Development and Demonstration of AI-Based Integrated Job Search and Recruitment Support Solution

Overview

In the rapidly changing labor market, job mismatches between employers and job seekers (including fraudulent job postings) generate social costs, with the burden of time and expense increasing annually. There is a growing need to provide efficient services, such as offering reliable job information to job seekers and supporting employers in creating job postings through AI adoption. Accordingly, an AI-based integrated job matching support solution has been developed and demonstrated, and the project is being advanced with support from an AI specialized consortium starting in 2024.

Project description

The Ministry of Employment and Labor utilizes its data—including job postings and job seeker resumes—to build AI training datasets. These datasets are employed to develop and validate an initial model capable of verifying job postings, assisting in writing postings, identifying successful hiring patterns, and recommending talent.

Key services include providing monitoring teams managing job postings with the capability to identify and block problematic postings, such as fraudulent job offers. For hiring companies, services will support automated job posting creation, hiring probability prediction, and talent recommendation.

Key technological features

• Development of AI Prediction Models Using the Employment24 Recruitment Dataset
• Building an RAG-based AI job matching support solution in an on-premises environment using LLM models, job ontologies, knowledge dictionaries, and other data

Expected outcomes

The introduction of the AI solution is expected to reduce social costs and save time and money by shortening the time required for the job posting monitoring team to identify false postings and for employers to recruit talent. Furthermore, applying it to systems like Employment24 in the future will increase the utilization of government recruitment platforms and contribute to resolving job mismatches.

Launch year: 2024

Attribution

Case study courtesy of the National Information Society Agency, Republic of Korea, Apolitical's Content Partner. Sourced from Use Cases of Public AI Service, Vol.1,  https://eng.nia.or.kr/site/nia_eng/ex/bbs/View.do?cbIdx=31975&bcIdx=28997&parentSeq=29016