A Knowledge-based Agent Prototype for Chinese Address Geocoding

摘要：

Chinese address geocoding is a difficult problem to deal with due to intrinsic complexities in Chinese address systems and a lack of standards in address assignments and usages.In order to improve existing address geocoding algorithm,a spatial knowledge-based agent prototype aimed at validating address geocoding results is built to determine the spatial accuracies as well as matching confidence.A portion of humans knowledge of judging the spatial closeness of two addresses is represented via first order logic and the corresponding algorithms are implemented with the Prolog language.Preliminary tests conducted using addresses matching result in Beijing area showed that the prototype can successfully assess the spatial closeness between the matching address and the query address with 97％ accuracy.

关键词： Address Geocoding Address Validation Knowledge Based Agent Spatial Ontology Inference Rules

作者: Ran Wei Xuehu Zhang Linfang Ding Haoming Ma Qi Li

作者单位: Center for Spatial Intelligent Computing Institute of Remote Sensing and Geographic Information Syst Institute of Remote Sensing and Geographic Information Systems Peking University,Beijing 100871,P.R.

会议类型: 国际会议

会议名称: 第16届国际地理信息科学与技术大会(16th International Conference on GeoInformatics and the Joint Conference)

会议地点: 广州

会议语种:英文

在线出版日期: 2008-06-28（万方平台首次上网日期，不代表论文的发表时间）