Credit threshold training method, IP address detection method and related devices

A technology of IP addresses and training methods, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as false interception and bypassing management and control.

Active Publication Date: 2020-11-27
GUANGZHOU BAIGUOYUAN INFORMATION TECH CO LTD
View PDF8 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] The embodiment of the present invention proposes a credit threshold training, IP address detection method and related devices to solve the problem of single thresholds such as passing frequency and verification rate affecting IP addresses. Monitor the behavior of the user, which is prone to misinterception and circumvention of control issues

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
  • Credit threshold training method, IP address detection method and related devices
  • Credit threshold training method, IP address detection method and related devices
  • Credit threshold training method, IP address detection method and related devices

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0070] figure 1 This is a flowchart of a credit threshold training method provided in Embodiment 1 of the present invention. This embodiment can be applied to obtain the degree of influence of different features on anomaly detection through historical data learning, so as to construct an effective credit scoring mechanism. This method may be performed by a credit threshold training device, which may be implemented in software and / or hardware, and may be configured in a computer device, such as a server, workstation, personal computer (PC), etc., Specifically include the following steps:

[0071] Step 101 , collect statistics on various service characteristics of service operations triggered based on IP address history.

[0072] In this embodiment, the client (client) historically requests the server (server) for services such as registration, login, password recall, payment, etc., thereby triggering corresponding business operations, such as sending a short message containing...

Embodiment 2

[0176] figure 2 A flowchart of a method for detecting an IP address provided in Embodiment 2 of the present invention. This embodiment can be adapted to detect the legitimacy of the IP address through the credit score of the IP address, and the method can be performed by an IP address detection device, The IP address detection device can be implemented by software and / or hardware, and can be configured in a computer device, such as a server, a workstation, a personal computer (PC), etc., and specifically includes the following steps:

[0177] Step 201 , collect statistics on various service characteristics of service operations triggered in real time based on the IP address.

[0178] In this embodiment, as image 3 As shown, the client (client) 311 can call the business operation interface 321 in real time, and request services such as registration, login, password recall, payment, etc. Send a text message containing a verification code, an email containing a verification l...

Embodiment 3

[0214] Figure 4 The structural block diagram of a credit threshold training device provided in Embodiment 3 of the present invention may specifically include the following modules:

[0215] The historical service feature statistics module 401 is used to count various service features for the service operations triggered based on the history of the IP address;

[0216] a correlation coefficient calculation module 402, configured to calculate at least two correlation coefficients for each of the service features, where the correlation coefficients are used to represent the correlation between the service features and legitimacy;

[0217] A credit value calculation module 403, configured to generate, for the IP address, a credit value representing legitimacy according to the correlation coefficient corresponding to the service feature;

[0218] An evaluation index generation module 404, configured to generate an evaluation index for the IP address, and the evaluation index is u...

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

An embodiment of the invention provides a credit threshold training method and device as well as an IP address detection method and device. The credit threshold training method comprises the followingsteps of: counting various service characteristics for service operation triggered based on IP address history; calculating at least two correlation coefficients for each service feature in a gradingmanner, wherein the correlation coefficient is used for representing the correlation between the service features and the legality; for an ip address, generating a credit value representing legalityaccording to the correlation coefficient corresponding to the service feature; generating an evaluation index for the IP address, wherein the evaluation index is used for evaluating the legality of predicting the IP address by using the service characteristics; and if the evaluation index of the IP address conforms to the target condition, determining a credit value corresponding to the evaluationindex as the credit threshold value. According to the credit threshold training method and the device as well as the IP address detection method and the device, multi-dimensional comprehensive judgment is realized, a threshold value for single dimension is avoided, the risk of mistaken interception caused by fault in single dimension can be reduced, and the risk that an illegal user bypasses thesingle-dimensional threshold value to bypass management and control is also reduced, namely, the risk of omission is reduced.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of operation monitoring, and in particular, to a method for training a credit threshold, a method for detecting an IP address, and a related device. Background technique [0002] When users register, log in, etc., the website usually sends a verification code through text messages, emails, etc., and the user enters the verification code to achieve registration, login and other purposes. [0003] SMS, email and other information carrying verification codes for authentication have been widely used because of their simple operation, high security, and strong timeliness. However, due to its convenient access and less restrictions, it is easy to be used by criminals to bombard information, especially malicious requests for short messages will generate a lot of costs and cause a lot of losses to enterprises or individuals. [0004] Therefore, the daily operation of the website will monitor t...

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): H04L29/06G06K9/62G06N3/04G06N3/08G06N20/00
CPCH04L63/1425H04L63/1416H04L63/1441G06N3/08G06N20/00G06N3/045G06F18/24G06F18/214H04L63/1466
Inventor 王相钟清华
Owner GUANGZHOU BAIGUOYUAN INFORMATION TECH CO LTD
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