Patent and thesis joining method and system, and storage medium
The invention belongs to the technical field of information processing, and particularly relates to a patent and thesis joining method and system and a storage medium. The connection method comprises the following steps: S1, performing translation deduplication, preprocessing and word segmentation p...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
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 | WANG ZUOCHENG WANG JIAN SUN XIN LV XIAOZHONG |
description | The invention belongs to the technical field of information processing, and particularly relates to a patent and thesis joining method and system and a storage medium. The connection method comprises the following steps: S1, performing translation deduplication, preprocessing and word segmentation processing on patent literatures to obtain corresponding patent word sequences; s2, label sequences corresponding to the patent word sequences are manually marked, a first training set is formed by the multiple patent word sequences and the corresponding label sequences, and after preliminary training is conducted on the basis of the first training set through a multi-label classification model, the label sequences of the patent word sequences are formally output through the multi-label classification model; s3, using a CRF model to output an optimal tag sequence corresponding to the current tag sequence based on the tag sequence of the current patent document; and S4, after the labels in the optimal label sequence |
format | Patent |
fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117891946A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117891946A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117891946A3</originalsourceid><addsrcrecordid>eNrjZLAPSCxJzStRSMxLUSjJSC3OLFbIys_My8xLV8hNLcnITwHLFFcWl6Tm6kDYJflFiempQOmUzNJcHgbWtMSc4lReKM3NoOjmGuLsoZtakB-fWlyQmJyal1oS7-xnaGhuYWloaWLmaEyMGgBqBjCt</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Patent and thesis joining method and system, and storage medium</title><source>esp@cenet</source><creator>WANG ZUOCHENG ; WANG JIAN ; SUN XIN ; LV XIAOZHONG</creator><creatorcontrib>WANG ZUOCHENG ; WANG JIAN ; SUN XIN ; LV XIAOZHONG</creatorcontrib><description>The invention belongs to the technical field of information processing, and particularly relates to a patent and thesis joining method and system and a storage medium. The connection method comprises the following steps: S1, performing translation deduplication, preprocessing and word segmentation processing on patent literatures to obtain corresponding patent word sequences; s2, label sequences corresponding to the patent word sequences are manually marked, a first training set is formed by the multiple patent word sequences and the corresponding label sequences, and after preliminary training is conducted on the basis of the first training set through a multi-label classification model, the label sequences of the patent word sequences are formally output through the multi-label classification model; s3, using a CRF model to output an optimal tag sequence corresponding to the current tag sequence based on the tag sequence of the current patent document; and S4, after the labels in the optimal label sequence</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; 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&date=20240416&DB=EPODOC&CC=CN&NR=117891946A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240416&DB=EPODOC&CC=CN&NR=117891946A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WANG ZUOCHENG</creatorcontrib><creatorcontrib>WANG JIAN</creatorcontrib><creatorcontrib>SUN XIN</creatorcontrib><creatorcontrib>LV XIAOZHONG</creatorcontrib><title>Patent and thesis joining method and system, and storage medium</title><description>The invention belongs to the technical field of information processing, and particularly relates to a patent and thesis joining method and system and a storage medium. The connection method comprises the following steps: S1, performing translation deduplication, preprocessing and word segmentation processing on patent literatures to obtain corresponding patent word sequences; s2, label sequences corresponding to the patent word sequences are manually marked, a first training set is formed by the multiple patent word sequences and the corresponding label sequences, and after preliminary training is conducted on the basis of the first training set through a multi-label classification model, the label sequences of the patent word sequences are formally output through the multi-label classification model; s3, using a CRF model to output an optimal tag sequence corresponding to the current tag sequence based on the tag sequence of the current patent document; and S4, after the labels in the optimal label sequence</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>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLAPSCxJzStRSMxLUSjJSC3OLFbIys_My8xLV8hNLcnITwHLFFcWl6Tm6kDYJflFiempQOmUzNJcHgbWtMSc4lReKM3NoOjmGuLsoZtakB-fWlyQmJyal1oS7-xnaGhuYWloaWLmaEyMGgBqBjCt</recordid><startdate>20240416</startdate><enddate>20240416</enddate><creator>WANG ZUOCHENG</creator><creator>WANG JIAN</creator><creator>SUN XIN</creator><creator>LV XIAOZHONG</creator><scope>EVB</scope></search><sort><creationdate>20240416</creationdate><title>Patent and thesis joining method and system, and storage medium</title><author>WANG ZUOCHENG ; WANG JIAN ; SUN XIN ; LV XIAOZHONG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117891946A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>WANG ZUOCHENG</creatorcontrib><creatorcontrib>WANG JIAN</creatorcontrib><creatorcontrib>SUN XIN</creatorcontrib><creatorcontrib>LV XIAOZHONG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WANG ZUOCHENG</au><au>WANG JIAN</au><au>SUN XIN</au><au>LV XIAOZHONG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Patent and thesis joining method and system, and storage medium</title><date>2024-04-16</date><risdate>2024</risdate><abstract>The invention belongs to the technical field of information processing, and particularly relates to a patent and thesis joining method and system and a storage medium. The connection method comprises the following steps: S1, performing translation deduplication, preprocessing and word segmentation processing on patent literatures to obtain corresponding patent word sequences; s2, label sequences corresponding to the patent word sequences are manually marked, a first training set is formed by the multiple patent word sequences and the corresponding label sequences, and after preliminary training is conducted on the basis of the first training set through a multi-label classification model, the label sequences of the patent word sequences are formally output through the multi-label classification model; s3, using a CRF model to output an optimal tag sequence corresponding to the current tag sequence based on the tag sequence of the current patent document; and S4, after the labels in the optimal label sequence</abstract><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | |
ispartof | |
issn | |
language | chi ; eng |
recordid | cdi_epo_espacenet_CN117891946A |
source | esp@cenet |
subjects | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
title | Patent and thesis joining method and system, 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=2025-02-05T13%3A07%3A40IST&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=WANG%20ZUOCHENG&rft.date=2024-04-16&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117891946A%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 |