Browse Prior Art Database

A system and method for generating new context based job descriptions

IP.com Disclosure Number: IPCOM000236394D
Publication Date: 2014-Apr-24
Document File: 2 page(s) / 63K

Publishing Venue

The IP.com Prior Art Database

Abstract

Identity resolution of job description involving cross organizational data would go a long way in addressing several high valued busi-ness problems. Job data normalization/sanitation, automated cre-ation of better job descriptions with context preference, description reuse and validation across different sources, semantic classifica-tion of jobs, routing of candidates to suitable jobs across different organization etc are some of the business centric functionalities that can be efficiently built by resolving job description identities. Job descriptions are highly unstructured with free flow textual data con-sisting of lines describing important attributes of job requirements, like education, skills, experience, role, responsibility etc. Much of the problem is due to the highly unstructured nature of job descrip-tions. Further, the attributes that are representative of the informa-tion in a job description is not readily available from the descrip-tion. Thus, the process of resolution involves deep data cleansing, classification, attributes identification, and building highly scalable similarity detection algorithms. In this work, we propose that uses values of attributes in the underlying job description data and similarity observed in the attributes to resolve identities across organizations. It proposes classification followed by similarity es-tablishment processes that eventually provides high quality of res-olution. Through extensive experiments performed on corpus of job descriptions from several real world recruitment systems, we demonstrate that our work can resolve the identities with high preci-sion and recall.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 100% of the total text.

Page 01 of 2

A system and method for generating new context based job descriptions


Job descriptions are today created manually through a template provided to the clients.

- Do not result in the best description of the job due to lack of well-structured constructs, job requirements and expression of intent for the job.

- Several 1000's of entries are created every week and thus a new description is defined for every such entry. Cumbersome to handle and time consuming.


• Leverage existing repo of job descriptions and requirements to provide the best possible description for a job role in the given context.

Input: Job Description for Research - Textual Job Description: We need a software professional who has at least 1 year of experience in Java, Cognos and SPSS. He should be capable of working on innovative ideas and prototype them to demonstrate its value.

- Response: 10 Master applicants and 6 Bachelor applicants

Input: Job Description for Software Development - Textual Job Description: We need a software professional who has at least 4 years of experience in Java and Web technologies. He should have worked on client related projects and delivery schedules. He should be able to lead the team.

- Response: 4 Master applicants and 15 Bachelor applicants

Output: Job Description for Software Engineer in Analytics Research - Skills: Java, SPSS, Cognos - Education: Master - Experience: At least 1 year
- Role: Innovative idea, prototyping, delivery schedule

1


Page 0...