Granted Patent B2

US 12,657,401 · App. 18/520,949 · Granted Jun 16, 2026

Inventors: Carolina Garcia Delgado (Zapopan, MX); Sarbajit K. Rakshit (Kolkata, IN)

Assignee: International Business Machines Corporation

G06F40/40G06T13/40G10L13/00

Abstract

Claims (62)

1 . A computer-implemented method for conversational collaboration in a metaverse environment, the computer-implemented method comprising:

using natural language processing to understand a question of a user about an object in the metaverse environment;

constructing an aggregated response to the question, based on one or more responses in the metaverse environment;

identifying one or more authentic sources of the aggregated response, one or more unauthentic sources of the aggregated response, and one or more personal sources of the aggregated response;

deploying first one or more avatars for the one or more authentic sources, second one or more avatars for the one or more unauthentic sources, and third one or more avatars for the one or more personal sources; and

constructing a spoken transcript of the aggregated response to be performed in the metaverse environment, wherein one or more portions corresponding to the one or more authentic sources are performed by the first one or more avatars in a first type of tone and body language, wherein one or more portions corresponding to the one or more unauthentic sources are performed by the second one or more avatars in a second type of tone and body language, and wherein one or more portions corresponding to the one or more personal sources are performed by the third one or more avatars in a third type of tone and body language.

2 . The computer-implemented method of claim 1 , further comprising:

identifying the object with which the user interacts in the metaverse environment.

3 . The computer-implemented method of claim 1 , further comprising:

splitting the question of the user about the object in the metaverse environment into one or more segments;

identifying one or more categories relevant to the question; and

identifying the one or more responses, the one or more questions being relevant to the one or more segments and to the one or more categories.

4 . The computer-implemented method of claim 3 , further comprising:

determining whether the one or more responses are from one or more public domains; and

determining whether the one or more responses from the one or more public domains are from the one or more authentic sources or from the one or more unauthentic sources.

5 . The computer-implemented method of claim 1 , further comprising:

mapping the first one or more portions of the spoken transcript to the first one or more avatars;

mapping the second one or more portions of the spoken transcript to the second one or more avatars; and

mapping the third one or more portions of the spoken transcript to the third one or more avatars.

6 . The computer-implemented method of claim 1 , further comprising:

generating, by an avatar generation system, the first one or more avatars, the second one or more avatars, and the third one or more avatars, including one or more visual distinctions in appearances between each set of avatars.

7 . The computer-implemented method of claim 1 , wherein the first one or more avatars are presented in the metaverse environment using a first appearance corresponding to the one or more authentic sources, wherein the second one or more avatars are presented in the metaverse using a second appearances corresponding to the one or more unauthentic sources, wherein the third one or more avatars are presented in the metaverse using a third appearance corresponding to the one or more personal sources, and wherein the first appearance, second appearance, and third appearance are all visually distinct from one another.

8 . The computer-implemented method of claim 1 , wherein a first portion of the spoken transcript is performed by the first one or more avatars, wherein a second portion of the spoken transcript is performed by the second one or more avatars, wherein a third portion of the spoken transcript is performed by the third one or more avatars.

9 . The computer-implemented method of claim 8 , wherein the first portion of the spoken transcript and the second portion of the spoken transcript are sent to a cloud server, and wherein the third portion of the spoken transcript is stored locally.

10 . The computer-implemented method of claim 1 , wherein the first type of tone and body language corresponds to a level of confidence associated with the one or more authentic sources, wherein the second type of tone and body language corresponds to a level of confidence associated with the one or more unauthentic sources, and wherein the third type of tone and body language corresponds to a level of confidence associated with the one or more personal sources.

11 . A computer program product for conversational collaboration in a metaverse environment, the computer program product comprising a computer readable storage medium having program instructions stored therewith, the program instructions executable by one or more processors, the program instructions executable to:

use natural language processing to understand a question of a user about an object in the metaverse environment;

construct an aggregated response to the question, based on one or more responses in the metaverse environment;

identify one or more authentic sources of the aggregated response, one or more unauthentic sources of the aggregated response, and one or more personal sources of the aggregated response;

deploy first one or more avatars for the one or more authentic sources, second one or more avatars for the one or more unauthentic sources, and third one or more avatars for the one or more personal sources; and

construct, a spoken transcript of the aggregated response to be performed in the metaverse environment, wherein one or more portions corresponding to the one or more authentic sources are performed by the first one or more avatars in a first type of tone and body language, wherein one or more portions corresponding to the one or more unauthentic sources are performed by the second one or more avatars in a second type of tone and body language, and wherein one or more portions corresponding to the one or more personal sources are performed by the third one or more avatars in a third type of tone and body language.

12 . The computer program product of claim 11 , further comprising the program instructions executable to:

identify the object with which the user interacts in the metaverse environment.

13 . The computer program product of claim 11 , further comprising the program instructions executable to:

split the question of the user about the object in the metaverse environment into one or more segments;

identify one or more categories relevant to the question; and

identify the one or more responses, the one or more questions being relevant to the one or more segments and to the one or more categories.

14 . The computer program product of claim 13 , further comprising the program instructions executable to:

determine whether the one or more responses are from one or more public domains; and

determine whether the one or more responses from the one or more public domains are from the one or more authentic sources or from the one or more unauthentic sources.

15 . The computer program product of claim 11 , further comprising the program instructions executable to:

map the first one or more portions of the spoken transcript to the first one or more avatars;

map the second one or more portions of the spoken transcript to the second one or more avatars; and

map the third one or more portions of the spoken transcript to the third one or more avatars.

16 . A computer system for conversational collaboration in a metaverse environment, the computer system comprising one or more processors, one or more computer readable tangible storage devices, and program instructions stored on at least one of the one or more computer readable tangible storage devices for execution by at least one of the one or more processors, the program instructions executable to:

use natural language processing to understand a question of a user about an object in the metaverse environment;

construct an aggregated response to the question, based on one or more responses in the metaverse environment;

identify one or more authentic sources of the aggregated response, one or more unauthentic sources of the aggregated response, and one or more personal sources of the aggregated response;

deploy first one or more avatars for the one or more authentic sources, second one or more avatars for the one or more unauthentic sources, and third one or more avatars for the one or more personal sources; and

construct, a spoken transcript of the aggregated response to be performed in the metaverse environment, wherein one or more portions corresponding to the one or more authentic sources are performed by the first one or more avatars in a first type of tone and body language, wherein one or more portions corresponding to the one or more unauthentic sources are performed by the second one or more avatars in a second type of tone and body language, and wherein one or more portions corresponding to the one or more personal sources are performed by the third one or more avatars in a third type of tone and body language.

17 . The computer system of claim 16 , further comprising the program instructions executable to:

identify the object with which the user interacts in the metaverse environment.

18 . The computer system of claim 16 , further comprising the program instructions executable to:

split the question of the user about the object in the metaverse environment into one or more segments;

identify one or more categories relevant to the question;

identify the one or more responses, the one or more questions being relevant to the one or more segments and to the one or more categories;

determine whether the one or more responses are from one or more public domains; and

determine whether the one or more responses from the one or more public domains are from the one or more authentic sources or from the one or more unauthentic sources.

19 . The computer system of claim 16 , further comprising the program instructions executable to:

map the first one or more portions of the spoken transcript to the first one or more avatars;

map the second one or more portions of the spoken transcript to the second one or more avatars; and

map the third one or more portions of the spoken transcript to the third one or more avatars.

Assignments (1)

Continuity (1)

References Cited (21)