基于互关联后继树的时间序列相似性查询

时间序列的相似性查询是分析时间序列变化规律的一种重要方法，对于时间序列的分类、预测以及知识发现都具有重要的现实意义。提出了一种基于分段技术的、同时支持可变长度的快速相似性查询方法。其主要思想是：首先依据序列变化的重要点将序列逐步分段，抽取各子段的变化特征，通过分类方法将其转变成符号序列，在此基础上，引入一种称为互关联后继树的全文索引技术，从而实现序列的快速相似性查询，其时间复杂度降到了O(L)，此外，该算法还保证在建立索引后查询结果不会有任何的错误丢失。

A Fast Similarity Query Method Based on Inter-Relevant Successive Trees Model in Time Series

Time series are an important type of data. Similarity querying in time series is a basic task to analyze the changing trend of time series. In this paper, a novel method is proposed, which supports fast search similar pattern in time series. It first segments time series based on a series of perceptually important points, and then time series are converted into meaningful symbol sequences in terms of the segment's features and MATH categorization. After that, a new index model is designed, which is called inter-relevant successive trees(IRST), to achieve fast similarity retrieval in multiple time series. Compared with the previous methods, the method is more efficient and allows different lengths matching.