Abstract: Collaborative filtering algorithm is one successful personalized recommendation technology, and is extensively used in many fields. Unfortunately, the efficiency of the method declines linearly with the number of users and items. To solve these problems, combining the two algorithm’s characteristics and advantages, a new hybrid algorithm is proposed based on the content and network structure, it improves the defects of the current recommendation algorithms and gives realization process of algorithm and experimental results.

Key words: personalized recommendation algorithm, contentbased, network structurebased, hybrid recommendation algorithm