국방 GIS 기반 RAG-LLM을 활용한 AI COP 자동생성 기술 연구

류재학¹^{, *} ; 오현규² ; 진유정³

1해군 중령/(주)우진지앤에스 기업연수 중
2(주)우진지앤에스 기술연구소 수석연구원
3(주)서일엔지니어링 책임연구원

Study on AI COP Automatic Generation Technology Using Defense GIS-Based RAG-LLM

Jae-Hak Ryu¹^{, *} ; Hyon-Gyu Oh² ; Yoo-Jyoung Jin³

1CDR, ROK Navy/Executive trainee at Woojin GNS Co., Ltd.
2Principal researcher, R&D Center at Woojin G&S Co., Ltd.
3Principal researcher, Seoil Eng Co., Ltd.

Correspondence to: *Jae-Hak Ryu E-mail: rjh0303@hanmail.net

초록

본 연구에서는 RAG-LLM과 국방 GIS를 결합한 AI 작전상황도(COP) 자동생성 프레임워크를 제안한다. 제안 프레임워크는 전장정보 전처리, AI 기반 전술추론, 공간정보 처리, AI COP 자동생성, 지휘관 검증의 5단계로 구성된다. RAG-LLM을 통해 비정형 군사정보에서 핵심 전술요소를 추출하고, 이를 GIS 공간객체와 표준 군대부호로 변환하여 COP에 자동 반영한다. 이를 통해 상황평가, 위협분석 및 상황전개 예측을 지원하며, 기존 수작업 중심의 COP 생성절차를 지능화하고 전장 상황인식과 지휘결심을 지원하기 위한 기술적 기반을 제시한다.

Abstract

This paper proposes an AI-based common operational picture (AI-COP) generation framework integrating a retrieval-augmented generation-based large language model (RAG-LLM) with a defense geographic information system (GIS). The framework consists of battlefield data preprocessing, AI-based tactical reasoning, spatial information processing, AI COP generation, and human-in-the-loop validation. RAG-LLM extracts key tactical entities from unstructured military information, which are converted into GIS spatial objects and standardized military symbols. The generated information is integrated into the COP to support situation assessment, threat analysis, and situation projection. The proposed framework provides a technical foundation for automating COP generation and enhancing battlefield situational awareness and command decision support.

Keywords:

Common Operational Picture, RAG-LLM, Tactical Reasoning, Defense GIS, Human-in-the-Loop

키워드:

공통작전상황도, 검색증강생성 기반 대규모 언어모델, 전술추론, 국방 GIS, 인간 참여형 검증

Acknowledgments

이 논문은 2026년도 한국해군과학기술학회 하계학술대회 발표자료를 기반으로 작성하였음.

References

Michael D. McNeese, Mark S. Pfaff, Erik S. Connors, Joaquin F. Obieta, Ivanna S. Terrell, & Marc A. Friedenberg, ‘Multiple Vantage Points of the Common Operational Picture: Supporting International Teamwork,’ Proceedings of the Human Factors and Ergonomics Society Annual Meeting, VOL. 50, NO. 3, 2006, pp. 467-471. [https://doi.org/10.1177/154193120605000354]
Carl G. Looney, ‘Exploring Fusion Architecture for a Common Operational Picture,’ Information Fusion, VOL. 2, NO. 4, 2001, pp. 251-260. [https://doi.org/10.1016/S1566-2535(01)00043-4]
Mica R. Endsley, ‘Toward a Theory of Situation Awareness in Dynamic Systems,’ Human Factors: The Journal of the Human Factors and Ergonomics Society, VOL. 37, NO. 1, 1995, pp. 32-64. [https://doi.org/10.1518/001872095779049543]
Katia Sycara, Robin Glinton, Bin Yu, Joseph Giampapa, Sean Owens, Michael Lewis, & LTC Charles Grindle, ‘An Integrated Approach to High-Level Information Fusion,’ Information Fusion, VOL. 10, NO. 1, 2009, pp. 25-50. [https://doi.org/10.1016/j.inffus.2007.04.001]
Samir Puuska, Lauri Rummukainen, Jussi Timonen, Lauri Lääperi, Markus Klemetti, Lauri Oksama, & Jouko Vankka, ‘Nationwide Critical Infrastructure Monitoring Using a Common Operating Picture Framework,’ International Journal of Critical Infrastructure Protection, VOL. 20, 2018, pp. 28-47. [https://doi.org/10.1016/j.ijcip.2017.11.005]
Arslan Munir, Alexander Aved, & Erik Blasch, ‘Situational Awareness: Techniques, Challenges, and Prospects,’ AI, VOL. 3, NO. 1, 2022, pp. 55-77. [https://doi.org/10.3390/ai3010005]
Kookjin Kim, Jaepil Youn, Sukjoon Yoon, Jiwon Kang, Kyungshin Kim, & Dongkyoo Shin, ‘Study on Cyber Common Operational Picture Framework for Cyber Situational Awareness,’ Applied Sciences, VOL. 13, NO. 4, 2023, Article 2331. [https://doi.org/10.3390/app13042331]
Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel et al., ‘Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,’ Advances in Neural Information Processing Systems, VOL. 33, 2020, pp. 9459-9474.
Wonjun Cho, Jaesung Yoo, Sang-Min Kim, & Jaeeun Jang, ‘RAG-Enhanced Small Large Language Models: Enhancing Battlefield Analysis Through Knowledge Distillation of Large Language Models,’ Journal of the Korea Society of Computer and Information, VOL. 30, NO. 3, 2025, pp. 43-57. [https://doi.org/10.9708/jksci.2025.30.03.043]
Hamsle Lee, Dong-Hyun Kim, Hyoung-Seok, Kim, & Jaesung Yoo, ‘Preference-Aligned sLLM for Safe and Helpful RAG-Based Battlefield Analysis System,’ Journal of the Korea Society of Computer and Information, VOL. 30, NO. 6, 2025, pp. 31-46. [https://doi.org/10.9708/jksci.2025.30.06.031]
Shu Hsien Liao, ‘A Knowledge-Based Architecture for Implementing Military Geographical Intelligence System on Intranet,’ Expert Systems with Applications, VOL. 20, NO. 4, 2001, pp. 313-324. [https://doi.org/10.1016/S0957-4174(01)00016-1]
Young J. Kim & Christoph M. Hoffmann, ‘Enhanced Battlefield Visualization for Situation Awareness,’ Computers & Graphics, VOL. 27, NO. 6, 2003, pp. 873-885. [https://doi.org/10.1016/j.cag.2003.08.006]
Krzysztof Pokonieczny & Albina Mościcka, ‘The Influence of the Shape and Size of the Cell on Developing Military Passability Maps,’ ISPRS International Journal of Geo-Information, VOL. 7, NO. 7, 2018, Article 261. [https://doi.org/10.3390/ijgi7070261]
S. Fleming, T. Jordan, M. Madden, E. L. Usery, & R. Welch, ‘GIS Applications for Military Operations in Coastal Zones,’ ISPRS Journal of Photogrammetry and Remote Sensing, VOL. 64, NO. 2, 2009, pp. 213-222. [https://doi.org/10.1016/j.isprsjprs.2008.10.004]
R. Parasuraman, T. B. Sheridan, & C. D. Wickens, ‘A Model for Types and Levels of Human Interaction with Automation,’ IEEE Transactions on Systems, Man, and Cybernetics—Part A: Systems and Humans, VOL. 30, NO. 3, 2000, pp. 286-297. [https://doi.org/10.1109/3468.844354]