A Method for Similarity Query of Time Series Data Based on Memory Computing

A time series and query method technology, applied in computing, digital data processing, structured data retrieval, etc., can solve problems such as increasing query delay and reducing query efficiency, achieving low space overhead and maintenance cost, and high query accuracy. , The effect of efficient time series similarity query

Active Publication Date: 2022-02-01
ANHUI UNIVERSITY OF TECHNOLOGY +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

According to whether the representation method satisfies the triangle inequality, it can be judged whether the method can build an index, and the representation method that cannot build an index will reduce the query efficiency and increase the query delay

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
  • A Method for Similarity Query of Time Series Data Based on Memory Computing
  • A Method for Similarity Query of Time Series Data Based on Memory Computing
  • A Method for Similarity Query of Time Series Data Based on Memory Computing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] combine figure 1 , a time series data similarity query method based on memory computing in this embodiment uses a cluster composed of distributed computing nodes, stores data through memory, and expands the computing power of the cluster by expanding distributed nodes. In this embodiment, time-series data is allocated to computing nodes according to corresponding steps, and index resident memory is formed according to corresponding steps. After the cluster receives a search request, each computing node is scheduled to search according to corresponding steps. The partitioning and index construction of each node's data are performed in local memory, and can communicate with other nodes or overall external submodules to aggregate, move and process data. The query process reads data on some of the nodes, guided by an in-memory index, eliminating the need to scan the entire cluster. This embodiment specifically includes the following steps:

[0068] (1) Data preprocessing,...

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 data similarity query method based on memory computing, and belongs to the technical fields of distributed databases, memory computing and information retrieval. The present invention uses a cluster composed of distributed computing nodes, stores data in memory, and expands the computing power of the cluster by expanding the distributed nodes; distributes time series data to computing nodes, and forms an index resident in memory. When the cluster receives a search request, the scheduling Each computing node searches; the partitioning and index construction of each node's data are carried out in local memory, and can communicate with other nodes or the overall external submodule; the query process will read data on some nodes and pass through the index resident in memory The bootstrap does not require scanning the entire cluster. The present invention can quickly find out most similar sequences from large-scale memory computing clusters for any time sequence given by the user.

Description

technical field [0001] The invention relates to the technical fields of distributed databases, memory computing and information retrieval, in particular to a time series data similarity query method based on memory computing. Background technique [0002] Time is a natural description of the objective existence of things, and almost all things have invisible or explicit time attributes. As the medium of this description, time-series data refers to a set of data arranged in chronological order, which has been widely used in various fields, such as exchange rate data in the foreign exchange financial market, temperature data in weather forecasts, and urban demographic data. , and genetic data in biomedicine, etc. [0003] The similarity query of time series is to find similar change patterns in time series data sets. It is an important query mode and has great significance for the classification, prediction and knowledge discovery of sequence data. According to different tec...

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 Patents(China)
IPC IPC(8): G06F16/2458G06F16/27
Inventor 秦锋茆凯成郑啸
Owner ANHUI UNIVERSITY OF TECHNOLOGY
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