Design and Implementation of a Knowledge Graph-Based Communication Jamming System

This paper proposes a knowledge graph-based intelligent decision-making framework for real-time communication countermeasures in complex electromagnetic environments. By fusing multimodal data such as spectrum signals, device status, and historical records, a structured knowledge graph is constructed to formalize entities like jammers, signals, and their relationships such as suppression capabilities. Graph embedding TransE and Graph Neural Networks GraphSAGE are integrated to model jamming paths and predict optimal strategies via semantic similarity analysis. Experimental results demonstrate that the framework achieves a Top-1 accuracy of 81.5% in jamming path prediction, with robust performance under varying training data scales. The proposed method combines knowledge-driven reasoning and data-driven learning, enhancing situational understanding and adaptive strategy generation for electronic warfare. This work provides a feasible pathway for intelligent decision-making in dynamic adversarial scenarios.