Similar appeal work order screening method and device based on topic model
The invention designs a similar appeal work order screening method and device based on a topic model. A historical work order similar to new appeal data is quickly and accurately given by adopting a topic model method based on word bag and word frequency vector + LDA + quick new appeal processing cl...
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 | YANG DAWEI LIU XIN SUN HONGZHAN XI YONGKE LI DICHENG HUANG WEI |
| description | The invention designs a similar appeal work order screening method and device based on a topic model. A historical work order similar to new appeal data is quickly and accurately given by adopting a topic model method based on word bag and word frequency vector + LDA + quick new appeal processing classification + similarity calculation. According to the method, data preprocessing operation is carried out on data, and mainly comprises data cleaning and data normalization. The method comprises the following steps: grouping data according to a handling department to which normalized data belongs under an actual condition, performing feature word extraction on grouped data word segmentation, forming a word bag and word frequency vector by applying a statistical method, then training data of each department by applying an LDA algorithm, and constructing a corresponding topic model. After a piece of new appeal data is obtained, weight superposition is combined, and the first three candidate classifications are dete |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN113239691A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN113239691A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN113239691A3</originalsourceid><addsrcrecordid>eNqNyjEKAjEQBdBtLES9w3gAixgQtpRFEQsb7Zcx83WDSSYkQa9v4wGsXvPm3fnqow9ciHMGB_poeZEWQaHqCpB8elJEm1SIk5Dg7R3ozhVCmqhp9o6iCsKymz04VKx-Lrr18XAbThtkHVEzOyS0cbgYY7e23_Vmb_85X_ViNKg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Similar appeal work order screening method and device based on topic model</title><source>esp@cenet</source><creator>YANG DAWEI ; LIU XIN ; SUN HONGZHAN ; XI YONGKE ; LI DICHENG ; HUANG WEI</creator><creatorcontrib>YANG DAWEI ; LIU XIN ; SUN HONGZHAN ; XI YONGKE ; LI DICHENG ; HUANG WEI</creatorcontrib><description>The invention designs a similar appeal work order screening method and device based on a topic model. A historical work order similar to new appeal data is quickly and accurately given by adopting a topic model method based on word bag and word frequency vector + LDA + quick new appeal processing classification + similarity calculation. According to the method, data preprocessing operation is carried out on data, and mainly comprises data cleaning and data normalization. The method comprises the following steps: grouping data according to a handling department to which normalized data belongs under an actual condition, performing feature word extraction on grouped data word segmentation, forming a word bag and word frequency vector by applying a statistical method, then training data of each department by applying an LDA algorithm, and constructing a corresponding topic model. After a piece of new appeal data is obtained, weight superposition is combined, and the first three candidate classifications are dete</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS ; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR</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=20210810&DB=EPODOC&CC=CN&NR=113239691A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25562,76317</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210810&DB=EPODOC&CC=CN&NR=113239691A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>YANG DAWEI</creatorcontrib><creatorcontrib>LIU XIN</creatorcontrib><creatorcontrib>SUN HONGZHAN</creatorcontrib><creatorcontrib>XI YONGKE</creatorcontrib><creatorcontrib>LI DICHENG</creatorcontrib><creatorcontrib>HUANG WEI</creatorcontrib><title>Similar appeal work order screening method and device based on topic model</title><description>The invention designs a similar appeal work order screening method and device based on a topic model. A historical work order similar to new appeal data is quickly and accurately given by adopting a topic model method based on word bag and word frequency vector + LDA + quick new appeal processing classification + similarity calculation. According to the method, data preprocessing operation is carried out on data, and mainly comprises data cleaning and data normalization. The method comprises the following steps: grouping data according to a handling department to which normalized data belongs under an actual condition, performing feature word extraction on grouped data word segmentation, forming a word bag and word frequency vector by applying a statistical method, then training data of each department by applying an LDA algorithm, and constructing a corresponding topic model. After a piece of new appeal data is obtained, weight superposition is combined, and the first three candidate classifications are dete</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><subject>SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyjEKAjEQBdBtLES9w3gAixgQtpRFEQsb7Zcx83WDSSYkQa9v4wGsXvPm3fnqow9ciHMGB_poeZEWQaHqCpB8elJEm1SIk5Dg7R3ozhVCmqhp9o6iCsKymz04VKx-Lrr18XAbThtkHVEzOyS0cbgYY7e23_Vmb_85X_ViNKg</recordid><startdate>20210810</startdate><enddate>20210810</enddate><creator>YANG DAWEI</creator><creator>LIU XIN</creator><creator>SUN HONGZHAN</creator><creator>XI YONGKE</creator><creator>LI DICHENG</creator><creator>HUANG WEI</creator><scope>EVB</scope></search><sort><creationdate>20210810</creationdate><title>Similar appeal work order screening method and device based on topic model</title><author>YANG DAWEI ; LIU XIN ; SUN HONGZHAN ; XI YONGKE ; LI DICHENG ; HUANG WEI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN113239691A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2021</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><topic>SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR</topic><toplevel>online_resources</toplevel><creatorcontrib>YANG DAWEI</creatorcontrib><creatorcontrib>LIU XIN</creatorcontrib><creatorcontrib>SUN HONGZHAN</creatorcontrib><creatorcontrib>XI YONGKE</creatorcontrib><creatorcontrib>LI DICHENG</creatorcontrib><creatorcontrib>HUANG WEI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>YANG DAWEI</au><au>LIU XIN</au><au>SUN HONGZHAN</au><au>XI YONGKE</au><au>LI DICHENG</au><au>HUANG WEI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Similar appeal work order screening method and device based on topic model</title><date>2021-08-10</date><risdate>2021</risdate><abstract>The invention designs a similar appeal work order screening method and device based on a topic model. A historical work order similar to new appeal data is quickly and accurately given by adopting a topic model method based on word bag and word frequency vector + LDA + quick new appeal processing classification + similarity calculation. According to the method, data preprocessing operation is carried out on data, and mainly comprises data cleaning and data normalization. The method comprises the following steps: grouping data according to a handling department to which normalized data belongs under an actual condition, performing feature word extraction on grouped data word segmentation, forming a word bag and word frequency vector by applying a statistical method, then training data of each department by applying an LDA algorithm, and constructing a corresponding topic model. After a piece of new appeal data is obtained, weight superposition is combined, and the first three candidate classifications are dete</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN113239691A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES ELECTRIC DIGITAL DATA PROCESSING PHYSICS SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR |
| title | Similar appeal work order screening method and device based on topic model |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T03%3A55%3A22IST&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=YANG%20DAWEI&rft.date=2021-08-10&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN113239691A%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 |