测绘通报 ›› 2022, Vol. 0 ›› Issue (4): 96-100.doi: 10.13474/j.cnki.11-2246.2022.0117

• 学术研究 • 上一篇    下一篇

基于多特征相似性的多源POI匹配方法

罗国玮, 叶嘉媛, 王金凤   

  1. 南宁师范大学地理科学与规划学院, 广西 南宁 530000
  • 收稿日期:2021-05-11 出版日期:2022-04-25 发布日期:2022-04-26
  • 通讯作者: 叶嘉媛。E-mail:409301906@qq.com
  • 作者简介:罗国玮(1979-),男,博士,教授级高级工程师,研究方向为智慧城市空间信息服务、智慧国土空间规划。E-mail:lgw@nnnu.edu.cn
  • 基金资助:
    中央引导地方科技发展专项(地方科技创新项目示范类)项目(桂科ZY18164006)

Multi-source POI matching method based on multi-feature similarity

LUO Guowei, YE Jiayuan, WANG Jinfeng   

  1. School of Geographic Science and Planning, Nanning Normal University, Nanning 530000, China
  • Received:2021-05-11 Online:2022-04-25 Published:2022-04-26

摘要: 本文针对多源POI的特征差异性导致同名对象识别难的问题,提出了一种多特征相似性的多源POI匹配方法。兼顾空间与非空间属性,选取名称、位置、地址、分类4个特征进行相似度计算;采用层次分析法对各特征指标进行重要性分析,得到特征权值;根据总相似度对候选匹配对象进行筛选,以确定最终匹配对象。试验结果显示,该方法具有较高的匹配精度,更适用于多源异构POI数据的匹配,可满足多源POI数据的高效匹配需求。

关键词: 多源异构, POI, 多特征相似性, 匹配, 层次分析法

Abstract: Aiming at the problem that multi-source POI feature differences lead to the difficulty of identifying the same objects, this paper proposes a multi-source POI matching based on feature similarity method. Considering POI spatial and non-spatial attributes, four features including name, location, address and classification are selected for similarity calculation. The importance of each feature index is analyzed by analytic hierarchy process, and the feature weight information is obtained. The candidate matching objects are screened according to the total similarity to determine the final matching comparison. Experimental results show that the proposed method has high matching accuracy and is more suitable for multi-source heterogeneous POI data matching. It can meet the demand of efficient matching of multi-source POI data.

Key words: multi-source heterogeneous, POI, multi-feature similarity, matching, analytic hierarchy process

中图分类号: