Activity-centric domain scoping

• US 7,836,002 B2
• Filed: 06/27/2006
• Issued: 11/16/2010
• Est. Priority Date: 06/27/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Oliver, Nuria M., Murillo, Oscar E., Fernandez, Roland L., Robertson, George G., Macbeth, Steven W., Tan, Desney S., Meyers, Brian R.
• Primary Examiner(s): Holmes; Michael B.
• Assistant Examiner(s): Fernandez Rivas; Omar F
• Application Number:
  US11/426,796
• Publication Number:
  US 20070299949A1
• Time in Patent Office: 1,603 Days
• Field of Search: 706 14- 18, 706/20, 706/21, 704 1- 10, 704/200, 704/202, 704/259, 715/700, 715/707, 715/708, 715727-728
• US Class Current: 706/46
• 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. Computer storage media having a system embodied thereon including computer-executable instructions that, when executed, perform a method for facilitating focusing of a domain, the system comprising:

a receiving component that accesses information related to an activity a user is attempting to accomplish, wherein the accessed information comprises information related to at least one of a lithe user, the user'"'"'s environment, or the activity; and

a domain scoping component that automatically scopes the domain into a plurality of sub-domains to facilitate accomplishment of the activity by reducing the domain resources available and narrowing a search space or recognition scope,

wherein the domain comprises resources including one or more applications and at least one of one or more files, web links, functionalities, services, or views,

wherein each sub-domain includes a subset of the resources in the domain, and

wherein the domain scoping component comprises;

an activity selection component that infers the activity the user is attempting to accomplish from the accessed information,

an application selection component that identifies domain resources, including one or more applications, to limit access to or functionality of for each sub-domain based on the inferred activity, and

a scaling component that limits access to or functionality of applications and other resources identified by the application selection component for each sub-domain to provide a focused workspace, including narrowing a grammar and lexicon available for recognition in natural language and speech processing to provide more efficient processing by limiting the number of words and grammatical constructs against which a language or speech input is compared during processing.

2. The media of claim 1, wherein the domain scoping component enhances recognition-based searching associated with the activity the user is attempting to accomplish.

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

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

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

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

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

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

9. The media of claim 8, wherein the user input is a speech input, and wherein the search component facilitates natural language processing (NLP) of the speech input based at least in part upon the grammar and lexicon available for recognition in natural language and speech processing in each sub-domain.

10. The media of claim 1, wherein the system further comprises a machine learning and reasoning component that facilitates automatic determination of the grammar and lexicon available for recognition in natural language and speech processing in each sub-domain, and wherein the grammar and lexicon available in each sub-domain are maintained within the sub-domain.

11. One or more computer storage media storing computer-executable instructions for performing a method of applying a recognition system in accordance with a non-search activity a user is attempting to accomplish by using a computing device, the method comprising:

accessing information related to a non-search activity a user is attempting to accomplish, wherein the accessed information comprises information related to at least one of the user, the user'"'"'s environment, or the activity;

inferring the non-search activity the user is attempting to accomplish from the accessed information;

determining a domain comprising resources including one or more applications and at least one of one or more files, web links, functionalities, services, or views;

scoping the domain into a plurality of sub-domains to facilitate accomplishment of the activity by;

identifying domain resources, including one or more applications, to limit access to or functionality of for each sub-domain based on the activity, and

limiting the access to or functionality of applications and other identified resources for each sub-domain to provide a focused workspace;

for each sub-domain;

narrowing a grammar and lexicon available for recognition in natural language and speech processing to provide more efficient processing by limiting the number of words and grammatical constructs against which a language or speech input is compared during processing, and

maintaining the narrowed grammar and lexicon in the sub-domain; and

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

12. The computer storage media of claim 11, wherein the method further comprises:

gathering context information; and

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

13. The computer storage media of claim 11, wherein the domain comprises a plurality of applications.

14. One or more computer storage media storing computer-executable instructions for performing a method of interpreting a user input, the method comprising:

accessing information related to an activity a user is attempting to accomplish, wherein the accessed information comprises information related to at least one of a user, the user'"'"'s environment, or the activity;

inferring the activity the user is attempting to accomplish from the accessed information;

determining a domain comprising resources including one or more applications and at least one of one or more files, web links, functionalities, services, or views;

automatically scoping a domain into a plurality of sub-domains to facilitate accomplishment of the activity by;

identifying domain resources, including one or more applications, to limit access to or functionality of for each sub-domain based on the activity, and

limiting the access to or functionality of applications and other identified resources for each sub-domain to provide a focused workspace;

for each sub-domain;

narrowing a grammar and lexicon available for recognition in natural language and speech processing to provide more efficient processing by limiting the number of words and grammatical constructs against which a language or speech input is compared during processing, and

maintaining the narrowed grammar and lexicon in the sub-domain; and

interpreting a user input based at least in part upon the grammar and lexicon associated with the one or more of the plurality of sub-domains.

15. The computer storage media of claim 14, wherein the user input is a spoken phrase.

16. The computer storage media of claim 15, wherein the identified domain comprises a plurality of applications.