《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (7): 2043-2055.DOI: 10.11772/j.issn.1001-9081.2024070970
• CCF第39届中国计算机应用大会 (CCF NCCA 2024) • 下一篇
收稿日期:
2024-07-03
修回日期:
2024-09-06
接受日期:
2024-09-25
发布日期:
2025-07-10
出版日期:
2025-07-10
通讯作者:
张丽萍
作者简介:
索晋贤(2001—),男,山西大同人,硕士研究生,CCF学生会员,主要研究方向:教育数据挖掘、智慧教育基金资助:
Jinxian SUO, Liping ZHANG(), Sheng YAN, Dongqi WANG, Yawen ZHANG
Received:
2024-07-03
Revised:
2024-09-06
Accepted:
2024-09-25
Online:
2025-07-10
Published:
2025-07-10
Contact:
Liping ZHANG
About author:
SUO Jinxian, born in 2001, M. S. candidate. His research interests include educational data mining,smart education.Supported by:
摘要:
知识追踪(KT)是一种认知诊断方法,旨在通过学习者的历史答题记录,模拟学习者对于学习知识的掌握程度,最终预测学习者未来的答题情况。目前基于深度神经网络模型的知识追踪技术以强大的特征提取能力和优越的预测能力成为知识追踪领域研究的热点;然而,基于深度学习的知识追踪模型通常缺乏较好的可解释性。清晰的可解释性不仅可以让学习者和教师充分理解知识追踪模型的推理过程和预测结果,从而为下一步学习制定符合当前知识状态的学习计划,还能够提升学习者和教师对知识追踪模型的信任程度。因此,对可解释的深度知识追踪(DKT)方法进行综述。首先,介绍知识追踪的发展历程,并介绍可解释性的定义和必要性;其次,从特征提取和模型内部提升两方面,对解决DKT模型缺乏可解释性而提出的改进方法进行总结和梳理;再次,介绍现有的可供研究者使用的相关公开数据集,并分析数据集内的数据特征对可解释性的影响,从而探讨如何从模型性能和可解释性两个方面对知识追踪模型进行评价,并整理DKT模型在不同数据集上的性能表现;最后,对DKT模型目前存在的问题提出一些未来可能的研究方向。
中图分类号:
索晋贤, 张丽萍, 闫盛, 王东奇, 张雅雯. 可解释的深度知识追踪方法综述[J]. 计算机应用, 2025, 45(7): 2043-2055.
Jinxian SUO, Liping ZHANG, Sheng YAN, Dongqi WANG, Yawen ZHANG. Review of interpretable deep knowledge tracing methods[J]. Journal of Computer Applications, 2025, 45(7): 2043-2055.
名称 | 技术举例 | 优点 | 缺点 |
---|---|---|---|
传统认知诊断模型 | 项目反应理论[ | 可解释性好 | 无法捕捉学生复杂学习行为特征 |
传统知识追踪模型 | 贝叶斯理论[ | 知识追踪过程和预测结果具有良好统计学可解释性 | 学生知识状态建模不充分;模型泛化能力差 |
基于深度学习的模型 | 深度神经网络[ | 可以处理多概念习题;对学生知识状态和习题特征建模更充分 | 深度知识追踪模型内部结构不透明,模型可解释性差 |
表1 知识追踪技术发展历史
Tab. 1 Development history of knowledge tracking technology
名称 | 技术举例 | 优点 | 缺点 |
---|---|---|---|
传统认知诊断模型 | 项目反应理论[ | 可解释性好 | 无法捕捉学生复杂学习行为特征 |
传统知识追踪模型 | 贝叶斯理论[ | 知识追踪过程和预测结果具有良好统计学可解释性 | 学生知识状态建模不充分;模型泛化能力差 |
基于深度学习的模型 | 深度神经网络[ | 可以处理多概念习题;对学生知识状态和习题特征建模更充分 | 深度知识追踪模型内部结构不透明,模型可解释性差 |
一级分类 | 二级分类 | 模型 | 改进方法 |
---|---|---|---|
不同特征角度对可解释性提升方法 | 学习者特征角度 | RKT[ | 增加学习者遗忘因素;考虑学习者重复练习的次数、练习之间的时间间隔、过去练习的数量 |
DKT+forgetting[ | 额外考虑了学习者与上一次互动的时间间隔、对问题的过去尝试次数对遗忘因素的影响 | ||
GKT-FM[ | 综合考虑了7种影响学习者遗忘因素的特征 | ||
LFKT[ | 额外添加学习者重复学习知识点的间隔时间、次数以及顺序学习间隔和掌握程度4种特征 | ||
LFEKT[ | 考虑学习者答题顺序以及答题表现对预测结果的影响 | ||
文献[ | 考虑学习者学习特征的动态性以及静态性 | ||
QRAKT[ | 考虑学习者答题过程中的猜题、跳题行为对预测结果的影响 | ||
MLB-KT[ | 考虑到不同学习者行为特征之间的相互影响 | ||
习题特征角度 | TSKT[ | 考虑历史知识点对当前知识点的影响,添加习题内知识点空间关系特征 | |
QFEKT[ | 添加知识点和习题关系的特征 | ||
FRKT[ | 拆分习题中的知识点,挖掘习题语义和难度信息 | ||
GAKT-IRT[ | 挖掘习题及概念的深层次特征对学习者答题的影响 | ||
ER-KTCP[ | 考虑了习题概念的先修关系特征 | ||
C&RM-MAKT[ | 考虑历史答题序列的影响 | ||
DGKT[ | 考虑了问题和概念特征的动态状态以及问题和概念之间的结构特征 | ||
模型内可解释性提升方法 | 添加注意力机制 | IDKT[ | 在模型内增加个性化注意力机制 |
MAKT[ | 注意力机制与元路径结合 | ||
AKTHE[ | 注意力机制和异质信息网络嵌入 | ||
ATCKT[ | 模型内添加针对练习的注意力机制 | ||
ADKT[ | 在DKT基础上增加注意力机制 | ||
结合项目反应理论或其他理论 | QIKT[ | 在模型预测层应用IRT提升预测结果解释性 | |
KIKT[ | 在键值记忆网络内添加IRT增强对学习者表现预测的解释 | ||
DKVMN-GACART-IRT[ | 在动态键值记忆网络内融合Deep-IRT | ||
TC-MIRT[ | 在深度神经网络内融合MIRT | ||
HHSKT[ | 将DKT模型与TrueSkill习题整合 |
表2 可解释性提升方法总结
Tab. 2 Summary of explainability enhancement methods
一级分类 | 二级分类 | 模型 | 改进方法 |
---|---|---|---|
不同特征角度对可解释性提升方法 | 学习者特征角度 | RKT[ | 增加学习者遗忘因素;考虑学习者重复练习的次数、练习之间的时间间隔、过去练习的数量 |
DKT+forgetting[ | 额外考虑了学习者与上一次互动的时间间隔、对问题的过去尝试次数对遗忘因素的影响 | ||
GKT-FM[ | 综合考虑了7种影响学习者遗忘因素的特征 | ||
LFKT[ | 额外添加学习者重复学习知识点的间隔时间、次数以及顺序学习间隔和掌握程度4种特征 | ||
LFEKT[ | 考虑学习者答题顺序以及答题表现对预测结果的影响 | ||
文献[ | 考虑学习者学习特征的动态性以及静态性 | ||
QRAKT[ | 考虑学习者答题过程中的猜题、跳题行为对预测结果的影响 | ||
MLB-KT[ | 考虑到不同学习者行为特征之间的相互影响 | ||
习题特征角度 | TSKT[ | 考虑历史知识点对当前知识点的影响,添加习题内知识点空间关系特征 | |
QFEKT[ | 添加知识点和习题关系的特征 | ||
FRKT[ | 拆分习题中的知识点,挖掘习题语义和难度信息 | ||
GAKT-IRT[ | 挖掘习题及概念的深层次特征对学习者答题的影响 | ||
ER-KTCP[ | 考虑了习题概念的先修关系特征 | ||
C&RM-MAKT[ | 考虑历史答题序列的影响 | ||
DGKT[ | 考虑了问题和概念特征的动态状态以及问题和概念之间的结构特征 | ||
模型内可解释性提升方法 | 添加注意力机制 | IDKT[ | 在模型内增加个性化注意力机制 |
MAKT[ | 注意力机制与元路径结合 | ||
AKTHE[ | 注意力机制和异质信息网络嵌入 | ||
ATCKT[ | 模型内添加针对练习的注意力机制 | ||
ADKT[ | 在DKT基础上增加注意力机制 | ||
结合项目反应理论或其他理论 | QIKT[ | 在模型预测层应用IRT提升预测结果解释性 | |
KIKT[ | 在键值记忆网络内添加IRT增强对学习者表现预测的解释 | ||
DKVMN-GACART-IRT[ | 在动态键值记忆网络内融合Deep-IRT | ||
TC-MIRT[ | 在深度神经网络内融合MIRT | ||
HHSKT[ | 将DKT模型与TrueSkill习题整合 |
数据集 | 题目数 | 学习者数 | 做题数 | 学习者平均做题数 | 数据集网站 |
---|---|---|---|---|---|
ASSIST2009 | 110 | 4 151 | 325 637 | 78 | https://sites.google.com/site/assistmentsdata/home/assistment-2009-2010-data/skill-builder-data-2009-2010 |
ASSIST2012 | 45 716 | 27 066 | 2 541 201 | 94 | https://sites.google.com/site/assistmentsdata/home/2012-13-school-data-with-affect |
ASSIST2017 | 102 | 1 709 | 942 816 | 552 | https://sites.google.com/view/assistmentsdatamining |
Statics2011 | 1 223 | 333 | 189 927 | 570 | https://pslcdatashop.web.cmu.edu/DatasetInfo?datasetId=507 |
EdNet | 13 169 | 784 309 | 131 441 538 | 167 | https://github.com/riiid/ednet |
Junyi | 701 | >50 000 | 7 868 952 | 157 | https://pslcdatashop.web.cmu.edu/DatasetInfo?datasetId=1198 |
MOOCCubeX | 35 8265 | 3 330 294 | >200 000 000 | 558 | https://github.com/THU-KEG/MOOCCubeX/blob/main/README-cn.md |
表3 数据集信息
Tab. 3 Dataset information
数据集 | 题目数 | 学习者数 | 做题数 | 学习者平均做题数 | 数据集网站 |
---|---|---|---|---|---|
ASSIST2009 | 110 | 4 151 | 325 637 | 78 | https://sites.google.com/site/assistmentsdata/home/assistment-2009-2010-data/skill-builder-data-2009-2010 |
ASSIST2012 | 45 716 | 27 066 | 2 541 201 | 94 | https://sites.google.com/site/assistmentsdata/home/2012-13-school-data-with-affect |
ASSIST2017 | 102 | 1 709 | 942 816 | 552 | https://sites.google.com/view/assistmentsdatamining |
Statics2011 | 1 223 | 333 | 189 927 | 570 | https://pslcdatashop.web.cmu.edu/DatasetInfo?datasetId=507 |
EdNet | 13 169 | 784 309 | 131 441 538 | 167 | https://github.com/riiid/ednet |
Junyi | 701 | >50 000 | 7 868 952 | 157 | https://pslcdatashop.web.cmu.edu/DatasetInfo?datasetId=1198 |
MOOCCubeX | 35 8265 | 3 330 294 | >200 000 000 | 558 | https://github.com/THU-KEG/MOOCCubeX/blob/main/README-cn.md |
模型 | ASSIST2009 | ASSIST2012 | ASSIST2017 | Statics2011 | EdNet | Junyi | ||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
AUC | ACC | AUC | ACC | AUC | ACC | AUC | ACC | AUC | ACC | AUC | ACC | |
RKT | 0.793 0 | 0.719 0 | 0.860 0 | 0.770 0 | ||||||||
DKT+forgetting | 0.730 9 | |||||||||||
GKT-FM | 0.849 0 | 0.835 0 | ||||||||||
LFKT | 0.751 3 | 0.723 0 | ||||||||||
LFEKT | 0.841 0 | 0.809 0 | 0.795 0 | 0.766 0 | 0.835 0 | 0.807 0 | ||||||
QRAKT | 0.771 0 | 0.702 0 | ||||||||||
MLB-KT | 0.768 0 | 0.815 0 | 0.864 0 | |||||||||
TSKT | 0.788 3 | 0.788 2 | 0.801 7 | 0.803 0 | 0.873 9 | 0.845 7 | ||||||
QFEKT | 0.802 1 | 0.752 6 | 0.827 8 | 0.781 2 | 0.763 6 | 0.728 2 | ||||||
FRKT | 0.850 0 | 0.769 0 | ||||||||||
GAKT-IRT | 0.782 1 | 0.846 1 | ||||||||||
DGKT | 0.816 0 | 0.763 0 | 0.797 0 | 0.746 0 | 0.762 0 | 0.723 0 | ||||||
IDKT | 0.800 1 | 0.751 7 | 0.786 6 | 0.758 7 | 0.744 1 | 0.717 3 | ||||||
ATCKT | 0.849 9 | 0.856 5 | 0.837 1 | 0.815 9 | ||||||||
ADKT | 0.803 0 | 0.744 0 | 0.806 0 | 0.738 0 | ||||||||
QIKT | 0.787 8 | |||||||||||
HHSKT | 0.816 0 | 0.749 0 | 0.842 0 | 0.757 0 | 0.826 0 | 0.852 0 |
表4 不同模型性能对比
Tab. 4 Performance comparison of different models
模型 | ASSIST2009 | ASSIST2012 | ASSIST2017 | Statics2011 | EdNet | Junyi | ||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
AUC | ACC | AUC | ACC | AUC | ACC | AUC | ACC | AUC | ACC | AUC | ACC | |
RKT | 0.793 0 | 0.719 0 | 0.860 0 | 0.770 0 | ||||||||
DKT+forgetting | 0.730 9 | |||||||||||
GKT-FM | 0.849 0 | 0.835 0 | ||||||||||
LFKT | 0.751 3 | 0.723 0 | ||||||||||
LFEKT | 0.841 0 | 0.809 0 | 0.795 0 | 0.766 0 | 0.835 0 | 0.807 0 | ||||||
QRAKT | 0.771 0 | 0.702 0 | ||||||||||
MLB-KT | 0.768 0 | 0.815 0 | 0.864 0 | |||||||||
TSKT | 0.788 3 | 0.788 2 | 0.801 7 | 0.803 0 | 0.873 9 | 0.845 7 | ||||||
QFEKT | 0.802 1 | 0.752 6 | 0.827 8 | 0.781 2 | 0.763 6 | 0.728 2 | ||||||
FRKT | 0.850 0 | 0.769 0 | ||||||||||
GAKT-IRT | 0.782 1 | 0.846 1 | ||||||||||
DGKT | 0.816 0 | 0.763 0 | 0.797 0 | 0.746 0 | 0.762 0 | 0.723 0 | ||||||
IDKT | 0.800 1 | 0.751 7 | 0.786 6 | 0.758 7 | 0.744 1 | 0.717 3 | ||||||
ATCKT | 0.849 9 | 0.856 5 | 0.837 1 | 0.815 9 | ||||||||
ADKT | 0.803 0 | 0.744 0 | 0.806 0 | 0.738 0 | ||||||||
QIKT | 0.787 8 | |||||||||||
HHSKT | 0.816 0 | 0.749 0 | 0.842 0 | 0.757 0 | 0.826 0 | 0.852 0 |
[1] | MARTÍN A C, ALARIO-HOYOS C, KLOOS C D. Smart education: a review and future research directions [J]. Proceedings, 2019, 37(1): No.57. |
[2] | MORZE N V, SMYRNOVA-TRYBULSKA E, GLAZUNOVA O. Design of a university learning environment for SMART education [M]// ISSA T, KOMMERS P, ISSA T, et al. Smart technology applications in business environments. Hershey, PA: IGI Global, 2017: 221-248. |
[3] | ABDELRAHMAN G, WANG Q, NUNES B. Knowledge tracing: a survey [J]. ACM Computing Surveys, 2023, 55(11): No.224. |
[4] | LIANG Y, PENG T, PU Y, et al. HELP-DKT: an interpretable cognitive model of how students learn programming based on deep knowledge tracing [J]. Scientific Reports, 2022, 12: No.4012. |
[5] | LIU Y, ZHANG T, WANG X, et al. New development of cognitive diagnosis models [J]. Frontiers of Computer Science, 2023, 17(1): No.171604. |
[6] | HARVEY R J, HAMMER A L. Item response theory [J]. The Counseling Psychologist, 1999, 27(3): 353-383. |
[7] | 丁泽元,梁嘉辉,张云飞,等.现代智慧教育下的认知诊断模型比较分析研究[J].计算机技术与发展,2023, 33(12): 1-7. |
DING Z Y, LIANG J H, ZHANG Y F, et al. Comparative analysis research of cognitive diagnostic models under modern smart education [J]. Computer Technology and Development, 2023, 33(12): 1-7. | |
[8] | RECKASE M D. 18 Multidimensional item response theory [J]. Handbook of Statistics, 2006, 26: 607-642. |
[9] | CORBETT AT, ANDERSON J R. Knowledge tracing: modeling the acquisition of procedural knowledge [J]. User Modeling and User-Adapted Interaction, 1994, 4: 253-278. |
[10] | LIU F, HU X G, BU C, et al. Fuzzy Bayesian knowledge tracing [J]. IEEE Transactions on Fuzzy Systems, 2022, 30(7): 2412-2425. |
[11] | KÄSER T, KLINGLER S, SCHWING A G, et al. Dynamic Bayesian networks for student modeling [J]. IEEE Transactions on Learning Technologies, 2017, 10(4): 450-462. |
[12] | 黄诗雯,刘朝晖,罗凌云,等.融合行为和遗忘因素的贝叶斯知识追踪模型研究[J].计算机应用研究,2021, 38(7): 1993-1997. |
HUANG S W, LIU Z H, LUO L Y, et al. Research on Bayesian knowledge tracing model integrating behavior and forgetting factors [J]. Application Research of Computers, 2021, 38(7): 1993-1997. | |
[13] | 张暖,江波.学习者知识追踪研究进展综述[J].计算机科学,2021, 48(4): 213-222. |
ZHANG N, JIANG B. Review progress of learner knowledge tracing [J]. Computer Science, 2021, 48(4): 213-222. | |
[14] | LU Y, WANG D L, MENG Q, et al. Towards interpretable deep learning models for knowledge tracing [C]// Proceedings of the 2020 International Conference Artificial Intelligence in Education, LNCS 12164. Cham: Springer, 2020: 185-190. |
[15] | PIECH C, BASSEN J, HUANG J, et al. Deep knowledge tracing [C]// Proceedings of the 29th International Conference on Neural Information Processing Systems — Volume 1. Cambridge: MIT Press, 2015: 505-513. |
[16] | 张鹏,文磊. F-TCKT:融合遗忘因素的深度时序卷积知识追踪模型[J].计算机应用研究,2023, 40(4): 1070-1074. |
ZHANG P, WEN L. F-TCKT: deep temporal convolution knowledge tracing model with forgetting factors [J]. Application Research of Computers, 2023, 40(4): 1070-1074. | |
[17] | 琚生根,康睿,赵容梅,等.多知识点融合嵌入的深度知识追踪模型[J].软件学报,2023, 34(11): 5126-5142. |
JU S G, KANG R, ZHAO R M, et al. Deep knowledge tracing model based on embedding of fused multiple concepts [J]. Journal of Software, 2023, 34(11): 5126-5142. | |
[18] | 陈冲,陈杰,张慧,等.深度学习可解释性综述[J].计算机科学,2023, 50(5): 52-63. |
CHEN C, CHEN J, ZHANG H, et al. Review on interpretability of deep learning [J]. Computer Science, 2023, 50(5): 52-63. | |
[19] | 窦慧,张凌茗,韩峰,等.卷积神经网络的可解释性研究综述[J].软件学报,2024, 35(1): 159-184. |
DOU H, ZHANG L M, HAN F, et al. Survey on convolutional neural network interpretability [J]. Journal of Software, 2024, 35(1): 159-184. | |
[20] | 刘坤佳,李欣奕,唐九阳,等.可解释深度知识追踪模型[J].计算机研究与发展,2021, 58(12): 2618-2629. |
LIU K J, LI X Y, TANG J Y, et al. Interpretable deep knowledge tracing [J]. Journal of Computer Research and Development, 2021, 58(12): 2618-2629. | |
[21] | LU Y, WANG D, CHEN P, et al. Interpreting deep learning models for knowledge tracing [J]. International Journal of Artificial Intelligence in Education, 2023, 33(3): 519-542. |
[22] | 贾瑞,董永权,刘源,等.知识点相关性与遗忘程度融合的深度知识追踪模型[J/OL].计算机研究与发展[2024-09-01].. |
JIA R, DONG Y Q, LIU Y, et al. Deep knowledge tracing model with the integration of skills relation and forgetting degree [J/OL]. Journal of Computer Research and Development [2024-09-01]. . | |
[23] | 张凯,刘月,覃正楚,等.概念表示增强的知识追踪模型[J].计算机应用研究,2022, 39(11): 3309-3314. |
ZHANG K, LIU Y, QIN Z C, et al. Concept representation enhanced knowledge tracing [J]. Application Research of Computers, 2022, 39(11): 3309-3314. | |
[24] | 李浩君,方璇,戴海容.基于自注意力机制和双向GRU神经网络的深度知识追踪优化模型[J].计算机应用研究,2022, 39(3): 732-738. |
LI H J, FANG X, DAI H R. Deep knowledge tracing optimization model based on self-attention mechanism and bidirectional GRU neural network [J]. Journal of Computer Applications Research, 2022, 39(3): 732-738. | |
[25] | WANG W, MA H, ZHAO Y, et al. Relevance-aware Q-matrix calibration for knowledge tracing [C]// Proceedings of the 2021 International Conference on Artificial Neural Networks, LNCS 12893. Cham: Springer, 2021: 101-112. |
[26] | PANDEY S, SRIVASTAVA J. RKT: relation-aware self-attention for knowledge tracing [C]// Proceedings of the 29th ACM International Conference on Information and Knowledge Management. New York: ACM, 2020: 1205-1214. |
[27] | MURRE J M J, DROS J. Replication and analysis of Ebbinghaus’ forgetting curve [J]. PLoS ONE, 2015, 10(7): No.e0120644. |
[28] | NAGATANI K, ZHANG Q, SATO M, et al. Augmenting knowledge tracing by considering forgetting behavior [C]// Proceedings of the 2019 World Wide Web Conference. New York: ACM, 2019: 3101-3107. |
[29] | 郑浩东,马华,谢颖超,等.融合遗忘因素与记忆门的图神经网络知识追踪模型[J].计算机应用,2023, 43(9): 2747-2752. |
ZHENG H D, MA H, XIE Y C, et al. Knowledge tracing model based on graph neural network blending with forgetting factors and memory gate [J]. Journal of Computer Applications, 2023, 43(9): 2747-2752. | |
[30] | 李晓光,魏思齐,张昕,等. LFKT:学习与遗忘融合的深度知识追踪模型[J].软件学报,2021, 32(3): 818-830. |
LI X G, WEI S Q, ZHANG X, et al. LFKT: deep knowledge tracing model with learning and forgetting behavior merging [J]. Journal of Software, 2021, 32(3): 818-830. | |
[31] | CHEN M, BIAN K, HE Y, et al. Enhanced learning and forgetting behavior for contextual knowledge tracing [J]. Information, 2023, 14(3): No.168. |
[32] | 周洋涛,李青山,褚华,等.基于静态与动态学习需求感知的知识点推荐方法[J].软件学报,2024, 35(9): 4425-4447. |
ZHOU Y T, LI Q S, CHU H, et al. Knowledge point recommendation method based on static and dynamic learning demand perception [J]. Journal of Software, 2024, 35(9): 4425-4447. | |
[33] | LI L, WANG Z. Calibrated Q-matrix-enhanced deep knowledge tracing with relational attention mechanism [J]. Applied Sciences, 2023, 13(4): No.2541. |
[34] | 张凯,覃正楚,刘月,等.多学习行为协同的知识追踪模型[J].计算机应用,2023, 43(5): 1422-1429. |
ZHANG K, QIN Z C, LIU Y, et al. Multi-learning behavior collaborated knowledge tracing model [J]. Journal of Computer Applications, 2023, 43(5): 1422-1429. | |
[35] | TONG S, LIU Q, HUANG W, et al. Structure-based knowledge tracing: an influence propagation view [C]// Proceedings of the 2020 IEEE International Conference on Data Mining Conference. Piscataway: IEEE, 2020: 541-550. |
[36] | TONG H, WANG Z, ZHOU Y, et al. HGKT: introducing hierarchical exercise graph for knowledge tracing [EB/OL]. [2024-03-25]. . |
[37] | 王剑,李易清,石琦.融合多维偏好与知识追踪的个性化学习路径推荐——以“系统建模”课程为例[J].现代教育技术,2023, 33(11): 99-108. |
WANG J, LI Y Q, SHI Q. Personalized learning path recommendation integrating multidimensional preferences and knowledge tracing — taking the “system modeling” course as an example [J]. Modern Educational Technology, 2023, 33(11): 99-108. | |
[38] | 张凯,付姿姿,覃正楚.时空相关性融合表征的知识追踪模型[J].计算机应用研究,2024, 41(5): 1381-1387. |
ZHANG K, FU Z Z, QIN Z C. Knowledge tracing model of temporal and spatial correlation fusion [J]. Application Research of Computers, 2024, 41(5): 1381-1387. | |
[39] | 许智宏,张惠斌,董永峰,等.问题特征增强的知识追踪模型[J].计算机科学与探索,2024, 18(9): 2466-2475. |
XU Z H, ZHANG H B, DONG Y F, et al. Question feature enhanced knowledge tracing model [J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(9): 2466-2475. | |
[40] | CHEN L, LIU X. Improvement of knowledge tracing by integrating exercise features and relationships of concepts [J]. Journal of Physics: Conference Series, 2023, 2562: No.012059. |
[41] | 董永峰,黄港,薛婉若,等.融合IRT的图注意力深度知识追踪模型[J].计算机科学,2023, 50(3): 173-180. |
DONG Y F, HUANG G, XUE W R, et al. Graph attention deep knowledge tracing model integrated with IRT [J]. Computer Science, 2023, 50(3): 173-180. | |
[42] | HE Y, WANG H, PAN Y, et al. Exercise recommendation method based on knowledge tracing and concept prerequisite relations [J]. CCF Transactions on Pervasive Computing and Interaction, 2022, 4(4): 452-464. |
[43] | 王炼红,罗志辉,林飞鹏,等.采用多头注意力机制的C&RM-MAKT预测算法[J].电子学报,2023, 51(5): 1215-1222. |
WANG L H, LUO Z H, LIN F P, et al. C&RM-MAKT Prediction algorithm using multi-head attention mechanism [J]. Acta Electronica Sinica, 2023, 51(5): 1215-1222. | |
[44] | TU L, ZHU X, JI Y. Graph-based dynamic interactive knowledge tracing [C]// Proceedings of the 8th International Conference on Distance Education and Learning. New York: ACM, 2023: 49-56. |
[45] | GHOSH A, HEFFERNAN N, LAN A S. Context-Aware attentive knowledge tracing [C]// Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2020: 2330-2339. |
[46] | YEUNG C K. Deep-IRT: make deep learning based knowledge tracing explainable using item response theory [EB/OL]. [2024-02-14]. . |
[47] | NIU Z, ZHONG G, YU H. A review on the attention mechanism of deep learning [J]. Neurocomputing, 2021, 452: 48-62. |
[48] | YANG S, ZHANG T, MAO S, et al. MAKT: a knowledge tracing model based on meta path and attention mechanism [C]// Proceedings of the 5th International Conference on Computer Science and Software Engineering. New York: ACM, 2022: 70-74. |
[49] | ZHANG N, DU Y, DENG K, et al. Attention-based knowledge tracing with heterogeneous information network embedding [C]// Proceedings of the 2020 International Conference on Knowledge Science, Engineering and Management, LNCS 12274. Cham: Springer, 2020: 95-103. |
[50] | 邵小萌,张猛.融合注意力机制的时间卷积知识追踪模型[J].计算机应用,2023, 43(2): 343-348. |
SHAO X M, ZHANG M. Temporal convolutional knowledge tracing model integrated with attention mechanism [J]. Journal of Computer Applications, 2023, 43(2): 343-348. | |
[51] | LI J, JIANG C, YE S. A knowledge tracing model based on attention mechanism [C]// Proceedings of the 2022 International Conference on Machine Learning, Cloud Computing and Intelligent Mining. Piscataway: IEEE, 2022: 219-224. |
[52] | CAI L, CHOI K, HANSEN M, et al. Item response theory [J]. Annual Review of Statistics and Its Application, 2016, 3: 297-321. |
[53] | CHEN J, LIU Z, HUANG S, et al. Improving interpretability of deep sequential knowledge tracing models with question-centric cognitive representations [C]// Proceedings of the 37th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2023: 14196-14204. |
[54] | OEDA S, KAKIZAKI T. Latent state estimation method for students using knowledge tracing combining with IRT [J]. Procedia Computer Science, 2022, 207: 1992-1999. |
[55] | CONVERSE G, PU S, OLIVEIRA S. Incorporating Item response theory into knowledge tracing [C]// Proceedings of the 2021 International Conference on Artificial Intelligence in Education, LNCS 12749. Cham: Springer, 2021: 114-118. |
[56] | GAN W, SUN Y, SUN Y. Knowledge interaction enhanced knowledge tracing for learner performance prediction [C]// Proceedings of the 7th International Conference on Behavioural and Social Computing. Piscataway: IEEE, 2020: 1-6. |
[57] | CHENG S, LIU Q, CHEN E, et al. DIRT: deep learning enhanced item response theory for cognitive diagnosis [C]// Proceedings of the 28th ACM International Conference on Information and Knowledge Management. New York: ACM, 2019: 2397-2400. |
[58] | 郭艺,何廷年,李爱斌,等.融合GA-CART和Deep-IRT的知识追踪模型[J].计算机工程与科学,2023, 45(9): 1691-1700. |
GUO Y, HE T N, LI A B, et al. A knowledge tracing model integrating GA-CART and Deep-IRT [J]. Computer Engineering and Science, 2023, 45(9): 1691-1700. | |
[59] | TSUTSUMI E, KINOSHITA R, UENO M. Deep item response theory as a novel test theory based on deep learning [J]. Electronics, 2021, 10(9): No.1020. |
[60] | SU Y, CHENG Z, LUO P, et al. Time-and-Concept enhanced deep multidimensional item response theory for interpretable knowledge tracing [J]. Knowledge-Based Systems, 2021, 218: No.106819. |
[61] | NI Q, WEI T, ZHAO J, et al. HHSKT: a learner-question interactions based heterogeneous graph neural network model for knowledge tracing [J]. Expert Systems with Applications, 2023, 215: No.119334. |
[62] | HERBRICH R, MINKA T, GRAEPEL T. TrueSkill: a Bayesian skill rating system [C]// Proceedings of the 20th International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2006: 569-576. |
[63] | DAS A, RAD P. Opportunities and challenges in Explainable Artificial Intelligence (XAI): a survey [EB/OL]. [2024-01-29]. . |
[64] | BARREDO ARRIETA A, DÍAZ-RODRÍGUEZ N, DEL SER J, et al. Explainable Artificial Intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI [J]. Information Fusion, 2020, 58: 82-115. |
[65] | 梁祥,刘梦赤,胡婕,等.融合习题难度和作答经验的深度知识追踪模型[J].华南师范大学学报(自然科学版), 2023, 55(4): 81-86. |
LIANG X, LIU M C, HU J, et al. Deep knowledge tracing model by integrating problem difficulty and answering experience [J]. Journal of South China Normal University (Natural Science Edition), 2023, 55(4): 81-86. |
[1] | 王震洲, 郭方方, 宿景芳, 苏鹤, 王建超. 面向智能巡检的视觉模型鲁棒性优化方法[J]. 《计算机应用》唯一官方网站, 2025, 45(7): 2361-2368. |
[2] | 齐巧玲, 王啸啸, 张茜茜, 汪鹏, 董永峰. 基于元学习的标签噪声自适应学习算法[J]. 《计算机应用》唯一官方网站, 2025, 45(7): 2113-2122. |
[3] | 赵小阳, 许新征, 李仲年. 物联网应用中的可解释人工智能研究综述[J]. 《计算机应用》唯一官方网站, 2025, 45(7): 2169-2179. |
[4] | 花天辰, 马晓宁, 智慧. 基于浅层人工神经网络的可移植执行恶意软件静态检测模型[J]. 《计算机应用》唯一官方网站, 2025, 45(6): 1911-1921. |
[5] | 李岚皓, 严皓钧, 周号益, 孙庆赟, 李建欣. 基于神经网络的多尺度信息融合时间序列长期预测模型[J]. 《计算机应用》唯一官方网站, 2025, 45(6): 1776-1783. |
[6] | 牛四杰, 刘昱良. 基于知识蒸馏双分支结构的视网膜病变辅助诊断方法[J]. 《计算机应用》唯一官方网站, 2025, 45(5): 1410-1414. |
[7] | 王文鹏, 秦寅畅, 师文轩. 工业缺陷检测无监督深度学习方法综述[J]. 《计算机应用》唯一官方网站, 2025, 45(5): 1658-1670. |
[8] | 李雪莹, 杨琨, 涂国庆, 刘树波. 基于局部增强的时序数据对抗样本生成方法[J]. 《计算机应用》唯一官方网站, 2025, 45(5): 1573-1581. |
[9] | 陈凯, 叶海良, 曹飞龙. 基于局部-全局交互与结构Transformer的点云分类算法[J]. 《计算机应用》唯一官方网站, 2025, 45(5): 1671-1676. |
[10] | 王丹, 张文豪, 彭丽娟. 基于深度学习的智能反射面辅助通信系统信道估计[J]. 《计算机应用》唯一官方网站, 2025, 45(5): 1613-1618. |
[11] | 徐春, 吉双焱, 马欢, 孙恩威, 王萌萌, 苏明钰. 基于知识图谱和对话结构的问诊推荐方法[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1157-1168. |
[12] | 周阳, 李辉. 基于语义和细节特征双促进的遥感影像建筑物提取网络[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1310-1316. |
[13] | 潘理虎, 彭守信, 张睿, 薛之洋, 毛旭珍. 面向运动前景区域的视频异常检测[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1300-1309. |
[14] | 王一丁, 王泽浩, 李耀利, 蔡少青, 袁媛. 多尺度2D-Adaboost的中药材粉末显微图像识别算法[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1325-1332. |
[15] | 薛振华, 李强, 黄超. 视觉基础模型驱动的像素级图像异常检测方法[J]. 《计算机应用》唯一官方网站, 2025, 45(3): 823-831. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||