基于知识图谱的人岗推荐系统构建

为解决传统人岗推荐系统存在的三个常见问题,即数据稀疏性、数据冷启动和数据利用率低,提出了基于知识图谱的人岗推荐系统构建方法。该方法通过改进传统推荐模型,将知识图谱作为辅助边信息融合到推荐系统中进行人岗推荐,有效解决了数据稀疏性和数据冷启动问题;引入知识图谱补全算法提高了数据利用率。提出的方法在人岗推荐上准确率可达92%,比现有人岗推荐方法准确率提高约1%。实验结果表明该方法是可行的,知识图谱的加入可以提升人岗推荐系统的推荐效果。

Construction of person-post matching recommended system based on knowledge graph

To solve the three common problems in the traditional person-post matching recommended system: data sparsiness, data cold start and low data utilization rate, this paper proposed knowledge graph-based person-post matching recommended system construction methods. By improving traditional recommendations, it integrated knowledge graph as auxiliary side information to the recommended system to carry out person-post matching recommended system, effectively solved data sparsiness and data cold start issues, and introduced knowledge graph completion algorithm to improve data utilization, the proposed method could reach 92% in the recommended accuracy rate, and the accuracy rate was increased by about 1% more than the existing person-post matching recommended methods. The experimental results show that the method is feasible, and the addition of the knowledge graph can improve the recommendation effect of the person-post matching recommended system.