With the increasing number of micro-video community applications, social media platforms have started to attract more people through their built-in micro-video features. More and more people like to record and share their favorite people or events through micro-videos. The content of micro-videos is very diverse. If we can accurately obtain the preferred character of each user and the degree of preference for that character, we can be considered as being able to obtain the user’s preference more accurately. Therefore, it is necessary to study and implement a micro-video recommendation system. Currently, video-oriented recommendation algorithms mostly start from the following parts: user rating, video text description, video content, etc. The recommendation algorithm that starts with user ratings is similar to the recommendation algorithm of ordinary e-commerce platforms. Most of them will first ask users to rate the videos they have watched, and then find other users who also rate these videos and whose scores are closer to those of the target user, as the nearest neighbors of the target user, so as to obtain the user-item similarity matrix. The research goal of this paper is to design and implement a micro-video recommendation system that integrates social relationships in order to solve the current problem of micro-video information overload on social platforms, which makes it difficult for users to find videos that meet their preferences. We can get users’ preferences for video content by recognizing their portraits and their weights, and get their nearest neighbors and making video recommendations by improving the social relationship similarity, familiarity, and interest similarity between users. And through several experiments and a series of comparative experiments, it was confirmed that the algorithm has an advantage in the recommendation accuracy rate of the algorithm has some advantages.