Unlock instant, AI-driven research and patent intelligence for your innovation.

A method and system for intercepting fraudulent calls in real time based on clustering algorithm

A fraudulent call and clustering algorithm technology, applied in the field of network communication, can solve the problems of automatic and accurate identification and real-time interception of fraudulent numbers that are not involved, and achieve the effect of high identification accuracy and rich information

Active Publication Date: 2017-08-25
EB INFORMATION TECH
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This technical solution does not involve the automatic and accurate identification and real-time interception of fraudulent numbers across the entire network

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
  • A method and system for intercepting fraudulent calls in real time based on clustering algorithm
  • A method and system for intercepting fraudulent calls in real time based on clustering algorithm
  • A method and system for intercepting fraudulent calls in real time based on clustering algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033]In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0034] According to the research, it is found that fraudulent calls and suspected fraudulent calls generally have obvious characteristic differences. High-frequency calls, relatively scattered called users, high overlap of call circles, and high dispersion of call time. Non-fraud calls have low-frequency calls and concentrated time, low overlap of call circles, and less calling behavior. There is basically no call behavior characteristic when busy. Therefore, the present invention can adopt clustering algorithm, carry out characteristic classification to calling number according to multiple feature index values ​​of all calling numbers in the bill record, divide the calling number with same or similar feature into a cluster, That is to say, all users are divided i...

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

A method and system for intercepting fraudulent calls in real time based on a clustering algorithm. The method includes: calculating several characteristic index values ​​of all calling numbers within a certain period of time according to the bill records, and then using a clustering algorithm to classify all calling numbers The numbers are divided into three clusters, so that the calling numbers in each cluster have the same or similar feature index values; the feature index values ​​of the confirmed fraud numbers are compared with the feature index values ​​of the calling numbers in the three clusters. Matching, if the value range formed by the feature index values ​​is closer, it means that the matching similarity is higher. Finally, the cluster with the highest matching similarity is set as a fraudulent call cluster, and the cluster with the second matching similarity is set as a suspected fraudulent call cluster. ; Update all calling numbers in the fraudulent number cluster and the suspected fraudulent number cluster to the forensic number table and the intercepted number table respectively. The invention belongs to the technical field of network communication, and can realize automatic and accurate identification and real-time interception of fraudulent numbers within the scope of the entire network.

Description

technical field [0001] The invention relates to a method and system for intercepting fraudulent calls in real time based on a clustering algorithm, belonging to the technical field of network communication. Background technique [0002] With the popularization of mobile phones, phone scams emerge in endlessly. Although the relevant government departments have issued reminders to the society and various news media have reported frequently, however, a large number of users are still being cheated every day, and the economic losses are increasing year by year. [0003] At present, the blacklist interception method is mainly adopted for fraudulent calls, that is, the confirmed fraudulent numbers are written into the blacklist. For example: patent application CN 201310004829.4 (application name: a spam call interception system based on call pattern recognition and its working method, applicant: Shanghai Xinfang Intelligent System Co., Ltd., application date: 2013‐01‐07) Based o...

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): H04M3/436
Inventor 廖建新王彦青林大庆林建洪张锦然单瑞超马宪
Owner EB INFORMATION TECH