Method for optimizing large model in reading field based on fine tuning and method for generating reading accompanying manuscript
The invention discloses a reading field large model optimization method and a reading accompanying manuscript generation method based on fine tuning, and the method comprises the steps: obtaining a manuscript generation demand of a reading accompanying manuscript and a local corpus, the manuscript g...
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 | ZHANG CHEN ZHANG FANG LIM JIN-BAE GAO ANG REN AINA GAO FENG |
| description | The invention discloses a reading field large model optimization method and a reading accompanying manuscript generation method based on fine tuning, and the method comprises the steps: obtaining a manuscript generation demand of a reading accompanying manuscript and a local corpus, the manuscript generation demand being used for representing a requirement for generating the reading accompanying manuscript, and the local corpus being used for generating the reading accompanying manuscript; the local corpus is constructed based on reading accompanying text data in the field of children language; according to the manuscript generation requirement, parameters to be fine-tuned are determined from the large language model, and the parameters to be fine-tuned are partial parameters suitable for the manuscript generation requirement in the large language model; according to the training corpus and the to-be-fine-tuned parameters in the local corpus, the large language model is fine-tuned and optimized, and a pre-tra |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118760762A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118760762A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118760762A3</originalsourceid><addsrcrecordid>eNqNjDELwjAUhLs4iPofnj9AsAqtqxTFRSf38kxeayB5LyTpoJv_3AYUV6fj7ru7afE6U7qLhk4CiE_GmafhHiyGnsCJJguGIRDqHHeGrIYbRtIgPFomSANnhKzB_b56YgqYMvmOUSlxHvmRjUMeogrGp3kx6dBGWnx0ViyPh2tzWpGXlqJHNV6ltrmU5a6u1nW12W__6bwBcclJwg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Method for optimizing large model in reading field based on fine tuning and method for generating reading accompanying manuscript</title><source>esp@cenet</source><creator>ZHANG CHEN ; ZHANG FANG ; LIM JIN-BAE ; GAO ANG ; REN AINA ; GAO FENG</creator><creatorcontrib>ZHANG CHEN ; ZHANG FANG ; LIM JIN-BAE ; GAO ANG ; REN AINA ; GAO FENG</creatorcontrib><description>The invention discloses a reading field large model optimization method and a reading accompanying manuscript generation method based on fine tuning, and the method comprises the steps: obtaining a manuscript generation demand of a reading accompanying manuscript and a local corpus, the manuscript generation demand being used for representing a requirement for generating the reading accompanying manuscript, and the local corpus being used for generating the reading accompanying manuscript; the local corpus is constructed based on reading accompanying text data in the field of children language; according to the manuscript generation requirement, parameters to be fine-tuned are determined from the large language model, and the parameters to be fine-tuned are partial parameters suitable for the manuscript generation requirement in the large language model; according to the training corpus and the to-be-fine-tuned parameters in the local corpus, the large language model is fine-tuned and optimized, and a pre-tra</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; 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=20241011&DB=EPODOC&CC=CN&NR=118760762A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20241011&DB=EPODOC&CC=CN&NR=118760762A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHANG CHEN</creatorcontrib><creatorcontrib>ZHANG FANG</creatorcontrib><creatorcontrib>LIM JIN-BAE</creatorcontrib><creatorcontrib>GAO ANG</creatorcontrib><creatorcontrib>REN AINA</creatorcontrib><creatorcontrib>GAO FENG</creatorcontrib><title>Method for optimizing large model in reading field based on fine tuning and method for generating reading accompanying manuscript</title><description>The invention discloses a reading field large model optimization method and a reading accompanying manuscript generation method based on fine tuning, and the method comprises the steps: obtaining a manuscript generation demand of a reading accompanying manuscript and a local corpus, the manuscript generation demand being used for representing a requirement for generating the reading accompanying manuscript, and the local corpus being used for generating the reading accompanying manuscript; the local corpus is constructed based on reading accompanying text data in the field of children language; according to the manuscript generation requirement, parameters to be fine-tuned are determined from the large language model, and the parameters to be fine-tuned are partial parameters suitable for the manuscript generation requirement in the large language model; according to the training corpus and the to-be-fine-tuned parameters in the local corpus, the large language model is fine-tuned and optimized, and a pre-tra</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>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjDELwjAUhLs4iPofnj9AsAqtqxTFRSf38kxeayB5LyTpoJv_3AYUV6fj7ru7afE6U7qLhk4CiE_GmafhHiyGnsCJJguGIRDqHHeGrIYbRtIgPFomSANnhKzB_b56YgqYMvmOUSlxHvmRjUMeogrGp3kx6dBGWnx0ViyPh2tzWpGXlqJHNV6ltrmU5a6u1nW12W__6bwBcclJwg</recordid><startdate>20241011</startdate><enddate>20241011</enddate><creator>ZHANG CHEN</creator><creator>ZHANG FANG</creator><creator>LIM JIN-BAE</creator><creator>GAO ANG</creator><creator>REN AINA</creator><creator>GAO FENG</creator><scope>EVB</scope></search><sort><creationdate>20241011</creationdate><title>Method for optimizing large model in reading field based on fine tuning and method for generating reading accompanying manuscript</title><author>ZHANG CHEN ; ZHANG FANG ; LIM JIN-BAE ; GAO ANG ; REN AINA ; GAO FENG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118760762A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</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 CHEN</creatorcontrib><creatorcontrib>ZHANG FANG</creatorcontrib><creatorcontrib>LIM JIN-BAE</creatorcontrib><creatorcontrib>GAO ANG</creatorcontrib><creatorcontrib>REN AINA</creatorcontrib><creatorcontrib>GAO FENG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHANG CHEN</au><au>ZHANG FANG</au><au>LIM JIN-BAE</au><au>GAO ANG</au><au>REN AINA</au><au>GAO FENG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Method for optimizing large model in reading field based on fine tuning and method for generating reading accompanying manuscript</title><date>2024-10-11</date><risdate>2024</risdate><abstract>The invention discloses a reading field large model optimization method and a reading accompanying manuscript generation method based on fine tuning, and the method comprises the steps: obtaining a manuscript generation demand of a reading accompanying manuscript and a local corpus, the manuscript generation demand being used for representing a requirement for generating the reading accompanying manuscript, and the local corpus being used for generating the reading accompanying manuscript; the local corpus is constructed based on reading accompanying text data in the field of children language; according to the manuscript generation requirement, parameters to be fine-tuned are determined from the large language model, and the parameters to be fine-tuned are partial parameters suitable for the manuscript generation requirement in the large language model; according to the training corpus and the to-be-fine-tuned parameters in the local corpus, the large language model is fine-tuned and optimized, and a pre-tra</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN118760762A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | Method for optimizing large model in reading field based on fine tuning and method for generating reading accompanying manuscript |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T06%3A26%3A46IST&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%20CHEN&rft.date=2024-10-11&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118760762A%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 |