A spatio-temporal data association analysis method based on big data technology

Abstract

The invention relates to a spatio-temporal data association analysis method based on big data technology, which can generate frequent itemsets according to the spatial and temporal relationship of data during spatio-temporal trajectory data mining, and according to a certain data type, the set with the smallest total amount of data Generate all frequent itemsets in a loop, increasing the time complexity of traditional data mining analysis algorithms from O(n^n) to O(n); by optimizing the input parameters of mining frequent itemsets algorithms, changing frequency to frequency, The accuracy of data analysis is improved; and combined with the big data technology based on memory computing, the speed of association analysis of spatiotemporal trajectory data is greatly improved. The present invention is especially suitable for the field of data mining where there are various types of association analysis data, each type of data is extremely large, and the data association results need to be quickly analyzed.

Description

technical field [0001] The invention relates to a spatio-temporal data correlation analysis method, in particular to a method for spatio-temporal trajectory data correlation analysis based on the big data of a specific industry and using a frequent itemset mining algorithm. Background technique [0002] With the development of computer technology, various analysis methods are now widely used in data comparison, data statistics, data mining and other fields. It is relatively slow and inefficient. The traditional analysis techniques are described in detail as follows. [0003] The specific steps of the first typical spatio-temporal trajectory data association analysis method are to extract a type of data that needs to be associated from the data, cycle through the list of such data, and then compare the data to be associated with the associated data one by one. Satisfy the association conditions, and feedback the comparison results one by one. Therefore, when there are many ...

AI Technical Summary

Problems solved by technology

Therefore, before the Apriori algorithm generates a complete set of frequent patterns, it needs to scan the database multiple times, and at the same time generate a large number of candidate frequent sets, which makes the time and space complexity of the Apriori algorithm larger.

The performance of the Apriori algorithm is often low when mining long-term frequent patterns

[0005] In the context of the advent of the big data era, the above-mentioned traditional spatio-temporal trajectory data association methods are completely unable to meet people's needs for fast data association and data mining, and the speed problem is also the main shortcoming of traditional technologies

Images