Model training improvement method and device

The invention discloses a model training improvement method and device, and the method comprises the steps: obtaining and for a plurality of pieces of to-be-trained data, filling the to-be-trained data into a multi-dimensional data space of a matrix space in a matrix manner, and obtaining a pluralit...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: NIE CHUNMEI, DONG YI, TAN MINGXU, LI FENG, LIANG ZHIHAI, LI RUIDONG, ZHAO WENJIE
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 NIE CHUNMEI
DONG YI
TAN MINGXU
LI FENG
LIANG ZHIHAI
LI RUIDONG
ZHAO WENJIE
description The invention discloses a model training improvement method and device, and the method comprises the steps: obtaining and for a plurality of pieces of to-be-trained data, filling the to-be-trained data into a multi-dimensional data space of a matrix space in a matrix manner, and obtaining a plurality of information regions; inputting the plurality of information areas into the model to obtain a training result of each information area; the training result of each information area is stored in a target area of a matrix space in a matrix mode; generating a model change report based on all the target areas and all the information areas; and determining a related direction of model training according to the model change report, and training the model. The correlation direction of model training is determined through the model change report, the model is trained through the to-be-trained data in the correlation direction of model training, the model does not need to be trained according to the data type of the to-
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118627573A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118627573A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118627573A3</originalsourceid><addsrcrecordid>eNrjZNDxzU9JzVEoKUrMzMvMS1fIzC0oyi9LzU3NK1HITS3JyE9RSMxLUUhJLctMTuVhYE1LzClO5YXS3AyKbq4hzh66qQX58anFBYnJqXmpJfHOfoaGFmZG5qbmxo7GxKgBAKDNKeo</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Model training improvement method and device</title><source>esp@cenet</source><creator>NIE CHUNMEI ; DONG YI ; TAN MINGXU ; LI FENG ; LIANG ZHIHAI ; LI RUIDONG ; ZHAO WENJIE</creator><creatorcontrib>NIE CHUNMEI ; DONG YI ; TAN MINGXU ; LI FENG ; LIANG ZHIHAI ; LI RUIDONG ; ZHAO WENJIE</creatorcontrib><description>The invention discloses a model training improvement method and device, and the method comprises the steps: obtaining and for a plurality of pieces of to-be-trained data, filling the to-be-trained data into a multi-dimensional data space of a matrix space in a matrix manner, and obtaining a plurality of information regions; inputting the plurality of information areas into the model to obtain a training result of each information area; the training result of each information area is stored in a target area of a matrix space in a matrix mode; generating a model change report based on all the target areas and all the information areas; and determining a related direction of model training according to the model change report, and training the model. The correlation direction of model training is determined through the model change report, the model is trained through the to-be-trained data in the correlation direction of model training, the model does not need to be trained according to the data type of the to-</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; 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=20240910&amp;DB=EPODOC&amp;CC=CN&amp;NR=118627573A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240910&amp;DB=EPODOC&amp;CC=CN&amp;NR=118627573A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>NIE CHUNMEI</creatorcontrib><creatorcontrib>DONG YI</creatorcontrib><creatorcontrib>TAN MINGXU</creatorcontrib><creatorcontrib>LI FENG</creatorcontrib><creatorcontrib>LIANG ZHIHAI</creatorcontrib><creatorcontrib>LI RUIDONG</creatorcontrib><creatorcontrib>ZHAO WENJIE</creatorcontrib><title>Model training improvement method and device</title><description>The invention discloses a model training improvement method and device, and the method comprises the steps: obtaining and for a plurality of pieces of to-be-trained data, filling the to-be-trained data into a multi-dimensional data space of a matrix space in a matrix manner, and obtaining a plurality of information regions; inputting the plurality of information areas into the model to obtain a training result of each information area; the training result of each information area is stored in a target area of a matrix space in a matrix mode; generating a model change report based on all the target areas and all the information areas; and determining a related direction of model training according to the model change report, and training the model. The correlation direction of model training is determined through the model change report, the model is trained through the to-be-trained data in the correlation direction of model training, the model does not need to be trained according to the data type of the to-</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZNDxzU9JzVEoKUrMzMvMS1fIzC0oyi9LzU3NK1HITS3JyE9RSMxLUUhJLctMTuVhYE1LzClO5YXS3AyKbq4hzh66qQX58anFBYnJqXmpJfHOfoaGFmZG5qbmxo7GxKgBAKDNKeo</recordid><startdate>20240910</startdate><enddate>20240910</enddate><creator>NIE CHUNMEI</creator><creator>DONG YI</creator><creator>TAN MINGXU</creator><creator>LI FENG</creator><creator>LIANG ZHIHAI</creator><creator>LI RUIDONG</creator><creator>ZHAO WENJIE</creator><scope>EVB</scope></search><sort><creationdate>20240910</creationdate><title>Model training improvement method and device</title><author>NIE CHUNMEI ; DONG YI ; TAN MINGXU ; LI FENG ; LIANG ZHIHAI ; LI RUIDONG ; ZHAO WENJIE</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118627573A3</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>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>NIE CHUNMEI</creatorcontrib><creatorcontrib>DONG YI</creatorcontrib><creatorcontrib>TAN MINGXU</creatorcontrib><creatorcontrib>LI FENG</creatorcontrib><creatorcontrib>LIANG ZHIHAI</creatorcontrib><creatorcontrib>LI RUIDONG</creatorcontrib><creatorcontrib>ZHAO WENJIE</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>NIE CHUNMEI</au><au>DONG YI</au><au>TAN MINGXU</au><au>LI FENG</au><au>LIANG ZHIHAI</au><au>LI RUIDONG</au><au>ZHAO WENJIE</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Model training improvement method and device</title><date>2024-09-10</date><risdate>2024</risdate><abstract>The invention discloses a model training improvement method and device, and the method comprises the steps: obtaining and for a plurality of pieces of to-be-trained data, filling the to-be-trained data into a multi-dimensional data space of a matrix space in a matrix manner, and obtaining a plurality of information regions; inputting the plurality of information areas into the model to obtain a training result of each information area; the training result of each information area is stored in a target area of a matrix space in a matrix mode; generating a model change report based on all the target areas and all the information areas; and determining a related direction of model training according to the model change report, and training the model. The correlation direction of model training is determined through the model change report, the model is trained through the to-be-trained data in the correlation direction of model training, the model does not need to be trained according to the data type of the to-</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN118627573A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title Model training improvement method and device
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T09%3A44%3A20IST&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=NIE%20CHUNMEI&rft.date=2024-09-10&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118627573A%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