nav emailalert searchbtn searchbox tablepage yinyongbenwen piczone journalimg journalInfo journalinfonormal searchdiv searchzone qikanlogo popupnotification paper paperNew
2018, 12, No.383 88-95+112
人工智能支持下的智适应学习模式
基金项目(Foundation): 全国教育科学“十三五”规划2018年度教育部重点课题“在线协作知识建构的深度汇谈机制研究”(项目编号:DCA180324)的阶段性成果
邮箱(Email):
DOI:
发布时间: 2018-12-05
出版时间: 2018-12-05
网络发布时间: 2018-12-05
移动端阅读
摘要:

因材施教抑或因材促学一直是个性化学习追求的价值取向,然而如何获悉已学知识点的掌握程度以及学习者学习捷径的引领则是其亟需面临的挑战,基于人工智能技术的智适应学习系统为解决这一困境提供了有效参照。智适应学习以知识空间理论、信息流理论以及贝叶斯定理等为基础实现了人工智能技术支持下的高效个性化学习。智适应学习以纳米级的知识点作为学习内容形态,以最佳学习路径的引荐作为学习过程向导,以个性化学习和高效学习效率作为智适应学习的出发点和最终归宿。智适应学习系统呈现了一个完整的智适应学习运行流程,形成了"测、学、练、测、辅"五位一体的学习模式。智适应学习的应用案例表明,其在1:1教与学、精准学习评价以及O2O学习中具有突出的潜在优势。

Abstract:

Teaching or promoting learning according to learners' aptitude have been the value orientation of the pursuit for individualized learning. However, how to learn the mastery of knowledge and how to guide learners to learn shortcuts are urgent challenges. The intelligent adaptive learning system based on artificial intelligence provides an effective reference to solve this dilemma, w realizes high efficient individualized learning under the support of artificial intelligence technology based on the theory of knowledge space, the theory of information flow and the Bayes theorem. The intelligence adaptation learning takes nanoscale knowledge points as learning content form, takes the recommendation of best learning path as the guide of learning process, and takes personalized and efficient learning as the starting point and final destination of intelligent adaptive learning. The system presents a complete intelligent adaptive learning process, builds the learning mode including five Essential factors that are "test, study, training, testing, and auxiliary". The application example of adaptive learning show that it have some outstanding advantages among 1:1 teaching and learning, precision learning evaluation and O2O learning.

参考文献

[11][10]Michael B.H..Adaptive Learning[DB/OL].https://www.pearson.com/corporate/about-pearson/innovation/smarter-digital-tools/adaptive-learning.html,2014-01-29.

[2]姜强,赵蔚等.基于用户模型的个性化本体学习资源推荐研究[J].中国电化教育,2010,(5):106-111.

[3]王丽萍,赵蔚等.自适应学习系统中基于Rasch的主题难度估计[J].现代教育技术,2017,(6):115-121.

[4]方海光,罗金萍等.基于教育大数据的量化自我MOOC自适应学习系统研究[J].电化教育研究,2016,(11):38-42.

[5]吴南中.自适应学习模型的构建及其实现策略[J].现代教育技术,2017,(9):12-18.

[6]赵呈领,陈智慧等.适应性学习路径推荐算法及应用研究[J].中国电化教育,2015,(8):85-91.

[7]梁迎丽,刘陈.人工智能教育应用的现状分析、典型特征与发展趋势[J].中国电化教育,2018,(3):24-30.

[8]Somyurek,S..The new trends in adaptive educational hypermedia systems[J].International Review of Research in Open and Distributed Learning,2015,(1):221-241.

[9]吴南中.自适应学习模型的构建及其实现策略[J].现代教育技术,2017,(9):12-18

[11]Doignon J.P.,Falmagne J.C..Spaces for the assessment of knowledge[J].International Journal of Man-Machine Studies,1985,(2):175-196.

[12]Falmagne,J.C.,et al.Introduction to knowledge spaces:How to build,test,and search them[J].Psychological Review,1990,(2):201-224.

[13]Bartl E.&Belohlavek R..Knowledge Spaces with Graded Knowledge States[J].Information Sciences,2001,(8):3-8.

[14]Shannon C.E..A Mathematical Theory of Communication:The Bell System Technical Journal[J].Journal of the Franklin Institute,1938,(4):519-520.

[15]Barwise,J.,Seligman,J..Information Flow:The Logic of Distributed Systems[M].Cambridge:Cambridge University Press,1997.67-200.

[16]李娜,娄永强.从条件句悖论看信息流理论的哲学基础[J].西南大学学报(社会科学版),2009,(1):74-80.

基本信息:

中图分类号:G434

引用信息:

[1]李海峰,王炜.人工智能支持下的智适应学习模式[J].中国电化教育,2018,No.383(12):88-95+112.

基金信息:

全国教育科学“十三五”规划2018年度教育部重点课题“在线协作知识建构的深度汇谈机制研究”(项目编号:DCA180324)的阶段性成果

发布时间:

2018-12-05

出版时间:

2018-12-05

网络发布时间:

2018-12-05

检 索 高级检索