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

Video traffic identification method and system based on Burst features, electronic equipment and storage medium

A traffic recognition and video recognition technology, applied in character and pattern recognition, electrical components, instruments, etc., can solve problems such as poor accuracy, inability to distinguish video traffic, and inability to apply video traffic to achieve fast training speed and high The effect of recognition efficiency and recognition accuracy

Active Publication Date: 2022-06-28
HARBIN INST OF TECH
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, its poor accuracy and the need to manually select features cannot meet the rapidly growing fine-grained traffic classification requirements
[0006] Methods based on traditional traffic classification cannot identify video traffic in a fine-grained manner
Common traffic identification features such as packet size, time interval, and TCP stream quintuple cannot distinguish video traffic and cannot be used as a fingerprint of video traffic
The traditional method used in video traffic identification only considers some metadata in the process of video traffic transmission, and cannot extract the characteristics of representative video traffic
Therefore, this type can only be applied to the identification of network protocols or APP traffic, and cannot be applied to the field of video traffic

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
  • Video traffic identification method and system based on Burst features, electronic equipment and storage medium
  • Video traffic identification method and system based on Burst features, electronic equipment and storage medium
  • Video traffic identification method and system based on Burst features, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Embodiment 1, refer to Figure 1-4 Describe this embodiment, a method for identifying video traffic based on Burst features, comprising the following steps:

[0043] S1. Capture video traffic and preprocess the video traffic. The specific method includes the following steps:

[0044] S11. Automatically capture video traffic. The specific method is to control the browser to play the corresponding video by entering the URL, and start tshark to capture the traffic;

[0045] Specifically, the automatic capture of video traffic can be implemented through the Selenium tool to automatically capture the script of video traffic;

[0046] Specifically, to automatically capture video traffic, a script for automatically capturing video traffic can be implemented through the Tshark tool;

[0047] Specifically, a stop threshold can be set for traffic capture, such as 5 minutes to stop the process.

[0048] S12.S12. Take the TCP stream in the video traffic, divide the TCP stream in...

Embodiment 2

[0068] Embodiment 2, a kind of video traffic identification method based on Burst feature, including traffic capture module, time sequence feature extraction module and traffic video identification module;

[0069] The traffic capture module is used to capture video traffic and preprocess the video traffic;

[0070] The time series feature extraction module is used to obtain time series features;

[0071] The traffic video recognition module is used to classify data and identify video traffic.

[0072] Definitions of abbreviations and key terms of the present invention:

[0073] DASH: The full name is Dynamic Adaptive Streaming over HTTP and the dynamic adaptive bit rate stream given to HTTP. The workflow is as follows: The HTTP Server divides the media file into small segments of equal time length, and each segment is encoded as a different bit rate and resolution. The client downloads through a GET request. The client downloads slices of the corresponding bit rate and res...

Embodiment 3

[0075] Embodiment 3. The computer device of the present invention may be a device including a processor and a memory, for example, a single-chip microcomputer including a central processing unit. And, when the processor is configured to execute the computer program stored in the memory, it implements the steps of the above-mentioned recommendation method based on CREO software that can modify the relationship-driven recommendation data.

[0076] The processor may be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf processors Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may b...

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 provides a video traffic identification method and system based on Burst features, electronic equipment and a storage medium, and belongs to the technical field of log anomaly detection. Comprising the following steps: step 1, capturing video traffic, and preprocessing the video traffic; step 2, acquiring a Burst feature of the preprocessed video traffic and a time sequence feature corresponding to a Burst sequence; and step 3, taking data after Burst feature and time sequence feature extraction as fingerprints of a single video, and classifying the data so as to identify video traffic. According to the method, video identification is mainly carried out on a video stream transmitted by a video platform constructed based on a DASH protocol, secondary feature extraction is carried out through unique Burst features of each video, and time sequence features in a Brst sequence are analyzed. And a Light GBM model is created to identify the time sequence characteristics of a single video. The technical problem that the video traffic cannot be identified in a fine-grained manner is solved.

Description

technical field [0001] The present application relates to a method for identifying video traffic, in particular to a method, system, electronic device and storage medium for identifying video traffic based on Burst features, belonging to the technical field of log anomaly detection. Background technique [0002] The continuous development of online video technology has made people's lives more and more colorful, and it has also brought opportunities for criminals. The criminals make illegal videos and upload them to the Internet, causing some illegal content to spread on the Internet. bad social impact. At present, the methods for network traffic identification are mainly divided into three categories: port-based methods, load-based methods, and statistical methods; [0003] Port-based method: This method is the most basic traffic classification method. It is classified by matching the port number in the TCP / UDP header and IANA assigning some known port numbers. Obviously, ...

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): H04N21/234H04N21/44G06K9/62
CPCH04N21/23418H04N21/44008G06F18/241G06F18/214
Inventor 余翔湛刘立坤史建焘李精卫葛蒙蒙张晓慧苗钧重刘凡韦贤葵石开宇王久金冯帅赵跃宋赟祖郭明昊车佳臻
Owner HARBIN INST OF 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