The invention discloses a tTelecommunication fraud event detection method and system

Abstract

The invention provides a telecommunication fraud event detection method and a telecommunication fraud event detection system. The constructed telecommunication fraud event detection model is used forpredicting a fraud mode. The construction of the fraud event detection model comprises the following steps: establishing a dynamic communication graph reflecting different time series communication modes based on existing fraud behavior data; an abnormal sub-graph sequence with fraud behaviors is mined based on the dynamic communication graph, and the abnormal sub-graph sequence is composed of abnormal nodes, nodes associated with the abnormal nodes and edges; and training a multi-classification model based on the abnormal subgraph sequence, and obtaining a telecommunication fraud event detection model for detecting multiple fraud modes. By utilizing the detection method and the detection system, the fraud behavior can be quickly and accurately predicted.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a method and system for detecting telecommunications fraud events. Background technique [0002] At present, telecom fraud is generally based on gang crimes. It usually uses methods such as number tampering and camouflage to carry out routine and scripted precise fraud activities against specific individuals within a period of time. Multi-point dynamic communication fraud is even implemented across borders. The monitoring of international gateways cannot restore the changes in fraudulent communication patterns. Such fraudulent activities usually cause heavy losses and are extremely harmful to society. During this process, the communication relationship corresponding to the fraudulent group and the accompanying call patterns will also undergo dynamic evolution. Although traditional crime detection methods such as traditional template matching, statistical analysis of si...

AI Technical Summary

Problems solved by technology

Although traditional crime detection methods such as traditional template matching, statistical analysis of signaling, and simple international gateway detection can curb some traditional fraud incidents to a certain extent, the fraud methods and camouflage of fraud gangs are constantly evolving. Complex and diverse, and the traditional telephone fraud detection method for single-point fraud has the problems of slow data collection and difficulty in sorting out huge data volumes, which ultimately leads to low efficiency of traditional detection methods

[0003] However, in the existing technology, there is no ability to analyze and mine the fraudulent methods of gangs, complex fraud patterns and communication relationships, multi-point cross-border implementation, and dynamic evolution characteristics.

Images