Method and system for controlling an object avatar

Patent metadata

Field	Value
Publication number	US-11100693-B2
Application number	US-201916276663-A
Country	US
Kind code	B2
Filing date	Feb 15, 2019
Priority date	Dec 26, 2018
Publication date	Aug 24, 2021
Grant date	Aug 24, 2021

Abstract

A technique is provided for controlling an object avatar. The technique includes receiving one or more utterance from one or more user. Further, one or more object avatar is determined from object avatar database based on context. Based on one or more utterances, one or more parameters is extracted to control the object avatar. Further, one or more outcome is determine based on the one or more parameters extracted. Subsequently, the object avatar is controlled when the one or more outcomes correspond to a one or more permissible outcomes.

First claim

What is claimed is:

1. A method of controlling an object avatar, the method comprising:
receiving, by an object avatar controlling device, one or more utterances from one or more users;
identifying, by the object avatar controlling device, one or more object avatars stored in an object avatar database, based on at least a context associated with the one or more utterances, wherein the object avatar database comprises one or more permissible outcomes corresponding to a set of parameters for controlling the one or more object avatars;
extracting, by the object avatar controlling device, one or more parameters to be used for controlling the one or more object avatars, from the one or more utterances;
determining, by the object avatar controlling device, based on a vector classification of the one or more parameters and the set of parameters, one or more outcomes of controlling the one or more object avatars based on the one or more parameters; and
controlling, by the object avatar controlling device, the one or more object avatars based on the one or more parameters, when the one or more outcomes correspond to the one or more permissible outcomes, wherein the controlling comprises looking up the object avatar database to determine if the one or more outcomes correspond to the one or more permissible outcomes, and wherein the one or more permissible outcomes indicate outcomes that are permissible when populated on a real object related to a corresponding object avatar.

2. The method as claimed in claim 1 , wherein the object avatar database further comprises one or more object avatar specification, the set of parameters, and one or more relationships among a plurality of object avatars from the one or more object avatars.

3. The method as claimed in claim 1 , wherein the object avatar database is updated with one or more new object avatars based on multimedia provided by an administrative user.

4. The method as claimed in claim 3 , wherein the one or more permissible outcomes are updated with one or more additionally permissible outcomes based on a set of new parameters provided by the administrative user.

5. The method as claimed in claim 1 , wherein the identification and extraction comprises parsing the one or more utterances based on Natural Language Processing (NLP) technique.

6. The method as claimed in claim 1 , further comprises generating one or more notifications indicative of an error in rendering of the one or more object avatars for the one or more users, when the one or more outcomes do not correspond to the one or more permissible outcomes.

7. The method as claimed in claim 1 , further comprising rendering the one or more object avatars on a user interface (UI), based on the one or more parameters.

8. The method as claimed in claim 7 , wherein rendering the one or more object avatars comprises transitioning the object avatar from a 2-dimensional (2D) UI to a 3-dimensional (3D) UI and vice versa, based on one or more pre-defined gestures performed by the one or more users on the 2D UI or the 3D UI.

9. A system for controlling an object avatar, the 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:
receive one or more utterances from one or more users;
identify one or more object avatars stored in an object avatar database, based on at least a context associated with the one or more utterances, wherein the object avatar database comprises one or more permissible outcomes corresponding to a set of parameters for controlling the one or more object avatars;
extract one or more parameters to be used for controlling the one or more object avatars, from the one or more utterances;
determine, based on a vector classification of the one or more parameters and the set of parameters, one or more outcomes of controlling the one or more object avatars based on the one or more parameters; and
control the one or more object avatars based on the one or more parameters, when the one or more outcomes correspond to the one or more permissible outcomes, wherein the controlling comprises looking up the object avatar database to determine if the one or more outcomes correspond to the one or more permissible outcomes, and wherein the one or more permissible outcomes indicate outcomes that are permissible when populated on a real object related to a corresponding object avatar.

10. The system as claimed in claim 9 , wherein the object avatar database further comprises one or more object avatar specification, the set of parameters, and one or more relationships among a plurality of object avatars from the one or more object avatars.

11. The system as claimed in claim 9 , wherein the processor is configured to update the object avatar database with one or more new object avatars based on multimedia provided by an administrative user.

12. The system as claimed in claim 11 , wherein the processor is configured to update the one or more permissible outcomes with one or more additionally permissible outcomes based on a set of new parameters provided by the administrative user.

13. The system as claimed in claim 9 , wherein the identification and extraction comprises parsing the one or more utterances based on Natural Language Processing (NLP) technique.

14. The system as claimed in claim 9 , wherein the processor is further configured to generate one or more notifications indicative of an error in rendering of the one or more object avatars for the one or more users, when the one or more outcomes do not correspond to the one or more permissible outcomes.

15. The system as claimed in claim 9 , wherein the processor is further configured to render the one or more object avatars on a user interface (UI), based on the one or more parameters.

16. The system as claimed in claim 15 , wherein rendering the one or more object avatars comprises transitioning the object avatar from a 2-dimensional (2D) UI to a 3-dimensional (3D) UI and vice versa, based on one or more pre-defined gestures performed by the one or more users on the 2D UI or the 3D UI.

17. A non-transitory computer-readable medium storing one or more instructions for controlling an object avatar, wherein upon execution of the instructions by one or more processors, the one or more processors perform one or more operations comprising:
receiving one or more utterances from one or more users;
identifying one or more object avatars stored in an object avatar database, based on at least a context associated with the one or more utterances, wherein the object avatar database comprises one or more permissible outcomes corresponding to a set of parameters for controlling the one or more object avatars;
extracting one or more parameters to be used for controlling the one or more object avatars, from the one or more utterances;
determining based on a vector classification of the one or more parameters and the set of parameters, one or more outcomes of controlling the one or more object avatars based on the one or more parameters; and
controlling the one or more object avatars based on the one or more parameters, when the one or more outcomes correspond to the one or more permissible outcomes, wherein the controlling comprises looking up the object avatar database to determine if the one or more outcomes correspond to the one or more permissible outcomes, and wherein the one or more permissible outcomes indicate outcomes that are permissible when populated on a real object related to a corresponding object avat

Assignees

• Wipro Ltd

Inventors

• Ramachandra Iyer Manjunath

Classifications

• G10L15/18

  using natural language modelling · CPC title

• G06T13/80

  Two-dimensional [2D] animation, e.g. using sprites · CPC title

• G06F3/167

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

• G10L2015/228

  of application context · CPC title

• G10L15/1815

  Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning · CPC title