Text2SQL semantic parsing method for domain large language model
The invention discloses a Text2SQL semantic parsing method oriented to a domain large language model. The method comprises the following steps: S1, connecting a domain database and storing database mode information; s2, constructing a knowledge base based on the domain database and the domain backgr...
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 | YU DONGJIN ZHONG YONGJUN QU GUANHUA WANG SIXUAN XU FANG |
| description | The invention discloses a Text2SQL semantic parsing method oriented to a domain large language model. The method comprises the following steps: S1, connecting a domain database and storing database mode information; s2, constructing a knowledge base based on the domain database and the domain background knowledge, and mounting the knowledge base into the large language model; s3, generating a Text-SQL (Structured Query Language) data set on the basis of an SQL-to-Text model; s4, performing fine adjustment, evaluation and optimization on the large language model by using the Text-SQL data set, and constructing a high-performance Text 2Sql model; s5, inputting a natural language question and optimizing the natural language question based on Prompt and a domain knowledge base; and S6, analyzing semantics through a Text2Sql model, and designing a Prompt reasoning result based on requirements. According to the method, natural language problem input is optimized based on Prompt, pre-training and fine tuning are car |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118377796A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118377796A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118377796A3</originalsourceid><addsrcrecordid>eNrjZHAISa0oMQoO9FEoTs1NzCvJTFYoSCwqzsxLV8hNLcnIT1FIyy9SSMnPTczMU8hJLEpPBZJ56aWJQEZufkpqDg8Da1piTnEqL5TmZlB0cw1x9tBNLciPTy0uSExOzUstiXf2MzS0MDY3N7c0czQmRg0AkhAw-A</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Text2SQL semantic parsing method for domain large language model</title><source>esp@cenet</source><creator>YU DONGJIN ; ZHONG YONGJUN ; QU GUANHUA ; WANG SIXUAN ; XU FANG</creator><creatorcontrib>YU DONGJIN ; ZHONG YONGJUN ; QU GUANHUA ; WANG SIXUAN ; XU FANG</creatorcontrib><description>The invention discloses a Text2SQL semantic parsing method oriented to a domain large language model. The method comprises the following steps: S1, connecting a domain database and storing database mode information; s2, constructing a knowledge base based on the domain database and the domain background knowledge, and mounting the knowledge base into the large language model; s3, generating a Text-SQL (Structured Query Language) data set on the basis of an SQL-to-Text model; s4, performing fine adjustment, evaluation and optimization on the large language model by using the Text-SQL data set, and constructing a high-performance Text 2Sql model; s5, inputting a natural language question and optimizing the natural language question based on Prompt and a domain knowledge base; and S6, analyzing semantics through a Text2Sql model, and designing a Prompt reasoning result based on requirements. According to the method, natural language problem input is optimized based on Prompt, pre-training and fine tuning are car</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=20240723&DB=EPODOC&CC=CN&NR=118377796A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240723&DB=EPODOC&CC=CN&NR=118377796A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>YU DONGJIN</creatorcontrib><creatorcontrib>ZHONG YONGJUN</creatorcontrib><creatorcontrib>QU GUANHUA</creatorcontrib><creatorcontrib>WANG SIXUAN</creatorcontrib><creatorcontrib>XU FANG</creatorcontrib><title>Text2SQL semantic parsing method for domain large language model</title><description>The invention discloses a Text2SQL semantic parsing method oriented to a domain large language model. The method comprises the following steps: S1, connecting a domain database and storing database mode information; s2, constructing a knowledge base based on the domain database and the domain background knowledge, and mounting the knowledge base into the large language model; s3, generating a Text-SQL (Structured Query Language) data set on the basis of an SQL-to-Text model; s4, performing fine adjustment, evaluation and optimization on the large language model by using the Text-SQL data set, and constructing a high-performance Text 2Sql model; s5, inputting a natural language question and optimizing the natural language question based on Prompt and a domain knowledge base; and S6, analyzing semantics through a Text2Sql model, and designing a Prompt reasoning result based on requirements. According to the method, natural language problem input is optimized based on Prompt, pre-training and fine tuning are car</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>eNrjZHAISa0oMQoO9FEoTs1NzCvJTFYoSCwqzsxLV8hNLcnIT1FIyy9SSMnPTczMU8hJLEpPBZJ56aWJQEZufkpqDg8Da1piTnEqL5TmZlB0cw1x9tBNLciPTy0uSExOzUstiXf2MzS0MDY3N7c0czQmRg0AkhAw-A</recordid><startdate>20240723</startdate><enddate>20240723</enddate><creator>YU DONGJIN</creator><creator>ZHONG YONGJUN</creator><creator>QU GUANHUA</creator><creator>WANG SIXUAN</creator><creator>XU FANG</creator><scope>EVB</scope></search><sort><creationdate>20240723</creationdate><title>Text2SQL semantic parsing method for domain large language model</title><author>YU DONGJIN ; ZHONG YONGJUN ; QU GUANHUA ; WANG SIXUAN ; XU FANG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118377796A3</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>YU DONGJIN</creatorcontrib><creatorcontrib>ZHONG YONGJUN</creatorcontrib><creatorcontrib>QU GUANHUA</creatorcontrib><creatorcontrib>WANG SIXUAN</creatorcontrib><creatorcontrib>XU FANG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>YU DONGJIN</au><au>ZHONG YONGJUN</au><au>QU GUANHUA</au><au>WANG SIXUAN</au><au>XU FANG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Text2SQL semantic parsing method for domain large language model</title><date>2024-07-23</date><risdate>2024</risdate><abstract>The invention discloses a Text2SQL semantic parsing method oriented to a domain large language model. The method comprises the following steps: S1, connecting a domain database and storing database mode information; s2, constructing a knowledge base based on the domain database and the domain background knowledge, and mounting the knowledge base into the large language model; s3, generating a Text-SQL (Structured Query Language) data set on the basis of an SQL-to-Text model; s4, performing fine adjustment, evaluation and optimization on the large language model by using the Text-SQL data set, and constructing a high-performance Text 2Sql model; s5, inputting a natural language question and optimizing the natural language question based on Prompt and a domain knowledge base; and S6, analyzing semantics through a Text2Sql model, and designing a Prompt reasoning result based on requirements. According to the method, natural language problem input is optimized based on Prompt, pre-training and fine tuning are car</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN118377796A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | Text2SQL semantic parsing method for domain large language model |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T12%3A08%3A43IST&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=YU%20DONGJIN&rft.date=2024-07-23&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118377796A%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 |