Telecommunication fraud library updating processing method and device

Abstract

The embodiment of the invention discloses a telecommunication fraud library updating processing method and device, and the method comprises the steps: enabling a received calling number to be matchedwith a number in a telecommunication fraud library, and intercepting the calling number at a core network side if the received calling number is matched with the number in the telecommunication fraudlibrary; if the calling number is not matched with the number in the telecommunication fraud library, matching the calling number with the number in the suspected telecommunication fraud library; andif the number in the suspected telecommunication fraud library is not matched, inputting the calling number into a neural network model, determining that the calling number is a fraud number accordingto an output result of the neural network model, and adding the calling number into the telecommunication fraud library. The received calling number is matched with a telecommunication fraud libraryand a suspected telecommunication fraud library; and when the matching is not successful, the neural network model is input for verification, and when the fraud number is confirmed according to the output result, the calling number is added to the telecommunication fraud library, so that the accuracy of telecommunication fraud identification is effectively improved, and the real-time prevention and control of telecommunication fraud behaviors are realized.

Description

technical field [0001] The embodiment of the present invention relates to the technical field of communications, and in particular to a method and device for updating a telecommunications fraud database. Background technique [0002] In recent years, telecommunications fraud has been very rampant, seriously threatening the safety of people's lives and property, seriously affecting social stability, and has become a cancer that hinders social development. Manpower, equipment, and technology are constantly being updated. They quickly change numbers and methods, which brings great difficulty to the prevention of telecommunications fraud. These fraudulent techniques are not only deceptive, but also the number of people being deceived is increasing, in order to cope with the continuous "upgrading" of fraudulent methods. [0003] The existing traditional method of telecom fraud identification mainly adopts the fraud database method based on the blacklist, but there is no effectiv...

AI Technical Summary

Problems solved by technology

[0005] The update speed of the existing fraud database is far behind the replacement speed of the fraudulent numbers, which greatly reduces the combat effectiveness of the existing fraud database against telecom fraud activities. Therefore, the timeliness of telecom fraud identification is very important to prevent telecom fraud. There are problems of high false alarm rate and low accuracy in the identification method of telecommunications fraud. The rapid update of fraudulent technology and means leads to the failure of the original identification method. The existing technology has been unable to accurately identify the changing telecommunications fraud activities.

Images