Time sequence data stream clustering method based on wavelet attenuation synopsis tree

Abstract

The invention discloses a time sequence data stream clustering method based on a wavelet attenuation synopsis tree. Firstly, time sequence attenuation characteristics are introduced into a wavelet synopsis structure, a multi-dimensional time sequence tree-like attenuation synopsis construction method based on wavelet transformation is provided, a good approximation of an original sequence can be reconstructed by reserving r<n most important wavelet coefficients, the influence of 'dimension disasters' is relieved, the synopsis structure is constructed, and a time sequence is approximately represented. On the basis, similar characteristics of data stream are rapidly extracted based on the synopsis structure, the approximate distance between the data stream and a clustering center is calculated, and the K-means clustering method is suitable for the multi-dimensional time sequence data stream and solves the problem that a traditional clustering method cannot be directly applied to the data stream with infinite length, evolution with time and large data volume.

Description

technical field [0001] The invention relates to the technical field of data flow mining, in particular to a time series data flow clustering method based on a wavelet attenuation summary tree. It is especially suitable for the large number of users and resources in smart business and smart financial applications. It stores multi-dimensional time series data streams, compresses and clusters them through cloud computing and electronic tags. technical background [0002] With the rapid development of Internet of Things technology, cloud computing, mobile Internet technology, electronic label technology, etc., based on the increasing demand for technology in the macro environment of the retail industry, data stream mining technology has become an important means to reduce operating costs and improve operational efficiency. However, due to the continuous generation of a large amount of sequential data that evolves over time in smart retail, a time-series data flow containing info...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the deficiencies of existing methods in storing and mining time series data streams with various characteristics such as dynamicity, nonlinearity, high dimensionality, complexity, and redundancy, the present invention provides a method that can reflect the attenuation characteristics of data streams Wavelet Summary Structure and Efficient Dataflow Knowledge Mining A Time Series Dataflow Clustering Method Based on Wavelet Decay Summary Tree

Images