Personal identification information identification system and method in high-performance ip network

A technology for identifying information and identification methods, which is applied in the fields of network information and security and network personal privacy protection, can solve the problems of large computing costs, and achieve the effects of large coverage area, strong operability, and good scalability

Active Publication Date: 2021-02-05
BEIJING INSTITUTE OF TECHNOLOGYGY +1
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to improve the accuracy of personal identification information identification; it does not need to obtain higher authority of the system or install additional software and hardware, improve compatibility and scalability; comprehensively collect various types of personal identification information, and propose an efficient and feasible algorithm, To overcome the problem of high computational overhead of massive data in high-performance networks, a system and method for identifying personal identification information in high-performance IP networks are proposed

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
  • Personal identification information identification system and method in high-performance ip network
  • Personal identification information identification system and method in high-performance ip network
  • Personal identification information identification system and method in high-performance ip network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068]This embodiment describes in detail the overall system structure diagram of a personal identification information identification system in an operator network of the present invention. Fromfigure 1 It can be seen that the network traffic is first input to the system in the PCAP format; secondly, the data packet is associated with the user (object) in the authentication system using the timestamp and IP address; again, the system uses regular expressions to extract the network traffic in the feature extraction process The HOST field and GET field of the HTTP data packet are extracted, and the characteristics are extracted according to the method in step 2 and then stored as a record (see Example 2 for details); then, the system statistics (statistics) the same records and aggregates, the same records The frequency of occurrence is FREQUENCY; finally a five-dimensional field data set {USER,DOMAIN,KEY,VALUE, FREQUENCY} is obtained. The system here uses the MAC address to represen...

Embodiment 2

[0074]This embodiment describes in detail the feature extraction process of a personal identification information recognition system in an operator network of the present invention. The feature extraction location map represents an HTTP data packet header field in actual network traffic. According to the prompt in step 2, the method extracts the string "mcgi.v.qq.com" in the HOST field and writes it into the DOMAIN field of the data set, and extracts 13 strings such as "app_id", "imsi" and "imei" to write data KEY field, and write 13 strings such as "248", "460023918121329" and "868129022933673" into the VALUE field corresponding to the data set, and finally write 13 records in the data set. See the feature extraction result table below for details.

[0075]Feature extraction location chart

[0076]

[0077]Feature extraction result table

[0078] DOMAIN KEY VALUE mcgi.v.qq.com cmd 51 mcgi.v.qq.com app_version_name 6.5.3 mcgi.v.qq.com app_version_build 0 mcgi.v.qq.com so_name p2p mcgi.v.qq...

Embodiment 3

[0080]This embodiment describes in detail the process of establishing a user behavior tree in the calculation process of a personal identification information recognition system in an operator network of the present invention. Fromfigure 2 It can be seen that according to the behavior of users accessing network resources, the five-dimensional data obtained in the previous process is used to construct a user behavior tree. The five fields of the five-dimensional data can more accurately represent the user's behavior in accessing network resources. When the user or object USER accesses the network resource DOMAIN, the VALUE of FREQUENCY times is transmitted at the location KEY. According to user access behavior, the method aggregates users who access the same network resources to construct a user behavior tree. The user behavior tree is fixed to 4 levels, with DOMAIN-KEY as the root of the user behavior tree; the second level is the USER level, which means USER data with the same DOMA...

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 relates to a personal identification information identification system and method in a high-performance IP network, and belongs to the technical field of network information security and network personal privacy protection. The network personal identification information identification system includes a feature extraction module, a data filtering and shaping module, an algorithm execution module and an optimization module; it does not require manual intervention; the network personal identification information identification method includes step 1: the traffic collected by the IP network is in the form of PCAP Input to the network personal identification information identification system; Step 2: Extract the network feature field to obtain a five-dimensional data group; Step 3: Filter and reshape the five-dimensional data group; Step 4: Establish a user behavior tree model, calculate the function VF and UVF, After two detections, output the list of PII-DK and PII-VALUE; step 5: the optimization module performs verification and diffusion; step 6: output the list of PII-DK. The system and method proposed by the invention have good compatibility and expansibility.

Description

Technical field[0001]The invention relates to a system and method for identifying personal identification information in a high-performance IP network, and belongs to the technical fields of network information and security and network personal privacy protection.Background technique[0002]First of all, the development of the mobile Internet is gradually changing people's lifestyles. People can get a variety of convenient and fast network services through a wide variety of applications on the Internet anytime, anywhere. At the same time, in order to provide these network services with high quality, application service providers (ASPs) usually directly or indirectly collect various types of user data to the cloud through applications. In particular, using various sensors such as GPS, cameras, and accelerators embedded in mobile terminals, mobile applications (APPs) will generate more types of user personal identification information (PII). The use of personal identification informatio...

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 Patents(China)
IPC IPC(8): H04L12/24H04L12/26H04L29/06
CPCH04L41/14H04L43/026H04L63/0236
Inventor 刘翼嵩天
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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