Association rule mining method and association rule mining device

Abstract

The invention discloses an association rule mining method. The mining method includes the following steps that a transaction set is acquired and scanned, the transaction set is converted into a multidimensional data cube, and the length of the entire transaction set is recorded; 1-item set and a 1-item frequent set are obtained according to the multidimensional data cube; a k-item set and a k-item frequent set are obtained according to the 1-item frequent set, and a k+1-item set and a k+1-item frequent set are obtained according to the k-item frequent set, wherein the k is a positive integer greater than or equal to 2; all subsets of the 1-item frequent set and all subsets of the k-item frequent set are generated according to the 1-item frequent set and the k-item frequent set so as to generate association rules of the transaction set. The association rule mining method can shorten the operation time of a system.

Description

technical field [0001] The invention relates to the field of remote sensing images, in particular to an association rule mining method and an association rule mining device. Background technique [0002] Association rule mining is a very important branch in the field of data mining, which is mainly used to find frequent item sets that satisfy the user's minimum support from transaction sets with large amounts of data. For remote sensing image data mining, the process can be understood as extracting different levels of knowledge from remote sensing images, analyzing the relationship between knowledge, so as to dig out the potential regular knowledge hidden in remote sensing images. [0003] The existing Sampling algorithm, Partition algorithm, DIC algorithm, etc. all try to reduce the number of searches in the transaction data collection, but there are still many shortcomings. The Sampling algorithm randomly samples some samples from the original data set, and uses the sampl...

AI Technical Summary

Problems solved by technology

Each calculation not only takes a lot of CPU time, but also involves I / O requests

[0004] That is to say, the existing association rule mining algorithm needs to traverse the transaction database multiple times, resulting in low mining efficiency and a large amount of CPU time.

In addition, the existing Apriori, FP-Growth and their improved algorithms have certain requirements on the data, that is, in the same transaction, the value of the item cannot be the same, otherwise the mining algorithm will not be able to run

Images