Design and Implementation of Employee Recommendation System Based on Neural Graph Collaborative Filtering

Abstract

Small, medium and micro enterprises are playing an increasingly important role in the growth of the national economy, but nowadays, they have significant difficulties in recruiting and retaining people. In this context, this paper studies the collaborative filtering algorithm based on Graph Neural Networks, according to the traditional recommendation algorithms and deep learning recommendation algorithms. First, this paper analyzes the traditional recommendation algorithm represented by item-based collaborative filtering and the deep learning algorithm represented by Graph Neural Network in the current recommendation system. It analyzes and compares their advantages and disadvantages. Secondly, combined with the characteristics of candidates, an improved algorithm is proposed. Finally, using the data set crawled from the public recruitment website, a recommendation demonstration system based on the collaborative filtering algorithm of Graph Neural Network is designed and implemented. The proposed algorithm has a particular reference value for the research of employee recommendation and recruitment systems, and recommendation systems in other fields can use the idea of combining traditional recommendation algorithms and deep learning recommendation algorithms.