针对基于知识图谱的推荐系统中存在的高阶建模困难与用户特征建模不足的问题，提出基于多跳机制的扩散图谱推荐模型（a diffusion map recommendation model based on multi-hop mechanism,MultiHop-GDN）。该模型通过端到端方法挖掘知识图谱高阶语义信息，涵盖知识图谱构建、特征提取网络构建与多跳扩散模型构建三部分内容。利用用户特征和项目特征构建知识图谱；深入分析用户兴趣、偏好和历史行为等信息，构建用户画像和兴趣模型；提出特征提取网络捕获深层次语义信息，通过本文模型的计算得到预测值。在两个公开数据集的对比实验表明，MultiHop-GDN能够同时实现用户和项目的高阶建模，与其他代表论文的模型相比有良好的推荐效果。
To address the challenges of high-order modeling and insufficient user feature modeling in knowledge graph-based recommendation systems, a diffusion map recommendation model based on multi-hop mechanism (MultiHop-GDN) is proposed. This model mines high-order semantic information from the knowledge graph through an end-to-end method, covering three parts: knowledge graph construction, feature extraction network design and multi-hop diffusion model development. The knowledge graph is constructed using user and project attributes, enabling in-depth analysis of information such as user interests, preferences, and historical behaviors to build user portraits and interest models. A feature extraction network is introduced to capture deep semantic information and obtain prediction values through the calculation of this model. Comparative experiments on two public datasets show that MultiHop-GDN effectively achieves high-level modeling of both users and projects, outperforming other representative models in recommendation effects.
[1] 朱磊, 胡沁涵, 赵雷, 等. 基于评分偏好和项目属性的协同过滤算法[J]. 计算机科学, 2020, 47(4): 67-73. Zhu L, Hu Q H, Zhao L, et al. Collaborative filtering algorithm based on rating preference and item attributes [J]. Computer Science, 2020, 47(4): 67-73. (in Chinese)
[2] 李翔锟, 贾彩燕. 融合重叠社区正则化及隐式反馈的协同过滤方法[J]. 计算机应用, 2021, 41(1): 53-59. Li X K, Jia C Y. Collaborative filtering method fusing overlapping community regularization and implicit feedback [J]. Journal of Computer Applications, 2021, 41(1): 53-59. (in Chinese)
[3] 何宗元. 基于知识图谱的个性化兴趣点推荐方法研究[D]. 广州: 广州大学, 2022.
[4] 王越群. 基于知识图谱的深度推荐系统研究[D]. 长春: 吉林大学, 2023.
[5] 张彬, 郝利新, 张国防. 融合元图邻域的知识图谱推荐模型[J]. 计算机应用研究, 2024, 41(8): 2412-2418. Zhang B, Hao L X, Zhang G F. Knowledge graph recommendation model with integrated meta-graph neighborhoods [J]. Application Research of Computers, 2024, 41(8): 2412-2418. (in Chinese)
[6] 季德强, 王海荣, 李明亮, 等. 融合用户-项目的邻居实体表示推荐方法[J]. 中文信息学报, 2022, 36(9): 112-119. Ji D Q, Wang H R, Li M L, et al. Incorporating user-item neighbor entity for recommendation [J]. Journal of Chinese Information Processing, 2022, 36(9): 112-119. (in Chinese)
[7] 苏哲晗, 徐涛, 戴玉刚, 等. 基于属性权重更新网络的跨语言实体对齐方法[J]. 西北工业大学学报, 2024, 42(1): 164-171. Su Z H, Xu T, Dai Y G, et al. Cross-language entity alignment method based on attribute weight update network [J]. Journal of Northwestern Polytechnical University, 2024, 42(1): 164- 171. (in Chinese)
[8] 王之腾, 刘畅, 纪存孝, 等. 水波中心扩散智能优化算法[J]. 陆军工程大学学报, 2023, 2(4): 1-8. Wang Z T, Liu C, Ji C X, et al. Intelligent optimization algorithm for the diffusion of water wave centers [J]. Journal of the Army University of Engineering, 2023, 2(4): 1-8. (in Chinese)
[9] 帅亚琦, 李燕, 陈月月, 等. 基于BERT-BILSTM-CRF的慢性支气管炎中医医案实体识别[J]. 现代信息科技, 2023, 7(5): 145-148, 152. Shuai Y Q, Li Y, Chen Y Y, et al. Entity recognition of traditional Chinese medical cases of chronic bronchitis based on BERT-BILSTM-CRF [J]. Modern Information Technology, 2023, 7(5): 145-148, 152. (in Chinese)
[10] 张鹏, 杜洪霞, 代劲. 基于超图神经网络以多角度概念特征融合的概念先决学习[J]. 中文信息学报, 2023, 37(12): 155-166. Zhang P, Du H X, Dai J. Concept prerequisite learning with multi-view concept feature fusion based on hypergraph neural network [J]. Journal of Chinese Information Processing, 2023, 37(12): 155-166. (in Chinese)
[11] 孙鹏钊, 毕可骏, 唐潮, 等. 基于邻居采样和图注意力机制的产业链风险评估模型[J]. 计算机科学, 2024, 51(10): 218-226. Sun P Z, Bi K J, Tang C, et al. Risk assessment model for industrial chain based on neighbor sampling and graph attention mechanism [J]. Computer Science, 2024, 51(10): 218-226. (in Chinese)
[12] 党伟超, 吴非凡, 高改梅, 等. 基于局部-邻域图信息与注意力机制的会话推荐[J]. 计算机工程与设计, 2024, 45(3): 925-931. Dang W C, Wu F F, Gao G M, et al. Session recommendation based on local-neighborhood graph information and attention mechanism [J]. Computer Engineering and Design, 2024, 45(3): 925-931. (in Chinese)
[13] 李泽霖, 吕兆峰, 陈富强, 等. 基于多跳信息融合的实体对齐模型[J]. 计算机工程, 2024, 50(9): 142-152. Li Z L, Lyu Z F, Chen F Q, et al. Entity alignment model based on multi-hop information fusion [J]. Computer Engineering, 2024, 50(9): 142-152. (in Chinese)
