Design And Implementation Of UE-Based Recommendation System

With the development of information technology,people gradually from the lack of information era into the era of information overload. For users, when they don’t know what they really want, it is difficult to find the information of interest from a lot of clutter.In this context, it is recommended that the system came into being, is considered to be an effective way to solve the problem of information overload. Contact the recommendation system users and information on the one hand to help users find valuable information, on the other hand so that the information can be displayed in front of the user interested in it, in order to achieve a win-win situation of information consumers and information producers.With the rise of the video industry, network video rapid growth in both user scale and depth. As the rapid increase in the amount of video, the video industry is also faced with the problem of information overload. Personalized recommendation system have been widely used on e-commerce sites, video navigation websites, music, radio sites, and brought great commercial value. User scale is increasing more stringent requirements in the Recommended system’s performance, the recommended system is facing a cold start and sparse data, user interest offset and other difficult problems.The evaluation criteria of user interest is fuzzy, user personalization recommended evaluation criteria fuzzy and the recommendation results poorly targeted also quickly become the problems encountered during this stage the major recommended website.The user experience is a purely subjective user products built up feelings, to accurately assess the user experience is not an easy thing.For the problems of the existing recommendation system, combined with the practical application of the combination of the user experience evaluation and recommendation system, design and video recommendation system based on item-based collaborative filtering.First of all we survey the existing mature online recommendation system,analysis of each system implementation methods and recommended effect and user experience.Develop implementations of the system combined with the evaluation of the user experience; research formulation of the existing user experience metrics;compared the dominant scoring system with implicit rating system to select and design the scoring system of user interest;designed an user behavioral data collection system, including front-end collection module and back-end storage module receives the data format, data storage solutions, the study of the Subscriber Identity Module; user behavior data and user interest model conversion module; combined with the actual scene select appropriate recommendation algorithm, and improved the performance of the recommendation algorithm based on forgetting curve; designed and implementation the rendering module; designed test module to verify the effectiveness of the present system.