Intelligently canceling user input

• US 9,767,801 B1
• Filed: 12/30/2016
• Issued: 09/19/2017
• 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 S
• Application Number:
  US15/395,450
• Time in Patent Office: 263 Days
• Field of Search: 704251, 704255, 704270, 704275
• 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 cancellation detector of a system that includes the dialog cancellation detector, a cancellation score database, and a dialog engine, a request that is input at a user device in response to a prompt;

identifying, by the dialog cancellation detector, an expected input type that is associated with the prompt;

identifying, by the dialog cancellation detector and using the cancellation score database, a cancellation score that is predefined for a potential cancellation term included in the request that is input at the user device in response to the prompt, based on the identified expected input type that is associated with the prompt, wherein the cancellation score that is predefined for the potential cancellation term is different for different expected input types that are associated with different prompts;

determining, by the dialog cancellation detector, that the identified cancellation score satisfies a first threshold score;

in response to determining that the identified cancellation score satisfies the first threshold score, identifying, by the dialog cancellation detector, the potential cancellation term included in the request that is input at the user device in response to the prompt as a cancellation command; and

in response to identifying the potential cancellation term included in the request that is input at the user device as a cancellation command, outputting, by the dialog cancellation detector and to the dialog engine, an indication to the user device that the potential cancellation term included in the request that is input at the user device is a cancellation command rather than a refinement of a previous input.

2. The method of claim 1, wherein the request comprises a spoken input.

3. The method of claim 1, wherein the cancellation score that is predefined for the potential cancellation command is generated based on activity performed by other users in response to previous inputs of the potential cancellation command.

4. The method of claim 1, wherein the prompt comprises a prompt for a refinement of a previous input.

5. The method of claim 1, wherein the expected input type comprises email dictation or a Short Messaging Service (SMS) dictation input type.

6. The method of claim 1, wherein the expected input type comprises a number input type.

7. The method of claim 1, wherein the cancellation score is stored in a data triple that comprises data identifying the expected input type, data identifying the potential cancellation term, and data identifying the cancellation score.

8. 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 cancellation detector of a system that includes the dialog cancellation detector, a cancellation score database, and a dialog engine, a request that is input at a user device in response to a prompt;

identifying, by the dialog cancellation detector, an expected input type that is associated with the prompt;

identifying, by the dialog cancellation detector and using the cancellation score database, a cancellation score that is predefined for a potential cancellation term included in the request that is input at the user device in response to the prompt, based on the identified expected input type that is associated with the prompt, wherein the cancellation score that is predefined for the potential cancellation term is different for different expected input types that are associated with different prompts;

determining, by the dialog cancellation detector, that the identified cancellation score satisfies a first threshold score;

in response to determining that the identified cancellation score satisfies the first threshold score, identifying, by the dialog cancellation detector, the potential cancellation term included in the request that is input at the user device in response to the prompt as a cancellation command; and

in response to identifying the potential cancellation term included in the request that is input at the user device as a cancellation command, outputting, by the dialog cancellation detector and to the dialog engine, an indication to the user device that the potential cancellation term included in the request that is input at the user device is a cancellation command rather than a refinement of a previous input.

9. The system of claim 8, wherein the request comprises a spoken input.

10. The system of claim 8, wherein the cancellation score that is predefined for the potential cancellation command is generated based on activity performed by other users in response to previous inputs of the potential cancellation command.

11. The system of claim 8, wherein the prompt comprises a prompt for a refinement of a previous input.

12. The system of claim 8, wherein the expected input type comprises email dictation or a Short Messaging Service (SMS) dictation input type.

13. The system of claim 8, wherein the expected input type comprises a number input type.

14. The system of claim 8, wherein the cancellation score is stored in a data triple that comprises data identifying the expected input type, data identifying the potential cancellation term, and data identifying the cancellation score.

15. 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 cancellation detector of a system that includes the dialog cancellation detector, a cancellation score database, and a dialog engine, a request that is input at a user device in response to a prompt;

identifying, by the dialog cancellation detector, an expected input type that is associated with the prompt;

identifying, by the dialog cancellation detector and using the cancellation score database, a cancellation score that is predefined for a potential cancellation term included in the request that is input at the user device in response to the prompt, based on the identified expected input type that is associated with the prompt, wherein the cancellation score that is predefined for the potential cancellation term is different for different expected input types that are associated with different prompts;

determining, by the dialog cancellation detector, that the identified cancellation score satisfies a first threshold score;

in response to determining that the identified cancellation score satisfies the first threshold score, identifying, by the dialog cancellation detector, the potential cancellation term included in the request that is input at the user device in response to the prompt as a cancellation command; and

in response to identifying the potential cancellation term included in the request that is input at the user device as a cancellation command, outputting, by the dialog cancellation detector and to the dialog engine, an indication to the user device that the potential cancellation term included in the request that is input at the user device is a cancellation command rather than a refinement of a previous input.

16. The medium of claim 15, wherein the request comprises a spoken input.

17. The medium of claim 15, wherein the cancellation score that is predefined for the potential cancellation command is generated based on activity performed by other users in response to previous inputs of the potential cancellation command.

18. The medium of claim 15, wherein the prompt comprises a prompt for a refinement of a previous input.

19. The medium of claim 15, wherein the expected input type comprises email dictation or a Short Messaging Service (SMS) dictation input type.

20. The medium of claim 15, wherein the expected input type comprises a number input type.