Gang fraud phone recognition method based on suspicion measurement

A technology of fraudulent calls and identification methods, which is applied in the field of computer information, can solve the problems of malicious labeling, weak recognition effect of fraudulent phone numbers, manual labeling and missing labels, etc., achieves small time complexity and space complexity, convenient monitoring and deployment, Strong real-time effect

Active Publication Date: 2019-09-13
INST OF INFORMATION ENG CAS
View PDF9 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the fraudulent method is highly deceptive, users are less likely to flag suspected fraudulent calls, resulting in poorer recognition results
[0007] 2. There is a hysteresis: due to the problems of missing labels, false labels, malicious labels, etc. in manual labeling, it often takes a certain amount of labeling results to take effect, and the identification effect on new fraudulent phone numbers is weak
[0008] 3. The identification effect of gang fraud is weak: due to the characteristics of high deception and strong concealment, gang fraud is the main form of telecommunications fraud at present
The current manual marking is mainly aimed at marking a single fraudulent call. For fraudulent gangs, if the fraud is successful, the defrauded phone number is usually not marked; fraudulent numbers, but the high-level fraudulent numbers have not been exposed, so it is impossible to identify and characterize the fraud gang as a whole

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
  • Gang fraud phone recognition method based on suspicion measurement
  • Gang fraud phone recognition method based on suspicion measurement
  • Gang fraud phone recognition method based on suspicion measurement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In order to make the above-mentioned features and advantages of the present invention more comprehensible, the following specific embodiments are described in detail in conjunction with the accompanying drawings.

[0032] This embodiment proposes a method for identifying fraudulent gang calls based on suspiciousness metrics, which introduces the suspiciousness metrics and suspiciousness scores of phone numbers, and identifies the user's level of gang fraud based on the number of suspicious calls within a time window.

[0033] The basic realistic assumption of this method is: in order to carry out fraud, fraudulent phone numbers will extensively search for potential victims, so that most of the communication relationships of fraudulent phone numbers are one-way outgoing calls, and the communication relationship is unstable; the phone number has The more unstable communication relationships there are, the higher the suspiciousness; scam gangs will use different calls and d...

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 gang fraud phone recognition method based on suspicion measurement, which adopts an unsupervised mode, utilizes call record information between phone numbers to define suspicion measurement for each phone number, and adopts a risk level quantification mode to recognize a gang fraud phone. According to the method, a subjective marking result of a user does not need to be introduced, defects caused by subjective judgment can be avoided, model training and online use can be completed within a short time, a simple and practical recognition method is provided for the user to suffer from group fraud, and the problem caused by lagging is effectively relieved.

Description

technical field [0001] The invention belongs to the field of computer information technology, and in particular relates to a method for identifying gang fraudulent calls based on suspiciousness measurement. Background technique [0002] With the rapid development of telecommunications technology, telecommunications fraud is showing a high incidence trend, and it is increasing year by year. For example, in 2017, the number of first-instance telecommunications and network fraud cases nationwide increased by 70.34% compared with 2016. Among the many forms of telecommunications fraud, gang fraud has developed rapidly in recent years due to its high deceptiveness and strong concealment, which seriously threatens people's property safety. In gang fraud calls, criminal gangs pretend to be different identities to lure and defraud the victim, making the victim easy to be deceived and suffer property losses. Therefore, the rapid and accurate identification of (gang) fraudulent calls ...

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): H04M3/22H04W12/12H04W12/128
CPCH04M3/2281H04W12/12
Inventor 周川高扬胡玥谭建龙郭莉
Owner INST OF INFORMATION ENG CAS
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