To improve the performance of Chinese text classification, a rule matching method based on rough set theory is proposed in this study. In the extracting process of textual features, the CHI statistical method is improved and the weight of the feature is scaled and discretized. It combines the discriminant matrix to achieve the attribute reduction and rule extraction for rough set theory, and uses rule pre-test method to optimize the decision parameters of rule matching to improve the effect of Chinese text categorization. The experimental results demonstrate that the categorization accuracy of the improved matching method is higher, and in the case of less training data, it can also achieve decent results