基于数据挖掘的网络情景化信息动态推荐系统  

Dynamic Recommendation System of Network Situational Information Based on Data Mining

作　　者：王喜宾 王玉标[2] 杨剑锋 WANG Xi-bin;WANG Yu-biao;YANG Jian-feng(Guizhou Institute of Technology,School of Data Science,Caiguan Road,Guiyang Guizhou 550003,China;School of Big Data&Software Engeering,Chongqing University,Chongqing 400030,China)

机构地区：[1]贵州理工学院大数据学院,贵州贵阳550003 [2]重庆大学大数据与软件学院,重庆400030

出　　处：《计算机仿真》2020年第11期344-347,379,共5页Computer Simulation

基　　金：国家自然科学基金项目(71901078);贵州省科技厅科学技术基金(黔科合基础[2020]1Y269);贵州省科技厅学术新苗项目(黔科合平台人才[2017]5789-21);贵州理工学院高层次人才项目(XJGC20190929);重庆市教委科技计划项目(KJQN201900102)。

摘　　要：传统方法难以区分用户不同的兴趣稀疏性特征,导致用户在访问网络时无法准确快速地浏览偏好的目标数据,因此提出基于数据挖掘的网络情境化信息动态推荐系统。收集网络用户的情景化信息属性,对应划分网络用户不同的兴趣稀疏性特征,利用协同过滤算法提取信息资源的语义相似度特征,并融合信息的稀疏性特征;根据融合特征构建资源访问节点之间存在的信任关系,建造知识库与模型库,进而为情景化信息动态推荐的硬件设计供给交互数据;通过ART算法内的Apriori算法分析交互数据,完成网络情景化信息动态推荐。仿真结果表明,所提方法能够更加快速的分析网络用户的兴趣与偏好,同时还能够处理一些较为新颖的信息,具有较好的实用性。It is difficult for traditional methods to distinguish the different sparse characteristics of users'interests,so users can’t accurately and quickly browse the target data.Therefore,a system of dynamic situational information recommendation based on data mining was presented.Firstly,the network users’situational information attributes were collected.Correspondingly,different sparse features were classified,and then the collaborative filtering algorithm was used to extract the semantic similarity characteristics of information resource.Meanwhile,the sparse characteristics of information were mixed together to construct the trust relationships between resource access nodes.Moreover,knowledge base and model base were built to provide interactive data for the hardware design of dynamic recommendation of situational information.Finally,Apriori algorithm in ART algorithm was used to analyze the interactive data and thus to complete the dynamic recommendation for network situational information.Simulation results prove that the proposed method can more quickly analyze network users’interests and preferences and process some new information,so it has better practicability.

关 键 词：数据挖掘 情景化 动态推荐 特征提取 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]