Environmentally aware dialog policies and response generation

Patent metadata

Field	Value
Publication number	US-9589565-B2
Application number	US-201313923917-A
Country	US
Kind code	B2
Filing date	Jun 21, 2013
Priority date	Jun 21, 2013
Publication date	Mar 7, 2017
Grant date	Mar 7, 2017

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.

First claim

What is claimed is:

1. A computer-implemented method, performed by at least one processor, for using environmental conditions in addition to other dialog state information in a conversational dialog system, comprising:
receiving a user dialog act requesting a computer system to perform a task;
based on the user dialog act, determining a first machine action to perform the task;
accessing environmental conditions that are associated with the user dialog act;
based on the environmental conditions and the user dialog act, determining a second machine action other than performing the task, wherein the second machine action at least temporarily prevents completion of the first machine action; and
performing the second machine action to provide a response to a user.

2. The method of claim 1 , further comprising determining a response type for the second machine action based on the environmental conditions.

3. The method of claim 1 , wherein accessing the environmental conditions that are associated with the input comprises accessing at least one of: a location; a noise level; a velocity; a temperature; a current activity, or a current computing device.

4. The method of claim 1 , wherein the environmental conditions comprise environmental conditions associated with another user.

5. The method of claim 1 , wherein determining the machine actions based on 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 2 , wherein determining the response type comprises using the environmental conditions to determine a type of response from: an audible response or a visual presentation of the response.

7. The method of claim 1 , further comprising updating the environmental conditions after determining the second 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. The method of claim 1 , wherein the response comprises a prompt to the user, wherein the prompt requests an additional response from the user based on the environmental conditions and the requested task.

11. A computer-readable storage device 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 requesting a computer system to perform a task;
based on the user dialog act, determining a first machine action to perform the task;
accessing environmental conditions that are associated with the user dialog act;
based on the environmental conditions and the user dialog act, determining a second machine action other than performing the task, wherein the second machine action at least temporarily prevents completion of the first machine action; and
performing the second machine action to provide a response to a user.

12. The computer-readable storage device of claim 11 , wherein accessing the environmental conditions that are associated with the input comprises accessing at least one of: a current activity being performed when the user dialog act is received or a current computing device.

13. The computer-readable storage device of claim 11 , wherein the environmental conditions comprise environmental conditions that are associated with a current contact.

14. The computer-readable storage device of claim 11 , wherein determining the machine actions comprises using a rules based model that include rules for different environmental conditions.

15. The computer-readable storage device of claim 11 , further comprising instruction for using the environmental conditions to determine a type of response from: an audible response or a visual presentation of the response.

16. The computer-readable storage device of claim 11 , further comprising updating the environmental conditions after determining the second 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:
receiving a user dialog act requesting a computer system to perform a task;
based on the user dialog act, determining a first machine action to perform the task;
accessing environmental conditions that are associated with a user dialog act;
determining a second machine action, other than performing the task, using the user dialog act and the environmental conditions, wherein the second machine action at least temporarily prevents completion of the first machine action; and
performing the second machine action to provide a response to a user.

18. The system of claim 17 , wherein accessing the environmental conditions comprises accessing 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 the dialog manager is further configured to determine, based on the environmental conditions, a type of response from: an audible response or a visual presentation of the response.

20. The system of claim 17 , wherein the dialog manager is further configured to update the environmental conditions after determining the second machine action using the environmental conditions.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Boies Daniel
• Heck Larry
• Anastasakos Tasos
• Sarikaya Ruhi

Classifications

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G06F40/30 Primary

  Semantic analysis · CPC title

• G10L17/22 Primary

  Interactive procedures; Man-machine interfaces · CPC title

• G06F17/2785

  Physics · mapped topic