面向地学分析AI建模的地理信息服务层次网络模型

doi:10.11947/j. AGCS.2024.20240109.

摘要/Abstract

摘要：

在人工智能生成（AIGC）和大语言模型（LLM）的大背景下，如何提升地学分析模型构建的智能化水平已成为业界广泛关注的焦点。为此，本文提出地理信息服务层次网络模型5-HiNet，基于需求描述、抽象模型、功能模块、服务接口、函数实例的5层子网络结构对海量地学分析模型进行建模，由抽象到具体逐层描述地学分析模型的实现过程，固化模型中的知识，形成面向地学分析模型的完备知识体系。5-HiNet模型能够进一步与大语言模型（LLM）进行耦合，实现地学分析模型的智能化生成。本文通过原型系统和应用案例，初步验证了5-HiNet的可行性，并为未来研究和应用提供新的方向和思路。

关键词: 地理信息服务, 地学分析模型, 层次网络, 领域知识, 智能化生成

Abstract:

Within the context of artificial intelligence generation (AIGC) and large language model (LLM), improving the intelligence level of generating geographic analysis models has gained widespread attention in the field. This paper proposes a geospatial information service hierarchical network model, named 5-HiNet. This model allows for a step-by-step description of heterogeneous geographic analysis models based on the five-layer hierarchical sub-network structure of demand description, abstract model, functional module, service interface, and functional instance, which depicts the realization process of geographic analysis models from the general to the specific. Within the five-layer hierarchical sub-network structure, the 5-HiNet can integrate massive expert knowledge embedded in the geographic analysis models and thus form a well-rounded domain knowledge system. Furthermore, the 5-HiNet can be coupled with the LLM to generate geographic analysis models automatically. A prototype system with a case study is developed in this paper to demonstrate the feasibility of the proposed 5-HiNet, and several research directions and insights for future study are provided.

Key words: geospatial information service, geographic analysis model, hierarchical network, domain knowledge, intelligent generation

中图分类号:

P208

吴华意, 赵安琪, 梁健源, 侯树洋. 面向地学分析AI建模的地理信息服务层次网络模型[J]. 测绘学报, 2024, 53(11): 2053-2063.

Huayi WU, Anqi ZHAO, Jianyuan LIANG, Shuyang HOU. Five-layer hierarchical network (5-HiNet) of geospatial information service for AIGC of geographic analysis model[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(11): 2053-2063.

图/表 6

图1

表1

图2

图3

图4

图5

参考文献 47

[1]	HE Yuanqing, CHEN Min, WEN Yongning, et al. A web-based strategy to reuse grids in geographic modeling[J]. International Journal of Applied Earth Observation and Geoinformation, 2023, 116: 103170.
[2]	LI Zhenlong, YANG Chaowei, HUANG Qunying, et al. Building model as a service to support geosciences[J]. Computers, Environment and Urban Systems, 2017, 61: 141-152.
[3]	DONG Guangsheng, LI Rui, WU Huayi, et al. Learning the spatial co-occurrence for browsing interests extraction of domain users on public map service platforms[J]. Geo-spatial Information Science, 2024, 27(2): 455-474.
[4]	游兰. 云环境下空间信息服务组合的自治愈关键技术研究[D]. 武汉: 武汉大学, 2015.
	YOU Lan. Research on key technologies of self-healing of spatial information service composition in cloud environment[D]. Wuhan: Wuhan University, 2015.
[5]	JIN Fengying, LI Rui, LIANG Jianyuan, et al. An augmented geospatial service web based on QoS constraints and geospatial service semantic relationships[J]. ISPRS International Journal of Geo-Information, 2022, 11(7): 357.
[6]	吴华意, 靳凤营, 梁健源, 等. 地理信息服务网络与协同研究进展[J]. 测绘学报, 2022, 51(6): 1050-1061. DOI:. doi: 10.11947/j.AGCS.2022.20210338
	WU Huayi, JIN Fengying, LIANG Jianyuan, et al. Research progress on geospatial service web and gollaboration[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(6): 1050-1061. DOI:. doi: 10.11947/j.AGCS.2022.20210338
[7]	谭振宇, 乐鹏, 张明达, 等. GeoQoS—QoS感知的空间信息服务组合建模工具[J]. 测绘通报, 2016(4): 43-48.
	TAN Zhenyu, LE Peng, ZHANG Mingda, et al. GeoQoS—a tool for QoS-aware geospatial information services composition[J]. Bulletin of Surveying and Mapping, 2016(4): 43-48.
[8]	邢华桥. 面向地表覆盖变化检测的服务关系模型与方法研究[J]. 测绘学报, 2018, 47(9): 1291. DOI:. doi: 10.11947/j.AGCS.2018.20170523
	XING Huaqiao. Modeling and methods of service relation for land cover change detection[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(9): 1291. DOI:. doi: 10.11947/j.AGCS.2018.20170523
[9]	GORELICK N, HANCHER M, DIXON M, et al. Google Earth Engine: planetary-scale geospatial analysis for everyone[J]. Remote Sensing of Environment, 2017, 202: 18-27.
[10]	SHAO Zhenfeng, CHENG Tao, FU Huyan, et al. Emerging issues in mapping urban impervious surfaces using high-resolution remote sensing images[J]. Remote Sensing, 2023, 15(10): 2562.
[11]	ZHANG Xianyuan, XIANG Longgang, YUE Peng, et. al. Opengeospatial engine: a cloud-based spatiotemporal computing platform[J]. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2024(10): 453-459.
[12]	CHEN Min, VOINOV A, AMES D P, et al. Position paper: open web-distributed integrated geographic modelling and simulation to enable broader participation and applications[J]. Earth-Science Reviews, 2020, 207: 103223.
[13]	GAO Fan, YUE Peng, CAO Zhipeng, et al. A multi-source spatio-temporal data cube for large-scale geospatial analysis[J]. International Journal of Geographical Information Science, 2022, 36(9): 1853-1884.
[14]	LIANG Jianyuan, JIN Fengying, ZHANG Xianyuan, et al. WS4GEE: enhancing geospatial web services and geoprocessing workflows by integrating the Google Earth Engine[J]. Environmental Modelling & Software, 2023, 161: 105636.
[15]	XING Huaqiao, LIU Chang, LI Rui, et al. Domain constraints-driven automatic service composition for online land cover geoprocessing[J]. ISPRS International Journal of Geo-Information, 2022, 11(12): 629.
[16]	HE Sheng, TAN Xicheng, ZHONG Yanfei, et al. Evolutionary PSO-based emergency monitoring geospatial edge service chain in the emergency communication network[J]. International Journal of Digital Earth, 2023, 16(1): 2797-2817.
[17]	刘波. 云制造环境中面向多任务的服务组合与优化技术研究[D]. 重庆: 重庆大学, 2012.
	LIU Bo. Research on multi-task oriented service composition and optimization technology in cloud manufacturing environment[D]. Chongqing: Chongqing University, 2012.
[18]	张严凯. 基于蚁群算法的云制造服务组合优化研究[D]. 南京: 南京邮电大学, 2018.
	ZHANG Yankai. Research on optimization of cloud manufacturing service composition based on ant colony algorithm[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2018.
[19]	张康, 高洪皓, 朱永华, 等. 一种基于改进模拟退火算法的QoS动态服务组合方法[J]. 应用科学学报, 2017, 35(5): 570-584.
	ZHANG Kang, GAO Honghao, ZHU Yonghua, et al. QoS dynamic web services composition method based on improved simulated annealing algorithm[J]. Journal of Applied Sciences, 2017, 35(5): 570-584.
[20]	GONG Jianya, WU Huayi, ZHANG Tong, et al. Geospatial Service Web: towards integrated cyberinfrastructure for GIScience[J]. Geo-spatial Information Science, 2012, 15(2): 73-84.
[21]	龚健雅, 耿晶, 吴华意, 等. 地理信息资源网络服务技术及其发展[J]. 测绘科学技术学报, 2013, 30(4): 353-360.
	GONG Jianya, GENG Jing, WU Huayi, et al. The technology on geospatial service web and its development[J]. Journal of Geomatics Science and Technology, 2013, 30(4): 353-360.
[22]	靳凤营. 基于地理信息服务网络的服务表征与智能推荐方法研究[D]. 武汉: 武汉大学, 2023.
	JIN Fengying. Research on service representation and intelligent recommendation method based on geographic information service network[D]. Wuhan: Wuhan University, 2023.
[23]	TAN Xicheng, DI Liping, DENG Meixia, et al. Cloud- and agent-based geospatial service chain: a case study of submerged crops analysis during flooding of the Yangtze River basin[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(3): 1359-1370.
[24]	凌朝阳, 李锐, 吴华意, 等. 语义驱动的地理实体关联网络构建与知识服务[J]. 测绘学报, 2023, 52(3): 478-489. DOI:. doi: 10.11947/j.AGCS.2023.20210349
	LING Zhaoyang, LI Rui, WU Huayi, et al. Semantic-driven construction of geographic entity association network and knowledge service[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(3): 478-489. DOI:. doi: 10.11947/j.AGCS.2023.20210349
[25]	王晓磊. 地理空间信息Web服务子片段排序与推荐[D]. 北京: 中国地质大学(北京), 2016.
	WANG Xiaolei. Ranking and recommendation of sub-segments of geospatial information Web services[D]. Beijing: China University of Geosciences (Beijing), 2016.
[26]	HU Boran, ZHOU Zhangbing, CHENG Zehui. Web services recommendation leveraging semantic similarity computing[J]. Procedia Computer Science, 2018, 129: 35-44.
[27]	YUE Peng, GUO Xia, ZHANG Mingda, et al. Linked Data and SDI: the case on Web geoprocessing workflows[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 114: 245-257.
[28]	VILCHES-BLÁZQUEZ L M, SAAVEDRA J. A framework for connecting two interoperability universes: OGC web feature services and linked data[J]. Transactions in GIS, 2019, 23(1): 22-47.
[29]	JIN Fengying, LI Rui, WU Huayi. Graph neural network-based similarity relationship construction model for geospatial services[J]. Geo-spatial Information Science, 2024, 27(5): 1509-1523.
[30]	CAO Yihan, LI Siyu, LIU Yixin, et al. A comprehensive survey of AI-generated content (AIGC): a history of generative AI from GAN to ChatGPT[EB/OL]. [2024-03-19]. http://arxiv.org/abs/2303.04226.
[31]	RAY P P. ChatGPT: a comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope[J]. Internet of Things and Cyber-Physical Systems, 2023, 3: 121-154.
[32]	LUO Haoran, E H, TANG Zichen, et al. ChatKBQA: a generate-then-retrieve framework for knowledge base question answering with fine-tuned large language models[EB/OL]. [2024-03-19]. http://arxiv.org/abs/2310.08975.
[33]	PAN Shirui, LUO Linhao, WANG Yufei, et al. Unifying large language models and knowledge graphs: a roadmap[J]. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(7): 3580-3599.
[34]	LI Zhenlong, NING Huan. Autonomous GIS: the next-generation AI-powered GIS[J]. International Journal of Digital Earth, 2023, 16(2): 4668-4686.
[35]	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.
[36]	MA Ning, LIU Yijun. SuperedgeRank algorithm and its application in identifying opinion leader of online public opinion supernetwork[J]. Expert Systems with Applications, 2014, 41(4): 1357-1368.
[37]	席运江, 杨茜, 廖晓. 超网络与知识超网络研究简述[J]. 现代管理, 2019(4): 557-565.
	XI Yunjiang, YANG Qian, LIAO Xiao. Research review on super-network and knowledge super-network[J]. Modern Management, 2019(4): 557-565.
[38]	CHEN Xiang, ZHANG Ningyu, XIE Xin, et al. KnowPrompt: knowledge-aware prompt-tuning with synergistic optimization for relation extraction[C]//Proceedings of the ACM Web Conference 2022. Lyon: ACM Press, 2022: 2778-2788.
[39]	LEWIS P, PEREZ E, PIKTUS A, et al. Retrieval-augmented generation for knowledge-intensiveNLP tasks[J]. Advances in Neural Information Processing Systems, 2020, 33: 9459-9474.
[40]	WEI J, WANG Xuezhi, SCHUURMANS D, et al. Chain-of-thought prompting elicits reasoning in large language models[J]. Advances in Neural Information Processing Systems, 2022, 35: 24824-24837.
[41]	SAHOO P, SINGH A K, SAHA S, et al. A systematic survey of prompt engineering in large language models: techniques and applications[EB/OL]. [2024-03-19]. http://arxiv.org/abs/2402.07927.
[42]	ZHANG Shengyu, DONG Linfeng, LI Xiaoya, et al. Instruction tuning for large language models: a survey[EB/OL]. [2024-03-19]. http://arxiv.org/abs/2308.10792.
[43]	XU Lingling, XIE Haoran, QIN S Z J, et al. Parameter-efficient fine-tuning methods for pretrained language models: a critical review and assessment[EB/OL]. [2024-03-19]. http://arxiv.org/abs/2312.12148.
[44]	NAVEED H, KHAN A U, QIU Shi, et al. A comprehensive overview of large language models[EB/OL]. [2024-03-19]. http://arxiv.org/abs/2307.06435.
[45]	TANG Jiabin, YANG Yuhao, WEI Wei, et al. GraphGPT: graph instruction tuning for large language models[EB/OL]. [2024-03-19]. http://arxiv.org/abs/2310.13023.
[46]	CHENG Tao, ZHANG Yang, HAWORTH J. Network SpaceTime AI: concepts, methods and applications[J]. Journal of Geodesy & Geoinformation Science, 2022, 5(3): 78-92.
[47]	ZHANG Ziwei, LI Haoyang, ZHANG Zeyang, et al. Graph meets LLMs: towards large graph models[EB/OL]. [2024-03-19]. http://arxiv.org/abs/2308.14522.

网络层级	实体类型	关系三元组
需求描述子网络	需求描述DescReq、主题Theme数据源、DataSource	<DescReq，涉及，Theme>
		<DescReq，依赖于，DataSource>
		<DescReq₁，等效，DescReq₂>
		<DescReq₁，包含，DescReq₂>
抽象模型子网络	抽象模型Abs Model	<Abs Model₁，需求相似，Abs Model₂>
		<Abs Model₁，结构相似，Abs Model₂>
		<Abs Model₁，协作，Abs Model₂>
		<Abs Model₁，包含，Abs Model₂>
功能模块子网络	功能模块Mod Unit	<Mod Unit₁，调用，Mod Unit₂>
		<Mod Unit₁，相似，Mod Unit₂>
		<Mod Unit₁，包含，Mod Unit₂>
服务接口子网络	服务接口ServiceInt	<ServiceInt₁，匹配，ServiceInt₂>
		<ServiceInt₁，包含，ServiceInt₂>
		<ServiceInt₁，竞争，ServiceInt₂>
函数实例子网络	函数实例FunctionInst	<FunctionInst₁，必要连接，FunctionInst₂>
函数实例子网络	函数实例FunctionInst	<FunctionInst₁，补充连接，FunctionInst₂>