论文部分内容阅读
移动互联网的快速发展和智能终端数量的迅速增长使得Internet服务更加密切地融入到人们的生活中,面向非专业用户的Mashup服务在移动计算环境下有着更广泛、迫切的需求,同时,用户行为过程中的上下文动态不确定性、用户行为模式复杂性和个性化特征等因素对传统Mashup技术提出了挑战.针对目前Mashup技术和研究中存在的问题,本文将关注点从离散的服务推荐扩展到Mashup构造与运行过程,提出一种新的基于迭代式自主构造的Mashup服务组合和运行模式,主要思想是对大量离散、孤立的历史执行轨迹进行挖掘处理,建立上下文相关和偏好相关的用户行为选择概率模型,为构造优化的个性化Mashup组合方案提供支持.分析和模拟实验表明,面对移动环境上下文动态性和普适性特点,本文方法能够有效简化Mashup构造过程中用户参与的复杂性,减少对用户专业知识的依赖;同时,在用户行为模式预测和Mashup服务构造与推荐方面能够获得比其他服务推荐或组合方法更好的效果.
With the rapid development of mobile Internet and the rapid growth of the number of intelligent terminals, Internet services are more closely integrated into people’s lives. Mashup services for non-professional users have broader and urgent needs in the mobile computing environment. Meanwhile, the user behavior process The uncertainty of the context, the complexity of the user behavior patterns and the personality characteristics of the traditional Mashup technology posed a challenge.For the current Mashup technology and the problems in the study, this article will focus on the discrete service recommendation extended to Mashup Structure and operation process of Mashup service, a new Mashup service composition and operation mode based on iterative autonomous construction is proposed. The main idea is to excavate a large number of discrete and isolated historical execution trajectories, and to establish context-related and preference-related user behavior selection probabilities Model to support the construction of an optimized and personalized Mashup scheme.The analysis and simulation experiments show that the proposed method can effectively simplify the complexity of user participation in Mashup construction and reduce the complexity of Users rely on professional knowledge; the same time, Mashup predict user behavior patterns and construction services and recommend possible to obtain the recommended terms than any other service or a combination of methods better results.