Managing dialog data providers

• US 10,255,921 B2
• Filed: 07/31/2015
• Issued: 04/09/2019
• Est. Priority Date: 07/31/2015
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Elson, David Kliger, Whipp, David P., Yehoshua, Shir Judith
• Primary Examiner(s): Adesanya, Olujimi A
• Application Number:
  US14/815,794
• Publication Number:
  US 20170032791A1
• Time in Patent Office: 1,348 Days
• Field of Search: 704 9, 704231, 704235, 704246, 704257, 704270, 7042701, 704275
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for managing dialogs. In one aspect, a method includes receiving a request associated with a task from a user device; submitting the request to each of a plurality of distinct data providers; receiving a plurality of suggested dialog responses from two or more of the data providers; scoring the one or more suggested dialog responses based on one or more scoring factors; determining a particular dialog response to provide to the user based on the scoring; and providing the determined dialog response to the user device.

Claims

1. A method comprising:

receiving a request, from a user device, made by a user to perform a task, wherein the request comprises a voice input of a user of the user device;

determining a dialog associated with the task, wherein the dialog has a particular state;

submitting the voice input of the request to each of a plurality of distinct data providers, wherein each data provider is associated with a distinct data model configured to interpret particular types of voice inputs;

in response to the voice input, receiving a plurality of suggested dialog responses to the voice input from two or more of the data providers including a first data provider and a second data provider, wherein the first data provider determines whether to change a first suggested dialog response of the first data provider that is responsive to the voice input of the request based on a second suggested dialog response of the second data provider that is responsive to the voice input of the request, wherein the determination of the first data provider occurs prior to providing a voice response to the voice input to the user device, and wherein each of the plurality of suggested dialog responses is associated with a respective context;

scoring the plurality of suggested dialog responses to generate a respective score for each suggested dialog response based on one or more scoring factors including the respective contexts for the plurality of suggested dialog responses;

determining, from the plurality of suggested dialog responses, a particular dialog response to provide to the user responsive to the voice input of the request based on the scoring;

synthesizing a voice response that corresponds to the determined dialog response;

providing the voice response to the user device; and

performing the task in response to completing the dialog.

2. The method of claim 1, comprising:

updating a state of a dialog based on the determined dialog response.

3. The method of claim 1, comprising converting the voice input request to text prior to submitting the request to the plurality of data providers.

4. The method of claim 1, wherein performing the task in response to completing the dialog comprises:

determining if the dialog requires further responses from the user device based on the dialog state and in response to determining that no further responses are required, performing the task requested by the user.

5. The method of claim 1, wherein each data provider independently analyzes the request according to the data model associated with the data provider.

6. The method of claim 1, wherein in response to determining that none of the respective scores for the plurality of suggested dialog responses satisfy a threshold amount, synthesizing a response to provide to the user device to ascertain the user intent.

7. The method of claim 1, wherein determining a particular dialog response to provide to the user based on the scoring includes disqualifying a suggested dialog response having a score that is lower than a threshold amount and also disqualifying all suggested dialog responses that refer to the suggested dialog response.

8. The method of claim 1, comprising:

receiving a second voice input associated with the task from the user device;

submitting the second voice input to each of a plurality of distinct data providers;

determining a second dialog response to provide to the user responsive to the second voice input based on the suggested dialog responses generated by the plurality of distinct data providers;

providing the second dialog response to the user device; and

updating the state of the dialog.

9. A system comprising:

one or more computers configured to perform operations comprising;

receiving a request, from a user device, made by a user to perform a task, wherein the request comprises voice input of a user of the user device;

determining a dialog associated with the task, wherein the dialog has a particular state;

submitting the voice input of the request to each of a plurality of distinct data providers, wherein each data provider is associated with a distinct data model configured to interpret particular types of voice inputs;

in response to the voice input, receiving a plurality of suggested dialog responses to the voice input from two or more of the data providers including a first data provider and a second data provider, wherein the first data provider determines whether to change a first suggested dialog response of the first data provider that is responsive to the voice input of the request based on a second suggested dialog response of the second data provider that is responsive to the voice input of the request, wherein the determination of the first data provider occurs prior to providing a voice response to the voice input to the user device, and wherein each of the plurality of suggested dialog responses is associated with a respective context;

scoring the plurality of suggested dialog responses to generate a respective score for each suggested dialog response based on one or more scoring factors including the respective contexts for the plurality of suggested dialog responses;

determining, from the plurality of suggested dialog responses, a particular dialog response to provide to the user responsive to the voice input of the request based on the scoring;

synthesizing a voice response that corresponds to the determined dialog response;

providing the voice response to the user device; and

performing the task in response to completing the dialog.

10. The system of claim 9, wherein the operations further comprises updating a state of a dialog based on the determined dialog response.

11. The system of claim 9, wherein the operations further comprises converting the voice input request to text prior to submitting the request to the plurality of data providers.

12. The system of claim 9, wherein performing the task in response to completing the dialog comprises:

determining if the dialog requires further responses from the user device based on the dialog state and in response to determining that no further responses are required, performing the task requested by the user.

13. The system of claim 9, wherein each data provider independently analyzes the request according to the data model associated with the data provider.

14. The system of claim 9, wherein in response to determining that none of the respective scores for the plurality of suggested dialog responses satisfy a threshold amount, synthesizing a response to provide to the user device to ascertain the user intent.

15. The system of claim 9, wherein determining a particular dialog response to provide to the user based on the scoring includes disqualifying a suggested dialog response having a score that is lower than a threshold amount and also disqualifying all suggested dialog responses that refer to the suggested dialog response.

16. One or more non-transitory computer-readable storage media encoded with instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising:

receiving a request, from a user device, made by a user to perform a task, wherein the request comprises a voice input of a user of the user device;

submitting the request to each of a plurality of distinct data providers, wherein each data provider is associated with a distinct data model configured to interpret particular types of voice inputs;

in response to the voice input, receiving a plurality of suggested dialog responses to the voice input from two or more of the data providers including a first data provider and a second data provider, wherein the first data provider determines whether to change a first suggested dialog response of the first data provider that is responsive to the voice input of the request based on a second suggested dialog response of the second data provider that is responsive to the voice input of the request, wherein the determination of the first data provider occurs prior to providing a voice response to the voice input to the user device, and wherein each of the plurality of suggested dialog responses is associated with a respective context;

scoring the plurality of suggested dialog responses to generate a respective score for each suggested dialog response based on one or more scoring factors including the respective contexts for the plurality of suggested dialog responses;

determining, from the plurality of suggested dialog responses, a particular dialog response to provide to the user responsive to the voice input of the request based on the scoring;

synthesizing a voice response that corresponds to the determined dialog response;

providing the voice response to the user device; and

performing the task in response to completing the dialog.

17. The one or more computer-readable storage media of claim 16, wherein the operations further comprises:

updating a state of a dialog based on the determined dialog response.

18. The one or more computer-readable storage media of claim 16, wherein the operations further comprises converting the voice input request to text prior to submitting the request to the plurality of data providers.

19. The one or more computer-readable storage media of claim 16, wherein performing the task in response to completing the dialog comprises:

determining if the dialog requires further responses from the user device based on the dialog state and in response to determining that no further responses are required, performing the task requested by the user.

20. The one or more computer-readable storage media of claim 16, wherein each data provider independently analyzes the request according to the data model associated with the data provider.

21. The one or more computer-readable storage media of claim 16, wherein determining a particular dialog response to provide to the user based on the scoring includes disqualifying a suggested dialog response having a score that is lower than a threshold amount and also disqualifying all suggested dialog responses that refer to the suggested dialog response.