现代防御技术 ›› 2025, Vol. 53 ›› Issue (4): 36-49.DOI: 10.3969/j.issn.1009-086x.2025.04.005
收稿日期:
2024-12-30
修回日期:
2025-01-14
出版日期:
2025-08-28
发布日期:
2025-09-02
作者简介:
刘鑫(1990-),男,四川遂宁人。高工,博士,研究方向为复杂系统建模、信息智能处理。
Xin LIU, Kan WANG, Lican DAI, Kaichen CAO, Lianggang WANG
Received:
2024-12-30
Revised:
2025-01-14
Online:
2025-08-28
Published:
2025-09-02
摘要:
系统性探讨了国内外战略情报预警预测相关概念内涵及其演变过程,给出了契合新时期我国情与军情的战略情报预警预测定义。针对预警预测要求与活动特点,提出了战略情报预警预测的基本环节与流程框架,归纳总结了实施战略情报预警预测的认知驱动类和数据驱动类智能化方法的基本思想和主要算法模型,能为战略情报分析领域研究人员开展研究提供工具选择、方法途径等方面的指导与参考。认知驱动类方法有可解释性和交互性方面的优势,数据驱动类方法在大规模数据处理效率方面更佳,两者结合在人机协同式的复杂战略情报预警预测分析任务中能发挥更好的效能。未来上述智能化方法将重点解决人机认知差异性度量、异构知识关联融合、弱隐微线索挖掘、证据链印证闭环等方面的问题,以满足预警预测领域的全面性、准确性、可信度等要求。
中图分类号:
刘鑫, 王侃, 戴礼灿, 曹开臣, 王良刚. 战略情报预警预测智能化方法发展[J]. 现代防御技术, 2025, 53(4): 36-49.
Xin LIU, Kan WANG, Lican DAI, Kaichen CAO, Lianggang WANG. Intelligent Method Development of Strategic Intelligence Warning and Prediction[J]. Modern Defense Technology, 2025, 53(4): 36-49.
方法类型 | 理论基础 | 主流方法 | 可用工具 | 优点 | 缺点 |
---|---|---|---|---|---|
数理逻辑类 | 谓词逻辑 命题逻辑 | 模板匹配、产生式规则推理、专家思维模型化 | LISP,SWI-Prolog,Problog等 | 可解释性强、准确率高、推理过程明确 | 规则模板构建困难、人工参与过度 |
场景分析类 | 想定描述 过程演绎 | 想定筹划法、洛克伍德法 | 指标构建工具、思维导图等 | 直观可视、分析过程显性、可读性强,结果带有一定启发性 | 场景准确描述困难、缺乏定量计算 |
结构化分析类 | 假设检验 对比试验 | 竞争性假设法、小概率高影响法、关键性假设验证法 | ACH结构化工具、SWOT模型、PESTEL分析模型 | 基于批判质疑思维,可应对不确定性与偶然事件 | 受研究者主观影响较大,无法克服偏好问题 |
群体分析类 | 群智理论 | 群体会商法、投票决策法、多智能体博弈推演 | 会商系统、即时通讯、线上投票器等 | 基于专家会商研判,结论权威可信,可处理复杂问题 | 强依赖专家经验,只能定性分析 |
统计分析类 | 概率论 信息论 | 征候指标法、线性回归法、逻辑回归法 | probhet,statsmodels等时序分析库 | 基于历史数据中的统计规律,有理有迹可循 | 影响因素过多时容易出现非平稳问题 |
机器学习类 | 特征工程 回归理论 | 决策树模型、多层感知机、支持向量机、贝叶斯网络 | Sklearn,XGBoost等机器学习库 | 从标注数据中学习映射关系,效率高,具有一定可解释性 | 特征选择与构造困难,人工依赖严重 |
深度学习类 | 表示学习 | 卷积神经网络、循环神经网络、图神经网络 | pytorch,tensorflow等深度学习框架 | 适合处理大规模数据,可自动学习特征 | 黑箱问题,可信度存疑 |
表1 战略情报预警预测智能化方法对比分析表
Table 1 Comparative analysis of the intelligent methodology
方法类型 | 理论基础 | 主流方法 | 可用工具 | 优点 | 缺点 |
---|---|---|---|---|---|
数理逻辑类 | 谓词逻辑 命题逻辑 | 模板匹配、产生式规则推理、专家思维模型化 | LISP,SWI-Prolog,Problog等 | 可解释性强、准确率高、推理过程明确 | 规则模板构建困难、人工参与过度 |
场景分析类 | 想定描述 过程演绎 | 想定筹划法、洛克伍德法 | 指标构建工具、思维导图等 | 直观可视、分析过程显性、可读性强,结果带有一定启发性 | 场景准确描述困难、缺乏定量计算 |
结构化分析类 | 假设检验 对比试验 | 竞争性假设法、小概率高影响法、关键性假设验证法 | ACH结构化工具、SWOT模型、PESTEL分析模型 | 基于批判质疑思维,可应对不确定性与偶然事件 | 受研究者主观影响较大,无法克服偏好问题 |
群体分析类 | 群智理论 | 群体会商法、投票决策法、多智能体博弈推演 | 会商系统、即时通讯、线上投票器等 | 基于专家会商研判,结论权威可信,可处理复杂问题 | 强依赖专家经验,只能定性分析 |
统计分析类 | 概率论 信息论 | 征候指标法、线性回归法、逻辑回归法 | probhet,statsmodels等时序分析库 | 基于历史数据中的统计规律,有理有迹可循 | 影响因素过多时容易出现非平稳问题 |
机器学习类 | 特征工程 回归理论 | 决策树模型、多层感知机、支持向量机、贝叶斯网络 | Sklearn,XGBoost等机器学习库 | 从标注数据中学习映射关系,效率高,具有一定可解释性 | 特征选择与构造困难,人工依赖严重 |
深度学习类 | 表示学习 | 卷积神经网络、循环神经网络、图神经网络 | pytorch,tensorflow等深度学习框架 | 适合处理大规模数据,可自动学习特征 | 黑箱问题,可信度存疑 |
[1] | 胡荟. 战后美国情报界关于战略情报与国家安全决策关系的争鸣[J]. 情报杂志, 2015, 34(7): 5-8. |
HU Hui. On the Debate of the Relations Between Strategic Intelligence and National Security Decision in the Post-War U. S. Intelligence Community[J]. Journal of Intelligence, 2015, 34(7): 5-8. | |
[2] | 刘媛. 新时期军事战略情报研究刍议[J]. 中国电力教育, 2013(17): 152-153, 173. |
LIU Yuan. On the Study of Military Strategic Intelligence in the New Period[J]. China Electric Power Education, 2013(17): 152-153, 173. | |
[3] | 陈烨, 高金虎. 战略预警情报问题研究——基于美国预警情报专业化发展的学术史视角[J]. 情报杂志, 2022, 41(8): 14-23. |
CHEN Ye, GAO Jinhu. Research on Strategic Early Warning Intelligence: The Academic History Perspective Based on the Professional Development of Early Warning Information in the United States[J]. Journal of Intelligence, 2022, 41(8): 14-23. | |
[4] | WOHLSTETTER R. Pearl Harbor: Warning and Decision[M]. Stanford: Stanford University Press, 1962. |
[5] | HANDEL M I. Perception, Deception, and Surprise: The Case of the Yom Kippur War[M]. Jerusalem: Hebrew University of Jerusalem, Leonard Davis Institute for International Relations, 1976. |
[6] | KNORR K. Failures in National Intelligence Estimates: The Case of the Cuban Missiles[J]. World Politics, 1964, 16(3): 455-467. |
[7] | ALLISON G T. Conceptual Models and the Cuban Missile Crisis[J]. American Political Science Review, 1969, 63(3): 689-718. |
[8] | HEUER J R. Psychology of Intelligence Analysis[M]. Washington: United States Government Printing Office, 1999. |
[9] | KAM E. Surprise Attack: The Victim’s Perspective[M]. Cambridge: Harvard University Press, 2004. |
[10] | GRABO C. Handbook of Warning Intelligence: Assessing the Threat to National Security[M]. Lanham: Scarecrow Press, 2010. |
[11] | BODNAR J W. Warning Analysis for the Information Age: Rethinking the Intelligence Process[M]. Washington: The Joint Military Intelligence College's Center for Strategic Intelligence Research, 2003. |
[12] | MEDINA C A. What to Do When Traditional Models Fail[EB/OL]. [2021-08-19]. . |
[13] | GENTRY J A, GORDON J S. U.S. Strategic Warning Intelligence: Situation and Prospects[J]. International Journal of Intelligence and CounterIntelligence, 2018, 31(1): 19-53. |
[14] | INSA’s Cyber Council. A Framework for Cyber Indications and Warning[EB/OL]. (2018-10) [2022-04-25]. . |
[15] | BARNEA A, MESHULACH A. Forecasting for Intelligence Analysis: Scenarios to Abort Strategic Surprise[J]. International Journal of Intelligence and CounterIntelligence, 2021, 34(1): 106-133. |
[16] | DAVIS J. Strategic Warning: Intelligence Support in a World of Uncertainty and Surprise[M]. New York: Routledge, 2006: 173-188. |
[17] | GEORGE R Z. Fixing the Problem of Analytical Mind-Sets: Alternative Analysis[J]. International Journal of Intelligence and CounterIntelligence, 2004, 17(3): 385-404. |
[18] | 全军军事术语管理委员会, 军事科学院. 中国人民解放军军语(全本)[M]. 北京: 军事科学出版社, 2011. |
Military Terminology Management Committee, Academy of Military Science. Chinese People’s Liberation Army Terminology(Complete Edition)[M]. Beijing: Military Science Publishing House, 2011. | |
[19] | United States, Department of Defense Dictionary of Military and Associated Terms[M]. Washington: United States, Department of Defense, 2010: 337. |
[20] | 华文. 国际情报战-风云变幻[M]. 北京: 军事谊文出版社, 1993: 4-5. |
HUA Wen. International Intelligence War-Constant Change[M]. Beijing: Yi Wen Publishing Military, 1993: 4-5. | |
[21] | 汪明敏. 预警概念界定问题研究[J]. 情报杂志, 2022, 41(1): 14-18. |
WANG Mingmin. A Study on the Definition of the Concept of Warning[J]. Journal of Intelligence, 2022, 41(1): 14-18. | |
[22] | 王宏伟. 应急管理理论与实践[M]. 北京: 社会科学文献出版社, 2010: 127-148. |
WANG Hongwei. Theory and Practice of Emergency Management[M]. Beijing: Social Science Academic Press, 2010: 127-148. | |
[23] | 张海瀛, 戴礼灿, 刘鑫, 等. 情报预测概念内涵与技术发展[J]. 电讯技术, 2023, 63(10): 1492-1499. |
ZHANG Haiying, DAI Lican, LIU Xin, et al. Intelligence Prediction: Connotation and Technology Development[J]. Telecommunication Engineering, 2023, 63(10): 1492-1499. | |
[24] | 张晓军, 任国军, 张长军, 等. 美国军事情报理论研究[M]. 北京: 军事科学出版社, 2007: 70. |
ZHANG Xiaojun, REN Guojun, ZHANG Changjun, et al. A Study of U. S. Military Intelligence Theory[M]. Beijing: Military Science Publishing House, 2007: 70. | |
[25] | WIRTZ J J. The Offensive: Intelligence Failure in War[M]. Ithaca,NY: Cornell University Press, 1994: 4. |
[26] | 魏来. 关于新形势下“战略预警”概念界定的若干思考[J]. 情报杂志, 2016, 35(4): 27-31. |
WEI Lai. Thoughts on the Concept of "Strategic Warning" in the New Situation[J]. Journal of Intelligence, 2016, 35(4): 27-31. | |
[27] | MCCARTHY M O. The Mission to Warn: Disaster Looms[J]. Defense Intelligence Journal, 1998, 7(2): 17-31. |
[28] | RUSSELL R L. Sharpening Strategic Intelligence: Why the CIA Gets It Wrong and What Needs to Be Done to Get It Right[M]. Cambridge: Cambridge University Press, 2007. |
[29] | 马克思,恩格斯. 马克思恩格斯选集-第三卷[M]. 2版. 中共中央马克思恩格斯列宁斯大林著作编译局, 译. 北京: 人民出版社, 1995: 514-515. |
Marx and Engels. Anthology of Marx and Engels (Volume 3)[M]. 2nd ed. Translated by Compilation Bureau of the Works of Marx, Engels, Lenin and Stalin. Beijing: People Press, 1995: 514-515. | |
[30] | TRISKA M. Boolean Constraints in SWI-Prolog: A Comprehensive System Description[J]. Science of Computer Programming, 2018, 164: 98-115. |
[31] | DRIES A, KIMMIG A, MEERT W, et al. ProbLog2: Probabilistic Logic Programming[C]∥Proceedings of Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Cham: Springer International Publishing, 2015: 312-315. |
[32] | 中国电子科技集团公司第十研究所. 一种垂直领域规则常识知识获取方法及系统: CN202210266934.4[P]. 2023-06-09. |
China Electronics Technology Group Corporation Tenth Research Institute. A Method and System of Vertical Domain Commonsense Knowledge Acquisition: CN202210266934.4[P]. 2023-06-09. | |
[33] | 中国电子科技集团公司第十研究所. 一种可控开放式组合规则知识生成方法及系统: CN202210266977.2[P]. 2023-06-06. |
China Electronics Technology Group Corporation Tenth Research Institute. A Method and System of Controllable Open Combination Rules Knowledge Generation: CN202210266977.2[P]. 2023-06-06. | |
[34] | 中国电子科技集团公司第十研究所. 一种基于专家思维模型的领域业务辅助分析方法: CN202211169348.4[P]. 2023-05-23. |
China Electronics Technology Group Corporation Tenth Research Institute. A Domain Business Support Analysis Method Based on Expert Thinking Model: CN202211169348.4[P]. 2023-05-23. | |
[35] | CLARK R M. Intelligence Analysis: A Target-Centric Approach[M]. Washington: CQ Press, 2010. |
[36] | LOCKWOOD J S. The Lockwood Analytical Method for Prediction (LAMP): A Method for Predictive Intelligence Analysis[M]. New York: Bloomsbury Academic, 2013. |
[37] | LILLY B, ABLON L, HODGSON Q E, et al. Applying Indications and Warning Frameworks to Cyber Incidents[EB/OL]. (2020-04-28) [2022-04-25]. . |
[38] | 中国电子科技集团公司第十研究所. 一种综合态势智能辅助生成方法: CN202210914211.0[P]. 2022-11-22. |
China Electronics Technology Group Corporation Tenth Research Institute. A Intelligent Aided Generation Method of Integrated Situation: CN202210914211.0[P]. 2022-11-22. | |
[39] | 中国电子科技集团公司第十研究所. 面向多领域的交互式危机事件动态预警方法及系统: CN202311380982.7[P]. 2024-01-12. |
China Electronics Technology Group Corporation Tenth Research Institute. Interactive Dynamic Early-Warning Method and System for Multi-domain Crisis Events: CN202311380982.7[P]. 2024-01-12. | |
[40] | 中国电子科技集团公司第十研究所. 一种超事理图网络构建与事件演化分析方法: CN202410182025.1[P]. 2024-05-07. |
China Electronics Technology Group Corporation Tenth Research Institute. A Method of Hypergraph Network and Event Evolution Analysis: CN202410182025.1[P]. 2024-05-07. | |
[41] | 吕学志, 胡晓峰, 吴琳, 等. 基于改进竞争性假设分析的战役企图分析方法[J]. 系统工程与电子技术, 2019, 41(3): 555-563. |
Xuezhi LÜ, HU Xiaofeng, WU Lin, et al. Analysis Method of Campaign Attempt Based on Improved Analysis of Competing Hypothesis[J]. Systems Engineering and Electronics, 2019, 41(3): 555-563. | |
[42] | 西南电子技术研究所(中国电子科技集团公司第十研究所). 统一检索跨媒体信息的CMR模型: CN202010481108.2[P]. 2024-02-23. |
Southwest China Research Institute of Electronic Equipment (China Electronics Technology Group Corporation Tenth Research Institute). CMR Model for Cross-Media Information Retrieval: CN202010481108.2[P]. 2024-02-23. | |
[43] | 中国电子科技集团公司第十研究所. 多模态知识本征表示学习方法、装置、设备及存储介质: CN202210214990.3[P]. 2023-09-19. |
China Electronics Technology Group Corporation Tenth Research Institute. Method, Device, Equipment and Storage Medium of Multimodal Knowledge Essence Representation Learning: CN202210214990.3[P]. 2023-09-19. | |
[44] | 中国电子科技集团公司第十研究所. 一种面向非对称跨域多模态数据的协同处理方法: CN202410558199.3[P]. 2024-07-30. |
China Electronics Technology Group Corporation Tenth Research Institute. A Collaborative Processing Method for Asymmetric Cross-Domain Multimodal Data: CN202410558199.3[P]. 2024-07-30. | |
[45] | 西南电子技术研究所(中国电子科技集团公司第十研究所). 事件知识图谱预测群体性事件的方法: CN202011043065.6[P]. 2022-06-14. |
Southwest China Research Institute of Electronic Equipment (China Electronics Technology Group Corporation Tenth Research Institute). Group Events Prediction Method Based on Events Knowledge Graph: CN202011043065.6[P]. 2022-06-14. | |
[46] | 西南电子技术研究所(中国电子科技集团公司第十研究所). 多类型事件预测模型: CN202111159151.8[P]. 2023-05-16. |
Southwest China Research Institute of Electronic Equipment (China Electronics Technology Group Corporation Tenth Research Institute). Multi-type Event Prediction Model: CN202111159151.8[P]. 2023-05-16. | |
[47] | 王征, 杨茜. 基于情境推演的微博突发事件预测模型研究[J]. 情报学报, 2017, 36(3): 267-273. |
WANG Zheng, YANG Qian. MEPD: A Micro-Blog Emergent Incident Prognosis Model Based on Situation Deduction[J]. Journal of the China Society for Scientific and Technical Information, 2017, 36(3): 267-273. | |
[48] | 王龙, 黄锋. 多智能体博弈、学习与控制[J]. 自动化学报, 2023, 49(3): 580-613. |
WANG Long, HUANG Feng. An Interdisciplinary Survey of Multi-agent Games, Learning, and Control[J]. Acta Automatica Sinica, 2023, 49(3): 580-613. | |
[49] | 吕世杰, 杜培珍, 刘红梅, 等. 描述性统计在Excel和SAS中的异同[J]. 内蒙古农业大学学报(自然科学版), 2012, 33(增1): 296-299. |
Shijie LÜ, DU Peizhen, LIU Hongmei, et al. The Similarities and Differences of Descriptive Statistics in Excel and SAS[J]. Journal of Inner Mongolia Agricultural University(Natural Science Edition), 2012, 33(S1): 296-299. | |
[50] | 杜志渊. 常用统计分析方法——SPSS应用[M]. 济南: 山东人民出版社, 2006. |
DU Zhiyuan. General Method of Statistical Analysis—SPSS Application[M]. Jinan: Shandong People's Publishing House, 2006. | |
[51] | 葛萌萌. 一种基于凸优化的装备能力指标权重赋值方法[J]. 电讯技术, 2024, 64(4): 632-636. |
GE Mengmeng. A Weight Calculation Method of Equipment Capability Index Based on Convex Optimization[J]. Telecommunication Engineering, 2024, 64(4): 632-636. | |
[52] | 孙文. 不确定信息下的评估指标权重配置方法[J]. 电讯技术, 2023, 63(6): 882-888. |
SUN Wen. A Method of Weight Allocation for Evaluation Indicators Under Uncertain Information[J]. Telecommunication Engineering, 2023, 63(6): 882-888. | |
[53] | 中国电子科技集团公司第十研究所. 一种基于细微特征的核心主题事件监测方法及设备: CN202410296609.1[P]. 2024-06-04. |
China Electronics Technology Group Corporation Tenth Research Institute. A Method and Equipment for Key Subject Event Monitoring Based on Subtle Features: CN202410296609.1[P]. 2024-06-04. | |
[54] | 曹开臣, 高东生. 融合理解与生成的文档级事件抽取[J]. 舰船电子工程, 2023, 43(10): 47-52. |
CAO Kaichen, GAO Dongsheng. Document-Level Event Extraction Based on Fusion of Understanding and Generation[J]. Ship Electronic Engineering, 2023, 43(10): 47-52. | |
[55] | 周志远, 沈固朝, 朱小龙. 贝叶斯网络在情报预测中的应用[J]. 情报科学, 2014, 32(10): 3-8, 14. |
ZHOU Zhiyuan, SHEN Guchao, ZHU Xiaolong. Application of Bayesian Network in Intelligence Prediction[J]. Information Science, 2014, 32(10): 3-8, 14. | |
[56] | TORRES J F, HADJOUT D, SEBAA A, et al. Deep Learning for Time Series Forecasting: A Survey[J]. Big Data, 2021, 9(1): 3-21. |
[57] | YE Jiexia, ZHAO Juanjuan, YE Kejiang, et al. How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(5): 3904-3924. |
[58] | MA Xiaolei, DAI Zhuang, HE Zhengbing, et al. Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction[J]. Sensors, 2017, 17(4): 818. |
[59] | LI Yaguang, YU R, SHAHABI C, et al. Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting[EB/OL]. (2018-02-22) [2022-04-25]. . |
[60] | ZHAO Ling, SONG Yujiao, ZHANG Chao, et al. T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(9): 3848-3858. |
[61] | 王国胤, 傅顺, 杨洁, 等. 基于多粒度认知的智能计算研究[J]. 计算机学报, 2022, 45(6): 1161-1175. |
WANG Guoyin, FU Shun, YANG Jie, et al. A Review of Research on Multi-granularity Cognition Based Intelligent Computing[J]. Chinese Journal of Computers, 2022, 45(6): 1161-1175. | |
[62] | 梁吉业, 钱宇华, 李德玉, 等. 大数据挖掘的粒计算理论与方法[J]. 中国科学(信息科学), 2015, 45(11): 1355-1369. |
LIANG Jiye, QIAN Yuhua, LI Deyu, et al. Theory and Method of Granular Computing for Big Data Mining[J]. Scientia Sinica(Informationis), 2015, 45(11): 1355-1369. |
No related articles found! |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||