基于层次分析法与二元蚁群算法的智能组卷设计  

Design of Intelligent Test Paper Based on AHP and Binary Ant Colony Algorithm

作　　者：金涛[1] 李娜[2] 

机构地区：[1]内蒙古大学鄂尔多斯学院,内蒙古鄂尔多斯017000 [2]内蒙古师范大学传媒学院,内蒙古呼和浩特010010

出　　处：《内蒙古师范大学学报（自然科学汉文版）》2014年第1期114-117,共4页Journal of Inner Mongolia Normal University(Natural Science Edition)

基　　金：内蒙古自然科学基金资助项目(2011MS0909);内蒙古大学鄂尔多斯学院项目(s2011012)

摘　　要：利用改进的二进制蚁群算法,根据试卷总分值、考试时间、试卷平均难度、知识点分值、试卷区分度、题型分值6个约束条件,建立多任务、多目标约束组卷模型;然后利用改进的层次分析法确定组卷目标的权重,通过加权离差模型对智能组卷问题进行建模;最后利用二元蚁群算法求解模型,得到最优组卷方案.层次分析方法比较全面地考虑了出题者的主观因素,而二元蚁群算法充分利用了蚁群算法的智能特点,二者相结合能有效地提高智能组卷的成功率.Make use of improved Binary Ant Colony Algorithm and build multitasking and multi-objec- tive constraint test paper models based on six constraint conditions, that is, total score, total time, paper level, key score, differentiation index, question type and value. Then, calculate the weight of the aims of test paper by taking the advantage of modified AHP, and construct models of intelligent test paper through Weighted Deviation Model （WDM）. Last,utilize Binary Ant Colony Algorithm to solve the model and get the best test paper. AHP takes the subjective factors of the test providers into all-sided consideration,while Binary Ant Colony Algorithm makes the best of the intelligent characters of ant colony algorithm. Their combination can improve the success rate of intelligent test paper effectively.

关 键 词：二元蚁群算法 智能组卷 信息素 层次分析 

分 类 号：TP391.7[自动化与计算机技术—计算机应用技术]