METHOD FOR DIALOG MANAGEMENT BASED ON MULTI-USER USING MEMORY CAPACITY AND APPARATUS FOR PERFORMING THE METHOD

The present invention relates to a chatting management method based on a multi-user. According to an embodiment of the present invention, the chatting management method based on the multi-user includes: a step of receiving an input sentence from the multi-user; a step of building chatting history da...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	CHOI, JUN HWI, KOO, SANG JUN, LEE, GEUN BAE, BANG, JEE SOO, NAM, DAE HWAN, RYU, SEONG HAN
Format:	Patent
Sprache:	eng ; kor
Schlagworte:	CALCULATING COMPUTING COUNTING DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES ELECTRIC DIGITAL DATA PROCESSING 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 invention relates to a chatting management method based on a multi-user. According to an embodiment of the present invention, the chatting management method based on the multi-user includes: a step of receiving an input sentence from the multi-user; a step of building chatting history database by analyzing the input sentence of each user and storing the same based on each user; a step of extracting unit knowledge from the input sentence and building ontology by selecting the unit knowledge based on whether there is user information for identifying the multi-user; and a step of generating a proper system response to the input sentence by modifying a previously extracted system response candidate based on ontology. Accordingly, the present invention can supply a customized chatting service for each user. 다중 사용자 기반의 대화 관리 방법 및 장치가 개시된다. 본 발명의 일 실시예에 따른 다중 사용자 기반의 대화 관리 방법은 다중 사용자로부터 입력 문장을 수신하는 단계, 입력 문장을 분석하여 사용자 별로 저장함으로써 대화 이력 데이터베이스를 구축하는 단계, 입력 문장으로부터 단위 지식을 추출하고, 다중 사용자를 식별할 수 있는 사용자 정보의 유무를 기반으로 단위 지식을 선별하여 온톨로지를 구축하는 단계 및 대화 이력 데이터베이스 및 온톨로지를 기반으로 미리 추출된 시스템 응답 후보를 수정하여 입력 문장에 적합한 시스템 응답을 생성하는 단계를 포함한다. 따라서, 사용자 각각에게 맞춤형 대화 서비스를 제공할 수 있다.