nav emailalert searchbtn searchbox tablepage yinyongbenwen piczone journalimg journalInfo searchdiv qikanlogo popupnotification paper paperNew
2025, 04, v.50 138-142
融合大语言模型和空间智能体的地灾知识问答系统设计与实现
基金项目(Foundation): 国家重点研发计划(2022YFC3105103)
邮箱(Email):
DOI: 10.14188/j.2095-6045.20240180
摘要:

随着ChatGPT的推出,大语言模型(large language models,LLMs)展现出了出色的知识覆盖、文本生成和持续学习进化等能力,大语言模型已成为人工智能迈向通用智能的里程碑技术。同时,大语言模型也给智能体(agent)的发展提供了新的契机。本文研究针对地质灾害领域,设计了一个融合大语言模型和空间智能体的地灾问答系统,系统通过引入本地地灾知识以弥补大语言模型在地灾专业领域知识的不足;通过融合空间智能体,解决了大语言模型难以理解和处理空间问题的能力,可实现用户针对地灾专业领域问题的回答和展示。

Abstract:

With the launch of ChatGPT, large language models(LLMs) have demonstrated remarkable abilities in knowledge coverage, text generation, and continuous learning evolution. LLMs have become a milestone technology in the journey of artificial intelligence towards general intelligence. At the same time, they also provide new opportunities for the development of intelligent agents. This paper focuses on the field of geological disasters and designs a geological disasters system with LLMs(GLMSA-QAS). This system integrates a LLMs with spatial intelligence agents to compensate for the deficiencies of LLMs in specialized knowledge of geological disasters. By incorporating spatial intelligence agents, the system overcomes the difficulty of LLMs in understanding and processing spatial issues, enabling responses and presentations for users′ questions in the field of geological disasters.

参考文献

[1] Chang Y, Wang X, Wang J, et al. A Survey on Evaluation of Large Language Models[J]. ACM Transactions on Intelligent Systems and Technology,2024,15(3):39

[2]张鹤译,王鑫,韩立帆,等.大语言模型融合知识图谱的问答系统研究[J].计算机科学与探索,2023,17(10):2 377-2 388

[3] Biswas S S. Potential Use of ChatGPT in Global Warming[J]. Annals of Biomedical Engineering,2023, 51(6):1 126-1 127

[4] Dai Y, Feng D, Huang J, et al. LAiW:A Chinese Legal Large Language Models Benchmark(A Technical Report)[J]. arXiv preprint arXiv:2310. 05620, 2023

[5] Huang Q, Tao M, An Z, et al. Lawyer LLaMA Technical Report[J]. arXiv preprint arXiv:2305. 15062, 2023

[6] Xi Z, Chen W, Guo X, et al. The Rise and Potential of Large Language Model Based智能体s:A survey[J]. arXiv preprint arXiv:2309. 07864, 2023

[7] Crooks A T. Constructing and Implementing an智能体-Based Model of Residential Segregation Through Vector GIS[J]. International Journal of Geographical Information Science, 2010, 24(5):661-675

[8] Camara A S, Raper J. Spatial Multimedia and Virtual Reality[M]. Leiden, Netherlands:CRC Press, 1999:111-129

[9]殷跃平.中国滑坡防治工程理论与实践[J].水文地质工程地质,1998,(1):8-12

[10]冷小鹏.基于G/S模式的三维地质灾害信息管理平台研究[D].成都:成都理工大学,2012

[11] Luo Y, Yang Z, Meng F, et al. An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-Tuning[J]. arXiv preprint arXiv:2308. 08747, 2023

[12] Liu V, Chilton L B. Design Guidelines for Prompt Engineering Text-to-Image Generative Models[C]. Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, New Orleans, USA,2022

[13] Wu T, He S, Liu J, et al. A Brief Overview of ChatGPT:The History, Status Quo and Potential Future Development[J]. IEEE/CAA Journal of Automatica Sinica, 2023, 10(5):1 122-1 136

[14] Bai J, Bai S, Yang S, et al. Qwen-vl:A Frontier Large Vision-Language Model With Versatile Abilities[J]. arXiv preprint arXiv:2308. 12966, 2023

[15] Zeng A, Liu X, Du Z, et al. Glm-130b:An Open Bilingual Pre-Trained Model[J]. arXiv preprint arXiv:2210. 02414, 2022

[16] Wu Mingxing,Luo Nianxue. Design and Implementation of a Geo-disaster Knowledge Q&A System Integrating Large Language Models and Spatial Agents[J].Journal of Applied Meteorological Science,2005,16(4):547-553

基本信息:

DOI:10.14188/j.2095-6045.20240180

中图分类号:P208;P694

引用信息:

[1]吴铭星,罗年学.融合大语言模型和空间智能体的地灾知识问答系统设计与实现[J].测绘地理信息,2025,50(04):138-142.DOI:10.14188/j.2095-6045.20240180.

基金信息:

国家重点研发计划(2022YFC3105103)

引用

GB/T 7714-2015 格式引文
MLA格式引文
APA格式引文
检 索 高级检索