摘要
针对POI数据的匹配更新工作成为目前各大地理信息服务平台亟需解决的问题,该文通过对POI数据的名称、地址及经纬度等主要属性的研究,提出了一种基于多属性综合相似度计算的同名POI实体识别的方法,能够有效解决多源POI数据的匹配更新慢及准确率低的难题。实验证明,相比于传统的文本相似度匹配方法,提高了POI数据的同名实体识别效率及精度。
With the in-depth application of the government,enterprises and the public in various aspects,the matching and updating of POI data had become an urgent problem to be solved by the major geographic information service platforms.Aiming at the main attributes of POI data,such as name,address,longitude and latitude,this paper proposed a method of POI identical entity recognition based on multi-attribute comprehensive similarity calculation,which effectively solved the problem of slow update and low accuracy of multi-source POI data matching.Experiments showed that compared with the traditional text similarity matching method,this method improved the efficiency and accuracy of identical entity recognition of POI data.
作者
李鹏飞
张亚
孙钦珂
LI Pengfei;ZHANG Ya;SUN Qinke(Faculty of Geomatics,Lanzhou Jiaotong University,Lanzhou 730070,China;National-Local Joint Engineering Research Center of Technologies and Applications for National Geographic State Monitoring,Lanzhou 730070,China;Gansu Provincial Engineering Laboratory for National Geographic State Monitoring,Lanzhou 730070,China)
出处
《测绘科学》
CSCD
北大核心
2021年第9期178-183,共6页
Science of Surveying and Mapping
关键词
POI数据
同名实体识别
文本相似度
综合相似度计算
POI data
identical entity recognition
text similarity
comprehensive similarity calculation
作者简介
李鹏飞(1995-),男,甘肃武威人,硕士研究生,主要研究方向为空间数据挖掘与分析。E-mail:865455663@qq.com;通信作者:张亚,博士研究生,E-mail:zhangya1519@163.com。
