[1]肖杨,冯军,钱亚冠,等.融合GRU和注意力机制的知识追踪优化模型研究[J].浙江科技学院学报,2023,(05):395-401411.[doi:10.3969/j.issn.1671-8798.2023.05.005]
　XIAO Yang,FENG Jun,QIAN Yaguan,et al.Study on knowledge tracking optimization model incorporating GRU and attention mechanism[J].,2023,(05):395-401411.[doi:10.3969/j.issn.1671-8798.2023.05.005]
点击复制

融合GRU和注意力机制的知识追踪优化模型研究(/HTML)
分享到：

《浙江科技学院学报》[ISSN:2097-5236/CN:33-1431/Z]

卷:
期数:
2023年05期
页码:
395-401411
栏目:
出版日期:
2023-10-31

文章信息/Info

Title:
Study on knowledge tracking optimization model incorporating GRU and attention mechanism
文章编号:
1671-8798(2023)05-0395-07
作者:
肖杨; 冯军; 钱亚冠; 孙雨璐; 毕云杉
(浙江科技学院 理学院，杭州 310023)
Author(s):
XIAO Yang;  FENG Jun;  QIAN Yaguan;  SUN Yulu;  BI Yunshan
(School of Science, ZheJiang University of Science and Technology, Hangzhou 310023, Zhejiang, China)
关键词:
深度学习; 知识追踪; 注意力机制
分类号:
TP183
DOI:
10.3969/j.issn.1671-8798.2023.05.005
文献标志码:
A
摘要:
【目的】现有基于注意力机制的知识追踪模型存在忽略序列顺序信息，模型组成结构单一，对序列信息提取不够充分等问题，对此提出一种多特征融合多结构的新知识追踪模型。模型由循环神经网络，带有位置编码的注意力机制以及因果卷积组成。【方法】首先将经过门控单元网络反应序列和练习序列输入注意力机制中，然后将此输出和经过门控单元网络反应序列的练习序列再一次输入注意力机制中，最后将得到的序列输入到因果卷积中。在序列隐藏信息的提取及注意力权重的分配上进行了优化。【结果】在Assistment2009、Assistment2015及Synthetic-5数据集上与现有的知识追踪模型相比，本文模型AUC(area under curve，曲线下方面积)值平均提升8%。【结论】本研究结果可为智能教育系统的实际应用提供一些参考。

参考文献/References:

[1] YUDELSON M V, KOEDINGER K R, GORDON G J. Individualized bayesian knowledge tracing models[C]//Proceedings of the 16th International Conference on Artificial Intelligence in Education. Berlin:Springer,2013:171.
[2] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J].Neural Computation,1997,9(8):1735.
[3] KYUNGHYUN C, BART V M, CAGLAR G, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Empirical Methods in Natural Language Processing. Doha:Association for Computational Linguistics,2014:1724.
[4] PIECH C, SPENCER J, HUANG J, et al. Deep knowledge tracing[J].Computer Science,2015,3(3):19.
[5] ABDELRAHMAN G, WANG Q. Knowledge tracing with sequential key-value memory networks[C]//Proceedings of the 42nd Int Conference on Research and Development in Information Retrieval(SIGIR). New York:ACM,2019:175.
[6] SHA L, HONG P Y. Neural knowledge tracing[C]//Proceedings of the International Conference on Brain Function Assessment in Learning. Berlin:Springer,2017:108.
[7] 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.
[8] 刘铁园,陈威,常亮,等.基于深度学习的知识追踪研究进展[J].计算机研究与发展,2022,59(1):81.
[9] ZHANG J N, SHI X J, KING I, et al. Dynamic key-value memory networks for knowledge tracing[C]//Proceedings of the 26th International Conference on World Wide Web. New York:ACM,2017:765.
[10] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of Advanceson Neural Information Processing Systems. Long Beach:Curran Associates Inc,2017:5998.
[11] PANDEY S, KARYPIS G. A self-attentive model for knowledgetracing[EB/OL].(2019-07-16)[2022-07-18].
[12] CHOI Y, LEE Y, CHO J, et al. Towards an appropriate query, key, and value computation for knowledge tracing[C]//Proceedings of the Seventh ACM Conference on Learning Scale. New York:Association for Computing Machinery,2020:341.
[13] OUYANG Y X, ZHOU Y C, ZHANG H B, et al. PAKT:a position-aware self-attentive approach for knowledge tracing[C]//Pro-ceedings of International Conference on Artificial Intelligence in Education. Cham:Springer,2021:285.
[14] FENG M, HEFFERNAN N, KOEDINGER K. Addressing the assessment challenge with an online system that tutors as it assesses[J].User Modeling and User Adapted Interaction,2009(19):243.
[15] XIONG X L, ZHAO S Y, VAN I, et al. Going deeper with deep knowledge tracing[C]//Proceedings of the 9th International Conference on Educational Data Mining. Raleigh:IEDMS,2016:545.
[16] BAI S, KOLTER J Z, KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequencemodeling[EB/OL].(2018-04-19)[2022-07-18].

相似文献/References:

[1]沈梦婷,岑岗,周闻,等.基于CNN智能AI助手的早期教育系统设计[J].浙江科技学院学报,2020,(06):590.
　Design of early education system based on CNN intelligent AI assistant[J].,2020,(05):590.
[2]陈力,王海江,吴凯.基于卷积神经网络的车载网络入侵检测方法[J].浙江科技学院学报,2021,(01):59.
[3]毕云杉,钱亚冠,张超华,等.基于ERNIE模型的中文文本分类研究[J].浙江科技学院学报,2021,(06):461.
　BI Yunshan,QIAN Yaguan,ZHANG Chaohua,et al.Research on Chinese text classification based on ERNIE model[J].,2021,(05):461.
[4]邵霭,许彩娥,万健,等.针对机器问答中多跳问题的深度学习网络模型[J].浙江科技学院学报,2022,(05):419.
　SHAO Ai,XU Caie,WAN Jian,et al.Deep learning network model for multihop problemsin machine question answering[J].,2022,(05):419.

备注/Memo

备注/Memo:
收稿日期:2022-07-19
基金项目:浙江省高等教育“十三五”第一批教学改革研究项目(jg20180223)
通信作者:冯 军(1963— )，男，浙江省海盐人，教授，硕士，主要从事教育管理研究。E-mail:101006@zust.edu.cn。
更新日期/Last Update: 2023-10-31