基于强化学习的Deep Web数据提取方法  

Retrieving Deep Web Data Based on Reinforcement Learning

作　　者：林治[1] 王睿[1] 

机构地区：[1]扬州职业大学信息工程学院,扬州225009

出　　处：《计算机与数字工程》2015年第2期299-302,共4页Computer & Digital Engineering

摘　　要：随着Web的飞速发展,Deep Web中蕴藏着海量高质量数据,如何高效地提取这些数据极具挑战。由于Deep Web的动态性,其数据经常处于频繁更新的状态,而用户总是希望获得最新鲜的内容。为此,论文在分析Deep Web数据变化特性的基础上,建立一个Deep Web数据生成模型,然后,提出一种强化学习的Deep Web数据提取方法。实验表明,该方法具有较好的数据提取效率,可有效提高Deep Web数据集成服务质量。With the rapid development of the Web ,there are massive high‐quality data in Deep Web .How to efficiently retrieve these data is challenging .Because Deep Web is dynamic ,the data are always in frequently update status ,and users always want to obtain the freshest content .In this paper ,through analyzing the variety characters of Deep Web ,a Deep Web data generation model is established ,and then a Deep Web data retrieval method based on reinforcement learning is proposed . Experimental results show that this method has better data retrieval efficiency ,which can effectively improve the service quality of Deep Web data integration .

关 键 词：DEEP WEB 强化学习 数据提取 更新频率 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]