Text bidirectional relation extraction method and system based on mixed deep relation matrix
The invention discloses a text bidirectional relation extraction method and system based on a mixed deep relation matrix. The method comprises the following steps: acquiring text data; inputting the text data into a pre-trained Bert model for word segmentation coding, and generating word vectors of...
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 | ZOU QINGZHI ZHANG RONGHUAN ZHAO JING CHEN LING HU YUSHUAI |
| description | The invention discloses a text bidirectional relation extraction method and system based on a mixed deep relation matrix. The method comprises the following steps: acquiring text data; inputting the text data into a pre-trained Bert model for word segmentation coding, and generating word vectors of the text data; the method comprises the following steps: inputting word vectors of text data into a text bidirectional relation extraction model based on a mixed deep relation matrix, and firstly, respectively extracting subject and object pair word vectors from a subject-to-object direction and a subject-to-object direction through a subject and object pair bidirectional extraction module; the extracted subject-object pair word vectors and the word vectors of the text data jointly pass through an RE module based on a relation extraction matrix, subjects, objects and relations of the word vectors in the text data are distributed, and finally entity relation triples of the subjects, the objects and the relations in |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117035086A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117035086A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117035086A3</originalsourceid><addsrcrecordid>eNrjZIgJSa0oUUjKTMksSk0uyczPS8xRKErNSQQxFYBSRYlgUYXc1JKM_BSFxLwUheLK4pLUXIWkxOLUFAWQVGYFkJGSmlqA0JmbWFKUWcHDwJqWmFOcyguluRkU3VxDnD10Uwvy41OLCxKTU_NSS-Kd_QwNzQ2MTQ0szByNiVEDAPUzPDs</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Text bidirectional relation extraction method and system based on mixed deep relation matrix</title><source>esp@cenet</source><creator>ZOU QINGZHI ; ZHANG RONGHUAN ; ZHAO JING ; CHEN LING ; HU YUSHUAI</creator><creatorcontrib>ZOU QINGZHI ; ZHANG RONGHUAN ; ZHAO JING ; CHEN LING ; HU YUSHUAI</creatorcontrib><description>The invention discloses a text bidirectional relation extraction method and system based on a mixed deep relation matrix. The method comprises the following steps: acquiring text data; inputting the text data into a pre-trained Bert model for word segmentation coding, and generating word vectors of the text data; the method comprises the following steps: inputting word vectors of text data into a text bidirectional relation extraction model based on a mixed deep relation matrix, and firstly, respectively extracting subject and object pair word vectors from a subject-to-object direction and a subject-to-object direction through a subject and object pair bidirectional extraction module; the extracted subject-object pair word vectors and the word vectors of the text data jointly pass through an RE module based on a relation extraction matrix, subjects, objects and relations of the word vectors in the text data are distributed, and finally entity relation triples of the subjects, the objects and the relations in</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&date=20231110&DB=EPODOC&CC=CN&NR=117035086A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,309,781,886,25569,76552</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20231110&DB=EPODOC&CC=CN&NR=117035086A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZOU QINGZHI</creatorcontrib><creatorcontrib>ZHANG RONGHUAN</creatorcontrib><creatorcontrib>ZHAO JING</creatorcontrib><creatorcontrib>CHEN LING</creatorcontrib><creatorcontrib>HU YUSHUAI</creatorcontrib><title>Text bidirectional relation extraction method and system based on mixed deep relation matrix</title><description>The invention discloses a text bidirectional relation extraction method and system based on a mixed deep relation matrix. The method comprises the following steps: acquiring text data; inputting the text data into a pre-trained Bert model for word segmentation coding, and generating word vectors of the text data; the method comprises the following steps: inputting word vectors of text data into a text bidirectional relation extraction model based on a mixed deep relation matrix, and firstly, respectively extracting subject and object pair word vectors from a subject-to-object direction and a subject-to-object direction through a subject and object pair bidirectional extraction module; the extracted subject-object pair word vectors and the word vectors of the text data jointly pass through an RE module based on a relation extraction matrix, subjects, objects and relations of the word vectors in the text data are distributed, and finally entity relation triples of the subjects, the objects and the relations in</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>eNrjZIgJSa0oUUjKTMksSk0uyczPS8xRKErNSQQxFYBSRYlgUYXc1JKM_BSFxLwUheLK4pLUXIWkxOLUFAWQVGYFkJGSmlqA0JmbWFKUWcHDwJqWmFOcyguluRkU3VxDnD10Uwvy41OLCxKTU_NSS-Kd_QwNzQ2MTQ0szByNiVEDAPUzPDs</recordid><startdate>20231110</startdate><enddate>20231110</enddate><creator>ZOU QINGZHI</creator><creator>ZHANG RONGHUAN</creator><creator>ZHAO JING</creator><creator>CHEN LING</creator><creator>HU YUSHUAI</creator><scope>EVB</scope></search><sort><creationdate>20231110</creationdate><title>Text bidirectional relation extraction method and system based on mixed deep relation matrix</title><author>ZOU QINGZHI ; ZHANG RONGHUAN ; ZHAO JING ; CHEN LING ; HU YUSHUAI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117035086A3</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>ZOU QINGZHI</creatorcontrib><creatorcontrib>ZHANG RONGHUAN</creatorcontrib><creatorcontrib>ZHAO JING</creatorcontrib><creatorcontrib>CHEN LING</creatorcontrib><creatorcontrib>HU YUSHUAI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZOU QINGZHI</au><au>ZHANG RONGHUAN</au><au>ZHAO JING</au><au>CHEN LING</au><au>HU YUSHUAI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Text bidirectional relation extraction method and system based on mixed deep relation matrix</title><date>2023-11-10</date><risdate>2023</risdate><abstract>The invention discloses a text bidirectional relation extraction method and system based on a mixed deep relation matrix. The method comprises the following steps: acquiring text data; inputting the text data into a pre-trained Bert model for word segmentation coding, and generating word vectors of the text data; the method comprises the following steps: inputting word vectors of text data into a text bidirectional relation extraction model based on a mixed deep relation matrix, and firstly, respectively extracting subject and object pair word vectors from a subject-to-object direction and a subject-to-object direction through a subject and object pair bidirectional extraction module; the extracted subject-object pair word vectors and the word vectors of the text data jointly pass through an RE module based on a relation extraction matrix, subjects, objects and relations of the word vectors in the text data are distributed, and finally entity relation triples of the subjects, the objects and the relations in</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN117035086A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | Text bidirectional relation extraction method and system based on mixed deep relation matrix |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-12T15%3A51%3A04IST&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=ZOU%20QINGZHI&rft.date=2023-11-10&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117035086A%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 |