一种有效的深网入口识别方法.pdfVIP

Vol. 38 No. 10 第 38 卷第10 期 计算机科学 2011 年 10 月 Computer Science 。ct 2011 一种有效的深网入口识别方法 吴春明1.2 谢德体2 (西南大学计算机与信息科学学院 重庆 400715) (西南大学资源环境学院 重庆 400715)2 摘要 深网入口自动识别是深网数据集成的前提和基础。由于农单在设计上具有较大的随意性，使得深网入口缺 乏统一的构建标准，难以利用确定性的规则对其进行判断。首先基于统计特征，抽取了部分表单属性作为深网入口与 非深网入口的可区分特征，在此基础上，提出了一种利用神经网络进行深网入口自动识别的方法。不同于基于规则的 判断方法，神经网络是被训练的.不需要任何先验知识，这种特性使其非常适合于对具有复杂表现形式的深网入口进 行判定。实验结采表明了该方法的有效性. 关键词深网入口，神经网络，特征抽取，机器学习 中固法分类号 TP391 文献标识码 A Effective Approach to D四p Web Entri四 Identification wu Chun-ming ,.2 XIE De-ti2 (Coll句e of Computer and Information Science. Southwest University.Chongqing 400715 •China) I (Coll喀e of Resources 缸ui Environment. Southw四t University.Chongqing 400715.China)2 Abstr田t Automatic identification of deep Web entries is the basis of deep Web data integration. Owing to the subjec- tivity of form design.deep Web entries lack unified standard and it is difficult to judge whether the form is a deep Web entry by the definite rules. Based on the statistics. this paper first chose several form attributes as the defining features , which αn distinguish searchable fo口ns from non-searchable forms. Then.an entry identification algorithm was proposed by using neural network. Unlike previous approaches.neural network 饵n be trained. which is very suitable for entry i- dentification of the deep Web. The experimental results show that our proposed algorithm αn be an effective way in au- tomatic identification of the deep Web. Keywor由Deep Web entries.Neural network.Feature extraction. Machine leaming 总体来说.突破性的研究成果相对较