In this paper, the characteristics of health safety risk and key issues of health safety management of construction industry in China have been analyzed first. Then, to make construction safety management and supervision available, health safety risk assessment model of construction industry is mainly converted into how to get the controlling indicator and health safety risk classification. Because of the dynamic nature of construction health safety development and the specificity of sample data, an intelligent assessment model based on support vector machines is presented to improve the assessment process. The proposed model takes advantage of SVMs abilities to solve the problem with small samples and nonlinear regression. Furthermore, the proposed approach is shown more accurate for prediction in the case of real-word application.