Terminal application data flow identification method and system

A technology of terminal application and identification method, applied in the field of mobile communication, can solve the problem of low accuracy rate of data stream identification, and achieve the effect of improving accuracy rate and ensuring identification efficiency

Inactive Publication Date: 2020-11-10
HUAZHONG UNIV OF SCI & TECH
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above defects or improvement needs of the prior art, the present invention provides a terminal application data flow identification method and system, which aims to solve the technical problem of low accuracy when performing data flow identification in the prior art

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Terminal application data flow identification method and system
  • Terminal application data flow identification method and system
  • Terminal application data flow identification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] A terminal application data flow identification method, such as figure 1 shown, including the following steps:

[0063] S1. Preprocessing the terminal application data stream collected in real time to obtain a collection of multiple categories of data packets classified according to the five-tuple information;

[0064] Specifically, in this embodiment, the wireshark protocol analysis software is used to collect terminal application data streams, and after storing them in the form of pcap files, the data packets in it are grouped every preset number, and the data packets in each group are grouped according to five yuan Group information is classified to obtain a collection of data packets of multiple categories, such as figure 2 As shown; wherein, if the number of data packets in a certain group is less than the preset number, continue to collect the data flow at the bottom layer of the terminal. It should be noted that the source of quintuple information includes IP ...

Embodiment 2

[0084] A terminal application data stream identification system, such as Figure 7 As shown, including: data preprocessing module, model training module and data flow identification module;

[0085] The data preprocessing module is used to preprocess the data stream, and obtain multiple categories of data packet collections classified according to the five-tuple information; specifically, the method for preprocessing the data stream includes: the data in the data stream The packets are grouped every preset number, and the data packets in each group are classified according to the five-tuple information to obtain a collection of data packets of multiple categories.

[0086] The model training module is used to collect a number of terminal application data streams, and mark the application business of each data packet in each data stream, input each data stream into the data preprocessing module, and obtain multiple data streams classified according to quintuple information A s...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a terminal application data flow identification method and system, and the method comprises the following steps: S1, carrying out the preprocessing of a to-be-identified terminal application data flow collected in real time, and obtaining a plurality of types of data package sets after classification according to quintuple information; s2, extracting a first data feature ofthe obtained data packet set of each category, respectively matching the first data feature with the features of a plurality of preset application services, if the first data feature can be successfully matched with the features of any preset application behavior, determining that the application services to which all data packets in the data packet set of the category belong are the preset application services, and ending the operation; otherwise, turning to the step S3; S3, extracting a second data feature of the obtained data packet set of each category, inputting the second data feature into a pre-trained data stream identification model, and identifying the data stream. According to the invention, through hierarchical data flow identification, the accuracy of data flow identificationcan be greatly improved while the identification efficiency is ensured.

Description

technical field [0001] The invention belongs to the technical field of mobile communication, and more specifically, relates to a terminal application data stream identification method and system. Background technique [0002] With the explosion of the Internet and smart phones, the Internet has had a profound impact on people's lifestyles, and people's lives are increasingly inseparable from the Internet. While the network brings great convenience to people, it also puts great pressure on network supervision and network load. Various traffic is transmitted in the network, which may contain various malicious traffic, which has a great impact on the network. have a greater impact. By identifying different types of network traffic, targeted management of traffic can be achieved, such as intercepting malicious traffic and transmitting high-priority traffic as soon as possible. Therefore, it is a very meaningful technology to identify and detect the type of traffic. [0003] D...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): H04L12/851G06N20/20
CPCG06N20/20H04L47/2483
Inventor 钟祎魏浩韩涛葛晓虎雷波
Owner HUAZHONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products