FEATURE EMBEDDING IN MATRIX FACTORIZATION

FEATURE EMBEDDING IN MATRIX FACTORIZATION

In various embodiments, systems and methods are provided for enhancing media content recommendations by using feature vectors. An enhanced-matrix having a first portion and a second portion is received. The first portion of the enhanced-matrix includes a user-item matrix and the second portion of th...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: KEREN SHAHAR ZVI, JAFFRAY ANDREW, PAQUET ULRICH, KOENIGSTEIN NOAM, NICE NIR
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
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 KEREN SHAHAR ZVI
JAFFRAY ANDREW
PAQUET ULRICH
KOENIGSTEIN NOAM
NICE NIR
description In various embodiments, systems and methods are provided for enhancing media content recommendations by using feature vectors. An enhanced-matrix having a first portion and a second portion is received. The first portion of the enhanced-matrix includes a user-item matrix and the second portion of the enhanced-matrix includes a feature-item matrix. Each entry in the feature-item matrix is item metadata. An item-stem vector is determined based on a weighted sum of each of the feature vectors associated with the item. An item-latent-trait vector is generated based on the item-stem vector and an item-offset vector. The item-offset vector is an item vector for the item in the user-item matrix. One or more recommended-media content derived based on the item-latent-trait vector is provided.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2014181121A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2014181121A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2014181121A13</originalsourceid><addsrcrecordid>eNrjZNB0c3UMCQ1yVXD1dXJ1cfH0c1fw9FPwdQwJ8oxQcHN0DvEP8oxyDPH09-NhYE1LzClO5YXS3AzKbq4hzh66qQX58anFBYnJqXmpJfGhwUYGhiaGFoaGRoaOhsbEqQIAvFIlQg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>FEATURE EMBEDDING IN MATRIX FACTORIZATION</title><source>esp@cenet</source><creator>KEREN SHAHAR ZVI ; JAFFRAY ANDREW ; PAQUET ULRICH ; KOENIGSTEIN NOAM ; NICE NIR</creator><creatorcontrib>KEREN SHAHAR ZVI ; JAFFRAY ANDREW ; PAQUET ULRICH ; KOENIGSTEIN NOAM ; NICE NIR</creatorcontrib><description>In various embodiments, systems and methods are provided for enhancing media content recommendations by using feature vectors. An enhanced-matrix having a first portion and a second portion is received. The first portion of the enhanced-matrix includes a user-item matrix and the second portion of the enhanced-matrix includes a feature-item matrix. Each entry in the feature-item matrix is item metadata. An item-stem vector is determined based on a weighted sum of each of the feature vectors associated with the item. An item-latent-trait vector is generated based on the item-stem vector and an item-offset vector. The item-offset vector is an item vector for the item in the user-item matrix. One or more recommended-media content derived based on the item-latent-trait vector is provided.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2014</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&amp;date=20140626&amp;DB=EPODOC&amp;CC=US&amp;NR=2014181121A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20140626&amp;DB=EPODOC&amp;CC=US&amp;NR=2014181121A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>KEREN SHAHAR ZVI</creatorcontrib><creatorcontrib>JAFFRAY ANDREW</creatorcontrib><creatorcontrib>PAQUET ULRICH</creatorcontrib><creatorcontrib>KOENIGSTEIN NOAM</creatorcontrib><creatorcontrib>NICE NIR</creatorcontrib><title>FEATURE EMBEDDING IN MATRIX FACTORIZATION</title><description>In various embodiments, systems and methods are provided for enhancing media content recommendations by using feature vectors. An enhanced-matrix having a first portion and a second portion is received. The first portion of the enhanced-matrix includes a user-item matrix and the second portion of the enhanced-matrix includes a feature-item matrix. Each entry in the feature-item matrix is item metadata. An item-stem vector is determined based on a weighted sum of each of the feature vectors associated with the item. An item-latent-trait vector is generated based on the item-stem vector and an item-offset vector. The item-offset vector is an item vector for the item in the user-item matrix. One or more recommended-media content derived based on the item-latent-trait vector is provided.</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>2014</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZNB0c3UMCQ1yVXD1dXJ1cfH0c1fw9FPwdQwJ8oxQcHN0DvEP8oxyDPH09-NhYE1LzClO5YXS3AzKbq4hzh66qQX58anFBYnJqXmpJfGhwUYGhiaGFoaGRoaOhsbEqQIAvFIlQg</recordid><startdate>20140626</startdate><enddate>20140626</enddate><creator>KEREN SHAHAR ZVI</creator><creator>JAFFRAY ANDREW</creator><creator>PAQUET ULRICH</creator><creator>KOENIGSTEIN NOAM</creator><creator>NICE NIR</creator><scope>EVB</scope></search><sort><creationdate>20140626</creationdate><title>FEATURE EMBEDDING IN MATRIX FACTORIZATION</title><author>KEREN SHAHAR ZVI ; JAFFRAY ANDREW ; PAQUET ULRICH ; KOENIGSTEIN NOAM ; NICE NIR</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2014181121A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2014</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>KEREN SHAHAR ZVI</creatorcontrib><creatorcontrib>JAFFRAY ANDREW</creatorcontrib><creatorcontrib>PAQUET ULRICH</creatorcontrib><creatorcontrib>KOENIGSTEIN NOAM</creatorcontrib><creatorcontrib>NICE NIR</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>KEREN SHAHAR ZVI</au><au>JAFFRAY ANDREW</au><au>PAQUET ULRICH</au><au>KOENIGSTEIN NOAM</au><au>NICE NIR</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>FEATURE EMBEDDING IN MATRIX FACTORIZATION</title><date>2014-06-26</date><risdate>2014</risdate><abstract>In various embodiments, systems and methods are provided for enhancing media content recommendations by using feature vectors. An enhanced-matrix having a first portion and a second portion is received. The first portion of the enhanced-matrix includes a user-item matrix and the second portion of the enhanced-matrix includes a feature-item matrix. Each entry in the feature-item matrix is item metadata. An item-stem vector is determined based on a weighted sum of each of the feature vectors associated with the item. An item-latent-trait vector is generated based on the item-stem vector and an item-offset vector. The item-offset vector is an item vector for the item in the user-item matrix. One or more recommended-media content derived based on the item-latent-trait vector is provided.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US2014181121A1
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title FEATURE EMBEDDING IN MATRIX FACTORIZATION
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-06T23%3A01%3A53IST&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=KEREN%20SHAHAR%20ZVI&rft.date=2014-06-26&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2014181121A1%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