MODEL PROCESSING METHOD AND SYSTEM

MODEL PROCESSING METHOD AND SYSTEM

Embodiments of the present description provide a model processing method and system. The model processing system comprises a client and a server. The client is configured to send a model processing request to the server, wherein the model processing request carries data to be processed. The server i...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LEI, Fanding, FENG, Bo, XUE, Shengke, CHEN, Luoyu, CHEN, Jian, LU, Lu, LI, Chenhaowen
Format: Patent
Sprache:chi ; eng ; fre
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
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 LEI, Fanding
FENG, Bo
XUE, Shengke
CHEN, Luoyu
CHEN, Jian
LU, Lu
LI, Chenhaowen
description Embodiments of the present description provide a model processing method and system. The model processing system comprises a client and a server. The client is configured to send a model processing request to the server, wherein the model processing request carries data to be processed. The server is configured to: acquire a non-zero weight of a machine learning model from a weight information storage unit; acquire, from a position information storage unit corresponding to the weight information storage unit, position information of the non-zero weight in a weight matrix of the machine learning model; and perform convolution calculation on said data according to the non-zero weight and the position information of the non-zero weight in the weight matrix. The weight information storage unit only needs to store the non-zero weight, thereby improving the data storage efficiency and saving the data storage space. Moreover, during the convolution calculation of the model, it is only necessary to perform convolutio
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_WO2024222484A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>WO2024222484A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_WO2024222484A13</originalsourceid><addsrcrecordid>eNrjZFDy9Xdx9VEICPJ3dg0O9vRzV_B1DfHwd1Fw9HNRCI4MDnH15WFgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8eH-RgZGJkZGRiYWJo6GxsSpAgDCdiNc</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>MODEL PROCESSING METHOD AND SYSTEM</title><source>esp@cenet</source><creator>LEI, Fanding ; FENG, Bo ; XUE, Shengke ; CHEN, Luoyu ; CHEN, Jian ; LU, Lu ; LI, Chenhaowen</creator><creatorcontrib>LEI, Fanding ; FENG, Bo ; XUE, Shengke ; CHEN, Luoyu ; CHEN, Jian ; LU, Lu ; LI, Chenhaowen</creatorcontrib><description>Embodiments of the present description provide a model processing method and system. The model processing system comprises a client and a server. The client is configured to send a model processing request to the server, wherein the model processing request carries data to be processed. The server is configured to: acquire a non-zero weight of a machine learning model from a weight information storage unit; acquire, from a position information storage unit corresponding to the weight information storage unit, position information of the non-zero weight in a weight matrix of the machine learning model; and perform convolution calculation on said data according to the non-zero weight and the position information of the non-zero weight in the weight matrix. The weight information storage unit only needs to store the non-zero weight, thereby improving the data storage efficiency and saving the data storage space. Moreover, during the convolution calculation of the model, it is only necessary to perform convolutio</description><language>chi ; eng ; fre</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=20241031&amp;DB=EPODOC&amp;CC=WO&amp;NR=2024222484A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20241031&amp;DB=EPODOC&amp;CC=WO&amp;NR=2024222484A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>LEI, Fanding</creatorcontrib><creatorcontrib>FENG, Bo</creatorcontrib><creatorcontrib>XUE, Shengke</creatorcontrib><creatorcontrib>CHEN, Luoyu</creatorcontrib><creatorcontrib>CHEN, Jian</creatorcontrib><creatorcontrib>LU, Lu</creatorcontrib><creatorcontrib>LI, Chenhaowen</creatorcontrib><title>MODEL PROCESSING METHOD AND SYSTEM</title><description>Embodiments of the present description provide a model processing method and system. The model processing system comprises a client and a server. The client is configured to send a model processing request to the server, wherein the model processing request carries data to be processed. The server is configured to: acquire a non-zero weight of a machine learning model from a weight information storage unit; acquire, from a position information storage unit corresponding to the weight information storage unit, position information of the non-zero weight in a weight matrix of the machine learning model; and perform convolution calculation on said data according to the non-zero weight and the position information of the non-zero weight in the weight matrix. The weight information storage unit only needs to store the non-zero weight, thereby improving the data storage efficiency and saving the data storage space. Moreover, during the convolution calculation of the model, it is only necessary to perform convolutio</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>eNrjZFDy9Xdx9VEICPJ3dg0O9vRzV_B1DfHwd1Fw9HNRCI4MDnH15WFgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8eH-RgZGJkZGRiYWJo6GxsSpAgDCdiNc</recordid><startdate>20241031</startdate><enddate>20241031</enddate><creator>LEI, Fanding</creator><creator>FENG, Bo</creator><creator>XUE, Shengke</creator><creator>CHEN, Luoyu</creator><creator>CHEN, Jian</creator><creator>LU, Lu</creator><creator>LI, Chenhaowen</creator><scope>EVB</scope></search><sort><creationdate>20241031</creationdate><title>MODEL PROCESSING METHOD AND SYSTEM</title><author>LEI, Fanding ; FENG, Bo ; XUE, Shengke ; CHEN, Luoyu ; CHEN, Jian ; LU, Lu ; LI, Chenhaowen</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_WO2024222484A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng ; fre</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>LEI, Fanding</creatorcontrib><creatorcontrib>FENG, Bo</creatorcontrib><creatorcontrib>XUE, Shengke</creatorcontrib><creatorcontrib>CHEN, Luoyu</creatorcontrib><creatorcontrib>CHEN, Jian</creatorcontrib><creatorcontrib>LU, Lu</creatorcontrib><creatorcontrib>LI, Chenhaowen</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>LEI, Fanding</au><au>FENG, Bo</au><au>XUE, Shengke</au><au>CHEN, Luoyu</au><au>CHEN, Jian</au><au>LU, Lu</au><au>LI, Chenhaowen</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>MODEL PROCESSING METHOD AND SYSTEM</title><date>2024-10-31</date><risdate>2024</risdate><abstract>Embodiments of the present description provide a model processing method and system. The model processing system comprises a client and a server. The client is configured to send a model processing request to the server, wherein the model processing request carries data to be processed. The server is configured to: acquire a non-zero weight of a machine learning model from a weight information storage unit; acquire, from a position information storage unit corresponding to the weight information storage unit, position information of the non-zero weight in a weight matrix of the machine learning model; and perform convolution calculation on said data according to the non-zero weight and the position information of the non-zero weight in the weight matrix. The weight information storage unit only needs to store the non-zero weight, thereby improving the data storage efficiency and saving the data storage space. Moreover, during the convolution calculation of the model, it is only necessary to perform convolutio</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng ; fre
recordid cdi_epo_espacenet_WO2024222484A1
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title MODEL PROCESSING METHOD AND SYSTEM
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T08%3A19%3A12IST&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=LEI,%20Fanding&rft.date=2024-10-31&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EWO2024222484A1%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