Abstract: In the traditional Item-based collaborative filtering algorithm, the project similarity is not related to the target user, which may lead to the calculated project similarity, which is not accurate for the target user. To solve this problem, a perceptual user's Item-based collaborative filtering algorithm was proposed. The algorithm takes into account the impact of the target user on the similarity of the project, and sets up different target similarity for different users. The MovieLens data set is used as the test data and the average absolute error is taken as the evaluation index. The experimental results showed that the algorithm can improve the accuracy rate effectively.