Abstract: Aiming at the problems of low efficiency and poor accuracy of traditional safety awareness assessment methods in the recruitment process of coal state-owned enterprises, this study explores the application potential of artificial intelligence, especially the large language model, breaks through the limitations of traditional interview subjectivity and personality test, and proposes a new method based on artificial intelligence to analyze open safety questionnaire. In the system construction stage, the high safety performance employees and ordinary safety performance employees in the organization enterprise complete the questionnaire survey, use the AI big model to analyze the answers, and construct the classification benchmark of personnel safety behavior tendency. In the application stage, after completing the same set of questionnaires and analyzing the AI model, the applicants classified the types of safety behavior tendencies and generated a safety awareness assessment report compared with the benchmark. The research results show that this method can improve the evaluation efficiency, effectively identify the safety decision-making characteristics of candidates, and provide new ideas and technical support for the front-end screening of high safety literacy talents in coal state-owned enterprises.