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

doi:10.13474/j.cnki.11-2246.2026.0526

Abstract

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

CLC Number:

P208

PENG Song, WU Hao, YU Youqi, LI Zongze, LIU Yujun. Intelligent production method of basic geographic entity data based on multi-agent collaboration[J]. Bulletin of Surveying and Mapping, 2026, 0(5): 161-168.

References

[1] 自然资源部办公厅.实景三维中国建设技术大纲(2021版)[EB/OL].[2021-08-11].http://sjy-info.com/uploa-ds/20240323/4728376051dfdbf84021be4e2f26ad08.pdf.
[2] 张元杰,田海波.基础地理实体工程化建模技术[J].测绘通报,2025(5):159-164.
[3] 王瑞幺,严荣华,肖建华,等.国家新型基础测绘体系建设试点的进展与思考[J].地理空间信息,2023,21(7):1-6.
[4] 肖建华.建立新型基础测绘体系的实践与思考[J].中国测绘,2018(1):32-36.
[5] 自然资源部办公厅.关于全面推进实景三维中国建设的通知[EB/OL].[2022-05-20].http://gi.mnr.gov.cn/202202/t20220225_2729401.html.
[6] 李小强,高华,王玲,等.三维地名实体构建与分级表达研究[J].测绘通报,2024(7):164-167.
[7] 王易,王成良,邱国栋.群体智能学习型决策:“大数据+AI”赋能的决策范式演化研究[J].中国软科学,2024(12):35-50.
[8] 罗斌,刘文豪,吴进,等.从地理信息系统到地理智能体[J].地球信息科学学报,2025,27(1):83-99.
[9] KE Zixuan,JIAO Fangkai,MING Yifei,et al.A survey of frontiers in LLM reasoning:inference scaling,learning to reason,and agentic systems[EB/OL].[2026-01-15].https://arxiv.org/abs/2504.09037.
[10] WOOLDRIDGE M,JENNINGS N R.Intelligent agents:theory and practice[J].The Knowledge Engineering Review,1995,10(2):115-152.
[11] WANG Lei,MA Chen,FENG Xueyang,et al.A survey on large language model based autonomous agents[J].Frontiers of Computer Science,2024,18(6):186345.
[12] DURANTE Z,HUANG Qiuyuan,WAKE N,et al.Agent AI:surveying the horizons of multimodal interaction[EB/OL].[2026-01-20].https://arxiv.org/abs/2401.03568.
[13] 杨小梅,李璐,黄芳,等.基础测绘成果转换地理实体生产研究[J].测绘与空间地理信息,2025,48(6):117-119.
[14] 邹磊,杨鹏,曹文涛,等.从存量地形图到地理实体的自动化生产实践[J].测绘通报,2022(12):147-152.
[15] LI Xinyi,WANG Sai,ZENG Siqi,et al.A survey on LLM-based multi-agent systems:workflow,infrastructure,and challenges[J].Vicinagearth,2024,1(1):9.
[16] 邓开艳,杨爱玲.基础地理实体数据库建设思路探索[J].测绘与空间地理信息,2022,45(S1):67-69.
[17] 陈军,王东华,商瑶玲,等.国家1∶50000数据库更新工程总体设计研究与技术创新[J].测绘学报,2010,39(1):7-10.
[18] 王东华,刘建军,商瑶玲,等.国家1∶50000基础地理信息数据库动态更新[J].测绘通报,2013(7):1-4.
[19] 杨元喜.地理空间数字孪生与时空智能[J].测绘学报,2025,54(2):213-220.
[20] 张鑫,姚庆安,赵健,等.全卷积神经网络图像语义分割方法综述[J].计算机工程与应用,2022,58(8):45-57.
[21] 陈妍洁.基于深度学习的点云三维目标检测技术研究[D].绵阳:西南科技大学,2023.
[22] 孙壮,刘坡,翟亮,等.一种基于三分支注意力网络的面状地理实体自监督匹配方法[J].测绘学报,2026,55(1):169-180.
[23] 中华人民共和国自然资源部国土测绘司.基础地理实体空间身份编码规则[EB/OL].[2021-12-16].https://gi.mnr.gov.cn/202112/t20211227_2715842.html.
[24] 刘纪平,周婷婷,刘坡,等.实景三维地理实体建模的思考与实践[J].测绘学报,2025,54(4):650-660.
[25] 王帮进,赵骞,叶远智,等.新型基础测绘地理实体成果质量检查模型[J].测绘通报,2025(2):13-17.
[26] 张继贤,张莉,张鹤.面向新型基础测绘的质检任务探讨[J].测绘通报,2018(7):71-73.