SYSTEM AND METHOD FOR FACILITATING SKILL GAP ANALYSIS AND REMEDIATION BASED ON TAG ANALYTICS

• US 20080313000A1
• Filed: 06/15/2007
• Published: 12/18/2008
• Est. Priority Date: 06/15/2007
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Zadrozny, Wlodek W., Keller, Neal M., Zhang, Lei, Sava, Michael, Degeratu, Melania
• Granted Patent: US 8,060,451 B2
• Time in Patent Office: Days
• US Class Current: 705/8
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 10/105 Human resources
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

This invention includes a workforce management system having a system bus, at least one database in communication with the system bus that includes data representative of workforce employees, and social networking data associated with the employees. A matching functional unit includes a text mining function for mining contextual information from the at least one database to generate context labels for an employee, a clustering function for generating concept labels for an employee, and a matching function that sorts and matches employees by the labels in accordance with a matching criteria. A user interface provides user input to the support operation of the workforce management system.

Claims

1. A computer-based method for operating upon a store of social networking data representative of members of an organization in order to provide mentoring services within the organization, the computer-based method comprising the steps of:

identifying concepts within a mentor member'"'"'s (“

mentor”

) social networking tagging data that are familiar to the mentor, with mentor concept labels;

identifying concepts within a mentee member'"'"'s (“

mentee”

) social networking tagging data that are familiar to mentee, with mentee concept labels;

matching mentors to mentees based on a comparison of said concept labels; and

delivering mentoring services based on the matching.

2. The method as set forth in claim 1, wherein said concepts are identified within the social networking data based on tag analytics.

3. The method as set forth in claim 1, further comprising steps of:

identifying contexts familiar to a mentor'"'"'s social networking tagging data that are familiar to the mentor, with mentor context labels; and

identifying contexts familiar to a mentee'"'"'s social networking tagging data that are familiar to the mentee, with mentee context labels.

4. The method as set forth in claim 3, wherein said step of matching further includes matching mentors and mentees based on a comparison of said context labels.

5. The method as set forth in claim 2, wherein said tag analytics apply probabilistic clustering techniques.

6. The method as set forth in claim 2, wherein said tag analytics apply text mining techniques to extract semantic context from said social networking tagging data.

7. The method as set forth in claim 1, wherein said social networking tagging data include audio files, video files and pictures.

8. The method as set forth in claim 1, wherein said step of matching is implemented to match said mentors and mentees in such a way that labeling said concepts and contexts using a distance metric in not required.

9. The method as set forth in claim 2, wherein said tag analytics implement text mining with the probabilistic clustering to disambiguate different senses of said social networking tagging data when assigning labels.

10. A computer-based method for managing resource data within an enterprise wide domain that is representative of a plurality of members comprising the enterprise, comprising the steps of:

identifying concepts in the resource data that are associated with a member;

identifying contexts in the resource data that are associated with a member;

matching members in accordance with the identified concepts and contexts using matching criteria.

11. The method as set forth in claim 10, wherein said concepts and their associated contexts pertain to a variety of dimensions, and wherein each dimension potentially includes two or more categories for the purpose of matching members for various purposes in an enterprise such as a corporation.

12. The method as set forth in claim 10 wherein said step of matching includes generating a virtual team of members based on said concepts and contexts.

13. The method as set forth in claim 10, wherein said contexts and concepts include mentor labels, and mentee labels, and wherein step of matching includes matching members identified as mentee with members identified as mentor.

14. The method as set forth in claim 13, wherein said mentor and mentee labels comprise informational list labels that identify a mentor'"'"'s mentee, and a mentee'"'"'s mentor, and wherein said steps of attaching include adding additional concept and context labels to a member'"'"'s existing labels to automatically modify the mentor/mentee'"'"'s informational list labels.

15. The method as set forth in claim 10, wherein said step of matching is carried out using a three-dimensional (3d) probabilistic generative model.

16. The method as set forth in claim 10, wherein step of matching implements text analytics and text mining processes.

17. The method as set forth in claim 10, wherein a set of N concept tags and M context tags forms an (N+M)-dimensional semantic space.

18. A workforce management system, comprising:

a system bus;

at least one database in communication with the system bus that includes workforce employee data, and social networking data associated with said employees;

a matching functional unit, the matching functional unit comprising;

a text mining function for mining contextual information from said at least one database to generate context labels for an employee,

a clustering function for generating concept labels for an employee based on said text mining, and

a matching function that sorts and matches employees by said context and concept labels in accordance with a matching criteria; and

a user interface for providing user input to the support operation of the workforce management system.

19. The workforce management system as set forth in claim 18, wherein the mentors and mentees comprise an organization under investigation to evaluate its human resource value in order to match the organization to a set of specific business requirements.

20. The workforce management system as set forth in claim 19, wherein the specific business requirements include qualifications for a corporate or asset purchase, and wherein said purchase is based on human resource characteristics.

21. The workforce management system as set forth in claim 18, wherein the clustering function implements probabilistic clustering techniques.