ACTIVITY-CENTRIC DOMAIN SCOPING

• US 20070299949A1
• Filed: 06/27/2006
• Published: 12/27/2007
• Est. Priority Date: 06/27/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Macbeth, Steven W., Fernandez, Roland L., Meyers, Brian R., Tan, Desney S., Robertson, George G., Oliver, Nuria M., Murillo, Oscar E.
• Granted Patent: US 7,836,002 B2
• Time in Patent Office: Days
• US Class Current: 709/223
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding

Abstract

A system that can automatically narrow the search space or recognition scope within an activity-centric environment based upon a current activity or set of activities is provided. In addition, the activity and context data can also be used to rank the results of the recognition or search activity. In accordance with the domain scoping, natural language processing (NLP) as well as other types of conversion and recognition systems can dynamically adjust to the scope of the activity or group of activities thereby increasing the recognition systems accuracy and usefulness. In operation, a user context, activity context, environment context and/or device profile can be employed to effectuate the scoping. As well, the system can combine context with extrinsic data, including but not limited to, calendar, profile, historical activity data, etc. in order to define the parameters for an appropriate scoping.

Claims

1. A system that facilitates focusing a domain, comprising:

a receiving component that accesses activity information; and

a domain scoping component that scopes the domain into a plurality of sub-domains based at least in part upon the activity information.

2. The system of claim 1, the domain scoping component redistributes recognition probability as a function of the activity information.

3. The system of claim 1, the domain scoping component scopes the domain based at least in part upon context information.

4. The system of claim 3, the context information comprises environment context information.

5. The system of claim 3, the context information comprises activity context information.

6. The system of claim 3, the context information comprises user context information.

7. The system of claim 1, the receiving component monitors user action to identify and update the activity information.

8. The system of claim 1, the domain scoping component comprises an activity selection component that facilitates selection of a plurality of activities based upon the activity information, the domain scoping component scopes the domain based at least in part a subset of the plurality of activities.

9. The system of claim 1, the domain scoping component comprises an application selection component that facilitates selection of a plurality of applications, the domain scoping component scopes the domain based at least in part upon a subset of the plurality of applications.

10. The system of claim 9, the domain scoping component comprises a scaling component that limits the functionality of the subset of the plurality of applications based at least in part upon the activity information.

11. The system of claim 2, further comprising a search component that facilitates searching a subset of the plurality of sub-domains based at least in part upon a user input.

12. The system of claim 11, the user input is a speech input, the subset of the plurality of sub-domains includes a scoped lexicon and grammar component, the search component facilitates natural language processing (NLP) of the speech input based at least in part upon the scoped lexicon and grammar component.

13. The system of claim 1, further comprising a machine learning and reasoning component that facilitates automatic determination of a grammar and lexicon based at least in part upon the activity information and extrinsic information, the grammar and lexicon are maintained within the plurality of sub-domains.

14. A computer-implemented method of applying a recognition system in accordance with an activity, comprising:

identifying the activity;

determining a domain related to the activity;

scoping the domain into the plurality of sub-domains based upon the activity; and

interpreting a user input based at least in part upon a subset of the plurality of sub-domains.

15. The computer-implemented method of claim 14, further comprising:

gathering context information; and

employing the context information in scoping the domain into the plurality of sub-domains.

16. The computer-implemented method of claim 14, further comprising:

determining a lexicon based at least in part upon the activity; and

maintaining the lexicon in at least one of the subset of the plurality of sub-domains.

17. The computer-implemented method of claim 16, the domain comprises a plurality of applications.

18. A system that facilitates interpreting a user input, comprising:

means for identifying an activity;

means for scoping a domain into a plurality of sub-domains based at least in part upon the activity;

means for establishing a lexicon and a grammar based upon the activity;

means for maintaining the lexicon and the grammar associated to a subset of the plurality of sub-domains; and

means for interpreting a user input based upon the lexicon and the grammar.

19. The system of claim 18, the user input is a spoken phrase.

20. The system of claim 19, further comprising means for identifying a plurality of applications associated to the activity, the domain comprises the plurality of applications.