基于时间上下文的军事信息推荐方法  

Recommendation Method of Military Information Based on Time Context

作　　者：王中伟 裘杭萍 孙毅 邓巧雨 WANG Zhongwei;QIU Hangping;SUN Yi;DENG Qiaoyu(College of Command and Control Engineering,Army Engineering University,Nanjing 210007,China)

机构地区：[1]陆军工程大学指挥控制工程学院

出　　处：《指挥信息系统与技术》2019年第6期55-59,共5页Command Information System and Technology

基　　金：国家自然科学青年基金(61802428)资助项目

摘　　要：针对军事信息服务中用户个性化信息需求,研究了基于时间上下文的军事信息推荐方法。首先,根据军事用户特征引入时空属性,建立军事用户画像来描述用户的需求变化;然后,基于传统的协同过滤推荐算法,提出了基于时间上下文的军事信息推荐算法,并将用户时空属性考虑在内;最后,通过军综网爬虫数据集对算法进行了试验验证。试验结果表明,当推荐数量处于[3,9]区间时,该算法较传统算法提高了推荐结果的质量,为提高军事信息服务质量提供参考。Aimed at the personalized information requirements of users in military information service,the military information recommendation method based on tim e context is studied.Firstly,the spatio-temporal attributes are introduced by the characteristics of military users,the military user portrait is established to describe the changes of user needs.Then,based on the traditional collaborative filtering recommendation algorithm,the recommendation algorithm based on tim e context is proposed,and the spatio-temporal attributes of users are taken into account.Finally,the crawler data set of the China military online is used to verify the algorithm.The experimental results show that the algorithm can improve the recommendation results quality compared with the traditional algorithm s as the recommendation quantity in the range of[3,9],and provide a reference for improving military information service quality.

关 键 词：用户画像 时间上下文 信息推荐 协同过滤 军事信息服务 

分 类 号：E917[军事]