面向属性概念格下的知识状态转移方法  

Knowledge-state Transfer Method Based on Attribute-oriented Concept Lattices

作　　者：朱泳帆 许晴媛 周银凤[3] 王大利 李进金 张培林 ZHU Yongfan;XU Qingyuan;ZHOU Yinfeng;WANG Dali;LI Jinjin;ZHANG Peilin(School of Computer Science,Minnan Normal University,Zhangzhou 363000,China;Fujian Provincial University Key Laboratory of Data Science and Intelligent Application(Minnan Normal University),Zhangzhou 363000,China;School of Mathematics and Statistics,Shaanxi Normal University,Xi′an 710119,China;School of Mathematics and Statistics,Minnan Normal University,Zhangzhou 363000,China;Fujian Provincial Key Laboratory of Granular Computing and Its Application(Minnan Normal University),Zhangzhou 363000,China)

机构地区：[1]闽南师范大学计算机学院,福建漳州363000 [2]数据科学与智能应用福建省高校重点实验室(闽南师范大学),福建漳州363000 [3]陕西师范大学数学与统计学院,西安710119 [4]闽南师范大学数学与统计学院,福建漳州363000 [5]福建省粒计算及其应用重点实验室(闽南师范大学),福建漳州363000

出　　处：《小型微型计算机系统》2024年第11期2647-2655,共9页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(62076221)资助;福建省自然科学基金项目(2022J01912)资助;福建省大学生创新训练项目(S202210402024)资助.

摘　　要：如何高效率地寻找猜测答对或粗心答错情况下不相容答题状态对应受测者真实的知识状态是目前计算机自适应测试领域研究的一个热点问题.现有知识状态转移方法时间成本高,不适用于含有大量测试问题和技能的应用场景.并且,现有知识状态转移方法将合取模型和能力模型均视为能力模型,采用同一种方法进行知识状态转移,灵活性不够,评估效率不高.本文针对合取模型和能力模型,分别提出基于面向属性概念格的知识状态转移方法.首先由技能映射或多映射建立技能背景并诱导出对应的面向属性概念格,进一步使用概念格中概念的外延并结合最大概率方法得到受测者猜测或粗心情况下的真实知识状态,最后给出知识评估过程.实验表明,在知识评估结果相同的前提下,本文所提方法相比现有方法极大地降低了评估时间成本,因此具有更好的性能.How to efficiently find the incompatible answer state in the case of guessing right or careless answer corresponding to the real knowledge state of the subject is a hot issue in the field of computer adaptive testing at present.The existing knowledge state transfer method has a high time cost and is not suitable for application scenarios with a large number of test problems and skills.Moreover,the existing knowledge state transfer method regards the combined model and the ability model as the ability model.The same method is used for knowledge state transfer,which is not flexible enough and the evaluation efficiency is not high.This paper proposes a knowledge state transfer method based on the attribute-oriented concept lattice for the combined model and the ability model respectively.First of all,the skill background is established by skill mapping or multiple mapping and the corresponding attribute-oriented concept grid is induced.The extension of the concept in the concept grid is further used and combined with the maximum probability method to obtain the real knowledge state of the subject′s guess or carelessness.Finally,the knowledge evaluation process is given.Experiments show that under the premise that the knowledge evaluation results are the same,the method proposed in this article greatly reduces the evaluation time cost compared with the existing methods,so it has better performance.

关 键 词：知识空间理论 形式概念分析 自适应测试 知识评估 知识状态转移 面向属性概念格 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]