计算机与现代化

• 应用与开发 • 上一篇    下一篇

 基于时空聚类分析的自动组卷模型研究

  

  1. 济南大学信息科学与工程学院,山东济南250022
  • 收稿日期:2017-01-11 出版日期:2017-05-26 发布日期:2017-05-31
  • 作者简介: 范玉玲(1976-),女,河北任丘人,济南大学信息科学与工程学院讲师,硕士,研究方向:数据挖掘与信息处理; 董立凯(1978-),男,讲师,硕士,研究方向:智能信息处理; 王钦(1980-),女,讲师,硕士,研究方向:数据挖掘与信息处理; 曹爱增(1972-),男,副教授,硕士,研究方向:人工智能。
  • 基金资助:
     国家自然科学基金资助项目(61302128); 教育部产学合作协同育人项目(201601023018); 济南大学科研基金(自然科学类)资助项目(XKY1622)

 Study on Model of Auto-generating Test Paper Based on Spatial-temporal Clustering

  1. School of Information Science and Engineering, University of Jinan, Jinan 250022, China
  • Received:2017-01-11 Online:2017-05-26 Published:2017-05-31

摘要: 为提高题库自动组卷的质量,以ACM Online Judge系统评测数据为研究对象,将时间方差和平均用时作为时空特征对题目进行自动聚类分析;在聚类基础上,使用各分类所有题目的提交次数和提交解决次数计算每类题目的难度系数,并采用高斯随机过程建立自动组卷模型。与传统经验组卷方法相比较,提出的自动组卷模型以题目难度和区分度为依据,组卷质量可科学评价测试者知识水平。实验结果表明,提出的自动组卷模型简单有效,适用性强。

关键词:  , 时空特征, 聚类算法, 难度系数, 自动组卷

Abstract:  To improve the quality of auto-generating test paper, a novel method is investigated on testing data from ACM Online Judge system, in which auto-clustering is done on questions by the features of temporal fluctuations and mean of time consumption firstly, then the difficulty coefficient is calculated through the submitting times and solved times of all types of questions, and eventually the model of auto-generating test paper is constructed by Gaussian stochastic process. Compared to the traditional model, the proposed model can scientifically evaluate testers’ knowledge level in the light of the difficulty and discrimination of questions. The experimental results suggest that the model is simple but effective and has strong adaptability.

Key words:  spatial-temporal feature, clustering algorithm, difficult coefficient, auto-generating test paper