Apriori method with low consumption

Abstract

The invention relates to an Apriori method with low consumption. The Apriori method is used for mining an associated movement rule of a movement track of an intelligent mobile terminal. The Apriori method comprises the following steps: the time attribute and the space attribute of the movement track of a mobile node are used as mining object data together, the dual attributes, including time and space, of the movement track are fully considered, and a scanning range of a movement track data set is reduced in a process that a frequency item set is generated by a candidate frequency item set to shorten time for obtaining the candidate item set so as to achieve a purpose or consumption reduction. Compared with a traditional Apriori method, the Apriori method provided by the invention is suitable for mining the associated rule of the movement track of the intelligent mobile terminal.

Description

technical field [0001] The present invention relates to a low-cost Apriori method. Background technique [0002] How to mine the hidden knowledge that people are interested in in the massive data has become a research hotspot. In 1994, Agrawal et al. proposed to use the Apriori method to mine the association rules between the database items of customer transactions. This method is divided into the following two parts to complete: First, find all the occurrence frequencies in the database that are greater than or equal to the minimum support Frequent itemsets; then, formulate strong association rules based on the obtained frequent itemsets, and these strong association rules must meet the two basic conditions of minimum credibility and minimum support. [0003] As can be seen from the two parts of the above method implementation, the implementation of the Apriori method is divided into the following two steps: 1. First, use the iterative method to scan all item sets in the d...

AI Technical Summary

Problems solved by technology

[0004] In the transaction database of mining objects in the traditional Apriori method, the internal transaction entries only have spatial attributes, which is not suitable for mining the association rules of mobile node movement trajectories.

[0005] In addition, if the traditional Apriori method is directly transplanted to mobile terminals with limited hardware resources, the efficiency will become very low. Firstly, it needs to consume high storage space to save a large number of candidate item sets during the execution process. Secondly, it needs to consume A long time of CPU resources is used to repeatedly scan the entire movement trajectory data set to obtain all candidate item sets

Images