Complex knowledge base question and answer oriented query graph generation method and system
The invention relates to a query graph generation method and system oriented to complex knowledge base questions and answers. The method comprises the steps that according to the semantic similarity between a target question and historical questions, the historical questions ranked in the top are sc...
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 | DAI JIAN TAO TIANYI HE QIBO CAO WEIJIE QUE YUNFEI XU JUN TANG SHUYANG GU BOYUAN ZHOU YUNFENG LIU ZHENGXIAO ZHANG YUFAN LI JINBO MIAO YE |
| description | The invention relates to a query graph generation method and system oriented to complex knowledge base questions and answers. The method comprises the steps that according to the semantic similarity between a target question and historical questions, the historical questions ranked in the top are screened out from historical cases; forming a case candidate relation set by the relations in the standard query graph corresponding to the screened historical questions; on the basis of the case candidate relation set, a search type semantic analysis method is adopted to generate a query graph; and converting the query graph into an executable query statement according to a grammar rule of a knowledge base query statement, and executing query on the knowledge base to obtain an answer to the target question. According to the method for remarkably reducing the retrieval space in the reasoning process through the historical cases, candidate relations obtained through retrieval are pre-screened, and the question answeri |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115858723A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115858723A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115858723A3</originalsourceid><addsrcrecordid>eNqNizsOwjAUBN1QIOAOjwNQhCgibWSBqKgokSKDlyTCP_yMQm5PiDgAxWqKnZmLi_Q2GLzp4XxvoBvQVTHo-QKnzjtSTo_jHpF87OAS9PeMAzVRhZYaOEQ1qRap9XoqeOAEuxSzuzKM1Y8LsT7sz_K4QfA1OKjbGKdanrKsKItyt82r_B_nA_n1PGg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Complex knowledge base question and answer oriented query graph generation method and system</title><source>esp@cenet</source><creator>DAI JIAN ; TAO TIANYI ; HE QIBO ; CAO WEIJIE ; QUE YUNFEI ; XU JUN ; TANG SHUYANG ; GU BOYUAN ; ZHOU YUNFENG ; LIU ZHENGXIAO ; ZHANG YUFAN ; LI JINBO ; MIAO YE</creator><creatorcontrib>DAI JIAN ; TAO TIANYI ; HE QIBO ; CAO WEIJIE ; QUE YUNFEI ; XU JUN ; TANG SHUYANG ; GU BOYUAN ; ZHOU YUNFENG ; LIU ZHENGXIAO ; ZHANG YUFAN ; LI JINBO ; MIAO YE</creatorcontrib><description>The invention relates to a query graph generation method and system oriented to complex knowledge base questions and answers. The method comprises the steps that according to the semantic similarity between a target question and historical questions, the historical questions ranked in the top are screened out from historical cases; forming a case candidate relation set by the relations in the standard query graph corresponding to the screened historical questions; on the basis of the case candidate relation set, a search type semantic analysis method is adopted to generate a query graph; and converting the query graph into an executable query statement according to a grammar rule of a knowledge base query statement, and executing query on the knowledge base to obtain an answer to the target question. According to the method for remarkably reducing the retrieval space in the reasoning process through the historical cases, candidate relations obtained through retrieval are pre-screened, and the question answeri</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2023</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=20230328&DB=EPODOC&CC=CN&NR=115858723A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25563,76418</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230328&DB=EPODOC&CC=CN&NR=115858723A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>DAI JIAN</creatorcontrib><creatorcontrib>TAO TIANYI</creatorcontrib><creatorcontrib>HE QIBO</creatorcontrib><creatorcontrib>CAO WEIJIE</creatorcontrib><creatorcontrib>QUE YUNFEI</creatorcontrib><creatorcontrib>XU JUN</creatorcontrib><creatorcontrib>TANG SHUYANG</creatorcontrib><creatorcontrib>GU BOYUAN</creatorcontrib><creatorcontrib>ZHOU YUNFENG</creatorcontrib><creatorcontrib>LIU ZHENGXIAO</creatorcontrib><creatorcontrib>ZHANG YUFAN</creatorcontrib><creatorcontrib>LI JINBO</creatorcontrib><creatorcontrib>MIAO YE</creatorcontrib><title>Complex knowledge base question and answer oriented query graph generation method and system</title><description>The invention relates to a query graph generation method and system oriented to complex knowledge base questions and answers. The method comprises the steps that according to the semantic similarity between a target question and historical questions, the historical questions ranked in the top are screened out from historical cases; forming a case candidate relation set by the relations in the standard query graph corresponding to the screened historical questions; on the basis of the case candidate relation set, a search type semantic analysis method is adopted to generate a query graph; and converting the query graph into an executable query statement according to a grammar rule of a knowledge base query statement, and executing query on the knowledge base to obtain an answer to the target question. According to the method for remarkably reducing the retrieval space in the reasoning process through the historical cases, candidate relations obtained through retrieval are pre-screened, and the question answeri</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNizsOwjAUBN1QIOAOjwNQhCgibWSBqKgokSKDlyTCP_yMQm5PiDgAxWqKnZmLi_Q2GLzp4XxvoBvQVTHo-QKnzjtSTo_jHpF87OAS9PeMAzVRhZYaOEQ1qRap9XoqeOAEuxSzuzKM1Y8LsT7sz_K4QfA1OKjbGKdanrKsKItyt82r_B_nA_n1PGg</recordid><startdate>20230328</startdate><enddate>20230328</enddate><creator>DAI JIAN</creator><creator>TAO TIANYI</creator><creator>HE QIBO</creator><creator>CAO WEIJIE</creator><creator>QUE YUNFEI</creator><creator>XU JUN</creator><creator>TANG SHUYANG</creator><creator>GU BOYUAN</creator><creator>ZHOU YUNFENG</creator><creator>LIU ZHENGXIAO</creator><creator>ZHANG YUFAN</creator><creator>LI JINBO</creator><creator>MIAO YE</creator><scope>EVB</scope></search><sort><creationdate>20230328</creationdate><title>Complex knowledge base question and answer oriented query graph generation method and system</title><author>DAI JIAN ; TAO TIANYI ; HE QIBO ; CAO WEIJIE ; QUE YUNFEI ; XU JUN ; TANG SHUYANG ; GU BOYUAN ; ZHOU YUNFENG ; LIU ZHENGXIAO ; ZHANG YUFAN ; LI JINBO ; MIAO YE</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115858723A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>DAI JIAN</creatorcontrib><creatorcontrib>TAO TIANYI</creatorcontrib><creatorcontrib>HE QIBO</creatorcontrib><creatorcontrib>CAO WEIJIE</creatorcontrib><creatorcontrib>QUE YUNFEI</creatorcontrib><creatorcontrib>XU JUN</creatorcontrib><creatorcontrib>TANG SHUYANG</creatorcontrib><creatorcontrib>GU BOYUAN</creatorcontrib><creatorcontrib>ZHOU YUNFENG</creatorcontrib><creatorcontrib>LIU ZHENGXIAO</creatorcontrib><creatorcontrib>ZHANG YUFAN</creatorcontrib><creatorcontrib>LI JINBO</creatorcontrib><creatorcontrib>MIAO YE</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>DAI JIAN</au><au>TAO TIANYI</au><au>HE QIBO</au><au>CAO WEIJIE</au><au>QUE YUNFEI</au><au>XU JUN</au><au>TANG SHUYANG</au><au>GU BOYUAN</au><au>ZHOU YUNFENG</au><au>LIU ZHENGXIAO</au><au>ZHANG YUFAN</au><au>LI JINBO</au><au>MIAO YE</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Complex knowledge base question and answer oriented query graph generation method and system</title><date>2023-03-28</date><risdate>2023</risdate><abstract>The invention relates to a query graph generation method and system oriented to complex knowledge base questions and answers. The method comprises the steps that according to the semantic similarity between a target question and historical questions, the historical questions ranked in the top are screened out from historical cases; forming a case candidate relation set by the relations in the standard query graph corresponding to the screened historical questions; on the basis of the case candidate relation set, a search type semantic analysis method is adopted to generate a query graph; and converting the query graph into an executable query statement according to a grammar rule of a knowledge base query statement, and executing query on the knowledge base to obtain an answer to the target question. According to the method for remarkably reducing the retrieval space in the reasoning process through the historical cases, candidate relations obtained through retrieval are pre-screened, and the question answeri</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN115858723A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | Complex knowledge base question and answer oriented query graph generation method and system |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T14%3A23%3A08IST&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=DAI%20JIAN&rft.date=2023-03-28&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115858723A%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 |