摘要【目的】为解决现有工作推荐存在的难以大规模应用冷启动缺乏新颖性和解释性等问题提出基于人才知识图谱推理的强化学习可解释推荐方法。【方法】基于真实的简历数据集构建人才社会经历知识图谱依据强化学习的理论在知识图谱上训练一个策略智能体将一次推理过程分解为选择方向、选择节点两个子过程使其能够在知识图谱上寻找潜在的优质推荐目标。结果】相比于LR、BPRJRL-int JRL-rep及PGPR模型基于人才知

Abstract: [Purpose] To solve the problems of difficult large-scale application, cold start, lack of novelty and interpretability in existing job recommendation, a reinforcement learning interpretable recommendation method based on talent knowledge graph reasoning is proposed. [Methods] Based on a real resume dataset, a talent social experience knowledge graph is constructed, and a policy agent is trained on the knowledge graph based on the theory of reinforcement learning. The recommendation process is decomposed into two sub-processes of direction selection and node selection, enabling the agent to search for potential high-quality recommendation targets on the knowledge graph. [Results] Compared with LR, BPR.JRL-int, JRL-rep, and PGPR models, the reinforcement learning interpretable recommendation model based on talent knowledge graph reasoning performs best in MRR@20 (81.7%), Hit@1 (74.8%), Hit@5 (92.2%), and Hit@10 (97.0%). [Limitations] The experimental dataset size and task types are relatively limited. [Conclusion] The model effectively combines the historical work experience of talents and recommends based on similar work experience, and combines the attribute associations of job positions in the knowledge graph. While providing recommendation results, it also provides reasoning paths, which can effectively deal with cold start, lack of novelty and interpretability issues. [Keywords] job recommendation, knowledge graph reasoning, reinforcement learning interpretable recommendation