Model reasoning acceleration method and device

Model reasoning acceleration method and device

The invention provides a model reasoning acceleration method and device, and the method comprises the steps: obtaining request information, analyzing the request information, determining a target model service with a dependency relationship corresponding to the request information, and enabling an i...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ZHANG DE, HUANG LELE, LIU SHUAICHAO
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
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 ZHANG DE
HUANG LELE
LIU SHUAICHAO
description The invention provides a model reasoning acceleration method and device, and the method comprises the steps: obtaining request information, analyzing the request information, determining a target model service with a dependency relationship corresponding to the request information, and enabling an integrated model service system to comprise at least one model service; determining a model parameter value, and processing the model parameter value through at least one target model service with a dependency relationship and a message queue arranged between the target model services in sequence to obtain a final output model calculation result; wherein the message queue between every two target model services with the dependency relationship is used for receiving task data generated by the previous target model service according to the processing capability value of the previous target model service, and sending the task data to the latter target model service according to the processing capability value of the la
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115130674A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115130674A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115130674A3</originalsourceid><addsrcrecordid>eNrjZNDzzU9JzVEoSk0szs_LzEtXSExOTs1JLUosyczPU8hNLcnIT1FIzEtRSEkty0xO5WFgTUvMKU7lhdLcDIpuriHOHrqpBfnxqcUFicmpeakl8c5-hoamhsYGZuYmjsbEqAEA9Okqcg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Model reasoning acceleration method and device</title><source>esp@cenet</source><creator>ZHANG DE ; HUANG LELE ; LIU SHUAICHAO</creator><creatorcontrib>ZHANG DE ; HUANG LELE ; LIU SHUAICHAO</creatorcontrib><description>The invention provides a model reasoning acceleration method and device, and the method comprises the steps: obtaining request information, analyzing the request information, determining a target model service with a dependency relationship corresponding to the request information, and enabling an integrated model service system to comprise at least one model service; determining a model parameter value, and processing the model parameter value through at least one target model service with a dependency relationship and a message queue arranged between the target model services in sequence to obtain a final output model calculation result; wherein the message queue between every two target model services with the dependency relationship is used for receiving task data generated by the previous target model service according to the processing capability value of the previous target model service, and sending the task data to the latter target model service according to the processing capability value of the la</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2022</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=20220930&amp;DB=EPODOC&amp;CC=CN&amp;NR=115130674A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,777,882,25545,76296</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20220930&amp;DB=EPODOC&amp;CC=CN&amp;NR=115130674A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHANG DE</creatorcontrib><creatorcontrib>HUANG LELE</creatorcontrib><creatorcontrib>LIU SHUAICHAO</creatorcontrib><title>Model reasoning acceleration method and device</title><description>The invention provides a model reasoning acceleration method and device, and the method comprises the steps: obtaining request information, analyzing the request information, determining a target model service with a dependency relationship corresponding to the request information, and enabling an integrated model service system to comprise at least one model service; determining a model parameter value, and processing the model parameter value through at least one target model service with a dependency relationship and a message queue arranged between the target model services in sequence to obtain a final output model calculation result; wherein the message queue between every two target model services with the dependency relationship is used for receiving task data generated by the previous target model service according to the processing capability value of the previous target model service, and sending the task data to the latter target model service according to the processing capability value of the la</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>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZNDzzU9JzVEoSk0szs_LzEtXSExOTs1JLUosyczPU8hNLcnIT1FIzEtRSEkty0xO5WFgTUvMKU7lhdLcDIpuriHOHrqpBfnxqcUFicmpeakl8c5-hoamhsYGZuYmjsbEqAEA9Okqcg</recordid><startdate>20220930</startdate><enddate>20220930</enddate><creator>ZHANG DE</creator><creator>HUANG LELE</creator><creator>LIU SHUAICHAO</creator><scope>EVB</scope></search><sort><creationdate>20220930</creationdate><title>Model reasoning acceleration method and device</title><author>ZHANG DE ; HUANG LELE ; LIU SHUAICHAO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115130674A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</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>ZHANG DE</creatorcontrib><creatorcontrib>HUANG LELE</creatorcontrib><creatorcontrib>LIU SHUAICHAO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHANG DE</au><au>HUANG LELE</au><au>LIU SHUAICHAO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Model reasoning acceleration method and device</title><date>2022-09-30</date><risdate>2022</risdate><abstract>The invention provides a model reasoning acceleration method and device, and the method comprises the steps: obtaining request information, analyzing the request information, determining a target model service with a dependency relationship corresponding to the request information, and enabling an integrated model service system to comprise at least one model service; determining a model parameter value, and processing the model parameter value through at least one target model service with a dependency relationship and a message queue arranged between the target model services in sequence to obtain a final output model calculation result; wherein the message queue between every two target model services with the dependency relationship is used for receiving task data generated by the previous target model service according to the processing capability value of the previous target model service, and sending the task data to the latter target model service according to the processing capability value of the la</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN115130674A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title Model reasoning acceleration 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=2025-01-18T13%3A09%3A01IST&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=ZHANG%20DE&rft.date=2022-09-30&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115130674A%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