Research On Supply Chain Network Resilience And Supplier Recommendation Based On Multi-Source Heterogeneous Big Data

In the context of globalization today,the complexity and degree of globalization of supply chains are becoming increasingly high,and supply chain security issues are becoming a focus of international attention.Interruptions from any link in the supply chain can trigger a chain reaction and extend to other business entities,causing serious and lasting damage to the entire supply chain network.How to improve the resilience of supply chain networks has become one of the important challenges that supply chain managers and researchers need to face.This study is based on multisource heterogeneous big data and investigates the resilience of supply chain networks and supplier recommendation issues.Firstly,based on the perspective of complex networks,the main factors affecting the resilience of supply chain networks were identified.A supply chain network was constructed using supplier and customer data from A-share listed companies.At the same time,network modeling and simulation methods were used to measure the resilience of the supply chain network.Finally,regression analysis was used to explore the impact of ripple effects,network structure characteristics,and supplier substitution strategies on the resilience of the supply chain network.At the same time,in order to further enhance the resilience of the supply chain network and enhance the sustainability of enterprises,this article constructs a two-stage supplier recommendation model with multisource heterogeneous network embedding and deep learning,in order to provide supplier recommendation services to enterprises,further strengthen industrial flow,and enhance supply chain resilience.The input of the model is business data and patent data of the enterprise.Based on the above data,a multi-source heterogeneous network was constructed,which includes technical cooperation relationships,knowledge flow relationships,and business cooperation relationships between enterprises.Extract network features of enterprises in multi-source heterogeneous networks using the GATNE method.Based on the network characteristics,commercial attributes,and technical attributes of the enterprise,a deep neural network model was used to recommend suitable suppliers for the enterprise.This article effectively identifies key network structural features that affect the resilience of supply chain networks,and verifies the mechanism of supplier substitution strategies on supply chain network resilience.It fills the gap in research on supply chain network resilience from the perspective of complex networks and provides guidance for researchers and supply chain managers to manage supply chain resilience.At the same time,a supplier recommendation system was successfully constructed,introducing cutting-edge multi-source heterogeneous network embedding and deep learning methods in the field of artificial intelligence,effectively achieving the fusion of multi-dimensional information and achieving automatic,supplier recommendation.Based on this,the model can provide upstream enterprises with alternative options when facing supply chain disruptions and other impacts,thereby effectively improving the resilience of their supply chain network and responding to external risks.