respective utterance occurred;
for each topic in the list of topics, segmenting the one or more utterances into one or more topic segments based on the topic, wherein the segmenting includes determining an utterance boundary based on a lexical score that is an inner product of two vectors associated with an adjacent pair of text blocks, wherein a vector contains a number of times a lexical item occurs within a corresponding text block;
for each of the topic segments:
classifying whether the respective topic segment is related to the topic;
determining that the respective topic segment is related to the topic; and
identifying a respective start time and a respective end time of each respective topic segment; and
transmitting, to one or more client devices, a list of the topic segments, the list of topic segments including a start and an end time for at least one of the topic segments.
|