Meeting insights with large language models
In accordance with examples of the present disclosure, a collaborative platform provides a digital collaboration assistant that continuously monitors and analyzes shared meeting contents (e.g., voice, text chat messages, shared links and documents, presentation materials, and the like) by participants during a collaborative meeting in near real-time, periodically updates a structure summary log of the meeting contents that are deemed important during the collaborative meeting, and interacts with the participants throughout the collaborative meeting in near real-time, for example, to answer questions or provide additional information.
1. A method for facilitating a collaborative meeting, the method comprising:
monitoring activities of participants of the collaborative meeting;
extracting insights from meeting contents shared by the participants, wherein the insights are extracted using a generative machine learning model;
selecting data from the insights that is deemed important based on engagement and interests of the participants;
generating a structured summary log based on the selected data from the insights associated with the collaborative meeting, wherein the structured summary log is generated using the generative machine learning model;
presenting the structured summary log in a collaborative canvas accessible by the participants during the collaborative meeting; and
generating one or more customized meeting summaries for one or more participants after the collaborative meeting, wherein the one or more customized meeting summaries are generated using the generative machine learning model.
2. The method of claim 1 , wherein the meeting contents include voice of the participants, text transcript of speech of participants, text chat messages, links and documents, and presentation materials shared by the participants during the collaborative meeting.
3. The method of claim 1 , wherein the insights include key points, action items, question-and-answer (QnA) pairs, contents from links and documents, and screenshots of presentation materials.
4. The method of claim 1 , wherein generating the structured summary log based on the insights associated with the collaborative meeting comprises generating the structured summary log every determined time period or predetermined number of contents during the collaborative meeting.
5. The method of claim 1 , wherein the structured summary log captures the insights that represent the meeting contents that are deemed important to the participants.
6. The method of claim 5 , wherein generating the structured summary log includes determining information from the meeting contents as important based on engagement and interests of the participants by listening for sentiment analysis to determine if the participants have a strong reaction.
7. The method of claim 5 , wherein generating the structured summary log includes determining information from the meeting contents as important based on engagement and interests of the participants by monitoring a density of dialog, a number of participants speaking or texting, and/or a number of hand-raised or emojis in a chat box when a particular meeting content is shared in the collaborative meeting.
8. The method of claim 1 , further comprising receiving, from a participant to the collaborative meeting, a change to content in the collaborative canvas.
9. The method of claim 8 , further comprising:
accepting the change to the content in the collaborative canvas; and
resharing the collaborative canvas with the participants.
10. A computing device for facilitating a collaborative meeting, the computing device comprising:
a processor; and
a memory having a plurality of instructions stored thereon that, when executed by the processor, causes the computing device to:
monitor activities of participants of the collaborative meeting;
extract insights from meeting contents shared by the participants, wherein the insights are extracted using a generative machine learning model;
select data from the insights that is deemed important based on engagement and interests of the participants;
generate a structured summary log based on the selected data from the insights associated with the collaborative meeting, wherein the structured summary log is generated using the generative machine learning model;
present the structured summary log in a collaborative canvas accessible by the participants during the collaborative meeting; and
generate one or more customized meeting summaries one or more of the participants after the collaborative meeting, wherein the one or more customized meeting summaries are generated using the generative machine learning model.
11. The computing device of claim 10 , wherein the meeting contents include voice of the participants, text transcript of speech of participants, text chat messages, links and documents, and presentation materials shared by the participants during the collaborative meeting, and the insights include key points, action items, question-and-answer (QnA) pairs, contents from links and documents, and screenshots of presentation materials.
12. The computing device of claim 10 , further comprising instructions stored thereon that, when executed by the processor, causes the computing device to receive, from a participant to the collaborative meeting, a change to content in the collaborative canvas.
13. The computing device of claim 12 , further comprising instructions stored thereon that, when executed by the processor, causes the computing device to:
accept the change to the content in the collaborative canvas; and
reshare the collaborative canvas with the participants.
14. The computing device of claim 10 , wherein to interact with the participants during the collaborative meeting includes to interact with an individual participant in a private chat box associated with the collaborative meeting based on the meeting contents that have hitherto been discussed or shared during the collaborative meeting in response to receiving a text message from the individual participant in the private chat box.
15. A non-transitory computer-readable medium storing instructions for facilitating a collaborative meeting, the instructions when executed by one or more processors of a computing device, cause the computing device to perform a method comprising:
monitoring activities of participants of the collaborative meeting;
extracting insights from meeting contents shared by the participants;
selecting data from the insights that is deemed important based on engagement and interests of the participants;
generating a structured summary log based on the selected data from the insights associated with the collaborative meeting;
presenting the structured summary log in a collaborative canvas accessible by the participants during the collaborative meeting;
interacting with participants during the collaborative meeting; and
generating a customized meeting summary for each of the participants after the collaborative meeting.
16. The non-transitory computer-readable medium of claim 15 , wherein the meeting contents include voice of the participants, text transcript of speech of participants, text chat messages, links and documents, and presentation materials shared by the participants during the collaborative meeting, and the insights include key points, action items, question-and-answer (QnA) pairs, contents from links and documents, and screenshots of presentation materials.
17. The non-transitory computer-readable medium of claim 15 , wherein the structured summary log captures the insights that represent the meeting contents that are deemed important to the participants.
18. The non-transitory computer-readable medium of claim 17 , wherein generating the structured summary log includes to determine information from the meeting contents as important based on engagement and interests of the participants by listening for sentiment analysis to determine if the participants have a strong reaction.
19. The non-transitory computer-readable medium of claim 17 , wherein to select data from the insights that is deemed important based on engagement and interests of the participants includes to monitor a density of dialog, a number of participants speaking or texting, and/or a number of hand-raised or emojis in a chat box when a particular meeting content is shared in the collaborative meeting.
20. The non-transitory computer-readable medium of claim 15 , wherein the method further comprises:
receiving, from a participant to the collaborative meeting, a change to content in the collaborative canvas;
accepting the change to the content in the collaborative canvas; and
resharing the collaborative canvas with the participants.