Abnormality detection method and device

Abstract

The invention discloses an anomaly detection method and device, and the method comprises the steps: obtaining the business data of a user in a current business period, classifying the business data for each pre-trained anomaly detection model according to a data interval corresponding to each node in the anomaly detection model, and determining a node corresponding to the data interval in which the service data falls as a target node; determining the position information of the target node in the tree structure corresponding to the anomaly detection model, and taking the position information as the position information corresponding to the business data in the anomaly detection model; and finally, performing anomaly detection on the business data according to the corresponding position information of the business data in each anomaly detection model. According to the method, anomaly detection can be carried out on the service data in real time, whether the service data is abnormal or not can be quickly determined, the speed of anomaly detection of the service data of the user in the current service period is increased, and the service processing efficiency is improved.

Description

technical field [0001] This description relates to the field of computer technology, and in particular to a method and device for anomaly detection. Background technique [0002] With the rapid development of Internet technology and the growth of Internet business, the amount of business data has increased greatly, so more and more abnormal data are generated. [0003] At present, for the abnormal data generated, the system usually adopts methods such as manual discovery and regular detection of historical data. In the case of high real-time requirements for processing results, it often leads to problems such as a long time for abnormal data discovery, and in the case of failure to find abnormal data in time, it may cause damage to the interests of users, and the business of users Handling is inconvenient. [0004] Therefore, how to detect abnormal data in real time is an urgent problem to be solved. Contents of the invention [0005] This specification provides a metho...

AI Technical Summary

Problems solved by technology

In the case of high real-time requirements for processing results, it often leads to problems such as a long time for abnormal data discovery, and in the case of failure to find abnormal data in time, it may cause damage to the interests of users, and the business of users Inconvenience to deal with

Images