Web时态对象模型研究分析  

Research and analysis of Web temporal object model

作　　者：李淑霞[1] 杨俊成[1] Li Shuxia;Yang Juncheng(School of Electronic Information Engineering,Henan Polytechnic Institute,Nanyang 473000,China)

机构地区：[1]河南工业职业技术学院电子信息工程学院,南阳473000

出　　处：《现代计算机》2023年第8期51-56,共6页Modern Computer

基　　金：河南省科技厅科技攻关项目(222102210203);河南省教育厅高等学校重点科研项目(22B520009);全国高等院校计算机基础教育研究会纵向课题(2022⁃AFCEC⁃288、2022⁃AFCEC⁃295)。

摘　　要：研究Web内容要素中加入时态要素的Web时态对象模型,解决层次树结构对站点、栏目、子栏目和内容统一建模问题,根据数据与时序密切相关的特性,利用时态特征词对各时态要素进行自动提取及评估,提出利用LSTM网络学习时态节点之间的时态约束关系,将Attention机制引入预测模型;实验表明该体系能自动发现Web过时信息,在同类网站质量排序、时间感知的搜索排序等方面有着重要的应用前景,能极大地节约人力,提高Web信息质量。This paper studies the Web temporal object model and adds temporal elements to the Web content elements.So as to solve the problem of unified modeling of site,column,sub column and content by hierarchical tree structure.According to the characteristics of data closely related to time series,this paper uses temporal feature words to automatically extract and evaluate various temporal elements,and proposes to use LSTM network to learn the temporal constraints between temporal nodes.At the same time,the Attention mechanism is introduced into the prediction model.Experimental results show that the system can automatically discover outdated Web information,and it has important application prospects in the quality ranking of similar websites and time aware search ranking,etc.It can greatly save manpower and improve the quality of Web information.

关 键 词：深度学习 时态要素 时态对象模型 时态特征词 层次树 

分 类 号：TP393.09[自动化与计算机技术—计算机应用技术]