基于sigmoid函数的题目难度值动态调整算法的设计  

The Design of Dynamic Adjustment Algorithm of Difficulty Value Based on Sigmoid Function

作　　者：莫怀训 刘晓瑞[2] MO Huaixun;LIU Xiaorui(Guangdong Light Industry School,Guangzhou 510310,China;Guangzhou City Polytechnic,Guangzhou 510405,China)

机构地区：[1]广东省轻工职业技术学校,广东广州510310 [2]广州城市职业学院,广东广州510405

出　　处：《软件工程》2020年第2期39-42,共4页Software Engineering

基　　金：广东省教育科研“十三五”规划2018年度研究：基于“互联网+教育”背景下的中职机电专业电类基础课程的知识图谱构建与应用研究;项目编号：2018Y QJK365

摘　　要：本文主要针对各级各类信息化教学或考试系统中的题库题目难度值进行讨论,分析如何进行分布计算并动态调整。本文将难度值定义为错误率,即错误次数/调用总次数,再进一步分析发现根据本定义直接进行计算的方法需要进行改进,可用sigmoid函数进行拟合,并在此基础上设计出分布计算算法和线性叠加算法。通过本方法,各终端无须额外存储其他数据,仅根据当前题目回答错误情况即可更新难度值;同时也无须连线中心服务器,可独立分布计算,然后线性叠加即可获得最终难度值。因此可在一定程度上降低整个题库系统设计的难度,同时也可以看出本方法对存储敏感型和去中心的任务具有一定参考价值。This paper mainly discusses the difficulty value of questions in various levels of information-based teaching or examination system,and analyzes how to calculate the distribution and adjust it dynamically.In this paper,the difficulty value is defined as the error rate,that is,the number of errors/the total number of calls.Further analysis shows that the method of calculation directly according to this definition can be improved.The sigmoid function is used for fitting,on this basis,the distribution calculation algorithm and the linear superposition algorithm are designed.Through this method,each terminal does not need to store additional data,and the difficulty value can be updated only based on the answer to the current question.At the same time,there is no need to connect to the central server.The calculation can be independently distributed,and then the final difficulty value linear can be obtained through linear superposition.Therefore,the difficulty of designing the entire test database system can be reduced to a certain extent.At the same time,it can also be seen that this method has certain reference value for storage-sensitive and decentralized tasks.

关 键 词：题目难度值 SIGMOID函数 分布计算 线性叠加 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]