Time series data classification method and device, terminal equipment and storage medium

Abstract

The invention discloses a time series data classification method, and the method comprises the steps: obtaining a to-be-classified time series set which comprises a plurality of time series; performing multi-dimensional feature extraction on each time sequence in the time sequence set to obtain multi-dimensional time sequence features; and classifying the time sequences in the time sequence set according to the multi-dimensional time sequence characteristics. The invention further discloses a time series data classification device, terminal equipment and a storage medium. According to the method, multi-dimensional feature extraction is carried out on the time sequence, classification is carried out in combination with the multi-dimensional time sequence features of the time sequence, and the classification precision of the time sequence data can be effectively improved, so that the classification precision of the time sequence data can meet the prediction requirements of complex business scenes in the financial field.

Description

technical field [0001] The present invention relates to the technical field of financial technology data processing, in particular to a time series data classification method, device, terminal equipment and storage medium. Background technique [0002] Time series data classification aims to analyze standard time series data and classify time series according to the trend of historical series to assist in the prediction of future trends, thereby assisting anomaly detection and business decision-making. Most of the current time-series data comes from single scenarios such as network technology and hydrological forecasting. The time-series data of these scenarios have relatively simple rules and structures. Therefore, simple data classification can meet the forecasting needs. [0003] However, in banking and other financial fields, the business scenarios are more complex, and various business processes generate various types of time series. When predicting time series data, it...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to provide a time-series data classification method, device, terminal equipment and storage medium, aiming at solving the problem that the existing time-series data classification method has insufficient classification accuracy of time series and cannot meet the prediction needs of complex business scenarios question

Images