Cyber-Physical Computer in Action: Generative Recommendation via Spatial-Temporal Subgraph Reasoning for Production Logistics Orchestration

Production logistics (PL) is essential for linking manufacturing activities through the timely transportation of work-in-progress items. However, increasing product customization, a broader range of materials, and more complex spatial-temporal constraints among resources have made PL orchestration significantly more challenging. To address these issues, we propose the cyber-physical computer (CPC), an intelligent edge terminal designed to coordinate operators, vehicles, robots, and materials involved in PL tasks. The CPC continuously collects Internet of Things (IoT) signals and extracts semantic-level relationships among PL resources, constructing a resource semantic graph that forms the basis for cyber-physical twinning. Upon receiving a new resource request, the CPC identifies relevant nodes to generate a corresponding spatial-temporal subgraph and performs subgraph reasoning by integrating contextual information with its local knowledge memory. Informed by task-specific insights distilled from prior expert decisions, the CPC recommends a prioritized allocation plan to the manager and enables interactive refinement using a large language model. To validate the proposed approach, we conduct comparative experiments across four simulated environments representing typical PL scenarios with varying degrees of dynamicity, along with a real-world case study at an air conditioning equipment manufacturer. Results demonstrate that the CPC, empowered by subgraph reasoning, outperforms existing methods in punctuality rate and delivery distance.