查询结果:   赵桂升,潘善亮.基于IRGAN模型和Hadoop的电影推荐系统的设计[J].计算机应用与软件,2019,36(5):43 - 50.
中文标题
基于IRGAN模型和Hadoop的电影推荐系统的设计
发表栏目
应用技术与研究
摘要点击数
743
英文标题
DESIGN OF FILM RECOMMENDATION SYSTEM BASED ON IRGAN MODEL AND HADOOP
作 者
赵桂升 潘善亮 Zhao Guisheng Pan Shanliang
作者单位
宁波大学信息科学与工程学院 浙江 宁波 315211     
英文单位
Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315211, Zhejiang, China     
关键词
IRGAN Hadoop Spark Kafka 电影推荐系统
Keywords
IRGAN Hadoop Spark Kafka Film recommendation system
基金项目
浙江省公益性技术应用研究计划项目(2017C33001)
作者资料
赵桂升,硕士生,主研领域:推荐系统,信息检索。潘善亮,教授。 。
文章摘要
随着近几年人工智能技术的飞速发展,深度学习技术在推荐系统领域中的应用也已经成为研究热点之一。尤其是生成对抗网络(GAN)作为无监督学习中最具前景的方法之一,在图像处理和自然语言等领域取得突破性进展。针对目前存在的电影市场规模扩大、观影用户数量增长过快以及电影资源更新频繁等带来的数据利用率低、系统压力大、实时性差等弊端,结合Hadoop、Spark和Kafka等大数据处理技术,设计基于IRGAN算法模型的离线推荐模块和基于在线用户行为数据收集处理的在线推荐模块。实现了基于IRGAN模型和Hadoop的电影推荐系统。测试表明,该系统具有良好的推荐准确性、稳定性和实时性。
Abstract
With the rapid development of artificial intelligence technology in recent years, the application of deep learning in the field of recommendation systems has become one of the research hotspots. Especially generative adversarial networks(GAN), as one of the most promising methods in unsupervised learning, has also made breakthroughs in the field of image processing and natural language. The disadvantages of low data utilization, high system pressure and poor real-time performance are caused by the expansion of the film market, the rapid growth of the number of movie-watching users and the frequent update of film resources. In order to solve the above problems, combining Hadoop, Spark and Kafka and other big data processing technologies, we designed the offline recommendation module based on IRGAN algorithm model and the online recommendation module based on online user behavior data collection and processing. And the film recommendation system based on IRGAN model and Hadoop was realized. The test shows that the system has good recommendation accuracy, stability and real-time.
下载PDF全文