Real-time verification method for deep learning model reasoning

The invention discloses a real-time verification method for deep learning model reasoning, and the method comprises the steps: determining each piece of verification data and result data corresponding to each piece of verification data, then obtaining to-be-detected data related to space edge calcul...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: CUI SHUYAO, TANG XIAOYU, QIU JIBING, TANG ZHAORONG
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 CUI SHUYAO
TANG XIAOYU
QIU JIBING
TANG ZHAORONG
description The invention discloses a real-time verification method for deep learning model reasoning, and the method comprises the steps: determining each piece of verification data and result data corresponding to each piece of verification data, then obtaining to-be-detected data related to space edge calculation in response to a prediction instruction of a user, adding the verification data into the to-be-detected data to obtain batch data, and carrying out the calculation of the batch data. And inputting the batch data into the prediction model to obtain a prediction result corresponding to the to-be-detected data and a prediction result corresponding to the at least one piece of verification data. And further, according to a prediction result corresponding to the verification data and result data corresponding to the verification data, determining a verification result, if the verification result is determined to indicate that the verification is passed, returning the prediction result corresponding to the to-be-de
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117726001A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117726001A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117726001A3</originalsourceid><addsrcrecordid>eNrjZLAPSk3M0S3JzE1VKEstykzLTE4syczPU8hNLcnIT1FIyy9SSElNLVDISU0sysvMS1fIzU9JzVEoSk0szgfxeRhY0xJzilN5oTQ3g6Kba4izh25qQX58anFBYnJqXmpJvLOfoaG5uZGZgYGhozExagCRXTDo</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Real-time verification method for deep learning model reasoning</title><source>esp@cenet</source><creator>CUI SHUYAO ; TANG XIAOYU ; QIU JIBING ; TANG ZHAORONG</creator><creatorcontrib>CUI SHUYAO ; TANG XIAOYU ; QIU JIBING ; TANG ZHAORONG</creatorcontrib><description>The invention discloses a real-time verification method for deep learning model reasoning, and the method comprises the steps: determining each piece of verification data and result data corresponding to each piece of verification data, then obtaining to-be-detected data related to space edge calculation in response to a prediction instruction of a user, adding the verification data into the to-be-detected data to obtain batch data, and carrying out the calculation of the batch data. And inputting the batch data into the prediction model to obtain a prediction result corresponding to the to-be-detected data and a prediction result corresponding to the at least one piece of verification data. And further, according to a prediction result corresponding to the verification data and result data corresponding to the verification data, determining a verification result, if the verification result is determined to indicate that the verification is passed, returning the prediction result corresponding to the to-be-de</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2024</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=20240319&amp;DB=EPODOC&amp;CC=CN&amp;NR=117726001A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240319&amp;DB=EPODOC&amp;CC=CN&amp;NR=117726001A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CUI SHUYAO</creatorcontrib><creatorcontrib>TANG XIAOYU</creatorcontrib><creatorcontrib>QIU JIBING</creatorcontrib><creatorcontrib>TANG ZHAORONG</creatorcontrib><title>Real-time verification method for deep learning model reasoning</title><description>The invention discloses a real-time verification method for deep learning model reasoning, and the method comprises the steps: determining each piece of verification data and result data corresponding to each piece of verification data, then obtaining to-be-detected data related to space edge calculation in response to a prediction instruction of a user, adding the verification data into the to-be-detected data to obtain batch data, and carrying out the calculation of the batch data. And inputting the batch data into the prediction model to obtain a prediction result corresponding to the to-be-detected data and a prediction result corresponding to the at least one piece of verification data. And further, according to a prediction result corresponding to the verification data and result data corresponding to the verification data, determining a verification result, if the verification result is determined to indicate that the verification is passed, returning the prediction result corresponding to the to-be-de</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLAPSk3M0S3JzE1VKEstykzLTE4syczPU8hNLcnIT1FIyy9SSElNLVDISU0sysvMS1fIzU9JzVEoSk0szgfxeRhY0xJzilN5oTQ3g6Kba4izh25qQX58anFBYnJqXmpJvLOfoaG5uZGZgYGhozExagCRXTDo</recordid><startdate>20240319</startdate><enddate>20240319</enddate><creator>CUI SHUYAO</creator><creator>TANG XIAOYU</creator><creator>QIU JIBING</creator><creator>TANG ZHAORONG</creator><scope>EVB</scope></search><sort><creationdate>20240319</creationdate><title>Real-time verification method for deep learning model reasoning</title><author>CUI SHUYAO ; TANG XIAOYU ; QIU JIBING ; TANG ZHAORONG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117726001A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>CUI SHUYAO</creatorcontrib><creatorcontrib>TANG XIAOYU</creatorcontrib><creatorcontrib>QIU JIBING</creatorcontrib><creatorcontrib>TANG ZHAORONG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CUI SHUYAO</au><au>TANG XIAOYU</au><au>QIU JIBING</au><au>TANG ZHAORONG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Real-time verification method for deep learning model reasoning</title><date>2024-03-19</date><risdate>2024</risdate><abstract>The invention discloses a real-time verification method for deep learning model reasoning, and the method comprises the steps: determining each piece of verification data and result data corresponding to each piece of verification data, then obtaining to-be-detected data related to space edge calculation in response to a prediction instruction of a user, adding the verification data into the to-be-detected data to obtain batch data, and carrying out the calculation of the batch data. And inputting the batch data into the prediction model to obtain a prediction result corresponding to the to-be-detected data and a prediction result corresponding to the at least one piece of verification data. And further, according to a prediction result corresponding to the verification data and result data corresponding to the verification data, determining a verification result, if the verification result is determined to indicate that the verification is passed, returning the prediction result corresponding to the to-be-de</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN117726001A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title Real-time verification method for deep learning model reasoning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T22%3A06%3A02IST&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=CUI%20SHUYAO&rft.date=2024-03-19&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117726001A%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