Fraud number identification method and device, computer equipment and storage medium

Abstract

The invention is suitable for the technical field of computers, and provides a fraud number identification method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining communication feature information of a to-be-identified number; processing the communication feature information according to a preset fraud number recognition model to generate a fraud number recognition result, wherein the preset fraud number recognition model is generated by training in advance based on a semi-supervised learning self-training classification algorithm. According to the fraud number identification method provided by the invention, the fraud number identification model is trained and generated by using the self-training classification algorithm which does not need to depend on a large amount of labeled sample data in the training process, so an optimal identification model can be obtained through training, and the method has good adaptability in the field of fraud phone identification with insufficient sample data; the fraudulent number recognition result obtained by processing the communication feature information by using the fraudulent number recognition model is high in accuracy.

Description

technical field [0001] The invention belongs to the technical field of computers, and in particular relates to a fraud number identification method, device, computer equipment and storage medium. Background technique [0002] In the business scenario of an operator, identification of fraudulent calls is a relatively important part. Existing fraud call identification solutions commonly used in the industry include rule engines and machine learning methods. Among them, machine learning methods have been widely promoted and applied in anti-fraud scenarios due to their automation and intelligence. From a technical point of view, the identification of fraudulent calls can be abstracted as a classification problem in supervised learning. In practical applications, the difficulty in obtaining positive and negative sample labels in supervised learning is an urgent problem to be solved. [0003] Supervised learning technology requires operators to have enough historical labels to ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the embodiments of the present invention is to provide a method for identifying fraudulent numbers, which aims to solve the existing fraudulent call identification technology that relies on labeling of known fraudulent phone labels, thereby affecting the recognition accuracy of fraudulent call identification, Identify technical issues of efficiency and scope

Images