Sentiment scoring for remote communication sessions

    公开(公告)号:US12118316B2

    公开(公告)日:2024-10-15

    申请号:US17712040

    申请日:2022-04-01

    摘要: Methods and systems provide for presenting sentiment scores within a communication session. In one embodiment, the system connects to a communication session with a number of participants; receives a transcript of a conversation between the participants produced during the communication session; extracts, from the transcript, utterances including one or more sentences spoken by the participants; identifies a subset of the utterances spoken by a subset of the participants associated with a prespecified organization; for each utterance, determines a word sentiment score for each word in the utterance, and determines an utterance sentiment score based on the word sentiment scores; determines an overall sentiment score for the conversation based on the utterance sentiment scores; and presenting, to one or more client devices, at least the overall sentiment score for the conversation.

    INTELLIGENT TOPIC SEGMENTATION WITHIN A COMMUNICATION SESSION

    公开(公告)号:US20240054289A9

    公开(公告)日:2024-02-15

    申请号:US17719314

    申请日:2022-04-12

    摘要: Methods and systems provide for providing intelligent topic segmentation within a communication session. In one embodiment, the system connects to a communication session with a number of participants; receives a transcript of a conversation between the participants produced during the communication session, the transcript including timestamps for a number of utterances associated with speaking participants; shifts a window over the utterances to generate blocks of utterances; for each shift of the window over one utterance, identifies topic model (“TM”) clusters (hereinafter “TM clusters”) and generates TM cluster scores to assign text labels for each cluster; aggregates the scores for the TM clusters to generate a number of utterance level scores; converts the utterance level scores into topic segments each including a start time, end time, and associated text label; and transmits, to one or more client devices, a list of the topic segments for the communication session.

    INTELLIGENT TOPIC SEGMENTATION WITHIN A COMMUNICATION SESSION

    公开(公告)号:US20230237270A1

    公开(公告)日:2023-07-27

    申请号:US17719314

    申请日:2022-04-12

    摘要: Methods and systems provide for providing intelligent topic segmentation within a communication session. In one embodiment, the system connects to a communication session with a number of participants; receives a transcript of a conversation between the participants produced during the communication session, the transcript including timestamps for a number of utterances associated with speaking participants; shifts a window over the utterances to generate blocks of utterances; for each shift of the window over one utterance, identifies topic model (“TM”) clusters (hereinafter “TM clusters”) and generates TM cluster scores to assign text labels for each cluster; aggregates the scores for the TM clusters to generate a number of utterance level scores; converts the utterance level scores into topic segments each including a start time, end time, and associated text label; and transmits, to one or more client devices, a list of the topic segments for the communication session.

    SENTIMENT SCORING FOR REMOTE COMMUNICATION SESSIONS

    公开(公告)号:US20230244874A1

    公开(公告)日:2023-08-03

    申请号:US17712040

    申请日:2022-04-01

    摘要: Methods and systems provide for presenting sentiment scores within a communication session. In one embodiment, the system connects to a communication session with a number of participants; receives a transcript of a conversation between the participants produced during the communication session; extracts, from the transcript, utterances including one or more sentences spoken by the participants; identifies a subset of the utterances spoken by a subset of the participants associated with a prespecified organization; for each utterance, determines a word sentiment score for each word in the utterance, and determines an utterance sentiment score based on the word sentiment scores; determines an overall sentiment score for the conversation based on the utterance sentiment scores; and presenting, to one or more client devices, at least the overall sentiment score for the conversation.