中文摘要：

随着云计算的发展，互联网上涌现出越来越多的功能相同但服务质量（QoS）不同的Web服务．基于服务质量的服务推荐，旨在从这些等功能服务中挑选出满足用户服务质量需求的服务，已成为服务计算领域的一个热门课题．由于极少有用户曾调用过所有候选服务，推荐系统将面临服务质量缺失的问题，因此，基于协同过滤的思想，提出一种服务质量预测算法RST．与以往算法相比，RST算法利用反向预测机制解决数据稀疏问题，提高了预测准确度．此外，RST算法基于用户对推荐结果的反馈，自动建立与维护信任度模型，可动态改善预测效果．最后，基于真实的数据集，验证RST预测算法的效果，并衡量各参数对预测结果的影响．

英文摘要：

With the development of cloud computing, there are increasing numbers of alternative Web services occurring on Internet, which provide the same functionality but differ in quality properties. QoS-based （ Quality of Service } service recommendation, with the goal to select web services from each set of functionally-equivalent services to satisfy end-to-end QoS requirements, is becoming an important issue of service-oriented computing. For the reason that a user can hardly have invoked all Web services, there are many missing QoS values of services to the consumer. In this paper, we propose a QoS prediction approach RST based on Collaborative Fil- tering. Meanwhile ~ a mechanism named Reversed Prediction is proposed to reduce the influence of data sparsity. In addition, to im- prove the accuracy of QoS prediction dynamically, we make full use of users＇ feedbacks for recommendation, maintian Trust model between users automatically. Experiment results of QoS prediction demonstrate that our approach outperforms existing methods for ac- curacy. Moreover, we evaluate the impact of each parameter in our QoS prediction system.