The present invention may comprise: a step for learning patent documents stored in a patent database by using machine learning technology, establishing a first classification criterion on the basis of the degree of similarity between the patent documents, and generating a basic classification model for classifying the patent documents on the basis of the first classification criterion; a step for generating a patent pool including a plurality of patent documents on the basis of a search and/or selection input of a user; a step for receiving a classification input of the user, and classifying the plurality of patent documents included in the patent pool according to the classification input; a step for predicting a second classification criterion for the user to classify the plurality of patent documents on the basis of the degree of similarity between the classified patent documents; and a step for classifying, on the basis of the basic classification model and the second classification criterion, the remaining patent documents which have yet to be classified in the patent pool.
展开▼