Share Email Print
cover

Proceedings Paper

A knowledge-based agent prototype for Chinese address geocoding
Author(s): Ran Wei; Xuehu Zhang; Linfang Ding; Haoming Ma; Qi Li
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

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 human's 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.

Paper Details

Date Published: 11 November 2008
PDF: 10 pages
Proc. SPIE 7146, Geoinformatics 2008 and Joint Conference on GIS and Built Environment: Advanced Spatial Data Models and Analyses, 71461D (11 November 2008); doi: 10.1117/12.813140
Show Author Affiliations
Ran Wei, Peking Univ. (China)
Xuehu Zhang, Peking Univ. (China)
Linfang Ding, Peking Univ. (China)
Haoming Ma, Peking Univ. (China)
Qi Li, Peking Univ. (China)


Published in SPIE Proceedings Vol. 7146:
Geoinformatics 2008 and Joint Conference on GIS and Built Environment: Advanced Spatial Data Models and Analyses
Lin Liu; Xia Li; Kai Liu; Xinchang Zhang, Editor(s)

© SPIE. Terms of Use
Back to Top