Task-based tagging and classification of enterprise resources
Embodiments of the present invention relate to systems and methods for task-based tagging and resource classification, which allow tags or metadata to emerge from execution of work-related tasks and activities. In certain embodiments, tags can be automatically extracted from activities performed, for example utilizing a textual description of tasks carried out by an employee. Accumulated tags can then be utilized to describe enterprise resources. Automatic tagging or metadata annotation can be integrated with everyday work utilizing one or more techniques. Candidate tags can be extracted from a task written description utilizing an algorithm that analyzes keywords. Candidate tags can be refined, for example by clustering utilizing a K-means approach. Candidate tags can be ranked based on an overall frequency adjusted against time, with the importance of a tag declining with time.
1. A computer-implemented method comprising:
receiving a written description that at least specifies actions comprising a job task;
performing text analysis and term extraction on the written description to produce extracted tags;
refining the extracted tags by clustering to produce refined tags;
describing an enterprise resource using the refined tags;
storing the refined tags associated with the enterprise resource in a data store of tagged enterprise resources; and
managing resources in the enterprise for a task to be performed in the enterprise, including specifying one or more refined tags stored in the data store of tagged enterprise resources to identify the resources.
2. The method of claim 1 wherein the written description refers to the enterprise resource.
3. The method of claim 2 further comprising storing the refined tags associated with the job task.
4. The method of claim 2 wherein the enterprise resource comprises a human being.
5. The method of claim 2 wherein the enterprise resource comprises a non-human resource.
6. The method of claim 1 further comprising preprocessing the written description with natural language processing methods prior to the extracting.
7. The method of claim 1 wherein the written description is linked to the job task through task patterning.
8. The method of claim 1 wherein the performing further includes one or more of:
analyzing resources of the enterprise using the refined tags; and
a recommendation of resources of the enterprise using the refined tags for a task to be performed in the enterprise.
9. A non-transitory computer readable storage medium embodying a computer program for performing a method, said method comprising:
receiving a written description that at least specifies actions comprising a job task;
performing text analysis and term extraction on the written description to produce extracted tags;
refining the extracted tags by clustering to produce refined tags;
describing an enterprise resource involved in the job task using the refined tags;
storing the refined tags associated with the enterprise resource in a data store of tagged enterprise resources; and
managing resources in the enterprise for a task to be performed in the enterprise, including specifying one or more refined tags stored in the data store of tagged enterprise resources to identify the resources.
10. The non-transitory computer readable storage medium of claim 9 wherein the written description refers to the enterprise resource.
11. The non-transitory computer readable storage medium of claim 10 wherein the method further comprises storing the refined tags associated with the job task.
12. The non-transitory computer readable storage medium of claim 10 wherein the enterprise resource comprises a human being.
13. The non-transitory computer readable storage medium of claim 10 wherein the enterprise resource comprises a non-human resource.
14. The non-transitory computer readable storage medium of claim 9 wherein the method further comprises preprocessing the written description with natural language processing methods prior to the extracting.
15. A computer system comprising:
one or more processors;
a software program, executable on said computer system, the software program configured to:
receive a written description that at least specifies actions comprising to a job task;
perform text analysis and term extraction on the written description to produce extracted tags;
refine the extracted tags by clustering to produce refined tags;
describe an enterprise resource involved in the job task using the refined tags;
store the refined tags associated with the enterprise resource in a data store of tagged enterprise resources; and
managing resources in the enterprise for a task to be performed in the enterprise, including specifying one or more refined tags stored in the data store of tagged enterprise resources to identify the resources.
16. The computer system of claim 15 wherein the written description refers to the enterprise resource.
17. The computer system of claim 16 wherein the method further comprises storing the refined tags associated with the job task.
18. The computer system of claim 16 wherein the enterprise resource comprises a human being or a non-human resource.
19. The computer system of claim 15 wherein the method further comprises preprocessing the written description with natural language processing methods prior to the extracting.
20. The computer system of claim 15 wherein the written description is linked to the job task through task patterning.