公开(公告)号：KR100912371B1

公开(公告)日：2009-08-19

申请号：KR1020070132589

申请日：2007-12-17

Applicant: 한국전자통신연구원

Inventor： 이규웅 ,  이미영 ,  이훈순 ,  김명준

IPC: G06F17/30

CPC classification number: G06F17/30327 ,  G06F17/30333

Abstract: Provided are a system and a method for indexing high-dimensional data in parallel in a cluster environment. The system for indexing high-dimensional data in parallel in a cluster environment includes a Spill-tree creation means for creating a Spill-tree using an sampled N-dimensional feature vector, a feature vector division storage means for distributedly storing the N-dimensional feature vector in a terminal node of the Spill-tree, and a local signature creation means for creating and managing a local signature for the N-dimensional feature vector dispersed into each node of the Spill-tree.

公开(公告)号：KR1020090065137A

公开(公告)日：2009-06-22

申请号：KR1020070132589

申请日：2007-12-17

Applicant: 한국전자통신연구원

Inventor： 이규웅 ,  이미영 ,  이훈순 ,  김명준

IPC: G06F17/30

CPC classification number: G06F17/30327 ,  G06F17/30333

Abstract: A large capacity high dimensional data indexing device supporting high-expandability in a cluster environment and a method thereof are provided to filter content-based search about high dimensional data first by using a spill tree and perform parallel search by using a signature in each node, thereby supporting rapid performance. A spill tree generation unit(210) generates a spill tree by extracting a sample of an N-dimensional feature vector. A feature vector divided storage unit(220) dividedly stores the N-dimensional feature vector in a terminal node of the spill tree. A local signature generation unit generates a signature locally about the N-dimensional feature vector distributed into each node of the spill tree.

Abstract translation: 提供了一种支持群集环境中的高扩展性的大容量高维数据索引设备及其方法，其首先通过使用溢出树来过滤关于高维数据的基于内容的搜索，并且通过使用每个节点中的签名进行并行搜索， 从而支持快速表现。 溢出树生成单元（210）通过提取N维特征向量的样本来生成溢出树。 特征矢量分割存储部（220）将N维特征矢量分割地存储在溢出树的终端节点中。 本地签名生成单元本地生成分布在溢出树的每个节点中的N维特征向量的签名。