| 基于中文网页的综合联系信息提取系统的设计与实现 |
| |
| 引用本文： | 郭威,纪星. 基于中文网页的综合联系信息提取系统的设计与实现[J]. 湖北汽车工业学院学报, 2012, 0(4): 72-75 |
| |
| 作者姓名： | 郭威 纪星 |
| |
| 作者单位： | 湖北汽车工业学院经济管理学院;湖北省金蚂蚁网络有限公司 |
| |
| 基金项目： | 湖北汽车工业学院大学生创新项目(SJ201025);湖北省教育厅千人计划项目(XD2010359);湖北省教育厅人文社科项目(2010B186) |
| |
| 摘 要： | 为满足用户希望通过搜索引擎查询综合联系信息的需求,设计了基于中文网页中的综合联系信息提取系统。研究与阐述了在搜索引擎返回结果的基础上提取有关联系方面的综合信息(例如邮箱、电话等)的实现方法,并通过构建特有的内置"实体"判断、SV值算法提高系统的提取精度。
|
| 关 键 词： | 信息抽取 网页分类 正向追加 查询关联度 实体判断 |
Design and Implementation on Extraction System of Comprehensive Information Based on Chinese Web |
| |
| Guo Wei,Ji Xing. Design and Implementation on Extraction System of Comprehensive Information Based on Chinese Web[J]. Journal of Hubei Automotive Industries Institute, 2012, 0(4): 72-75 |
| |
| Authors: | Guo Wei Ji Xing |
| |
| Affiliation: | 2(School of Economics and Management,Hubei Automotive Industries Institute,Shiyan 442002,China) |
| |
| Abstract: | In order to meet the needs of user inquiry into contact information by search engines,the extraction system of comprehensive information was designed based on Chinese Web.The way of extracting comprehensive information based on the search engines was discussed such as mail,telephone and so on.The system accuracy was improved by this unique combination of built-in "entity" to determine and SV value. |
| |
| Keywords: | information extraction page classification additional positive inquiry correlation entity to determine |
| 本文献已被 CNKI 等数据库收录！ |
