Missed word detection method and system based on fine tuning generative adversarial network model
The invention provides a missed word detection method and system based on a fine tuning generative adversarial network model. A to-be-detected text corpus is preprocessed to form a sequence composed of a plurality of segmented words, the segmented words in the sequence are read as embedded vectors a...
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 | SHEN XIN LAN JIANMIN |
| description | The invention provides a missed word detection method and system based on a fine tuning generative adversarial network model. A to-be-detected text corpus is preprocessed to form a sequence composed of a plurality of segmented words, the segmented words in the sequence are read as embedded vectors according to an ERNIE word list, the embedded vectors of the plurality of segmented words form a vector sequence Eseq, and the vector sequence Eseq is stored in the ERNIE word list; adopting a distance formula to calculate the distance between the generation sequence and the standard sequence as a threshold value, preprocessing the to-be-detected sequence to obtain a to-be-detected input sequence, inputting the to-be-detected input sequence into the generation network to obtain a to-be-detected generation sequence, and comparing the distance between the to-be-detected generation sequence and the standard sequence with the threshold value; if the threshold value is greater than the threshold value, the missing word e |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN113743110A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN113743110A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN113743110A3</originalsourceid><addsrcrecordid>eNqNjDEKwkAQRdNYiHqH8QCCSwRrCYqNVvZhzPzEJclu2Bkj3t4IHsDqFe_x5hlfvCqEXjEJCQyV-Riohz2iEAchfauhpzt_s0nVPoDsGXxoqEFAYvMjiGVEUk6eOwqw6ddSHwXdMpvV3ClWPy6y9el4K84bDLGEDlxNEyuLq3P5fpc7tz3k_zQfKiM98Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Missed word detection method and system based on fine tuning generative adversarial network model</title><source>esp@cenet</source><creator>SHEN XIN ; LAN JIANMIN</creator><creatorcontrib>SHEN XIN ; LAN JIANMIN</creatorcontrib><description>The invention provides a missed word detection method and system based on a fine tuning generative adversarial network model. A to-be-detected text corpus is preprocessed to form a sequence composed of a plurality of segmented words, the segmented words in the sequence are read as embedded vectors according to an ERNIE word list, the embedded vectors of the plurality of segmented words form a vector sequence Eseq, and the vector sequence Eseq is stored in the ERNIE word list; adopting a distance formula to calculate the distance between the generation sequence and the standard sequence as a threshold value, preprocessing the to-be-detected sequence to obtain a to-be-detected input sequence, inputting the to-be-detected input sequence into the generation network to obtain a to-be-detected generation sequence, and comparing the distance between the to-be-detected generation sequence and the standard sequence with the threshold value; if the threshold value is greater than the threshold value, the missing word e</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2021</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=20211203&DB=EPODOC&CC=CN&NR=113743110A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,777,882,25545,76296</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20211203&DB=EPODOC&CC=CN&NR=113743110A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SHEN XIN</creatorcontrib><creatorcontrib>LAN JIANMIN</creatorcontrib><title>Missed word detection method and system based on fine tuning generative adversarial network model</title><description>The invention provides a missed word detection method and system based on a fine tuning generative adversarial network model. A to-be-detected text corpus is preprocessed to form a sequence composed of a plurality of segmented words, the segmented words in the sequence are read as embedded vectors according to an ERNIE word list, the embedded vectors of the plurality of segmented words form a vector sequence Eseq, and the vector sequence Eseq is stored in the ERNIE word list; adopting a distance formula to calculate the distance between the generation sequence and the standard sequence as a threshold value, preprocessing the to-be-detected sequence to obtain a to-be-detected input sequence, inputting the to-be-detected input sequence into the generation network to obtain a to-be-detected generation sequence, and comparing the distance between the to-be-detected generation sequence and the standard sequence with the threshold value; if the threshold value is greater than the threshold value, the missing word e</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>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjDEKwkAQRdNYiHqH8QCCSwRrCYqNVvZhzPzEJclu2Bkj3t4IHsDqFe_x5hlfvCqEXjEJCQyV-Riohz2iEAchfauhpzt_s0nVPoDsGXxoqEFAYvMjiGVEUk6eOwqw6ddSHwXdMpvV3ClWPy6y9el4K84bDLGEDlxNEyuLq3P5fpc7tz3k_zQfKiM98Q</recordid><startdate>20211203</startdate><enddate>20211203</enddate><creator>SHEN XIN</creator><creator>LAN JIANMIN</creator><scope>EVB</scope></search><sort><creationdate>20211203</creationdate><title>Missed word detection method and system based on fine tuning generative adversarial network model</title><author>SHEN XIN ; LAN JIANMIN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN113743110A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2021</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>SHEN XIN</creatorcontrib><creatorcontrib>LAN JIANMIN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SHEN XIN</au><au>LAN JIANMIN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Missed word detection method and system based on fine tuning generative adversarial network model</title><date>2021-12-03</date><risdate>2021</risdate><abstract>The invention provides a missed word detection method and system based on a fine tuning generative adversarial network model. A to-be-detected text corpus is preprocessed to form a sequence composed of a plurality of segmented words, the segmented words in the sequence are read as embedded vectors according to an ERNIE word list, the embedded vectors of the plurality of segmented words form a vector sequence Eseq, and the vector sequence Eseq is stored in the ERNIE word list; adopting a distance formula to calculate the distance between the generation sequence and the standard sequence as a threshold value, preprocessing the to-be-detected sequence to obtain a to-be-detected input sequence, inputting the to-be-detected input sequence into the generation network to obtain a to-be-detected generation sequence, and comparing the distance between the to-be-detected generation sequence and the standard sequence with the threshold value; if the threshold value is greater than the threshold value, the missing word e</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN113743110A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | Missed word detection method and system based on fine tuning generative adversarial network model |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-21T07%3A04%3A49IST&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=SHEN%20XIN&rft.date=2021-12-03&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN113743110A%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 |