Commodity sequence recommendation method based on attention mechanism
The invention discloses a commodity sequence recommendation method based on an attention mechanism, and the method comprises the steps: obtaining a commodity historical data set of a user, and carrying out the data preprocessing; a multi-head attention mechanism is used for capturing relation depend...
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 | HOU LIXIAN DENG MING XIE GANG LIU CHAO LIU QINGLONG |
| description | The invention discloses a commodity sequence recommendation method based on an attention mechanism, and the method comprises the steps: obtaining a commodity historical data set of a user, and carrying out the data preprocessing; a multi-head attention mechanism is used for capturing relation dependence between articles in recent historical behaviors of the user, and a short-term interest preference vector of the user is obtained; and adding the similarity coefficient of the user and the item in the implicit space into the weight of the attention mechanism, and distributing different weights for the long-term interest to obtain the final representation of the long-term preference. And finally, performing weighted fusion on long and short term preferences to obtain final interest preferences of the user. The method comprises the following steps of: acquiring a correlation score value, then interacting the correlation score value with each article in a candidate set, acquiring the correlation score value in a p |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN114529364A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN114529364A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN114529364A3</originalsourceid><addsrcrecordid>eNrjZHB1zs_NzU_JLKlUKE4tLE3NS05VKEpNBgqm5qUklmTm5ynkppZk5KcoJCUWp6YoAPmJJSWpeVCZ5IzEvMziXB4G1rTEnOJUXijNzaDo5hri7KGbWpAfn1pckJicmpdaEu_sZ2hoYmpkaWxm4mhMjBoAR-Az3Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Commodity sequence recommendation method based on attention mechanism</title><source>esp@cenet</source><creator>HOU LIXIAN ; DENG MING ; XIE GANG ; LIU CHAO ; LIU QINGLONG</creator><creatorcontrib>HOU LIXIAN ; DENG MING ; XIE GANG ; LIU CHAO ; LIU QINGLONG</creatorcontrib><description>The invention discloses a commodity sequence recommendation method based on an attention mechanism, and the method comprises the steps: obtaining a commodity historical data set of a user, and carrying out the data preprocessing; a multi-head attention mechanism is used for capturing relation dependence between articles in recent historical behaviors of the user, and a short-term interest preference vector of the user is obtained; and adding the similarity coefficient of the user and the item in the implicit space into the weight of the attention mechanism, and distributing different weights for the long-term interest to obtain the final representation of the long-term preference. And finally, performing weighted fusion on long and short term preferences to obtain final interest preferences of the user. The method comprises the following steps of: acquiring a correlation score value, then interacting the correlation score value with each article in a candidate set, acquiring the correlation score value in a p</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 ; 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=20220524&DB=EPODOC&CC=CN&NR=114529364A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220524&DB=EPODOC&CC=CN&NR=114529364A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>HOU LIXIAN</creatorcontrib><creatorcontrib>DENG MING</creatorcontrib><creatorcontrib>XIE GANG</creatorcontrib><creatorcontrib>LIU CHAO</creatorcontrib><creatorcontrib>LIU QINGLONG</creatorcontrib><title>Commodity sequence recommendation method based on attention mechanism</title><description>The invention discloses a commodity sequence recommendation method based on an attention mechanism, and the method comprises the steps: obtaining a commodity historical data set of a user, and carrying out the data preprocessing; a multi-head attention mechanism is used for capturing relation dependence between articles in recent historical behaviors of the user, and a short-term interest preference vector of the user is obtained; and adding the similarity coefficient of the user and the item in the implicit space into the weight of the attention mechanism, and distributing different weights for the long-term interest to obtain the final representation of the long-term preference. And finally, performing weighted fusion on long and short term preferences to obtain final interest preferences of the user. The method comprises the following steps of: acquiring a correlation score value, then interacting the correlation score value with each article in a candidate set, acquiring the correlation score value in a p</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>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>eNrjZHB1zs_NzU_JLKlUKE4tLE3NS05VKEpNBgqm5qUklmTm5ynkppZk5KcoJCUWp6YoAPmJJSWpeVCZ5IzEvMziXB4G1rTEnOJUXijNzaDo5hri7KGbWpAfn1pckJicmpdaEu_sZ2hoYmpkaWxm4mhMjBoAR-Az3Q</recordid><startdate>20220524</startdate><enddate>20220524</enddate><creator>HOU LIXIAN</creator><creator>DENG MING</creator><creator>XIE GANG</creator><creator>LIU CHAO</creator><creator>LIU QINGLONG</creator><scope>EVB</scope></search><sort><creationdate>20220524</creationdate><title>Commodity sequence recommendation method based on attention mechanism</title><author>HOU LIXIAN ; DENG MING ; XIE GANG ; LIU CHAO ; LIU QINGLONG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN114529364A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</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>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>HOU LIXIAN</creatorcontrib><creatorcontrib>DENG MING</creatorcontrib><creatorcontrib>XIE GANG</creatorcontrib><creatorcontrib>LIU CHAO</creatorcontrib><creatorcontrib>LIU QINGLONG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>HOU LIXIAN</au><au>DENG MING</au><au>XIE GANG</au><au>LIU CHAO</au><au>LIU QINGLONG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Commodity sequence recommendation method based on attention mechanism</title><date>2022-05-24</date><risdate>2022</risdate><abstract>The invention discloses a commodity sequence recommendation method based on an attention mechanism, and the method comprises the steps: obtaining a commodity historical data set of a user, and carrying out the data preprocessing; a multi-head attention mechanism is used for capturing relation dependence between articles in recent historical behaviors of the user, and a short-term interest preference vector of the user is obtained; and adding the similarity coefficient of the user and the item in the implicit space into the weight of the attention mechanism, and distributing different weights for the long-term interest to obtain the final representation of the long-term preference. And finally, performing weighted fusion on long and short term preferences to obtain final interest preferences of the user. The method comprises the following steps of: acquiring a correlation score value, then interacting the correlation score value with each article in a candidate set, acquiring the correlation score value in a p</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN114529364A |
| 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 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 | Commodity sequence recommendation method based on attention mechanism |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-25T12%3A35%3A48IST&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=HOU%20LIXIAN&rft.date=2022-05-24&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN114529364A%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 |