Lightweight classification model training method and device, medium and equipment

The invention provides a lightweight classification model training method and device, a medium and equipment. The method comprises the following steps: collecting first text data with a classification label and second text data without a classification label; according to the first text data, traini...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ZHANG ZHENG, CHANG BINGXIN, HUANG DENGRONG, YUE AIZHEN
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 ZHANG ZHENG
CHANG BINGXIN
HUANG DENGRONG
YUE AIZHEN
description The invention provides a lightweight classification model training method and device, a medium and equipment. The method comprises the following steps: collecting first text data with a classification label and second text data without a classification label; according to the first text data, training a large-scale language model to obtain a training convergent large-scale language model; inputting the second text data into the large-scale language model to obtain a classification label corresponding to the second text data, and labeling the second text data by using the classification label; and training a lightweight classification model on the edge device according to the labeled second text data. According to the embodiment of the invention, the problem that more accurate text classification is difficult to realize due to less marked data in a small scene is solved based on the existing large-scale language model. And meanwhile, the lightweight classification model has the advantage of real-time response.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116975624A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116975624A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116975624A3</originalsourceid><addsrcrecordid>eNrjZAj0yUzPKClPBZEKyTmJxcWZaZnJiSWZ-XkKufkpqTkKJUWJmXmZeekKuaklGfkpCol5KQopqWWZyak6QKGUzNJcsFBqYWlmQW5qXgkPA2taYk5xKi-U5mZQdHMNcfbQTS3Ij08tLkhMTs1LLYl39jM0NLM0NzUzMnE0JkYNAAjnN_8</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Lightweight classification model training method and device, medium and equipment</title><source>esp@cenet</source><creator>ZHANG ZHENG ; CHANG BINGXIN ; HUANG DENGRONG ; YUE AIZHEN</creator><creatorcontrib>ZHANG ZHENG ; CHANG BINGXIN ; HUANG DENGRONG ; YUE AIZHEN</creatorcontrib><description>The invention provides a lightweight classification model training method and device, a medium and equipment. The method comprises the following steps: collecting first text data with a classification label and second text data without a classification label; according to the first text data, training a large-scale language model to obtain a training convergent large-scale language model; inputting the second text data into the large-scale language model to obtain a classification label corresponding to the second text data, and labeling the second text data by using the classification label; and training a lightweight classification model on the edge device according to the labeled second text data. According to the embodiment of the invention, the problem that more accurate text classification is difficult to realize due to less marked data in a small scene is solved based on the existing large-scale language model. And meanwhile, the lightweight classification model has the advantage of real-time response.</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; 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=20231031&amp;DB=EPODOC&amp;CC=CN&amp;NR=116975624A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20231031&amp;DB=EPODOC&amp;CC=CN&amp;NR=116975624A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHANG ZHENG</creatorcontrib><creatorcontrib>CHANG BINGXIN</creatorcontrib><creatorcontrib>HUANG DENGRONG</creatorcontrib><creatorcontrib>YUE AIZHEN</creatorcontrib><title>Lightweight classification model training method and device, medium and equipment</title><description>The invention provides a lightweight classification model training method and device, a medium and equipment. The method comprises the following steps: collecting first text data with a classification label and second text data without a classification label; according to the first text data, training a large-scale language model to obtain a training convergent large-scale language model; inputting the second text data into the large-scale language model to obtain a classification label corresponding to the second text data, and labeling the second text data by using the classification label; and training a lightweight classification model on the edge device according to the labeled second text data. According to the embodiment of the invention, the problem that more accurate text classification is difficult to realize due to less marked data in a small scene is solved based on the existing large-scale language model. And meanwhile, the lightweight classification model has the advantage of real-time response.</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZAj0yUzPKClPBZEKyTmJxcWZaZnJiSWZ-XkKufkpqTkKJUWJmXmZeekKuaklGfkpCol5KQopqWWZyak6QKGUzNJcsFBqYWlmQW5qXgkPA2taYk5xKi-U5mZQdHMNcfbQTS3Ij08tLkhMTs1LLYl39jM0NLM0NzUzMnE0JkYNAAjnN_8</recordid><startdate>20231031</startdate><enddate>20231031</enddate><creator>ZHANG ZHENG</creator><creator>CHANG BINGXIN</creator><creator>HUANG DENGRONG</creator><creator>YUE AIZHEN</creator><scope>EVB</scope></search><sort><creationdate>20231031</creationdate><title>Lightweight classification model training method and device, medium and equipment</title><author>ZHANG ZHENG ; CHANG BINGXIN ; HUANG DENGRONG ; YUE AIZHEN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116975624A3</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>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>ZHANG ZHENG</creatorcontrib><creatorcontrib>CHANG BINGXIN</creatorcontrib><creatorcontrib>HUANG DENGRONG</creatorcontrib><creatorcontrib>YUE AIZHEN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHANG ZHENG</au><au>CHANG BINGXIN</au><au>HUANG DENGRONG</au><au>YUE AIZHEN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Lightweight classification model training method and device, medium and equipment</title><date>2023-10-31</date><risdate>2023</risdate><abstract>The invention provides a lightweight classification model training method and device, a medium and equipment. The method comprises the following steps: collecting first text data with a classification label and second text data without a classification label; according to the first text data, training a large-scale language model to obtain a training convergent large-scale language model; inputting the second text data into the large-scale language model to obtain a classification label corresponding to the second text data, and labeling the second text data by using the classification label; and training a lightweight classification model on the edge device according to the labeled second text data. According to the embodiment of the invention, the problem that more accurate text classification is difficult to realize due to less marked data in a small scene is solved based on the existing large-scale language model. And meanwhile, the lightweight classification model has the advantage of real-time response.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN116975624A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title Lightweight classification model training method and device, medium and equipment
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T20%3A08%3A08IST&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%20ZHENG&rft.date=2023-10-31&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116975624A%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