Digital twin-enabled dynamic spatial-temporal knowledge graph for production logistics resource allocation

• Dynamic spatial–temporal knowledge graph for resource allocation is proposed. • IoT signal big data are handled to spatial–temporal values through deep learning. • A graph algorithm is designed for production logistics resource allocation. • Case study is conducted to verify the performance of the proposed approach. Production logistics (PL) is increasingly receiving attention from supply chain research. The spatial disorder and temporal asynchrony of the PL resources due to the uncertainty and dynamicity pose great challenges to efficient resource allocation. The inability to obtain and rational use of PL resource spatial–temporal values causes unnecessary long travelling distances and excessive waiting time, which impede the sustainable performance of PL operations. In response, this research proposes a PL resource allocation approach based on the dynamic spatial–temporal knowledge graph (DSTKG). Internet of Things(IoT) signals data generated from large-scale deployed IoT devices are investigated and analysed to spatial–temporal values through deep neural networks. The DSTKG model is established for representing the digital twin replica with spatial–temporal consistency, followed by reasoning and completion of relationships based on PL task information. The PL resources are allocated efficiently through the graph algorithm from the directed and weighted graph. The case study is conducted to verify the feasibility and practicality of the proposed solution based on large-scale deployment. Finally, the result demonstrates the effectiveness of the proposed methodology.