基于知识图谱的行为路径协同过滤推荐算法  

Collaborative Filtering Recommendation Algorithm of Behavior Route Based on Knowledge Graph

作　　者：陈源毅 冯文龙[2,3] 黄梦醒[2,3] 冯思玲[2,3] CHEN Yuan-yi;FENG Wen-long;HUANG Meng-xing;FENG Si-ling(College of Computer Science and Cyberspace Security,Hainan University,Haikou 570228,China;College of Information Science&Technology,Hainan University,Haikou 570228,China;State Key Laboratory of Marine Resource Utilization in South China Sea,Hainan University,Haikou 570228,China)

机构地区：[1]海南大学计算机与网络空间安全学院,海口570228 [2]海南大学信息与通信工程学院,海口570228 [3]海南大学南海海洋资源利用国家重点实验室,海口570228

出　　处：《计算机科学》2021年第11期176-183,共8页Computer Science

基　　金：国家重点研发计划项目(2018YFB1404400)。

摘　　要：针对个性化推荐,常用的推荐算法有内容推荐、物品协同过滤(Item CF)和用户协同过滤(User CF),但是这些算法以及它们的改进算法大多偏向于关注用户的显性反馈(标签、评分等)或评分数据,缺少对多维度用户行为和行为顺序的利用,导致推荐准确率不够高及冷启动等问题。为了提高推荐精度,文中提出了一种基于知识图谱的行为路径协同过滤推荐算法(BR-CF)。首先根据用户行为数据,考虑行为顺序创建行为图谱(behavior graph)和行为路径(behavior route),然后采用向量化技术(Keras Tokenizer)将文本类型的路径向量化,最后计算多维度行为路径向量之间的相似度,对各维度分别进行路径协同过滤推荐。在此基础上,文中提出了两种BR-CF与Item CF相结合的改进算法。实验结果表明,在阿里天池数据集UserBehavior上,BR-CF算法能够有效地在多个维度中进行推荐,实现数据的充分利用和推荐的多样性,并且此改进算法很好地提升了Item CF的推荐性能。For personalized recommendation,common recommendation algorithms include content recommendation,Item CF and User CF.However,most of these algorithms and their improved algorithms tend to focus on users’explicit feedback(tags,ratings,etc.)or rating data,and lack the use of multi-dimensional user behavior and behavior order,resulting in low recommendation accuracy and cold start problems.In order to improve the recommendation accuracy,a collaborative filtering recommendation algorithm based on knowledge graph(BR-CF)is proposed.Firstly,according to the user behavior data,behavior graph and behavior route are created considering the behavior order,and then the vectorization technology(Keras Tokenizer)is used.Finally,the similarity between multi-dimensional behavior route vectors is calculated,and the route collaborative filtering recommendation is carried out for each dimension.On this basis,two improved algorithms combining BR-CF and Item CF are proposed.The experimental results show that the BR-CF algorithm can recommend effectively in multiple dimensions on the user behavior dataset of Ali Tianchi,realize the full utilization of data and the diversity of recommendation,and the improved algorithm can improve the recommendation performance of Item CF.

关 键 词：推荐算法 行为顺序 行为图谱 行为路径 路径协同 多维度推荐 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]