DATA PROCESSING METHOD AND RELATED APPARATUS
The present application discloses a data processing method, which can be applied to the field of artificial intelligence. The method comprises: acquiring an operation log, the operation log comprising first operation data of a user in a first recommendation scenario; obtaining a first feature repres...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng ; fre |
| 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 | DONG, Zhenhua CAO, Zelin XU, Jun LAI, Jincai HE, Xiuqiang |
| description | The present application discloses a data processing method, which can be applied to the field of artificial intelligence. The method comprises: acquiring an operation log, the operation log comprising first operation data of a user in a first recommendation scenario; obtaining a first feature representation and a second feature representation according to the first operation data by means of a first feature extraction network and a second feature extraction network, respectively; obtaining first tendency information and second tendency information according to the first feature representation by means of a task network, and using a first weight and a second weight of a first gated network to fuse the first tendency information and the second tendency information, so as to obtain first target tendency information. The present application can reduce the interference between different recommendation scenarios, thereby solving the problem that a single-task model is affected by the different distributions of data |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_WO2023185925A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>WO2023185925A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_WO2023185925A13</originalsourceid><addsrcrecordid>eNrjZNBxcQxxVAgI8nd2DQ729HNX8HUN8fB3UXD0c1EIcvVxDHEFsgMCHIMcQ0KDeRhY0xJzilN5oTQ3g7Kba4izh25qQX58anFBYnJqXmpJfLi_kYGRsaGFqaWRqaOhMXGqACAXJgo</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>DATA PROCESSING METHOD AND RELATED APPARATUS</title><source>esp@cenet</source><creator>DONG, Zhenhua ; CAO, Zelin ; XU, Jun ; LAI, Jincai ; HE, Xiuqiang</creator><creatorcontrib>DONG, Zhenhua ; CAO, Zelin ; XU, Jun ; LAI, Jincai ; HE, Xiuqiang</creatorcontrib><description>The present application discloses a data processing method, which can be applied to the field of artificial intelligence. The method comprises: acquiring an operation log, the operation log comprising first operation data of a user in a first recommendation scenario; obtaining a first feature representation and a second feature representation according to the first operation data by means of a first feature extraction network and a second feature extraction network, respectively; obtaining first tendency information and second tendency information according to the first feature representation by means of a task network, and using a first weight and a second weight of a first gated network to fuse the first tendency information and the second tendency information, so as to obtain first target tendency information. The present application can reduce the interference between different recommendation scenarios, thereby solving the problem that a single-task model is affected by the different distributions of data</description><language>chi ; eng ; fre</language><subject>CALCULATING ; 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=20231005&DB=EPODOC&CC=WO&NR=2023185925A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,309,781,886,25569,76552</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20231005&DB=EPODOC&CC=WO&NR=2023185925A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>DONG, Zhenhua</creatorcontrib><creatorcontrib>CAO, Zelin</creatorcontrib><creatorcontrib>XU, Jun</creatorcontrib><creatorcontrib>LAI, Jincai</creatorcontrib><creatorcontrib>HE, Xiuqiang</creatorcontrib><title>DATA PROCESSING METHOD AND RELATED APPARATUS</title><description>The present application discloses a data processing method, which can be applied to the field of artificial intelligence. The method comprises: acquiring an operation log, the operation log comprising first operation data of a user in a first recommendation scenario; obtaining a first feature representation and a second feature representation according to the first operation data by means of a first feature extraction network and a second feature extraction network, respectively; obtaining first tendency information and second tendency information according to the first feature representation by means of a task network, and using a first weight and a second weight of a first gated network to fuse the first tendency information and the second tendency information, so as to obtain first target tendency information. The present application can reduce the interference between different recommendation scenarios, thereby solving the problem that a single-task model is affected by the different distributions of data</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZNBxcQxxVAgI8nd2DQ729HNX8HUN8fB3UXD0c1EIcvVxDHEFsgMCHIMcQ0KDeRhY0xJzilN5oTQ3g7Kba4izh25qQX58anFBYnJqXmpJfLi_kYGRsaGFqaWRqaOhMXGqACAXJgo</recordid><startdate>20231005</startdate><enddate>20231005</enddate><creator>DONG, Zhenhua</creator><creator>CAO, Zelin</creator><creator>XU, Jun</creator><creator>LAI, Jincai</creator><creator>HE, Xiuqiang</creator><scope>EVB</scope></search><sort><creationdate>20231005</creationdate><title>DATA PROCESSING METHOD AND RELATED APPARATUS</title><author>DONG, Zhenhua ; CAO, Zelin ; XU, Jun ; LAI, Jincai ; HE, Xiuqiang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_WO2023185925A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng ; fre</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>DONG, Zhenhua</creatorcontrib><creatorcontrib>CAO, Zelin</creatorcontrib><creatorcontrib>XU, Jun</creatorcontrib><creatorcontrib>LAI, Jincai</creatorcontrib><creatorcontrib>HE, Xiuqiang</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>DONG, Zhenhua</au><au>CAO, Zelin</au><au>XU, Jun</au><au>LAI, Jincai</au><au>HE, Xiuqiang</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>DATA PROCESSING METHOD AND RELATED APPARATUS</title><date>2023-10-05</date><risdate>2023</risdate><abstract>The present application discloses a data processing method, which can be applied to the field of artificial intelligence. The method comprises: acquiring an operation log, the operation log comprising first operation data of a user in a first recommendation scenario; obtaining a first feature representation and a second feature representation according to the first operation data by means of a first feature extraction network and a second feature extraction network, respectively; obtaining first tendency information and second tendency information according to the first feature representation by means of a task network, and using a first weight and a second weight of a first gated network to fuse the first tendency information and the second tendency information, so as to obtain first target tendency information. The present application can reduce the interference between different recommendation scenarios, thereby solving the problem that a single-task model is affected by the different distributions of data</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng ; fre |
| recordid | cdi_epo_espacenet_WO2023185925A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | DATA PROCESSING METHOD AND RELATED APPARATUS |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-13T05%3A11%3A28IST&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=DONG,%20Zhenhua&rft.date=2023-10-05&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EWO2023185925A1%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 |