《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (1): 48-58.DOI: 10.11772/j.issn.1001-9081.2024010010

• 人工智能 • 上一篇    下一篇

强化学习和矩阵补全引导的多目标试卷生成

邢长征1, 梁浚锋1(), 金海波1, 徐佳玉1, 乌海荣2   

  1. 1.辽宁工程技术大学 电子与信息工程学院,辽宁 葫芦岛 125105
    2.阜新市大数据管理中心,辽宁 阜新 123000
  • 收稿日期:2024-01-11 修回日期:2024-03-26 接受日期:2024-03-26 发布日期:2024-05-09 出版日期:2025-01-10
  • 通讯作者: 梁浚锋
  • 作者简介:邢长征(1967—),男,辽宁阜新人,教授,博士,CCF高级会员,主要研究方向:人工智能、数据挖掘;
    金海波(1983—),男,辽宁葫芦岛人,副教授,博士,主要研究方向:随机过程、决策理论;
    徐佳玉(1999—),女,辽宁锦州人,硕士研究生,主要研究方向:数据挖掘、机器学习;
    乌海荣(1977—),女,辽宁阜新人,高级工程师,主要研究方向:信息系统项目管理。
  • 基金资助:
    国家自然科学基金资助项目(62173171)

Multi-objective exam paper generation guided by reinforcement learning and matrix completion

Changzheng XING1, Junfeng LIANG1(), Haibo JIN1, Jiayu XU1, Hairong WU2   

  1. 1.School of Electronic and Information Engineering,Liaoning Technical University,Huludao Liaoning 125105,China
    2.Fuxin Big Data Management Center,Fuxin Liaoning 123000,China
  • Received:2024-01-11 Revised:2024-03-26 Accepted:2024-03-26 Online:2024-05-09 Published:2025-01-10
  • Contact: Junfeng LIANG
  • About author:XING Changzheng, born in 1967, Ph. D., professor. His research interests include artificial intelligence, data mining.
    JIN Haibo, born in 1983, Ph. D., associate professor. His research interests include random process, decision theory.
    XU Jiayu, born in 1999, M. S candidate. Her research interests include data mining, machine learning.
    WU Hairong, born in 1977, senior engineer. Her research interests include information system project management.
  • Supported by:
    National Natural Science Foundation of China(62173171)

摘要:

针对现有的试卷生成技术存在过多关注生成试卷的难易程度,而忽略了其他相关目标,例如质量、分数分布和技能覆盖范围的问题,提出一种强化学习和矩阵补全引导的多目标试卷生成方法,以优化试卷生成领域的特定目标。首先,运用深度知识追踪方法对学生之间的交互信息和响应日志进行建模以获取学生群体的技能熟练程度;其次,运用矩阵分解和矩阵补全方法对学生未做的习题进行得分预测;最后,基于多目标试卷生成策略,为提升Q网络的更新效率,设计一个Exam Q-Network函数逼近器以自动地选择合适的问题集来更新试卷组成。实验结果表明,相较于DEGA (Diseased-Enhanced Genetic Algorithm)、SSA-GA (Sparrow Search Algorithm - Genetic Algorithm)等模型,在试卷难度、合理性、准确性这3个指标上验证了所提模型在解决试卷生成场景的多重困境方面上效果显著。

关键词: 多目标试卷生成, 深度知识追踪, Q网络, 矩阵分解, 矩阵补全

Abstract:

In view of the problem that the existing exam paper generation technologies pay too much attention to the difficulty of generated exam papers, while ignoring other related objectives, such as quality, score distribution, and skill coverage, a multi-objective exam paper generation method guided by reinforcement learning and matrix completion was proposed to optimize the specific objectives in the field of exam paper generation. Firstly, deep knowledge tracking method was used to model the interaction information among students and response logs in order to obtain the skill proficiency of the student group. Secondly, matrix factorization and matrix completion methods were used to predict the scores of students' undone exercises. Finally, based on the multi-objective exam paper generation strategy, in order to improve the Q network update efficiency, an Exam Q-Network function approximator was designed to select the appropriate question set automatically for update of the exam paper composition. Experimental results show that compared with the models such as DEGA (Diseased-Enhanced Genetic Algorithm) and SSA-GA (Sparrow Search Algorithm - Genetic Algorithm), it is verified that the proposed model has significant effect in solving multiple dilemmas of exam paper generation scenarios in terms of three indicators — difficulty, rationality and accuracy. The effect of verifying the models mentioned in the solution of the test papers is significantly effective.

Key words: multi-objective exam paper generation, deep knowledge tracking, Q-Network, matrix decomposition, matrix completion

中图分类号: