期刊文献+

军事信息精准服务过程中信息特征捕获方法 被引量:5

Information Character Capturing Method in Military Precise Information Service Process
下载PDF
导出
摘要 针对军事信息高维性和高复杂性的特点,提出了军事信息特征捕获方法。信息高维性不仅增加了信息利用复杂度,还严重影响到信息利用和精准服务的效果。明确了军事信息特征捕获概念和内涵,阐述了军事信息特征捕获流程;结合文本、图像、视频和音频等多种分析技术研究了不同承载格式的军事信息内容特征捕获方法;针对具体任务需求,对军事信息任务类别进行分析,得出不同任务条件下信息需求特征;同时,为兼顾用户静态和动态需求,基于用户的背景和访问2种信息分析方式提出了用户需求信息的特征捕获方法。 Aimed at high dimensions and great complexity of the military information, the mili-tary information character capturing method is proposed. The high dimensions increase the com- plexity for using the military information and have negative effects on using the information and precise service. The concept and the connotation of military information character capturing are defined and the process of military information character capturing is systemically introduced. Different kinds of military information character capturing methods are researched based on text analysis, image analysis, video analysis and audio analysis methods. Aimed at certain mission re- quirements, the military information mission species are analyzed and the information require- ment characters are obtained under different mission conditions. The users' requirement informa- tion character capturing methods are proposed based on users' background and visit information for meeting users' static and dynamic requirements.
出处 《指挥信息系统与技术》 2015年第3期24-30,共7页 Command Information System and Technology
基金 国家"973"计划 国家自然科学基金资助项目
关键词 信息精准服务 特征捕获 信息需求 用户需求 precise information service character capturing information requirements usersr re-quirements
  • 相关文献

参考文献6

  • 1刘宗和,卢克旺.中国军事百科全书:学科分册[M].2版.北京:中国大百科全书出版社,2007.
  • 2Schtitze H, HullB A, Pedersen J O. A comparison of classifiers and document representations for the routing problem[C]//Proceedings of the 18th Annual Interna- tional ACM SIGIR Conference on Research and Devel- opment in Information Retrieval. New York: ACM, 1995 : 229-237.
  • 3Sebastiani F. Machine learning in automated text cate- gorization[J].ACM Computing Surveys, 2002, 34 (1) : 1-47.
  • 4Yang Y. Noise reduction in a statistical approach to text categorization[C]//Proceedings of the 18th Annu- al International ACM SIGIR Conference on Researchand Development in Information Retrieval. New York: ACM, 1995: 256-263.
  • 5Deerwester S. Indexing by latent semantic analysis [J]. Journal of American Society for Information Sci- ence, 1990, 41(6): 391-407.
  • 6Lee D, Seung H. Learning the parts of objects by non- negative matrix factorization[J]. Nature, 1999 (401) : 788-791.

同被引文献31

引证文献5

二级引证文献17

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部