公开(公告)号：US20210200824A1

公开(公告)日：2021-07-01

申请号：US17139375

申请日：2020-12-31

Applicant: Samsung Electronics Co., Ltd.

Inventor： Junbeom KIM ,  Jihyun KIM ,  Taehun KIM ,  Kimin OH ,  Hangyul YI

IPC: G06F16/9535 ,  G06K9/62

Abstract: A method and apparatus for personalizing a content recommendation model are provided. The method includes obtaining a first content recommendation model used to recommend content to a user of the electronic device, personalizing the first content recommendation model based on a content use history of the user, receiving a second content recommendation model from a server, receiving a personalization model for personalizing the second content recommendation model from the server, personalizing the second content recommendation model by using input/output data of the personalized first content recommendation model and the personalization model, and providing a content recommendation service to the user by using the personalized second content recommendation model.

公开(公告)号：US20220222712A1

公开(公告)日：2022-07-14

申请号：US17526421

申请日：2021-11-15

Applicant: Samsung Electronics Co., Ltd.

Inventor： Junbeom KIM ,  Kimin OH ,  Taeho HWANG ,  Kiwon CHOI

IPC: G06Q30/02 ,  G06N3/04

Abstract: A server and a method for generating a user-advertisement (user-ad) matching list for online advertisement is provided. The method includes obtaining profile information and advertisement exposure history information of users exposed to a plurality of advertisements through an ad impression server, obtaining advertisement information of an advertisement to be delivered by an advertiser, identifying candidate users for the advertisement of the advertiser among the users, based on the profile information of the users, predicting an access time when the candidate users will access the ad impression server, selecting target users to be provided with the advertisement of the advertiser among the candidate users, based on the predicted access time, obtaining a preference of each target user for an advertisement product of the advertiser, and generating the user-ad matching list by matching the advertisement of the advertiser with the target users, based on the preference.