Dynamic boundary creation for voice command authentication

Patent metadata

Field	Value
Publication number	US-12014734-B2
Application number	US-202117382540-A
Country	US
Kind code	B2
Filing date	Jul 22, 2021
Priority date	Jul 22, 2021
Publication date	Jun 18, 2024
Grant date	Jun 18, 2024

Abstract

A computer-implemented method executes voice commands issued from within a command boundary. The method includes defining a command boundary for a VCD, where the command boundary is based on receiving an input from a user. The method further includes receiving, from the user and by the VCD, a voice command. The method also includes determining an origination location of the voice command. The method includes classifying the voice command into a command category. The method further includes executing the voice command in response to determining the origination location is within the command boundary for the VCD. The method also includes storing a set of data for the voice command.

First claim

What is claimed is:

1. A computer-implemented method comprising:
receiving an input from a user;
defining a command boundary for a voice controlled device (VCD), wherein the command boundary is based on the receiving the input from the user, and the command boundary outlines a physical area;
receiving, from the user by the VCD and in response to the defining the command boundary, a voice command, wherein the receiving the voice command is in response to the defining the command boundary;
determining an origination location of the voice command;
determining the origination location of the voice command is within the command boundary;
classifying the voice command into a command category;
executing the voice command in response to the determining the origination location is within the command boundary for the VCD; and
storing a set of data for the voice command.

2. The method of claim 1 , wherein the command boundary is a first command boundary, the method further comprising:
defining a second command boundary for the VCD, wherein the first command boundary is associated with a first command category, and the second command boundary is associated with a second command category.

3. The method of claim 2 , wherein the executing the voice command is in response to the command category being the same as the first command category.

4. The method of claim 2 , wherein the first command boundary and the second command boundary do not overlap.

5. The method of claim 2 , wherein the first command boundary and the second command boundary at least partially overlap.

6. The method of claim 2 , wherein the first command boundary is associated with the user, and the second command boundary is associated with a second user.

7. The method of claim 1 further comprising:
training a learning model, by a set of training data, to generate a recommendation for first command boundary, wherein the defining the first command boundary is in response to the generating of the recommendation.

8. The method of claim 7 , further comprising updating, in response to receiving feedback from the user, the learning model.

9. The method of claim 1 , wherein the command boundary is configured to deactivate in response to a trigger.

10. The method of claim 9 , wherein the trigger is includes executing a predetermined number of commands from the first command boundary.

11. The method of claim 9 , wherein the trigger is based on a period of time.

12. The method of claim 1 , wherein the input from the user is received from a virtual device.

13. The method of claim 12 , wherein the input is based on a user-drawn boundary on an interface of the virtual device.

14. The method of claim 12 , wherein the voice command is a second voice command and the origination location is a second origination location, the method further comprising:
receiving, from the user, a first voice command;
determining a first origination location of the first voice command;
determining the first origination location is outside of the command boundary;
prompting, in response to determining the first origination location is outside the command area, the user to move into the command area; and
receiving, from the user, the second voice command.

15. The method of claim 14 , wherein the prompting includes displaying, on the virtual device, the command boundary.

16. A system comprising:
a processor; and
a computer-readable storage medium communicatively coupled to the processor and storing program instructions which, when executed by the processor, are configured to cause the processor to:
define a first command boundary for a first voice controlled device (VCD), wherein the first command boundary is based on receiving an input from a user, and the command boundary outlines a physical area;
receive, from the user by the first VCD and in response to the defining the command boundary, a voice command;
determine an origination location of the voice command;
determine the origination location of the voice command is within the command boundary;
classify the voice command into a command category;
determine the origination location is within the first command boundary;
execute, by the first VCD and in response to the determination the origination location is within the first command boundary, the voice command; and
store a set of data for the voice command.

17. The system of claim 16 , and the program instructions are further configured to cause the processor to:
define a second command boundary for a second VCD;
receive, from the user and by the second VCD, the voice command;
determine the origination location is outside the second command boundary; and
deny, by the second VCD and in response to the determination the origination location is outside the second command boundary, execution of the voice command.

18. The system of claim 17 , wherein the user is a first user, the first command boundary is correlated to the first user, the defining of the second command boundary is based on receiving an input from a second user, and the second command boundary is correlated to the second user.

19. A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processing unit to cause the processing unit to:
define a first command boundary for a first voice controlled device (VCD), wherein the first command boundary is based on receiving an input from a user, and the command boundary outlines a physical area;
receive, from the user by the first VCD and in response to the defining the command boundary, a voice command;
determine an origination location of the voice command;
determine the origination location of the voice command is within the command boundary;
classify the voice command into a command category;
execute the voice command in response to determining the origination location is within the command boundary for the VCD; and
store a set of data for the voice command.

20. The computer program product of claim 19 , wherein the program instructions are further configured to cause the processing unit to:
define a second command boundary for a second VCD;
receive, from the user and by the second VCD, the voice command;
determine the origination location is outside the second command boundary; and
deny, by the second VCD and in response to the determination the origination location is outside the second command boundary, execution of the voice command.

Assignees

• IBM

Inventors

• Decrop Clement
• Agrawal Tushar
• Fox Jeremy R
• Rakshit Sarbajit K

Classifications

• G10L15/063

  Training · CPC title

• G10L15/16

  using artificial neural networks · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G06F3/167 Primary

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