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

Time series similarity calculation method and system based on deep learning, and medium

A time series and deep learning technology, applied in computing, computer components, instruments, etc.

Active Publication Date: 2020-02-07
SUN YAT SEN UNIV
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional similarity calculation methods have their own disadvantages. If there is a similarity calculation method that is more in line with the characteristics of the current time series, it will naturally greatly improve the accuracy of sequence data classification and prediction

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 similarity calculation method and system based on deep learning, and medium
  • Time series similarity calculation method and system based on deep learning, and medium
  • Time series similarity calculation method and system based on deep learning, and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] The following will take the closing price data of daily stocks as an example of time series data to further describe in detail the calculation method, system and medium of time series similarity based on deep learning of the present invention.

[0043] Such as figure 1 As shown, the implementation steps of the calculation method of the time series similarity based on deep learning in this embodiment include:

[0044] 1) Obtain time series data of two equal time periods;

[0045] 2) Input the time series data of two equal time periods into the pre-trained neural network model based on deep learning, and obtain the similarity between the time series data of two equal time periods.

[0046] Step 1) of this embodiment specifically refers to acquiring stock closing price data with a granularity of 5 seconds per day.

[0047] Such as figure 2 As shown, before step 2) of the present embodiment, the step of training the neural network model based on deep learning is also in...

Embodiment 2

[0155] This embodiment is a further application of Embodiment 1, specifically for implementing noise-based mechanical fault state diagnosis of power system transformers. Step 1) also includes the step of establishing a sample database, which records a variety of time series data samples (noise) and their corresponding fault status information; by repeatedly executing step 1) and step 2) until the completion of the The time series data of diagnostic noise and the similarity calculation of all time series data samples in the sample database are calculated, and then the fault status information of the data to be diagnosed is determined according to the time series data sample with the highest similarity.

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 sequence similarity calculation method and system based on deep learning, and a medium. The time sequence similarity calculation method based on deep learning comprisesthe implementation steps of 1) obtaining time sequence data of two equal-length time periods; and 2) inputting the time series data of the two equal-length time periods into a pre-trained neural network model based on deep learning to obtain the similarity between the time series data of the two equal-length time periods. According to the invention, the advantages of various traditional measurement methods are integrated; the effect is better than that of each traditional measurement method in the aspect of time sequence similarity measurement; according to different requirements and differentdata sets, the same method can be used to learn a data similarity measurement method suitable for different fields, and for different problems, a similarity calculation method does not need to consider inherent characteristics of data.

Description

technical field [0001] The invention relates to deep learning prediction time series similarity detection technology, in particular to a calculation method, system and medium for time series similarity based on deep learning. Background technique [0002] With the continuous development and progress of science and technology, big data technology has penetrated into people's life and work, and time series is a form of recording data: a series of observations obtained in chronological order. As humans leap into the era of big data, the amount of time series data is also increasing day by day, which exists in all aspects of social life, such as financial income, meteorological research, network security, etc. Time series can be used to analyze historical data, predict possible data for a period of time in the future, and analyze possible trends. [0003] In the process of time series data mining, it is necessary to calculate the similarity between input samples, so as to bette...

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): G06K9/62G06N3/04G06Q40/04
CPCG06Q40/04G06N3/045G06F18/22
Inventor 汤琪卢宇彤陈志广肖侬
Owner SUN YAT SEN UNIV
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