基于国网商旅大数据融合背景的用户画像构建

doi:10.11959/j.issn.1000-0801.2019285

Abstract

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

CLC Number:

TP393

Changhao ZHANG,Zhiyong YU,Zhen ZHOU,Ruijie SHI,Xinyong WANG. User image construction framework based on big data fusion background for power grid business travel[J]. Telecommunications Science, 2019, 35(12): 148-154.

Figures/Tables 7

References 12

[1]	黎文阳 . 大数据处理模型 Apache Spark 研究[J]. 现代计算机(专业版), 2015(8): 55-60.
	LI W Y . Research on big data processing model apache spark[J]. Modern Computer (Professional Edition), 2015(8): 55-60.
[2]	李荟娆 . K-means 聚类方法的改进及其应用[D]. 哈尔滨:东北农业大学, 2014.
	LI H W . Improvement of K-means clustering method and its application[D]. Harbin:Northeast Agricultural University, 2014.
[3]	祝恒书 . 面向移动商务的数据挖掘方法及应用研究[D]. 中国科学技术大学, 2014.
	ZHU H S . Research on data mining methods and applications for mobile commerce[D]. China University of science and technology, 2014.
[4]	马聪 . 基于用户行为挖掘的情景感知推荐[D]. 浙江:浙江大学, 2015.
	MA C . Situational awareness recommendation based on user behavior mining[D]. Zhejiang:Zhejiang University, 2015.
[5]	吴智勤, 柳益君, 李仁璞 ,等. 基于社交网络的高校图书馆用户画像构建研究[J]. 图书馆学研究, 2018,435(16): 27-32.
	WU Z Q , LIU Y J , LI R P ,et al. Research on the construction of user portrait in university library based on social network[J]. Library science research, 2018,435(16): 27-32.
[6]	赵腾, 张焰, 张东霞 . 智能配电网大数据应用技术与前景分析[J]. 电网技术, 2014,38(12): 3305-3312.
	ZHAO T , ZHANG Y , ZHANG D X . Analysis of big data application technology and prospect of intelligent distribution network[J]. Power System Technology, 2014,38(12): 3305-3312.
[7]	曾晶 . Radviz可视化技术度量模型的研究[D]. 北京:北京交通大学, 2011.
	ZENG J . Research on radvizvisualization technology measurement model[D]. Beijing:Beijing Jiaotong University, 2011.
[8]	代双凤, 董继阳, 薛健 . 科学计算中大数据可视化分析与应用[J]. 工程研究-跨学科视野中的工程, 2014,6(3): 275-281.
	DAI S F , DONG J Y , XUE J . Visualization analysis and application of big data in scientific computing[J]. Engineering Research-Interdisciplinary Engineering, 2014,6(3): 275-281.
[9]	雷莹 . 基于 Web 的可视化数据挖掘分析平台及可视化度量模型的研究与实现[D]. 北京:北京交通大学, 2014.
	LEI Y . Research and implementation of Web-based visual data mining analysis platform and visual measurement model[D]. Beijing:Beijing Jiaotong University, 2014.
[10]	宋亚奇, 周国亮, 朱永利 . 智能电网大数据处理技术现状与挑战[J]. 电网技术, 2013(4): 927-935.
	SONG Y Q , ZHOU G L , ZHU Y L . Current status and challenges of big data processing technology in smart grid[J]. Power System Technology, 2013(4): 927-935.
[11]	姚晓辉, 胡源, 张宇翔 . 电信行业客户行为标签数据对外经营模式研究[J]. 电信科学, 2013,29(11): 17-22.
	YAO X H , HU Y , ZHANG Y X . Research on external business model of customer behavior label data in telecom industry[J]. Telecom Science, 2013,29(11): 17-22.
[12]	黄勇军, 冯明, 丁圣勇 ,等. 电信运营商大数据发展策略探讨[J]. 电信科学, 2013,29(3): 13-17.
	HUANG Y J , FENG M , DING S Y ,et al. Discussion on big data development strategy of telecom operators[J]. Telecommunications Science, 2013,29(3): 13-17.

Metrics

Recommended 0

No Suggested Reading articles found!

特征类型	业务信息特征群	差旅控制信息特征群	酒店信息特征群
类别	√
统计	√	√	√
数值	√	√	√
时间	√
聚类	√		√
文本	√	√

模型		F值
模型	低活跃度用户		高活跃度用户
DT	0.749		0.790
XGBoost	0.901		0.842
RF	0.809		0.790
GBDT	0.860		0.821
SVM	0.780		0.789
LR	0.724		0.779

模型		F1值
模型	低活跃度用户	高活跃度用户	线上得分
MVEM	0.942	0.891	0.933 80
Single	0.781	0.861	0.892 11
单模型	0.912	0.835	0.891 22
Stacking	0.901	0.831	0.898 21

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

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 12

Related Articles 1

Metrics

Recommended 0