计算机工程与应用 ›› 2023, Vol. 59 ›› Issue (10): 142-150.DOI: 10.3778/j.issn.1002-8331.2201-0129

• 模式识别与人工智能 • 上一篇    下一篇

数字文化资源知识图谱多目标跨域推荐方法

童小凯,朱欣娟,王西汉,胡竹林   

  1. 1.西安工程大学 计算机科学学院,西安 710048
    2.陕西省图书馆 数字资源部,西安 710061
  • 出版日期:2023-05-15 发布日期:2023-05-15

Knowledge Graph Multi-Target Cross-Domain Recommendation on Digital Cultural Resources

TONG Xiaokai, ZHU Xinjuan, WANG Xihan, HU Zhulin   

  1. 1.School of Computer Science, Xi’an Polytechnic University, Xi’an 710048, China
    2.Department of Digital Resources, Shaanxi Library, Xi’an 710061, China
  • Online:2023-05-15 Published:2023-05-15

摘要: 数字文化资源具有资源丰富、种类繁多等特点。针对数字文化资源的推荐,考虑到其资源类型的异构多样性,又可以划分为多个不同的子类别域。然而目前大多数的推荐方法仅针对单个物品类别域,无法捕获用户偏好在多个域之间的传播,并有效地利用其他域所提供的信息。基于此,一种基于知识图谱的多目标跨域推荐模型(knowledge graph multi-target cross-domain recommendation model,KGMT)被提出。首先通过知识图谱构建不同域之间的联系,并生成其中有关用户和物品的全局域嵌入。然后采用一种基于自注意力机制的融合注意力模块来联合目标域和全局域的嵌入表征,有效地利用全局域信息来提高每个目标域的推荐效果。最后分别在豆瓣和国家文化云平台的真实数据集上进行了多组实验,实验结果证明KGMT的表现优于基线模型,同时提高了多个目标域的推荐指标。

关键词: 推荐系统, 跨域推荐, 知识图谱, 数据异构, 数字文化资源

Abstract: Digital cultural resources are rich and diverse. Considering the diversity and heterogeneity of resource types, the recommendation of digital cultural resources can be divided into several different subdomains. However, most of the current recommendation methods only aim at single domain, which are unable to capture the propagation of user preferences among multiple domains and make effective use of the information provided by other domains. Therefore, a know-
ledge graph multi-target cross-domain recommendation model(KGMT) is proposed. Firstly, the relationship between different domains is constructed through knowledge graph, and the global domain embedding of users and items is generated. Then, a fusion attention module based on self-attention mechanism is adopted to combine the embedding representation of target domain and global domain. The whole information is effectively used to improve each target domain. Finally, several experiments are carried out on the real-world datasets of Douban and national culture cloud platform. The experimental results show that the performance of KGMT is better than the baselines, and the evaluating indicators of target domains are improved.

Key words: recommendation system, cross-domain recommendation, knowledge graph, data heterogeneity, digital cultural resources