Querying an artificial intelligence chatbot based on meeting discussions

Patent metadata

Field	Value
Publication number	US-2026067119-A1
Application number	US-202418819823-A
Country	US
Kind code	A1
Filing date	Aug 29, 2024
Priority date	Aug 29, 2024
Publication date	Mar 5, 2026
Grant date	—

Abstract

Aspects of the disclosure are directed to querying an artificial intelligence chatbot based on meeting discussions. Media streams that are generated by participants of a virtual meeting can be provided as input data to an artificial intelligence (AI) model. The AI model can generate one or more summaries of one or more portions of the virtual meeting based on the input data. The AI model can receive, via an AI chatbot, user queries pertaining to the virtual meeting. The AI model can generate responses to user queries based on the information within the one or more summaries and/or relevant corpus data.

First claim

What is claimed is:

1 . A method comprising:
causing a virtual meeting user interface (UI) to be presented during a virtual meeting between a plurality of participants; receiving, via the virtual meeting UI, a command from a first participant of the plurality of participants to enable automatic note taking; receiving, at a first point in time during the virtual meeting, a query from the first participant for information pertaining to a portion of the virtual meeting, the portion of the virtual meeting preceding the first point in time during the virtual meeting; and providing the requested information to the first participant.

2 . The method of claim 1 , wherein the first participant is at least partially absent from the virtual meeting during the portion of the virtual meeting.

3 . The method of claim 1 , wherein the query from the first participant for the information pertaining to the portion of the virtual meeting comprises a request for a meeting summary of the portion of the virtual meeting.

4 . The method of claim 3 , further comprising generating a meeting summary of the portion of the virtual meeting using an artificial intelligence (AI) model and using media streams provided by a plurality of client devices associated with the plurality of participants during the portion of the virtual meeting as input to the AI model.

5 . The method of claim 4 , wherein the AI model is trained to generate meeting summaries of virtual meetings using training data comprising media streams associated with historical virtual meetings.

6 . The method of claim 4 , wherein the meeting summary of the portion of the virtual meeting is generated based on a transcript of the portion of the virtual meeting, wherein the transcript is generated based on the media streams provided by the plurality of client devices associated with the plurality of participants during the portion of the virtual meeting.

7 . The method of claim 1 , wherein the query from the first participant for the information pertaining to the portion of the virtual meeting comprises a query about the portion of the virtual meeting, and the requested information comprises a response to the query about the portion of the virtual meeting.

8 . The method of claim 7 , wherein the query is received via an artificial intelligence (AI) chatbot UI.

9 . The method of claim 7 , further comprising generating the response to the query about the portion of the virtual meeting using an artificial intelligence (AI) model and using a prompt and information about the portion of the virtual meeting as input to the AI model.

10 . The method of claim 9 , wherein the prompt comprises the query and an indication of a command to provide the response to the query, and the information about the portion of the virtual meeting comprises at least one of a meeting summary of the portion of the virtual meeting or a transcript of the portion of the virtual meeting.

11 . The method of claim 7 , wherein the query requests information corresponding to a participant of the plurality of participants, wherein the information corresponds to at least one of:
actions items assigned to the participant during the portion of the virtual meeting; a number of times the participant is mentioned during the portion of the virtual meeting; or a number of times the participant participated in the during the portion of the virtual meeting.

12 . The method of claim 7 , wherein the response to the query identifies one or more internal documents associated with the portion of the virtual meeting.

13 . The method of claim 7 , wherein the response to the query identifies one or more external documents providing information related to topics discussed during the portion of the virtual meeting.

14 . A system comprising:
a memory; and a processing device, coupled to the memory, configured to perform operations comprising:
causing a virtual meeting user interface (UI) to be presented during a virtual meeting between a plurality of participants;
receiving, via the virtual meeting UI, a command from a first participant of the plurality of participants to enable automatic note taking;
receiving, at a first point in time during the virtual meeting, a query from the first participant for information pertaining to a portion of the virtual meeting, the portion of the virtual meeting preceding the first point in time during the virtual meeting; and
providing the requested information to the first participant.

15 . The system of claim 14 , wherein the query from the first participant for the information pertaining to the portion of the virtual meeting comprises a request for a meeting summary of the portion of the virtual meeting.

16 . The system of claim 14 , wherein the query from the first participant for the information pertaining to the portion of the virtual meeting comprises a query about the portion of the virtual meeting, and the requested information comprises a response to the query about the portion of the virtual meeting.

17 . The system of claim 16 , wherein the query is received via an artificial intelligence (AI) chatbot UI.

18 . A non-transitory computer readable storage medium comprising instructions that, when executed by a processing device, cause the processing device to perform operations comprising:
causing a virtual meeting user interface (UI) to be presented during a virtual meeting between a plurality of participants; receiving, via the virtual meeting UI, a command from a first participant of the plurality of participants to enable automatic note taking; receiving, at a first point in time during the virtual meeting, a query from the first participant for information pertaining to a portion of the virtual meeting, the portion of the virtual meeting preceding the first point in time during the virtual meeting; and providing the requested information to the first participant.

19 . The non-transitory computer readable storage medium of claim 18 , wherein the query from the first participant for the information pertaining to the portion of the virtual meeting comprises a query about the portion of the virtual meeting, and the requested information comprises a response to the query about the portion of the virtual meeting.

20 . The non-transitory computer readable storage medium of claim 18 , wherein the query is received via an artificial intelligence (AI) chatbot UI.

Assignees

• Google Llc

Inventors

• Shernan Ethan Samuel
• Sanglaji Maryam
• Shen Jennifer
• Mruthyunjaya Ravindra
• Castaneda Humberto
• Levin Dmitry Denisovich
• Moore Kristin
• Callas Jan Arvid Kristoffer
• Volkov Anton
• Dern Kelly
• Liu Yan
• Yi Daqing
• Tsay Jacqueline Amy
• Mao Yu
• Fatiha Deeni
• Sandholm Anders Thorhauge
• Chin Constance

Classifications

• G10L15/26

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• H04L51/02

  using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title

• H04L12/1831 Primary

  Tracking arrangements for later retrieval, e.g. recording contents, participants activities or behavior, network status · CPC title