Data anomaly detection method, device, readable storage medium and electronic equipment

Abstract

The disclosure relates to a data anomaly detection method, device, readable storage medium and electronic equipment. The method includes: obtaining the current index data; obtaining the time series set corresponding to the current index data; for each time series in the time series set, judging whether there is a memory neuron for recording the time series; when it is determined that the memory neuron exists When it is determined that the memory neuron does not exist, assign a memory neuron to the time series to record the time series, and activate the assigned memory neuron; at least according to the activated memory The neuron determines whether the current indicator data is abnormal. Therefore, the anomaly monitoring system is more adaptable to different types of index data and index data with complex changes, and the larger the scale of the acquired index data, the stronger its learning ability and judgment ability, and the higher the accuracy of anomaly detection. higher.

Description

technical field [0001] The present disclosure relates to the field of anomaly detection, and in particular, to a data anomaly detection method, device, readable storage medium, and electronic equipment. Background technique [0002] Data anomaly detection technology plays an extremely important role in all walks of life, for example, discovering small changes in indicators such as a patient's heartbeat, blood pressure, and respiration, locating suspicious operating behaviors of key system administrators, and detecting abnormal stock price changes in the stock market. Detect the instability of key indicators such as the CPU, memory, and HTTP response time of the application system, etc. The realization of these functions is inseparable from fast and accurate data anomaly detection methods. [0003] However, with the rapid development of computer software technology, it becomes more and more difficult to realize the monitoring system, especially the abnormal monitoring system...

AI Technical Summary

Problems solved by technology

[0003] However, with the rapid development of computer software technology, it becomes more and more difficult to realize the monitoring system, especially the abnormal monitoring system.

The main reasons are as follows: (1) Due to the increasing scale of monitored applications, more and more indicators are included in the monitoring; (2) The complexity of the monitoring system is getting higher and higher, and the regularity of indicator changes (3) The traditional time series analysis model used for anomaly detection is becoming less and less adaptable to highly complex index changes, which not only leads to increased computational complexity, but also reduces the effectiveness of anomaly detection. also affected

Images