基于加权贝叶斯的数字图书资源个性化推荐方法研究

Research on Personalized Recommendation Method of Digital Book Resources Based on Weighted Bayes

传统图书资源推荐方法的推荐准确率较低,难以实现精细化和个性化推荐。因此,提出基于加权贝叶斯的数字图书资源个性化推荐方法。首先,采集数字图书信息后,利用贝叶斯分类器对个性化图书实施分类处理。其次,设置情景化偏好模块,并计算情景下读者的相似度。最后,根据相似度计算结果,利用加权贝叶斯算法为读者推荐书籍。实验结果表明,与传统方法相比,该方法的推荐准确度高且稳定性强。

The accuracy of traditional book resource recommendation methods is low,making it difficult to achieve refined and personalized recommendations.Therefore,a weighted Bayesian based personalized recommendation method for digital book resources is proposed.Firstly,after collecting digital book information,a Bayesian classifier is used to classify personalized books.Secondly,set up a situational preference module and calculate the similarity of readers in the context.Finally,based on the similarity calculation results,a weighted Bayesian algorithm is used to recommend books to readers.The experimental results show that compared with traditional methods,this method has high recommendation accuracy and strong stability.