A real-time prediction method of performance index, computer equipment and storage medium
A real-time prediction and computer technology, applied in calculation, error detection/correction, instruments, etc., can solve problems such as determining model parameters, achieve rapid training and improve pertinence
Active Publication Date: 2021-10-08
NETWORKBENCH SYST
View PDF9 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In addition, it is difficult to determine the appropriate model parameters for each indicator through manual modeling
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0024] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
[0025] In the following description, use of suffixes such as 'module', 'part' or 'unit' for denoting elements is only for facilitating description of the present invention and has no specific meaning by itself. Therefore, 'module', 'part' or 'unit' may be used in combination.
[0026] In applications in the field of performance monitoring, focus on time series forecasting, that is, corresponding modeling based on time series data, and predict data values at future time points based on the model and past data.
[0027] figure 1 A flow chart of an implementation of the performance index real-time prediction method provided in the embodiment of the present application, as shown in figure 1 As shown, the method includes step S102 to step S104.
[0028] Step S102, a step of model training and selection performed accor...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present application relates to a method for real-time prediction of performance indicators, computer equipment and storage media, wherein the method includes: a step of model training and selection according to a predetermined cycle; a step of performance indicator prediction; wherein the steps of model training and selection include : Obtain the time series data of the previous period of performance indicators; according to at least some of the model parameters obtained from the previous training of multiple time series forecasting models, use the above time series data to iteratively optimize the above multiple time series forecasting models; evaluate the results of this training The prediction accuracy of multiple time series prediction models; select the time series prediction model of the performance index according to the prediction accuracy of the above multiple time series prediction models; the step of performance index prediction includes: receiving the streaming time series data of the performance index , perform real-time forecasting of performance metrics using the selected time series forecasting model. Through this application, the prediction accuracy is improved.
Description
technical field [0001] The present application relates to the technical field of performance monitoring, in particular to a method for real-time prediction of performance indicators, computer equipment and storage media. Background technique [0002] In the application scenario of performance monitoring, the value of the performance index is collected according to the time interval to obtain the time series data of the performance index. Performance metrics predictions are used for anomaly detection. The performance of a predictive model depends in large part on the data it is used on. Usually the number of performance indicators is huge, and the prediction is very frequent, and in order to detect abnormalities in time, it is usually online real-time prediction. However, there are great differences among these indicators, and it is difficult to find one or several general models (and model parameters) that can be applied to all indicators. In addition, it is also difficul...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F11/30
CPCG06F11/3072G06F11/3093
Inventor 钟书毅
Owner NETWORKBENCH SYST