Information recommendation service is one of important functions of digital library, aiming at the problem that book recommendation service exists the insufficient requirement mining of service object information in the current university library, personalized book recommendation method based on ontology information and collaborative filtering algorithm (abbreviated as OI-CFA algorithm) is proposed. Firstly, this paper discusses the necessity of collaborative recommendation in digital library, introduces main methods and technology based on collaborative filtering recommendation system. However, there are several problems that are data sparse and new item forecast with collaborative filtering recommendation method based on item. In order to solve these problems, this paper introduced an integrated similarity algorithms of structured semantic information based on OI-CFA. Extracting the semantic information of items including knowledge representation based on ontology, through ontology learning, the specified domain ontology is constructed. Compared with the traditional collaborative filtering algorithm and SVM, experimental results show that this method can not only solve the problems caused by the item-based collaborative filtering algorithm, but also improve the accuracy of recommendation.