METHOD AND APPARATUS FOR PROCESSIMG NATURAL LANGUAGES
Disclosed are a method and a device for processing a natural language. The disclosed method for processing a natural language comprises the steps of: determining a first degree of similarity between an input sentence of a user and a first query sentence stored in a database; determining a second deg...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Patent |
| Sprache: | eng ; kor |
| 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 | PARK, JEONG HOON KIM, MI SUK YOO, SANG HYUN JEON, JE HUN HAN, GYU BUM |
| description | Disclosed are a method and a device for processing a natural language. The disclosed method for processing a natural language comprises the steps of: determining a first degree of similarity between an input sentence of a user and a first query sentence stored in a database; determining a second degree of similarity between a part of the input sentence and a second query sentence stored in the database when the first similarity is lower than a first threshold; and outputting a response sentence corresponding to the second query sentence from the database as a response of the input sentence, when the second degree of similarity is higher than a second threshold.
자연어 처리 방법 및 장치가 개시된다. 개시된 자연어 처리 방법은 사용자의 입력 문장 및 데이터베이스에 저장된 제1 쿼리 문장 간 제1 유사도를 결정하는 단계, 상기 제1 유사도가 제1 임계치보다 낮으면, 상기 입력 문장의 일부와 상기 데이터베이스에 저장된 제2 쿼리 문장 간 제2 유사도를 결정하는 단계 및 상기 제2 유사도가 제2 임계치보다 높으면, 상기 데이터베이스에서 상기 제2 쿼리 문장에 대응하는 응답 문장을 상기 입력 문장의 응답으로 출력하는 단계를 포함한다. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_KR20210061141A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>KR20210061141A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_KR20210061141A3</originalsourceid><addsrcrecordid>eNrjZDD1dQ3x8HdRcPQD4oAAxyDHkNBgBTf_IIWAIH9n1-BgT193BT-gYJCjj4KPo597qKO7azAPA2taYk5xKi-U5mZQdnMNcfbQTS3Ij08tLkhMTs1LLYn3DjIyMDI0MDAzNDQxdDQmThUAipYocg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>METHOD AND APPARATUS FOR PROCESSIMG NATURAL LANGUAGES</title><source>esp@cenet</source><creator>PARK, JEONG HOON ; KIM, MI SUK ; YOO, SANG HYUN ; JEON, JE HUN ; HAN, GYU BUM</creator><creatorcontrib>PARK, JEONG HOON ; KIM, MI SUK ; YOO, SANG HYUN ; JEON, JE HUN ; HAN, GYU BUM</creatorcontrib><description>Disclosed are a method and a device for processing a natural language. The disclosed method for processing a natural language comprises the steps of: determining a first degree of similarity between an input sentence of a user and a first query sentence stored in a database; determining a second degree of similarity between a part of the input sentence and a second query sentence stored in the database when the first similarity is lower than a first threshold; and outputting a response sentence corresponding to the second query sentence from the database as a response of the input sentence, when the second degree of similarity is higher than a second threshold.
자연어 처리 방법 및 장치가 개시된다. 개시된 자연어 처리 방법은 사용자의 입력 문장 및 데이터베이스에 저장된 제1 쿼리 문장 간 제1 유사도를 결정하는 단계, 상기 제1 유사도가 제1 임계치보다 낮으면, 상기 입력 문장의 일부와 상기 데이터베이스에 저장된 제2 쿼리 문장 간 제2 유사도를 결정하는 단계 및 상기 제2 유사도가 제2 임계치보다 높으면, 상기 데이터베이스에서 상기 제2 쿼리 문장에 대응하는 응답 문장을 상기 입력 문장의 응답으로 출력하는 단계를 포함한다.</description><language>eng ; kor</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2021</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=20210527&DB=EPODOC&CC=KR&NR=20210061141A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25563,76318</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210527&DB=EPODOC&CC=KR&NR=20210061141A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>PARK, JEONG HOON</creatorcontrib><creatorcontrib>KIM, MI SUK</creatorcontrib><creatorcontrib>YOO, SANG HYUN</creatorcontrib><creatorcontrib>JEON, JE HUN</creatorcontrib><creatorcontrib>HAN, GYU BUM</creatorcontrib><title>METHOD AND APPARATUS FOR PROCESSIMG NATURAL LANGUAGES</title><description>Disclosed are a method and a device for processing a natural language. The disclosed method for processing a natural language comprises the steps of: determining a first degree of similarity between an input sentence of a user and a first query sentence stored in a database; determining a second degree of similarity between a part of the input sentence and a second query sentence stored in the database when the first similarity is lower than a first threshold; and outputting a response sentence corresponding to the second query sentence from the database as a response of the input sentence, when the second degree of similarity is higher than a second threshold.
자연어 처리 방법 및 장치가 개시된다. 개시된 자연어 처리 방법은 사용자의 입력 문장 및 데이터베이스에 저장된 제1 쿼리 문장 간 제1 유사도를 결정하는 단계, 상기 제1 유사도가 제1 임계치보다 낮으면, 상기 입력 문장의 일부와 상기 데이터베이스에 저장된 제2 쿼리 문장 간 제2 유사도를 결정하는 단계 및 상기 제2 유사도가 제2 임계치보다 높으면, 상기 데이터베이스에서 상기 제2 쿼리 문장에 대응하는 응답 문장을 상기 입력 문장의 응답으로 출력하는 단계를 포함한다.</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>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZDD1dQ3x8HdRcPQD4oAAxyDHkNBgBTf_IIWAIH9n1-BgT193BT-gYJCjj4KPo597qKO7azAPA2taYk5xKi-U5mZQdnMNcfbQTS3Ij08tLkhMTs1LLYn3DjIyMDI0MDAzNDQxdDQmThUAipYocg</recordid><startdate>20210527</startdate><enddate>20210527</enddate><creator>PARK, JEONG HOON</creator><creator>KIM, MI SUK</creator><creator>YOO, SANG HYUN</creator><creator>JEON, JE HUN</creator><creator>HAN, GYU BUM</creator><scope>EVB</scope></search><sort><creationdate>20210527</creationdate><title>METHOD AND APPARATUS FOR PROCESSIMG NATURAL LANGUAGES</title><author>PARK, JEONG HOON ; KIM, MI SUK ; YOO, SANG HYUN ; JEON, JE HUN ; HAN, GYU BUM</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_KR20210061141A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; kor</language><creationdate>2021</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>PARK, JEONG HOON</creatorcontrib><creatorcontrib>KIM, MI SUK</creatorcontrib><creatorcontrib>YOO, SANG HYUN</creatorcontrib><creatorcontrib>JEON, JE HUN</creatorcontrib><creatorcontrib>HAN, GYU BUM</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>PARK, JEONG HOON</au><au>KIM, MI SUK</au><au>YOO, SANG HYUN</au><au>JEON, JE HUN</au><au>HAN, GYU BUM</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>METHOD AND APPARATUS FOR PROCESSIMG NATURAL LANGUAGES</title><date>2021-05-27</date><risdate>2021</risdate><abstract>Disclosed are a method and a device for processing a natural language. The disclosed method for processing a natural language comprises the steps of: determining a first degree of similarity between an input sentence of a user and a first query sentence stored in a database; determining a second degree of similarity between a part of the input sentence and a second query sentence stored in the database when the first similarity is lower than a first threshold; and outputting a response sentence corresponding to the second query sentence from the database as a response of the input sentence, when the second degree of similarity is higher than a second threshold.
자연어 처리 방법 및 장치가 개시된다. 개시된 자연어 처리 방법은 사용자의 입력 문장 및 데이터베이스에 저장된 제1 쿼리 문장 간 제1 유사도를 결정하는 단계, 상기 제1 유사도가 제1 임계치보다 낮으면, 상기 입력 문장의 일부와 상기 데이터베이스에 저장된 제2 쿼리 문장 간 제2 유사도를 결정하는 단계 및 상기 제2 유사도가 제2 임계치보다 높으면, 상기 데이터베이스에서 상기 제2 쿼리 문장에 대응하는 응답 문장을 상기 입력 문장의 응답으로 출력하는 단계를 포함한다.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng ; kor |
| recordid | cdi_epo_espacenet_KR20210061141A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | METHOD AND APPARATUS FOR PROCESSIMG NATURAL LANGUAGES |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T01%3A50%3A18IST&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=PARK,%20JEONG%20HOON&rft.date=2021-05-27&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EKR20210061141A%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 |