Data processing method, terminal and computer readable storage medium

Abstract

The invention provides a data processing method, a terminal and a computer readable storage medium. The data processing method comprises the following steps of acquiring sampled data; generating indicator data based on normal distribution according to a mean value and a standard deviation of the sampled data; acquiring to-be-tested data; determining whether the to-be-tested data falls into a dynamic standard range of the indicator data; and if the to-be-tested data is beyond the dynamic standard range of the indicator data, determining that the to-be-tested data is abnormal data, warning the abnormal data, recording to-be-tested data in a previous preset time domain with a time point at when the abnormal data is generated as a reference time point, and using the to-be-tested data as warning prediction data. Through adoption of the method, laws of different types of data are learned, so as to determine a normal range and an abnormal range of data, so that operation and maintenance personnel can work more efficiently, and to-be-tested equipment is less likely to fail.

Description

technical field [0001] The present invention relates to the field of equipment operation and maintenance, in particular to a data processing method, a terminal and a computer-readable storage medium. Background technique [0002] With the development of computer technology and the Internet, various data are processed and applied, and the learning ability of machines is gradually improving. A large amount of data is collected and processed. [0003] In order to cope with the greatly increased amount of data that needs to be processed, the number of servers and virtual servers has also increased rapidly, and the cooperation among a large number of servers has become more complicated, resulting in a large amount of data accumulation. As a result, two main requirements arise. One is how to manage the continuously generated data, conduct daily system inspections, establish relevant empirical models, form insights, and establish models to pre-judge problems and prevent them from...

AI Technical Summary

Problems solved by technology

The above-mentioned traditional algorithms each have disadvantages in practical applications, such as the fixed threshold comparison method. Considering the aging and changes of equipment, the set fixed threshold cannot be used as a standard value for long-term comparison, and the false detection rate and false detection rate are high. The dynamic baseline method and the Gaussian distribution method are difficult to apply to different recognition environments and recognition modes, and are easily affected by dirty data in data with a low signal-to-noise ratio, and the error is also large

Images