电信科学 ›› 2019, Vol. 35 ›› Issue (12): 148-154.doi: 10.11959/j.issn.1000-0801.2019285

• 运营技术广角 • 上一篇    

基于国网商旅大数据融合背景的用户画像构建

张长浩1,余志勇2,周振2,石瑞杰1,王新勇1   

  1. 1 国网电子商务有限公司,北京 100053
    2 国家电网有限公司,北京 100031
  • 修回日期:2019-12-10 出版日期:2019-12-20 发布日期:2020-01-15
  • 作者简介:张长浩(1971- ),男,国网电子商务有限公司副总经理、党委委员、纪委书记、工会主席,主要研究方向为财务信息化、大数据、行政管理、纪检监察、人力资源、党建管理|余志勇(1974- ),男,国家电网有限公司财务部会计处副处长、会计师,主要研究方向为管理会计、信息化|周振(1984- ),男,国家电网有限公司财务部会计处高级会计师,主要研究方向为财务管理、财务信息化|石瑞杰(1973- ),男,国网电子商务有限公司业务运营中心高级工程师、业务运营中心主任,主要研究方向为财务管理、财务信息化|王新勇(1976- ),男,国网电子商务有限公司高级经济师、财务共享中心主任,主要研究方向为财务管理、财务信息化

User image construction framework based on big data fusion background for power grid business travel

Changhao ZHANG1,Zhiyong YU2,Zhen ZHOU2,Ruijie SHI1,Xinyong WANG1   

  1. 1 State Grid E-commerce Co.,Ltd.,Beijing 100053,China
    2 State Grid Corporation,Beijing 100031,China
  • Revised:2019-12-10 Online:2019-12-20 Published:2020-01-15

摘要:

基于大数据分析的商旅计划决策是掌控差旅动态、制定差旅规范的重要组成部分。基于国网商旅信息数据,针对出差过程中出行方式的优化选取、酒店住宿的个人喜好,构建一种用户画像框架技术,实现快速、准确识别敏感客户群体。首先针对用户不同特性采用双通道建模方式预测用户敏感程度;其次围绕业务审批、差旅控制、酒店评价、时间特征、数值特征等类型刻画用户,构建用户多源特征体系;最后充分利用商旅数据多源性,创建基于双层XGBoost的多视角融合模型,提升分类精确率,并通过对比实验验证方法的有效性。

关键词: 用户画像, 多视角学习, 模型融合

Abstract:

Business travel planning decisions based on big data analysis are an important part of controlling travel dynamics and developing travel specifications.Based on the information of the national network business travel information,aiming at the optimization of the travel mode during the travel process and the personal preference of hotel accommodation,a user portrait framework technology was constructed to realize the rapid and accurate identification of sensitive customer groups.Firstly,the user's sensitivity was predicted by two-channel modeling for different characteristics of users.Secondly,users were characterized by business approval,travel control,hotel evaluation,time characteristics,numerical characteristics,etc.,and users’ multi-source feature system was constructed.Finally,business travel data was fully utilized.Multi-source,create a multi-view fusion model based on double-layer XGBoost,improve classification accuracy,and verify the effectiveness of the method by comparing experiments.

Key words: user portrait, multi-view learning, model fusion

中图分类号: 

No Suggested Reading articles found!