摘要
文章基于贝叶斯网络理论,提出了知识覆盖型贝叶斯网学生模型。文章深入探讨了构建贝叶斯网学生模型的方法和途径,并实现了自适应选题算法和推荐引擎算法,使模型具有很强的推理能力。把模型用于在线测试中,能自适应选题,自动结束,结果除获得成绩外,还能诊断,并把测试中未掌握的知识项呈现出来。从而,为准确掌握学生的知识水平,为教学策略的调整和学生进一步学习提供了有力依据。实验表明该算法能高效快捷地将学生测试中未掌握好的知识项产生推荐集合。
A knowledge covering type of the Bayesian network student model was proposed,based on the Bayesian network theory.The method and way of constructing the Bayesian network student model is discussed in this paper,and adaptive topic selection algorithm and recommend engine algorithm are developed,then the model has a strong reasoning ability.Applications of the model in the adaptive on-line test system,which show the model,can adaptive topic selection,automatic end,and results except get score still can diagnosis student ability and the knowledge that was not mastered by student have a show during testing.Thus,by using the model,students＇ knowledge level could be accurately mastered,and provides a strong basis to adjust teaching strategy and students＇ further study.The experiment results show that the proposed technique can efficient quickly will to be produce recommend set that not mastered knowledge in students＇ tests.
出处
《计算机与数字工程》
2012年第2期61-64,共4页
Computer & Digital Engineering
基金
校级基金项目"基于Web考试系统的研究与开发"(编号:DSK201004)资助
关键词
贝叶斯网
在线测试
学生模型
Bayesian network
online testing
student model
