Integrating IRT and Knowledge Graphs for the Selection of Cybersecurity Talent

In recent years, the cybersecurity landscape has become increasingly severe, with a significant shortage of skilled professionals in the field. Against this backdrop, cultivating high-quality cybersecurity talent has become an urgent task. This paper proposes an innovative method that integrates Item Response Theory (IRT) and knowledge graphs to address this challenge. The core innovation lies in the fusion of IRT with knowledge graph technology to provide personalized, adaptive assessments. By leveraging cognitive diagnosis theory and adaptive theory, the method assesses participants' cognitive levels while considering factors such as psychological state, professional skills, and cognitive ability. This approach intelligently adjusts the difficulty of questions in real-time based on the participant's performance. Furthermore, the incorporation of knowledge graph technology allows for a deeper analysis of the relationships between different knowledge domains. Based on these comprehensive insights, personalized learning suggestions and strategies are formulated, enabling continuous tracking of talent development. This adaptive method offers a scientific and effective pathway for the cultivation and selection of cybersecurity professionals.