The Application Of Collaborative Filtering Recommendation Technology Based On Cloud Model And Ants Clustering In Book Recommendation

With the continuous expansion of network and library resources,in the face of the exponential increases in the amount of data,if there is no system or technology to process the data,readers would be difficult to find their interesting books.With the development of personalized book recommendations technology,library management is automated and personalized,so that readers can found their own books and information in the vast library resources,which helps to improve the utilization of resources in the library,and to share resources for real.In personalized recommendation systems,collaborative filtering is more widely used and one of the most successful technology,but with the increase of users and resource,collaborative filtering is also facing many problems,like the sparse data,similarity measurement,cold start problems.Similarly,books,journals,magazines,newspapers and other information in library are everywhere,the longer they accumulate,the greater the amount of information is,this is an enormous challenge for recommended system' performance.In response to these challenges,this paper mainly does the following works based on the improved algorithms:First,by analyzing the problems of traditional collaborative filtering technology,this paper presents a cloud-filled method based on cloud model,which is much more different from the traditional filling algorithm for considering statistical characteristics of projects;Experimental results show that the proposed algorithm can effectively improve cold start problems.Second,the traditional ants clustering were studied;this paper presents an improved Ant Colony clustering algorithm,improving the quality and efficiency of clustering.Third,the books recommended technology were studied,Using Ant Colony clustering and cloud-filled for collaborative filtering,and applying the algorithm to intelligent recommendation of books.Experimental results show that this method solve the problem of data sparseness and inefficient,improving the efficiency and accuracyForth,to verify its validity,this paper design experiments to prove the feasibility of the proposed book recommendation algorithm and efficiently.