-
公开(公告)号：US11783829B2
公开(公告)日：2023-10-10
申请号：US17244804
申请日：2021-04-29
Applicant: Outreach Corporation
Inventor： Rohit Ganpat Mane , Abhishek Abhishek , Krishnamohan Reddy Nareddy , Rajiv Garg
CPC classification number: G10L15/22 , G10L15/063 , G10L25/51
Abstract: Described herein is a system for automatically detecting and assigning action items in a real-time conversation and determining whether such action items have been completed. The system detects, during a meeting, a plurality of action items and an utterance that corresponds to a completed action item. Responsive to detecting the utterance, the system generates a similarity score with respect to a first action item of the plurality of action items. The system compares the similarity score to a first threshold. Responsive to determining that the similarity score does not exceed the first threshold, the system generates a second similarity score with respect to a second action item of the plurality of action items. The system compares the second similarity score to a second threshold, which exceeds the first threshold. Responsive to determining that the second similarity score exceeds the second threshold, the system marks the second action item as completed.
-
公开(公告)号：US20210343282A1
公开(公告)日：2021-11-04
申请号：US17244804
申请日：2021-04-29
Applicant: Outreach Corporation
Inventor： Rohit Ganpat Mane , Abhishek Abhishek , Krishnamohan Reddy Nareddy , Rajiv Garg
Abstract: Described herein is a system for automatically detecting and assigning action items in a real-time conversation and determining whether such action items have been completed. The system detects, during a meeting, a plurality of action items and an utterance that corresponds to a completed action item. Responsive to detecting the utterance, the system generates a similarity score with respect to a first action item of the plurality of action items. The system compares the similarity score to a first threshold. Responsive to determining that the similarity score does not exceed the first threshold, the system generates a second similarity score with respect to a second action item of the plurality of action items. The system compares the second similarity score to a second threshold, which exceeds the first threshold. Responsive to determining that the second similarity score exceeds the second threshold, the system marks the second action item as completed.
-
公开(公告)号：US12142276B2
公开(公告)日：2024-11-12
申请号：US18233304
申请日：2023-08-12
Applicant: Outreach Corporation
Inventor： Rohit Ganpat Mane , Abhishek Abhishek , Krishnamohan Reddy Nareddy , Rajiv Garg
Abstract: Described herein is a system for automatically detecting and assigning action items in a real-time conversation and determining whether such action items have been completed. The system detects, during a meeting, a plurality of action items and an utterance that corresponds to a completed action item. Responsive to detecting the utterance, the system generates a similarity score with respect to a first action item of the plurality of action items. The system compares the similarity score to a first threshold. Responsive to determining that the similarity score does not exceed the first threshold, the system generates a second similarity score with respect to a second action item of the plurality of action items. The system compares the second similarity score to a second threshold, which exceeds the first threshold. Responsive to determining that the second similarity score exceeds the second threshold, the system marks the second action item as completed.
-
Patent Agency Ranking
公开(公告)号：US20250029609A1
公开(公告)日：2025-01-23
申请号：US18908467
申请日：2024-10-07
Applicant: Outreach Corporation
Inventor： Rohit Ganpat Mane , Abhishek Abhishek , Krishnamohan Reddy Nareddy , Rajiv Garg
Abstract: Described herein is a system for automatically detecting and assigning action items in a real-time conversation and determining whether such action items have been completed. The system detects, during a meeting, a plurality of action items and an utterance that corresponds to a completed action item. Responsive to detecting the utterance, the system generates a similarity score with respect to a first action item of the plurality of action items. The system compares the similarity score to a first threshold. Responsive to determining that the similarity score does not exceed the first threshold, the system generates a second similarity score with respect to a second action item of the plurality of action items. The system compares the second similarity score to a second threshold, which exceeds the first threshold. Responsive to determining that the second similarity score exceeds the second threshold, the system marks the second action item as completed.
-
5.发明公开公开(公告)号：US20230386477A1
公开(公告)日：2023-11-30
申请号：US18233303
申请日：2023-08-12
Applicant: Outreach Corporation
Inventor： Krishnamohan Reddy Nareddy , Abhishek Abhishek , Rohit Ganpat Mane , Rajiv Garg
CPC classification number: G10L17/14 , G06F16/3344 , G06N20/00 , G06F16/9535
Abstract: A system and a method are disclosed for identifying a subjectively interesting moment in a transcript. In an embodiment, a device receives a transcription of a conversation, and identifies a participant of the conversation. The device accesses a machine learning model corresponding to the participant, and applies, as input to the machine learning model, the transcription. The device receives as output from the machine learning model a portion of the transcription having relevance to the participant, and generates for display, to the participant, information pertaining to the portion.
-
6.发明公开公开(公告)号：US20230386465A1
公开(公告)日：2023-11-30
申请号：US18233304
申请日：2023-08-12
Applicant: Outreach Corporation
Inventor： Rohit Ganpat Mane , Abhishek Abhishek , Krishnamohan Reddy Nareddy , Rajiv Garg
CPC classification number: G10L15/22 , G10L25/51 , G10L15/063
Abstract: Described herein is a system for automatically detecting and assigning action items in a real-time conversation and determining whether such action items have been completed. The system detects, during a meeting, a plurality of action items and an utterance that corresponds to a completed action item. Responsive to detecting the utterance, the system generates a similarity score with respect to a first action item of the plurality of action items. The system compares the similarity score to a first threshold. Responsive to determining that the similarity score does not exceed the first threshold, the system generates a second similarity score with respect to a second action item of the plurality of action items. The system compares the second similarity score to a second threshold, which exceeds the first threshold. Responsive to determining that the second similarity score exceeds the second threshold, the system marks the second action item as completed.
-
公开(公告)号：US11763823B2
公开(公告)日：2023-09-19
申请号：US17179125
申请日：2021-02-18
Applicant: Outreach Corporation
Inventor： Krishnamohan Reddy Nareddy , Abhishek Abhishek , Rohit Ganpat Mane , Rajiv Garg
IPC: G06F16/9535 , G10L17/14 , G06F16/33 , G06N20/00
CPC classification number: G10L17/14 , G06F16/3344 , G06N20/00 , G06F16/9535
Abstract: A system and a method are disclosed for identifying a subjectively interesting moment in a transcript. In an embodiment, a device receives a transcription of a conversation, and identifies a participant of the conversation. The device accesses a machine learning model corresponding to the participant, and applies, as input to the machine learning model, the transcription. The device receives as output from the machine learning model a portion of the transcription having relevance to the participant, and generates for display, to the participant, information pertaining to the portion.
-
公开(公告)号：US20210287683A1
公开(公告)日：2021-09-16
申请号：US17179125
申请日：2021-02-18
Applicant: Outreach Corporation
Inventor： Krishnamohan Reddy Nareddy , Abhishek Abhishek , Rohit Ganpat Mane , Rajiv Garg
Abstract: A system and a method are disclosed for identifying a subjectively interesting moment in a transcript. In an embodiment, a device receives a transcription of a conversation, and identifies a participant of the conversation. The device accesses a machine learning model corresponding to the participant, and applies, as input to the machine learning model, the transcription. The device receives as output from the machine learning model a portion of the transcription having relevance to the participant, and generates for display, to the participant, information pertaining to the portion.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.017 seconds)
