Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Traffic data category identification method and device

A flow data and identification method technology, applied in the direction of digital data protection, electronic digital data processing, character and pattern recognition, etc., can solve the problem of unable to realize classification, etc.

Pending Publication Date: 2022-02-15
BEIJING TOPSEC NETWORK SECURITY TECH +2
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in practice, it is found that the statistical characteristics of traffic can be the maximum, minimum, average and variance of the number of bytes, number of packets, duration, etc. of a flow. Since the characteristics of all data in a flow need to be counted, so Classification can only be performed after the connection ends, which makes it impossible to achieve real-time classification

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
  • Traffic data category identification method and device
  • Traffic data category identification method and device
  • Traffic data category identification method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Please see figure 1 , figure 1 A schematic flowchart of a method for classifying traffic data is provided for the embodiment of the present application. Among them, the category identification method of the traffic data includes:

[0041] S101. Acquire the traffic data to be tested sent to the same destination address within a preset time period.

[0042] In this embodiment, the types of traffic data include: instant messaging data, file transfer data, streaming media data, mail and so on.

[0043] In this embodiment, the flow data carries a mark or label of the flow type.

[0044] In this embodiment, the method can collect flow data within 3 minutes, 5 minutes, and 10 minutes.

[0045] In this embodiment, the method may only collect traffic within a specified time period for each category of traffic.

[0046] S102. Perform cleaning processing on the traffic data to obtain valid data.

[0047] In this embodiment, the method can preferentially delete invalid data (...

Embodiment 2

[0075] Please see figure 2 , figure 2 It is a schematic structural diagram of an apparatus for classifying traffic data provided in an embodiment of the present application. Such as figure 2 As shown, the category identification device of the flow data includes:

[0076] An acquisition unit 210, configured to acquire flow data to be measured;

[0077] A preprocessing unit 220, configured to preprocess the traffic data to obtain preprocessed data;

[0078] The extraction unit 230 is configured to perform feature extraction on the preprocessed data through a joint histogram to obtain traffic features;

[0079] The identifying unit 240 is configured to classify and identify the traffic characteristics through a preset classifier to obtain the traffic category.

[0080] As an optional implementation manner, the obtaining unit 210 is specifically configured to obtain the traffic data to be measured sent to the same destination address within a preset time period.

[0081] ...

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 embodiment of the invention provides a traffic data category identification method and device, and relates to the field of data processing and identification. The traffic data category identification method comprises the steps of obtaining to-be-detected traffic data; preprocessing the traffic data to obtain preprocessed data; performing feature extraction on the preprocessed data through a combined histogram to obtain traffic features; and performing classification identification on the traffic features through a preset classifier to obtain a traffic category. Therefore, by implementing the implementation mode, real-time classification can be carried out, and the associated flow characteristics of the multiple angles can be obtained through the combined histogram, so that the classification accuracy can be improved; in addition, since the content features of the data packet do not need to be extracted, the method can also perform data classification on the encrypted traffic.

Description

technical field [0001] The present application relates to the field of data processing and identification, in particular, to a method and device for class identification of traffic data. Background technique [0002] In recent years, the technology of using the statistical characteristics of network traffic and machine learning algorithms to classify traffic has attracted the attention of many researchers. However, in practice, it is found that the statistical characteristics of traffic can be the maximum, minimum, average and variance of the number of bytes, number of packets, duration, etc. of a flow. Since the characteristics of all data in a flow need to be counted, so The classification can only be performed after the connection ends, which makes it impossible to realize real-time classification. Contents of the invention [0003] The purpose of the embodiments of the present application is to provide a method and device for classifying traffic data, which can realiz...

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
IPC IPC(8): G06F21/60G06K9/62
CPCG06F21/602G06F18/2135G06F18/24323G06F18/214
Inventor 张新
Owner BEIJING TOPSEC NETWORK SECURITY TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com