A grid sampling and machine learning-based plot-level planning scheme generation method

CN121787707BActive Publication Date: 2026-08-28GUANGXI TEACHERS EDUCATION UNIV +1
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202511790167.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-12-01
Publication Date
2026-08-28
Estimated Expiration
2045-12-01

AI Technical Summary

Technical Problem

[0003]现有技术中，地块规划数据采集大多采用规则栅格或固定尺度的点状采样方式，缺乏对区域内部空间异质性的分析与适配，容易在结构复杂区采样不足、在均质区域造成数据冗余，既影响采样效率，也不利于后续参数预测的空间分辨率

Benefits of technology

本发明，通过构建基于高程变异、植被覆盖、土壤类型与基础设施密度多维特征的空间异质性指数模型，能够量化每个采样单元的内部特征复杂程度。进而采用多级阈值划分与四叉树递归、边界梯度感知等手段，在高异质性区域进行局部加密、在突变边界执行选择性细化、在低异质性区域保持稀疏采样，并结合采样质量反馈与特征相似融合机制动态优化网格结构。该机制使有限采样资源集中于空间结构复杂区域，大幅减少冗余数据采集，增强局部特征解析能力，为后续规划模型提供高质量输入，提升采样效率与表达精度。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121787707B_ABST
    Figure CN121787707B_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of planning analysis, and particularly relates to a land parcel level planning scheme generation method based on grid sampling and machine learning, comprising the following steps: S1: performing initial grid sampling on a target land parcel to generate an initial sampling unit set; based on the initial sampling unit set, calculating a spatial heterogeneity index of each sampling unit through an identification model; S2: performing adaptive dynamic sampling on the target land parcel according to the heterogeneity index to generate an optimized sampling unit set; S3: inputting the optimized sampling unit set into a planning parameter prediction model to generate planning parameters of each optimized sampling unit. The present application effectively solves the problems of local conflicts, boundary jumps and functional breaks commonly encountered in the planning process, and improves the executability and coordination of the overall scheme.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Landslide susceptibility evaluation method and system fusing feature interaction and dynamic weighting

    CN120541692A