In the context of globalization and frequent extreme events, the identification of supply chain network topology and the characterization of risk propagation are key points to enhance industry resilience. This study constructs a heterogeneous supply chain graph containing multiple types of nodes and multi-dimensional edge weights for enterprises, logistics, finance and regulation, and proposes explanatory indicators such as multi-type PageRank and heterogeneous redundancy coefficient. A heterogeneous graph neural network based on the meta-path attention mechanism is constructed, and time coding is introduced to capture the dynamic changes of the structure. The identification of key nodes and the estimation of the probability of supply interruption are jointly optimized by multi-task learning. In the context of Resilinc and BTS public data sets, the recall rate of the model for hidden key nodes is 14 percentage points higher than that of the traditional centrality method. In the simulation of the collapse of the Baltimore Bridge, a re-planned route plan can be recommended 36 hours in advance. This framework can provide accurate, interpretable, timely and effective network monitoring and decision support, and build a methodological foundation for the subsequent integration of federated learning and digital twins.

Xuezhi Wu, Yuchen Huang, Wenqing Bao. Using GNN to Identify Supply Chain Network Structure. International Journal of Big Data Intelligent Technology (2025), Vol. 6, Issue 2: 46-55. https://doi.org/10.38007/IJBDIT.2025.060205.

[1] Gu Y. Javascript Code Simplification and Optimization Based on Hybrid Static and Dynamic Analysis Techniques[C]//2025 IEEE 14th International Conference on Communication Systems and Network Technologies (CSNT). IEEE, 2025: 826-833.

[2] Zhang J. Research on User Behavior Interest Feature Extraction and Accurate Advertising Recommendation Algorithm based on Deep Learning and Improved LDA Model[C]//2025 3rd International Conference on Integrated Circuits and Communication Systems (ICICACS). IEEE, 2025: 1-5.

[3] Xu Q. Architecture Design and Performance Analysis of Mobile Instant Chat System based on Asynchronous Communication Model[C]//2025 3rd International Conference on Integrated Circuits and Communication Systems (ICICACS). IEEE, 2025: 1-7.

[4] Chen J. Design and Implementation of a Personalized Recommendation System Based on Deep Learning Distributed Collaborative Filtering Algorithm on Social Media Platforms[C]//2025 3rd International Conference on Integrated Circuits and Communication Systems (ICICACS). IEEE, 2025: 1-5.

[5] Xingyu Liu, Exploration of Personalized User Experience Optimization in Virtual Reality with Deep Learning, International Journal of Finance and Investment, 2025, 2(2),15-19

[6] Liu Z. Research on the Application of Signal Integration Model in Real-Time Response to Social Events[J]. Journal of Computer, Signal, and System Research, 2025, 2(2): 102-106.

[7] Xuan Li, Research on integration technology of architectural CAD and budget estimate, Journal of Computing and Electronic Information Management, 2024, 15(1), 20-23

[8] Zou Y. Application of Cross Platform Integration Technology in Modern Communication Systems[J]. European Journal of AI, Computing & Informatics, 2025, 1(1): 64-70.

[9] Boyang Liu, Research on Holographic Retrieval and Analysis System for Scientific Research Data Based on SSH Framework and Lucene Engine, Journal of Artificial Intelligence Practice, 2024, 7(3), 164-171.

[10] Zhao, Fengyi "Research and Optimization of Enterprise Standard System Construction Method Based on Process Analysis." Accounting and Corporate Management (2024), 6(5): 61-66

[11] Zhang, Jinshuo "Research on Real Time Condition Monitoring and Fault Warning System for Construction Machinery under Multi Source Heterogeneous Data Fusion." Journal of Engineering Mechanics and Machinery (2024), 9(2): 139-144

[12] Wu, Wei "Research on Customer Traffic Value Recognition Model Based on Improved Random Forest Algorithm." Accounting and Corporate Management (2024), 6(5): 30-35

[13] Wang Y. Design and Implementation of a General Data Collection System Architecture Based on Relational Database Technology[C]//The International Conference on Cyber Security Intelligence and Analytics. Cham: Springer Nature Switzerland, 2024: 561-572.

[14] Yuchen Liu, Research on the Inner Logic and Practical Path of Empowering Enterprise Financial Intelligence Construction with Digital Economy, International Journal of Social Sciences and Economic Management, 2025, 6(1),179-187

[15] Zhu, Zhongqi. "Strategies for Improving Vector Database Performance through Algorithm Optimization." Scientific Journal of Technology 7.2 (2025): 138-144.

[16] Ding M. Application of AI Technology in Improving Design Process Efficiency[J]. European Journal of AI, Computing & Informatics, 2025, 1(1): 101-106.

[17] Tan, Weiyan, Shujia Wu, and Ke Ma. "Freight Volume Prediction for Logistics Sorting Centers Using an Integrated GCN-BiLSTM-Transformer Model." Advances in Computer and Engineering Technology Research 1.4 (2024): 320-324