Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020092488 - TECHNIQUES FOR RECOMMENDING ITEMS TO USERS

Publication Number WO/2020/092488
Publication Date 07.05.2020
International Application No. PCT/US2019/058742
International Filing Date 30.10.2019
IPC
G06N 5/00 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
G06N 3/08 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
CPC
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
G06N 5/003
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
003Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
G06Q 30/0631
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
30Commerce, e.g. shopping or e-commerce
06Buying, selling or leasing transactions
0601Electronic shopping
0631Item recommendations
G06Q 30/0633
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
30Commerce, e.g. shopping or e-commerce
06Buying, selling or leasing transactions
0601Electronic shopping
0633Lists, e.g. purchase orders, compilation or processing
G06Q 30/0643
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
30Commerce, e.g. shopping or e-commerce
06Buying, selling or leasing transactions
0601Electronic shopping
0641Shopping interfaces
0643Graphical representation of items or shoppers
Applicants
  • NETFLIX, INC. [US]/[US]
Inventors
  • STECK, Harald
Agents
  • CAREY, John C.
  • MIRZA, Sarah
  • WELCH, Henry
Priority Data
16/664,76125.10.2019US
62/754,53601.11.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) TECHNIQUES FOR RECOMMENDING ITEMS TO USERS
(FR) TECHNIQUES POUR RECOMMANDER DES ARTICLES À DES UTILISATEURS
Abstract
(EN)
In various embodiments, a training application generates a preference prediction model based on an interaction matrix and a closed-form solution for minimizing a Lagrangian. The interaction matrix reflects interactions between users and items, and the Lagrangian is formed based on a constrained optimization problem associated with the interaction matrix. A service application generates a first application interface that is to be presented to the user. The service application computes predicted score(s) using the preference prediction model, where each predicted score predicts a preference of the user for a different item. The service application then determines a first item from the items to present to the user via an interface element included in the application interface. Subsequently, the service application causes a representation of the first item to be displayed via the interface element included in the application interface.
(FR)
Selon divers modes de réalisation, cette invention concerne une application d'apprentissage automatique qui génère un modèle de prédiction de préférences sur la base d'une matrice d'interactions et d'une solution de forme fermée pour minimiser une fonction de Lagrange. La matrice d'interactions reflète des interactions entre des utilisateurs et des articles, et la fonction de Lagrange est formée sur la base d'un problème d'optimisation sous contrainte associé à la matrice d'interactions. Une application de service génère une première interface d'application destinée à être présentée à l'utilisateur. L'application de service calcule un/des score(s) prédit(s) à l'aide du modèle de prédiction de préférences, chaque score prédit prédisant une préférence de l'utilisateur pour un article différent. L'application de service détermine ensuite un premier article parmi les articles à présenter à l'utilisateur par l'intermédiaire d'un élément d'interface inclus dans l'interface d'application. Ensuite, l'application de service provoque l'affichage d'une représentation du premier article par l'intermédiaire de l'élément d'interface inclus dans l'interface d'application.
Latest bibliographic data on file with the International Bureau