Conceptualization of job candidate information

• US 7,555,441 B2
• Filed: 10/10/2003
• Issued: 06/30/2009
• Est. Priority Date: 10/10/2003
• Status: Expired due to Fees

• Current Assignee: Cadient LLC
• Original Assignee: Kronos Talent Management Incorporated (Seahawk Acquisition Corp.)
• Inventors: Crow, Daniel Nicholas, Pitiyanuvath, Visnu Ted
• Primary Examiner(s): Jeanty; Romain
• Application Number:
  US10/684,272
• Publication Number:
  US 20050080656A1
• Time in Patent Office: 2,090 Days
• Field of Search: 705/8, 705/9
• US Class Current: 705/7.14
• CPC Class Codes: G06Q 10/0631 Resource planning, allocation, distributing or scheduling for enterprises or organisations
• CPC Class Codes: G06Q 10/063112 Skill-based matching of a person or a group to a task
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 10/1053 Employment or hiring

Abstract

A variety of technologies are applied to conceptualization of job candidate information. For example, concepts can be extracted from a job candidate'"'"'s resume via an ontology. Concepts can be arranged hierarchically within the ontology, and parent concepts can be extracted. Concepts relating to job skills, job title, management, and the like can be extracted. A set of concepts can be represented as a point in n-dimensional concept space. Thus, candidates and desired candidate criteria can be represented in the concept space. Those candidates closest to the desired candidate criteria in the concept space can be designated as matches for the desired candidate criteria.

Claims

1. A computer-implemented method for finding a plurality of job candidates suitable for a position, the job candidates resembling a single particular employee who previously performed well in the position, the method comprising:

via at least one ontology-based extractor and at least one ontology-independent extractor, conceptualizing job candidate data for a plurality of job candidates to generate conceptualized job candidate data, wherein the conceptualized job candidate data comprises, for each job candidate, a set of concept scores defining a respective point in an n-dimensional concept space, the concept scores including concept scores for at least one job title, and at least one job skill for the job candidate, whereby the job candidates are represented by job candidate points in the n-dimensional concept space;

generating desired job candidate criteria via extraction of concepts from job candidate data for the single particular employee who previously performed well in the position, wherein the job candidate data for the single particular employee who previously performed well in the position comprises a resume of the single particular employee who previously performed well in the position;

receiving the desired job candidate criteria, wherein the desired job candidate criteria comprises a desired job candidate criteria point in the n-dimensional concept space;

matching, by a computer, the desired job candidate criteria generated from the single particular employee who previously performed well in the position to the plurality of job candidates, wherein the matching comprises finding m job candidate points closest to the desired job candidate criteria point in the n-dimensional concept space; and

in a graphical user interface, indicating job candidates associated with the m job candidate points as job candidates matching the desired job candidate criteria, whereby job candidates suitable for the position resembling the single particular employee who previously performed well in the position are indicated.

2. The method of claim 1 wherein the job candidate data for the job candidate comprises assessment results of the job candidate.

3. The method of claim 1 wherein the extraction of concepts is performed based on detecting a synonym for a concept in the job candidate data for the single particular employee who previously performed well in the position.

4. The method of claim 1 wherein the concept scores are based at least in part on a level of experience for at least one associated concept.

5. The method of claim 1 wherein the concept scores are increased based at least in part on reputation of an organization at which an associated concept was applied according to the job candidate data.

6. The method of claim 1 wherein the job candidate data for the job candidate comprises a resume of the job candidate.

7. A computer-implemented method of finding a job candidate suitable to fill a position via finding a job candidate for the position, the job candidate resembling a single particular employee who previously performed well in the position, the method comprising:

via at least one ontology-based extractor and at least one ontology-independent extractor, conceptualizing job candidate data for a plurality of job candidates to generate conceptualized job candidate data, wherein the conceptualized job candidate data comprises, for each job candidate, a set of concept scores defining a respective point in an n-dimensional concept space, the concept scores including concept scores for at least one job title, and at least one job skill for the job candidate, whereby the job candidates are represented by job candidate points in the n-dimensional concept space;

generating desired job candidate characteristics via extraction of concepts from job candidate data for the single particular employee who previously performed well in the position, wherein the job candidate data comprises a resume of the single particular employee who previously performed well in the position;

matching the desired job candidate characteristics to the plurality of job candidates for the position via an n-dimensional concept space, wherein the generating and the matching steps are performed by a computer system; and

providing results indicating a plurality of job candidates for the position matching the desired job candidate characteristics extracted from the job candidate data for the single particular employee who previously performed well in the position.

8. The method of claim 7 wherein

the plurality of job candidates for the position are represented by a plurality of job candidate representations in the n-dimensional concept space;

the desired job candidate characteristics are represented by a point in the n-dimensional concept space; and

the matching is performed via a distance function to find the m job candidate representations closest to the point in the n-dimensional concept space.

9. At least one computer-readable storage medium having stored thereon computer executable instructions, which instructions when executed by a computer system cause to be performed a method of finding a plurality of job candidates suitable for a position, the job candidates resembling a single particular employee who previously performed well in the position, the method comprising:

via at least one ontology-based extractor and at least one ontology-independent extractor, conceptualizing job candidate data for a plurality of job candidates to generate conceptualized job candidate data, wherein the conceptualized job candidate data comprises, for each job candidate, a set of concept scores defining a respective point in an n-dimensional concept space, the concept scores including concept scores for at least one job title, and at least one job skill for the job candidate, whereby the job candidates are represented by job candidate points in the n-dimensional concept space;

generating desired job candidate criteria via extraction of concepts from job candidate data for the single particular employee who previously performed well in the position, wherein the job candidate data for the single particular employee who previously performed well in the position comprises a resume of the single particular employee who previously performed well in the position;

receiving the desired job candidate criteria, wherein the desired job candidate criteria comprises a desired job candidate criteria point in the n-dimensional concept space;

finding m job candidate points closest to the job candidate criteria point in the n-dimensional concept space; and

in a graphical user interface, indicating job candidates associated with the m job candidate points as job candidates matching the desired job candidate criteria, whereby job candidates suitable for the position resembling the single particular employee who previously performed well in the position are indicated.

10. The at least one computer-readable storage medium of claim 9, wherein the job candidate data for the job candidate comprises a resume of the job candidate.

11. The at least one computer-readable storage medium of claim 9, wherein the job candidate data for the job candidate comprises assessment results of the job candidate.

12. The at least one computer-readable storage medium of claim 9, wherein the extraction of concepts is performed based on detecting a synonym for a concept in the job candidate data for the single particular employee who previously performed well in the position.

13. The at least one computer-readable storage medium of claim 9, wherein the concept scores are based at least in part on a level of experience for at least one associated concept.

14. The at least one computer-readable storage medium of claim 9, wherein the concept scores are increased based at least in part on reputation of an organization at which an associated concept was applied according to the job candidate data.

15. A system for finding a plurality of job candidates suitable for a position, the job candidates resembling a single particular employee who previously performed well in the position, the system comprising:

memory for storing computer executable instructions; and

at least one processor operable in conjunction with the instructions stored in the memory for finding the plurality of job candidates suitable for the position resembling the single particular employee who previously performed well in the position by performing the following;

via at least one ontology-based extractor and at least one ontology-independent extractor, conceptualizing job candidate data for a plurality of job candidates to generate conceptualized job candidate data, wherein the conceptualized job candidate data comprises, for each job candidate, a set of concept scores defining a respective point in an n-dimensional concept space, the concept scores including concept scores for at least one job title, and at least one job skill for the job candidate, whereby the job candidates are represented by job candidate points in the n-dimensional concept space;

generating desired job candidate criteria via extraction of concepts from job candidate data for the single particular employee who previously performed well in the position, wherein the job candidate data for the single particular employee who previously performed well in the position comprises a resume of the single particular employee who previously performed well in the position;

receiving the desired job candidate criteria, wherein the desired job candidate criteria comprises a desired job candidate criteria point in the n-dimensional concept space;

finding m job candidate points closest to the job candidate criteria point in the n-dimensional concept space; and

in a graphical user interface, indicating job candidates associated with the m job candidate points as job candidates matching the desired job candidate criteria, whereby job candidates suitable for the position resembling the single particular employee who previously performed well in the position are indicated.

16. The system of claim 15 wherein the job candidate data for the job candidate comprises a resume of the job candidate.

17. The system of claim 15 wherein the job candidate data for the candidate comprises assessment results of the job candidate.

18. The system of claim 15 wherein the extraction of concepts is performed based on detecting a synonym for a concept in the job candidate data for the single particular employee who previously performed well in the position.

19. The system of claim 15 wherein the concept scores are based at least in part on a level of experience for at least one associated concept.

20. The system of claim 15 wherein the concept scores are increased based at least in part on reputation of an organization at which an associated concept was applied according to the job candidate data.

21. A computer-implemented method of finding job candidate suitable to fill a position via finding job candidates for the position who resemble a single particular employee having desired characteristics and who previously performed well in the position, the method comprising:

via at least one ontology-based extractor and at least one ontology-independent extractor, conceptualizing job candidate data for a plurality of job candidates to generate conceptualized job candidate data, wherein the conceptualized job candidate data comprises, for each job candidate, a set of concept scores defining a respective point in an n-dimensional concept space, the concept scores including concept scores for at least one job title, and at least one job skill for the lob candidate, whereby the lob candidates are represented by job candidate points in the n-dimensional concept space;

generating desired job candidate characteristics via extraction of concepts from job candidate data for the single particular employee having characteristics and who previously performed well in the position, wherein the job candidate data comprises a resume of the single particular employee having desired characteristics and who previously performed well in the position, wherein generating desired job candidate characteristics comprises submitting the job candidate data to plurality of cloners configured to select concepts, wherein the cloners comprise a role cloner, a skill cloner, a company cloner, an industry cloner, and an education cloner;

matching by a computer the desired job candidate characteristics extracted from the job candidate data for the single particular employee to the plurality of job candidates for the position via an n-dimensional concept space, wherein the generating and the matching are performed by a computer system; and

providing results indicating a plurality of job candidates for the position matching the desired job candidate characteristics extracted from the job candidate data for the single particular employee having desired characteristics and who previously performed well in the position.

22. One or more computer-readable storage media comprising computer-executable instructions when executed by a computer causing the computer to perform a computer-implemented method of finding a job candidate suitable to fill a position via finding a job candidate for the position who resembles a single particular employee having desired characteristics and who previously performed well in the position, the method comprising:

generating desired job candidate characteristics via extraction of concepts from job candidate data for the single particular employee having characteristics and who previously performed well in the position, wherein the job candidate data comprises a resume of the single particular employee having desired characteristics and who previously performed well in the position, wherein generating desired job candidate characteristics comprises submitting the job candidate data to plurality of cloners configured to select concepts, wherein the cloners comprise a role cloner, a skill cloner, a company cloner, an industry cloner, and an education cloner;

matching the desired job candidate characteristics extracted from the job candidate data for the single particular employee to a set of a plurality of job candidates for the position via an n-dimensional concept space, wherein the generating and the matching are performed by a computer system; and

providing results indicating a plurality of job candidates for the position matching the desired job candidate characteristics extracted from the job candidate data for the single particular employee having desired characteristics and who previously performed well in the position.