{"title":"基于知识图和图卷积网络的制造服务推荐方法","authors":"Qing Zheng , Tingfeng Guo , Guofu Ding , Haizhu Zhang , Kai Zhang","doi":"10.1016/j.aei.2025.103599","DOIUrl":null,"url":null,"abstract":"<div><div>Service-oriented manufacturing is a novel manufacturing model that involves a deep integration of manufacturing and services, facilitated by the operation of manufacturing service platforms. This signifies the tight integration between advanced manufacturing and modern service industries. In this context, the advancement of new-generation information technology has prompted increased participation from both service providers and demanders, leading to a significant expansion of information available on manufacturing services platforms. On the demand side, there is a challenge in selecting from a vast array of manufacturing services, while on the service provide side, there is a challenge in selecting from numerous tasks. At the same time, there are issues with manufacturing service recommendation methods, including cold start, insufficient information utilization, introduction of noise, and inadequate modeling representation. To address the aforementioned issues, this study proposes a manufacturing service recommendation method based on knowledge graphs and graph convolutional networks. The method utilizes graph convolutional networks to aggregate neighborhood information of manufacturing service providers and tasks in the knowledge graph, and introduces self-attention mechanism during the aggregation process to reduce noise interference. Finally, the obtained neighborhood information is integrated into the initial representation of manufacturing service providers and tasks, predicting the probability of their interaction, thus achieving manufacturing service recommendation. Using service data from a specific platform to create a dataset for validation, the effectiveness of the proposed service recommendation method has been demonstrated.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"68 ","pages":"Article 103599"},"PeriodicalIF":9.9000,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Manufacturing service recommendation method based on knowledge graph and graph convolutional network\",\"authors\":\"Qing Zheng , Tingfeng Guo , Guofu Ding , Haizhu Zhang , Kai Zhang\",\"doi\":\"10.1016/j.aei.2025.103599\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Service-oriented manufacturing is a novel manufacturing model that involves a deep integration of manufacturing and services, facilitated by the operation of manufacturing service platforms. This signifies the tight integration between advanced manufacturing and modern service industries. In this context, the advancement of new-generation information technology has prompted increased participation from both service providers and demanders, leading to a significant expansion of information available on manufacturing services platforms. On the demand side, there is a challenge in selecting from a vast array of manufacturing services, while on the service provide side, there is a challenge in selecting from numerous tasks. At the same time, there are issues with manufacturing service recommendation methods, including cold start, insufficient information utilization, introduction of noise, and inadequate modeling representation. To address the aforementioned issues, this study proposes a manufacturing service recommendation method based on knowledge graphs and graph convolutional networks. The method utilizes graph convolutional networks to aggregate neighborhood information of manufacturing service providers and tasks in the knowledge graph, and introduces self-attention mechanism during the aggregation process to reduce noise interference. Finally, the obtained neighborhood information is integrated into the initial representation of manufacturing service providers and tasks, predicting the probability of their interaction, thus achieving manufacturing service recommendation. Using service data from a specific platform to create a dataset for validation, the effectiveness of the proposed service recommendation method has been demonstrated.</div></div>\",\"PeriodicalId\":50941,\"journal\":{\"name\":\"Advanced Engineering Informatics\",\"volume\":\"68 \",\"pages\":\"Article 103599\"},\"PeriodicalIF\":9.9000,\"publicationDate\":\"2025-07-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Advanced Engineering Informatics\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1474034625004926\",\"RegionNum\":1,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advanced Engineering Informatics","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1474034625004926","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
Manufacturing service recommendation method based on knowledge graph and graph convolutional network
Service-oriented manufacturing is a novel manufacturing model that involves a deep integration of manufacturing and services, facilitated by the operation of manufacturing service platforms. This signifies the tight integration between advanced manufacturing and modern service industries. In this context, the advancement of new-generation information technology has prompted increased participation from both service providers and demanders, leading to a significant expansion of information available on manufacturing services platforms. On the demand side, there is a challenge in selecting from a vast array of manufacturing services, while on the service provide side, there is a challenge in selecting from numerous tasks. At the same time, there are issues with manufacturing service recommendation methods, including cold start, insufficient information utilization, introduction of noise, and inadequate modeling representation. To address the aforementioned issues, this study proposes a manufacturing service recommendation method based on knowledge graphs and graph convolutional networks. The method utilizes graph convolutional networks to aggregate neighborhood information of manufacturing service providers and tasks in the knowledge graph, and introduces self-attention mechanism during the aggregation process to reduce noise interference. Finally, the obtained neighborhood information is integrated into the initial representation of manufacturing service providers and tasks, predicting the probability of their interaction, thus achieving manufacturing service recommendation. Using service data from a specific platform to create a dataset for validation, the effectiveness of the proposed service recommendation method has been demonstrated.
期刊介绍:
Advanced Engineering Informatics is an international Journal that solicits research papers with an emphasis on 'knowledge' and 'engineering applications'. The Journal seeks original papers that report progress in applying methods of engineering informatics. These papers should have engineering relevance and help provide a scientific base for more reliable, spontaneous, and creative engineering decision-making. Additionally, papers should demonstrate the science of supporting knowledge-intensive engineering tasks and validate the generality, power, and scalability of new methods through rigorous evaluation, preferably both qualitatively and quantitatively. Abstracting and indexing for Advanced Engineering Informatics include Science Citation Index Expanded, Scopus and INSPEC.