IP Library Granted Patent US 12,243,177
Granted Patent B1
US 12,243,177 · App. 18/461,392 · Granted Mar 4, 2025

Systems and methods for using artificial intelligence with assistive bots in extended reality environments

Inventor: Ethan Fieldman (Gainesville, FL)
Assignee: VR-EDU, Inc.
G06T19/006G06T13/40G10L15/1815
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 12,243,177
App. No.
18/461,392
Granted
Mar 4, 2025
Kind
B1
Abstract

Assistive bots, such as computer-generated avatars that do not correspond to real world persons, provide automated instructional capabilities through the use of artificial intelligence to real world users seeking information in extended reality (XR) environments, like students learning in XR environments.

Claims (24)

1. A method for assisting a user experiencing an extended reality environment comprising:

displaying an assistive avatar in the extended reality environment to the user with a display of an extended reality hardware device being used by the user, wherein the assistive avatar is automatically controlled in real time by software communicating with the extended reality hardware device and the assistive avatar is not under real time control of a human;

receiving an input from the user in the extended reality environment that provides an inquiry to the assistive avatar for additional information about either a virtual object or a real-world object that the user is holding, touching or pointing to in the extended reality environment, wherein the input further includes the user indicating the virtual object or the real-world object that the user is holding, touching or pointing to, and the additional information is not already present at such time and location in the extended reality environment when the user provides the inquiry to the assistive avatar;

retrieving a response to the inquiry; and

providing the response to the inquiry via the assistive avatar as an answer to the inquiry, wherein said retrieving a response includes submitting a request for information based on the inquiry being provided as text data to an artificial intelligence process that applies a large language model to the text data and then transmits the response that includes the additional information about the virtual object or real-world object.

2. The method of claim 1 , wherein the input includes the user touching or pointing at a virtual page that includes text.

3. The method of claim 1 , wherein the input includes the user touching or pointing at a virtual tablet being displayed in the extended reality environment.

4. The method of claim 1 , wherein the input includes a user speaking the inquiry to the assistive avatar.

5. The method of claim 4 , wherein the response that includes the additional information presents one or more of a picture, graphic, three-dimensional object display and video.

6. The method of claim 5 , wherein the input includes the user speaking a pronoun to reference the virtual object or real-world object.

7. The method of claim 4 , wherein the input includes the user touching or pointing at a virtual page that includes text while the user is speaking the inquiry to the assistive avatar.

8. The method of claim 7 , wherein the input includes the user speaking a pronoun to reference the text or virtual page.

9. The method of claim 4 , wherein the input includes the user touching or pointing at a screen of a virtual tablet being displayed in the extended reality environment while the user is speaking the inquiry to the assistive avatar.

10. The method of claim 9 , wherein the input includes the user speaking a pronoun to reference an object or text shown on the screen of the virtual tablet.

11. The method of claim 4 , wherein the input includes the user speaking a pronoun to reference the virtual object or real-world object.

12. The method of claim 11 , wherein the pronoun is the word “this”.

13. The method of claim 1 , wherein the input includes an image captured from the real world of the user from a camera.

14. The method of claim 13 , further comprising receiving the image from a camera of the extended reality hardware device.

15. The method of claim 14 , further comprising receiving the image from an external camera of a smartphone or webcam device.

16. The method of claim 14 , wherein the camera of the extended reality hardware device is worn by the user.

17. The method of claim 16 , wherein the image is received by the extended reality hardware device while in a passthrough mode that allows the user to see objects in the user's real world.

18. The method of claim 17 , further comprising the extended reality hardware device receiving the image while the camera is restricted from capturing surrounding real-world environment other than subject matter of the image permitted to be received into the extended reality environment.

19. The method of claim 1 , further comprising evaluating context of the user's inquiry to optimize the request for information based on the inquiry to the artificial intelligence process that transmits the reply to the response.

20. The method of claim 1 , wherein the response that includes the additional information presents one or more of a picture, graphic, three-dimensional object display and video.

Assignments (2)
CHANGE OF NAME Recorded Dec 4, 2024
From: VR-EDU, INC.
To: CURIOXR, INC.
Reel/Frame 069510/0242 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 26, 2023
From: FIELDMAN, ETHAN
To: VR-EDU, INC.
Reel/Frame 065362/0031 →
References Cited (14)
US 9369410B2 · Capper et al. · 2016 [cited by applicant]
US 11431660B1 · Leeds et al. · 2022 [cited by applicant]
CN 108881319A · 2018 [cited by applicant]
CN 114327060B · 2023 [cited by applicant]
Nathie, “How to Get Hand Tracking on The Oculus Meta Quest 2”, 2020, https://www.youtube.com/watch?v=hX7GJfYmj7M. (Year: 2020). [cited by examiner]
Paradise Decay, “Oculus Quest Passthrough Camera & Guardian System in Action”, https://www.youtube.com/watch?v=nQQJu1WV4_A, 2019. (Year: 2019). [cited by examiner]
Kim et al., “Does a Digital Assistant Need a Body? The Influence of Visual Embodiment and Social Behavior on the perception of Intelligent Virtual Agents in AR”, IEEE, 2018. (Year: 2018). [cited by examiner]
Uchino et al., “VR Interaction in Real-Time between Avatar with Voice and Gesture Recognition System”, IEEE, 2007 (Year: 2007). [cited by examiner]
Topsakal et al., “Framework for a Foreign Language Teaching Software for Children Utilizing AR, Voicebots and ChatGPT (Large Language Models)”, 2022 (Year: 2022). [cited by examiner]
Dall-E/Dall-E2; retrieved on Sep. 28, 2023; 12 pages; https://openai.com/product/dall-e-2. [cited by applicant]
Janati, et al., “Adaptive e-Learning Al-Powered Chatbot based on Multimedia Indexing,” IJACSA, vol. 11, No. 12, 2020, 10 pgs. [cited by applicant]
Nalbant, “The Importance of Artificial Intelligence in Education: A short review,” JRSE-2106302112361, 15 pgs. [cited by applicant]
Huang, et al., “A Review on Artificial Intelligence in Education,” Academic Journal of Interdisciplinary Studies, vol. 10, No. 3, May 2021, 12 pgs. [cited by applicant]
Chamola, et al., “Beyond Reality: The Pivotal Role of Generative AI in the Metaverse,” arXiv:2308.06272v1, Jul. 28, 2023, 8 pgs. [cited by applicant]