Cloud native index data prediction method and system based on time sequence pattern adaptation

A technology of time series and index data, applied in the cloud native field, can solve the problems of consuming a lot of manpower, time resources, inability to process, and poor accuracy

Pending Publication Date: 2021-07-30
EISOO SOFTWARE
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, in the field of observability, most machine learning algorithms only predict the indicator data of a specific pattern, and need to know the indicator pattern in advance and select the algorithm. In the case of the surge of services and indicators caused by cloud native, it is necessary to deal with mixed and effective For indicator data with various data characteristics, traditional monitoring requires a lot of manpower and time resources, and the accuracy is poor, or even impossible to process

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Cloud native index data prediction method and system based on time sequence pattern adaptation
  • Cloud native index data prediction method and system based on time sequence pattern adaptation
  • Cloud native index data prediction method and system based on time sequence pattern adaptation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0084] A cloud-native index data prediction method based on time series pattern adaptation, including:

[0085] 1) Collect the time series data of the indicators to be predicted in the cloud native system;

[0086] 2) Perform data characteristic detection on the time series data to obtain the time series pattern of the time series data;

[0087] 3) According to the time series model, according to the selection rules, select the prediction algorithm adapted to the time series data;

[0088] 4) Predict the time series data of the future time of the index to be predicted through the prediction algorithm selected in step 3).

[0089] Data characteristic detection includes stationarity detection, trend detection and periodicity detection, time series pattern includes stationary data pattern, trend data pattern, periodic data pattern, composite data pattern and random data pattern;

[0090] In the present embodiment, the partial data of the time series data of the indicators to be...

Embodiment 2

[0172] A cloud-native index data prediction system based on time series pattern adaptation, including an index data collection module, a data characteristic detection module, a prediction algorithm selection module, and an index data prediction module;

[0173] The indicator data collection module is used to collect the time series data of the indicators to be predicted in the cloud native system;

[0174] The data characteristic detection module is used to detect the data characteristics of the time series data, and obtain the time series pattern of the time series data;

[0175] A forecasting algorithm selection module, used to select a forecasting algorithm adapted to the time series data according to a selection rule according to the time series pattern;

[0176] The index data prediction module is used to predict the time series data of the index to be predicted according to the prediction algorithm selected by the prediction algorithm selection module.

[0177] The data...

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

No PUM Login to view more

Abstract

The invention relates to a cloud native index data prediction method and system based on time sequence pattern adaptation. The method comprises the following steps: 1) collecting time sequence data of to-be-predicted indexes of a cloud native system; 2) performing data characteristic detection on the time sequence data to obtain a time sequence mode of the time sequence data; 3) selecting a prediction algorithm matched with the time sequence data according to the time sequence mode and a selection rule; and 4) predicting the time sequence data of the to-be-predicted index through the prediction algorithm selected in the step 3). Compared with the prior art, the method has the advantages of high efficiency, high accuracy, labor saving and the like.

Description

technical field [0001] The present invention relates to the cloud-native field, in particular to a method and system for predicting cloud-native index data based on time series pattern adaptation. Background technique [0002] With the maturity of virtualization technology and the popularization of distributed frameworks, driven by container technology, sustainable delivery, and the concept of microservice development, it is an irreversible trend for applications to go to the cloud. In the cloud-native environment, the basic hardware is mostly abstracted and blurred, and the software running environment has undergone earth-shaking changes. The monitoring objects, time series indicators and their quantity have also changed, from the original host as the main body to the container. and services as the main body. Metrics are a basic type of signal that can be emitted by a service or the infrastructure it runs on, and are the primary way to represent system state and health ove...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q10/06G06F17/14
CPCG06F17/142G06Q10/04G06Q10/06393
Inventor 陈园
Owner EISOO SOFTWARE
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap