Data processing method, electronic equipment and storage medium

Data processing method, electronic equipment and storage medium

The invention relates to the technical field of artificial intelligence, and discloses a data processing method, electronic equipment and a storage medium, in the data processing method, partially connected processing layers in a model are divided into a processing layer set, and parameters correspo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: CHEN BAITAO, GAO FENG, LIU CHAO
Format: Patent
Sprache:chi ; eng
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 CHEN BAITAO
GAO FENG
LIU CHAO
description The invention relates to the technical field of artificial intelligence, and discloses a data processing method, electronic equipment and a storage medium, in the data processing method, partially connected processing layers in a model are divided into a processing layer set, and parameters corresponding to all processing layers in the processing layer set are divided into a parameter set; and obtaining a plurality of parameter sets. When the multi-core NPU performs data processing, the segmentation information in the memory can be read, and based on the segmentation information, different parameter sets corresponding to different processing layer sets are loaded at the same time by adopting a plurality of cores in the multi-core NPU, and input data of the processing layer sets are processed respectively. Therefore, the plurality of cores in the multi-core NPU are simultaneously adopted for data processing, so that the waste of computing power resources of the multi-core NPU can be reduced under the condition
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116957027A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116957027A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116957027A3</originalsourceid><addsrcrecordid>eNrjZLB3SSxJVCgoyk9OLS7OzEtXyE0tychP0VFIzUlNLinKz8tMVkgtLM0syE3NK1FIzEtRKC7JL0pMTwUqTMkszeVhYE1LzClO5YXS3AyKbq4hzh66qQX58anFBYnJqXmpJfHOfoaGZpam5gZG5o7GxKgBAKJOMR8</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Data processing method, electronic equipment and storage medium</title><source>esp@cenet</source><creator>CHEN BAITAO ; GAO FENG ; LIU CHAO</creator><creatorcontrib>CHEN BAITAO ; GAO FENG ; LIU CHAO</creatorcontrib><description>The invention relates to the technical field of artificial intelligence, and discloses a data processing method, electronic equipment and a storage medium, in the data processing method, partially connected processing layers in a model are divided into a processing layer set, and parameters corresponding to all processing layers in the processing layer set are divided into a parameter set; and obtaining a plurality of parameter sets. When the multi-core NPU performs data processing, the segmentation information in the memory can be read, and based on the segmentation information, different parameter sets corresponding to different processing layer sets are loaded at the same time by adopting a plurality of cores in the multi-core NPU, and input data of the processing layer sets are processed respectively. Therefore, the plurality of cores in the multi-core NPU are simultaneously adopted for data processing, so that the waste of computing power resources of the multi-core NPU can be reduced under the condition</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</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=20231027&amp;DB=EPODOC&amp;CC=CN&amp;NR=116957027A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20231027&amp;DB=EPODOC&amp;CC=CN&amp;NR=116957027A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CHEN BAITAO</creatorcontrib><creatorcontrib>GAO FENG</creatorcontrib><creatorcontrib>LIU CHAO</creatorcontrib><title>Data processing method, electronic equipment and storage medium</title><description>The invention relates to the technical field of artificial intelligence, and discloses a data processing method, electronic equipment and a storage medium, in the data processing method, partially connected processing layers in a model are divided into a processing layer set, and parameters corresponding to all processing layers in the processing layer set are divided into a parameter set; and obtaining a plurality of parameter sets. When the multi-core NPU performs data processing, the segmentation information in the memory can be read, and based on the segmentation information, different parameter sets corresponding to different processing layer sets are loaded at the same time by adopting a plurality of cores in the multi-core NPU, and input data of the processing layer sets are processed respectively. Therefore, the plurality of cores in the multi-core NPU are simultaneously adopted for data processing, so that the waste of computing power resources of the multi-core NPU can be reduced under the condition</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLB3SSxJVCgoyk9OLS7OzEtXyE0tychP0VFIzUlNLinKz8tMVkgtLM0syE3NK1FIzEtRKC7JL0pMTwUqTMkszeVhYE1LzClO5YXS3AyKbq4hzh66qQX58anFBYnJqXmpJfHOfoaGZpam5gZG5o7GxKgBAKJOMR8</recordid><startdate>20231027</startdate><enddate>20231027</enddate><creator>CHEN BAITAO</creator><creator>GAO FENG</creator><creator>LIU CHAO</creator><scope>EVB</scope></search><sort><creationdate>20231027</creationdate><title>Data processing method, electronic equipment and storage medium</title><author>CHEN BAITAO ; GAO FENG ; LIU CHAO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116957027A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</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>CHEN BAITAO</creatorcontrib><creatorcontrib>GAO FENG</creatorcontrib><creatorcontrib>LIU CHAO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CHEN BAITAO</au><au>GAO FENG</au><au>LIU CHAO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Data processing method, electronic equipment and storage medium</title><date>2023-10-27</date><risdate>2023</risdate><abstract>The invention relates to the technical field of artificial intelligence, and discloses a data processing method, electronic equipment and a storage medium, in the data processing method, partially connected processing layers in a model are divided into a processing layer set, and parameters corresponding to all processing layers in the processing layer set are divided into a parameter set; and obtaining a plurality of parameter sets. When the multi-core NPU performs data processing, the segmentation information in the memory can be read, and based on the segmentation information, different parameter sets corresponding to different processing layer sets are loaded at the same time by adopting a plurality of cores in the multi-core NPU, and input data of the processing layer sets are processed respectively. Therefore, the plurality of cores in the multi-core NPU are simultaneously adopted for data processing, so that the waste of computing power resources of the multi-core NPU can be reduced under the condition</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN116957027A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title Data processing method, electronic equipment and storage medium
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T04%3A59%3A03IST&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=CHEN%20BAITAO&rft.date=2023-10-27&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116957027A%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