METHOD AND SYSTEM FOR PROVIDING REGIONAL-BASED RECOMMENDATION SERVICE

The present disclosure relates to a method for providing a region-based recommendation service, executed by at least one process. The method comprises the steps of: receiving user information collected during a first period in an application through a user account subscribed to the application that...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	LEE YOUNG MOO, HAN SEUNG HO, JEON MU IK
Format:	Patent
Sprache:	eng ; kor
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES PHYSICS SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	The present disclosure relates to a method for providing a region-based recommendation service, executed by at least one process. The method comprises the steps of: receiving user information collected during a first period in an application through a user account subscribed to the application that provides a region-based recommendation service; extracting information related to one or more recently posted posts among a plurality of posts uploaded through the application; calculating a user's expected level of interest in each of the one or more posts by inputting user information and information associated with the one or more extracted posts into a machine learning model; and determining a posting order of at least some of a plurality of posts including the one or more posts, based on the calculated user's expected level of interest, in order to recommend customized postings for the user account. According to the present invention, a region-based recommendation service based on collected user information can be provided. 본 개시는 적어도 하나의 프로세서에 의해 실행되는, 지역 기반 추천 서비스를 제공하는 방법에 관한 것이다. 이 방법은, 지역 기반 추천 서비스를 제공하는 어플리케이션에 가입된 사용자 계정을 통해 어플리케이션 내에서의 제1 기간 동안에 수집된 사용자 정보를 수신하는 단계, 어플리케이션을 통해 업로드된 복수의 게시글 중에서, 최근에 게시된 하나 이상의 게시글과 연관된 정보를 추출하는 단계, 사용자 정보 및 추출된 하나 이상의 게시글과 연관된 정보를 기계학습 모델에 입력하여, 하나 이상의 게시글의 각각에 대한 사용자 예상 관심도를 산출하는 단계, 사용자 계정을 위한 맞춤형 게시글 추천을 위하여, 산출된 사용자 예상 관심도를 기초로, 하나 이상의 게시글을 포함한 복수의 게시글 중 적어도 일부의 게시 순서를 결정하는 단계를 포함한다.