Time sequence similarity search method, recording medium and system

Abstract

The invention belongs to the technical field of data mining, and particularly relates to a time sequence similarity search method, which comprises the following steps of: acquiring a time sequence data set and performing linear transformation, so that a result value is mapped between (0, 1); dividing the data set into an index sequence and a query sequence, constructing a cumulative distance matrix, and preliminarily judging the similarity of the index sequence and the query sequence; and initializing the boundary of the cumulative distance matrix, calculating the cumulative distance line by line, stopping calculation when an early termination condition is met, filtering the index sequence, and calculating the most similar matching result from the remaining candidate index sequences which are not terminated in advance. According to the method, a large amount of redundant calculation of the DTW is reduced, and the time sequence similarity search efficiency is effectively improved. The invention also provides a non-transitory readable recording medium storing a program of the method and a system comprising the medium, and the program can be called by a processing circuit to execute the method.

Description

technical field [0001] The invention belongs to the technical field of data mining, and discloses a time series similarity search method, a recording medium and a system storing a program capable of executing the method. Background technique [0002] With the rapid development of computer science and technology, the data generated by the Internet, meteorology, astronomy, industry and commerce, medical care and other fields has exploded. How to transform data into organized knowledge and provide guidance and help for people's production and living practices and even decision-making activities has become an extremely urgent need in the era of big data. Time series is one of many data types, and refers to an ordered data sequence formed over time. Time series widely exist in different application fields, such as the ECG data of patients in the medical field, the real-time price of stocks in the financial field, the real-time monitoring data of temperature and humidity in the m...

AI Technical Summary

Problems solved by technology

However, the principles of the above two methods are simplified algorithms. Although they can effectively reduce redundant calculations, they cannot avoid complex and time-consuming calculations of accurate dynamic time warping distances. Therefore, the efficiency improvement is very limited when dealing with large-scale time series.

Images