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

Data stream classification method and device based on time sequence feature learning

A technology of feature learning and data flow, which is applied in the direction of neural learning methods, instruments, biological neural network models, etc., and can solve problems such as server-difficult big data classification requirements

Active Publication Date: 2020-06-09
上海飞旗网络技术股份有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, with the expansion of data scale and the increase of data types, it is difficult for servers to efficiently cope with the data stream classification requirements of big data

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
  • Data stream classification method and device based on time sequence feature learning
  • Data stream classification method and device based on time sequence feature learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0066] In order to better understand the above technical solutions, the technical solutions of the present invention will be described in detail below through the accompanying drawings and specific examples. It should be understood that the embodiments of the present invention and the specific features in the examples are detailed descriptions of the technical solutions of the present invention, and It is not a limitation to the tec...

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 provides a data stream classification method and device based on time sequence feature learning. The method comprises the steps of: when the number of the to-be-classified data streams in the cache is relatively small, extracting time sequence features of the to-be-classified data streams in the cache by adopting a first setting mode of starting part of feature extraction threads, sothat more time slice resources can be allocated to the identification thread corresponding to the LSTM neural network, the time consumed for determining the identification tag is reduced, and the to-be-detected data streams are classified in time; and when the number of the to-be-classified data streams in the cache is large, extracting the time sequence features of the to-be-classified data streams in the cache by adopting a second setting mode of starting all feature extraction threads. By starting all the feature extraction threads, it can be ensured that time sequence feature extraction is carried out on each to-be-classified data stream in the cache, and omission of time sequence feature extraction on part of the to-be-classified data streams in the cache is avoided. In this way, itcan be ensured that all the obtained to-be-classified data streams are classified through the LSTM neural network.

Description

technical field [0001] The present invention relates to the technical field of big data data classification, in particular to a data flow classification method and device based on time series feature learning. Background technique [0002] With the continuous development of big data technology, various types of servers are faced with an increasing demand for data processing, which poses new challenges to the data processing capabilities of servers. When the server processes massive data, data classification is a common step. By classifying massive data, the data processing efficiency of the server can be improved and time cost can be saved. However, with the expansion of data scale and the increase of data types, it is difficult for servers to efficiently cope with the data flow classification requirements of big data. Contents of the invention [0003] In order to improve the above problems, the present invention provides a data stream classification method and device b...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/044G06N3/045G06F18/241
Inventor 杨贻宏
Owner 上海飞旗网络技术股份有限公司
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