EP 4066154 A1 20221005 - SYSTEMS AND METHODS FOR DEEP RECOMMENDATIONS USING SIGNATURE ANALYSIS
Title (en)
SYSTEMS AND METHODS FOR DEEP RECOMMENDATIONS USING SIGNATURE ANALYSIS
Title (de)
SYSTEME UND VERFAHREN FÜR TIEFE EMPFEHLUNGEN UNTER VERWENDUNG VON SIGNATURANALYSE
Title (fr)
SYSTÈMES ET PROCÉDÉS DE RECOMMANDATIONS PROFONDES À L'AIDE D'UNE ANALYSE DE SIGNATURE
Publication
Application
Priority
- US 201916698618 A 20191127
- US 201916698625 A 20191127
- US 2020062418 W 20201125
Abstract (en)
[origin: WO2021108707A1] Systems and methods are described herein for providing content item recommendations based on a video. Using feature vectors corresponding to at least one frame of a video (e.g., generated based on texture and shape intensity of a frame), a recommendation system improves content recommendation using analytic and quantitative characteristics derived from a frame of a content item rather than merely manually labeled bibliographic data (e.g., a genre or producer). The recommendation system may generate a feature vector based on a texture, a shape intensity (e.g., generated from a Generalized Hough Transform), and temporal data corresponding to at least one frame of a video. The feature vector is analyzed using a machine learning model (e.g., a neural network) to produce a machine learning model output. The recommendation system causes a recommended content item to be provided based on the machine learning model output.
IPC 8 full level
G06K 9/00 (2022.01); H04N 21/466 (2011.01)
CPC (source: EP US)
G06V 10/48 (2022.01 - EP US); G06V 10/50 (2022.01 - EP US); G06V 10/54 (2022.01 - EP US); G06V 20/46 (2022.01 - EP US); H04N 21/4668 (2013.01 - EP US)
Citation (search report)
See references of WO 2021108707A1
Designated contracting state (EPC)
AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
Designated extension state (EPC)
BA ME
DOCDB simple family (publication)
WO 2021108707 A1 20210603; CA 3143948 A1 20210603; EP 4066154 A1 20221005
DOCDB simple family (application)
US 2020062418 W 20201125; CA 3143948 A 20201125; EP 20828203 A 20201125