Risk detection method and device, electronic equipment and readable storage medium

Abstract

The invention relates to the technical field of computers, in particular to a risk detection method and device, electronic equipment and a readable storage medium, and the method comprises the steps: storing obtained target transaction data of a target user in a Kafka message system; the method comprises the following steps: reading target transaction data in a Kafka message system based on an Apache Storm program; analyzing and processing the target transaction data and outputting an analysis result based on a program of an Apache Storm and Esper complex event processing component; and if the analysis result accords with a preset risk alarm rule, starting risk alarm. According to the risk detection scheme provided by the invention, high availability of 7 * 24 hours is achieved, online horizontal capacity expansion is supported, an efficient rule editing function is provided for business personnel, historical transaction regression verification and query are supported, and 10 billion-level data volume is supported.

Description

technical field [0001] The present application relates to the technical field of computer data processing, and in particular to a risk detection method, device, electronic equipment and readable storage medium. Background technique [0002] Online payment is favored by consumers due to its convenience and close correlation with daily life, and has become a mainstream transaction payment method. However, online payments also lead to more risks of transaction fraud. At present, the industry mainly adopts a rule-based method to deal with the transaction fraud risk of online payment. For example, the traditional transaction risk detection system based on the relational database mainly uses the SQL query statement in the database table, which is the risk control rule. The number of SQL to be queried in the database = risk control The number of rules * the current instantaneous transaction volume, the amount of daily risk detection data is small, so there is no problem, but when ...

AI Technical Summary

Problems solved by technology

However, online payments also lead to a greater risk of transaction fraud

At present, the industry mainly adopts a rule-based method to deal with the transaction fraud risk of online payment. For example, the traditional transaction risk detection system based on the relational database mainly uses the SQL query statement in the database table, which is the risk control rule. The number of SQL to be queried in the database = risk control The number of rules * the current instantaneous transaction volume, the amount of daily risk detection data is small, so there is no problem, but when the instantaneous transaction volume of the customer group surges (such as a huge number of customers concentrated on consumption transactions after 0:00 on Double Eleven), it is necessary to query the database After the number of SQL is enlarged in equal proportions (that is, read amplification), the performance of the database will drop sharply, resulting in a sharp drop in system processing capacity, which will eventually lead to delays in risk transaction alarms, untimely corresponding risk control disposals, and losses to customers and financial companies

Images