主题网络爬虫技术在高速公路信息采集中的应用  

Application of the Topic Web Crawler for Obtaining the Highway Information

作　　者：张芳[1] 王培进[1] 

机构地区：[1]烟台大学计算机与控制工程学院,山东烟台264005

出　　处：《烟台大学学报（自然科学与工程版）》2017年第3期255-260,共6页Journal of Yantai University(Natural Science and Engineering Edition)

基　　金：烟台市科技项目(2015ZH057)

摘　　要：主题网络爬虫技术是获取特定主题的有效手段,其搜索算法的性能直接决定着搜索结果的优劣.文章综合分析了现有的网络信息搜索算法,并将遗传算法思想应用到主题网络爬虫技术中,提出了非贪婪遗传主题网络搜索算法.实验结果表明,该算法能够采集到更多主题相关度高的网页,提高信息采集正确率,快速高效获取交通相关的信息.In the Topic web crawler technology as an effective approach to obtain a specific topic, the performance of the search algorithm directly determines the strengths and weaknesses of the search results. The existing network inlimnation searching algorithm is analyzed, and the idea of genetic algorithm is applied to the technology of topic web crawler, and a non greedy genetic algorithm is proposed. The experimental results show that the algorithm can acquire more topic related web pages, improve the accuracy of the information collection, and get traffic related in- formation quickly and efficiently.

关 键 词：主题网络爬虫 遗传算法 非贪婪策略 主题相关度 

分 类 号：O177.91[理学—数学]