Multi-turn canned dialog

• US 10,636,424 B2
• Filed: 03/01/2018
• Issued: 04/28/2020
• Est. Priority Date: 11/30/2017
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Piernot, Philippe P., Pitolin, Kevin D.
• Primary Examiner(s): Pullias, Jesse S
• Application Number:
  US15/909,867
• Publication Number:
  US 20190164546A1
• Time in Patent Office: 789 Days
• Field of Search: 704231-257, 704270-275
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

Systems and processes for providing multi-turn canned dialog are provided. An example method includes, at an electronic device, receiving a natural-language input; determining whether the natural-language input satisfies dialog criteria for multi-turn canned dialog; in accordance with a determination that the natural-language input satisfies the dialog criteria for multi-turn canned dialog: identifying a natural-language output of the multi-turn canned dialog corresponding to the natural-language input; and outputting the natural-language output; and in accordance with a determination that the natural-language input does not satisfy the dialog criteria for multi-turn canned dialog: identifying a task associated with the natural-language input; and performing the task associated with the natural-language input.

Claims

1. An electronic device, comprising:

one or more processors;

a memory; and

one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for;

receiving a first natural-language input;

determining whether the first natural-language input satisfies a first dialog criteria of a multi-turn canned dialog;

in accordance with a determination that the first natural-language input satisfies the first dialog criteria of the multi-turn canned dialog;

identifying a first predefined natural-language output of the multi-turn canned dialog corresponding to the first natural-language input;

outputting the first predefined natural-language output;

receiving a second natural language input;

determining whether the second natural-language input satisfies a second dialog criteria of the multi-turn canned dialog; and

in accordance with a determination that the second natural-language input satisfies the second dialog criteria of the multi-turn canned dialog;

identifying a second predefined natural-language output of the multi-turn canned dialog corresponding to the second natural-language input; and

outputting the second predefined natural-language output;

in accordance with a determination that the first natural-language input does not satisfy the first dialog criteria of the multi-turn canned dialog;

identifying a task associated with the first natural-language input; and

performing the task associated with the first natural-language input.

2. The electronic device of claim 1, wherein the first dialog criteria of the multi-turn canned dialog includes a requirement that the first natural-language input matches a pattern of the multi-turn canned dialog.

3. The electronic device of claim 1, wherein the one or more programs further include instructions for:

determining, for the first natural-language input, a first saliency score associated with the multi-turn canned dialog; and

determining, for the first natural-language input, a second saliency score associated with a domain,

wherein the first dialog criteria of the multi-turn canned dialog includes a requirement that the first saliency score is higher than the second saliency score.

4. The electronic device of claim 3, wherein determining, for the first natural-language input, the first saliency score associated with the multi-turn canned dialog includes:

determining a degree to which the first natural-language input matches a span of the multi-turn canned dialog.

5. The electronic device of claim 3, wherein determining whether the first natural-language input satisfies a first dialog criteria of the multi-turn canned dialog includes:

determining whether the multi-turn canned dialog is associated with an override tag; and

in accordance with a determination that the multi-turned canned dialog is associated with the override tag, determining that the first natural-language input satisfies the first dialog criteria of the multi-turn canned dialog.

6. The electronic device of claim 1, wherein the one or more programs further include instructions for:

in accordance with a determination that the second natural-language input does not satisfy the second dialog criteria of the multi-turn canned dialog, storing a state of the multi-turn canned dialog.

7. The electronic device of claim 6, wherein the one or more programs further include instructions for:

receiving a third natural-language input;

determining whether the third natural-language input corresponds to the state of the multi-turn canned dialog; and

in accordance with a determination that the third natural-language input corresponds to the state of the multi-turn canned dialog, outputting the second predefined natural-language output.

8. The electronic device of claim 7, wherein determining whether the third natural-language input corresponds to the state of the multi-turn canned dialog includes determining whether the third natural-language input satisfies the second dialog criteria of the multi-turn canned dialog.

9. The electronic device of claim 1, wherein identifying a task associated with the first natural-language input includes identifying the task based on an intent associated with the first natural-language input.

10. The electronic device of claim 9, wherein performing the task associated with the first natural-language input includes performing a task associated with the intent.

11. A non-transitory computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by one or more processors of an electronic device, cause the electronic device to:

receive a first natural-language input;

determine whether the first natural-language input satisfies a first dialog criteria of a multi-turn canned dialog;

in accordance with a determination that the first natural-language input satisfies the first dialog criteria of the multi-turn canned dialog;

identify a first predefined natural-language output of the multi-turn canned dialog corresponding to the first natural-language input;

output the first predefined natural-language output;

determine whether the second natural-language input satisfies a second dialog criteria of the multi-turn canned dialog;

in accordance with a determination that the second natural-language input satisfies the second dialog criteria of the multi-turn canned dialog;

identify a second predefined natural-language output of the multi-turn canned dialog corresponding to the second natural-language input; and

output the second predefined natural-language output;

in accordance with a determination that the first natural-language input does not satisfy the first dialog criteria of the multi-turn canned dialog;

identify a task associated with the first natural-language input; and

perform the task associated with the first natural-language input.

12. The non-transitory computer-readable storage medium of claim 11, wherein the first dialog criteria of the multi-turn canned dialog includes a requirement that the first natural-language input matches a pattern of the multi-turn canned dialog.

13. The non-transitory computer-readable storage medium of claim 11, wherein the one or more programs further include instructions, which when executed by one or more processors of an electronic device, cause the electronic device to:

determining, for the first natural-language input, a first saliency score associated with the multi-turn canned dialog; and

determining, for the first natural-language input, a second saliency score associated with a domain,

wherein the first dialog criteria of the multi-turn canned dialog includes a requirement that the first saliency score is higher than the second saliency score.

14. The non-transitory computer-readable storage medium of claim 13, wherein determining, for the first natural-language input, the first saliency score associated with the multi-turn canned dialog includes:

determining a degree to which the first natural-language input matches a span of the multi-turn canned dialog.

15. The non-transitory computer-readable storage medium of claim 13, wherein determining whether the first natural-language input satisfies a first dialog criteria of the multi-turn canned dialog includes:

determining whether the multi-turn canned dialog is associated with an override tag; and

in accordance with a determination that the multi-turned canned dialog is associated with the override tag, determining that the first natural-language input satisfies the first dialog criteria of the multi-turn canned dialog.

16. The non-transitory computer-readable storage medium of claim 11, wherein the one or more programs further include instructions, which when executed by one or more processors of an electronic device, cause the electronic device to:

in accordance with a determination that the second natural-language input does not satisfy the second dialog criteria of the multi-turn canned dialog, store a state of the multi-turn canned dialog.

17. The non-transitory computer-readable storage medium of claim 16, wherein the one or more programs further include instructions, which when executed by one or more processors of an electronic device, cause the electronic device to:

receive a third natural-language input;

determine whether the third natural-language input corresponds to the state of the multi-turn canned dialog; and

in accordance with a determination that the third natural-language input corresponds to the state of the multi-turn canned dialog, output the second predefined natural-language output.

18. The non-transitory computer-readable storage medium of claim 17, wherein determining whether the third natural-language input corresponds to the state of the multi-turn canned dialog includes determining whether the third natural-language input satisfies the second dialog criteria of the multi-turn canned dialog.

19. The non-transitory computer-readable storage medium of claim 11, wherein identifying a task associated with the first natural-language input includes identifying the task based on an intent associated with the first natural-language input.

20. The non-transitory computer-readable storage medium of claim 19, wherein performing the task associated with the first natural-language input includes performing a task associated with the intent.

21. A method, comprising:

at an electronic device with one or more processors;

receiving a first natural-language input;

determining whether the first natural-language input satisfies a first dialog criteria of a multi-turn canned dialog;

in accordance with a determination that the first natural-language input satisfies the first dialog criteria of the multi-turn canned dialog;

identifying a first predefined natural-language output of the multi-turn canned dialog corresponding to the first natural-language input;

outputting the first predefined natural-language output;

receiving a second natural language input;

determining whether the second natural-language input satisfies a second dialog criteria of the multi-turn canned dialog; and

in accordance with a determination that the second natural-language input satisfies the second dialog criteria of the multi-turn canned dialog;

identifying a second predefined natural-language output of the multi-turn canned dialog corresponding to the second natural-language input; and

outputting the second predefined natural-language output;

in accordance with a determination that the first natural-language input does not satisfy the first dialog criteria of the multi-turn canned dialog;

identifying a task associated with the first natural-language input; and

performing the task associated with the first natural-language input.

22. The method of claim 21, wherein the first dialog criteria of the multi-turn canned dialog includes a requirement that the first natural-language input matches a pattern of the multi-turn canned dialog.

23. The method of claim 21, further comprising:

determining, for the first natural-language input, a first saliency score associated with the multi-turn canned dialog; and

determining, for the first natural-language input, a second saliency score associated with a domain,

wherein the first dialog criteria of the multi-turn canned dialog includes a requirement that the first saliency score is higher than the second saliency score.

24. The method of claim 23, wherein determining, for the first natural-language input, the first saliency score associated with the multi-turn canned dialog includes:

determining a degree to which the first natural-language input matches a span of the multi-turn canned dialog.

25. The method of claim 23, wherein determining whether the first natural-language input satisfies a first dialog criteria of the multi-turn canned dialog includes:

determining whether the multi-turn canned dialog is associated with an override tag; and

in accordance with a determination that the multi-turned canned dialog is associated with the override tag, determining that the first natural-language input satisfies the first dialog criteria of the multi-turn canned dialog.

26. The method of claim 21, further comprising:

in accordance with a determination that the second natural-language input does not satisfy the second dialog criteria of the multi-turn canned dialog, storing a state of the multi-turn canned dialog.

27. The method of claim 26, further comprising:

receiving a third natural-language input;

determining whether the third natural-language input corresponds to the state of the multi-turn canned dialog; and

in accordance with a determination that the third natural-language input corresponds to the state of the multi-turn canned dialog, outputting the second predefined natural-language output.

28. The method of claim 27, wherein determining whether the third natural-language input corresponds to the state of the multi-turn canned dialog includes determining whether the third natural-language input satisfies the second dialog criteria of the multi-turn canned dialog.

29. The method of claim 21, wherein identifying a task associated with the first natural-language input includes identifying the task based on an intent associated with the first natural-language input.

30. The method of claim 29, wherein performing the task associated with the first natural-language input includes performing a task associated with the intent.