Evaluation method for model generation text and computer equipment

Evaluation method for model generation text and computer equipment

The invention discloses a model generation text evaluation method and computer equipment, which do not depend on labels and are suitable for a production environment. According to the evaluation method, evaluation is carried out through three indexes of genes, readability and fingerprints, and then...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: FENG HAOGUO, YAN CHANGCHUN, PEI FEI, FAN EMEI, XU QINGWEI
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
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 FENG HAOGUO
YAN CHANGCHUN
PEI FEI
FAN EMEI
XU QINGWEI
description The invention discloses a model generation text evaluation method and computer equipment, which do not depend on labels and are suitable for a production environment. According to the evaluation method, evaluation is carried out through three indexes of genes, readability and fingerprints, and then comprehensive evaluation is carried out. Wherein the gene index is used for measuring semantic correlation and homology of the model generation text and the input text, and the readability index is used for measuring the degree that the model generation text can be read by people according to the length mean value of sentences segmented from punctuations and the text repetition degradation condition. The fingerprint index is used for measuring the semantic feature distribution consistency degree of the model generation text and the training set label; specifically, a fingerprint extraction network model is trained in advance based on a ternary twin network, a fingerprint database is generated at the same time, then
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116776868A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116776868A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116776868A3</originalsourceid><addsrcrecordid>eNrjZHByLUvMKU0syczPU8hNLcnIT1FIyy9SyM1PSc1RSE_NSy2CyJWkVpQoJOalKCTn5xaUlqQWKaQWlmYW5KbmlfAwsKYl5hSn8kJpbgZFN9cQZw_d1IL8-NTigsRkoDEl8c5-hoZm5uZmFmYWjsbEqAEAdksyqQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Evaluation method for model generation text and computer equipment</title><source>esp@cenet</source><creator>FENG HAOGUO ; YAN CHANGCHUN ; PEI FEI ; FAN EMEI ; XU QINGWEI</creator><creatorcontrib>FENG HAOGUO ; YAN CHANGCHUN ; PEI FEI ; FAN EMEI ; XU QINGWEI</creatorcontrib><description>The invention discloses a model generation text evaluation method and computer equipment, which do not depend on labels and are suitable for a production environment. According to the evaluation method, evaluation is carried out through three indexes of genes, readability and fingerprints, and then comprehensive evaluation is carried out. Wherein the gene index is used for measuring semantic correlation and homology of the model generation text and the input text, and the readability index is used for measuring the degree that the model generation text can be read by people according to the length mean value of sentences segmented from punctuations and the text repetition degradation condition. The fingerprint index is used for measuring the semantic feature distribution consistency degree of the model generation text and the training set label; specifically, a fingerprint extraction network model is trained in advance based on a ternary twin network, a fingerprint database is generated at the same time, then</description><language>chi ; eng</language><subject>CALCULATING ; 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=20230919&amp;DB=EPODOC&amp;CC=CN&amp;NR=116776868A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230919&amp;DB=EPODOC&amp;CC=CN&amp;NR=116776868A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>FENG HAOGUO</creatorcontrib><creatorcontrib>YAN CHANGCHUN</creatorcontrib><creatorcontrib>PEI FEI</creatorcontrib><creatorcontrib>FAN EMEI</creatorcontrib><creatorcontrib>XU QINGWEI</creatorcontrib><title>Evaluation method for model generation text and computer equipment</title><description>The invention discloses a model generation text evaluation method and computer equipment, which do not depend on labels and are suitable for a production environment. According to the evaluation method, evaluation is carried out through three indexes of genes, readability and fingerprints, and then comprehensive evaluation is carried out. Wherein the gene index is used for measuring semantic correlation and homology of the model generation text and the input text, and the readability index is used for measuring the degree that the model generation text can be read by people according to the length mean value of sentences segmented from punctuations and the text repetition degradation condition. The fingerprint index is used for measuring the semantic feature distribution consistency degree of the model generation text and the training set label; specifically, a fingerprint extraction network model is trained in advance based on a ternary twin network, a fingerprint database is generated at the same time, then</description><subject>CALCULATING</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>eNrjZHByLUvMKU0syczPU8hNLcnIT1FIyy9SyM1PSc1RSE_NSy2CyJWkVpQoJOalKCTn5xaUlqQWKaQWlmYW5KbmlfAwsKYl5hSn8kJpbgZFN9cQZw_d1IL8-NTigsRkoDEl8c5-hoZm5uZmFmYWjsbEqAEAdksyqQ</recordid><startdate>20230919</startdate><enddate>20230919</enddate><creator>FENG HAOGUO</creator><creator>YAN CHANGCHUN</creator><creator>PEI FEI</creator><creator>FAN EMEI</creator><creator>XU QINGWEI</creator><scope>EVB</scope></search><sort><creationdate>20230919</creationdate><title>Evaluation method for model generation text and computer equipment</title><author>FENG HAOGUO ; YAN CHANGCHUN ; PEI FEI ; FAN EMEI ; XU QINGWEI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116776868A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>FENG HAOGUO</creatorcontrib><creatorcontrib>YAN CHANGCHUN</creatorcontrib><creatorcontrib>PEI FEI</creatorcontrib><creatorcontrib>FAN EMEI</creatorcontrib><creatorcontrib>XU QINGWEI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>FENG HAOGUO</au><au>YAN CHANGCHUN</au><au>PEI FEI</au><au>FAN EMEI</au><au>XU QINGWEI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Evaluation method for model generation text and computer equipment</title><date>2023-09-19</date><risdate>2023</risdate><abstract>The invention discloses a model generation text evaluation method and computer equipment, which do not depend on labels and are suitable for a production environment. According to the evaluation method, evaluation is carried out through three indexes of genes, readability and fingerprints, and then comprehensive evaluation is carried out. Wherein the gene index is used for measuring semantic correlation and homology of the model generation text and the input text, and the readability index is used for measuring the degree that the model generation text can be read by people according to the length mean value of sentences segmented from punctuations and the text repetition degradation condition. The fingerprint index is used for measuring the semantic feature distribution consistency degree of the model generation text and the training set label; specifically, a fingerprint extraction network model is trained in advance based on a ternary twin network, a fingerprint database is generated at the same time, then</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN116776868A
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title Evaluation method for model generation text and computer equipment
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T06%3A21%3A31IST&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=FENG%20HAOGUO&rft.date=2023-09-19&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116776868A%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