地址树模型的中文地址提取方法

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。

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

Address is a spatial location encoding method of individual geographical area .In China , address pl anning is rel atively backward due to the rapid development of the city ,resulting in the presence of l arge number of non‐standard address .The space constrain rel ationship 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 rel ationship as consistent criteri a 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 .