Intelligently canceling user input

• US 9,570,086 B1
• Filed: 11/14/2012
• Issued: 02/14/2017
• Est. Priority Date: 11/18/2011
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Sanders, Jason, Taubman, Gabriel
• Primary Examiner(s): Wozniak, James
• Application Number:
  US13/676,283
• Time in Patent Office: 1,553 Days
• Field of Search: 704/251, 704/255, 704/270, 704/275
• US Class Current: 1/1
• CPC Class Codes: G10L 15/01 Assessment or evaluation of speech recognition systems
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/222 Barge in, i.e. overridable guidance for interrupting prompts
• 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 2015/228 of application context

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for intelligently cancelling user inputs. In one aspect, a requests input by a user is received by a dialog engine. A prompt or notification regarding the request is output by the dialog engine. That the user has taken an action in response to the prompt or notification is determined by the dialog engine. Based on the action taken by the user, that the response corresponds to a potential cancellation command is determined by the dialog system.

Claims

1. A computer-implemented method, comprising:

receiving, by a dialog engine, a response to a prompt regarding a request to clarify an initial request;

determining, based at least on a cancellation score that is pre-associated with the response satisfying a first threshold, that the response represents a potential user cancellation of the initial request;

determining that the user has taken an action after the prompt was output that is inconsistent with completion of the initial request;

in response to determining that the response represents a potential user cancellation of the initial request and determining that the user has taken an action after the prompt was output that is inconsistent with completion of the initial request, determining, by the dialog engine, an amount by which to adjust the cancellation score that is pre-associated with the response based on the action the user has taken that is inconsistent with completion of the initial request, wherein the amount by which to adjust the cancellation score that is pre-associated with the response is selected from among multiple values each associated with a different action; and

adjusting the cancellation score that is pre-associated with the response by the amount selected based on the action taken by the user after the prompt was output that is inconsistent with completion of the initial request.

2. The method of claim 1, comprising:

receiving a subsequent request from the user; and

determining that a subsequently received response that matches the response is an indication of cancellation of the subsequent request based on the adjusted cancellation score associated with the response satisfying a second threshold.

3. The method of claim 1, comprising receiving speech data encoding a request spoken by the user.

4. The method of claim 1, comprising:

outputting a prompt that requests the user to confirm that the initial request is to be cancelled, and

determining that the user has taken an action comprises determining that the user has confirmed that the initial request is to be cancelled.

5. The method of claim 1, comprising:

outputting a notification indicating that an action will be automatically initiated unless the user provides an additional input; and

determining that the user has taken an action comprises determining that that the user has provided the additional input.

6. The method of claim 1, wherein determining that the user has taken an action comprises determining that the user has input the request again.

7. The method of claim 1, wherein determining that the user has taken an action comprises determining that the user has input a different request.

8. The method of claim 1, wherein determining that the user has taken an action comprises determining powering down, disabling, or locking of a device that includes the dialog engine.

9. The method of claim 1, wherein determining that the user has taken an action comprises determining that the user has opened an application.

10. The method of claim 1, wherein determining that the user has taken an action comprises determining that the user has input a term that also corresponds to a potential cancellation command.

11. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers to perform operations comprising;

receiving, by a dialog engine, a response to a prompt regarding a request to clarify an initial request;

determining, based at least on a cancellation score that is pre-associated with the response satisfying a first threshold, that the response represents a potential user cancellation of the initial request;

determining that the user has taken an action after the prompt was output that is inconsistent with completion of the initial request;

in response to determining that the response represents a potential user cancellation of the initial request and determining that the user has taken an action after the prompt was output that is inconsistent with completion of the initial request, determining, by the dialog engine, an amount by which to adjust the cancellation score that is pre-associated with the response based on the action the user has taken that is inconsistent with completion of the initial request, wherein the amount by which to adjust the cancellation score that is pre-associated with the response is selected from among multiple values each associated with a different action; and

adjusting the cancellation score that is pre-associated with the response by the amount selected based on the action taken by the user after the prompt was output that is inconsistent with completion of the initial request.

12. The system of claim 11, comprising:

receiving a subsequent request from the user; and

determining that a subsequently received response that matches the response is an indication of cancellation of the subsequent request based on the adjusted cancellation score associated with the response satisfying a second threshold.

13. The system of claim 11, comprising receiving speech data encoding a request spoken by the user.

14. The system of claim 11, comprising:

outputting a prompt that requests the user to confirm that the initial request is to be cancelled, and

determining that the user has taken an action comprises determining that the user has confirmed that the initial request is to be cancelled.

15. The system of claim 11, comprising:

outputting a notification indicating that an action will be automatically initiated unless the user provides an additional input; and

determining that the user has taken an action comprises determining that that the user has provided the additional input.

16. The system of claim 11, wherein determining that the user has taken an action comprises determining that the user has input the request again.

17. The system of claim 11, wherein determining that the user has taken an action comprises determining that the user has input a different request.

18. The system of claim 11, wherein determining that the user has taken an action comprises determining powering down, disabling, or locking of a device that includes the dialog engine.

19. The system of claim 11, wherein determining that the user has taken an action comprises determining that the user has opened an application.

20. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

receiving, by a dialog engine, a response to a prompt regarding a request to clarify an initial request;

determining, based at least on a cancellation score that is pre-associated with the response satisfying a first threshold, that the response represents a potential user cancellation of the initial request;

determining that the user has taken an action after the prompt was output that is inconsistent with completion of the initial request;

in response to determining that the response represents a potential user cancellation of the initial request and determining that the user has taken an action after the prompt was output that is inconsistent with completion of the initial request, determining, by the dialog engine, an amount by which to adjust the cancellation score that is pre-associated with the response based on the action the user has taken that is inconsistent with completion of the initial request, wherein the amount by which to adjust the cancellation score that is pre-associated with the response is selected from among multiple values each associated with a different action; and

adjusting the cancellation score that is pre-associated with the response by the amount selected based on the action taken by the user after the prompt was output that is inconsistent with completion of the initial request.