Method, device and terminal for inference model training and credit attribute inference
The embodiment of the invention discloses an inference model training and credit attribute inference method and device and a terminal. Determining a plurality of sample user features of the plurality of sample users and a prior credit attribute corresponding to each sample user feature, and determin...
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 | JIANG LINBO PENG YIMENG LIN JIANAN |
| description | The embodiment of the invention discloses an inference model training and credit attribute inference method and device and a terminal. Determining a plurality of sample user features of the plurality of sample users and a prior credit attribute corresponding to each sample user feature, and determining a loss weight of each sample user feature, the loss weight of each sample user feature being positively correlated with a confidence coefficient of the prior credit attribute; inputting all the sample user features into an initial inference model, controlling the initial inference model to output a predicted credit attribute of each sample user feature, and adjusting parameters of the initial inference model according to the predicted credit attributes, the prior credit attributes and the loss weights of all the sample user features; and updating a prior credit attribute and a loss weight of a target sample user feature meeting a preset updating condition in all the sample user features based on the adjusted in |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118798360A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118798360A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118798360A3</originalsourceid><addsrcrecordid>eNqNyrEKwjAURuEsDqK-w3VXsBS0jlIUF50ExxKTP_VCelPSq8-viODqdIbzjc31BL0nvyCPJzuQFU-K3LHYSCFlYgnIkPfqkkckzZaFpf1Il-FZyapmvj0UPz01o2DjgNm3EzM_7C_1cYk-NRh66yDQpj4XRbXZVuV6tSv_MS8zhDnU</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Method, device and terminal for inference model training and credit attribute inference</title><source>esp@cenet</source><creator>JIANG LINBO ; PENG YIMENG ; LIN JIANAN</creator><creatorcontrib>JIANG LINBO ; PENG YIMENG ; LIN JIANAN</creatorcontrib><description>The embodiment of the invention discloses an inference model training and credit attribute inference method and device and a terminal. Determining a plurality of sample user features of the plurality of sample users and a prior credit attribute corresponding to each sample user feature, and determining a loss weight of each sample user feature, the loss weight of each sample user feature being positively correlated with a confidence coefficient of the prior credit attribute; inputting all the sample user features into an initial inference model, controlling the initial inference model to output a predicted credit attribute of each sample user feature, and adjusting parameters of the initial inference model according to the predicted credit attributes, the prior credit attributes and the loss weights of all the sample user features; and updating a prior credit attribute and a loss weight of a target sample user feature meeting a preset updating condition in all the sample user features based on the adjusted in</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES ; PHYSICS ; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR</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=20241018&DB=EPODOC&CC=CN&NR=118798360A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20241018&DB=EPODOC&CC=CN&NR=118798360A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>JIANG LINBO</creatorcontrib><creatorcontrib>PENG YIMENG</creatorcontrib><creatorcontrib>LIN JIANAN</creatorcontrib><title>Method, device and terminal for inference model training and credit attribute inference</title><description>The embodiment of the invention discloses an inference model training and credit attribute inference method and device and a terminal. Determining a plurality of sample user features of the plurality of sample users and a prior credit attribute corresponding to each sample user feature, and determining a loss weight of each sample user feature, the loss weight of each sample user feature being positively correlated with a confidence coefficient of the prior credit attribute; inputting all the sample user features into an initial inference model, controlling the initial inference model to output a predicted credit attribute of each sample user feature, and adjusting parameters of the initial inference model according to the predicted credit attributes, the prior credit attributes and the loss weights of all the sample user features; and updating a prior credit attribute and a loss weight of a target sample user feature meeting a preset updating condition in all the sample user features based on the adjusted in</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES</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>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyrEKwjAURuEsDqK-w3VXsBS0jlIUF50ExxKTP_VCelPSq8-viODqdIbzjc31BL0nvyCPJzuQFU-K3LHYSCFlYgnIkPfqkkckzZaFpf1Il-FZyapmvj0UPz01o2DjgNm3EzM_7C_1cYk-NRh66yDQpj4XRbXZVuV6tSv_MS8zhDnU</recordid><startdate>20241018</startdate><enddate>20241018</enddate><creator>JIANG LINBO</creator><creator>PENG YIMENG</creator><creator>LIN JIANAN</creator><scope>EVB</scope></search><sort><creationdate>20241018</creationdate><title>Method, device and terminal for inference model training and credit attribute inference</title><author>JIANG LINBO ; PENG YIMENG ; LIN JIANAN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118798360A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES</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>JIANG LINBO</creatorcontrib><creatorcontrib>PENG YIMENG</creatorcontrib><creatorcontrib>LIN JIANAN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>JIANG LINBO</au><au>PENG YIMENG</au><au>LIN JIANAN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Method, device and terminal for inference model training and credit attribute inference</title><date>2024-10-18</date><risdate>2024</risdate><abstract>The embodiment of the invention discloses an inference model training and credit attribute inference method and device and a terminal. Determining a plurality of sample user features of the plurality of sample users and a prior credit attribute corresponding to each sample user feature, and determining a loss weight of each sample user feature, the loss weight of each sample user feature being positively correlated with a confidence coefficient of the prior credit attribute; inputting all the sample user features into an initial inference model, controlling the initial inference model to output a predicted credit attribute of each sample user feature, and adjusting parameters of the initial inference model according to the predicted credit attributes, the prior credit attributes and the loss weights of all the sample user features; and updating a prior credit attribute and a loss weight of a target sample user feature meeting a preset updating condition in all the sample user features based on the adjusted in</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN118798360A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES PHYSICS SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR |
| title | Method, device and terminal for inference model training and credit attribute inference |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T13%3A23%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=JIANG%20LINBO&rft.date=2024-10-18&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118798360A%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 |