Translation of spatial direction relationship for We-map making

doi:10.11947/j.AGCS.2025.20250187

Abstract

Abstract:

We-maps are a generalized form of maps emerging in the era of social media, characterized by micro-content, low entry barriers, rapid production, and personalization. However, current research on We-maps lacks mechanisms to translate spatial directional relations from textual descriptions into cartographic expressions, which limits the development of We-map generation. In response, this paper proposes a spatial directional relation translation method for We-map making. A We-map representation model is established under the support of graph theory, defining its data organization and description structure, which serves as the target schema for the translation process. Structured spatial directional relations are extracted from natural language and stored in graph-based structures. A dual-layout strategy is designed to visualize these structures into map representations. The proposed method is validated using a custom dataset through both qualitative (feature matching of We-maps) and quantitative (structural stability of We-maps, including readability, stability, and balanced) metrics. Quantitative evaluation on 500 test samples shows that the readability scores ranged from 0.772 9 to 0.982 1, with a mean of 0.928 6. The stability values ranged from 0.001 6 to 0.463 8, with a mean of 0.091 2. The balance values ranged from 0.000 016 to 0.062 816, with a mean of 0.008 5. The readability value is close to 1, while the stability and balance metrics are close to 0, confirming consistency with We-map characteristics. These results demonstrate the method's effectiveness in extracting cartographic entities and their spatial relations, enabling the automatic generation of readable and stable We-maps with connected paths and structured layouts.

Key words: We-map, spatial direction relationships, graph theory, natural language process

CLC Number:

P208

Xiaolong WANG, Zhuo WANG, Jingzhong LI, Haowen YAN. Translation of spatial direction relationship for We-map making[J]. Acta Geodaetica et Cartographica Sinica, 2025, 54(11): 2040-2051.

Figures/Tables 9

Fig. 1

Fig. 2

Tab. 1

Tab. 2

Tab. 3

Fig. 3

Fig. 4

Fig. 5

Fig. 6

References 29

[1]	高俊, 曹雪峰. 空间认知推动地图学学科发展的新方向[J]. 测绘学报, 2021, 50(6): 711-725. DOI: 10.11947/j.AGCS.2021.20210043.
	GAO Jun, CAO Xuefeng. The new development direction of cartography promoted by spatial cognition[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(6): 711-725. DOI: 10.11947/j.AGCS.2021.20210043.
[2]	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.
[3]	RAPANT P, MENŠÍK M, ALBERT A. Automatic sketch map creation from labeled planar graph[J]. International Journal of Geographical Information Science, 2024, 38(5): 981-1006.
[4]	SEN A, ZHAN Zhicheng, WINTER S, et al. Automatic translation of human route descriptions into schematic maps for indoor navigation[J]. Cartography and Geographic Information Science, 2024, 51(3): 445-461.
[5]	应申, 徐雅洁, 李玉. 叙事地图的要素及组织：基于电子游戏“要素-结构-场景”架构的视角[J]. 测绘学报, 2024, 53(5): 967-980. DOI: 10.11947/j.AGCS.2024.20230435.
	YING Shen, XU Yajie, LI Yu. Elements and organization of narrative maps: a element-structure-scene architecture based on the video game perspective[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(5): 967-980. DOI: 10.11947/j.AGCS.2024.20230435.
[6]	RAISZ E. Rectangular statistical cartograms of the world[J]. Journal of Geography, 1936, 35(1): 8-10.
[7]	任桂磊, 高俊. 人类世地图：绘制人类世的地图[J]. 武汉大学学报(信息科学版), 2024, 49(4): 624-630.
	REN Guilei, GAO Jun. Anthropocene map: mapping the anthropocene[J]. Geomatics and Information Science of Wuhan University, 2024, 49(4): 624-630.
[8]	齐凯, 张衡, 周杨, 等. 综合局部莫兰指数和PageRank算法的网络空间资源节点隐喻可视化表达[J]. 地球信息科学学报, 2024, 26(5): 1283-1295.
	QI Kai, ZHANG Heng, ZHOU Yang, et al. Metaphor representation of resource nodes in cyberspace based on local moran index and PageRank algorithm[J]. Journal of Geo-information Science, 2024, 26(5): 1283-1295.
[9]	陈业滨. 泛地图可视化框架构建与实证研究[J]. 测绘学报, 2023, 52(8): 1418. DOI: 10.11947/j.AGCS.2023.20220157.
	CHEN Yebin. The construction and empirical exploration of pan-maps visualization framework[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(8): 1418. DOI: 10.11947/j.AGCS.2023.20220157.
[10]	郭仁忠, 陈业滨, 应申, 等. 三元空间下的泛地图可视化维度[J]. 武汉大学学报(信息科学版), 2018, 43(11): 1603-1610.
	GUO Renzhong, CHEN Yebin, YING Shen, et al. Geographic visualization of pan-map with the context of ternary spaces[J]. Geomatics and Information Science of Wuhan University, 2018, 43(11): 1603-1610.
[11]	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): 1108-1113. DOI: 10.11947/j.AGCS.2022.20220140.
	GUO Renzhong, CHEN Yebin, MA Ding, et al. Pan-map representation in ICT era[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(7): 1108-1113. DOI: 10.11947/j.AGCS.2022.20220140.
[12]	闫浩文, 王卓, 王小龙, 等. 微地图[M]. 北京: 科学出版社, 2024.
	YAN Haowen, WANG Zhuo, WANG Xiaolong, et al. We-map[M]. Beijing: Science Press, 2024.
[13]	闫浩文, 张黎明, 杜萍, 等. 自媒体时代的地图：微地图[J]. 测绘科学技术学报, 2016, 33(5): 520-523.
	YAN Haowen, ZHANG Liming, DU Ping, et al. We-map: a new type of map in the era of we media[J]. Journal of Geomatics Science and Technology, 2016, 33(5): 520-523.
[14]	余懿韬, 闫浩文, 李精忠, 等. 面向微地图的手绘地图符号自动提取方法[J]. 地球信息科学学报, 2024, 26(7): 1646-1658.
	YU Yitao, YAN Haowen, LI Jingzhong, et al. Automatic extraction method of point symbols in modern hand-drawn maps for we-map[J]. Journal of Geo-information Science, 2024, 26(7): 1646-1658.
[15]	何阳, 闫浩文, 王卓, 等. 面向微地图的地标提取方法及个性化寻路应用[J]. 地球信息科学学报, 2022, 24(5): 827-836.
	HE Yang, YAN Haowen, WANG Zhuo, et al. Landmark extraction method and personalized wayfinding application for we-map[J]. Journal of Geo-information Science, 2022, 24(5): 827-836.
[16]	WANG Xiaolong, YAN Haowen, WANG Zhuo, et al. Wemap-based direction model for individuals with limited spatial orientation skills[J]. Transactions in GIS, 2024, 28(2): 111-129.
[17]	ZHANG Yifan, HE Zhengting, LI Jingxuan, 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.
[18]	CHEN Jiaqi, LIN Bingqian, XU Ran, et al. MapGPT: map-guided prompting with adaptive path planning for vision-and-language navigation[C]//Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. Bangkok: ACL, 2024: 9796-9810.
[19]	ZHANG Chiqun, KARATZOGLOU A, CRAIG H, et al. Map GPT playground: smart locations and routes with GPT[C]//Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems. Hamburg: ACM Press, 2023: 1-4.
[20]	ZHANG Yifan, ZHANG Wenbo, ZENG Ziyi, et al. MapReader: a framework for learning a visual language model for map analysis[J]. International Journal of Geographical Information Science, 2025, 39(9): 1973-2008.
[21]	艾廷华. 深度学习赋能地图制图的若干思考[J]. 测绘学报, 2021, 50(9): 1170-1182. DOI: 10.11947/j.AGCS.2021.20210091.
	AI Tinghua. Some thoughts on deep learning enabling cartography[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(9): 1170-1182. DOI: 10.11947/j.AGCS.2021.20210091.
[22]	LAPAINE M, MIDTBØ T, GARTNER G, et al. Definition of the map[J]. Advances in Cartography and GIScience of the ICA, 2021, 3: 1-6.
[23]	王小龙. 微地图辅助寻路的定向智能制图方法及应用[D]. 兰州: 兰州大学, 2025.
	WANG Xiaolong. Oriented intelligent cartographic method for We-map and its wayfinding application[D]. Lanzhou: Lanzhou University, 2025.
[24]	DI BARTOLOMEO S, CRNOVRSANIN T, SAFFO D, et al. Evaluating graph layout algorithms: a systematic review of methods and best practices[J]. Computer Graphics Forum, 2024, 43(6): e15073.
[25]	康健梓, 周虹. 基于力导向布局的知识图谱可视化方法[J]. 计算机辅助设计与图形学学报, 2024, 36(8): 1214-1223.
	KANG Jianzi, ZHOU Hong. Force-directed layout based knowledge graph visualization method[J]. Journal of Computer-Aided Design & Computer Graphics, 2024, 36(8): 1214-1223.
[26]	奎晓燕, 王子潇, 郑智浩, 等. 增强多层网络心理地图保持效果的力引导布局算法[J]. 计算机辅助设计与图形学学报, 2024, 36(6): 960-968.
	KUI Xiaoyan, WANG Zixiao, ZHENG Zhihao, et al. A force-directed layout algorithm for enhancing the mental map preservation in multilayer networks[J]. Journal of Computer-Aided Design & Computer Graphics, 2024, 36(6): 960-968.
[27]	王权于, 李振华, 涂志鹏, 等. 基于BERT-BiGRU-CRF模型的岩土工程实体识别[J]. 地球科学, 2023, 48(8): 3137-3150.
	WANG Quanyu, LI Zhenhua, TU Zhipeng, et al. Geotechnical named entity recognition based on BERT-BiGRU-CRF model[J]. Earth Science, 2023, 48(8): 3137-3150.
[28]	陈谊, 胡海云, 李志龙. 树图布局算法的比较与优化研究[J]. 计算机辅助设计与图形学学报, 2013, 25(11): 1623-1634.
	CHEN Yi, HU Haiyun, LI Zhilong. Performance compare and optimization of rectangular treemap layout algorithms[J]. Journal of Computer-Aided Design & Computer Graphics, 2013, 25(11): 1623-1634.
[29]	胡海云, 陈谊, 甄远刚, 等. 一种正方化有序树图布局算法[J]. 计算机辅助设计与图形学学报, 2014, 26(10): 1703-1710.
	HU Haiyun, CHEN Yi, ZHEN Yuangang, et al. A squarified and ordered treemap layout algorithm[J]. Journal of Computer-Aided Design & Computer Graphics, 2014, 26(10): 1703-1710.

序号	自然语言文本生成算法			自动标注算法
1	定义词表：spatial_terms，prepositions，entities			定义正则表达式P₁、P₂　//完整结构与缺主语结构
2	For i in 1 to N：			For sentence in corpus：
3		paragraph ← []		entities← extract_entities（sentence，P₁，P₂）
4		subject ← 随机实体		subject← track_or_default（entities，上一句主语）
5		For j in 1 to随机（3~5）：		tags← apply_BIO（entities，roles=["Subj"，"Obj"，"Rel"]）
6			sentence ← 生成描述链（subject，5~10子句），更新subject	tags← fix_labels（tags）　//修正方向词错误等
7			paragraph.append（sentence），写入文件	store_to_JSON（sentence，tags），写入为JSON文件

行数	文本数据集	标注数据集
1	行政楼临近排球场的东北，……，积石堂在天演楼的西南。……	[{"tokens"：["行"，"政"，"楼"，"临"，"近"，"排"，"球"，"场"，"的"，"东"，"北"，"，"，……，"积"，"石"，"堂"，"在"，"天"，"演"，"楼"，"的"，"西"，"南"，"。" ……]，"labels"：["B-SUBJ"，"I-SUBJ"，"I-SUBJ"，"O"，"O"，"B-OBJ"，"I-OBJ"，"I-OBJ"，"O"，"B-REL"，"I-REL"，"O"，……，["B-SUBJ"，"I-SUBJ"，"I-SUBJ"，"O"，"O"，"B-OBJ"，"I-OBJ"，"I-OBJ"，"O"，"B-REL"，"I-REL"，"O"，……，]
	⋮	⋮
10 000	……。停车场则在图书馆的正北，……，第二化学楼在南一门的正西。	"tokens"：[……，"停"，"车"，"场"，"则"，"在"，"图"，"书"，"馆"，"的"，"正"，"北"，"，"，……，"第"，"二"，"化"，"学"，"楼"，"在"，"南"，"一"，"门"，"的"，"正"，"西"，"。" ……]，"labels"：["B-SUBJ"，"I-SUBJ"，"I-SUBJ"，"O"，"O"，"B-OBJ"，"I-OBJ"，"I-OBJ"，"O"，"B-REL"，"I-REL"，"O"，……，["B-SUBJ"，"I-SUBJ"，"I-SUBJ"，"I-SUBJ"，"I-SUBJ"，"O"，"O"，"B-OBJ"，"I-OBJ"，"I-OBJ"，"O"，"B-REL"，"I-REL"，"O"]}]

环境	工具	描述
硬件	CPU	Inte® Core^TM i7-10750H CPU @ 2.60 GHz
	GPU	NVIDIA GeForce GTX 1650
	内存	16 GB
软件	操作系统	Windows 11
软件	开发语言	Python 3.9.19