基于PageRank算法的校园好友关系分析  

Campus Friend Relationship Analysis Based on Pagerank Algorithm

作　　者：王全民[1] 赵亚康 WANG Quan-min;ZHAO Ya-kang(School of Computer,Beijing University of Technology,Beijing 100124,China)

机构地区：[1]北京工业大学计算机学院

出　　处：《计算机技术与发展》2020年第1期140-143,共4页Computer Technology and Development

基　　金：国家自然科学基金(61272500)

摘　　要：随着校园信息化、数字化建设的普及,作为该建设进程重要组成部分的"校园一卡通"系统的建设也逐步深入,校园一卡通系统是校园信息化建设中信息采集的基础工程。利用校园一卡通系统采集的学生日常生活数据去分析学生的行为特点,挖掘出大数据中隐藏的价值,将在很大程度上帮助学校的日常管理并为学校领导提供相关决策依据。文中以学生校园生活中的一卡通消费数据为研究对象,首先应用高斯相似度函数构造相似度矩阵,系统地对学生间好友关系进行研究分析;然后应用PageRank算法找出疑似"孤立"学生或者是社交圈较小的学生群体,及早发现不善交友的学生群体,为学校的相关管理部门提供数据支撑,以便引导学生更健康的交友,构造和谐校园;最后通过实验进行了有效性验证。With the popularization of campus informatization and digitalization construction,the construction of“campus all-in-one card” system,which is an important part of the construction process,has been gradually deepened.The campus all-in-one card system is the basic project of information collection in the campus informatization construction.The daily life data collected by the campus onecard system are used to analyze the behavior characteristics of students and dig out the hidden value in big data,which will greatly help the daily management of the school and provide relevant decision-making basis for school leaders.The students' campus life of IC card consumption data is taken as the research object.First of all,we use the Gaussian similarity function to construct the similarity matrix,and carry on the research analysis to the friend relation between the students.Then we adopt PageRank algorithm to identify suspected“isolated” students or students with small social circles,timely detection of students who are not good at making friends,to provide data support for school related management department and guide students to healthier dating,constructing harmonious campus.Finally,the validity verification is carried out by experiment.

关 键 词：一卡通 数据分析 高斯相似度 PAGERANK 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]