基于Spark的高校图书馆书目推荐系统
|
摘要
如何将推荐系统应用于高校图书馆,将图书以个性化的方式推荐给用户,为用户提供优质的服务,是一个值得研究的课题。该文通过优化公开数据,消除时间偏置,确保推荐的准确性。同时,利用Spark大数据计算平台提高计算效率。经过测试,该系统的运行速度有了大幅提升,平均绝对偏差(MAE)也有显著的降低,能够给用户带来更快、更准确的个性化推荐,提高用户体验。
How to apply the recommendation system to university libraries and recommend books to users in a personalized manner for offering superior services to users is a topic worthy of study. The recommendation accuracy is ensured by optimizing public data and eliminating time offset. The Spark big data calculation platform is used to improve the calculation efficiency. The test results show that the system has a greatly-improved operation speed,and significantly-reduced mean absolute errors(MAEs),which can provide users with fast and accurate personalized recommendations to enhance user experiences.
How to apply the recommendation system to university libraries and recommend books to users in a personalized manner for offering superior services to users is a topic worthy of study. The recommendation accuracy is ensured by optimizing public data and eliminating time offset. The Spark big data calculation platform is used to improve the calculation efficiency. The test results show that the system has a greatly-improved operation speed,and significantly-reduced mean absolute errors(MAEs),which can provide users with fast and accurate personalized recommendations to enhance user experiences.
引文
[1]任星怡,宋美娜,宋俊德.基于用户签到行为的兴趣点推荐[J].计算机学报,2017,40(1):28-51.REN Xingyi,SONG Meina,SONG Junde. Point-of-interest recommendation based on the user check-in behavior[J]. Chinese journal of computers,2017,40(1):28-51.
[2]何胜,冯新翎,武群辉,等.基于用户行为建模和大数据挖掘的图书馆个性化服务研究[J].图书情报工作,2017,61(1):40-46.HE Sheng,FENG Xinling,WU Qunhui,et al. Research on personalized services of library based on user behavior modelling and big data mining[J]. Library and information service,2017,61(1):40-46.
[3]车晋强,谢红薇.基于Spark的分层协同过滤推荐算法[J].电子技术应用,2015,41(9):135-138.CHE Jinqiang,XIE Hongwei. Hierarchical collaborative filtering algorithm based on Spark[J]. Application of electronic technique,2015,41(9):135-138.
[4]王成,朱志刚,张玉侠,等.基于用户的协同过滤算法的推荐效率和个性化改进[J].小型微型计算机系统,2016,37(3):428-432.WANG Cheng,ZHU Zhigang,ZHANG Yuxia,et al. Improvement in recommendation efficiency and personalized of userbased collaborative filtering algorithm[J]. Journal of Chinese computer systems,2016,37(3):428-432.
[5]魏琳东,黄永峰.融合用户属性信息的冷启动推荐算法[J].电子技术应用,2017,43(10):137-140.WEI Lindong,HUANG Yongfeng. Incorporating user attribute data in recommendation system[J]. Application of electronic technique,2017,43(10):137-140.
[6]詹义,方媛.基于Spark技术的网络大数据分析平台搭建与应用[J].互联网天地,2016(2):75-78.ZHAN Yi,FANG Yuan. Building and application of network big data analysis platform based on Spark technology[J]. China Internet,2016(2):75-78.
[7]马玲娜.基于集体智慧的标签推荐系统的设计与开发[D].西安:陕西师范大学,2013.MA Lingna. Design and development of tag recommendation system based on collective intelligence[D]. Xi’an:Shaanxi Normal University,2013.
[8]郑炳维.基于Spark平台的协同过滤算法的研究与实现[D].广州:华南农业大学,2016.ZHENG Bingwei. Research and implementation of collaborative filtering algorithm based on Spark platform[D]. Guangzhou:South China Agricultural University,2016.
[9]张宏,王慧.基于用户评分和共同评分项的协同过滤算法研究[J].计算机应用研究,2019,36(1):77-80.ZHANG Hong,WANG Hui. Research on collaborative filtering algorithm based on user score and common score[J]. Application research of computers,2019,36(1):77-80.
[10]王捷.基于用户行为数据分析的高校图书馆信息服务平台研究[J].现代情报,2017,37(1):127-130.WANG Jie. Study of information service platform based on data analysis of user behavior in university libraries[J]. Modern information,2017,37(1):127-130.
[2]何胜,冯新翎,武群辉,等.基于用户行为建模和大数据挖掘的图书馆个性化服务研究[J].图书情报工作,2017,61(1):40-46.HE Sheng,FENG Xinling,WU Qunhui,et al. Research on personalized services of library based on user behavior modelling and big data mining[J]. Library and information service,2017,61(1):40-46.
[3]车晋强,谢红薇.基于Spark的分层协同过滤推荐算法[J].电子技术应用,2015,41(9):135-138.CHE Jinqiang,XIE Hongwei. Hierarchical collaborative filtering algorithm based on Spark[J]. Application of electronic technique,2015,41(9):135-138.
[4]王成,朱志刚,张玉侠,等.基于用户的协同过滤算法的推荐效率和个性化改进[J].小型微型计算机系统,2016,37(3):428-432.WANG Cheng,ZHU Zhigang,ZHANG Yuxia,et al. Improvement in recommendation efficiency and personalized of userbased collaborative filtering algorithm[J]. Journal of Chinese computer systems,2016,37(3):428-432.
[5]魏琳东,黄永峰.融合用户属性信息的冷启动推荐算法[J].电子技术应用,2017,43(10):137-140.WEI Lindong,HUANG Yongfeng. Incorporating user attribute data in recommendation system[J]. Application of electronic technique,2017,43(10):137-140.
[6]詹义,方媛.基于Spark技术的网络大数据分析平台搭建与应用[J].互联网天地,2016(2):75-78.ZHAN Yi,FANG Yuan. Building and application of network big data analysis platform based on Spark technology[J]. China Internet,2016(2):75-78.
[7]马玲娜.基于集体智慧的标签推荐系统的设计与开发[D].西安:陕西师范大学,2013.MA Lingna. Design and development of tag recommendation system based on collective intelligence[D]. Xi’an:Shaanxi Normal University,2013.
[8]郑炳维.基于Spark平台的协同过滤算法的研究与实现[D].广州:华南农业大学,2016.ZHENG Bingwei. Research and implementation of collaborative filtering algorithm based on Spark platform[D]. Guangzhou:South China Agricultural University,2016.
[9]张宏,王慧.基于用户评分和共同评分项的协同过滤算法研究[J].计算机应用研究,2019,36(1):77-80.ZHANG Hong,WANG Hui. Research on collaborative filtering algorithm based on user score and common score[J]. Application research of computers,2019,36(1):77-80.
[10]王捷.基于用户行为数据分析的高校图书馆信息服务平台研究[J].现代情报,2017,37(1):127-130.WANG Jie. Study of information service platform based on data analysis of user behavior in university libraries[J]. Modern information,2017,37(1):127-130.