Methods, apparatus and equipment for building urban stock space databases and analyzing current status
By using the improved deep learning model BFE-Net and a dual-engine attribute matching strategy, combined with DBSCAN and Z-score anomaly detection, the problem of automated integration and efficient computation of multi-source heterogeneous urban spatial data was solved, enabling high-precision extraction and rapid analysis of existing urban spatial data.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINESE ACAD OF SURVEYING & MAPPING
- Filing Date
- 2026-02-10
- Publication Date
- 2026-05-26
AI Technical Summary
Existing technologies suffer from low efficiency, insufficient accuracy, and long processing times in integrating multi-source heterogeneous urban spatial data, extracting building information, and calculating massive spatial indicators, making it difficult to meet the needs of smart city construction.
An improved deep learning model, BFE-Net, combined with a spatial boundary enhancement module (SBM), is used for building outline extraction. A dual-engine attribute matching strategy is employed to achieve efficient data fusion. Intelligent analysis is performed using DBSCAN spatial clustering and Z-score anomaly detection methods, and parallel computing is carried out using a distributed computing framework.
It improved the accuracy of building outline extraction and data fusion efficiency, shortened the calculation time, realized high-precision automated extraction of building information and rapid analysis of massive indicators, and enhanced the automation level and objectivity of urban spatial data database construction.
Smart Images

Figure CN122086865A_ABST