南京大学学报(自然科学版) ›› 2023, Vol. 59 ›› Issue (1): 120–133.doi: 10.13232/j.cnki.jnju.2023.01.012

• • 上一篇    下一篇

基于用户特征聚类与服务质量预测的推荐方法

刘佳慧, 袁卫华, 曹家伟, 张涛, 张志军()   

  1. 山东建筑大学计算机科学与技术学院，济南，250101
  • 收稿日期:2022-10-25 出版日期:2023-01-31 发布日期:2023-03-01
  • 通讯作者: 张志军 E-mail:zzjsdcn@163.com
  • 基金资助:
    国家自然科学基金(61902221);山东省自然科学基金(ZR2021MF099);山东省教学改革研究项目(M2021130);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)

Recommendation method based on user feature clustering and quality of service prediction

Jiahui Liu, Weihua Yuan, Jiawei Cao, Tao Zhang, Zhijun Zhang()   

  1. School of Computer Science and Technology，Shandong Jianzhu University，Ji'nan，250101，China
  • Received:2022-10-25 Online:2023-01-31 Published:2023-03-01
  • Contact: Zhijun Zhang E-mail:zzjsdcn@163.com

RichHTML

12

PDF (PC)

405

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.

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

Abstract:

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.

Key words: service recommendation, user clustering, Particle Swarm Optimization (PSO), location aware, reputation aware, Matrix Factorization (MF)

中图分类号: 

  • TP391

图1

用户服务响应时间矩阵"

图2

PLRMF的整体框架"

图3

基于PSO聚类流程图"

表1

实验使用的WS?Dream数据集的数据统计"

用户数339
服务数5825
服务调用记录QoS1974675
用户国家数30
用户自治系统数136
服务国家数73
服务自治系统数990

表2

PLRMF的实验参数"

实验参数参数值
α和β0.01
λ1和λ20.01
d50
δ0.1
ε0.05
γ1和γ20.01
θ0.5
w0.5
c1和c22
τ0.6

表3

各算法预测准确性的比较(无不可靠用户和服务)"

方法矩阵密度5%矩阵密度10%矩阵密度15%矩阵密度20%
MAERMSEMAERMSEMAERMSEMAERMSE
UPCC0.75451.55330.57911.35860.53261.31510.51471.3007
IPCC0.78651.60450.59631.39380.57201.33660.55241.3190
UIPCC0.73021.53920.56711.35110.52861.30350.50741.2967
CMF0.56751.42420.50891.26180.48291.20240.45721.1669
PMF0.56691.41380.50781.25950.48121.20670.45591.1649
NCF0.54321.37850.48661.24340.45421.17690.43411.1393
RMF0.56371.41060.49941.25990.47351.19820.45531.1639
LRMF0.55411.39120.49521.25110.46481.18460.44501.1475
RRMF0.55341.38950.49491.25080.46461.18360.44301.1462
PLRMF0.54481.37670.48511.24050.45291.17370.43231.1366
vs LRMF0.93%1.45%1.01%1.06%1.19%1.09%1.27%1.09%
vs RRMF0.86%1.28%0.98%1.03%1.17%0.99%1.07%0.96%

表4

各算法预测准确性的比较(10个不可靠用户和30个不可靠服务)"

方法矩阵密度5%矩阵密度10%矩阵密度15%矩阵密度20%
MAERMSEMAERMSEMAERMSEMAERMSE
UPCC0.75581.55130.58111.35950.53491.31680.51701.3024
IPCC0.78771.60440.59901.39390.57491.33690.55541.3196
UIPCC0.73221.53900.56981.35260.53161.30540.51011.2986
CMF0.57121.42680.51391.27010.48981.20530.46141.1711
PMF0.56931.41380.51141.26150.48371.20600.46051.1684
NCF0.54871.38360.49041.24610.45801.18020.43791.1415
RMF0.56861.41600.50271.26180.47751.20160.45931.1664
LRMF0.55781.39230.49951.25470.46841.18650.44641.1480
RRMF0.55631.39190.49871.25330.46731.18570.44471.1472
PLRMF0.54611.37730.48541.24170.45321.17450.43261.1363
vs LRMF1.17%1.50%1.41%1.30%1.52%1.20%1.38%1.17%
vs RRMF1.02%1.46%1.33%1.16%1.41%1.12%1.21%1.09%

图4

不同聚类方法的影响"

图5

不可靠服务的影响"

图6

信誉计算的影响"

图7

参数θ的影响"

图8

参数γ1和γ2的影响"

图9

矩阵密度的影响"

图10

维度d的影响"

1 Ding F， Wen T， Ren S J，et al. Performance analysis of a clustering model for QoS?aware service recommendation. Electronics，2020，9(5)：740.
2 Wang Q R， Zhang M， Zhang Y W，et al. Location?based deep factorization machine model for service recommendation. Applied Intelligence，2022，52(9)：9899-9918.
3 Zhang Y W， Yin C H， Wu Q L，et al. Location?aware deep collaborative filtering for service recommen?dation. IEEE Transactions on Systems，Man，and Cybernetics：Systems，2019，51(6)：3796-3807.
4 Guo L， Yin H Z， Wang Q Y，et al. Streaming session?based recommendation∥Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. Anchorage，AK，USA：ACM，2019：1569-1577.
5 Guo L， Yin H Z， Chen T，et al. Hierarchical hyperedge embedding?based representation learning for group recommendation. ACM Transactions on Information Systems，2021，40(1)：3.
6 Guo L， Zhang J Y， Chen T，et al. Reinforcement learning?enhanced shared?account cross?domain sequential recommendation. IEEE Transactions on Knowledge and Data Engineering，2022：1-14.
7 Zhang F G， Qi S M， Liu Q H，et al. Alleviating the data sparsity problem of recommender systems by clustering nodes in bipartite networks. Expert Systems with Applications，2020(149)：113346.
8 Fayala M， Mezni H. Web service recommendation based on time?aware users clustering and multi?valued QoS prediction. Concurrency and Compu?tation：Practice and Experience，2020，32(9)：e5603.
9 Indira K， Kavitha Devi M K. Multi cloud based service recommendation system using DBSCAN algorithm. Wireless Personal Communications，2020，115(2)：1019-1034.
10 Hao J S， Su G P， Han X F，et al. An expanded matrix factorization model for real?time Web service QoS prediction. KSII Transactions on Internet and Information Systems，2021，15(11)：3913-3934.
11 Chang Z H， Ding D， Xia Y H. A graph?based QoS prediction approach for web service recommendation. Applied Intelligence，2021，51(10)：6728-6742.
12 Wang Z X， Xiao Y Y， Sun C C，et al. Location?aware feature interaction learning for web service recommendation∥2020 IEEE International Conference on Web Services. Beijing，China：IEEE，2020：232-239.
13 Zou G B， Chen J， He Q，et al. NDMF：Neighbor?hood?integrated deep matrix factorization for service QoS prediction. IEEE Transactions on Network and Service Management，2020，17(4)：2717-2730.
14 Shao L S， Zhang J， Wei Y，et al. Personalized qos prediction forweb services via collaborative filtering∥2007 IEEE International Conference on Web Services. Salt Lake City，UT，USA：IEEE，2007：439-446.
15 Sarwar B， Karypis G， Konstan J，et al. Item?based collaborative filtering recommendation algorithms∥Proceedings of the 10th International Conference on World Wide Web. Hong Kong，China：ACM，2001：285-295.
16 Zheng Z B， Ma H， Lyu M R，et al. WSRec：A collaborative filtering based web service recommender system∥2009 IEEE International Conference on Web Services. Los Angeles，CA，USA：IEEE，2009：437-444.
17 Botangen K A， Yu J， Sheng Q Z，et al. Geographic?aware collaborative filtering for web service recommendation. Expert Systems with Applications，2020(151)：113347.
18 Ngaffo A N， Ayeb W E， Choukair Z. Service recommendation driven by a matrix factorization model and time series forecasting. Applied Intelligence，2022，52(1)：1110-1125.
19 Gunes I， Kaleli C， Bilge A，et al. Shilling attacks against recommender systems：A comprehensive survey. Artificial Intelligence Review，2014，42(4)：767-799.
20 Mokdad L， Fourneau J M， Abdelli A，et al. Performance evaluation of a solution for composite service selection problem with multiple consumers. Simulation Modelling Practice and Theory，2021(109)：102271.
21 Pal D， Vanijja V. Effect of network QoS on user QoE for a mobile video streaming service using H.265/VP9 codec. Procedia Computer Science，2017(111)：214-222.
22 Xu J L， Zheng Z B， Lyu M R. Web service personalized quality of service prediction via reputation?based matrix factorization. IEEE Transactions on Reliability，2015，65(1)：28-37.
23 Li S， Wen J H， Luo F J，et al. A location and reputation aware matrix factorization approach for personalized quality of service prediction∥2017 IEEE International Conference on Web Services. Honolulu，HI，USA：IEEE，2017：652-659.
24 Kuang L， Yu L， Huang L，et al. A personalized QoS prediction approach for CPS service recommendation based on reputation and location?aware collaborative filtering. Sensors，2018，18(5)：1556.
25 Ghafouri S H， Hashemi S M， Razzazi M R，et al. Web service quality of service prediction via regional reputation?based matrix factorization. Concurrency and Computation：Practice and Experience，2021，33(17)：e6318.
26 Kennedy J， Eberhart R. Particle swarm optimi?zation∥Proceedings of International Conference on Neural Networks. Perth，Australia：IEEE，1995(4)：1942-1948.
27 Jain P， Dixit V S. Recommendations with context aware framework using particle swarm optimization and unsupervised learning. Journal of Intelligent & Fuzzy Systems，2019，36(5)：4479-4490.
28 Mezni H， Ait Arab S， Benslimane D，et al. An evolutionary clustering approach based on temporal aspects for context?aware service recommendation. Journal of Ambient Intelligence and Humanized Computing，2020，11(1)：119-138.
29 Ahmadian M， Ahmadi M， Ahmadian S. A reliable deep representation learning to improve trust?aware recommendation systems. Expert Systems with Applications，2022(197)：116697.
30 Guo J， Zhou Y， Zhang P，et al. Trust?aware recommendation based on heterogeneous multi?relational graphs fusion. Information Fusion，2021(74)：87-95.
31 Zheng Q Q， Liu G F， Liu A，et al. Implicit relation?aware social recommendation with variational auto?encoder. World Wide Web，2021，24(5)：1395-1410.
32 Koren Y， Bell R， Volinsky C. Matrix factorization techniques for recommender systems. Computer，2009，42(8)：30-37.
33 Zheng Z B， Ma H， Lyu M R，et al. QoS?aware web service recommendation by collaborative filtering. IEEE Transactions on Services Computing，2011，4(2)：140-152.
34 Salakhutdinov R R， Mnih A. Probabilistic matrix factorization∥Proceedings of the 20th International Conference on Neural Information Processing Systems. Vancouver，Canada：Curran Associates Inc.，2007(20)：1257-1264.
35 He X N， Liao L Z， Zhang H W，et al. Neural collaborative filtering∥Proceedings of the 26th International Conference on World Wide Web. Perth，Australia：International World Wide Web Conferences Steering Committee，2017：173-182.
[1] 田小瑜, 秦永彬, 黄瑞章, 陈艳平. 基于相关性约束矩阵分解的多标签分类方法[J]. 南京大学学报(自然科学版), 2023, 59(1): 76-84.
[2] 时照群, 刘兆伟, 刘惊雷. 基于相关熵和流形正则化的图像聚类[J]. 南京大学学报(自然科学版), 2022, 58(3): 469-482.
[3] 吕亚兰, 徐媛媛, 张恒汝. 一种可解释性泛化矩阵分解推荐算法[J]. 南京大学学报(自然科学版), 2022, 58(1): 135-142.
[4] 郝昱猛, 马文明, 王冰. 基于特定用户约束的概率矩阵分解算法[J]. 南京大学学报(自然科学版), 2021, 57(5): 818-827.
[5] 袁晓峰, 钱苏斌, 周彩根. 基于填充先验约束的矩阵分解算法[J]. 南京大学学报(自然科学版), 2021, 57(2): 197-207.
[6] 孙颖, 蔡天使, 张毅, 鞠恒荣, 丁卫平. 基于合理粒度的局部邻域决策粗糙计算方法[J]. 南京大学学报(自然科学版), 2021, 57(2): 262-271.
[7] 李子龙,周勇,鲍蓉. AdaBoost图像到类距离学习的图像分类方法[J]. 南京大学学报(自然科学版), 2020, 56(1): 51-56.
[8] 何轶凡, 邹海涛, 于化龙. 基于动态加权Bagging矩阵分解的推荐系统模型[J]. 南京大学学报(自然科学版), 2019, 55(4): 644-650.
[9] 廖国琼, 黄志伟. 基于事件社会网络中考虑约束全局推荐策略[J]. 南京大学学报(自然科学版), 2018, 54(1): 11-.
[10] 吴家豪1，彭志平2*，崔得龙2，李启锐2，何杰光2. 基于多Agent系统的粒子群遗传优化云工作流调度算法[J]. 南京大学学报(自然科学版), 2017, 53(6): 1114-.
[11]  宗林林，张宪超*，赵乾利，于　红，刘馨月.  一种多流形正则化的多视图非负矩阵分解算法[J]. 南京大学学报(自然科学版), 2017, 53(3): 557-.
[12] 卢文凯*，景丽萍*，杨　柳 . 截断式鲁棒非负矩阵分解算法[J]. 南京大学学报(自然科学版), 2016, 52(4): 714-.
[13] 张燕平1,2张顺1,2钱付兰1,2严远亭1,2. 一种局部和全局用户影响力相结合的社交推荐算法[J]. 南京大学学报(自然科学版), 2015, 51(4): 858-865.
[14] 周文猛1，杨一品1，周余1，于耀1，金苏文2，都思丹1*. 基于Kinect的无标记手部姿态估计系统[J]. 南京大学学报(自然科学版), 2015, 51(2): 297-.
[15]   韩飞**，杨春生，刘清 .  一种改进的基于梯度搜索的粒子群优化算法*[J]. 南京大学学报(自然科学版), 2013, 49(2): 196-201.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!

版权所有 © 2021 《南京大学学报(自然科学)》

地址：江苏省南京市鼓楼区汉口路22号，南京大学学报编辑部，210093

电话：025-83592704 , 传真：025-83592704        技术支持：北京玛格泰克科技发展有限公司