Payment abnormity detection method and device, storage medium and electronic equipment

Abstract

The invention relates to a payment abnormity detection method and device, a storage medium and electronic equipment, and aims to improve the accuracy of payment abnormity detection. The method comprises the following steps: respectively acquiring characteristic data of a user account and a payment mode bound with the user account in a payment process, wherein the characteristic data comprises behavior characteristic data, consumption characteristic data and position characteristic data; according to the feature data, calculating the similarity between a node representing the user account and anode representing the payment mode in a preset topological structure; updating the label values of the nodes representing the user account and the nodes representing the payment mode in the preset topological structure through a label propagation algorithm according to the similarity among the nodes; and determining whether the user account is paid abnormally or not according to the updated labelvalues of the nodes representing the user account and the nodes representing the payment mode.

Description

technical field [0001] The present disclosure relates to the field of information technology, and in particular, to a payment anomaly detection method, device, storage medium and electronic equipment. Background technique [0002] With the rapid development of the Internet, it not only facilitates daily life, but also provides opportunities for criminals. Taking Internet payment as an example, due to its characteristics of large transaction volume and imperfect monitoring methods, it is easy for criminals to hide behind payment operations and complete illegal and criminal activities such as swiping orders and cashing out. [0003] In related technologies, the detection of abnormal payment is mainly based on the calculation of the abnormal index based on the collected payment data of the user account. If the abnormal index is greater than a preset threshold, it is determined that the payment is abnormal. However, since the preset threshold depends on manual setting, if the p...

AI Technical Summary

Problems solved by technology

However, since the preset threshold depends on manual setting, if the preset threshold is not set accurately, it will directly lead to inaccurate judgment results of abnormal payment

Moreover, for each user, the preset threshold is the same, so it is impossible to perform personalized detection for different users, resulting in the determination of normal payment behaviors that are only different from the group average as payment anomalies, which affects the accuracy of payment anomaly detection

Images