Spatiotemporal High-Utility Occupancy Mining for Multiple Unmanned Aerial Vehicle Mission Organization Preferences

Multi-unmanned-aerial-vehicle (multi-UAV) collaborative mission systems face critical scheduling challenges in complex dynamic environments due to insufficient dynamic adaptability, fragmented multidimensional features, and low computational efficiency. To address these issues, this paper proposes a mission organization preference mining framework based on the spatiotemporal high-utility occupancy mining (SHUOMining) algorithm. The framework integrates spatiotemporal and utility multidimensional features to construct high-utility time-series patterns with spatial information, revealing global correlations among mission deployment, temporal collaboration, and operational effectiveness. A dual-layer pruning strategy is introduced to reduce computational complexity, and a closed-loop verification mechanism combining Monte Carlo simulation ensures theoretical rigor and operational practicality. Experimental validation in a maritime antithreat target interception scenario demonstrates that the optimized mission plan reduces the damage rate to protected assets by 18.3% compared to traditional methods. The proposed approach provides an effective solution for intelligent multi-UAV scheduling in complex battlefield environments.