IP Library Granted Patent US 12,711,958
Granted Patent B1
US 12,711,958 · App. 18/756,475 · Granted Aug 18, 2026

Voice-enabled virtual whiteboard permitting extended reality (XR) collaboration

Inventors: Ric M. Peña (Boerne, TX); Rodney Tyrone Thomas (Cibolo, TX); Dustin Bowen Bitter (Lehi, UT); Megan Sarah Jennings (San Antonio, TX); Paula Ann Whittington (Helotes, TX); Nathan Lee Post (Rockport, TX); Timothy Blair Chalmers (San Antonio, TX)
Assignee: United Services Automobile Association (USAA)
G10L15/22G06T11/60G10L15/18G10L2015/223
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,711,958
App. No.
18/756,475
Granted
Aug 18, 2026
Kind
B1
Abstract

A voice-enabled virtual whiteboard permitting extended reality (XR) collaboration is disclosed. Specifically, the embodiments provide systems and methods that display a virtual whiteboard to various participants who wish to communicate more effectively. The system and method allow participants to provide voice inputs, where the voice inputs are interpreted to add content to the virtual whiteboard. For example, embodiments identify pictures that correspond to the voice inputs and allow the users to add the pictures to add them to the virtual whiteboard. Embodiments may also allow users to edit content to add to the virtual whiteboard privately before providing the virtual whiteboard for public viewing.

Claims (44)

1 . A method of communicating using a virtual whiteboard, comprising:

displaying the virtual whiteboard to a group of participants;

receiving a voice input from a particular participant from the group of participants;

processing the voice input to generate content to add to the virtual whiteboard;

generating an updated virtual whiteboard by adding the content to the virtual whiteboard; and

displaying the updated virtual whiteboard to the group of participants;

wherein the voice input from the particular participant is a voice input corresponding to text defining a picture input and the method further comprises using at least one of an image search, natural language processing, and an artificial intelligence image generation model to generate at least one candidate picture corresponding to the text.

2 . The method of claim 1 , wherein the group of participants each view the virtual whiteboard using an extended reality headset.

3 . The method of claim 1 , wherein the voice input from the particular participant corresponds to an instruction to add one of text, a shape, and a picture to the virtual whiteboard and is processed accordingly to generate corresponding content.

4 . The method of claim 1 , wherein the at least one candidate picture comprises a preferred candidate picture associated with a confidence value greater than a threshold confidence value and the preferred candidate picture is automatically selected as the content to be added to the virtual whiteboard.

5 . The method of claim 1 , wherein the at least one candidate picture is displayed to the particular participant and the particular participant selects a picture from the at least one candidate picture as the content to be added to the virtual whiteboard.

6 . The method of claim 1 , further comprising:

receiving an instruction that an additional modification to the virtual whiteboard is desired by the particular participant; and

updating the virtual whiteboard further based on receiving and processing an additional voice input from the particular participant.

7 . A method of communicating using a virtual whiteboard, comprising:

showing the virtual whiteboard privately to a particular participant from a group of participants for private editing;

receiving a voice input from the particular participant;

determining a text command corresponding to the voice input, using speech recognition;

processing the text command to produce generated candidate content to add to the virtual whiteboard;

updating the virtual whiteboard locally based on a selection of the generated candidate content from the particular participant;

receiving an indication from the particular participant that the private editing is complete; and

providing the updated virtual whiteboard for public viewing;

wherein the generated candidate content includes a plurality of candidate images associated with respective confidence values and the generated candidate content is selected based on the respective confidence values.

8 . The method of claim 7 , wherein the generated candidate content is produced using an image search based on the text command.

9 . The method of claim 7 , wherein the generated candidate content is produced using natural language processing to determine a meaning of the text command.

10 . The method of claim 7 , wherein the generated candidate content is produced using the text command as a prompt to generate candidate images using an artificial intelligence image generation algorithm.

11 . The method of claim 7 , further comprising:

receiving an indication that an additional modification to the virtual whiteboard is desired by the particular participant; and

updating the virtual whiteboard further based on receiving and processing an additional voice input from the particular participant.

12 . A system for communicating using a virtual whiteboard, comprising:

at least one processor, configured to:

show the virtual whiteboard for private editing to a particular participant from a group of participants;

receive a voice input from the particular participant;

recognize natural language content corresponding to the voice input;

process the natural language content to produce generated candidate content to add to the virtual whiteboard;

update the virtual whiteboard locally based on a selection of the generated candidate content from the particular participant;

receive an indication that the private editing is complete; and

add the generated candidate content to the virtual whiteboard for public viewing;

wherein the voice input from the particular participant is a voice input corresponding to text defining a picture input and the method further comprises using at least one of an image search, natural language processing, and an artificial intelligence image generation model to generate at least one candidate picture corresponding to the text.

13 . The system of claim 12 , wherein the generated candidate content is produced using an image search based on the natural language content.

14 . The system of claim 12 , wherein the generated candidate content is produced using natural language processing to determine a meaning of the natural language content.

15 . The system of claim 12 , wherein the generated candidate content is produced using the natural language content to generate candidate images using an artificial intelligence image generation algorithm.

16 . The system of claim 12 , wherein the particular participant provides additional instructions and the generated candidate content is regenerated based on the additional instructions.

17 . The system of claim 12 , wherein the particular participant provides additional instructions and the generated candidate content is supplemented based on the additional instructions.