-
公开(公告)号:US12118316B2
公开(公告)日:2024-10-15
申请号:US17712040
申请日:2022-04-01
发明人: Yipeng Shi , Peng Su , Junqing Wang
IPC分类号: G06F40/30 , G06Q30/0201 , G10L17/00 , H04L12/18
CPC分类号: G06F40/30 , G06Q30/0201 , G10L17/00 , H04L12/1831
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.
-
公开(公告)号:US20240054289A9
公开(公告)日:2024-02-15
申请号:US17719314
申请日:2022-04-12
发明人: Peng Su , Ling Tsou , Junqing Wang , Tong Wang
IPC分类号: G06F40/295 , G06F40/205 , H04L12/18 , G06N20/00 , G06F40/40
CPC分类号: G06F40/295 , G06F40/205 , H04L12/1831 , G06N20/00 , G06F40/40
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.
-
公开(公告)号:US20240129150A1
公开(公告)日:2024-04-18
申请号:US18538599
申请日:2023-12-13
发明人: Cècile Boucheron , Ganna Isayeva , Sharvari Nerurkar , Yoshifumi Takebuchi , Junqing Wang , Yuchen Zhang
IPC分类号: H04L12/18 , G06Q10/1093
CPC分类号: H04L12/1831 , G06Q10/1095 , H04L12/1822
摘要: Methods, systems, and apparatus, including computer programs encoded on computer storage media related to a method for dynamic sharing of meeting assets within a messaging platform. A communication system receives one or more meeting assets that are associated with a meeting that was conducted via a video communication platform. After the meeting has ended, the communication system generates a meeting summary component configured to be displayed within the messaging platform. The meeting summary component may include information describing the meeting and meeting assets. The meeting summary component may be posted into a messaging channel of the messaging platform.
-
公开(公告)号:US20230237270A1
公开(公告)日:2023-07-27
申请号:US17719314
申请日:2022-04-12
发明人: Peng Su , Ling Tsou , Junqing Wang , Tong Wang
IPC分类号: G06F40/295 , G06F40/205 , H04L12/18 , G06N20/00 , G06F40/40
CPC分类号: G06F40/295 , G06F40/205 , H04L12/1831 , G06N20/00 , G06F40/40
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.
-
公开(公告)号:US11888634B2
公开(公告)日:2024-01-30
申请号:US17472568
申请日:2021-09-10
发明人: Cécile Boucheron , Ganna Isayeva , Sharvari Nerurkar , Yoshifumi Takebuchi , Junqing Wang , Yuchen Zhang
IPC分类号: H04L12/18 , G06Q10/10 , G06Q10/1093
CPC分类号: H04L12/1831 , G06Q10/1095 , H04L12/1822
摘要: Methods, systems, and apparatus, including computer programs encoded on computer storage media related to a method for dynamic sharing of meeting assets within a messaging platform. A communication system receives one or more meeting assets that are associated with a meeting that was conducted via a video communication platform. After the meeting has ended, the communication system generates a meeting summary component configured to be displayed within the messaging platform. The meeting summary component may include information describing the meeting and meeting assets. The meeting summary component may be posted into a messaging channel of the messaging platform.
-
公开(公告)号:US20230244874A1
公开(公告)日:2023-08-03
申请号:US17712040
申请日:2022-04-01
发明人: Yipeng Shi , Peng Su , Junqing Wang
CPC分类号: G06F40/30 , G06Q30/0201 , G10L17/00 , H04L12/1831
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.
-
公开(公告)号:US20230230589A1
公开(公告)日:2023-07-20
申请号:US17589829
申请日:2022-01-31
发明人: Davide Giovanardi , Vijay Parthasarathy , Xiaoli Song , Peng Su , Junqing Wang
IPC分类号: G10L15/22 , G06F40/284 , G06F40/117 , G06F40/166 , G10L15/06 , G10L15/02 , G06F40/253 , G06F40/211 , G10L25/57
CPC分类号: G10L15/22 , G06F40/284 , G06F40/117 , G06F40/166 , G10L15/063 , G10L15/02 , G06F40/253 , G06F40/211 , G10L25/57
摘要: Methods and systems provide for extracting engaging questions from 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; extracts engaging questions within the subset of utterances, the engaging questions each including a question asked by the participant associated with the organization that is immediately answered in the following utterance by a participant not associated with the organization; and presents, for display at one or more client devices, data corresponding to the extracted engaging questions.
-
-
-
-
-
-