测绘通报 ›› 2026, Vol. 0 ›› Issue (5): 161-168.doi: 10.13474/j.cnki.11-2246.2026.0526

• 技术交流 • 上一篇    

多智能体协同下的基础地理实体数据智能化生产

彭松1, 吴昊2, 俞友齐3, 李宗泽3, 刘昱君3   

  1. 1. 江苏省测绘产品质量监督检验站, 江苏 南京 210019;
    2. 江苏省测绘工程院, 江苏 南京 210019;
    3. 南京师范大学, 江苏 南京 210023
  • 收稿日期:2026-01-30 发布日期:2026-06-09
  • 通讯作者: 刘昱君。E-mail:lyj@nnu.edu.cn
  • 作者简介:彭松(1978—),男,高级工程师,主要从事测绘产品质量检验、基础测绘、工程测量等工作。E-mail:1012098663@qq.com
  • 基金资助:
    自然资源部国土卫星遥感应用重点实验室开放基金(KLSMNR-K202503);2025年度江苏省自然资源科技项目(JSZRKJ202506)

Intelligent production method of basic geographic entity data based on multi-agent collaboration

PENG Song1, WU Hao2, YU Youqi3, LI Zongze3, LIU Yujun3   

  1. 1. Jiangsu Surveying and Mapping Product Quality Supervision and Inspection Station, Nanjing 210019, China;
    2. Jiangsu Institute of Surveying and Mapping Engineering, Nanjing 210019, China;
    3. Nanjing Normal University, Nanjing 210023, China
  • Received:2026-01-30 Published:2026-06-09

摘要: [目的]针对基础地理实体生产中流程割裂、人工依赖度高及质量控制困难等瓶颈,需探索满足新型基础测绘大规模、高时效更新需求的生产新模式。[方法]本文提出了一种大语言模型驱动的多智能体协同生产方法,通过构建由任务编排、实体识别、属性关系和质量检查智能体组成的协同体系,实现生产任务的自适应解构与智能行动链执行。[结果]试验应用表明,该系统能够产出不同类别的地理实体,实现生成任务从任务编排到质量检验的智能化闭环,形成了“边生产、边检查、边修正”的敏捷质控模式。[结论]该方法为新型基础测绘智能化转型提供了可行路径与参考范式,有效提升了生产效率与数据一致性。

关键词: 基础地理实体, 多智能体系统, 智能化生产

Abstract: [Purposes]To address bottlenecks such as fragmented workflows,high dependence on manual labor,and quality control difficulties in basic geographic entity production,this study explores a new production model to satisfy the large-scale and high-timeliness update requirements of new-type fundamental surveying and mapping.[Methods]A LLM-driven multi-agent collaborative production method is proposed.A collaborative system comprising task orchestration,entity recognition,attribute relationship,and quality inspection agents is established to achieve the adaptive deconstruction of production goals and the execution of intelligent action chains.[Findings]Application in an experimental area shows that the system can generate diverse categories of geographic entities and realize an intelligent closed-loop covering the entire process from task orchestration to quality inspection.An agile quality control mode of “simultaneous production,inspection,and correction” has been successfully implemented.[Conclusions]This approach provides a feasible technical path and reference paradigm for the intelligent transformation of fundamental surveying and mapping,effectively improving production efficiency and data consistency.

Key words: basic geographic entities, multi-agent system, intelligent production

中图分类号: