The wide application of information technology leads to the rapid growth of network information,which triggers information overload and confusion,making it difficult for people to find useful data when searching,and the related research on recommender systems thus arises. Although the book retrieval system based on traditional search engine technology has high coverage,it cannot accurately reflect readers' preferences,resulting in low accuracy of book recommendation results. Aiming at the above problems,a Bayesian network-based intelligent recommendation algorithm for segmented books is proposed. First,the association rule algorithm is used to mine the questionnaire research data to find the association between readers and their favorite book types. Second,the results mined by the association rule algorithm are analyzed in depth. Finally,a personalized book intelligent recommendation model is established using Bayesian network. The experimental results show that the method improves the accuracy and reliability of book recommendation results,and can effectively mine readers' reading preferences,simplify the book recommendation process,and achieve the purpose of personalized book recommendation for different groups and types of readers.
关键词
贝叶斯网络/关联规则挖掘/分众化/图书智能推荐
Key words
Bayesian networks/association rule mining/audience demassification/intelligent book recommendations
维普
万方数据