基于图神经网络的云制造服务推荐方法研究

doi:10.3969/j.issn.1007-7375.2023.05.013

摘要/Abstract

摘要： 针对云制造服务平台上的海量制造服务信息所带来的信息过载问题，提出一种基于图神经网络的云制造服务推荐方法，有效克服了传统推荐方法无法利用数据高维特征的局限性。提取平台上制造服务资源的特征，根据不同的相似度计算方法将制造服务资源构建为网络图；利用邻居采样图神经网络 (graph sample and aggregate, GraphSAGE) 进行网络的表示学习，并将学习到的网络特征带入链接预测函数进行模型训练；通过对资源节点间的链接概率进行预测，完成对用户的制造服务推荐。结果表明，基于图神经网络算法的链接预测模型，其预测性能要优于所对比的共同邻居 (common neighbors, CN) 、Adamic-adar (AA) 与资源分配 (resource allocation, RA) 链接预测算法，从而取得较好的推荐效果，为解决云制造服务推荐问题提供理论依据，有助于提高用户的决策效率。

关键词: 云制造, 图神经网络, 链接预测, 制造服务推荐

Abstract: To address the problem of information overload caused by the massive manufacturing service information on cloud manufacturing service platforms, a graph neural network-based recommendation method for cloud manufacturing services is proposed in this paper, which effectively overcomes the limitations of traditional recommendation methods that cannot use high-dimensional features of data. Firstly, the features of manufacturing service resources on a platform are extracted, and manufacturing service resources are constructed as a network graph according to different similarity calculation methods. Secondly, a graph sample and aggregate (GraphSAGE) neural network is used for network representation learning, and the learned network features are brought into the link prediction function for model training. Finally, by predicting the link probability among resource nodes, the manufacturing service recommendation for users is completed. Experimental results show that the performance of the link prediction model based on GraphSAGE is better than that of link prediction models based on common neighbors (CN), Adamic-adar (AA) and resource allocation (RA). Thus, better recommendation results are achieved. It provides a theoretical basis for solving the recommendation problem of cloud manufacturing services and helps to improve the decision-making efficiency of users.

Key words: cloud manufacturing, graph neural network, link prediction, manufacturing service recommendation

中图分类号:

TP181

董学文, 石宇强, 田永政. 基于图神经网络的云制造服务推荐方法研究[J]. 工业工程, 2023, 26(5): 115-123,167.

DONG Xuewen, SHI Yuqiang, TIAN Yongzheng. A Recommendation Method for Cloud Manufacturing Services Based on Graph Neural Networks[J]. Industrial Engineering Journal, 2023, 26(5): 115-123,167.

参考文献

[1] JIANG Z, FENG G, YI Z, et al. Service-oriented manufacturing: a literature review and future research directions[J]. Frontiers of Engineering Management, 2022, 9(1): 71-78
[2] 李伯虎, 张霖, 王石龙, 等. 云制造——面向服务的网络化制造新模式[J]. 计算机集成制造系统, 2010, 16(1): 1-7
LI Bohu, ZHANG Lin, WANG Shilong, et al. Cloud manufacturing: a new service-oriented manufacturing model[J]. Computer Integrated Manufacturing Systems, 2010, 16(1): 1-7
[3] 徐松. 云制造环境下服务个性化推荐与组合优化研究[D]. 杭州: 浙江财经大学, 2016.
XU Song. Research on service personalized recommendation and composition in cloud manufacturing environment[D]. Hangzhou: Zhejiang University of Finance and Economics, 2016.
[4] TAO F, ZHANG L, LIU Y. Manufacturing service management in cloud manufacturing: overview and future research directions[J]. Journal of Manufacturing Science and Engineering, 2015, 137(4): 1-38
[5] FAN Y, HUANG K, TAN W, et al. Domain-aware reputable service recommendation in heterogeneous manufacturing service ecosystem[J]. International Journal of Computer Integrated Manufacturing, 2015, 28(11): 1178-1195
[6] 禹春霞, 刘玉茹, 高旭. 面向用户个性化需求的云服务商推荐[J]. 工业工程, 2019, 22(2): 1-9
YU Chunxia, LIU Yuru, GAO Xu. Cloud service supplier recommendation based on user personalized preference[J]. Industrial Engineering Journal, 2019, 22(2): 1-9
[7] ZHANG W, ZHANG S, CHEN Y, et al. Combining social network and collaborative filtering for personalised manufacturing service recommendation[J]. International Journal of Production Research, 2013, 51(22): 6702-6719
[8] 鲁城华, 高升, 郭倩倩. 基于大数据技术的云制造服务个性化智能推荐[J]. 信息系统工程, 2020(8): 31-35
[9] 万年红, 王雪蓉. 多目标事务模糊关联聚类的云制造服务组合算法[J]. 计算机测量与控制, 2022, 30(6): 287-295
WAN Nianhong, WANG Xuerong. Service composition algorithms in cloud manufacturing based on fuzzy correlation clustering of multi-objective transactions[J]. Computer Measurement & Control, 2022, 30(6): 287-295
[10] YU Bingbing. Research on recommendation system based on deep learning[J]. International Journal of Social Science and Education Research, 2022, 5(3): 310-314
[11] SIMEONE A, ZENG Yunfeng, CAGGIANO A. Intelligent decision-making support system for manufacturing solution recommendation in a cloud framework[J]. The International Journal of Advanced Manufacturing Technology, 2021, 112: 1035-1050
[12] FATHOLLAHI M S, RAZZAZI F. Music similarity measurement and recommendation system using convolutional neural networks[J]. International Journal of Multimedia Information Retrieval, 2021, 10(1): 43-53
[13] LIU R, JIA C, ZHOU T, et al. Personal recommendation via modified collaborative filtering[J]. Physica A, 2009, 388(4): 462-468
[14] SONG H, MOON N. Eye-tracking and social behavior preference-based recommendation system[J]. The Journal of Supercomputing, 2019, 75(4): 1990-2006
[15] MOHAMMAD A. Power coefficient as a similarity measure for memory-based collaborative recommender systems[J]. Expert Systems with Applications, 2014, 41(13): 5680-5688
[16] HAMILTON W L, YING R, LESKOVEC J. Inductive representation learning on large graphs[C/OL]// NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems. USA: arXiv e-prints, 2017. (2017-06). http://10.48550/arXiv.1706.02216.
[17] 李元香, 董夏磊, 项正龙, 等. 基于图卷积神经网络的软件缺陷分派方法[J]. 武汉大学学报 (理学版), 2020, 66(3): 244-252
LI Yuanxiang, DONG Xialei, XIANG Zhenglong, et al. Software bug triage approach based on graph convolutional neural network[J]. Journal of Wuhan University (Natural Science Edition), 2020, 66(3): 244-252
[18] GUNDONGDU O, EGRIOGLU E, ALADAG C H. Multiplicative neuron model artificial neural network based on Gaussian activation function[J]. Neural Computing and Applications, 2016, 27(4): 927-935
[19] PENG F, LU X, MA C, et al. Multi-level preference regression for cold-start recommendations[J]. International Journal of Machine Learning and Cybernetics, 2018, 9(7): 1117-1130
[20] KINGMA D P, BA J. Adam: a method for stochastic optimization[C/OL]//The 3rd International Conference on Learning Representations. San Diego: arXiv, 2015. (2017-01-30). http://doi.org/10.48550/arXiv.1412.6980.
[21] 张健沛, 姜延良. 一种基于节点相似性的链接预测算法[J]. 中国科技论文, 2013, 8(7): 659-662
ZHANG jianpei, JIANG Yanliang. A link prediction algorithm based on node similarity[J]. China Sciencepaper, 2013, 8(7): 659-662
[22] HANLEY J A, MCNEIL B J. The meaning and use of the area under a receiver operating characteristic (ROC) curve[J]. Radiology, 1982, 143(1): 29-36
[23] HERLOCKER J L, KONSTAN J A, TERVEEN L G, et al. Evaluating collaborative filtering recommender systems[J]. ACM Transactions on Information Systems, 2014, 22(1): 5-53