| 139 | 0 | 185 |
| 下载次数 | 被引频次 | 阅读次数 |
围绕地图制图长期存在专业门槛高、自动化程度低的问题，基于工具增强的大语言模型、模型微调和Web地图制图等关键技术，研究了基于工具集增强的地图制图大模型构建方法，通过基于大模型的自动化工具集构建、微调样本生成及领域微调等环节，构建了地图制图领域的大语言模型原型系统，实验结果表明，该方法能够有效理解用户的自然语言指令，准确调用相应的制图工具，实现智能化地图生成。本研究为地图制图领域的智能化提供了新的技术路径，同时也为大语言模型在垂直专业领域的应用提供了新思路。
Abstract：Cartography has long faced challenges such as high professional thresholds and low automation levels. We used the tool-enhanced large language model, model fine-tuning, and Web cartography technologies to explore a cartography large models construction method. Through the automated construction of tool sets based on large models, generation of fine-tuning samples, and domain-specific fine-tuning, we developed a prototype large language model system for cartography. Experimental results demonstrate that this method can effectively understand users' natural language instructions, accurately call upon relevant cartographic tools, and achieve intelligent map generation. This research provides a new technical approach for intelligent cartography and offers fresh insights into the application of large language models in specialized professional fields.
[1]李志林，徐柱，慎利，等.自主式情境化地图表达：大模型时代的智能化地图制图理论探讨[J].测绘学报，2024,53(11):2 043-2 052
[2]李桂娥，蔡忠亮，李伯钊，等.新型专题地图制图自动化系统框架与关键技术[J].测绘科学，2024,49(1):181-189
[3]郭仁忠，陈业滨，马丁，等.论ICT时代的泛地图表达[J].测绘学报，2022,51(7):1 108-1 113
[4]王家耀，武芳，闫浩文.大变化时代的地图学[J].测绘学报，2022,51(6):829-842
[5]Li M,Zhao Y,Yu B,et al. API-bank:A Comprehensive Benchmark for Tool-augmented Llms[J]. arXiv Preprint arXiv:2 304.082 44
[6]Wei J,Wang X,Schuurmans D,et al. Chain-of-thought Prompting Elicit Reasoning in Large Language Models[J].Advances in Neural Information Processing Systems,2022,35:24 824-24 837
[7]Wei C,Zhang Y,Zhao X,et al. GeoTool-gPT:A Trainable Method for Facilitating Large Language Models to Master GIS Tools[J]. International Journal of Geographical Information Science,2025,39(4):707-731
[8]Tang Q,Deng Z,Lin H,et al. Toolalpaca:Generalized Tool Learning for Language Models with 3 000 Simulated Cases[J]. arXiv Preprint arXiv:2 306.05301
[9]Qin Y,Liang S,Ye Y,et al. Toolllm:Facilitating Large Language Models to Master 16 000+Real-world Apis[J].arXiv Preprint arXiv:2 307
[10]Zhang Y,Li J,Wang Z,et al. Geospatial Large Language Model Trained with a Simulated Environment for Generating Tool-use Chains Autonomously[J]. International Journal of Applied Earth Observation and Geoinformation,2025,136:104 312
[11]Qiao S,Gui H,Lv C,et al. Making Language Models Better Tool Learners with Execution Feedback[J]. arXiv Preprint arXiv:2 305.13 068
[12]Bran A M,Cox S,Schilter O,et al. Augmenting Large Language Models with Chemistry Tools[J]. Nature Machine Intelligence,2024,6(5):525-535
[13]Yang R,Song L,Li Y,et al. GPT4Tools:Teaching Large Language Model to Use Tools Via Self-instruction[J]. arXiv Preprint arXiv:2 305.18 752
[14]张岸，朱俊锴.新一代人工智能驱动下地图学研究的机遇与挑战[J].地球信息科学学报，2024,26(1):35-45
[15]Zhang Y,He Z,Li J,et al. MapGPT:An Autonomous Framework for Mapping by Integrating Large Language Model and Cartographic Tools[J]. Cartography and Geographic Information Science,2024,51(6):717-743
[16]Akinboyewa T,Li Z,Ning H,et al. GIS Copilot:Towards an Autonomous GIS Agent for Spatial Analysis[J]. International Journal of Digital Earth,2025,18(1):2 497 489
[17]Lin Q,Hu R,Li H,et al. Shapefile GPT:A Multi-agent Large Language Model Framework for Automated Shapefile Processing[J]. arXiv Preprint arXiv:2 410.12 376
[18]Dettmers T,Pagnoni A,Holtzman A, et al. Qlora:Efficient Fnetuning of Auantized Llms[J]. Advances in Neural Information Processing Systems,2023,36:10 088-10 115
[19]张颖，张宇，蔡凯伦，等.城市大比例尺快速供图服务体系设计与实现[J].测绘，2023,46(6):243-248
[20]马炅妤，李平，周启，等. WebGL在线动态地图服务框架设计[J].测绘通报，2019(1):118-122
[21]Mansourian A,Oucheikh R. ChatGeoAI:Enabling Geospatial Analysis for Public Through Natural Language,with Large Language Models[J]. ISPRS International Journal of Geo-information,2024,13(10):348
基本信息:
中图分类号:P283
引用信息:
[1]任东宇,韦钰华,刘阳杰,等.基于工具集增强的地图制图大模型构建方法研究[J].地理空间信息,2025,23(12):1-6.
基金信息:
四川省地理时空大数据中心建设关键技术研究项目
2025-12-28
2025-12-28