ENVIRONMENTALLY AWARE DIALOG POLICIES AND RESPONSE GENERATION

• US 20170162201A1
• Filed: 02/21/2017
• Published: 06/08/2017
• Est. Priority Date: 06/21/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Heck, Larry, Boies, Daniel, Sarikaya, Ruhi, Anastasakos, Tasos
• Granted Patent: US 10,304,448 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces

Abstract

Environmental conditions, along with other information, are used to adjust a response of a conversational dialog system. The environmental conditions may be used at different times within the conversational dialog system. For example, the environmental conditions can be used to adjust the dialog manager'"'"'s output (e.g., the machine action). The dialog state information that is used by the dialog manager includes environmental conditions for the current turn in the dialog as well as environmental conditions for one or more past turns in the dialog. The environmental conditions can also be used after receiving the machine action to adjust the response that is provided to the user. For example, the environmental conditions may affect the machine action that is determined as well as how the action is provided to the user. The dialog manager and the response generation components in the conversational dialog system each use the available environmental conditions.

Claims

1. A method for using environmental conditions in addition to other dialog state information in a conversational dialog system, comprising:

determining environmental conditions that are associated with a user dialog act;

determining a machine action using the environmental conditions and the user dialog act;

determining a response for the machine action; and

providing the response.

2. The method of claim 1, wherein determining the response for the machine action comprises using the environmental conditions to adjust the response.

3. The method of claim 1, wherein determining the environmental conditions that are associated with the input comprises determining at least one of:

a location;

a noise level;

a velocity;

a temperature;

a current activity, or a current computing device when authorized.

4. The method of claim 1, wherein determining the environmental conditions comprises determining a second set of environmental conditions that are associated with another user when authorized.

5. The method of claim 1, wherein determining the machine action using the environmental conditions and the user dialog act comprises using at least one of a rules based model or a statistical model.

6. The method of claim 1, wherein determining the response for the machine action comprises using the environmental conditions to determine a type of response from:

a spoken response or a visual presentation of the response.

7. The method of claim 1, further comprising updating the environmental conditions after determining the machine action.

8. The method of claim 1, further comprising receiving a selection of environmental conditions that may be used for a particular user.

9. The method of claim 1, further comprising updating a dialog policy to include rules relating to different environmental conditions.

10. A computer-readable storage medium storing computer-executable instructions for using environmental conditions in addition to other dialog state information in a conversational dialog system, comprising:

receiving a user dialog act;

determining environmental conditions that are associated with the user dialog act;

determining a machine action using the user dialog act;

determining a response for the machine action using the environmental conditions and the machine action; and

providing the response.

11. The computer-readable storage medium of claim 10, wherein determining the machine action comprises using the environmental conditions.

12. The computer-readable storage medium of claim 10, wherein determining the environmental conditions that are associated with the input comprises determining at least one of:

a current activity being performed when the user dialog act is received or a current computing device when authorized.

13. The computer-readable storage medium of claim 10, wherein determining the environmental conditions comprises determining a second set of environmental conditions that are associated with a current contact.

14. The computer-readable storage medium of claim 10, wherein determining the machine action and determining the response comprises using a rules based model that include rules for different environmental conditions.

15. The computer-readable storage medium of claim 10, wherein determining the response comprises using the environmental conditions to determine a type of response from:

a spoken response or a visual presentation of the response.

16. The computer-readable storage medium of claim 10, further comprising updating the environmental conditions after determining the machine action using the environmental conditions.

17. A system for using environmental conditions in addition to other dialog state information in a conversational dialog system, comprising:

a processor and memory;

an operating environment executing using the processor; and

a dialog manager that is configured to perform actions comprising;

determining environmental conditions that are associated with a user dialog act;

determining a machine action using the user dialog act and the environmental conditions;

determining a response for the machine action using the environmental conditions and the machine action; and

providing the response.

18. The system of claim 17, wherein determining the environmental conditions that are associated with the input comprises determining at least one of:

a current activity being performed when the user dialog act is received or a current computing device when authorized.

19. The system of claim 17, wherein determining the response comprises using the environmental conditions to determine a type of response from:

a spoken response or a visual presentation of the response.

20. The system of claim 17, further comprising updating the environmental conditions after determining the machine action using the environmental conditions.