摘要
随着服务系统中Web服务的不断增加,为用户进行个性化Web服务推荐成为服务计算领域最热门的研究课题之一,然而,服务推荐面临不可靠用户和服务导致推荐的不准确性问题.为了解决上述问题,提出一种基于位置和信誉感知的Web服务推荐方法.首先采用粒子群优化(Particle Swarm Optimization,PSO)对用户进行聚类,得到相似用户;其次,计算用户和服务的信誉来识别可信的用户和服务;最后,将相似用户和可信服务的信息整合到矩阵分解(Matrix Factorization,MF)中,为用户预测缺失的服务质量(Quality of Service,QoS).在真实数据集WS-Dream上的实验验证了提出方法的可行性与有效性.与其他先进的预测方法相比,该方法的MAE(Mean Absolute Error)和RMSE(Root Mean Squared Error)较低,证明该方法有较高的预测准确性.
With the continuous increase of Web services in service systems,personalized Web service recommendation for users has become one of the most popular research topics in the field of service computing.However,service recommendation faces the problem of inaccuracy caused by unreliable users and services.To solve these problems,this paper proposes a location-and reputation-aware Web service recommendation method.Firstly,Particle Swarm Optimization(PSO)is used to cluster users to obtain similar users.Secondly,the reputation of users and services is calculated to identify trusted users and services.Finally,the information of similar users and trusted services are combined into Matrix Factorization(MF),so as to predict the missing Quality of Service(QoS)for users.The feasibility and effectiveness of the proposed method are verified by experiments on the real dataset WS-Dream.Compared with other advanced prediction methods,the MAE(Mean Absolute Error)and RMSE(Root Mean Squared Error)of the proposed method are lower,proving higher prediction accuracy.
作者
刘佳慧
袁卫华
曹家伟
张涛
张志军
Liu Jiahui;Yuan Weihua;Cao Jiawei;Zhang Tao;Zhang Zhijun(School of Computer Science and Technology,Shandong Jianzhu University,Ji'nan,250101,China)
出处
《南京大学学报（自然科学版）》
CAS
CSCD
北大核心
2023年第1期120-133,共14页
Journal of Nanjing University（Natural Science）
基金
国家自然科学基金(61902221,62177031)
山东省自然科学基金(ZR2021MF099,ZR2022MF334)
山东省教学改革研究项目(M2021130,M2022245,Z2022202)
山东省优质专业学位教学案例库建设项目(SDYAL2022155)
山东省重点研发计划(软科学项目)(2021RKY03056)。
关键词
服务推荐
用户聚类
粒子群优化
位置感知
信誉感知
矩阵分解
service recommendation
user clustering
Particle Swarm Optimization(PSO)
location aware
reputation aware
Matrix Factorization(MF)
