计算机工程 ›› 2019, Vol. 45 ›› Issue (1): 206-209,216.doi: 10.19678/j.issn.1000-3428.0049121

• 人工智能及识别技术 • 上一篇    下一篇

基于深度学习的个性化网吧游戏推荐

陈耀旺1,严伟2,俞东进1,徐凯辉1,夏艺1,杨威3   

  1. 1.杭州电子科技大学 计算机学院,杭州 310018; 2.浙江省科技信息研究院,杭州 310006; 3.浙江天正信息科技有限公司,杭州 310006
  • 收稿日期:2017-10-30 出版日期:2019-01-15 发布日期:2019-01-15
  • 作者简介:陈耀旺(1987—),男,硕士,主研方向为推荐系统、软件体系架构;严伟,高级工程师、硕士;俞东进(通信作者),教授、博士生导师;徐凯辉,硕士研究生;夏艺,工程师;杨威,高级工程师、硕士
  • 基金项目:

    国家自然科学基金(61472112);浙江省重点研发项目(2017C01010,2016F50014,2015C01040)

Personalized Internet Bar Game Recommendation Based on Deep Learning

CHEN Yaowang 1,YAN Wei 2,YU Dongjin 1,XU Kaihui 1,XIA Yi 1,YANG Wei 3   

  1. 1.School of Computer,Hangzhou Dianzi University,Hangzhou 310018,China; 2.Zhejiang Institute of Science and Technology Information,Hangzhou 310006,China; 3.Zhejiang Topcheer Information Technology Co.,Ltd.,Hangzhou 310006,China
  • Received:2017-10-30 Online:2019-01-15 Published:2019-01-15

摘要:

与传统推荐模型相比,深度学习可以更好地理解用户需求、项目特征及用户与项目之间的互动性,从而更有效地发现用户和项目之间的匹配关系。将深度神经网络应用于网吧游戏推荐场景,分析用户的个人偏好,根据时间推移兴趣的变化,对用户历史游戏行为记录进行建模训练,为用户提供个性化Top-N游戏推荐。基于深度神经网络设计训练模型,输入层采用对用户历史行为数据处理后的用户偏好向量,隐藏层运用ReLU激活函数的多层网络,输出层则采用逻辑回归的Softmax结构,最终运用带L2规范项的代价函数评估学习到的模型可靠性。在真实数据集下的实验结果表明,随着隐藏层的增加,该方法能明显降低均方根误差,且能提高召回率。

关键词: 个性化网吧, 深度学习, 推荐算法, 深度神经网络, 游戏场景

Abstract:

Compared with the traditional recommendation model,deep learning can better understand user needs,project characteristics and user-project interaction,so as to more effectively discover the matching relationship between users and projects.The deep neural network is applied to the recommended scene of the internet bar game,and the user’s personal preference is analyzed.According to the change of interest in the time,the game record of the user history is modeled and trained to provide the user with personalized Top-N game recommendation.Based on the deep neural network design training model,the input layer uses the user preference vector processed by the user’s historical behavior data,the hidden layer uses the multi-layer network of the ReLU activation function,and the output layer uses the Logical regression Softmax structure,and finally the L2 specification item is used.The cost function evaluates the reliability of the learned model.Experimental results under the real data set show that with the increase of the hidden layer,the method can significantly reduce the root mean square error and improve recall rate.

Key words: personalized internet bar, deep learning, recommendation algorithm, deep neural network, game scene

中图分类号: