[1]聂黎生.基于行为分析的学习资源个性化推荐[J].计算机技术与发展,2020,30(07):34-37.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 008]
　NIE Li-sheng.Personalized Recommendation of Learning Resources Based on Behavior Analysis[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2020,30(07):34-37.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 008]
点击复制

基于行为分析的学习资源个性化推荐()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
30
期数:
2020年07期
页码:
34-37
栏目:
智能、算法、系统工程
出版日期:
2020-07-10

文章信息/Info

Title:
Personalized Recommendation of Learning Resources Based on Behavior Analysis
文章编号:
1673-629X(2020)07-0034-04
作者:
聂黎生
江苏师范大学 计算机科学与技术学院,江苏 徐州 221116
Author(s):
NIE Li-sheng
School of Computer Science and Technology,Jiangsu Normal University,Xuzhou 221116,China
关键词:
行为分析; 学习资源; 个性化推荐; 协同过滤; 推荐精度
Keywords:
behavior analysis; learning resources; personalized recommendation; collaborative filtering; recommendation accuracy
分类号:
TP301;G434
DOI:
10. 3969 / j. issn. 1673-629X. 2020. 07. 008
摘要:
随着数字化学习资源规模急剧扩张,“知识过载”和“学习迷航”等问题限制了在线学习资源推荐的性能, 学习者从海量的学习资源中选择合适资源的难度随之增大。 针对传统推荐算法中存在的数据稀疏和学习资源个性化推荐精度不高等问题,提出了基于行为分析的学习资源个性化推荐算法。首先,构建学习者-学习资源评分矩阵;其次,挖掘学习者行为数据并将行为数据格式化融入到协同过滤个性化推荐过程;最后,计算学习者相似度并为待推荐学习者生成学习资源推荐列表。为验证模型的有效性,以“Live Course 在线课程平台”数据为样本构建实验数据集,通过对比实验表明,该方法具有更高的推荐精度,能够更加精确和全面定位学习者的真实需求,实现学习资源个性化推荐。
Abstract:
With the rapid expansion of the scale of digital learning resources,“knowledge overload”and “learning maze”and other issues limit the performance of online learning resources recommendation,and it is more difficult for learners to select appropriate resources from a large number of learning resources. Aiming at the problems of sparse data and low accuracy of personalized recommendation of learning resources in traditional recommendation algorithms, a personalized recommendation algorithm of learning resources based on behavior analysis is proposed. First of all,the rating matrix of learner learning resources is constructed. Secondly,the behavior data of learners is mined and the behavior data format is integrated into the collaborative filtering personalized recommendation process. Finally, the similarity     of learners is calculated and the learning resources recommendation list is generated for the learners to be recommended. In order to verify the validity of the model,an experimental data set is constructed based on the “Live Course online course platform”data. The comparative experiment shows that the proposed method has higher recommendation accuracy, can more accurately and comprehensively locate the real needs of learners and achieve personalized recommendation of learning resources.

相似文献/References:

[1]宫婧 孙知信 陈二运[].一种基于流量行为分析的P2P流媒体识别方法[J].计算机技术与发展,2009,(09):128.
　GONG Jing,SUN Zhi-xin,CHEN Er-yun.A Kind of P2P Streaming Media Identification Method Based on Traffic Behavior Analysis[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2009,(07):128.
[2]王攀 张顺颐 陈雪娇.基于动态行为轮廓库的Web用户行为分析关键技术[J].计算机技术与发展,2009,(02):20.
　WANG Pan,ZHANG Shun-yi,CHEN Xue-jiao.Key Technology of Web Users＇ Behavior Analysis Based on Dynamic Behavior Profile Database[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2009,(07):20.
[3]边悦,戴航,慕德俊. Android恶意软件特征研究[J].计算机技术与发展,2014,24(11):178.
　BIAN Yue,DAI Hang,MU De-jun. Research on Android Malware Characteristic[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2014,24(07):178.
[4]陈珂[],柯文德[],王爱国[],等. 基于沙盒技术的行为分析系统研究[J].计算机技术与发展,2015,25(08):166.
　CHEN Ke[],KE Wen-de[],WANG Ai-guo[],et al. Research on Behavior Analysis System Based on Sandbox Technology[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2015,25(07):166.
[5]任占广,尚福华.基于行为分析的在线课程成绩预测模型[J].计算机技术与发展,2019,29(11):139.[doi:10. 3969 / j. issn. 1673-629X. 2019. 11. 028]
　REN Zhan-guang,SHANG Fu-hua.Online Course Grade Prediction Model Based on Behavior Analysis[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2019,29(07):139.[doi:10. 3969 / j. issn. 1673-629X. 2019. 11. 028]
[6]陈鑫宇,杨冬黎,鲁金秋,等.基于学习者模型的文本学习资源推荐算法研究[J].计算机技术与发展,2020,30(06):77.[doi:10. 3969 / j. issn. 1673-629X. 2020. 06. 015]
　CHEN Xin-yu,YANG Dong-li,LU Jin-qiu,et al.Research on Text-learning Resource Recommendation Algorithm Based on Learner Model[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2020,30(07):77.[doi:10. 3969 / j. issn. 1673-629X. 2020. 06. 015]
[7]李 建,张 锋*,陈 冲,等.基于 AI 智能语音交互气象服务的研究与应用[J].计算机技术与发展,2020,30(12):197.[doi:10. 3969 / j. issn. 1673-629X. 2020. 12. 035]
　LI Jian,ZHANG Feng*,CHEN Chong,et al.Research and Application of Intelligent Voice Interactive Meteorological Service Based on AI[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2020,30(07):197.[doi:10. 3969 / j. issn. 1673-629X. 2020. 12. 035]
[8]覃忠台,张明军.基于协同过滤算法的学习资源推荐模型研究[J].计算机技术与发展,2021,31(09):31.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 006]
　QIN Zhong-tai,ZHANG Ming-jun.Research on Learning Resource Recommendation Model Based on Collaborative Filtering Algorithm[J].COMPUTER TECHNOLOGY AND DEVELOPMENT,2021,31(07):31.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 006]

更新日期/Last Update: 2020-07-10