Data interpolation method and device based on graph representation learning, medium and equipment
The embodiment of the invention provides a data interpolation method and device based on graph representation learning, a medium and equipment. According to the method, modeling is carried out on similarity and difference between a target prediction node and neighbor nodes in multiple heterogeneous...
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 | PENG CHAOPENG FAN XIAOLIANG FENG MINGKUAN WANG CHENG ZHENG CHUANPAN |
| description | The embodiment of the invention provides a data interpolation method and device based on graph representation learning, a medium and equipment. According to the method, modeling is carried out on similarity and difference between a target prediction node and neighbor nodes in multiple heterogeneous relationships at the same time, so that node information of the neighbor nodes is aggregated, and inductive feature representation of the target prediction node is obtained; based on the GRU neural network, the modeling of the time correlation of the target prediction node is guided adaptively according to the information flow mode of the neighbor node in the time dimension in the multi-heterogeneous relationship; and dynamically fusing the target node representation of the target prediction node learned in the multiple heterogeneous relationship at different time steps to output an estimation sequence of the target prediction node. According to the technical scheme of the embodiment of the invention, the reasonabi |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117010490A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117010490A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117010490A3</originalsourceid><addsrcrecordid>eNqNy7EKwjAUheEuDqK-w3VXaFEQR6mKk5N7uTbHNpDcXJPU57eoD-B0hvP904KPnJmsZEQNjrMNQh65D4ZYDBm8bAu6c4Kh8eoia08RGpEg-esdOIqVbjWWxg7-U-I5WPWjmReTB7uExW9nxfJ8utWXNTQ0SMotBLmpr1W1K6tyuy8Pm3_MGximPcU</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Data interpolation method and device based on graph representation learning, medium and equipment</title><source>esp@cenet</source><creator>PENG CHAOPENG ; FAN XIAOLIANG ; FENG MINGKUAN ; WANG CHENG ; ZHENG CHUANPAN</creator><creatorcontrib>PENG CHAOPENG ; FAN XIAOLIANG ; FENG MINGKUAN ; WANG CHENG ; ZHENG CHUANPAN</creatorcontrib><description>The embodiment of the invention provides a data interpolation method and device based on graph representation learning, a medium and equipment. According to the method, modeling is carried out on similarity and difference between a target prediction node and neighbor nodes in multiple heterogeneous relationships at the same time, so that node information of the neighbor nodes is aggregated, and inductive feature representation of the target prediction node is obtained; based on the GRU neural network, the modeling of the time correlation of the target prediction node is guided adaptively according to the information flow mode of the neighbor node in the time dimension in the multi-heterogeneous relationship; and dynamically fusing the target node representation of the target prediction node learned in the multiple heterogeneous relationship at different time steps to output an estimation sequence of the target prediction node. According to the technical scheme of the embodiment of the invention, the reasonabi</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; 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=20231107&DB=EPODOC&CC=CN&NR=117010490A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20231107&DB=EPODOC&CC=CN&NR=117010490A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>PENG CHAOPENG</creatorcontrib><creatorcontrib>FAN XIAOLIANG</creatorcontrib><creatorcontrib>FENG MINGKUAN</creatorcontrib><creatorcontrib>WANG CHENG</creatorcontrib><creatorcontrib>ZHENG CHUANPAN</creatorcontrib><title>Data interpolation method and device based on graph representation learning, medium and equipment</title><description>The embodiment of the invention provides a data interpolation method and device based on graph representation learning, a medium and equipment. According to the method, modeling is carried out on similarity and difference between a target prediction node and neighbor nodes in multiple heterogeneous relationships at the same time, so that node information of the neighbor nodes is aggregated, and inductive feature representation of the target prediction node is obtained; based on the GRU neural network, the modeling of the time correlation of the target prediction node is guided adaptively according to the information flow mode of the neighbor node in the time dimension in the multi-heterogeneous relationship; and dynamically fusing the target node representation of the target prediction node learned in the multiple heterogeneous relationship at different time steps to output an estimation sequence of the target prediction node. According to the technical scheme of the embodiment of the invention, the reasonabi</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</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>eNqNy7EKwjAUheEuDqK-w3VXaFEQR6mKk5N7uTbHNpDcXJPU57eoD-B0hvP904KPnJmsZEQNjrMNQh65D4ZYDBm8bAu6c4Kh8eoia08RGpEg-esdOIqVbjWWxg7-U-I5WPWjmReTB7uExW9nxfJ8utWXNTQ0SMotBLmpr1W1K6tyuy8Pm3_MGximPcU</recordid><startdate>20231107</startdate><enddate>20231107</enddate><creator>PENG CHAOPENG</creator><creator>FAN XIAOLIANG</creator><creator>FENG MINGKUAN</creator><creator>WANG CHENG</creator><creator>ZHENG CHUANPAN</creator><scope>EVB</scope></search><sort><creationdate>20231107</creationdate><title>Data interpolation method and device based on graph representation learning, medium and equipment</title><author>PENG CHAOPENG ; FAN XIAOLIANG ; FENG MINGKUAN ; WANG CHENG ; ZHENG CHUANPAN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117010490A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>PENG CHAOPENG</creatorcontrib><creatorcontrib>FAN XIAOLIANG</creatorcontrib><creatorcontrib>FENG MINGKUAN</creatorcontrib><creatorcontrib>WANG CHENG</creatorcontrib><creatorcontrib>ZHENG CHUANPAN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>PENG CHAOPENG</au><au>FAN XIAOLIANG</au><au>FENG MINGKUAN</au><au>WANG CHENG</au><au>ZHENG CHUANPAN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Data interpolation method and device based on graph representation learning, medium and equipment</title><date>2023-11-07</date><risdate>2023</risdate><abstract>The embodiment of the invention provides a data interpolation method and device based on graph representation learning, a medium and equipment. According to the method, modeling is carried out on similarity and difference between a target prediction node and neighbor nodes in multiple heterogeneous relationships at the same time, so that node information of the neighbor nodes is aggregated, and inductive feature representation of the target prediction node is obtained; based on the GRU neural network, the modeling of the time correlation of the target prediction node is guided adaptively according to the information flow mode of the neighbor node in the time dimension in the multi-heterogeneous relationship; and dynamically fusing the target node representation of the target prediction node learned in the multiple heterogeneous relationship at different time steps to output an estimation sequence of the target prediction node. According to the technical scheme of the embodiment of the invention, the reasonabi</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN117010490A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | Data interpolation method and device based on graph representation learning, medium and equipment |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T05%3A56%3A12IST&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=PENG%20CHAOPENG&rft.date=2023-11-07&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117010490A%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 |