A relational triplet extraction method for constructing network security knowledge graph
Guanlin Chen, Jennifer Xu, Tieming Chen, Wujian Yang, Wenyong Weng · International Journal of Sensor Networks · 2025
Faced with the challenges brought by the rapid growth of cyber threat intelligence (CTI) data, traditional information extraction methods have shown limitations regarding efficiency, accuracy, intelligence, and scalability. To help network security experts develop more solid security strategies based on reliable intelligence and improve network security defence and deterrence capability, this paper focuses on constructing a CTI knowledge graph based on a relational triplet. Besides, this paper provides a ternary extraction method for constructing a network security knowledge graph associated with a sensor system, which reduces the labour consumption of constructing a network security knowledge graph. Compared with the traditional method, the method is more efficient and accurate and can improve the performance of extracting entity relationships from complex text.