Method and apparatus for performing plan-based dialog

• US 20040249638A1
• Filed: 04/16/2004
• Published: 12/09/2004
• Est. Priority Date: 09/14/2000
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Wang, Kuansan
• Granted Patent: US 7,398,211 B2
• Time in Patent Office: Days
• US Class Current: 704/246
• CPC Class Codes: G06F 40/143 Markup, e.g. Standard Generalized Markup Language [SGML] or Document Type Definition [DTD]
• CPC Class Codes: G06F 40/154 Tree transformation for tree-structured or markup documents, e.g. XSLT, XSL-FO or stylesheets
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G06F 9/453 Help systems
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

The present invention provides a dialog system in which the subsystems are integrated under a single technology model. In particular, each of the sub-systems uses stochastic modeling to identify a probability for its respective output. The combined probabilities identify a most probable action to be taken by the dialog system given the latest input from the user and the past dialog states. An additional aspect of the present invention is an embodiment in which the sub-systems communicate with one another through XML pages, thus allowing the sub-systems to be distributed across a distributed network.

Claims

1. A system for providing a computer-based dialog interface to a user, the system comprising:

a dialog state engine that receives input from the user and that uses at least one model to generate at least one score for a current dialog state based on the user'"'"'s input and a previous dialog state; and

a rendering engine that uses a model to identify a score for at least one action based on a current dialog state.

2. The system of claim 1 wherein the dialog state engine comprises:

a recognition engine that uses a model to determine a score for at least one surface semantic based on the user input; and

a discourse engine that uses a model to determine a score for at least one current dialog state based on the surface semantic from the recognition engine and a previous dialog state.

3. The system of claim 2 wherein the current dialog state is represented by a discourse semantic structure.

4. The system of claim 3 wherein the discourse engine expands a discourse semantic structure based on the surface semantic before using a model to determine a score for the discourse semantic structure.

5. The system of claim 4 wherein the dialog state engine further comprises a memory that is accessed by the discourse engine to resolve implicit references found in the user input.

6. The system of claim 5 wherein the memory comprises:

a long-term memory containing values determined from previous user input;

an explicit memory containing values taken from explicit references made in a current user input; and

an implicit memory containing values that have been resolved from implicit references made in a current user input.

7. The system of claim 4 wherein the discourse semantic structure comprises semantic tokens that provide a general representation of specific entities and wherein the dialog state engine further comprises a database containing the specific entities that are represented by the semantic tokens.

8. The system of claim 1 wherein the rendering engine also receives an indication of the output interfaces that are available and wherein the rendering engine uses the model to identify a best action to take given the current dialog state, the score of the current dialog state and the available output interface.

9. The system of claim 1 wherein the dialog state engine describes the current dialog state to the rendering engine by using a markup language.

10. A method of providing a dialog interface, the method comprising:

receiving input generated by a user;

determining a current dialog state based on the received input and a past dialog state;

formatting the current dialog state into a markup language page;

converting the markup language page into an output markup language page based on the current dialog state and an available output user interface; and

passing the output markup language page to the available output user interface.

11. The method of claim 10 wherein formatting the current dialog state comprises formatting the current dialog state in an extensible markup language.

12. The method of claim 11 wherein formatting the current dialog state comprises formatting a discourse semantic structure into a markup language page.

13. The method of claim 12 wherein determining a current dialog state comprises:

identifying a surface semantic in the input;

formatting the surface semantic into a surface semantic markup language page; and

identifying a discourse semantic structure from the surface semantic markup language page.

14. A system for providing a computer-based dialog interface to a user, the system comprising:

a dialog state engine that receives input from the user and that generates a markup language page representing a current dialog state; and

a rendering engine that converts the markup language page representing the current dialog state into a markup language page representing an action.

15. The system of claim 14 wherein the dialog state engine comprises:

a recognition engine that receives user input and generates a markup language page representing the surface semantics of the user input; and

a discourse engine that converts the markup language page representing the surface semantics into the markup language page representing the dialog state.