福建电脑2024，Vol.40Issue(4)：5-8,4.DOI:10.16707/j.cnki.fjpc.2024.04.002
融合异构图注意力网络的知识推荐
Knowledge Recommendation Through Fusion of Heterogeneous Graph Attention Networks
摘要
Abstract
To address the issue of neglecting user knowledge level differences in direct recommendation services on online course platforms,this paper proposes a knowledge recommendation method.By applying heterogeneous information networks and attention mechanisms,the knowledge recommendation problem is viewed as a reinforcement learning task,simulating the interaction between users and knowledge concepts,and utilizing heterogeneous information networks to learn the semantic representation of users,guiding the propagation of user preferences through meta paths.The experimental results show that compared to other methods,this method performs better in terms of performance.关键词
元路径/异构信息网络/注意力机制/知识推荐Key words
Meta-Path/Heterogeneous Information Networks/Attention Mechanism/Knowledge Recommendation分类
信息技术与安全科学引用本文复制引用
胡博发,马丽,仲尚..融合异构图注意力网络的知识推荐[J].福建电脑,2024,40(4):5-8,4.基金项目
本文得到河北省教育科学规划课题一般资助课题(No.2303121)、河北省高等学校科学技术研究重点项目(No.ZD2018043)、河北地质大学博士基金(No.BQ2017045)资助. （No.2303121）
