基于个性化排名算法的高考志愿可视推荐研究-《计算机技术与发展》

文章信息/Info

Title:: Research on Visual Recommendation of Novel College Entrance Filling Recommendation Based on Interactive Ranking Algorithm

作者:: 李俊锟1; 李学俊1; 王桂娟1; 陈华容1; 周颖鑫1; 吴亚东2; 1. 西南科技大学计算机科学与技术学院,四川绵阳 621000;
2. 四川轻化工大学计算机科学与工程学院,四川自贡 643000

Author(s):: LI Jun-kun1; LI Xue-jun1; WANG Gui-juan1; CHEN Hua-rong1; ZHOU Ying-xin1; WU Ya-dong2; 1. School of Computer Science and Technology,Southwest University of Science and Technology,Mianyang 621000,China;
2. School of Computer Science and Engineering,Sichuan University of Science and Engineering,Zigong 643000,China

Keywords:: university data visualization; multidimensional visual analysis; interactive ranking; personalized recommendations

摘要:: 高考志愿填报对考生个人发展至关重要,如何有效提升高校志愿填报效率是考生关注的重要问题。针对这一问题,该文提出了一种基于交互式排名算法的高考志愿个性化可视推荐方法。首先,设计了一种个性化志愿推荐算法(NCEF-Rank),通过多目标决策方法量化考生对不同属性特征的偏好,并将其加权至高校多维属性特征中,从而构建新的高校偏序对关系。然后,利用排名支持向量机(Ranking Support Vector Machine,RankSVM)算法模型推荐出个性化的志愿排名列表。其次,采用多视图协调可视化技术,设计了一套交互式的高考志愿推荐可视分析框架。该框架支持用户交互式挖掘志愿的多维属性特征,建立个性化的决策路径,并展示多维属性的排名规则,从而帮助用户高效地从众多的可选志愿中挑选出符合自身个性化需求的高校和专业。最后,通过性能评估和案例分析,验证了算法和框架的有效性。

Abstract:: College entrance examination voluntary reporting is crucial for candidates’ personal development. Improving the efficiency of this process is a significant concern for candidates. To address this,we propose a personalized visual recommendation method for college entrance examination volunteers based on an interactive ranking algorithm. Firstly,a personalized volunteer recommendation algorithm (NCEF - Rank) is designed. It uses a multi - objective decision - making method to quantify candidates’ preferences for different attributes, integrating them into a new partial order pair relationship of universities. Then, the Ranking Support Vector Machine(RankSVM) is then used to recommend a personalized volunteer ranking list. Secondly, multi - view coordination visualization technology is employed to design an interactive visual analysis framework for college entrance examination voluntary recommendations.This framework allows users to interactively explore multidimensional attribute features,establish personalized decision-making paths,and display ranking rules,aiding users in efficiently selecting universities and majors that meet their needs. Finally,the effectiveness of the proposed algorithm and framework is validated through performance evaluations and case analyses.