测绘学报 ›› 2015, Vol. 44 ›› Issue (1): 99-107.doi: 10.11947/j.AGCS.2015.20130205

• 地图学与地理信息 • 上一篇    下一篇

地址树模型的中文地址提取方法

亢孟军, 杜清运, 王明军   

  1. 武汉大学资源与环境科学学院, 湖北 武汉 430079
  • 收稿日期:2014-01-08 修回日期:2014-10-05 出版日期:2015-01-20 发布日期:2015-01-22
  • 作者简介:亢孟军(1983-), 男, 讲师, 主要研究方向为电子地图、地理编码. E-mail: mengjunk@gmail.com
  • 基金资助:
    国家自然科学基金(41201403)

A New Method of Chinese Address Extraction Based on Address Tree Model

KANG Mengjun, DU Qingyun, WANG Mingjun   

  1. School of Resources and Environmental Science, Wuhan University, Wuhan 430079, China
  • Received:2014-01-08 Revised:2014-10-05 Online:2015-01-20 Published:2015-01-22
  • Supported by:
    The National Natural Science Foundation of China(No.41201403)

摘要: 地址是一种对个体地域空间位置信息的编码方法.在我国,由于城市快速发展,地址规划相对落后,非标准地址大量存在.本文在分析标准地址模型空间约束关系类型的基础上,提出了一种基于地址树模型的中文地址提取方法.该模型以拓扑关系作为空间约束关系是否一致的判断标准,可以从非标准地址中提取标准地址,并剔除非标准和错误地址元素.试验证明,该方法有较高的地址匹配率.

关键词: 标准地址, 地理编码, 地址树, 中文地址提取, 地址匹配率

Abstract: Address is a spatial location encoding method of individual geographical area. In China, address planning is relatively backward due to the rapid development of the city, resulting in the presence of large number of non-standard address. The space constrain relationship of standard address model is analyzed in this paper and a new method of standard address extraction based on the tree model is proposed, which regards topological relationship as consistent criteria of space constraints. With this method, standard address can be extracted and errors can be excluded from non-standard address. Results indicate that higher math rate can be obtained with this method.

Key words: standard address, geocoding, address tree model, Chinese address extraction, address math rate

中图分类号: