基于AHP-BPNN方法的高校学生人工智能素养指标体系构建  

Development of an Artificial Intelligence Literacy Indicator System for University Students Using a Combined AHP-BPNN Approach

作　　者：丁继红 郭丽媛 张文轩 刘华中 Ding Jihong;Guo Liyuan;Zhang Wenxuan;Liu Huazhong(School of Computer Science and Technology,Hainan University,Haikou Hainan 570228)

机构地区：[1]海南大学计算机科学与技术学院,海南海口570228

出　　处：《远程教育杂志》2025年第1期46-56,共11页Journal of Distance Education

基　　金：国家自然科学基金面上项目“双螺旋协作学习过程多模态分析与全息数字画像及精准干预研究”(项目编号:62277012);“教育大数据跨模态融合与多场景高效预测及其可解释性研究”(项目编号:62177013)的阶段性研究成果。

摘　　要：随着人工智能(artificial intelligence,AI)技术的快速发展及其在社会、经济和生活各领域的广泛应用,AI素养已成为提高生产力的必备能力。然而,针对高校学生群体的AI素养,目前尚缺乏统一且明确的指标体系。基于现有的AI素养框架,并通过国内外专家的咨询反馈和指标修正,研究构建了一个包含知识与理解、技能与应用、评价与创造、伦理与道德等4个一级指标和17个二级指标的AI素养评价体系。随后,研究利用层次分析法确立了各级指标的权重,并通过构建反向传播神经网络对这些权重进行了验证。通过将专家知识引导与数据驱动相结合,研究最终构建了一个科学且具有较强操作性的AI素养指标体系,为我国高校学生AI素养评价提供了理论支持和工具借鉴。With the rapid growth of artificial intelligence(AI)technology and its increasing use in society,the economy,and daily life,AI literacy has become a critical competency for improving productivity.However,there is still no standardized and well-defined framework for assessing AI literacy among university students.Building on existing AI literacy models and incorporating feedback from both domestic and international experts,this study develops an AI literacy evaluation framework consisting of four primary dimensions—knowledge and understanding,skills and application,evaluation and creation,and ethics and responsibility—along with 17 secondary indicators.The study used the analytic hierarchy process(AHP)to assign weights to these indicators and validated these weights using a backpropagation neural network(BPNN)model.By combining expert knowledge with data-driven methods,this research develops a reliable and practical AI literacy assessment system,providing both theoretical guidance and practical tools for evaluating university students’AI literacy in China.

关 键 词：人工智能素养 层次分析法 反向传播神经网络 人工智能教育 学习评价 

分 类 号：G40-057[文化科学—教育学原理]