A real time approach to user interest classification using DPI

Kang CHEN; Huazheng FU; Chong CHEN; Yuyi ZHANG; Yu WEI

doi:10.11959/j.issn.1000-0801.2016304

您当前的位置：

首页 >

文章列表页 >

A real time approach to user interest classification using DPI

Operating technology wide-angle | 更新时间：2024-06-05

- A real time approach to user interest classification using DPI
- Telecommunications Science Vol. 32, Issue 12, Pages: 109-115(2016)
- 作者机构：
  
  1. 中国电信股份有限公司广州研究院，广东广州 510630
  2. 广东工业大学计算机学院，广东广州 510006
  3. 广州优亿信息科技有限公司，广东广州 510630
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2016304
  CLC： TP311
- Published Online：2016-12，
  
  Published：20 December 2016
- 稿件说明：
移动端阅览
Kang CHEN, Huazheng FU, Chong CHEN, et al. A real time approach to user interest classification using DPI[J]. Telecommunications science, 2016, 32(12): 109-115.
DOI：

Kang CHEN, Huazheng FU, Chong CHEN, et al. A real time approach to user interest classification using DPI[J]. Telecommunications science, 2016, 32(12): 109-115. DOI： 10.11959/j.issn.1000-0801.2016304.

摘要

近年来，随着大数据发展热潮兴起，电信运营商能获得的DPI数据规模越来越大。如何对如此海量的DPI数据进行实时的挖掘和分类是运营商研究的热点。设计了一种基于混合n-gram特征的URL分类算法和基于Doc2Vec模型的文本分类算法相结合的DPI数据分类方法，大大提高了DPI数据的分类速度和分类准确率，为电信运营商进行精准营销提供了良好的基础。

Abstract

In recent years

with the rapid development of internet

telecom operators can gather more and more DPI data. How to mine and classify huge amounts of DPI data in real time is the key point. A DPI data classification method was presented

which combined the URL classification model based on mixed n-gram features and the Doc2Vec based text classification algorithm. The DPI data classification speed and classification accuracy were greatly improved

and good support for precise marketing was provided.

关键词

Keywords

references

罗忆祖 . DPI技术助力运营商精细化运营 [J ] . 电信网技术 , 2009 ( 3 ): 22 - 24 .

LUO Y Z . DPI helps operators refinement operation [J ] . Telecommunication Network Technology , 2009 ( 3 ): 22 - 24 .

ABRAMSON M , AHA D W . Whatˊs in a URL? Genre classification from URLs [J ] . Workshops at the Twenty , 2012 .

边凌燕，贺仁龙，姚晓辉 . 于DPI数据挖掘实现URL分类挂载的相关技术研究 [J ] . 电信科学 , 2013 , 29 ( 11 ): 6 - 11 .

BIAN L Y , HE R L , YAO X H . Research on URL classification with DPI data mining and related technology [J ] . Telecommunications Science , 2013 , 29 ( 11 ): 6 - 11 .

朱丽娜 . 中文网页分类特征提取方法研究 [D ] . 北京 : 中国石油大学， 2009 .

ZHU L N . Research of feature selection for Chinese Web page categorization [D ] . Beijing : China University of Petroleum , 2009 .

KAN M Y , THI H O N . Fast webpage classification using URL features [C ] // 14th ACM international conference on Information and knowledge management , October 31 - November 5 , 2005 , New York, USA . New York : ACM Press , 2005 : 325 - 326 .

汪光庆 . 基于SVM的网页分类技术研究 [D ] . 北京 : 中国石油大学， 2011 .

WANG G Q . The research of Web pages classification based on SVM technique [D ] . Beijing : China University of Petroleum , 2011 .

陈燃燃 . 基于SVM算法的Web分类研究与实现 [D ] . 北京 : 北京邮电大学， 2009 .

CHEN R R . Research and implementation of Web classification based on SVM algorithm [D ] . Beijing : University of Posts and Telecommunications , 2009 .

苏金树，张博锋，徐昕 . 基于机器学习的文本分类技术研究进展 [J ] . 软件学报 , 2006 , 17 ( 9 ): 1848 - 1859 .

SU J S , ZHANG B F , XU X . Advances in machine learning based text categorization [J ] . Journal of Software , 2006 , 17 ( 9 ): 1848 - 1859 .

BERNERS-LEE T , MASINTER L , MCCAHILL M . RFC 1738:uniform resource locator [J ] . Internet Engineering Task Force , 1994 .

余小军，刘峰，张春 . 基于n-gram文本特征提取的改进算法 [J ] . 现代计算机 , 2012 ( 23 ): 3 - 7 .

YU X J , LIU F , ZHANG C . Improved text feature extraction algorithm based on n-gram [J ] . Modem Computer , 2012 ( 23 ): 3 - 7 .

郑霖，徐德华 . 基于改进TFIDF算法的文本分类研究 [J ] . 计算机与现代化 , 2014 ( 9 ): 6 - 9 .

ZHENG L , XU D H . Research on text categorization based on improved TFIDF algorithm [J ] . Computer and Modernization , 2014 ( 9 ): 6 - 9 .

LE Q V , MIKOLOV T . Distributed representations of sentences and documents [J ] . Computer Science , 2014 ( 14 ): 1188 - 1196 .

庞观松，蒋胜益 . 文本自动分类技术研究综述．情报理论与实践 [J ] . 信息学：理论与应用 , 2012 , 35 ( 2 ): 123 - 128 .

PAND G S , JIANG S y . A survey of automatic text classification techniques [J ] . Information Studies: Theory ＆ Application , 2012 , 35 ( 2 ): 123 - 128 .

Views

811

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research and implementation of text classification method for customer service orders based on multi-model fusion

Application on text classification of telecom user complaints based on GRW and FastText model

Virtualized deployment of DPI based on Docker

Accurate analysis method of network element performance and service data characteristics

Key technology research and model validation of text classification system based on deep learning

Related Author

Tongze He

Rong ZHENG

Xiaoju DAI

Liang ZHANG

Xiaojun YANG

Jin ZHAO

Zhao XUE

Jie PAN

Related Institution

Shanghai Ideal Information Industry (Group) Co., Ltd.

Beijing University of Posts and Telecommunications

⁰