An Intelligent Map Cartography Framework Integrating Knowledge Graph and Large Language Model

WANG Mengqi; LI Bozhao; WANG Zhenli; LIU Songcao; LIAO Cheng; CAI Zhongliang

doi:10.13203/j.whugis20240266

您当前的位置：

首页 >

文章列表页 >

An Intelligent Map Cartography Framework Integrating Knowledge Graph and Large Language Model

Cartography and GIS | 更新时间：2026-11-05

- An Intelligent Map Cartography Framework Integrating Knowledge Graph and Large Language Model
- Geomatics and Information Science of Wuhan University Vol. 51, Issue 4, Pages: 840-851(2026)
- 作者机构：
  
  1.武汉大学资源与环境科学学院，湖北武汉，430079
  2.浙江省测绘科学技术研究院，浙江杭州，311100
- 作者简介：
- 基金信息：
- DOI：10.13203/j.whugis20240266
  CLC： P208
- Received：17 December 2024，
  
  Published：05 April 2026
- 稿件说明：
移动端阅览
王孟琪,李伯钊,王振立，等.一种集成知识图谱和大语言模型的智能地图制图框架[J].武汉大学学报（信息科学版）,2026,51(4):840-851.

WANG Mengqi,LI Bozhao,WANG Zhenli,et al.An Intelligent Map Cartography Framework Integrating Knowledge Graph and Large Language Model[J].Geomatics and Information Science of Wuhan University,2026,51(4):840-851.
王孟琪,李伯钊,王振立，等.一种集成知识图谱和大语言模型的智能地图制图框架[J].武汉大学学报（信息科学版）,2026,51(4):840-851. DOI：10.13203/j.whugis20240266

WANG Mengqi,LI Bozhao,WANG Zhenli,et al.An Intelligent Map Cartography Framework Integrating Knowledge Graph and Large Language Model[J].Geomatics and Information Science of Wuhan University,2026,51(4):840-851. DOI：10.13203/j.whugis20240266

摘要

已有研究探索了生成式人工智能在地图制图任务中的应用，例如应用图像翻译模型进行地图风格转换，使用图像扩散模型尝试将文本描述转换成地图图像，以及将大语言模型（large language model

LLM）作为制图助手完成用户需求解析和专业制图工具调用。上述研究验证了生成式人工智能在地图制图任务中的可行性，但地图生成结果存在不准确和制图知识缺失等问题。因此，提出一种集成制图规则的制图框架，以制图知识图谱为决策支持，以LLM为决策智能体，以制图插件为决策执行器。实验以制作武汉市交通地图为例，实现了制图策略生成、交互式修改、地图结果生成的智能制图流程，验证了智能制图框架和制图知识在人工智能生成地图任务中的有效性。

Abstract

Objectives

Generative artificial intelligence has introduced new possibilities for map cartography. Existing studies have explored map style transformation

text-to-map generation

and large language model (LLM)-assisted cartography

indicating the potential of generative artificial intelligence for cartographic tasks. However

generated results still suffer from inaccurate map representation

insufficient cartographic knowledge

and limited support for stable cartographic reasoning. Traditional cartographic expert systems also make limited progress because of the difficulty of cartographic knowledge modeling and reasoning construction. Direct use of general LLM for cartographic tasks faces additional problems

including weak understanding of cartographic concepts

unstable output

and limited capability in computation and operation. The intelligent map cartography framework is therefore constructed to integrate cartographic knowledge graph

LLM reasoning

and cartographic execution tools

so that cartographic knowledge could be explicitly embedded into map-making tasks.

Methods

The framework is designed according to the logic of practical cartographic workflow and organized into three major stages that are cartographic strategy generation

interactive modification

and map generation. The cartographic knowledge graph is first constructed to formalize cartographic concepts

entities

rules

and relations. Map ontology is used to organize cartographic concepts at different levels. Similarity relations between cartographic regions and themes are added to strengthen associations among map entities and support knowledge retrieval when the exact match is unavailable. The knowledge graph serves as the external knowledge base for cartographic reasoning

and the LLM acts as the decision agent. The fine-tuning strategy based on low-rank adaptation is adopted to improve the model's understanding of cartographic concepts and map-making tasks. During cartographic strategy generation

natural-language requirements are parsed into structured task information

including cartographic region

map theme

and related design conditions. The structured information is used to retrieve relevant data and cartographic configuration knowledge from the knowledge graph. Cartographic reasoning is performed by decomposing the map-making problem into multiple sub-tasks and generating corresponding query sequences

so that symbol

annotation

and other map design configurations could be inferred step by step. During interactive modification

user feedback is transformed into parameterized revision information

and the corresponding configurations are updated. During map generation

the selected data

inferred design configuration

and existing symbol resources are combined to complete data processing and automated map output.

Results

The traffic map of Wuhan is used to verify the proposed framework. The framework completes a full intelligent cartographic process covering requirement parsing

cartographic strategy inference

interactive revision

data processing

and automated map output. Natural-language cartographic requirements could be transformed into structured task descriptions and used as the basis for subsequent processing. The knowledge graph supports the retrieval and recommendation of cartographic knowledge related to symbols

annotations

and other map design elements. When exact knowledge for a target map is unavailable

related knowledge could still be inferred through similarity relations between cartographic regions and themes. Interactive modification enables users to adjust map configurations according to revised requirements

and the updated configuration could be directly incorporated into the subsequent cartographic process. The experiment of Wuhan traffic map shows that the framework could connect cartographic knowledge

LLM-based reasoning

and execution tools within one workflow

while reducing operational steps and alleviating problems caused by insufficient professional knowledge. The proposed framework also demonstrats the value of cartographic knowledge in constraining and guiding artificial intelligence (AI)-based map generation.

Conclusions

Integration of cartographic knowledge graph

LLM

and cartographic tools provides a feasible framework for intelligent map cartography. Explicit representation of cartographic knowledge improves support for cartographic reasoning

strategy generation

and interactive revision. The framework extends AI-assisted cartography from isolated task execution to coordinated workflow linking requirement understanding

knowledge-guided reasoning

user interaction

and automated map production. Results from the Wuhan traffic map validate the effectiveness and practical applicability of incorporating cartographic knowledge into AI-based map generation.

关键词

Keywords

references

BUTTENFIELD B P . Line Structure in Graphic and Geographic Space ［D］. Seattle ： University of Washington ， 1984 .

FISHERP F ， MACKANESS W A . Are Cartographic Expert Systems Possible？［C］// The 8th International Symposium on Computer-Assisted Cartography ， Baltimore， USA ， 1987 .

王家耀，吴战家，武芳 . 制图综合专家系统工具研究［J］. 解放军测绘学院学报， 1992 ， 9 （ 4 ）： 66 - 72 .

WANG Jiayao ， WU Zhanjia ， WU Fang . The Research on Tools of the Cartographic Generalization Expert System ［J］. Journal of the Pla Institute of Surveying and Mapping ， 1992 ， 9 （ 4 ）： 66 - 72 .

KAZEMI S ， LIM S ， GE L . Integration of Cartographic Knowledge with Generalization Algorithms ［C］// IEEE International Geoscience and Remote Sensing Symposium ， Seoul， Korea ， 2005 .

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 .

ZHANG An ， ZHU Junkai . Opportunities and Challenges of Cartography Research Driven by New Generation Artificial Intelligence ［J］. Journal of Geo‐Information Science ， 2024 ， 26 （ 1 ）： 35 - 45 .

孟立秋 . 地图为人人，人人都制图［J］. 测绘科学技术学报， 2012 ， 29 （ 5 ）： 313 - 320 .

MENG Liqiu . Map Serves Everybody and Everybody Makes Map ［J］. Journal of Geomatics Science and Technology ， 2012 ， 29 （ 5 ）： 313 - 320 .

吴明光，孙彦杰，闾国年 . 地图风格迁移：概念、综述与展望［J］. 武汉大学学报（信息科学版）， 2022 ， 47 （ 12 ）： 2069 - 2084 .

WU Mingguang ， SUN Yanjie ， LÜ Guonian . Cartographic Style Transfer： Idea， Review and Envision ［J］. Geomatics and Information Science of Wuhan University ， 2022 ， 47 （ 12 ）： 2069 - 2084 .

SONG J Q ， LI J ， CHEN H ， et al . MapGen-GAN： A Fast Translator for Remote Sensing Image to Map via Unsupervised Adversarial Learning ［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing ， 2021 ， 14 ： 2341 - 2357 .

FU Y ， LIANG S Z ， CHEN D D ， et al . Translation of Aerial Image into Digital Map via Discriminative Segmentation and Creative Generation ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2022 ， 60 ： 4703715 .

CHEN X ， CHEN S Q ， XU T ， et al . SMAPGAN： Generative Adversarial Network-Based Semisupervised Styled Map Tile Generation Method ［J］. IEEE Transactions on Geoscience and Remote Sensing ， 2021 ， 59 （ 5 ）： 4388 - 4406 .

WANG C L ， CHEN T J ， LIU Y Q ， et al . TransMI： A Transfer-Learning Method for Generalized Map Information Evaluation ［J］. Cartography and Geographic Information Science ， 2025 ， 52 （ 4 ）： 370 - 386 .

亢孟军，叶蕾，朱军，等 . 一种顾及制图区域要素密度均衡的地图变换算法［J］. 武汉大学学报（信息科学版）， 2022 ， 47 （ 12 ）： 2096 - 2104 .

KANG Mengjun ， YE Lei ， ZHU Jun ， et al . An Improved Map Transformation Algorithm Considering the Balance of Features Density in Cartographical Region ［J］. Geomatics and Information Science of Wuhan University ， 2022 ， 47 （ 12 ）： 2096 - 2104 .

SAHU M ， OHRI A . Vector Map Generation from Aerial Imagery Using Deep Learning ［J］. ISPRS Annals of the Photogrammetry， Remote Sensing and Spatial Information Sciences ， 2019 ， IV-2/W 5 ： 157 - 162 .

BASTANI F ， HE S ， ABBAR S ， et al . RoadTracer： Automatic Extraction of Road Networks from Aerial Images ［C］// IEEE/CVF Conference on Computer Vision and Pattern Recognition ， Salt Lake City， USA ， 2018 .

TAN Y Q ， GAO S H ， LI X Y ， et al . VecRoad： Point-Based Iterative Graph Exploration for Road Graphs Extraction ［C］// IEEE/CVF Conference on Computer Vision and Pattern Recognition ， Seattle， USA ， 2020 .

SCHEIDER S ， RICHTER K F . Pragmatic GeoAI： Geographic Information as Externalized Practice ［J］. Künstliche Intelligenz ， 2023 ， 37 （ 1 ）： 17 - 31 .

张良培，张乐飞，袁强强 . 遥感大模型：进展与前瞻［J］. 武汉大学学报（信息科学版）， 2023 ， 48 （ 10 ）： 1574 - 1581 .

ZHANG Liangpei ， ZHANG Lefei ， YUAN Qiang‐

qiang . Large Remote Sensing Model： Progress and Prospects ［J］. Geomatics and Information Science of Wuhan University ， 2023 ， 48 （ 10 ）： 1574 - 1581 .

杨必胜，陈一平，邹勤 . 从大模型看测绘时空信息智能处理的机遇和挑战［J］. 武汉大学学报（信息科学版）， 2023 ， 48 （ 11 ）： 1756 - 1768 .

YANG Bisheng ， CHEN Yiping ， ZOU Qin . Opportunities and Challenges of Spatiotemporal Information Intelligent Processing of Surveying and Mapping in the Era of Large Models ［J］. Geomatics and Information Science of Wuhan University ， 2023 ， 48 （ 11 ）： 1756 - 1768 .

TAO R ， XU J W . Mapping with ChatGPT ［J］. ISPRS International Journal of Geo‐Information ， 2023 ， 12 （ 7 ）： 284 .

ZHANG Y F ， HE Z T ， LI J X ， 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 .

周成虎，王华，王成善，等 . 大数据时代的地学知识图谱研究［J］. 中国科学：地球科学， 2021 ， 51 （ 7 ）： 1070 - 1079 .

ZHOU Chenghu ， WANG Hua ， WANG Chengshan ， et al . Research on Geo-knowledge Map in the Age of Big Data ［J］. Scientia Sinica （Terrae）， 2021 ， 51 （ 7 ）： 1070 - 1079 .

王家耀 . 地图科学技术：由数字化到智能化［J］. 武汉大学学报（信息科学版）， 2022 ， 47 （ 12 ）： 1963 - 1977 .

WANG Jiayao . Cartography： From Digital to Intelligent ［J］. Geomatics and Information Science of Wuhan University ， 2022 ， 47 （ 12 ）： 1963 - 1977 .

张雪英，张春菊，吴明光，等 . 顾及时空特征的地理知识图谱构建方法［J］. 中国科学：信息科学， 2020 ， 50 （ 7 ）： 1019 - 1032 .

ZHANG Xueying ， ZHANG Chunju ， WU Mingguang ， et al . Spatiotemporal Features Based Geographical Knowledge Graph Construction ［J］. Scientia Sinica （Informationis）， 2020 ， 50 （ 7 ）： 1019 - 1032 .

YAO S Y ， ZHAO J ， YU D ， et al . ReAct： Synergizing Reasoning and Acting in Language Models ［C］// The 11th International Conference on Learning Representations ， Kigali， Rwanda ， 2023 .

HU E J ， SHEN Y L ， WALLIS P ， et al . LoRA： Low-Rank Adaptation of Large Language Models ［C］// International Conference on Learning Representations ， Online ， 2022 .

CORCHO O ， FERNÁNDEZ-LÓPEZ M ， GÓMEZ-PÉREZ A . Methodologies， Tools and Languages for Building Ontologies： Where Is Their Meeting Point？［J］. Data & Knowledge Engineering ， 2003 ， 46 （ 1 ）： 41 - 64 .

SMITH R A . Designing a Cartographic Ontology for Use with Expert Systems ［C］// Special Joint Symposium of ISPRS Technical Commission IV & AutoCarto 2010 in Conjunction with ASPRS/CaGIS 2010 Fall Specialty Conference ， Orlando， USA ， 2010 .

SUN J S ， XU C J ， TANG L M Y ， et al . Think-on-Graph： Deep and Responsible Reasoning of Large Language Model on Knowledge Graph ［C］// The 12th International Conference on Learning Representations ， Vienna， Austria ， 2024 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Hill-Shading Generation Method Based on ResUNet

An Improved Schema for Vector Tile Map Considering Symbol Integrity

High-Resolution L-Band InSAR Study of Intense Near-Field Deformation Associated with Shallow Moderate Earthquakes

Spatiotemporal Evolution and Explainable Analysis of Grassland Vulnerability in the Hohhot-Baotou-Ordos-Yulin Urban Agglomeration

Machine Learning-Based Remote Sensing Retrieval of Soil Moisture： Advances and Challenges

Related Author

YIN Guangzhi

LI Shaomei

MA Jingzhen

LÜ Dongxu

BIAN Chenglin

Pengcheng LIU

Xiaofeng XU

Min YANG

Related Institution

Institute of Geospatial Information, Information Engineering University

Troops

Key Laboratory for Geographical Process Analysis and Simulation, Central China Normal University

School of Urban and Environmental Science, Central China Normal University

Wuhan Natural Resources and Planning Information Center

AI问答

⁰