Time series data complement method, device and electronic device

Abstract

The invention discloses a method for completing time series data, a device and an electronic device. The method comprises the following steps of: constructing a data set according to a set format of the collected data; the data set comprises at least a series of data; the data set comprises at least a series of data. Inserting a point in time at which each series needs to be completed into the data set; Repartition the data set inserted into the time point according to the series, and put the same series of data into the same partition; Sorting the data within the partition to obtain a data list; Traversing the data in the partition and completing the data respectively. Under the distributed computing framework, the method can complete the missing time series data forward or backward, andonly a small number of variables need to be traversed once to complete the data completion.

Description

technical field [0001] The present invention relates to the field of computer technology, and more specifically, to a time series data completion method, device and electronic equipment. Background technique [0002] With the rapid development of computer science technology, Internet technology, and Internet of Things technology, the amount of information has exploded, and it is becoming more and more difficult to find useful information, and it is becoming more and more difficult to process all the required data in one server. It is getting more and more difficult, and the emergence of distributed computing framework just solves this problem, so that data can be distributed in different servers and processed in parallel, thus solving the performance bottleneck of a single server. [0003] Time series refers to the sequence of the values ​​of the same indicator arranged in chronological order, which exists in large quantities in human society and nature, such as financial da...

AI Technical Summary

Problems solved by technology

[0004] The current time series similarity method is mainly aimed at the situation where there is no missing data, but in the application of actual scenarios, it is impossible to ensure that there is data at every moment

For example, in the application of the Internet of Things, there may be multiple devices, and the sampling time of each device cannot be guaranteed to be exactly the same. If the sampling time of one of the devices is used as the benchmark to analyze other devices, there will be a large number of time series missing value

Images