Slot extraction method in multiple rounds of conversations, model training method and storage medium

The invention provides a slot extraction method in multi-round dialogues, a model training method and a storage medium, and the training method comprises the steps: obtaining first training data of a plurality of non-preset scene dialogues, obtaining a plurality of preset scene dialogues, and obtain...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: HAO ZHULIN, PI HUAIYU, JIANG XIAOLIN, LUO CHAO
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 HAO ZHULIN
PI HUAIYU
JIANG XIAOLIN
LUO CHAO
description The invention provides a slot extraction method in multi-round dialogues, a model training method and a storage medium, and the training method comprises the steps: obtaining first training data of a plurality of non-preset scene dialogues, obtaining a plurality of preset scene dialogues, and obtaining second training data of slot information corresponding to the preset scene dialogues, the preset large model is trained based on the first training data to obtain a pre-training model, the pre-training model is finely adjusted based on the second training data to obtain a slot position extraction model corresponding to the preset scene, and the slot position extraction model is used for slot position extraction of multiple rounds of conversations. According to the method, the large language model is trained through the non-preset scene dialogue and the preset scene dialogue, the robustness of the model is enhanced, accurate recognition of slot positions in multi-round dialogue scenes is achieved through fine ad
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117787292A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117787292A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117787292A3</originalsourceid><addsrcrecordid>eNqNi7EKAjEQBa-xEPUf1l6LO4toKYdiZaP9EZK9M5DshmQjfr4RtLd6w2Nm3tibZwF8SdJGHBMElAdbcJWKFxc9QuJCNgOPYJiemLL-mHkDgS16qKkjR9Mv1WQhCyc9Yb2sK2HZzEbtM66-u2jW59O9v2wx8oA5aoOEMvTXtlVqr7pDd9z947wBMb8_aw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Slot extraction method in multiple rounds of conversations, model training method and storage medium</title><source>esp@cenet</source><creator>HAO ZHULIN ; PI HUAIYU ; JIANG XIAOLIN ; LUO CHAO</creator><creatorcontrib>HAO ZHULIN ; PI HUAIYU ; JIANG XIAOLIN ; LUO CHAO</creatorcontrib><description>The invention provides a slot extraction method in multi-round dialogues, a model training method and a storage medium, and the training method comprises the steps: obtaining first training data of a plurality of non-preset scene dialogues, obtaining a plurality of preset scene dialogues, and obtaining second training data of slot information corresponding to the preset scene dialogues, the preset large model is trained based on the first training data to obtain a pre-training model, the pre-training model is finely adjusted based on the second training data to obtain a slot position extraction model corresponding to the preset scene, and the slot position extraction model is used for slot position extraction of multiple rounds of conversations. According to the method, the large language model is trained through the non-preset scene dialogue and the preset scene dialogue, the robustness of the model is enhanced, accurate recognition of slot positions in multi-round dialogue scenes is achieved through fine ad</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&amp;date=20240329&amp;DB=EPODOC&amp;CC=CN&amp;NR=117787292A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240329&amp;DB=EPODOC&amp;CC=CN&amp;NR=117787292A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>HAO ZHULIN</creatorcontrib><creatorcontrib>PI HUAIYU</creatorcontrib><creatorcontrib>JIANG XIAOLIN</creatorcontrib><creatorcontrib>LUO CHAO</creatorcontrib><title>Slot extraction method in multiple rounds of conversations, model training method and storage medium</title><description>The invention provides a slot extraction method in multi-round dialogues, a model training method and a storage medium, and the training method comprises the steps: obtaining first training data of a plurality of non-preset scene dialogues, obtaining a plurality of preset scene dialogues, and obtaining second training data of slot information corresponding to the preset scene dialogues, the preset large model is trained based on the first training data to obtain a pre-training model, the pre-training model is finely adjusted based on the second training data to obtain a slot position extraction model corresponding to the preset scene, and the slot position extraction model is used for slot position extraction of multiple rounds of conversations. According to the method, the large language model is trained through the non-preset scene dialogue and the preset scene dialogue, the robustness of the model is enhanced, accurate recognition of slot positions in multi-round dialogue scenes is achieved through fine ad</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>eNqNi7EKAjEQBa-xEPUf1l6LO4toKYdiZaP9EZK9M5DshmQjfr4RtLd6w2Nm3tibZwF8SdJGHBMElAdbcJWKFxc9QuJCNgOPYJiemLL-mHkDgS16qKkjR9Mv1WQhCyc9Yb2sK2HZzEbtM66-u2jW59O9v2wx8oA5aoOEMvTXtlVqr7pDd9z947wBMb8_aw</recordid><startdate>20240329</startdate><enddate>20240329</enddate><creator>HAO ZHULIN</creator><creator>PI HUAIYU</creator><creator>JIANG XIAOLIN</creator><creator>LUO CHAO</creator><scope>EVB</scope></search><sort><creationdate>20240329</creationdate><title>Slot extraction method in multiple rounds of conversations, model training method and storage medium</title><author>HAO ZHULIN ; PI HUAIYU ; JIANG XIAOLIN ; LUO CHAO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117787292A3</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>HAO ZHULIN</creatorcontrib><creatorcontrib>PI HUAIYU</creatorcontrib><creatorcontrib>JIANG XIAOLIN</creatorcontrib><creatorcontrib>LUO CHAO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>HAO ZHULIN</au><au>PI HUAIYU</au><au>JIANG XIAOLIN</au><au>LUO CHAO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Slot extraction method in multiple rounds of conversations, model training method and storage medium</title><date>2024-03-29</date><risdate>2024</risdate><abstract>The invention provides a slot extraction method in multi-round dialogues, a model training method and a storage medium, and the training method comprises the steps: obtaining first training data of a plurality of non-preset scene dialogues, obtaining a plurality of preset scene dialogues, and obtaining second training data of slot information corresponding to the preset scene dialogues, the preset large model is trained based on the first training data to obtain a pre-training model, the pre-training model is finely adjusted based on the second training data to obtain a slot position extraction model corresponding to the preset scene, and the slot position extraction model is used for slot position extraction of multiple rounds of conversations. According to the method, the large language model is trained through the non-preset scene dialogue and the preset scene dialogue, the robustness of the model is enhanced, accurate recognition of slot positions in multi-round dialogue scenes is achieved through fine ad</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN117787292A
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title Slot extraction method in multiple rounds of conversations, model training method 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=2025-01-26T16%3A04%3A35IST&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=HAO%20ZHULIN&rft.date=2024-03-29&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117787292A%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