基于主题模型的地理环境时空数据隐含语义理解

doi:10.11947/j.AGCS.2021.20200380

摘要/Abstract

摘要： 文本是战场信息的重要数据模态，从中挖掘地理环境时空语义信息是机器理解战场环境的重要方法，有助于扩展战场环境的空间认知与理解。本文设计一种基于主题模型，反映地理时空因素与事件主题之间语义关系的计算方法，通过信息抽取，挖掘主题要素相关信息，形成不同主题分类及其对应的特征词汇分布；将事件主题与地理时空语义特征建立联合分布模型，自动发现时间、空间与事件主题之间的相关性，从而生成地理时空隐含的语义主题。通过试验验证并结合应用实践，得到如下结论：利用事件主题与位置信息的关联，并应用空间分析方法探寻不同主题的时空分布规律，可为新事件的位置预测及趋利避害对策制定提供基础，从而拓展传统的地理事件主题分析。

关键词: 主题模型, 地理环境, 时空数据, 语义理解, 空间分析

Abstract: Text is an important data mode of battlefield information. Mining spatial-temporal semantic information of geographical environment from battlefield text is an important method for machine to understand battlefield environment, which is helpful to expand battlefield environment spatial cognition and understanding. A method based on topic model is designed to reflect the semantic relationship between geographical spatio-temporal factors and event topics, and different topic classification with its distribution of word features are formed by the method of information extraction to mine the relevant information of topic elements; the joint distribution model of event topic and geographical spatio-temporal semantic features is established to automatically discover the correlation among time, space and event topics, thus generating the latent geographical spatio-temporal semantic topics; through the experimental verification and the application practice, we believe that the law of spatio-temporal distribution under different topics can be seek by using correlation between the event topics and location information with spatial analysis method, so as to provide the basis for the location prediction of new events and the countermeasures of seeking advantages and avoiding disadvantages, and expand the traditional thematic analysis of geographical events.

Key words: topic model, geographical environment, spatio-temporal data, semantic understanding, spatial analysis

中图分类号:

P208

朱杰, 张宏军, 廖湘琳, 田江鹏. 基于主题模型的地理环境时空数据隐含语义理解[J]. 测绘学报, 2021, 50(10): 1404-1415.

ZHU Jie, ZHANG Hongjun, LIAO Xianglin, TIAN Jiangpeng. Latent semantic understanding of geographical environment spatio-temporal data based on topic model[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(10): 1404-1415.

参考文献

[1] 高俊, 万刚. 战场环境工程理论和技术[M]. 北京:解放军出版社, 2016:16-18. GAO Jun, WAN Gang. Theory and technology of battlefield environment engineering[M]. Beijing:PLA Press, 2016:16-18.
[2] 徐志红. 基于事件语义的时空数据模型的研究[D]. 武汉:武汉大学, 2005. XU Zhihong. Study on spatio-temporal data model based on event semantics[D]. Wuhan:Wuhan University, 2005.
[3] 姚迪, 张超, 黄建辉, 等. 时空数据语义理解:技术与应用[J]. 软件学报, 2018, 29(7):2018-2045. YAO Di, ZHANG Chao, HUANG Jianhui, et al. Semantic understanding of spatio-temporal data:technology & application[J]. Journal of Software, 2018, 29(7):2018-2045.
[4] 胡丹露. 战场环境信息支持作战决策研究[J]. 军事运筹与系统工程, 2004, 18(2):43-47. HU Danlu. Support decision making system on geo-data[J]. Military Operations Research and Systems Engineering, 2004, 18(2):43-47.
[5] 李锋, 万刚, 蒋秉川, 等. 虚拟地理环境时空建模及其作战计划推演应用[J]. 测绘学报, 2018, 47(8):1072-1079. DOI:10.11947/j.AGCS.2018.20180115. LI Feng, WAN Gang, JIANG Bingchuan, et al. Spatio-temporal modeling of virtual geographic environments and its application in battle plan deduction[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(8):1072-1079. DOI:10.11947/j.AGCS.2018.20180115.
[6] 王琦文. 战场态势推理关键技术研究及应用[D]. 西安:西安电子科技大学, 2018. WANG Qiwen. Research and application of key techniques of battlefield situational reasoning[D]. Xian:Xidian University, 2018.
[7] 游雄, 田江鹏. 面向无人自主平台的战场地理环境模型研究[J]. 系统仿真学报, 2020, 32(9):1645-1653. YOU Xiong, TIAN Jiangpeng. Research on geographical battlefield environment model facing autonomous platform[J]. Journal of System Simulation, 2020, 32(9):1645-1653.
[8] 白亮, 郭金林, 老松杨. 基于深度认知神经网络的跨媒体情报大数据智能处理技术[J]. 指挥与控制学报, 2016, 2(4):345-349. BAI Liang, GUO Jinlin, LAO Songyang. Cross-media intelligence processing based on deep cognition neural networks[J]. Journal of Command and Control, 2016, 2(4):345-349.
[9] 李鸿飞, 魏勇, 赵彦庆, 等. 语义模型支持的战场环境数据集成方法[J]. 测绘科学技术学报, 2019, 36(6):632-636, 642. LI Hongfei, WEI Yong, ZHAO Yanqing, et al. Battlefield environment data integration method supported by semantic model[J]. Journal of Geomatics Science and Technology, 2019, 36(6):632-636, 642.
[10] 王保魁, 吴琳, 胡晓峰, 等. 基于知识图谱的联合作战态势实体描述方法[J]. 指挥控制与仿真, 2020, 42(3):8-13. WANG Baokui, WU Lin, HU Xiaofeng, et al. Description method of joint operation situation entity based on knowledge graph[J]. Command Control & Simulation, 2020, 42(3):8-13.
[11] 张永亮, 董浩洋, 刘勇. 基于知识的智能指挥决策运行机制及其支撑技术研究[J]. 军事运筹与系统工程, 2020, 34(2):5-12. ZHANG Yongliang, DONG Haoyang, LIU Yong. Research on the support technology and its intelligent command decision-making mechanism based on knowledge[J]. Military Operations Research and Systems Engineering, 2020, 34(2):5-12.
[12] LACY L W, THERESA T, DOUG R. Extending the military scenario description language (MSDL) to represent deep green course of action descriptions[C]. Proceedings of Spring Simulation Interoperability Worksho, 2010. Orlando:SISO (Simulation Inleroperability Standard Organization), 2010:131-142.
[13] United States Department of Defense. Unmanned systems integrated roadmap FY2017-2042[R]. Washinton D C:United States Department of Defense, 2017.
[14] 陶超, 谭毅华, 彭碧发, 等. 一种基于概率潜在语义模型的高分辨率遥感影像分类方法[J]. 测绘学报, 2011, 40(2):156-162. TAO Chao, TAN Yihua, PENG Bifa, et al. A probabilistic latent semantic analysis based classification for high resolution remotely sensed imagery[J]. Acta Geodaetica et Cartographica Sinica, 2011, 40(2):156-162.
[15] 王志宝, 夏昊, 王成波. 地理信息检索关键技术研究综述[J]. 计算机工程与科学, 2018, 40(3):533-543. WANG Zhibao, XIA Hao, WANG Chengbo. Review of the key techniques of geographic information retrieval[J]. Computer Engineering and Science, 2018, 40(3):533-543.
[16] 罗月童, 刘璐, 刘新月, 等. 空间语义增强下的城市交通事故数据可视分析[J]. 中国图象图形学报, 2019, 24(12):2279-2290. LUO Yuetong, LIU Lu, LIU Xinyue, et al. Visual spatial analytic method for spatial semantic-enhanced urban traffic data[J]. Journal of Image and Graphics, 2019, 24(12):2279-2290.
[17] 段炼, 呙维, 朱欣焰, 等. 基于时空主题模型的微博主题提取[J]. 武汉大学学报(信息科学版), 2014, 39(2):210-213, 243. DUAN Lian, GUO Wei, ZHU Xinyan, et al. Constructing spatio-temporal topic model for microblog topic retrieving[J]. Geomatics and Information Science of Wuhan University, 2014, 39(2):210-213, 243.
[18] 陈世莉, 陶海燕, 李旭亮, 等. 基于潜在语义信息的城市功能区识别——广州市浮动车GPS时空数据挖掘[J]. 地理学报, 2016, 71(3):471-483. CHEN Shili, TAO Haiyan, LI Xuliang, et al. Discovering urban functional regions using latent semantic information:spatiotemporal data mining of floating cars GPS data of Guangzhou[J]. Acta Geographica Sinica, 2016, 71(3):471-483.
[19] 王艳东, 李昊, 王腾, 等. 基于社交媒体的突发事件应急信息挖掘与分析[J]. 武汉大学学报(信息科学版), 2016, 41(3):290-297. WANG Yandong, LI Hao, WANG Teng, et al. The mining and analysis of emergency information in sudden events based on social media[J]. Geomatics and Information Science of Wuhan University, 2016, 41(3):290-297.
[20] 蒋波涛, 王艳东, 叶信岳. 使用点评数据探测城市商业服务设施的发展规律[J]. 测绘学报, 2015, 44(9):1022-1028. DOI:10.11947/j.AGCS.2015.20140556. JIANG Botao, WANU Yandong, YE Xinyue. Detecting development pattern of urban business facilities using reviews data[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(9):1022-1028. DOI:10.11947/j.AGCS.2015.20140556.
[21] 沈盛彧, 刘哲, 张平仓, 等. 一种基于LDA的高分辨率遥感影像检索方法[J]. 长江科学院院报, 2014, 31(8):98-102, 121. SHEN Shengyu, LIU Zhe, ZHANG Pingcang, et al. A method of high-resolution remote sensing image retrieval based on LDA[J]. Journal of Yangtze River Scientific Research Institute, 2014, 31(8):98-102, 121.
[22] MEI Qiaozhu, LIU Chao, SU Hang, et al. A probabilistic approach to spatiotemporal theme pattern mining on weblogs[C]//Proceedings of the 15th International Conference on World Wide Web. Edinburgh, Scotland:ACM, 2006:533-542.
[23] YUAN Quan, CONG Gao, MA Zongyang, et al. Who, where, when and what:discover spatio-temporal topics for twitter users[C]//Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Chicago, Illinois:ACM, 2013:605-613.
[24] HU Bo, JAMALI M, ESTER M. Spatio-temporal topic modeling in mobile social media for location recommendation[C]//Proceedings of the 2013 IEEE 13th International Conference on Data Mining. Dallas, TX:IEEE, 2013:1073-1078.
[25] HONG Liangjie, AHMED A, GURUMURTHY S, et al. Discovering geographical topics in the twitter stream[C]//Proceedings of the 21st International Conference on World Wide Web. Lyon, France:ACM, 2012:769-778.
[26] YIN Zhijun, CAO Liangliang, HAN Jiawei, et al. Geographical topic discovery and comparison[C]//Proceedings of the 20th International Conference on World Wide Web.Hyderabad, India:ACM, 2011:247-256.
[27] ZHAO Fei, DU Qingyun, REN Fu, et al. Syntactic characteristics and a smart construction mechanism for thematic map symbols[J]. Journal of Geodesy and Geoinformation Science, 2019, 2(1):37-48.
[28] 孙锐, 郭晟, 姬东鸿. 融入事件知识的主题表示方法[J]. 计算机学报, 2017, 40(4):791-804. SUN Rui, GUO Sheng, JI Donghong. Topic representation integrated with event knowledge[J]. Chinese Journal of Computers, 2017, 40(4):791-804.
[29] 黄宗财, 仇培元, 陆锋, 等. 基于联合主题特征的网络新闻文本蕴含环境污染事件检测[J]. 地球信息科学学报, 2019, 21(10):1510-1517. HUANG Zongcai, QIU Peiyuan, LU Feng, et al. Detection of environmental pollution events in news corpora based on joint thematic features[J]. Journal of Geo-information Science, 2019, 21(10):1510-1517.
[30] 郭域峰, 战晓苏. 基于LDA的综合集成研讨实验数据聚类分析方法研究[J]. 军事运筹与系统工程, 2016, 30(2):63-67. GUO Yufeng, ZHAN Xiaosu. Research on clustering analysis method of experiment data of comprehensive discussion based on LDA[J]. Military Operations Research and Systems Engineering, 2016, 30(2):63-67.
[31] WANG Xuerui, MCCALLUM A. Topics over time:a non-Markov continuous-time model of topical trends[C]//Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Philadelphia:ACM, 2006:424-433.
[32] 邢汉发, 孟媛, 侯东阳, 等. 一种应用兴趣点数据进行地表覆盖分类的方法[J]. 武汉大学学报(信息科学版), 2019, 44(5):758-764. XING Hanfa, MENG Yuan, HOU Dongyang, et al. A land-cover classification method using point of interest[J]. Geomatics and Information Science of Wuhan University, 2019, 44(5):758-764.