Crowd sourcing information to fulfill user requests

Patent metadata

Field	Value
Publication number	US-9953088-B2
Application number	US-201615063223-A
Country	US
Kind code	B2
Filing date	Mar 7, 2016
Priority date	May 14, 2012
Publication date	Apr 24, 2018
Grant date	Apr 24, 2018

Abstract

A user request is received from a mobile client device, where the user request includes at least a speech input and seeks an informational answer or performance of a task. A failure to provide a satisfactory response to the user request is detected. In response to detection of the failure, information relevant to the user request is crowd-sourced by querying one or more crowd sourcing information sources. One or more answers are received from the crowd sourcing information sources, and the response to the user request is generated based on at least one of the one or more answers received from the one or more crowd sourcing information sources.

First claim

What is claimed is:

1. A method for providing a response to a user request, comprising:
at an electronic device with one or more processors and memory:
receiving a user request, the user request including at least a speech input and seeks an informational answer or performance of a task, wherein:
the user request is associated with a detected failure to provide a satisfactory response to the user request; and
one or more crowd sourcing information sources relevant to the user request are queried in response to the detected failure to provide a satisfactory response to the user request; and

generating a response to the user request based on the one or more answers obtained from querying the one or more crowd sourcing information sources.

2. The method of claim 1 , wherein:
one or more queries are generated based on the user request; and
the one or more queries are sent to the one or more crowd sourcing information sources to obtain the one or more answers.

3. The method of claim 1 , wherein:
the one or more crowd sourcing information sources are identified from a set of crowd sourcing information sources.

4. The method of claim 1 , further comprising:
prior to the one or more crowd sourcing information sources being queried:
requesting user permission to send the information contained in the user request to the one or more crowd sourcing information sources; and
receiving user permission to send the information contained in the user request to the one or more crowd sourcing information sources.

5. The method of claim 1 , further comprising:
presenting at least one real-time answer to the user request, wherein the real-time answer is obtained from a real-time answer-lookup database; and
after presenting the at least one real-time answer, presenting at least one non-real-time answer to the user request, wherein the non-real-time answer is obtained from a non-real-time expert service.

6. The method of claim 1 , further comprising:
presenting a remedial response to the user request, wherein the remedial response is presented upon failing to obtain any answer from at least one of the one or more crowd sourcing information sources.

7. The method of claim 1 , wherein:
more than one answer is obtained from the one or more crowd sourcing information sources; and
the more than one answer is ranked in accordance with predetermined criteria.

8. The method of claim 1 , wherein at least one of the one or more answers from the crowd sourcing information sources is obtained from individual members of the public in non-real-time.

9. The method of claim 1 , wherein the detected failure to provide a satisfactory response to the user request comprises a determination that a web-search based on information contained in the user request is unsatisfactory to the user.

10. The method of claim 1 , further comprising:
prior to generating the response to the user request, providing a second response to the user request; and
receiving user input indicating that the second response is unsatisfactory, wherein the detected failure to provide a satisfactory response to the user request comprises the received user input.

11. The method of claim 1 , wherein the detected failure to provide a satisfactory response to the user request is based on usage logs associated with a user.

12. The method of claim 1 , wherein querying the one or more crowd sourcing information sources includes querying one or more remote sources.

13. A non-transitory computer-readable medium storing instructions, the instructions, when executed by one or more processors, cause the processors to perform operations comprising:
receiving a user request, the user request including at least a speech input and seeks an informational answer or performance of a task, wherein:
the user request is associated with a detected failure to provide a satisfactory response to the user request; and
one or more crowd sourcing information sources relevant to the user request are queried in response to detecting the failure to provide a satisfactory response to the user request; and

generating a response to the user request based on the one or more answers obtained from querying the one or more crowd sourcing information sources.

14. The non-transitory computer-readable medium of claim 13 , wherein:
one or more queries are generated based on the user request; and
the one or more queries are sent to the one or more crowd sourcing information sources to obtain the one or more answers.

15. The non-transitory computer-readable medium of claim 13 , wherein:
the one or more crowd sourcing information sources are identified from a set of crowd sourcing information sources.

16. The non-transitory computer-readable medium of claim 13 , wherein the operations further comprise:
prior to the one or more crowd sourcing information sources being queried:
requesting user permission to send the information contained in the user request to the one or more crowd sourcing information sources; and
receiving user permission to send the information contained in the user request to the one or more crowd sourcing information sources.

17. The non-transitory computer-readable medium of claim 13 , wherein the operations further comprise:
presenting at least one real-time answer to the user request, wherein the real-time answer is obtained from a real-time answer-lookup database; and
after presenting the at least one real-time answer, presenting at least one non-real-time answer to the user request, wherein the non-real-time answer is obtained from a non-real-time expert service.

18. The non-transitory computer-readable medium of claim 13 , wherein the operations further comprise:
presenting a remedial response to the user request, wherein the remedial response is presented upon failing to obtain any answer from at least one of the one or more crowd sourcing information sources.

19. The non-transitory computer-readable medium of claim 13 , wherein:
more than one answer is obtained from the one or more crowd sourcing information sources; and
the more than one answer is ranked in accordance with predetermined criteria.

20. The non-transitory computer-readable medium of claim 13 , wherein at least one of the one or more answers from the crowd sourcing information sources is obtained from individual members of the public in non-real-time.

21. The non-transitory computer-readable medium of claim 13 , wherein querying the one or more crowd sourcing information sources includes querying one or more remote sources.

22. A system, comprising:
one or more processors; and
memory storing instructions, the instructions, when executed by the one or more processors, cause the processors to perform operations comprising:
receiving a user request, the user request including at least a speech input and seeks an informational answer or performance of a task, wherein:
the user request is associated with a detected failure to provide a satisfactory response to the user request; and
one or more crowd sourcing information sources relevant to the user request are queried in response to detecting the failure to provide a satisfactory response to the user request; and
generating a response to the user request based on the one or more answers obtained from querying the one or more crowd sourcing information sources.

23. The system of claim 22 , wherein:
one or more queries are generated based on the user request; and
the

Assignees

• Apple Inc

Inventors

• Gruber Thomas R
• Cheyer Adam John
• Pitschel Donald W

Classifications

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/248

  Presentation of query results · CPC title

• G06F16/24575

  using context · CPC title

• G06F16/90332 Primary

  Natural language query formulation or dialogue systems · CPC title

• G06F17/30554

  Physics · mapped topic