Collaborative filtering recommendation method and system based on user portrait clustering and storage medium

The invention provides a collaborative filtering recommendation method and system based on user portrait clustering and a storage medium, and the method comprises the steps: obtaining user data whichcomprises attribute data and behavior data; characterizing the user data to form user characterization information; performing dimension reduction compression on the user representation information toform a low-dimensional user portrait; clustering the low-dimensional user portraits by adopting a clustering method to form a user interest cluster; for the target user, recommending the target userby adopting a user-based collaborative filtering method in the interest cluster where the target user is located. According to the method, the change of user behaviors along with time information is considered, the inherent attribute information of the users, past behaviors of the users and short-term behaviors of the users are adaptively fused, the users are clustered according to low-dimensionaluser portraits, collaborati