System for multi-layered knowledge base and processing method thereof
Provided are a multi-layered knowledge base system and a processing method thereof. In the knowledge base system, semantic space learning of converting learning data into a semantic vector, which is a vector of semantic space, by learning a transformation function based on a plurality of learning da...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Patent |
Sprache: | eng ; kor |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Provided are a multi-layered knowledge base system and a processing method thereof. In the knowledge base system, semantic space learning of converting learning data into a semantic vector, which is a vector of semantic space, by learning a transformation function based on a plurality of learning data is performed. Then, relational knowledge learning of acquiring a relation between the semantic vectors by learning a relation function based on the semantic vectors obtained by the semantic space learning is performed. The acquired relation is converted into graph knowledge and stored. The graph knowledge uses the relation as an edge and the semantic vector corresponding to the relation as a node. Therefore, various services are made possible with one knowledge base.
다계층 지식베이스 시스템 및 그의 처리 방법이 제공된다. 지식 베이스 시스템에서, 복수의 학습 데이터를 기반으로 변환 함수를 학습하여 학습 데이터를 의미 공간의 벡터인 의미 벡터로 변환하는 의미 공간 학습을 수행한다. 그리고 의미 공간 학습에 따라 획득되는 의미 벡터들을 기반으로 관계 함수를 학습하여 의미 벡터들 간의 관계를 획득하는 관계 지식 학습을 수행한다. 다음에, 획득되는 관계를 그래프 지식으로 변환하여 저장하며, 그래프 지식은 관계를 에지로 하고 관계에 대응하는 의미 벡터를 노드로 한다. |
---|