The invention provides an intelligent customs declaration form filling method based on historical data mining. The method comprises the following steps: preprocessing historical data of a customs declaration, combining a header with form data, and removing irrelevant fields; designing and realizing a correlation analysis algorithm of each field based on a specific value; designing a tree structure, constructing a dynamic tree based on the correlation of each field, and storing the dynamic tree; and intelligently recommending filling contents according to the generated dynamic tree. And periodically and automatically maintaining and updating the data according to the newly input data. According to the correlation analysis algorithm and the dynamic tree designed by the invention, intelligentfilling of other filling fields can be carried out according to the current input content of the user, and the accuracy is relatively high. The customs declaration system has strong generalization and self-learning capabilities, customs declaration efficiency can be greatly improved, and manpower and material resources are saved for customs declaration organizations and customs declaration enterprises.