Bridge detection report polishing method and system based on large language model
The invention relates to the technical field of intelligent algorithms, in particular to a bridge detection report polishing method and system based on a large language model, and the method specifically comprises the following steps: collecting report samples; different report template specificatio...
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 WEILEI WU HUAYONG JIA PENGFEI ZHAO RONGXIN XING YUN CAI JUEWEI ZHOU ZIJIE WANG XIAOYUN |
| description | The invention relates to the technical field of intelligent algorithms, in particular to a bridge detection report polishing method and system based on a large language model, and the method specifically comprises the following steps: collecting report samples; different report template specification libraries are constructed according to the element types of the bridge detection reports, and report samples are subjected to slice division according to the element types of the reports; reading a to-be-polished report text and an element type; calling a corresponding template specification library, filling the template specification text and the to-be-polished text into a preset cue word template, and constructing a model cue word; and selecting a large language model, inputting a constructed model cue word, and outputting a polishing result of the bridge inspection report. Compared with the prior art, the method has the advantages that different report template standard libraries are respectively constructed a |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117556798A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117556798A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117556798A3</originalsourceid><addsrcrecordid>eNqNjD0KwkAQRrexEPUO4wEsgsRoqUGxEgT7MGbGzcL-sTMW3t4tPIDV-4r3vbm5n4ojy0CsPKpLEQrnVBRy8k4mFy0E1ikRYCSQjygHeKIwQXU9lvr1GO0b6wiJ2C_N7IVeePXjwqwv50d_3dTuwJJx5Mg69Lem6dp21x32x-0_zhfeeDfE</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Bridge detection report polishing method and system based on large language model</title><source>esp@cenet</source><creator>YU WEILEI ; WU HUAYONG ; JIA PENGFEI ; ZHAO RONGXIN ; XING YUN ; CAI JUEWEI ; ZHOU ZIJIE ; WANG XIAOYUN</creator><creatorcontrib>YU WEILEI ; WU HUAYONG ; JIA PENGFEI ; ZHAO RONGXIN ; XING YUN ; CAI JUEWEI ; ZHOU ZIJIE ; WANG XIAOYUN</creatorcontrib><description>The invention relates to the technical field of intelligent algorithms, in particular to a bridge detection report polishing method and system based on a large language model, and the method specifically comprises the following steps: collecting report samples; different report template specification libraries are constructed according to the element types of the bridge detection reports, and report samples are subjected to slice division according to the element types of the reports; reading a to-be-polished report text and an element type; calling a corresponding template specification library, filling the template specification text and the to-be-polished text into a preset cue word template, and constructing a model cue word; and selecting a large language model, inputting a constructed model cue word, and outputting a polishing result of the bridge inspection report. Compared with the prior art, the method has the advantages that different report template standard libraries are respectively constructed a</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=20240213&DB=EPODOC&CC=CN&NR=117556798A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240213&DB=EPODOC&CC=CN&NR=117556798A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>YU WEILEI</creatorcontrib><creatorcontrib>WU HUAYONG</creatorcontrib><creatorcontrib>JIA PENGFEI</creatorcontrib><creatorcontrib>ZHAO RONGXIN</creatorcontrib><creatorcontrib>XING YUN</creatorcontrib><creatorcontrib>CAI JUEWEI</creatorcontrib><creatorcontrib>ZHOU ZIJIE</creatorcontrib><creatorcontrib>WANG XIAOYUN</creatorcontrib><title>Bridge detection report polishing method and system based on large language model</title><description>The invention relates to the technical field of intelligent algorithms, in particular to a bridge detection report polishing method and system based on a large language model, and the method specifically comprises the following steps: collecting report samples; different report template specification libraries are constructed according to the element types of the bridge detection reports, and report samples are subjected to slice division according to the element types of the reports; reading a to-be-polished report text and an element type; calling a corresponding template specification library, filling the template specification text and the to-be-polished text into a preset cue word template, and constructing a model cue word; and selecting a large language model, inputting a constructed model cue word, and outputting a polishing result of the bridge inspection report. Compared with the prior art, the method has the advantages that different report template standard libraries are respectively constructed a</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>eNqNjD0KwkAQRrexEPUO4wEsgsRoqUGxEgT7MGbGzcL-sTMW3t4tPIDV-4r3vbm5n4ojy0CsPKpLEQrnVBRy8k4mFy0E1ikRYCSQjygHeKIwQXU9lvr1GO0b6wiJ2C_N7IVeePXjwqwv50d_3dTuwJJx5Mg69Lem6dp21x32x-0_zhfeeDfE</recordid><startdate>20240213</startdate><enddate>20240213</enddate><creator>YU WEILEI</creator><creator>WU HUAYONG</creator><creator>JIA PENGFEI</creator><creator>ZHAO RONGXIN</creator><creator>XING YUN</creator><creator>CAI JUEWEI</creator><creator>ZHOU ZIJIE</creator><creator>WANG XIAOYUN</creator><scope>EVB</scope></search><sort><creationdate>20240213</creationdate><title>Bridge detection report polishing method and system based on large language model</title><author>YU WEILEI ; WU HUAYONG ; JIA PENGFEI ; ZHAO RONGXIN ; XING YUN ; CAI JUEWEI ; ZHOU ZIJIE ; WANG XIAOYUN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117556798A3</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>YU WEILEI</creatorcontrib><creatorcontrib>WU HUAYONG</creatorcontrib><creatorcontrib>JIA PENGFEI</creatorcontrib><creatorcontrib>ZHAO RONGXIN</creatorcontrib><creatorcontrib>XING YUN</creatorcontrib><creatorcontrib>CAI JUEWEI</creatorcontrib><creatorcontrib>ZHOU ZIJIE</creatorcontrib><creatorcontrib>WANG XIAOYUN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>YU WEILEI</au><au>WU HUAYONG</au><au>JIA PENGFEI</au><au>ZHAO RONGXIN</au><au>XING YUN</au><au>CAI JUEWEI</au><au>ZHOU ZIJIE</au><au>WANG XIAOYUN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Bridge detection report polishing method and system based on large language model</title><date>2024-02-13</date><risdate>2024</risdate><abstract>The invention relates to the technical field of intelligent algorithms, in particular to a bridge detection report polishing method and system based on a large language model, and the method specifically comprises the following steps: collecting report samples; different report template specification libraries are constructed according to the element types of the bridge detection reports, and report samples are subjected to slice division according to the element types of the reports; reading a to-be-polished report text and an element type; calling a corresponding template specification library, filling the template specification text and the to-be-polished text into a preset cue word template, and constructing a model cue word; and selecting a large language model, inputting a constructed model cue word, and outputting a polishing result of the bridge inspection report. Compared with the prior art, the method has the advantages that different report template standard libraries are respectively constructed a</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN117556798A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | Bridge detection report polishing method and system based on 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=2024-12-27T02%3A16%3A24IST&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%20WEILEI&rft.date=2024-02-13&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117556798A%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 |