兵棋推演态势认知的态势数学表达方法

打开文本图片集

中图分类号：TP391.9 文献标志码：A DOI：10.12305/j.issn.1001-506X.2025.03.20

situation mathematical expression method of situational awareness in wargame

PAN Chenhui1，*，XIAN Yong1，MA Peiyang1，NI Wancheng²，ZHAO Xiaonan²，LI Shaopeng1，3 （1. Sohoolof Missile Engineerings Rocket Force University of Engineering，Xi'an 710025，China; 2.Instituteof Automation，Chinese Academy of Sciences，Beijing l0ol9o，China； 3.Departmentof Automation，Tsinghua University，Beijing looo84，China）

Abstract：In order to meet the demand for intelligent situationcognition，this paper proposes a standardized construction method of machine learning dataset for batlefield situation cognition in wargame.Based on feature engineering analysis，this study focusesonarmy tactical wargameand analyzes key elements of batlefield situation，and proposes a hierarchical and grid based model for expressng the battlefield situation.By using the equal interval time correlation mode to slide sliceand map transformation the data of the wargame process，the problems of inconsistent military chess data structure，imbalanced feature labels，and diffculty in data transformation fidelityare solved，and the automatic collctionand storage of samples are achieved.A machine learning for situational awarenessin military chess deduction dataset containing 26o Oo samples is constructed and publicly available.The experiment shows thatthedataset constructed using the mapping modelin this paper has fewer subjective colors，good data fidelity，automatic and eficient data colection process，and good dataset consistency.

Keywords：wargame； feature expression； situation awareness；machine learning；data set

0 引言

人工智能技术的发展给军事斗争准备带来巨大冲击，在信息化战争后，智能化战争逐步成为各军事大国争相研究的热点、难点。（剩余17406字）