基于相似性控制的智能出题方法及实现  

Intelligent Question Setting Method and Implementation Based on Similarity Control

作　　者：李菊 李蒙 吴庆阳 蔡泰锋 LI Ju;LI Meng;WU Qingyang;CAI Taifeng(College of Big Data and Internet,Shenzhen Technology University,Shenzhen Guangdong 518000,China)

机构地区：[1]深圳技术大学大数据与互联网学院,广东深圳518000

出　　处：《信息与电脑》2024年第17期205-207,共3页Information & Computer

基　　金：深圳技术大学新引进高端人才财政补助科研启动项目(项目编号:GDRC202132);天地一体化融合网络智能边缘计算终端及协同组网体制的研究(项目编号:2022010802002);草地放牧系统可持续管理关键计算模型研发(项目编号:2021ZD0044);深圳技术大学自制实验仪器设备基金资助项目(项目编号:2021015777701043)。

摘　　要：出题是计算机编程类上机实验的重要工作,目前部分大学开设的编程实验课程,存在多个班级无法同时上机实验的情况,如何保证公平性和有效性是出题的关键问题。结合每次实验同一班级实验题的差异性,以及不同班级实验题的相似性需求,本文提出了一种基于相似性控制的智能出题方法。实验结果表明,该方法不仅可以保证不同组实验题的相似度较高但又不完全相同,确保平时实验测试的公平性,还能保证同一组实验题具有一定差异,从而促进出题的有效性。Problems is an important work of computer programming class on-line experiments,at present,some universities offer programming experimental courses,there are multiple classes can not be at the same time on-line experiments,how to ensure fairness and effectiveness is the key issue of problem solving.Combined with the difference of the experimental questions of the same class in each experiment,and the similarity demand of the experimental questions of different classes,this paper proposes an intelligent question-asking method based on similarity control.The experimental results show that the method can not only ensure that different groups of experimental questions have a high degree of similarity but are not identical,ensuring the fairness of the usual experimental test,but also ensure that the same group of experimental questions have a certain degree of difference,thus promoting the effectiveness of the questions.

关 键 词：公平性 有效性 相似性控制 智能出题 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]