Monitoring network card model training method, application and system thereof and electronic equipment

The invention provides a monitoring network card model training method, application and system thereof and electronic equipment, and the method comprises the steps: obtaining an expelling historical record set, carrying out the calculation to generate a verification set matrix, and constructing a tr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: QIU SHUHONG, MAI FUQUAN, LIU JUNJING, LIN DONG, LIU HANLIANG, HUANG MINXING, LONG BUYUN
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator QIU SHUHONG
MAI FUQUAN
LIU JUNJING
LIN DONG
LIU HANLIANG
HUANG MINXING
LONG BUYUN
description The invention provides a monitoring network card model training method, application and system thereof and electronic equipment, and the method comprises the steps: obtaining an expelling historical record set, carrying out the calculation to generate a verification set matrix, and constructing a training set through the verification set matrix; the optimized training set is input into a convolutional neural network, training is carried out in a stochastic gradient descent mode combined with a back propagation algorithm, a trained parameter adjustment model is obtained, the parameter adjustment model is used for dynamically calculating a soft expulsion threshold value and a hard expulsion threshold value according to the data condition on a current node cluster machine, and the soft expulsion threshold value and the hard expulsion threshold value are obtained. When the network card flow meets the soft expelling threshold value or the hard expelling threshold value, respectively executing soft expelling and ha
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115714692A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115714692A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115714692A3</originalsourceid><addsrcrecordid>eNqNjTsOwjAQRNNQIOAOSw9F-IoSRSAaqOijlb1JLOxdYy9C3J6AOADVSPNGb4ZFcxZ2KslxC0z6lHQDg8lCEEseNKHjDwukndgZYIzeGVQnDMgW8isrBdCOEknzrciT0dRrDdD94WIg1nExaNBnmvxyVEyPh2t1mlOUmnJEQ_17XV3Kcr0tV5vdYr_8Z_MGyyhARQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Monitoring network card model training method, application and system thereof and electronic equipment</title><source>esp@cenet</source><creator>QIU SHUHONG ; MAI FUQUAN ; LIU JUNJING ; LIN DONG ; LIU HANLIANG ; HUANG MINXING ; LONG BUYUN</creator><creatorcontrib>QIU SHUHONG ; MAI FUQUAN ; LIU JUNJING ; LIN DONG ; LIU HANLIANG ; HUANG MINXING ; LONG BUYUN</creatorcontrib><description>The invention provides a monitoring network card model training method, application and system thereof and electronic equipment, and the method comprises the steps: obtaining an expelling historical record set, carrying out the calculation to generate a verification set matrix, and constructing a training set through the verification set matrix; the optimized training set is input into a convolutional neural network, training is carried out in a stochastic gradient descent mode combined with a back propagation algorithm, a trained parameter adjustment model is obtained, the parameter adjustment model is used for dynamically calculating a soft expulsion threshold value and a hard expulsion threshold value according to the data condition on a current node cluster machine, and the soft expulsion threshold value and the hard expulsion threshold value are obtained. When the network card flow meets the soft expelling threshold value or the hard expelling threshold value, respectively executing soft expelling and ha</description><language>chi ; eng</language><subject>ELECTRIC COMMUNICATION TECHNIQUE ; ELECTRICITY ; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION</subject><creationdate>2023</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230224&amp;DB=EPODOC&amp;CC=CN&amp;NR=115714692A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230224&amp;DB=EPODOC&amp;CC=CN&amp;NR=115714692A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>QIU SHUHONG</creatorcontrib><creatorcontrib>MAI FUQUAN</creatorcontrib><creatorcontrib>LIU JUNJING</creatorcontrib><creatorcontrib>LIN DONG</creatorcontrib><creatorcontrib>LIU HANLIANG</creatorcontrib><creatorcontrib>HUANG MINXING</creatorcontrib><creatorcontrib>LONG BUYUN</creatorcontrib><title>Monitoring network card model training method, application and system thereof and electronic equipment</title><description>The invention provides a monitoring network card model training method, application and system thereof and electronic equipment, and the method comprises the steps: obtaining an expelling historical record set, carrying out the calculation to generate a verification set matrix, and constructing a training set through the verification set matrix; the optimized training set is input into a convolutional neural network, training is carried out in a stochastic gradient descent mode combined with a back propagation algorithm, a trained parameter adjustment model is obtained, the parameter adjustment model is used for dynamically calculating a soft expulsion threshold value and a hard expulsion threshold value according to the data condition on a current node cluster machine, and the soft expulsion threshold value and the hard expulsion threshold value are obtained. When the network card flow meets the soft expelling threshold value or the hard expelling threshold value, respectively executing soft expelling and ha</description><subject>ELECTRIC COMMUNICATION TECHNIQUE</subject><subject>ELECTRICITY</subject><subject>TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjTsOwjAQRNNQIOAOSw9F-IoSRSAaqOijlb1JLOxdYy9C3J6AOADVSPNGb4ZFcxZ2KslxC0z6lHQDg8lCEEseNKHjDwukndgZYIzeGVQnDMgW8isrBdCOEknzrciT0dRrDdD94WIg1nExaNBnmvxyVEyPh2t1mlOUmnJEQ_17XV3Kcr0tV5vdYr_8Z_MGyyhARQ</recordid><startdate>20230224</startdate><enddate>20230224</enddate><creator>QIU SHUHONG</creator><creator>MAI FUQUAN</creator><creator>LIU JUNJING</creator><creator>LIN DONG</creator><creator>LIU HANLIANG</creator><creator>HUANG MINXING</creator><creator>LONG BUYUN</creator><scope>EVB</scope></search><sort><creationdate>20230224</creationdate><title>Monitoring network card model training method, application and system thereof and electronic equipment</title><author>QIU SHUHONG ; MAI FUQUAN ; LIU JUNJING ; LIN DONG ; LIU HANLIANG ; HUANG MINXING ; LONG BUYUN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115714692A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>ELECTRIC COMMUNICATION TECHNIQUE</topic><topic>ELECTRICITY</topic><topic>TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION</topic><toplevel>online_resources</toplevel><creatorcontrib>QIU SHUHONG</creatorcontrib><creatorcontrib>MAI FUQUAN</creatorcontrib><creatorcontrib>LIU JUNJING</creatorcontrib><creatorcontrib>LIN DONG</creatorcontrib><creatorcontrib>LIU HANLIANG</creatorcontrib><creatorcontrib>HUANG MINXING</creatorcontrib><creatorcontrib>LONG BUYUN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>QIU SHUHONG</au><au>MAI FUQUAN</au><au>LIU JUNJING</au><au>LIN DONG</au><au>LIU HANLIANG</au><au>HUANG MINXING</au><au>LONG BUYUN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Monitoring network card model training method, application and system thereof and electronic equipment</title><date>2023-02-24</date><risdate>2023</risdate><abstract>The invention provides a monitoring network card model training method, application and system thereof and electronic equipment, and the method comprises the steps: obtaining an expelling historical record set, carrying out the calculation to generate a verification set matrix, and constructing a training set through the verification set matrix; the optimized training set is input into a convolutional neural network, training is carried out in a stochastic gradient descent mode combined with a back propagation algorithm, a trained parameter adjustment model is obtained, the parameter adjustment model is used for dynamically calculating a soft expulsion threshold value and a hard expulsion threshold value according to the data condition on a current node cluster machine, and the soft expulsion threshold value and the hard expulsion threshold value are obtained. When the network card flow meets the soft expelling threshold value or the hard expelling threshold value, respectively executing soft expelling and ha</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN115714692A
source esp@cenet
subjects ELECTRIC COMMUNICATION TECHNIQUE
ELECTRICITY
TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION
title Monitoring network card model training method, application and system thereof and electronic equipment
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T09%3A08%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=QIU%20SHUHONG&rft.date=2023-02-24&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115714692A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true