[1]沈苗,来天平,王素美,等.北京大学课程推荐引擎的设计和实现[J].智能系统学报,2015,10(03):369-375.[doi:10.3969/j.issn.1673-4785.201409045]
 SHEN Miao,LAI Tianping,WANG Sumei,et al.Design and implementation of the course recommendation engine in Peking University[J].CAAI Transactions on Intelligent Systems,2015,10(03):369-375.[doi:10.3969/j.issn.1673-4785.201409045]
点击复制

北京大学课程推荐引擎的设计和实现(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第10卷
期数:
2015年03期
页码:
369-375
栏目:
出版日期:
2015-06-25

文章信息/Info

Title:
Design and implementation of the course recommendation engine in Peking University
作者:
沈苗 来天平 王素美 彭一明 高志同
北京大学 计算中心, 北京 100871
Author(s):
SHEN Miao LAI Tianping WANG Sumei PENG Yiming GAO Zhitong
Computer Center, Peking University, Beijing 100871, China
关键词:
北京大学课程推荐推荐引擎协同过滤选课系统管理信息系统
Keywords:
Peking Universitycourse recommendationrecommendation enginecollaborative filteringelective systemmanagement information systems
分类号:
TP319
DOI:
10.3969/j.issn.1673-4785.201409045
文献标志码:
A
摘要:
为了在管理信息系统中向师生提供更个性化、人性化的服务,将推荐引擎应用到北京大学学生选课系统中,设计并实现北京大学课程推荐引擎.改进的推荐算法是一种以学生属性分类为前提的协同过滤算法,通过分析选课系统中课程推荐与商业推荐的不同点和学生属性、改进学生相似度的计算方法实现推荐.以北京大学学生选课系统为平台,2013—2014学年度第1学期的10 682名本科生为测试集,为其推荐课程,推荐结果的准确率为34.6%.该系统为学生选课提供了有效的指导,填补了选课系统智能化、个性化方面的空白.
Abstract:
In order to provide a more personalized and humanized service for students and teachers in the management information system, a recommendation engine is applied to the Peking University student course-selecting system. The Peking University course recommendation engine is designed and implemented. The improved recommendation algorithm is a collaborative filtering algorithm on the premises of student attribute classification. The recommendation is achieved through analyzing different points between course recommendation and commercial recommendation, analyzing student attribute and improving the calculation method of students’ similarity. As the platform, course-selecting system in Peking University recommend courses to 10 682 undergraduate students in the first semester of the 2013-2014 school year. The precision of recommendation results is 34.6%. This system can provide the effective guidance for the students choosing courses, and fill the blank of the system’s intelligent and personalized.

参考文献/References:

[1] 赵晨婷, 马春娥. 探索推荐引擎内部的秘密, 第1部分:推荐引擎初探.[EB/OL]. [2014-09-25]. http://www.ibm. com/developerworks/cn/web/1103_zhaoct_recommstudy1/index.html.
[2] 张瑶, 陈维斌, 傅顺开. 基于大数据的高校图书馆推荐系统仿真研究[J]. 计算机工程与设计, 2013, 34(7): 2533-2541. ZHANG Yao, CHEN Weibin, FU Shunkai. Simulation study of recommendation system for university library based on big data[J]. Computer Engineering and Design, 2013, 34(7): 2533-2541.
[3] 祁褎然, 潘志成, 罗敬, 等. 大学选课推荐系统的数学模型[J]. 南开大学学报:自然科学版, 2011, 44(4): 50-55.QI Youran, PAN Zhicheng, LUO Jing, et al. The mathematical model of the university course recommendation system[J]. Acta Scientiarum Naturalium Universitatis Nankaiensis, 2011, 44(4): 50-55.
[4] 陆刚. 数字信息资源利用中的“马太效应”及消除策略[J]. 图书馆建设, 2003(6): 43-45. LU Gang. The Matthew effect of the digital information resources using in the library and its solutions[J]. Library Development, 2003(6): 43-45.
[5] GOLDBERG D, NICHOLS D, OKI B M, et al. Using collaborative filtering to weave an information tapestry[J]. Communications of the ACM, 1992, 35(12): 61-70.
[6] RESNICK P, IACOVOU N, SUCHAK M, et al. Grouplens: an open architecture for collaborative filtering of netnews[C]//Proceedings of the 1994 ACM Conference on Computer Supported Cooperative Work. New York, USA, 1994: 175-186.
[7] 项亮. 推荐系统实践[M]. 北京: 人民邮电出版社, 2012.
[8] GE M Z, DELGADO-BATTENFELD C, JANNACH D. Beyond accuracy: evaluating recommender systems by coverage and serendipity[C]//Proceedings of the 4th ACM Conference on Recommender Systems. New York, USA, 2010: 257-260.

备注/Memo

备注/Memo:
收稿日期:2014-9-30;改回日期:。
基金项目:北京大学教育发展研究中心2013北大研究课题 (Y+25).
作者简介:沈苗,女,1985年生,工程师,主要研究方向为高校信息化.来天平,男,1977年,高级工程师,主要研究方向为高校信息化.王素美,女,1980年生,工程师,主要研究方向为高校信息化,负责和参与信息管理系统的设计开发工作10余项,曾获“北京大学第五届实验技术成果奖”二等奖,发表学术论文10篇.
通讯作者:沈苗. E-mail: shenm@pku.edu.cn.
更新日期/Last Update: 2015-07-15