A Supply–Demand Balance Guided Hierarchical Reinforcement Learning Approach for Truck-Cargo Matching

Truck-cargo matching is one of the core tasks of online freight platforms, where the primary objective is to optimally assign each cargo task to the most suitable truck. The existing matching strategies seek to maximize total transported weight of cargoes by increasing the number of truck-cargo pairings. However, these strategies fail to ensure global matching pair maximization across all regions due to the heterogeneous spatial distribution of truck supply and cargo transporting demand. This limitation necessitates the incorporation of regional supply–demand gap prediction into the matching process. Two critical challenges emerge in achieving optimal matching: (1) the prediction accuracy of supply–demand gaps is influenced by multiple complex factors, and (2) the multi-objective optimization conflicts within current matching decisions may adversely impact subsequent matching performance. To address these challenges, we propose a hierarchical reinforcement learning framework for multi-objective truck-cargo matching, comprising two key components: a supply–demand gap prediction module and a multi-objective optimization matching module.For accurate supply–demand gap prediction, we develop a hypergraph attention network model incorporating an adaptive confidence interval optimization mechanism to capture complex relationships among various predictive factors. Furthermore, to mitigate negative effects of multi-objective conflicts on long-term matching performance, we design a hierarchical deep Q network model that dynamically adjusts objective weights based on predicted long-term benefits. Extensive experiments conducted on two real-world logistics datasets demonstrate that our proposed method achieves a 10.7% higher competitive ratio compared to state-of-the-art approaches, validating the effectiveness of our supply–demand balance guided matching strategy in practical operational scenarios.