基于网格计算框架的Web信息提取系统的研究  

THE RESEARCH ON WEB INFORMATION EXTRACTION SYSTEM BASED ON GRID COMPUTING FRAMEWORK

作　　者：施佺[1] 肖仰华[2] 

机构地区：[1]南通大学计算机科学与技术学院,江苏南通226019 [2]复旦大学计算机与信息技术系,上海200433

出　　处：《计算机应用与软件》2007年第10期56-57,98,共3页Computer Applications and Software

基　　金：江苏省高校自然科学基金资助(05KJB520107);南通市科技项目基金资助(S40041)。

摘　　要：大规模Web信息提取是面向Internet非规范知识处理中的一个典型问题。以网格计算框架为实现平台,设计了分层的网格应用系统架构,针对Web信息提取中链接分析和信息提取功能,描述了面向一般网格计算框架的资源调度与编程模型。最后结合Web信息提取系统的实验结果,给出了网格应用系统的评价标准。Web Information Extraction System is known as a typical problem in informal knowledge processing. Based on grid computing framework, a layered architecture of Grid Application System is provided to solve such kind of problem. The general principle for grid resource scheduling and grid programming is proposed to implement linkage analysis and information extraction. Finally, several evaluation criterions for the performance of the Grid Application System are discussed and the analytical results based on the experiment data in Web Information Extraction System are presented.

关 键 词：网格 计算网格 WEB信息提取 网格资源调度 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]