Generating customized meeting insights based on user interactions and meeting media
Methods, systems, and non-transitory computer readable storage media are disclosed for generating meeting insights based on media data and device input data. In one or more embodiments, the system analyzes media data and inputs to client devices associated with a meeting to determine a portion of the meeting that is relevant for a user. In one or more embodiments, the system generates a meeting summary, meeting highlights, or action items related to the media data to provide to the client device. In one or more embodiments, the system also uses the summary, highlights, or action items to train a machine-learning model for use with future meetings.
1 . A computer-implemented method comprising:
receiving, from a video conference system and at a content management system, meeting data corresponding to an online meeting hosted by the video conference system;
generating relevance information indicating correlations between the meeting data and content items stored within the content management system for an account associated with the online meeting by processing, utilizing a trained machine-learning model, the meeting data together with text or metadata associated with the content items;
identifying, by the content management system based on the relevance information, a content item previously stored within the content management system that is relevant to the online meeting;
generating a content item suggestion that includes a reference to the content item; and
providing the content item suggestion to at least one participant client device associated with the online meeting hosted by the video conference system.
2 . The computer-implemented method as recited in claim 1 , further comprising:
receiving audio data as part of the meeting data corresponding to the online meeting hosted by the video conference system;
processing the audio data to generate a transcription for the online meeting; and
analyzing the transcription using the trained machine-learning model to identify the content item stored within the content management system.
3 . The computer-implemented method as recited in claim 1 , wherein providing the content item suggestion to the at least one participant client device comprises providing the content item suggestion to each participant client device associated with the online meeting.
4 . The computer-implemented method as recited in claim 1 , wherein providing the content item suggestion to the at least one participant client device associated with the online meeting comprises providing the content item suggestion to a subset of participant client devices associated with the online meeting.
5 . The computer-implemented method as recited in claim 1 , further comprising:
transcribing audio data from the meeting data corresponding to the online meeting to generate a transcription;
accessing an agenda content item from the meeting data corresponding to the online meeting;
analyzing the transcription to determine a current topic in the agenda content item is being discussed; and
providing an indication of the current topic within the online meeting.
6 . The computer-implemented method as recited in claim 1 , further comprising:
generating, after a conclusion of the online meeting, a meeting summary based on analyzing the meeting data corresponding to the online meeting; and
including the reference to the content item from the content item suggestion on the meeting summary.
7 . The computer-implemented method as recited in claim 1 , further comprising:
accessing an agenda content item from the meeting data corresponding to the online meeting, the agenda content item comprising a plurality of agenda items;
identifying a planned time for each agenda item of the plurality of agenda items based on a scheduled start time and a scheduled end time for the online meeting; and
providing, during the online meeting, a message to the at least one participant client device associated with the online meeting based on determining a remaining planned time for a remaining set of agenda items is greater than a remaining scheduled time based on the scheduled end time for the online meeting.
8 . A non-transitory computer readable storage medium comprising instructions that, when executed by at least one processor, cause a computer device to:
receive, from a video conference system and at a content management system, meeting data corresponding to an ongoing online meeting hosted by the video conference system;
generating relevance information indicating correlations between the meeting data and content items stored within the content management system for an account associated with the ongoing online meeting by processing, utilizing a trained machine-learning model, the meeting data together with text or metadata associated with the content items;
identify, by the content management system based on the relevance information, a content item previously stored within the content management system that is relevant to the ongoing online meeting;
generating a content item suggestion that includes a reference to the content item; and
providing the content item suggestion to the video conference system hosting the ongoing online meeting.
9 . The non-transitory computer readable storage medium as recited in claim 8 , wherein:
the meeting data comprises audio data from the ongoing online meeting; and
the non-transitory computer readable storage medium further comprising further comprising instructions that, when executed by the at least one processor, cause the computer device to:
generate a transcription for the ongoing online meeting based on processing the audio data from the ongoing online meeting; and
analyze the transcription to identify the content item stored within the content management system.
10 . The non-transitory computer readable storage medium as recited in claim 8 , wherein providing the content item suggestion to the video conference system causes the video conference system to provide the content item suggestion to each participant client device associated with the ongoing online meeting.
11 . The non-transitory computer readable storage medium as recited in claim 8 , wherein providing the content item suggestion to the video conference system causes the video conference system to provide the content item suggestion to a subset of participant client devices associated with the ongoing online meeting.
12 . The non-transitory computer readable storage medium as recited in claim 8 , further comprising instructions that cause the computer device to:
access ongoing transcription data for the ongoing online meeting;
analyzing the ongoing transcription data to determine a current topic being discussed; and
providing the current topic to the video conference system to cause the video conference system to provide an indication of the current topic to each participant client device associated with the ongoing online meeting.
13 . The non-transitory computer readable storage medium as recited in claim 8 , further comprising instructions that cause the computer device to:
generating a meeting summary for the ongoing online meeting, the meeting summary comprising the reference to the content item from the content item suggestion; and
providing the meeting summary to at least one participant client device associated with the ongoing online meeting.
14 . The non-transitory computer readable storage medium as recited in claim 8 , wherein the instructions further cause the computer device to:
access an agenda content item from the meeting data corresponding to the ongoing online meeting, the agenda content item comprising a plurality of agenda items;
identifying a planned time for each agenda item of the plurality of agenda items; and
providing a time tracking indication to at least one participant client device associated with the ongoing online meeting based on determining whether the ongoing online meeting is on track to end on time based on the planned time for a remaining set of agenda items and a scheduled end time of the ongoing online meeting.
15 . A system comprising:
at least one processor; and
a non-transitory computer memory comprising instructions that, when executed by the at least one processor, cause the system to:
receive, from a video conference system and at a content management system, meeting data corresponding to an online meeting hosted by the video conference system;
generating relevance information indicating correlations between the meeting data and content items stored within the content management system for an account associated with the online meeting by processing, utilizing a trained machine-learning model, the meeting data together with text or metadata associated with the content items;
identify, by the content management system based on the relevance information, a content item previously stored within the content management system that is relevant to the online meeting;
generate a content item suggestion that includes a reference to the content item; and
provide the content item suggestion to at least one participant client device associated with the online meeting hosted by the video conference system.
16 . The system as recited in claim 15 , wherein providing the content item suggestion to the at least one participant client device associated with the online meeting comprises causing the video conference system to provide the content item suggestion to the at least one participant client device.
17 . The system as recited in claim 15 , further comprising instructions that, when executed by the at least one processor, cause the system to:
receive audio data as part of the meeting data corresponding to the online meeting hosted by the video conference system;
process the audio data to generate a transcription for the online meeting; and
analyze the transcription using the trained machine-learning model to identify the content item stored within the content management system.
18 . The system as recited in claim 15 , further comprising instructions that, when executed by the at least one processor, cause the system to:
access transcription text from the meeting data for the online meeting;
analyzing the transcription text to determine a current topic being discussed; and
providing the current topic to the video conference system to cause the video conference system to provide an indication of the current topic to each participant client device associated with the online meeting.
19 . The system as recited in claim 15 , further comprising instructions that, when executed by the at least one processor, cause the system to generate, after a conclusion of the online meeting, a meeting summary based on analyzing the meeting data corresponding to the online meeting, wherein the meeting summary comprises the reference to the content item from the content item suggestion.
20 . The system as recited in claim 15 , further comprising instructions that, when executed by the at least one processor, cause the system to:
access an agenda content item corresponding to the online meeting, the agenda content item comprising a plurality of agenda items;
identify a planned time for each agenda item of the plurality of agenda items based on a scheduled start time and a scheduled end time for the online meeting; and
provide, during the online meeting, a message to the at least one participant client device associated with the online meeting based on determining a remaining planned time for a remaining set of agenda items is greater than a remaining scheduled time based on the scheduled end time for the online meeting.