基于知识图谱和大语言模型增强的推荐系统研究  

Research on recommendation system based on knowledge graph and large language model enhancement

作　　者：王敏[1] 高晓影 汪诗蕊 向阳[1] WANG Min;GAO Xiaoying;WANG Shirui;XIANG Yang(College of Computer Science and Technology,Tongji University,Shanghai 200000,China)

机构地区：[1]同济大学计算机科学与技术学院,上海200000

出　　处：《大数据》2025年第2期29-46,共18页Big Data Research

基　　金：国家自然科学基金项目(No.72071145)。

摘　　要：推荐系统的核心是用户和商品,用户与商品之间的关系可抽象为图结构,因此图神经网络在推荐领域具有广泛应用。但基于图的推荐交互数据较稀疏,严重依赖于编号信息和图结构信息,忽略了与用户和商品相关的有价值的文本信息,表征信息较少。同时,隐式反馈数据中存在一定的噪声和偏差,为推荐系统理解用户行为与偏好带来挑战。为了解决这些问题,提出了一种基于知识图谱和大语言模型增强的推荐系统。知识图谱可以提供商品的结构化信息,使模型能学习商品之间的潜在关系,理解用户行为和偏好。大语言模型具备非常出色的生成与理解能力,可以通过提示工程技术,深入分析并挖掘文本信息,推理获取商品和用户画像特征。所提模型分别将这些辅助信息增强的特征编码,并对表征进行增强以与图神经网络获得的ID表征对齐,完成下游推荐任务。实验结果证明,本文提出的系统可以全面地表征用户和商品,具有较好的性能。ed as graph structure,so graph neural network has been widely used in recommendation field.However,graphbased recommendation interaction data is sparse,relying heavily on numbering information and graph structure information,ignoring valuable text information related to user and commodity,and less representational information.At the same time,there are some noise and bias in the implicit feedback data,which bring challenges for recommendation system to understand user behavior and preferences.To solve these problems,this paper proposes a recommendation system based on knowledge graph and large language model enhancement.Knowledge graphs can provide structured information about commodities,enabling models to learn potential relationships between commodities and understand user behavior and preferences.Large language models have excellent ability to generate and understand,and can use prompt engineering techniques to deeply analyze and mine text information,and deduce the features of commoditiy and user portraits.The features enhanced by these auxiliary information are encoded,and the representations are enhanced to align with the ID representations obtained by the graph neural network to complete the downstream recommendation task.The experimental results show that the proposed system can help to comprehensively characterize users and commodities,and has good performance.

关 键 词：大语言模型 知识图谱 推荐系统 表征学习 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]