Collaborative filtering method is an important method of personalized recommendation, while the method often resulting in the problem of low efficiency with the increase in the number of users. To solve this problem, this paper presents a presents a personalized recommendation method with the adoption of user classification and collaborative filtering algorithm. Firstly, the huge users are classified into several groups according to a rule-based classification method. Then, on the premise of the accuracy of recommendation, the local neighbor users are discovered for users. Finally, based on the discovered local neighbors, personalized recommendation conducted. Experimental results show that with the adoption of a rule-based user classification, collaborative filtering algorithm has been significantly improved on the premise of the accuracy of recommendation.