| 437 | 0 | 61 |
| 下载次数 | 被引频次 | 阅读次数 |
以数据支持教育决策与治理，是人工智能全面赋能教育变革的核心要义。从教育大数据驱动视角出发，借鉴军事领域的“态势感知”理念，系统梳理国内外相关研究进展，提出教育大数据驱动的“学生发展态势感知”概念。基于“物理-事理-人理”系统方法论建构学生发展态势感知理论框架，通过整合学生学业行为、认知表现、情感状态与社会互动等多源异构数据，构建涵盖“数据融合层—态势感知层—态势理解层—风险预测预警层—干预推荐层”的学生发展态势感知预警系统。进一步设计融合大模型的动态图神经网络与时序预测模型的风险预测核心算法，以刻画学生发展状态的时序演化与风险传导机制，并从四个方面给出应用场景与融合思路：一是依托数据协同推动教育治理提升，二是通过多场景赋能实现教育过程深度融入，三是围绕预警治理促进教育策略有效转化，四是基于人机协同强化数据治理与决策。
Abstract：Using data to support educational decision-making and governance is the core essence of how artificial intelligence fully empowers educational transformation. This article starts from the perspective of educational big data-driven approaches, draws on the concept of “situation awareness” from the military field, systematically reviews the relevant research progress at home and abroad, and proposes the concept of “student development situation awareness” driven by educational big data. Based on the Wuli-Shili-Renli, a theoretical framework for student development situation awareness is constructed. By integrating multi-source heterogeneous data such as students' academic behaviors, cognitive performances, emotional states, and social interactions, a student development situation awareness early warning system covering “data fusion layer—situation awareness layer—situation understanding layer—risk prediction and warning layer—intervention recommendation layer” is constructed. Further, this study designs the core algorithm for risk prediction by integrating the dynamic graph neural network with the time series prediction model based on large-scale models, in order to depict the temporal evolution and risk transmission mechanism of students' development status. Four application scenarios and integration ideas are provided from the following four aspects: First, leveraging data collaboration to enhance educational governance; second, enabling deep integration of the educational process through multiple scenarios; third, promoting effective transformation of educational strategies through early warning governance; fourth, strengthening data governance and decision-making through human-machine collaboration.
[1]中华人民共和国中央人民政府.中共中央国务院印发《教育强国建设规划纲要(2024—2035年)》[EB/OL].[2025-10-25].https://www.gov.cn/zhengce/202501/content_6999913.htm.
[2]Bai X,Zhang F,Li J,et al.Educational big data:Predictions,applications and challenges[J].Big Data Research,2021,26:100270.
[3]Cao Y,Gao J,Lian D,et al.Orderliness predicts academic performance:behavioural analysis on campus lifestyle[J].Journal of The Royal Society Interface,2018(146):20180210.
[4]Elbadrawy A,Polyzou A,Ren Z,et al.Predicting student performance using personalized analytics[J].Computer,2016(4):61-69.
[5]班文静，姜强，赵蔚.基于多算法融合的在线学习成绩精准预测研究[J].现代远距离教育，2022(3):37-45.
[6]Endsley M R.Design and evaluation for situation awareness enhancement[C]//Proceedings of the Human Factors Society Annual Meeting.Los Angeles:Sage,1988(2):97-101.
[7]Endsley M R.Toward a theory of situation awareness in dynamic systems[J].Human Factors,1995(1):32-64.
[8]Steinberg A N,Bowman C L,White F E.Revisions to the JDL data fusion model[C]//Sensor Fusion:Architectures,Algorithms,and Applications III.Bellingham:SPIE,1999,3719:430-441.
[9]Boyd J R.A discourse on winning and losing[M].USA:Air University Library,1987.
[10]Klein G.The recognition-primed decision model[M]//Sources of Power:How People Make Decisions.Cambridge:MIT Press,1998:15-32.
[11]Bass T.Multisensor data fusion for next generation distributed intrusion detection systems[C]//Proceedings of the IRIS National Symposium on Sensor and Data Fusion.1999:24-27.
[12]粟锋.特朗普政府国家反情报战略的调整及其应对——基于对美国最新版《国家反情报战略》报告的分析[J].情报杂志，2020(9):15-20.
[13]贾若男，陈晓琳，郭宇.多模态数据驱动的网络数据安全态势感知理论模型构建[J].情报杂志，2025(7):69-76.
[14]Shen B,Li Q,Chen B,et al.Large language model-based security situation awareness for smart grid:Framework and approaches[J].IEEE Access,2025:173600-173613.
[15]Liu X,Li Z,Tang Z,et al.Application of artificial intelligence technology in electromechanical information security situation awareness system[J].Scalable Computing:Practice and Experience,2024(1):127-136.
[16]Nasir M,Maiti A,Xu S,et al.Controller modelling for situation awareness in industrial internet of things[J].International Journal of Systems Science,2025:1-36.
[17]王明程，王高开，李勇男.基于大模型智能体的安全风险态势感知框架构建[J].情报理论与实践，2024(7):190-198.
[18]李伟周.基于人工智能的网络安全态势感知技术研究[J].信息记录材料，2025(4):147-149.
[19]潘镜淇.基于大数据和人工智能技术的信息安全态势感知系统研究[J].软件，2025(2):134-136.
[20]Wang S,Ni L,Zhang Z,et al.Multimodal prediction of student performance:A fusion of signed graph neural networks and large language models[J].Pattern Recognition Letters,2024,181:1-8.
[21]王明程，李勇男.基于多模态大数据的国家安全风险态势感知模型构建[J].情报杂志，2024(2):103-109.
[22] Li M,Wang W,Zhou K.Exploring the technology emergence related to artificial intelligence:A perspective of coupling analyses[J].Technological Forecasting and Social Change,2021,172:121064.
[23]邢蓓蓓，杨现民，李勤生.教育大数据的来源与采集技术[J].现代教育技术，2016 (8):14-21.
[24]Gu J,Zhu Z.The Wu-li Shi-li Ren-li approach (WSR):An Oriental systems methodology[C]//International Conference on Computers and Industrial Engineering.London:Springer,1995:31-40.
[25]寇晓东，杨琳.再论WSR方法论及其应用[C]//中国系统工程学会.和谐发展与系统工程——中国系统工程学会第十五届年会论文集，2008:173-179.
[26]刘军，郭绍青，黄琰，等.WSR视野下网络学习空间开展自主学习SPA模型构建——网络学习空间内涵与学校教育发展研究之九[J].电化教育研究，2019(7):46-52.
[27]金占勇，邱宵慧，魏楚元.基于WSR方法论和改进AHP-FCE模型的智慧校园可持续发展综合评价[J].现代教育技术，2020(7):73-80.
[28]喻国明，滕文强，李钒.AIGC时代人机关系的再思考：本质认知、特征演化与协同路径——基于机体哲学与WSR方法论的分析[J].广州大学学报(社会科学版),2024(6):52-63.
[29]穆肃，崔萌，黄晓地.全景透视多模态学习分析的数据整合方法[J].现代远程教育研究，2021(1):26-37+48.
[30]张琪，李福华，孙基男.多模态学习分析：走向计算教育时代的学习分析学[J].中国电化教育，2020(9):7-14+39.
[31]Ji X,Sun L,Huang K.The construction and implementation direction of personalized learning model based on multimodal data fusion in the context of intelligent education[J].Cognitive Systems Research,2025,92:101379.
[32]张琪，武法提，许文静.多模态数据支持的学习投入评测：现状、启示与研究趋向[J].远程教育杂志，2020 (1):76-86.
[33]顾小清，王馨怡.从数据驱动到数智融合：以数字轨迹刻画学习经历[J].现代远程教育研究，2025(3):3-11.
[34]张乐乐，顾小清.多模态数据支持的课堂教学行为分析模型与实践框架[J].开放教育研究，2022(6):101-110.
[35]Li Q,Luximon Y,Zhang J,et al.Measuring and classifying students’ cognitive load[J].British Journal of Educational Technology,2024(2):625-653.
[36]姜强，刘盼，倪静，等.基于时间序列数据驱动的在线学业预测机理模型研究[J].现代远距离教育，2025 (1):58-67.
[37]冷静，吴子豪，都洋岚，等.在线学习表现预测模型研究：基于智能学业测评系统的数据分析[J].现代教育技术，2025(8):87-96.
[38]唐烨伟，卜凡丽，赵一婷.学习者多模态情绪融合分析：动因、框架与路向[J].开放教育研究，2023(3):96-103.
[39]沈阳，张怡冉，叶心怡，等.认知投入视角下力反馈交互对学习效果的影响机制研究——基于多模态数据分析[J].现代教育技术，2025(11):70-78.
[40]Dubovi I.Cognitive and emotional engagement while learning with VR:The perspective of multimodal methodology[J].Computers & Education,2022,183:104495.
[41]余淑珍，单俊豪，闫寒冰.情感计算赋能个性化教学：逻辑框架、问题解构与多元重塑[J].现代远距离教育，2024(2):53-61.
[42]张屹，林裕如，周平红，等.基于社会认知网络分析的学习者协作问题解决能力发展研究[J].现代远距离教育，2024(2):42-52.
[43]王梦倩.行为—认知—情感多层网络视角下在线学习共同体互动分析模型与应用[J].电化教育研究，2022 (12):86-92+113.
[44]刘逸伦，黄微，周思琪.多智能体协同赋能的突发事件风险情报感知及预警模式研究[J/OL].图书情报工作，1-13[2025-11-30].https://link.cnki.net/urlid/11.1541.G2.20251117.1126.002.
[45]尹睿，何淑茵.基于系统性文献综述的多模态学习分析研究进展与前瞻[J].现代远程教育研究，2022(6):54-63.
[46]郭宇，李昶霏，张传洋，等.多模态数据驱动的安全态势感知框架构建[J].图书情报工作，2024(24):4-14.
[47]于爽，叶俊民，尹兴翰，等.联结人智协同学习干预的设计与应用：理论模型及实践框架[J].电化教育研究，2025(7):93-99+107.
[48]武法提，田浩.人机协同的精准学习干预：动力机制、逻辑理路与实践模型[J].开放教育研究，2023(2):81-90.
[49]孙众，于子淳.人工智能课堂教学分析与改进：人在回路的协同机制[J].电化教育研究，2023(1):116-122.
[50]Feng Z,Wang R,Wang T,et al.A comprehensive survey of dynamic graph neural networks:Models,Frameworks,Benchmarks,Experiments and Challenges[J].IEEE Transactions on Knowledge and Data Engineering,2025:1-17.
[51]但金凤，王正青.数据支持帮扶：美国中学早期学业预警系统的发展轨迹与运行特色[J].现代远距离教育，2022(6):30-38.
[52]翟洁，陈乐旋，庞智玉.基于图神经网络的学业表现预测方法研究综述[J/OL].计算机科学，1-18[2025-11-09].https://link.cnki.net/urlid/50.1075.tp.20251107.1554.022.
基本信息:
DOI：10.13927/j.cnki.yuan.20260303.001
中图分类号:G434
引用信息:
[1]张琪,罗霞,陈玉杰.教育大数据驱动的学生发展态势感知预警系统研究[J].现代远距离教育,2025,No.222(06):53-63.DOI:10.13927/j.cnki.yuan.20260303.001.
基金信息:
2025年度教育部人文社会科学研究一般项目“GAI视域下人机对话过程中学生思维互动规律挖掘及其增值评价研究”(编号：25YJC880016); 安徽省教育厅科研创新团队“智能教育范式创新”(编号：2025AHGXSK10012)
2026-03-03
2026-03-03
2026-03-03