Selecting avatar for videoconference

Patent metadata

Field	Value
Publication number	US-12317002-B2
Application number	US-202218047420-A
Country	US
Kind code	B2
Filing date	Oct 18, 2022
Priority date	Oct 18, 2022
Publication date	May 27, 2025
Grant date	May 27, 2025

Abstract

A method can include selecting, from at least a first avatar and a second avatar based on at least one attribute of a calendar event associated with a user, a session avatar, the first avatar being based on a first set of images of a user wearing a first outfit and the second avatar being based on a second set of images of the user wearing a second outfit, and presenting the session avatar during a videoconference, the presentation of the session avatar changing based on audio input received from the user during the videoconference.

First claim

What is claimed is:

1. A method comprising:
storing an association between features for a plurality of avatars and probabilities for the plurality of avatars, the plurality of avatars including a first avatar that was generated based on a first set of images of a user wearing a first outfit and a second avatar that was generated based on a second set of images of the user wearing a second outfit, the features being based on at least one of the first set of images and the second set of images;
selecting the first avatar as a session avatar based on video input and the association between the features and the probabilities, the second avatar being an unselected avatar; and
presenting the session avatar during a videoconference.

2. The method of claim 1 , wherein the selection of the session avatar is further based on at least one attribute of a calendar event, a description of the first avatar received from the user, and a description of the second avatar received from the user.

3. The method of claim 2 , wherein:
the description of the first avatar includes a contact identifier; and
the at least one attribute of the calendar event includes the contact identifier.

4. The method of claim 1 , wherein the selection is further based on a time of day of a calendar event.

5. The method of claim 1 , wherein the selection of the session avatar is further based on at least one attribute of a calendar event associated with the videoconference.

6. The method of claim 1 , wherein the selection of the session avatar is further based on audio input received from the user.

7. The method of claim 1 , wherein the selection of the session avatar is further based on previous selections, by the user, of either the first avatar or the second avatar.

8. The method of claim 1 , wherein the selection of the session avatar is further based on video input of the user received during previous videoconferences, the video input indicating a type of outfit worn by the user during the previous videoconferences.

9. The method of claim 1 , wherein the video input indicates a type of outfit worn by the user during the videoconference.

10. The method of claim 1 , wherein the selection of the session avatar includes:
presenting the session avatar to the user; and
receiving an indication of approval of the session avatar from the user.

11. The method of claim 1 , further comprising:
capturing a third set of images of the user during the videoconference; and
storing a third avatar based on the third set of images of the user.

12. The method of claim 1 , wherein the user was speaking predetermined words from a script as part of generating the first avatar.

13. The method of claim 1 , wherein selecting the first avatar as the session avatar is further based on a tone of voice of the user.

14. The method of claim 1 , further comprising:
receiving audio input during presentation of the session avatar during the videoconference; and
changing the session avatar to the second avatar based on features in the audio input.

15. The method of claim 1 , wherein the features include facial landmarks.

16. The method of claim 1 , wherein the association between the features and the probabilities are stored in a model.

17. A non-transitory computer-readable storage medium comprising instructions stored thereon that, when executed by at least one processor, are configured to cause a computing system to:
store an association between features for a plurality of avatars and probabilities for the plurality of avatars, the plurality of avatars including a first avatar that was generated based on a first set of images of a user wearing a first outfit and a second avatar that was generated based on a second set of images of the user wearing a second outfit, the features being based on at least one of the first set of images and the second set of images;
select the first avatar as a session avatar based on video input and the association between the features and the probabilities, the second avatar being unselected; and
present the session avatar during a videoconference.

18. The non-transitory computer-readable storage medium of claim 17 , wherein the selection of the session avatar is further based on at least one attribute of a calendar event, a description of the first avatar received from the user, and a description of the second avatar received from the user.

19. The non-transitory computer-readable storage medium of claim 17 , wherein the selection of the session avatar is further based on an attendee of a calendar event other than the user.

20. A computing system comprising:
at least one processor; and
a non-transitory computer-readable storage medium comprising instructions stored thereon that, when executed by the at least one processor, are configured to cause the computing system to:
store an association between features for a plurality of avatars and probabilities for the plurality of avatars, the plurality of avatars including a first avatar that was generated based on a first set of images of a user wearing a first outfit and a second avatar that was generated based on a second set of images of the user wearing a second outfit, the features being based on at least one of the first set of images and the second set of images;
select the first avatar as based on video input and the association between the features and the probabilities, the second avatar being an unselected avatar; and
present the session avatar during a videoconference.

21. The computing system of claim 20 , wherein the selection of the first avatar is further based on an attendee of a calendar event other than the user.

22. The computing system of claim 20 , wherein the instructions are further configured to cause the computing system to:
change the session avatar to the second avatar based on features in audio input received during presentation of the session avatar during the videoconference.

Assignees

• Google Llc

Inventors

• Zhang Yinda
• Du Ruofei

Classifications

• G06T13/00

  Animation · CPC title

• G06F3/167 Primary

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title

• G06T13/205

  driven by audio data · CPC title

• H04N7/147

  Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals (selecting H04Q) · CPC title

• H04N7/157 Primary

  defining a virtual conference space and using avatars or agents (computer conference optimisation or adaptation H04L12/1827) · CPC title