A Polygon Constraint-based Multi-source Geocoding optimization method

Online geocoding platforms transform textual addresses into geographic coordinates, yet their outputs often exhibit substantial geocoding errors. Moreover, most multi-source geocoding approaches lack explicit spatial constraints, which limits the stability and spatial interpretability of fused results. To address this issue, this study proposes a Polygon Constraint-based Multi-source Geocoding optimization method (PCMG) that integrates geocoding outputs from multiple platforms under explicit polygon constraints corresponding to address semantics. The method aggregates candidate coordinates obtained from online geocoding platforms, including Baidu Maps, Amap (Gaode), and Tencent Maps, and introduces hierarchical polygon units as spatial constraints to filter and optimize candidate locations. POI data was employed to filter the optimized candidate locations and enhance spatial plausibility and consistency. The method was evaluated using 1,884 real-world addresses in Nanjing, China, with ground-truth locations collected through field surveys. Experimental results demonstrate that PCMG significantly reduces average geocoding error compared with single-platform results and effectively suppresses extreme positional deviations. Error distributions under PCMG are more concentrated and exhibit a clearer relationship with polygon scale, indicating improved spatial consistency. The findings suggest that polygon units can serve as active constraints for multi-source geocoding optimization and provide a practical solution for improving the reliability of online geocoding services in complex urban environments.