VOICE COMMAND RESPONSE ACCURACY

• US 20160365088A1
• Filed: 06/10/2016
• Published: 12/15/2016
• Est. Priority Date: 06/10/2015
• Status: Abandoned Application

• Current Assignee: Synapse.ai Inc.
• Original Assignee: Synapse.ai Inc.
• Inventors: LIANG, Tao, PATEL, Mehul, CHHATRALA, Hitesh, BILSBORROW, Todd
• Application Number:
  US15/179,277
• Publication Number:
  US 20160365088A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 3/016 Input arrangements with force or tactile feedback as computer generated output to the user
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/221 Announcement of recognition results
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/225 Feedback of the input speech
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology

Abstract

According to an example, a processor may receive a request via voice command and obtain a response to the request. The processor may also obtain a confidence level of the obtained response, in which the confidence level corresponds to an accuracy of the identified response to the received request, identify an indication aspect corresponding to the identified confidence level, wherein different indication aspects correspond to different confidence levels, and output the obtained response with the identified indication aspect. The processor may also receive user feedback on the outputted response, in which the received user feedback is used to improve an accuracy of responses provided by the processor to requests received via voice command.

Claims

1. A computing device for improving voice command response accuracy, said computing device comprising:

a processor;

a memory on which is stored machine readable instructions that are to cause the processor to;

receive a request via voice command;

obtain a response to the request;

obtain a confidence level of the obtained response, wherein the confidence level corresponds to an accuracy of the identified response to the received request;

identify an indication aspect corresponding to the identified confidence level, wherein different indication aspects correspond to different confidence levels;

output the obtained response with the identified indication aspect; and

receive user feedback on the outputted response, wherein the received user feedback is used to improve an accuracy of responses provided by the processor to requests received via voice command.

2. The computing device according to claim 1, wherein the machine readable instructions are further to cause the processor to:

implement the received user feedback to improve the accuracy of responses to requests received via voice command.

3. The computing device according to claim 1, wherein the machine readable instructions are further to cause the processor to:

communicate the received user feedback to a server, and wherein the server is to implement the received user feedback to improve the accuracy of responses to requests received via voice command.

4. The computing device according to claim 1, wherein, to obtain the response to the request, the machine readable instructions are further to cause the processor to:

identify a plurality of candidate responses to the request; and

identify a confidence level of each of the plurality of candidate responses, wherein the obtained response corresponds to the candidate response of the plurality of candidate responses having the highest confidence level.

5. The computing device according to claim 1, wherein, to obtain the response to the request, the machine readable instructions are further to cause the processor to:

identify a plurality of sub-responses to the request; and

identify a confidence level of each of the plurality of sub-responses, wherein the obtained response is a combination of the identified confidence levels of the plurality of sub-responses.

6. The computing device according to claim 1, wherein the user feedback indicates a confidence measure the user has in the outputted response.

7. The computing device according to claim 6, further comprising:

an audio input device, wherein the user feedback is received as an audible input through the audio input device.

8. The computing device according to claim 1, wherein the different indication aspects includes different values of an indicator, and wherein the different values include at least one of different colors, different shades of a same color, and combinations thereof.

9. The computing device according to claim 1, wherein to output the obtained response with the identified indication aspect, the instructions are further to cause the processor to:

at least one of;

display the obtained response and the identified indication aspect on a display screen;

audibly output the obtained response and the identified indication aspect; and

mechanically output the identification indication as a vibration.

10. A method for improving voice command response accuracy comprising:

receiving, by a processor, a request via voice command;

obtaining, by the processor, a response to the request;

obtaining, by the processor, a confidence level of the obtained response, wherein the confidence level corresponds to an accuracy of the identified response to the received request;

identifying, by the processor, an indication aspect corresponding to the identified confidence level, wherein different indication aspects correspond to different confidence levels;

outputting, by the processor, the identified response with the identified indication aspect; and

receiving, by the processor, user feedback on the outputted response and the identified indication aspect, wherein the received user feedback indicates a confidence measure the user has in the outputted response.

11. The method according to claim 10, further comprising:

implementing the received user feedback to improve the accuracy of responses to requests received via voice command.

12. The method according to claim 10, further comprising:

communicating the received user feedback to a server, and wherein the server is to implement the received user feedback to improve the accuracy of responses to requests received via voice command.

13. The method according to claim 10, wherein obtaining the response to the request further comprises:

identifying a plurality of candidate responses to the request; and

identifying a confidence level of each of the plurality of candidate responses, wherein the obtained response corresponds to the candidate response of the plurality of candidate responses having the highest confidence level.

14. The method according to claim 10, wherein obtaining the response to the request further comprises:

identifying a plurality of sub-responses to the request; and

identifying a confidence level of each of the plurality of sub-responses, wherein the obtained response is a combination of the identified confidence levels of the plurality of sub-responses.

15. The method according to claim 10, wherein the different indication aspects includes different values of an indicator, and wherein the different values include at least one of different colors, different shades of a same color, and combinations thereof.

16. The method according to claim 10, wherein outputting the obtained response with the identified indication aspect further comprises:

at least one of;

displaying the obtained response and the identified indication aspect on a display screen;

audibly outputting the obtained response and the identified indication aspect; and

mechanically outputting the identification indication as a vibration.

17. A non-transitory computer readable storage medium on which is stored machine readable instructions that when executed by a processor cause the processor to:

receive a request via voice command;

obtain a response to the request;

obtain a confidence level of the obtained response, wherein the confidence level corresponds to an accuracy of the identified response to the received request;

identify an indication aspect corresponding to the identified confidence level, wherein different indication aspects correspond to different confidence levels;

output the identified response with the identified indication aspect; and

receive user feedback on the outputted response and the identified indication aspect, wherein the received user feedback indicates a confidence measure the user has in the outputted response.

18. The non-transitory computer readable storage medium according to claim 17, wherein the machine readable instructions are further to cause the processor to:

implement the received user feedback to improve the accuracy of responses to requests received via voice command.

19. The non-transitory computer readable storage medium according to claim 17, wherein the machine readable instructions are further to cause the processor to:

identify a plurality of candidate responses to the request; and

identify a confidence level of each of the plurality of candidate responses, wherein the obtained response corresponds to the candidate response of the plurality of candidate responses having the highest confidence level.

20. The non-transitory computer readable storage medium according to claim 17, wherein the machine readable instructions are further to cause the processor to:

identify a plurality of sub-responses to the request; and

identify a confidence level of each of the plurality of sub-responses, wherein the obtained response is a combination of the identified confidence levels of the plurality of sub-responses.