基于数据挖掘的虚拟仿真实训个性化学习资源推荐算法  

A personalized learning resource recommendation algorithm for virtual simulation training based on data mining

作　　者：童绪军 陈涛[1] TONG Xujun;CHEN Tao(Public Basic College,Anhui Medical College,Hefei 230601,China)

机构地区：[1]安徽医学高等专科学校公共基础学院,安徽合肥230601

出　　处：《山东理工大学学报(自然科学版)》2025年第4期35-40,46,共7页Journal of Shandong University of Technology:Natural Science Edition

基　　金：安徽省高校科学研究一般项目(ZR2021B002);安徽省高等学校质量工程项目(2022kcsz150,2022xnfzjd012)。

摘　　要：现有的学习资源推荐算法缺乏有效的数据挖掘,推荐结果无法充分满足用户需求,因此提出基于数据挖掘的虚拟仿真实训个性化学习资源推荐算法。利用虚拟仿真技术对学习资源进行深度挖掘,总结学习资源特征;通过数据函数提取个性化学习资源特征,并实时监测异常数据,减少误差产生;将用户偏好特征与用户需求相结合,形成数据匹配点,实现虚拟仿真实训个性化学习资源推荐。实验结果表明:本文算法在资源数据为12000个时,运算时间对比深度集成学习算法缩短了60.4%,对比协同过滤个性化推荐算法缩短了53.1%,能够有效提升个性化学习资源推荐效率;算法能够将异常数据检测率稳定在90%左右,较对比算法检测率提高了20%。The existing learning resource recommendation algorithms lack effective data mining,and the recommendation results cannot fully meet the needs of users.Therefore,a personalized learning resource recommendation algorithm based on data mining for virtual simulation training is proposed.Firstly,virtual simulation technology is used to conduct in-depth analysis of learning resources and summarize their characteristics.Then,personalized learning resource features are extracted through data functions,and abnormal data is monitored in real-time to reduce errors.Finally,the algorithm combines user preference features with user needs to form data matching points,achieving personalized learning resource recommendation for virtual simulation training.The experimental results show that when testing 12000 learning data,the proposed algorithm has reduced the computation time by 60.4%compared to deep learning ensemble algorithms and by 53.1%compared to collaborative filtering personalized recommendation algorithms,effectively improving the efficiency of personalized learning resource recommendation.Meanwhile,the proposed algorithm maintains the detection rate of abnormal data at around 90%,which is 20%higher than the detection rate of comparative algorithms.

关 键 词：数据挖掘 虚拟仿真 个性化学习资源 推荐算法 

分 类 号：TP748[自动化与计算机技术—检测技术与自动化装置]