METHOD AND APPARATUS FOR CAPABILITY-BASED PROCESSING OF VOICE QUERIES IN A MULTI-ASSISTANT ENVIRONMENT

• US 20200135200A1
• Filed: 10/31/2019
• Published: 04/30/2020
• Est. Priority Date: 10/31/2018
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: TAPARIA, Ankit, SHARMA, Mugula Satya Shankar kameshwar, KUMAR, Deepak, DUBEY, Shaktiman, RAJ, Rishabh, PADALA, Srikant, RAIMULE, Aishwarya Vitthal, PANDEY, Kislay, LOGANATHAN, Mohit
• Granted Patent: US 11,361,767 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

A method and an apparatus for processing audio commands includes receiving an audio command from a user, determining that a proper response to the audio command is unavailable in a first assistant device based on analyzing the audio command, transmitting the audio command to at least one second assistant device, and receiving at least one response to the audio command from the at least one second assistant device.

Claims

1. A method of processing commands by a first assistant device, the method comprising:

receiving an audio command from a user;

determining that a proper response to the audio command is unavailable in the first assistant device based on analyzing the audio command;

transmitting the audio command to at least one second assistant device; and

receiving at least one response to the audio command from the at least one second assistant device.

2. The method of claim 1, wherein determining that the proper response is unavailable further comprises determining that a proper application to process the audio command is unavailable in the first assistant device.

3. The method of claim 1, further comprising connecting to the at least one second assistant device.

4. The method of claim 1, wherein transmitting the audio command further comprises:

transmitting the audio command to a plurality of assistant devices including the second assistant device,

wherein the first assistant device is connected to the plurality of assistant devices via a network.

5. The method of claim 4, wherein the plurality of assistant devices are authorized to be used by the user.

6. The method of claim 4, wherein receiving the at least one response to the audio command from the at least one second assistant device further comprises:

receiving a plurality of responses from each of the plurality of assistant devices;

analyzing each of the plurality of responses;

selecting a most proper response based on parameters; and

providing the most proper response to the user.

7. The method of claim 6, wherein the parameters comprise ratings, price information, time information or location information included in the plurality of responses.

8. The method of claim 4, wherein receiving the at least one response to the audio command from the at least one second assistant device further comprises:

receiving a plurality of responses from each of the plurality of assistant devices;

analyzing each of the plurality of responses;

generating a response by combining the plurality of responses; and

providing the response to the user.

9. The method of claim 1, further comprising storing the at least one response to a database for the proper response in the first assistant device.

10. The method of claim 1, wherein receiving the at least one response further comprises receiving the at least one response generated by a third assistant device, wherein the audio command is forwarded to the third assistant device by the second assistant device.

11. The method of claim 10, wherein the audio command is forwarded to the third assistant device based on a determination that a proper response to the audio command is unavailable at the second assistant device.

12. The method of claim 1, wherein the audio command comprises a query or a command by voice of the user.

13. A first assistant apparatus for processing an audio command, the apparatus comprising:

a sensor configured to receive an audio command from a user; and

a processor configured to;

determine that a proper response to the audio command is unavailable based on analyzing the audio command,

transmit the audio command to at least one second assistant device, and

receive at least one response to the audio command from the at least one second assistant device.

14. The first assistant apparatus of claim 13, wherein determining that the proper response is unavailable further comprises determining that a proper application to process the audio command is unavailable in the first assistant apparatus.

15. The first assistant apparatus of claim 13, wherein transmitting the audio command comprises:

transmitting the audio command to a plurality of assistant devices including the second assistant device,

wherein the first assistant apparatus is connected to the plurality of assistant devices via a network.

16. The first assistant apparatus of claim 15, wherein receiving the at least one response to the audio command from the at least one second assistant device comprises:

receiving a plurality of responses from each of the plurality of assistant devices;

analyzing each of the plurality of responses;

selecting a most proper response based on parameters; and

providing the most proper response to the user.

17. The first assistant apparatus of claim 15, wherein receiving the at least one response to the audio command from the at least one second assistant device comprises:

receiving a plurality of responses from each of the plurality of assistant devices;

analyzing each of the plurality of responses;

generating a response by combining the plurality of responses; and

providing the response to the user.

18. The first assistant apparatus of claim 13, wherein receiving the at least one response further comprises receiving the at least one response generated by a third assistant device, wherein the audio command is forwarded to the third assistant device by the second assistant device.

19. The first assistant apparatus of claim 18, wherein the audio command is forwarded to the third assistant based on a determination that a proper response to the audio command is unavailable at the second assistant device.

20. A non-transitory computer-readable medium storing instructions thereon that, when executed, instruct at least one processor to perform a method, the method comprising:

receiving an audio command from a user;

determining that a proper response to the audio command is unavailable in the first assistant device based on analyzing the audio command;

transmitting the audio command to at least one second assistant device; and

receiving at least one response to the audio command from the at least one second assistant device.