Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020111571 - ARTIFICIAL INTELLIGENCE-BASED SEVERE DELINQUENCY DETECTION DEVICE AND METHOD

Publication Number WO/2020/111571
Publication Date 04.06.2020
International Application No. PCT/KR2019/015258
International Filing Date 11.11.2019
IPC
G06Q 40/02 2012.01
GPHYSICS
06COMPUTING; CALCULATING OR 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
40Finance; Insurance; Tax strategies; Processing of corporate or income taxes
02Banking, e.g. interest calculation, credit approval, mortgages, home banking or on-line banking
G06Q 40/00 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR 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
40Finance; Insurance; Tax strategies; Processing of corporate or income taxes
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 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
G06Q 40/025
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
40Finance; Insurance; Tax strategies; Processing of corporate or income taxes
02Banking, e.g. interest calculation, credit approval, mortgages, home banking or on-line banking
025Credit processing or loan processing, e.g. risk analysis for mortgages
G06Q 40/12
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
40Finance; Insurance; Tax strategies; Processing of corporate or income taxes
12Accounting
Applicants
  • (주) 위세아이텍 WISEITECH CO., LTD. [KR]/[KR]
Inventors
  • 김지혁 KIM, Ji Hyeok
  • 이지현 LEE, Ji Hyeon
  • 조아라 CHO, Ara
Agents
  • 유민규 YOU, Min Gyu
Priority Data
10-2018-014755026.11.2018KR
Publication Language Korean (KO)
Filing Language Korean (KO)
Designated States
Title
(EN) ARTIFICIAL INTELLIGENCE-BASED SEVERE DELINQUENCY DETECTION DEVICE AND METHOD
(FR) DISPOSITIF ET PROCÉDÉ DE DÉTECTION DE DÉLINQUANCE GRAVE À BASE D'INTELLIGENCE ARTIFICIELLE
(KO) 인공지능 기반 악성 연체 탐지 장치 및 방법
Abstract
(EN)
An artificial intelligence-based severe delinquency detection device according to an embodiment of the present application can comprise: a data pre-processing unit for calculating a characteristic variable from rental fee payment history data; a pattern detection unit for detecting a normal pattern and a delinquency pattern on the basis of an abnormality detection algorithm taking the characteristic variable as an input; a new pattern classification unit for classifying a new pattern of rental fee payments on the basis of an unsupervised learning-based clustering algorithm taking the normal pattern and delinquency pattern as inputs; and a new payment pattern detection unit for detecting a severe pattern of a new severe delinquent by constructing a pattern distinguishing model taking the normal pattern, delinquency pattern and new pattern as inputs.
(FR)
Un dispositif de détection de délinquance grave à base d'intelligence artificielle selon un mode de réalisation de la présente invention peut comprendre : une unité de prétraitement de données permettant de calculer une variable caractéristique à partir de données d'historique de paiement de loyer ; une unité de détection de motif permettant de détecter un motif normal et un motif de délinquance en fonction d'un algorithme de détection d'anomalie recevant la variable caractéristique en entrée ; une unité de classification de nouveau motif permettant de classifier un nouveau motif de paiements de loyer en fonction d'un algorithme de groupement à base d'apprentissage non supervisé recevant le motif normal et le motif de délinquance en entrée ; et une unité de détection de nouveau motif de paiement permettant de détecter un motif grave d'un nouveau délinquant grave en construisant un modèle de distinction de motifs recevant le motif normal, le motif de délinquance et le nouveau motif en entrée.
(KO)
본원의 일 실시예에 따른 인공지능 기반 악성 연체 탐지 장치는 렌탈비 납부 내역 데이터로부터 특질 변수를 산출하는 데이터 전처리부, 상기 특질 변수를 입력으로 하는 이상 탐지 알고리즘에 기초하여 정상 패턴 및 연체 패턴을 검출하는 패턴 검출부, 상기 정상 패턴 및 연체 패턴을 입력으로 하는 비지도 학습 기반의 군집 알고리즘에 기초하여 렌탈비 납부의 신규 패턴을 분류하는 신규 패턴 분류부 및 상기 정상 패턴, 상기 연체 패턴 및 상기 신규 패턴을 입력으로 하는 패턴 판별 모델을 구축하여 신규 악성 연체자의 악성 패턴을 검출하는 신규 납부 패턴 검출부를 포함할 수 있다.
Also published as
Latest bibliographic data on file with the International Bureau