Smart prediction of the complaint hotspot problem in mobile network

Lin ZHU; Juan ZHAO; Yiting WANG; Junlan FENG; Gchao DEN

doi:10.11959/j.issn.1000-0801.2019099

您当前的位置：

首页 >

文章列表页 >

Smart prediction of the complaint hotspot problem in mobile network

Topics:intelligent communication technologies and applications | 更新时间：2024-06-05

- Smart prediction of the complaint hotspot problem in mobile network
- Telecommunications Science Vol. 35, Issue 5, Pages: 17-24(2019)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2019099
  CLC： TN915
- Published Online：2019-05，
  
  Published：20 May 2019
- 稿件说明：
移动端阅览
Lin ZHU, Juan ZHAO, Yiting WANG, et al. Smart prediction of the complaint hotspot problem in mobile network[J]. Telecommunications science, 2019, 35(5): 17-24.
DOI：

Lin ZHU, Juan ZHAO, Yiting WANG, et al. Smart prediction of the complaint hotspot problem in mobile network[J]. Telecommunications science, 2019, 35(5): 17-24. DOI： 10.11959/j.issn.1000-0801.2019099.

摘要

在移动通信网络中，一旦发生投诉热点问题，通常会影响大量用户的上网、通话体验，进而引发大量用户投诉，即网络投诉热点问题，该问题因其影响范围大、用户多，一旦发生往往影响恶劣，需实时监控并提前预警和处理。提出一种基于用户级信令数据的投诉热点问题预警方法。首先基于对业务逻辑的理解，选择了S1接口数据中与用户体验相关的30个关键字段；然后，提取one-hot特征、统计衍生特征和差分特征3类特征来详细刻画用户感知状况；针对数据中噪声大及正负样本不均衡等问题，采用泛化能力较强且针对样本不均衡问题有所改善的 LightGBM 分类器实时识别受影响的用户。这一方法可以实时输出潜在受影响的用户与区域，先于用户投诉提前处理问题或进行客户关怀，有效降低影响，提升客户体验。试验结果与某省现网部署应用均验证了算法的有效性。

Abstract

In telecom communication network

a hot customer complaint often affects hundreds even thousands of users’ service and leads to significant economic losses and bulk complaints.An approach was proposed to predict a customer complaint based on real-time user signaling data.Through analyzing the network business layer logic

30 key segments related to the user experience in the S1 interface data were selected.Further

one-hot features

statistical derived features

and differential features were extracted to classify user perceptions in detail.Considering the problems of noise data and unbalanced training samples

LightGBM was chosen to train the prediction model.Experiments are conducted to prove the effectiveness and efficiency of this proposal.As of today

this approach has been deployed in our daily business to locate the hot complaint problem scope as well as to report affected users and area.

关键词

Keywords

references

CHAO H C , TANG K A , LIU Y H , et al . Using Kernel density estimation to target customer complaint handling service [C ] // Asia-Pacific Network Operations and Management Symposium,Sep 27-29,2017,Seoul,Korea.[S.l.:s.n] . 2017 : 215 - 218 .

TUĞ BA K , ÖNEŞ O , ALBEY E , et al . Smart diagnosis and solution systems for network based customer complaints [C ] // Signal Processing ＆ Communication Application Conference,May 16-19,2016,Zonguldak,Turkey . Piscataway:IEEE Press , 2016 : 1753 - 1756 .

ZHANG K , YANG P . WCDMA ratio network optimization approach based on measurement report [C ] // IET International Conference on Communication Technology ＆ Application,Oct 14-16,2011,Beijing,China . Piscataway:IEEE Press , 2011 : 379 - 383 .

FEYZULLAH K , ZEYDAN E , YIGIT I O , et al . A customer complaint analysis tool for mobile network operators [C ] // ACM International Conference on Advances in Social Networks Analysis and Mining,August 28-31,2018,Barcelona,Spain . New York:ACM Press , 2018 : 609 - 612 .

LI Y , LI J , LI W C , et al . Rural distribution network fault location algorithm based on fault complaint information [C ] // Third International Conference on Measuring Technology ＆ Mechatronics Automation,Jan 6-7,2011,Shanghai,China . Piscataway:IEEE Press , 2011 : 199 - 202 .

YIGIT I O , ZEYDAN E , ATES A F . An application for detecting network related problems from call center text data [C ] // International Black Sea Conference on Communicationsand Networking,June 5-8,2017,Istanbul,Turkey . Piscataway:IEEE Press , 2017 .

YANG Q , JI G Q , ZHOU W . The correlation analysis and prediction between mobile phone users complaints and telecom equipment failures under big data environments [C ] // 2017 2nd International Conference on Advanced Robotics and Mechatronics,August 27-31,2017,Hefei,China . Piscataway:IEEE Press , 2017 : 201 - 206 .

FRIEDMAN J H . Greedy function approximation:a gradient boosting machine [J ] . The Annals of Statistics , 2001 , 29 ( 5 ): 1189 - 1232 .

FRIEDMAN J H . Stochastic gradient boosting [J ] . Computational Statistics ＆ Data Analysis , 2002 , 38 ( 4 ): 367 - 378 .

陈晓芳 , 张天韵 , 张儒申 , 等 . 基于 GBDT 等数据挖掘算法的场景用户识别方法 [J ] . 电信科学 , 2018 , 34 ( S2 ): 167 - 175 .

CHEN X F , ZHANG T Y , ZHANG R S , et al . Scene user identification method based on data mining algorithm such as GBDT [J ] . Telecommunications Science , 2018 , 34 ( S2 ): 167 - 175 .

MENG Q , KE G , WANG T , et al . A communication-efficient parallel algorithm for decision tree [J ] . arXiv:1611.01276 , 2016 .

Views

241

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A hybrid model for smart grid theft detection based on deep learning

Optimal active defense decision model of wireless communication network under APT attack

Low complexity radar signal classification based on spectrum shape

Face recognition algorithm based on attractive local second gradient contours

Internet bad information detection based on Bert model

Related Author

Yaoyuan LIANG

Jun ZHANG

Yinling LIAO

Jincan LI

Bing WANG

Danni WANG

Meng MENG

Fuliang ZHANG

Related Institution

Guangxi Power Grid Co., Ltd.

Wuzhou Power Supply Bureau of Guangxi Power Grid Co., Ltd.

School of Communication and Information Engineering, Beijing University of Posts and Telecommunications

National Innovation Institute of Defense Technology, Academy of Military Science

College of Information Engineering,China Jiliang University

⁰