Time sequence anomaly detection method and device, electronic equipment and storage medium

Abstract

The invention provides a time sequence anomaly detection method and device, electronic equipment and a storage medium. The time sequence anomaly detection method comprises the steps: carrying out themulti-window sampling of a current time sequence, and generating a corresponding current sequence matrix; encoding the current sequence matrix to obtain corresponding current encoding information; inputting the current coded information into attention processing to obtain the current coded information carrying the attention information; performing sequence reconstruction on the current coded information carrying the attention information to obtain prediction information of a next time sequence; obtaining a residual error sequence according to the actual measurement information and the prediction information of the next time sequence; and traversing each residual value in the residual sequence, and when the residual value is out of the reasonable interval, determining that the measured value in the next time sequence corresponding to the residual value is abnormal data. According to the time sequence anomaly detection method, the prediction accuracy of the regression model can be improved, and the problem of strong hypothesis of data distribution in an anomaly detection strategy is avoided.

Description

technical field [0001] The invention relates to the field of data detection, in particular to a time series anomaly detection method and device, electronic equipment, and a storage medium. Background technique [0002] Unmanned vehicles are equipped with many sensor devices and radar devices. The driving data collected by them has the characteristics of fast, real-time and data flow mode, and is usually multi-dimensional time series data in a non-stationary state without any supervision information. [0003] Traditional anomaly detection methods include statistical and probability models, linear models, models based on similarity measurement, etc. The starting point of these methods can be summarized as similarity estimation. Estimation methods can be divided by density, angle, distance, hyperplane, etc. . [0004] Due to the complex types of anomalies in the sensor data of unmanned vehicles, relying on traditional anomaly detection methods cannot detect anomalies effective...

AI Technical Summary

Problems solved by technology

Considering that the sensor data of unmanned vehicles are mostly data in a non-stationary environment, for the regression modeling part, the large changes in the data mode lead to insufficient model fitting ability, frequent data fluctuations are difficult to predict, and the model is not sensitive enough to produce abnormal hysteresis. Severe constraints on downstream detection strategies

For the residual analysis part, there is usually no out-of-the-box solution, and the data is usually required to obey a certain distribution. It is difficult for existing methods to adapt to unmanned vehicle sensor data well.

Images