FEDERATED LEARNING SYSTEM, FEDERATED LEARNING METHOD, AND FEDERATED LEARNING DEVICE

The present invention provides a federated learning system, a federated learning method, and a federated learning device. A specific implementation solution is as follows: a display operation module, used for displaying data resource information and model algorithm names of multiple parties, receivi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: HU, Jiaojiao, TAO, Zhengping, ZHONG, Yixing, WANG, Shengyi, YANG, Shu, XIE, Zhenqiang, HUANG, Guo
Format: Patent
Sprache:chi ; eng ; fre
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 HU, Jiaojiao
TAO, Zhengping
ZHONG, Yixing
WANG, Shengyi
YANG, Shu
XIE, Zhenqiang
HUANG, Guo
description The present invention provides a federated learning system, a federated learning method, and a federated learning device. A specific implementation solution is as follows: a display operation module, used for displaying data resource information and model algorithm names of multiple parties, receiving task information inputted by a demand party and an operation of the demand party for the data resource information and the model algorithm names, and generating a task request on the basis of the operation; and a data processing module, used for receiving the task request and the task information, determining a demand task of the demand party, performing validity judgment on the demand task, and in response to the demand task being valid, performing federated training on models of the parties corresponding to the demand task so as to obtain a global task model. By means of the present embodiments, the efficiency of federated learning is improved. La présente invention concerne un système d'apprentissage fédéré,
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_WO2024212418A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>WO2024212418A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_WO2024212418A13</originalsourceid><addsrcrecordid>eNrjZAh2c3VxDXIMcXVR8HF1DPLz9HNXCI4MDnH11VHAIuXrGuLh76Kj4Ojngk3axTXM09mVh4E1LTGnOJUXSnMzKLu5hjh76KYW5MenFhckJqfmpZbEh_sbGRiZGBkamRhaOBoaE6cKAH9hMDs</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>FEDERATED LEARNING SYSTEM, FEDERATED LEARNING METHOD, AND FEDERATED LEARNING DEVICE</title><source>esp@cenet</source><creator>HU, Jiaojiao ; TAO, Zhengping ; ZHONG, Yixing ; WANG, Shengyi ; YANG, Shu ; XIE, Zhenqiang ; HUANG, Guo</creator><creatorcontrib>HU, Jiaojiao ; TAO, Zhengping ; ZHONG, Yixing ; WANG, Shengyi ; YANG, Shu ; XIE, Zhenqiang ; HUANG, Guo</creatorcontrib><description>The present invention provides a federated learning system, a federated learning method, and a federated learning device. A specific implementation solution is as follows: a display operation module, used for displaying data resource information and model algorithm names of multiple parties, receiving task information inputted by a demand party and an operation of the demand party for the data resource information and the model algorithm names, and generating a task request on the basis of the operation; and a data processing module, used for receiving the task request and the task information, determining a demand task of the demand party, performing validity judgment on the demand task, and in response to the demand task being valid, performing federated training on models of the parties corresponding to the demand task so as to obtain a global task model. By means of the present embodiments, the efficiency of federated learning is improved. La présente invention concerne un système d'apprentissage fédéré,</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=20241017&amp;DB=EPODOC&amp;CC=WO&amp;NR=2024212418A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20241017&amp;DB=EPODOC&amp;CC=WO&amp;NR=2024212418A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>HU, Jiaojiao</creatorcontrib><creatorcontrib>TAO, Zhengping</creatorcontrib><creatorcontrib>ZHONG, Yixing</creatorcontrib><creatorcontrib>WANG, Shengyi</creatorcontrib><creatorcontrib>YANG, Shu</creatorcontrib><creatorcontrib>XIE, Zhenqiang</creatorcontrib><creatorcontrib>HUANG, Guo</creatorcontrib><title>FEDERATED LEARNING SYSTEM, FEDERATED LEARNING METHOD, AND FEDERATED LEARNING DEVICE</title><description>The present invention provides a federated learning system, a federated learning method, and a federated learning device. A specific implementation solution is as follows: a display operation module, used for displaying data resource information and model algorithm names of multiple parties, receiving task information inputted by a demand party and an operation of the demand party for the data resource information and the model algorithm names, and generating a task request on the basis of the operation; and a data processing module, used for receiving the task request and the task information, determining a demand task of the demand party, performing validity judgment on the demand task, and in response to the demand task being valid, performing federated training on models of the parties corresponding to the demand task so as to obtain a global task model. By means of the present embodiments, the efficiency of federated learning is improved. La présente invention concerne un système d'apprentissage fédéré,</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>eNrjZAh2c3VxDXIMcXVR8HF1DPLz9HNXCI4MDnH11VHAIuXrGuLh76Kj4Ojngk3axTXM09mVh4E1LTGnOJUXSnMzKLu5hjh76KYW5MenFhckJqfmpZbEh_sbGRiZGBkamRhaOBoaE6cKAH9hMDs</recordid><startdate>20241017</startdate><enddate>20241017</enddate><creator>HU, Jiaojiao</creator><creator>TAO, Zhengping</creator><creator>ZHONG, Yixing</creator><creator>WANG, Shengyi</creator><creator>YANG, Shu</creator><creator>XIE, Zhenqiang</creator><creator>HUANG, Guo</creator><scope>EVB</scope></search><sort><creationdate>20241017</creationdate><title>FEDERATED LEARNING SYSTEM, FEDERATED LEARNING METHOD, AND FEDERATED LEARNING DEVICE</title><author>HU, Jiaojiao ; TAO, Zhengping ; ZHONG, Yixing ; WANG, Shengyi ; YANG, Shu ; XIE, Zhenqiang ; HUANG, Guo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_WO2024212418A13</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>HU, Jiaojiao</creatorcontrib><creatorcontrib>TAO, Zhengping</creatorcontrib><creatorcontrib>ZHONG, Yixing</creatorcontrib><creatorcontrib>WANG, Shengyi</creatorcontrib><creatorcontrib>YANG, Shu</creatorcontrib><creatorcontrib>XIE, Zhenqiang</creatorcontrib><creatorcontrib>HUANG, Guo</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>HU, Jiaojiao</au><au>TAO, Zhengping</au><au>ZHONG, Yixing</au><au>WANG, Shengyi</au><au>YANG, Shu</au><au>XIE, Zhenqiang</au><au>HUANG, Guo</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>FEDERATED LEARNING SYSTEM, FEDERATED LEARNING METHOD, AND FEDERATED LEARNING DEVICE</title><date>2024-10-17</date><risdate>2024</risdate><abstract>The present invention provides a federated learning system, a federated learning method, and a federated learning device. A specific implementation solution is as follows: a display operation module, used for displaying data resource information and model algorithm names of multiple parties, receiving task information inputted by a demand party and an operation of the demand party for the data resource information and the model algorithm names, and generating a task request on the basis of the operation; and a data processing module, used for receiving the task request and the task information, determining a demand task of the demand party, performing validity judgment on the demand task, and in response to the demand task being valid, performing federated training on models of the parties corresponding to the demand task so as to obtain a global task model. By means of the present embodiments, the efficiency of federated learning is improved. La présente invention concerne un système d'apprentissage fédéré,</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng ; fre
recordid cdi_epo_espacenet_WO2024212418A1
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title FEDERATED LEARNING SYSTEM, FEDERATED LEARNING METHOD, AND FEDERATED LEARNING DEVICE
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T23%3A36%3A21IST&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=HU,%20Jiaojiao&rft.date=2024-10-17&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EWO2024212418A1%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