Power data prediction model optimization method and system
The invention provides an electric power data prediction model optimization method and system, the electric power data prediction model optimization method is applied to object type data processing, and the method comprises the steps: collecting and obtaining electric power structured information, a...
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 | WU SHAOLEI DOU LIANGJUN XU FEI CHENG HUIDONG ZHOU JIANJUN ZHAO CHENG WU KAI YU AIBIN LUO CHEN FENG YU ZHANG ZHENGKAI QI ZHENBIAO LI WEI |
| description | The invention provides an electric power data prediction model optimization method and system, the electric power data prediction model optimization method is applied to object type data processing, and the method comprises the steps: collecting and obtaining electric power structured information, and generating electric power state sample data according to the electric power structured information; classifying and identifying the power state sample data to obtain sample label information, and obtaining training model parameters and prediction target data from a preset training model; processing the training model parameters and the prediction target data to obtain sample loss parameters; processing the sample label information according to a sample loss parameter so as to obtain adaptive sample mining data; and carrying out convergence processing on the preset training model by using the adaptive sample mining data. According to the method, the online difficult sample mining loss function is designed, the we |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115048989A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115048989A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115048989A3</originalsourceid><addsrcrecordid>eNrjZLAKyC9PLVJISSxJVCgoSk3JTC7JzM9TyM1PSc1RyC8oyczNrEqECKWWZOSnKCTmpSgUVxaXpObyMLCmJeYUp_JCaW4GRTfXEGcP3dSC_PjU4oLE5NS81JJ4Zz9DQ1MDEwtLC0tHY2LUAACiay-E</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Power data prediction model optimization method and system</title><source>esp@cenet</source><creator>WU SHAOLEI ; DOU LIANGJUN ; XU FEI ; CHENG HUIDONG ; ZHOU JIANJUN ; ZHAO CHENG ; WU KAI ; YU AIBIN ; LUO CHEN ; FENG YU ; ZHANG ZHENGKAI ; QI ZHENBIAO ; LI WEI</creator><creatorcontrib>WU SHAOLEI ; DOU LIANGJUN ; XU FEI ; CHENG HUIDONG ; ZHOU JIANJUN ; ZHAO CHENG ; WU KAI ; YU AIBIN ; LUO CHEN ; FENG YU ; ZHANG ZHENGKAI ; QI ZHENBIAO ; LI WEI</creatorcontrib><description>The invention provides an electric power data prediction model optimization method and system, the electric power data prediction model optimization method is applied to object type data processing, and the method comprises the steps: collecting and obtaining electric power structured information, and generating electric power state sample data according to the electric power structured information; classifying and identifying the power state sample data to obtain sample label information, and obtaining training model parameters and prediction target data from a preset training model; processing the training model parameters and the prediction target data to obtain sample loss parameters; processing the sample label information according to a sample loss parameter so as to obtain adaptive sample mining data; and carrying out convergence processing on the preset training model by using the adaptive sample mining data. According to the method, the online difficult sample mining loss function is designed, the we</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 ; HANDLING RECORD CARRIERS ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS ; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR</subject><creationdate>2022</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=20220913&DB=EPODOC&CC=CN&NR=115048989A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220913&DB=EPODOC&CC=CN&NR=115048989A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WU SHAOLEI</creatorcontrib><creatorcontrib>DOU LIANGJUN</creatorcontrib><creatorcontrib>XU FEI</creatorcontrib><creatorcontrib>CHENG HUIDONG</creatorcontrib><creatorcontrib>ZHOU JIANJUN</creatorcontrib><creatorcontrib>ZHAO CHENG</creatorcontrib><creatorcontrib>WU KAI</creatorcontrib><creatorcontrib>YU AIBIN</creatorcontrib><creatorcontrib>LUO CHEN</creatorcontrib><creatorcontrib>FENG YU</creatorcontrib><creatorcontrib>ZHANG ZHENGKAI</creatorcontrib><creatorcontrib>QI ZHENBIAO</creatorcontrib><creatorcontrib>LI WEI</creatorcontrib><title>Power data prediction model optimization method and system</title><description>The invention provides an electric power data prediction model optimization method and system, the electric power data prediction model optimization method is applied to object type data processing, and the method comprises the steps: collecting and obtaining electric power structured information, and generating electric power state sample data according to the electric power structured information; classifying and identifying the power state sample data to obtain sample label information, and obtaining training model parameters and prediction target data from a preset training model; processing the training model parameters and the prediction target data to obtain sample loss parameters; processing the sample label information according to a sample loss parameter so as to obtain adaptive sample mining data; and carrying out convergence processing on the preset training model by using the adaptive sample mining data. According to the method, the online difficult sample mining loss function is designed, the we</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>HANDLING RECORD CARRIERS</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</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>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLAKyC9PLVJISSxJVCgoSk3JTC7JzM9TyM1PSc1RyC8oyczNrEqECKWWZOSnKCTmpSgUVxaXpObyMLCmJeYUp_JCaW4GRTfXEGcP3dSC_PjU4oLE5NS81JJ4Zz9DQ1MDEwtLC0tHY2LUAACiay-E</recordid><startdate>20220913</startdate><enddate>20220913</enddate><creator>WU SHAOLEI</creator><creator>DOU LIANGJUN</creator><creator>XU FEI</creator><creator>CHENG HUIDONG</creator><creator>ZHOU JIANJUN</creator><creator>ZHAO CHENG</creator><creator>WU KAI</creator><creator>YU AIBIN</creator><creator>LUO CHEN</creator><creator>FENG YU</creator><creator>ZHANG ZHENGKAI</creator><creator>QI ZHENBIAO</creator><creator>LI WEI</creator><scope>EVB</scope></search><sort><creationdate>20220913</creationdate><title>Power data prediction model optimization method and system</title><author>WU SHAOLEI ; DOU LIANGJUN ; XU FEI ; CHENG HUIDONG ; ZHOU JIANJUN ; ZHAO CHENG ; WU KAI ; YU AIBIN ; LUO CHEN ; FENG YU ; ZHANG ZHENGKAI ; QI ZHENBIAO ; LI WEI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115048989A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</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>HANDLING RECORD CARRIERS</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</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>WU SHAOLEI</creatorcontrib><creatorcontrib>DOU LIANGJUN</creatorcontrib><creatorcontrib>XU FEI</creatorcontrib><creatorcontrib>CHENG HUIDONG</creatorcontrib><creatorcontrib>ZHOU JIANJUN</creatorcontrib><creatorcontrib>ZHAO CHENG</creatorcontrib><creatorcontrib>WU KAI</creatorcontrib><creatorcontrib>YU AIBIN</creatorcontrib><creatorcontrib>LUO CHEN</creatorcontrib><creatorcontrib>FENG YU</creatorcontrib><creatorcontrib>ZHANG ZHENGKAI</creatorcontrib><creatorcontrib>QI ZHENBIAO</creatorcontrib><creatorcontrib>LI WEI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WU SHAOLEI</au><au>DOU LIANGJUN</au><au>XU FEI</au><au>CHENG HUIDONG</au><au>ZHOU JIANJUN</au><au>ZHAO CHENG</au><au>WU KAI</au><au>YU AIBIN</au><au>LUO CHEN</au><au>FENG YU</au><au>ZHANG ZHENGKAI</au><au>QI ZHENBIAO</au><au>LI WEI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Power data prediction model optimization method and system</title><date>2022-09-13</date><risdate>2022</risdate><abstract>The invention provides an electric power data prediction model optimization method and system, the electric power data prediction model optimization method is applied to object type data processing, and the method comprises the steps: collecting and obtaining electric power structured information, and generating electric power state sample data according to the electric power structured information; classifying and identifying the power state sample data to obtain sample label information, and obtaining training model parameters and prediction target data from a preset training model; processing the training model parameters and the prediction target data to obtain sample loss parameters; processing the sample label information according to a sample loss parameter so as to obtain adaptive sample mining data; and carrying out convergence processing on the preset training model by using the adaptive sample mining data. According to the method, the online difficult sample mining loss function is designed, the we</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN115048989A |
| 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 HANDLING RECORD CARRIERS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR |
| title | Power data prediction model optimization 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=2025-01-26T12%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=WU%20SHAOLEI&rft.date=2022-09-13&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115048989A%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 |