Virtual expert analysis method and device based on big language model intention recognition
The invention relates to a virtual expert analysis method and device based on big language model intention recognition, electronic equipment and a computer readable medium. The method comprises the steps of obtaining a query request generated by a user based on a natural language; performing intenti...
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 | SONG RONGXIN LEI CHAIWEI NI SIYONG WANG HAIFENG HUANG JIANTING |
description | The invention relates to a virtual expert analysis method and device based on big language model intention recognition, electronic equipment and a computer readable medium. The method comprises the steps of obtaining a query request generated by a user based on a natural language; performing intention recognition on the query request, and performing query in at least one pre-generated SQL index database in combination with a large language model based on an intention recognition result to generate an SQL index query result; determining an SQL script and chart data according to the SQL query result; extracting the splicing template and the corresponding business data; splicing the SQL script, the chart data and the business data according to the splicing template to generate a virtual expert pre-report; performing natural language processing on the virtual expert pre-report to extract keywords; and performing data insight analysis and generating a display chart by combining the big language model again accordi |
format | Patent |
fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117931834A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117931834A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117931834A3</originalsourceid><addsrcrecordid>eNqNijEKwkAQRdNYiHqH8QAWywpqKUGxshIbizDJfteBzWzIbkRvbwQPYPXf4_1pcbtKnwcOhFeHPhMrh3eSRC3yI7rRHTk8pQHVnOAoKtXiKbD6gT2ojQ6BRDM0yxh7NNGrfHleTO4cEha_nRXL4-FSnlboYoXUcQNFrsqzMZudNVu73tt_Ph-C3zuv</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Virtual expert analysis method and device based on big language model intention recognition</title><source>esp@cenet</source><creator>SONG RONGXIN ; LEI CHAIWEI ; NI SIYONG ; WANG HAIFENG ; HUANG JIANTING</creator><creatorcontrib>SONG RONGXIN ; LEI CHAIWEI ; NI SIYONG ; WANG HAIFENG ; HUANG JIANTING</creatorcontrib><description>The invention relates to a virtual expert analysis method and device based on big language model intention recognition, electronic equipment and a computer readable medium. The method comprises the steps of obtaining a query request generated by a user based on a natural language; performing intention recognition on the query request, and performing query in at least one pre-generated SQL index database in combination with a large language model based on an intention recognition result to generate an SQL index query result; determining an SQL script and chart data according to the SQL query result; extracting the splicing template and the corresponding business data; splicing the SQL script, the chart data and the business data according to the splicing template to generate a virtual expert pre-report; performing natural language processing on the virtual expert pre-report to extract keywords; and performing data insight analysis and generating a display chart by combining the big language model again accordi</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&date=20240426&DB=EPODOC&CC=CN&NR=117931834A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25563,76418</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240426&DB=EPODOC&CC=CN&NR=117931834A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SONG RONGXIN</creatorcontrib><creatorcontrib>LEI CHAIWEI</creatorcontrib><creatorcontrib>NI SIYONG</creatorcontrib><creatorcontrib>WANG HAIFENG</creatorcontrib><creatorcontrib>HUANG JIANTING</creatorcontrib><title>Virtual expert analysis method and device based on big language model intention recognition</title><description>The invention relates to a virtual expert analysis method and device based on big language model intention recognition, electronic equipment and a computer readable medium. The method comprises the steps of obtaining a query request generated by a user based on a natural language; performing intention recognition on the query request, and performing query in at least one pre-generated SQL index database in combination with a large language model based on an intention recognition result to generate an SQL index query result; determining an SQL script and chart data according to the SQL query result; extracting the splicing template and the corresponding business data; splicing the SQL script, the chart data and the business data according to the splicing template to generate a virtual expert pre-report; performing natural language processing on the virtual expert pre-report to extract keywords; and performing data insight analysis and generating a display chart by combining the big language model again accordi</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>eNqNijEKwkAQRdNYiHqH8QAWywpqKUGxshIbizDJfteBzWzIbkRvbwQPYPXf4_1pcbtKnwcOhFeHPhMrh3eSRC3yI7rRHTk8pQHVnOAoKtXiKbD6gT2ojQ6BRDM0yxh7NNGrfHleTO4cEha_nRXL4-FSnlboYoXUcQNFrsqzMZudNVu73tt_Ph-C3zuv</recordid><startdate>20240426</startdate><enddate>20240426</enddate><creator>SONG RONGXIN</creator><creator>LEI CHAIWEI</creator><creator>NI SIYONG</creator><creator>WANG HAIFENG</creator><creator>HUANG JIANTING</creator><scope>EVB</scope></search><sort><creationdate>20240426</creationdate><title>Virtual expert analysis method and device based on big language model intention recognition</title><author>SONG RONGXIN ; LEI CHAIWEI ; NI SIYONG ; WANG HAIFENG ; HUANG JIANTING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117931834A3</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>SONG RONGXIN</creatorcontrib><creatorcontrib>LEI CHAIWEI</creatorcontrib><creatorcontrib>NI SIYONG</creatorcontrib><creatorcontrib>WANG HAIFENG</creatorcontrib><creatorcontrib>HUANG JIANTING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SONG RONGXIN</au><au>LEI CHAIWEI</au><au>NI SIYONG</au><au>WANG HAIFENG</au><au>HUANG JIANTING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Virtual expert analysis method and device based on big language model intention recognition</title><date>2024-04-26</date><risdate>2024</risdate><abstract>The invention relates to a virtual expert analysis method and device based on big language model intention recognition, electronic equipment and a computer readable medium. The method comprises the steps of obtaining a query request generated by a user based on a natural language; performing intention recognition on the query request, and performing query in at least one pre-generated SQL index database in combination with a large language model based on an intention recognition result to generate an SQL index query result; determining an SQL script and chart data according to the SQL query result; extracting the splicing template and the corresponding business data; splicing the SQL script, the chart data and the business data according to the splicing template to generate a virtual expert pre-report; performing natural language processing on the virtual expert pre-report to extract keywords; and performing data insight analysis and generating a display chart by combining the big language model again accordi</abstract><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | |
ispartof | |
issn | |
language | chi ; eng |
recordid | cdi_epo_espacenet_CN117931834A |
source | esp@cenet |
subjects | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
title | Virtual expert analysis method and device based on big language model intention recognition |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T11%3A45%3A19IST&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=SONG%20RONGXIN&rft.date=2024-04-26&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117931834A%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 |