Method and system for generating augmented reality (AR)/virtual reality (VR) content in real-time

Patent metadata

Field	Value
Publication number	US-11217027-B2
Application number	US-202016819505-A
Country	US
Kind code	B2
Filing date	Mar 16, 2020
Priority date	Mar 13, 2020
Publication date	Jan 4, 2022
Grant date	Jan 4, 2022

Abstract

The present disclosure discloses a method and a system for generating AR/VR content in real-time. The system upon receiving a user query or gestures, identifies query attributes and action attributes associated with IOT devices. Thereafter, system identifies IOT data corresponding to the query attributes and the action attributes from the IOT devices. Based on the IOT data, system generates multimedia content using trained machine learning model. The machine learning model is trained to provide multimedia content based on the IOT data associated with the query attributes or the action attributes. Thereafter, the system generates AR/VR content in real-time based on the multimedia content. In this manner, present disclosure supports interactive queries over AR/VR content and provides AR/VR content in real-time thereby reducing storage requirement for storing various images for interpolation.

First claim

What is claimed is:

1. A method of generating Virtual Reality (VR) content in real-time, the method comprising:
identifying, by a content generation system, one or more gestures of a user 105 while performing a user action associated with one or more Internet of Things (IOT) devices;
identifying, by the content generation system, IOT data corresponding to each of one or more action attributes associated with the user action;
generating, by the content generation system, one or more multimedia content corresponding to the IOT data and the one or more gestures, wherein the one or more multimedia content is generated by a trained machine learning model based on the IOT data associated with each of the one or more action attributes and the one or more gestures; and
generating, by the content generation system, the VR content in real-time in response to the one or more gestures based on the one or more multimedia content.

2. The method as claimed in claim 1 , wherein the one or more gestures are identified based on one or more virtual devices associated with the user.

3. The method as claimed in claim 1 , further comprising training a machine learning model to generate the one or more multimedia content based on the IOT data from the one or more IOT devices and based on one or more gestures of the user.

4. The method as claimed in claim 3 , wherein the machine learning model generates one or more updated multimedia content based on updated IOT data from the one or more IOT devices.

5. The method as claimed in claim 1 , wherein generating the VR content comprises rendering the one or more multimedia content in 3-D space along with timestamp information of each IOT data.

6. The method as claimed in claim 1 , wherein generating the VR content comprises changing user interface of a device associated with the user for rendering the VR content based on the one or more IOT devices in communication with the device associated with the user.

7. A content generation system for generating Virtual Reality (VR) content in real-time, the content generation system comprising:
a processor; and
a memory communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which, on execution, causes the processor to:
identify one or more gestures of a user while performing a user action associated with one or more Internet of Things (IOT) devices;
identify IOT data corresponding to each of one or more action attributes associated with the user action;
generate one or more multimedia content corresponding to the IOT data and the one or more gestures, wherein the one or more multimedia content is generated by a trained machine learning model based on the IOT data associated with each of the one or more action attributes and the one or more gestures; and
generate the VR content in real-time in response to the one or more gestures based on the one or more multimedia content.

8. The content generation system as claimed in claim 7 , wherein the processor identifies the one or more gestures using one or more virtual devices associated with the user.

9. The content generation system as claimed in claim 7 , wherein the processor trains a machine learning model to generate the one or more multimedia content based on the IOT data from the one or more IOT devices and based on one or more gestures of the user, wherein the machine learning model generates one or more updated multimedia content based on updated IOT data from the one or more IOT devices.

10. The content generation system as claimed in claim 7 , wherein the processor renders the one or more multimedia content in 3-D space along with timestamp information of each IOT data for generating the VR content.

11. The content generation system as claimed in claim 7 , wherein the processor generates the VR content by changing user interface of a device associated with the user for rendering the VR content based on the one or more IOT devices in communication with the device associated with the user.

12. A non-transitory computer readable medium including instructions stored thereon that when processed by at least one processor cause the processor to generate Virtual Reality (VR) content in real-time by:
identifying one or more gestures of a user 105 while performing a user action associated with one or more Internet of Things (IOT) devices;
identifying IOT data corresponding to each of one or more action attributes associated with the user action;
generating one or more multimedia content corresponding to the IOT data and the one or more gestures, wherein the one or more multimedia content is generated by a trained machine learning model based on the IOT data associated with each of the one or more action attributes and the one or more gestures; and
generating the VR content in real-time in response to the one or more gestures based on the one or more multimedia content.

Assignees

• Wipro Ltd

Inventors

• Ramachandra Iyer Manjunath

Classifications

• G06N3/045

  Combinations of networks · CPC title

• G06N3/0475

  Generative networks · CPC title

• G06N3/094

  Adversarial learning · CPC title

• H04L67/131

  Protocols for games, networked simulations or virtual reality · CPC title

• G06N3/08

  Learning methods · CPC title