In view of the threat of coal and gas outburst in coal mine production safety and the complexity of the influencing factors, this paper collects the relevant data of outburst, analyzes and rationally selects the main indicators of the mine coal and gas outburst. It also clusters the coal and gas outburst based on the fuzzy mathematics K-means clustering method, and obtains a reasonable classification and clustering center matrix by using the least squares method for the technical staff’s reference to predict whether there will be the coal and gas outburst and make preparations for the sudden accident. It shows that the results of this model evaluation agree with the actual situation, and provides a scientific theory and method for the outburst risk assessment of coal and gas of hi-gas coal mines.