LAUSR

The information period has significantly changed in the use of warfare patterns, and modern operations require rapid operational planning and decision making under different combat conditions. Weapon-target recommendation is essential for the automation of military command and control, which is of tremendous military significance for the eventual outcome of warfare. In this paper, we study the weapon-target recommendation problem in heterogeneous combat networks (HCNs) and propose a united framework named meta-path-based HCN weapon-target recommendation (MPWTR). The MPWTR not only considers the topological information of an HCN, but also explores the semantic similarity hidden in the various meta-paths. Specifically, first, the weapon-target-related meta-paths in an HCN are extracted and defined to calculate the similarities in the weapon-target pairs. Subsequently, a weapon-target recommendation model is presented by assigning each meta-path with different preferences and combining all the meta-path similarities by an optimal process. Finally, we conduct considerable experiments on an HCN case to demonstrate the feasibility and effectiveness of the proposed MPWTR. This paper compares several baseline methods and it shows that the MPWTR can achieve very good performance, which is superior to the baselines. The results provide useful insight into the operation guidance and optimal planning and scheduling of the allocated weapon resources.