Systems and methods for virtual assistants in virtual reality meetings

Patent metadata

Field	Value
Publication number	US-2025363747-A1
Application number	US-202418674193-A
Country	US
Kind code	A1
Filing date	May 24, 2024
Priority date	May 24, 2024
Publication date	Nov 27, 2025
Grant date	—

Abstract

A computer-implemented method for virtual assistants performing actions during virtual reality meetings may include (i) identifying a meeting in a virtual reality environment that includes a plurality of participants, (ii) monitoring, by an artificial intelligence (AI) agent, the meeting in the virtual reality environment, (iii) detecting, by the AI agent while monitoring the meeting, a trigger behavior by at least one of the participants that correlates to an action within capabilities of the AI agent, and (iv) altering, by the AI agent, the virtual reality environment by performing the action correlated to the trigger behavior. Various other methods, systems, and computer-readable media are also disclosed.

First claim

What is claimed is:

1 . A computer-implemented method comprising:
identifying a meeting in a virtual reality environment that comprises a plurality of participants; monitoring, by an artificial intelligence (AI) agent, the meeting in the virtual reality environment; detecting, by the AI agent while monitoring the meeting, a trigger behavior by at least one of the participants that correlates to an action within capabilities of the AI agent; and altering, by the AI agent, the virtual reality environment by performing the action correlated to the trigger behavior.

2 . The computer-implemented method of claim 1 , wherein the trigger behavior comprises speech.

3 . The computer-implemented method of claim 1 , wherein the trigger behavior comprises physical movement within the virtual reality environment.

4 . The computer-implemented method of claim 1 , wherein:
the trigger behavior comprises a reference to a digital file; and the action comprises displaying a user interface within the virtual reality environment to one or more of the participants that comprises an option to open the digital file.

5 . The computer-implemented method of claim 4 , wherein displaying the user interface within the virtual environment comprises:
identifying a subset of the participants with permissions to view the digital file; displaying the user interface to the subset of the participants with the permissions; and avoiding displaying the user interface to the participants not in the subset.

6 . The computer-implemented method of claim 1 , wherein the action comprises generating a three-dimensional model within the virtual environment.

7 . The computer-implemented method of claim 1 , wherein the action comprises modifying a three-dimensional model within the virtual environment.

8 . The computer-implemented method of claim 1 , wherein:
monitoring the meeting comprises creating a transcript of the meeting; and the action comprises creating and displaying a summary of at least a portion of the transcript of the meeting.

9 . The computer-implemented method of claim 8 , wherein creating the summary comprises:
identifying a job category of a participant in the meeting; and tailoring the summary to the job category of the participant.

10 . The computer-implemented method of claim 8 , wherein creating the summary comprises:
detecting a physical action performed a participant within the virtual environment; and annotating the transcript of the meeting with a description of the physical action.

11 . The computer-implemented method of claim 1 , further comprising displaying a three-dimensional model that represents the AI agent within the virtual reality environment.

12 . A system comprising:
at least one physical processor; physical memory comprising computer-executable instructions that, when executed by the physical processor, cause the physical processor to:
identify a meeting in a virtual reality environment that comprises a plurality of participants;
monitor, by an AI agent, the meeting in the virtual reality environment;
detect, by the AI agent while monitoring the meeting, a trigger behavior by at least one of the participants that correlates to an action within capabilities of the AI agent; and
alter, by the AI agent, the virtual reality environment by performing the action correlated to the trigger behavior.

13 . The system of claim 12 , wherein the trigger behavior comprises speech.

14 . The system of claim 12 , wherein the trigger behavior comprises physical movement within the virtual reality environment.

15 . The system of claim 12 , wherein:
the trigger behavior comprises a reference to a digital file; and the action comprises displaying a user interface within the virtual reality environment to one or more of the participants that comprises an option to open the digital file.

16 . The system of claim 15 , wherein displaying the user interface within the virtual environment comprises:
identifying a subset of the participants with permissions to view the digital file; displaying the user interface to the subset of the participants with the permissions; and avoiding displaying the user interface to the participants not in the subset.

17 . The system of claim 12 , wherein the action comprises generating a three-dimensional model within the virtual environment.

18 . The system of claim 12 , wherein the action comprises modifying a three-dimensional model within the virtual environment.

19 . The system of claim 12 , wherein:
monitoring the meeting comprises creating a transcript of the meeting; and the action comprises creating and displaying a summary of at least a portion of the transcript of the meeting.

20 . A non-transitory computer-readable medium comprising one or more computer-readable instructions that, when executed by at least one processor of a computing device, cause the computing device to:
identify a meeting in a virtual reality environment that comprises a plurality of participants; monitor, by an AI agent, the meeting in the virtual reality environment; detect, by the AI agent while monitoring the meeting, a trigger behavior by at least one of the participants that correlates to an action within capabilities of the AI agent; and alter, by the AI agent, the virtual reality environment by performing the action correlated to the trigger behavior.

Assignees

• Meta Platforms Inc

Inventors

• Bagotra Ankush
• Jahed Saeed

Classifications

• H04N7/15

  Conference systems · CPC title

• G06F40/169

  Annotation, e.g. comment data or footnotes · CPC title

• G06F3/011 Primary

  Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00) · CPC title

• G06T2200/24

  involving graphical user interfaces [GUIs] · CPC title

• G06T2219/024

  Multi-user, collaborative environment · CPC title