模式识别与人工智能
Wednesday, Apr. 2, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2024, Vol. 37 Issue (1): 13-26    DOI: 10.16451/j.cnki.issn1003-6059.202401002
Papers and Reports Current Issue| Next Issue| Archive| Adv Search |
Computerized Adaptive Testing Method Based on Reinforcement Learning for Series Diagnosis
LIU Zirui1, WU Jinze2, YAO Fangzhou1, LIU Qi1, CHEN Enhong1, SHA Jing2, WANG Shijin2, SU Yu3
1. School of Computer Science and Technology, University of Sci-ence and Technology of China, Hefei 230027;
2. iFLYTEK Co., Ltd, Hefei 230088;
3. School of Computer and Artificial Intelligence, Hefei Normal University, Hefei 230061

Download: PDF (1169 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Computerized adaptive testing is designed to select appropriate questions for students based on their historical performance, thereby measuring their actual ability quickly and effectively. However, in intelligent education scenarios, the existing selection strategy of traditional computerized adaptive testing is still faced with some problems such as target complexity and knowledge sparseness. To solve these problems, a computerized adaptive testing method based on reinforcement learning for series diagnosis is proposed in this paper to accurately assess students' knowledge proficiency for intelligent scenarios. A student simulator and a student portrait model based on series diagnosis model are adopted. To address the complexity of computerized adaptive testing goals in real-world scenarios, five evaluation indicators are designed, including accuracy of weak points, coupling of prediction performance, adaptive testing duration, testing anomaly rate and testing difficulty structure. Furthermore, a selection strategy for reinforcement learning based computerized adaptive testing is proposed. The dual-channel self-attention learning module and the contradiction learning module are utilized to ameliorate knowledge sparseness problem. Experiments on real datasets show that the proposed selection strategy not only efficiently measures students' actual abilities, but also optimizes their answering experience. The selected questions exhibit a certain level of interpretability, and the method provides a feasible solution for computerized adaptive testing in intelligent education scenarios.
Key wordsIntelligent Education      Personalized Education      Computerized Adaptive Testing      Reinforcement Learning      Q Learning     
Received: 07 September 2023     
ZTFLH: G434  
Fund:National Key Research and Development Program of China(No.2022YFC3303504)
Corresponding Authors: CHEN Enhong, Ph.D., professor. His research interests in-clude machine learning, data mining, social network and personalized recommender system.   
About author:: LIU Zirui, Master student. His research interests include data mining and intelligent education.WU Jinze, Master, engineer. His research interests include natural language processing, intelligent education and federated learning.YAO Fangzhou, Ph.D.candidate. Her re-search interests include educational data mi-ning and data sampling.LIU Qi, Ph.D., professor. His research inte-rests include data mining, knowledge disco-very, machine learning method and application.SHA Jing, Master, engineer. His research interests include natural language processing and intelligent education.WANG Shijin, Ph.D., senior engineer. His research interests include speech techno-logy, natural language processing and intelli-gent education.SU Yu, Ph.D. candidate, associate professor. His research interests include data mining and image identification.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
LIU Zirui
WU Jinze
YAO Fangzhou
LIU Qi
CHEN Enhong
SHA Jing
WANG Shijin
SU Yu
Cite this article:   
LIU Zirui,WU Jinze,YAO Fangzhou等. Computerized Adaptive Testing Method Based on Reinforcement Learning for Series Diagnosis[J]. Pattern Recognition and Artificial Intelligence, 2024, 37(1): 13-26.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202401002      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2024/V37/I1/13
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn