文献类型：期刊文献

中文题名：基于决策树和大模型的个性化计算机实验教学探索与实践

英文题名：Exploration and practice of personalized computer laboratory teaching based on decision trees and large models

作者：翟洁[1];李艳豪[1];孟天鑫[1];郭卫斌[1];王占全[1];李冬冬[1]

机构：[1]华东理工大学信息科学与工程学院,上海200237

年份：2023

卷号：40

期号：12

起止页码：8

中文期刊名：实验技术与管理

外文期刊名：Experimental Technology and Management

收录：CSTPCD;;北大核心:【北大核心2020】；

基金：2022年度上海高校市级重点课程建设项目(沪教委高〔2022〕27号);上海市教育委员会课题“面向专业应用的人工智能课程体系建设和教学改革”(沪教委高〔2021〕47号)。

语种：中文

中文关键词：个性化教学;大模型;决策树;计算机实验教学

外文关键词：personalized teaching;large models;decision trees;computer laboratory teaching

摘要：传统的计算机实验教学常受限于固定的实验内容和资源,难以满足不同学习者的个性化需求。而个性化教学由于对学习者群体进行能力评估的总体时间成本高、执行效率低,不易推行。针对上述问题,提出了一种基于决策树和大模型的学生能力评估模型,进而设计个性化推荐工具,实现了依据学习者水平自动推荐学习资料或实验任务的目的,提升了个性化实验教学的效率。
Traditional computer laboratory teaching is constrained by fixed experiment content and resources,making it difficult to meet the personalized needs of different learners.However,personalized teaching,due to the high overall time cost of assessing the abilities of the learner population and low execution efficiency,is challenging to implement.To address these issues,a student competence assessment model based on decision trees and large models is proposed.Furthermore,a personalized recommendation tool is designed,which automatically recommends learning materials or experimental tasks based on the learner’s level,enhancing the efficiency of personalized laboratory teaching.