Tuple measurement method and system based on CFI-Apriori algorithm in foggy environment

Abstract

The invention provides a tuple measurement method and a system based on a CFI-Apriori algorithm in a foggy environment, and the method and the system can effectively utilize the hidden information ofa non-frequent item set lost in an iteration process of an original Apriori algorithm, and improve the effective utilization rate and accuracy of data. The method comprises the following steps: acquiring original data on a fog node; associating the acquired original data locally at the fog node by using a CFI-based Apriori algorithm to generate a frequent item set, and storing a candidate frequentitem set of which the pruning process is less than the minimum support degree, the CFI represents the candidate frequent item set, and the candidate frequent item set of which the pruning process isless than the minimum support degree is a non-frequent item set; and uploading the obtained original data, the generated frequent item set and the stored infrequent item set to a cloud server, so thatthe cloud server associates and measures the received original data according to the received frequent item set and infrequent item set, and extracts the data according to a measurement result. The invention relates to the technical field of communication.

Description

technical field [0001] The invention relates to the field of communication technology, in particular to a tuple measurement method and system based on the CFI-Apriori algorithm in a fog environment. Background technique [0002] In recent years, with the development of social networks, information technology is also constantly innovating. Social networks, e-commerce, and artificial intelligence have entered a period of vigorous development. Network data presents the characteristics of massive, complex structures, and difficult to trace dynamics. Unstructured data is flooding every corner of the social network. We have entered the era of big data, and the correlation between data is getting closer and more complex. Mining the value hidden in linked data is worth exploring and researching. [0003] With the improvement of wireless network and sensing technology, the coverage area of ​​wireless network is further expanded. The existing cloud computing framework can satisfy mos...

AI Technical Summary

Problems solved by technology

[0003] With the improvement of wireless network and sensing technology, the coverage area of ​​wireless network is further expanded. The existing cloud computing framework can satisfy most of the fixed network users, but it cannot meet the diversified service requirements of new intelligent mobile terminals. In order to adapt to the new demand, Cisco first proposed the concept of fog computing

The advantage of using the Apriori algorithm in the fog node is that it can easily find out the relationship between the data, but according to the nature of the Apriori algorithm, the Apriori algorithm will delete the candidate frequent itemsets that are less than the minimum support. Some hidden information is lost, resulting in a decrease in data accuracy, and the associated data samples contain information on frequent itemsets and infrequent itemsets at different item levels, the sample information is messy, and the effective utilization rate of data is low

Images