[1]冯 祥,杨庆红*.结合知识图谱进行信息强化的协同过滤算法[J].江西师范大学学报(自然科学版),2022,(04):386-393.[doi:10.16357/j.cnki.issn1000-5862.2022.04.09]
　FENG Xiang,YANG Qinghong*.The Collaborative Filtering Algorithm for Information Enhancement Combined with Knowledge Graph[J].Journal of Jiangxi Normal University:Natural Science Edition,2022,(04):386-393.[doi:10.16357/j.cnki.issn1000-5862.2022.04.09]
点击复制

结合知识图谱进行信息强化的协同过滤算法()
分享到：

《江西师范大学学报》（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2022年04期
页码:
386-393
栏目:
信息科学与技术
出版日期:
2022-07-25

文章信息/Info

Title:
The Collaborative Filtering Algorithm for Information Enhancement Combined with Knowledge Graph
文章编号:
1000-5862(2022)04-0386-08
作者:
冯 祥; 杨庆红*
江西师范大学计算机信息工程学院,江西 南昌 330022
Author(s):
FENG Xiang; YANG Qinghong*
School of Computer Information Engineering,Jiangxi Normal University,Nanchang Jiangxi 330022,China
关键词:
协同过滤;  知识图谱;  信息强化;  相似度融合
Keywords:
collaborative filtering;  knowledge graph;  information enhancement;  similarity fusion
分类号:
TP 311
DOI:
10.16357/j.cnki.issn1000-5862.2022.04.09
文献标志码:
A
摘要:
针对传统协同过滤算法存在使用信息单一、基础评分数据过于稀疏导致推荐效果不佳等问题,该文提出一种结合知识图谱进行信息强化的协同过滤(KGRI-CF)算法.该算法利用电影的特征数据构建1张关于电影的知识图谱,对用户-评分矩阵进行有条件的填充,有效改善了传统协同过滤算法的数据稀疏性问题.通过对评分数据进行统计与挖掘获取用户的偏好信息,构建了关于用户偏好的知识图谱.利用实体向量化算法将知识图谱中的实体以及关系向量化后计算出用户信息相似度,将其与基于用户的传统协同过滤算法得到的用户评分相似度以一定比例进行融合,从而得到最终的用户相似度,并以此为基础进行评分预测并得到推荐列表.实验结果表明:与传统协同过滤算法相比,该算法能有效地改善数据稀疏性问题,预测结果的精准率和召回率均有显著提升,同时具有较好的可解释性.
Abstract:
The collaborative filtering algorithm that combines knowledge graphs for information enhancement(KGRI-CF)is proposed,aiming at the problems of single use information and too sparse basic scoring data leading to poor recommendation effect in traditional collaborative filtering algorithms.The algorithm uses the feature data of the movie to construct a knowledge map about the movie,and conditionally fills the user-rating matrix,which effectively improves the data sparsity problem of the traditional collaborative filtering algorithm.Preference information is used to build a knowledge graph about user preferences.The entity vectorization algorithm is used to vectorize the entities and relationships in the knowledge graph to calculate the similarity of user information,which is fused with the similarity of user ratings obtained by the traditional user-based collaborative filtering algorithm in a certain proportion to obtain the final user similarity.On this basis the score prediction is performed and the recommendation list is obtained.The experimental results show that,compared with the traditional collaborative filtering algorithm,the algorithm can effectively improve the data sparsity problem,the accuracy and recall rate of the prediction results are significantly improved,and it has better interpretability.

参考文献/References:

[1] 翁小兰,王志坚.协同过滤推荐算法研究进展[J].计算机工程与应用,2018,54(1):7-8.
[2] GOLDBERG D,NICHOLS D,Oki B M,et al.Using collaborative filtering to weave an information tapestry[J].Communications of the ACM,1992,35(12):61-70.
[3] DI Jiaqi,WANG Nihong.Incremental collaborative filtering algorithm based on gridgis[EB/OL].[2021-06-16].http://en.cnki.com.cn/Article_en/CJFDTOTAL-JSJA201312048.htm.
[4] XU Yueshen,YIN Jianwei.Collaborative recommendation with user generated content[J].Engineering Applications of Artificial Intelligence,2015,45:281-294.
[5] CUI Hua,ZHU Ming.Collaboration filtering recommendation optimization with user implicit feedback[J].Journal of Computational Information Systems,2014,10(14):5855-5862.
[6] ZHOU Xun,HE Jing,HUANG Guangyan,et al.SVD-based incremental approaches for recommender systems[J].Journal of Computer and System,2015,81(4):717-733.
[7] SHAN Hanhuan,BANERJEE A.Generalized probabilistic matrix factorizations for collaborative filtering[EB/OL].[2021-06-17].https://doi.org/10.1109/ICDM.2010.116.
[8] 李浩,张亚钏,康雁,等.融合循环知识图谱和协同过滤电影推荐算法[J].计算机工程与应用,2020,56(2):106-114.
[9] 吴玺煜,陈启买,刘海,等.基于知识图谱表示学习的协同过滤推荐算法[J].计算机工程,2018,44(2):226-232,263
[10] WANG Xiang,HE Xiangnan,CAO Yixin,et al.Kgat:knowledge graph attention network for recommendation[EB/OL].[2021-06-11].https://arxiv.org/abs/1905.07854v2.
[11] WANG Hongwei,ZHANG Fuzheng,XIE Xing,et al.DKN:deep knowledge-aware network for news recommendation[EB/OL].[2021-06-21].https://arxiv.org/pdf/1801.08284.pdf.
[12] BORDES A,USUNIER N,GARCIA-DURÁN A,et al.Translating embeddings for modeling multi-relational data[C]∥BURGES C J,BOTTOU L,WELLING M,et al.Proceedings of the 26th International Conference on Neural Information Processing Systems.Cancouver:MIT Press,2013:2787-2795.
[13] WANG Zhen,ZHANG Jianwen,FENG Jianlin,et al.Knowledge graph embedding by translatingonhyperplanes[J].Proceedings of the AAAI Conference on Artificial Intelligence,2014,28(1):1112-1119.
[14] DAI Shaozhi,LIANG Yanchun,LIU Shuyan,et al.Learning entity and relation embeddings with entity description for knowledge graph completion[EB/OL].[2021-06-16].http://download.atlantis-press.com/article/25894200.pdf.
[15] JI Guoliang,HE Shizhu,XU Liheng,et al.Knowledge graph embedding via dynamic mapping matrix[EB/OL].[2021-06-16].https://aclanthology.org/P15-1067/.

相似文献/References:

[1]陈开阳,徐 凡*,王明文.基于知识图谱和图像描述的虚假新闻检测研究[J].江西师范大学学报(自然科学版),2021,(04):398.[doi:10.16357/j.cnki.issn1000-5862.2021.04.12]
　CHEN Kaiyang,XU Fan*,WANG Mingwen.The Fake News Detection Based on Knowledge Graph and Image Description[J].Journal of Jiangxi Normal University:Natural Science Edition,2021,(04):398.[doi:10.16357/j.cnki.issn1000-5862.2021.04.12]
[2]邓 泓,吴 祎,于程远*,等.基于可信预测值的协同过滤推荐算法[J].江西师范大学学报(自然科学版),2022,(06):642.[doi:10.16357/j.cnki.issn1000-5862.2022.06.12]
　DENG Hong,WU Yi,YU Chengyuan*,et al.The Collaborayive Filtering Recommendation Algorithm Based on Reliable Prediction Value[J].Journal of Jiangxi Normal University:Natural Science Edition,2022,(04):642.[doi:10.16357/j.cnki.issn1000-5862.2022.06.12]

备注/Memo

备注/Memo:
收稿日期:2022-01-13
基金项目:国家自然科学基金(61877031)资助项目.
通信作者:杨庆红(1968—),女,江西南昌人,教授,主要从事软件形式化和智能教育软件的研究.E-mail:yangqh120@163.com
更新日期/Last Update: 2022-07-25