Safety is a primary concern for the civil aviation industry. Airlines record high-frequency but potentially low-severity unsafe events, i.e., incidents, in their reports. Over the past few decades, civil aviation security practitioners have made efforts to analyze these issues. The information in incident reports is valuable for risk analysis. However, incident reports were inefficiently utilized due to incoherence, large volume, and poor structure. In this study, we proposed a technical scheme to intelligently classify and extract risk factors from Chinese civil aviation incident reports. Firstly, we adopted machine learning classifiers and vectorization strategies to classify incident reports into 11 categories. Grid search was used to adjust the parameters of the classifier. In the preliminary experiment, the combination of the extreme gradient boosting (XGBoost) classifier and the occurrence position (OC-POS) vectorization strategy outperformed with an 0.85 weighted F1-score. In addition, we designed a rule-based system to identify the factors related to the occurrence of incidents from 25 empirical causes, which included equipment, human, environment, and organizational causes. For cause identification, we used rules obtained through manual analysis with keywords and discourse. F1-score above 0.90 was obtained on the test set using the causes identification model derived from the training set. The proposed system permits insights into unsafe factors in aviation incidents and prevents reoccurrence. Future works can proceed on this study, such as exploring the causal relationship between causes and incidents.