Proceedings of the 3rd International Conference on Big Data Economy and Digital Management, BDEDM 2024, January 12–14, 2024, Ningbo, China

Research Article

Design of Position Recommendation Model based on Knowledge Graph

Download50 downloads
  • @INPROCEEDINGS{10.4108/eai.12-1-2024.2347129,
        author={Binyong  Li and Jie  Fang and Mengqi  Xu},
        title={Design of Position Recommendation Model based on Knowledge Graph},
        proceedings={Proceedings of the 3rd International Conference on Big Data Economy and Digital Management, BDEDM 2024, January 12--14, 2024, Ningbo, China},
        publisher={EAI},
        proceedings_a={BDEDM},
        year={2024},
        month={6},
        keywords={knowledge graph; position recommendation; data sparse; data cold start},
        doi={10.4108/eai.12-1-2024.2347129}
    }
    
  • Binyong Li
    Jie Fang
    Mengqi Xu
    Year: 2024
    Design of Position Recommendation Model based on Knowledge Graph
    BDEDM
    EAI
    DOI: 10.4108/eai.12-1-2024.2347129
Binyong Li1, Jie Fang2,*, Mengqi Xu1
  • 1: Chengdu University of Information Technology
  • 2: Sichuan Institute of Computer Sciences
*Contact email: jolence@foxmail.com

Abstract

Under the background of the current epidemic, facing the severe employment pressure, the position recommendation system has become one of the important ways of employment. The traditional position recommendation model often has the problems of data sparsity and data cold start, so it can not recommend jobs well. In order to alleviate these disadvantages, a position recommendation model based on knowledge graph is studied and designed. Using the rich semantic relationship of knowledge graph, the recommendation efficiency of position recommendation system is improved, which can not only provide more efficient services for enterprise recruiters, but also alleviate the employment pressure of job seekers to a certain extent. Good model performance can help improve user stickiness, give better play to talent efficiency, and provide reasonable and feasible support for accelerating the rational and orderly flow of talents.