Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Time series processing method and device

A time series and processing method technology, applied in the field of data processing, can solve the problems of non-stationary processing, unsuitable non-stationary data, inaccurate modeling, etc., and achieve the effect of accurate results

Active Publication Date: 2015-07-22
SHANXI CHINA MOBILE COMM CORP
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Most of the existing time series data forecasting methods only consider the single time series itself, the factors considered are not accurate enough (the influence of time series with correlation with it is not considered), and non-stationarity is not dealt with (non-stationary data does not Suitable for regression analysis, it will cause inaccurate modeling)
Therefore, if they are predicted according to existing methods, the prediction accuracy will not be high, which will affect the business judgment of decision makers

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
  • Time series processing method and device
  • Time series processing method and device
  • Time series processing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] Such as figure 1 As shown, this embodiment provides a time series processing method, the method comprising:

[0059] Step S110: analyzing the first time series to obtain at least one second time series related to the first time series;

[0060] Step S120: performing multiple regression processing on the second time series to obtain a first function with the second time series as the dependent variable and the fitting sequence as the independent variable;

[0061] Step S130: Calculate a fitting sequence corresponding to the first time series according to the first function;

[0062] Step S140: Check the difference between the fitted sequence and the first time series, if the difference is not greater than the threshold, then enter step S150, if the difference is greater than the threshold, return to step S110:

[0063] Step S150: Calculate the residual sequence of the fitting sequence and the first time series;

[0064] Step S160: performing a smoothing process on the...

example 1

[0091] Step 1.1: First, process the collected or received values ​​in chronological order to form the first time series y t , analyze y t , initially determined with y t The other n time series with correlation, denoted as

[0092] Step 2.1: Right Perform multiple regression to obtain the first function where y t ' is the fitting sequence; the is the i-th second time series at time t; the wi for the said influence weight. Estimating the parameters by the least square method requires necessary inspection and evaluation to determine whether the first function can be used to estimate the first time series. In this example, the F test method is used, and the critical value Fa is given. If F>Fa, it means that the dependent variable relationship in the first function has a significant impact on the independent variable, and the regression effect is obvious. Go to step 3.1; otherwise, the regression effect is not obvious, then Go to step 1.1.

[0093] Step 3.1: Due t...

example 2

[0102] This example is applied to the processing of time series in the business analysis system. This example takes a company's prediction of the key indicator of "China Unicom's daily new users" as an example to illustrate the correlation-oriented non-stationary time proposed by the present invention Actual forecasting performance of sequence forecasting methods.

[0103] Step 1. Observe the time series y of "the number of new users of the first service provider every day" t , considering that the first service provider, the second service provider, and the third service provider are in a competitive relationship, the time series formed by the number of daily new users of the second service provider can be initially defined as The time series formed by the number of daily new users of the third service provider is Will with as with y t A second time series with a correlation.

[0104] Step 2, right with Perform multiple regression modeling to get Carry out para...

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 discloses a time series processing method and device. The time series processing method comprises the steps that a first time series is analyzed, and at least one second time series relevant to the first time series is obtained; multiple regression processing is conducted on the second time series, and a first function with the second time series as a dependent variable and a fitting series as an independent variable is obtained; according to the first function, the fitting series corresponding to the first time series is calculated; the difference between the fitting series and the first time series is detected; when the difference between the fitting series and the first time series is not larger than a threshold, a residual error series between the fitting series and the first time series is worked out; stationary processing is conducted on the residual error series, a stationary series corresponding to the residual error series is obtained, autoregressive moving average processing is conducted on the stationary series, and a second function for the relation between a front element and a rear element in the stationary series is obtained; according to the first function and the second function, a prediction result of a prediction time is obtained.

Description

technical field [0001] The invention relates to sequence processing technology in the field of data processing, in particular to a time sequence processing method and device. Background technique [0002] A time series is a sequence formed by arranging the values ​​of a certain statistical indicator in chronological order. The forecasting method based on time series is to compile and analyze time series, and carry out analogy or extension according to the development process, direction and trend reflected in the time series, so as to predict the level that may be reached in the next period of time or in the next few years. In practical applications, most time series have other time series that are correlated with them, and present non-stationary characteristics. By predicting such time series, some existing trends can be discovered in time, and then potential trends can be predicted in advance. Take certain measures to reduce possible losses; and through forecasting, it can...

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
IPC IPC(8): G06F17/30
Inventor 秦晓飞
Owner SHANXI CHINA MOBILE COMM CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com