Abstract
With the development of the massive amount of web services, the popular research area is involved with the solution to select the required services according to the personal preference for different users. To solve these urgent problems, a user preference awareness k-neighbour optimised selection algorithm is proposed in this paper. Initially, the potential interest of the user is explored by using association rules method of data mining technology. Then, an expanded LDA model is used to analyse the influence on user preference calculation for different types of services caused from the functional attributes of web services. To improve the accuracy of the service selection result, the ant colony algorithm is modified to optimise the service selection process of k-neighbours in traditional collaborative filtering. The experiment shows that our proposed method leads to a higher accuracy and coverage than the traditional web service selection methods based on the real service set.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call