Mining method of massive data of mobile library under information asymmetry facing large-scare database

摘要

The current method generates a large number of candidate sets when mining data in mobile libraries under asymmetric information, and the mining time and efficiency are poor. To this end, a new method for mobile library massive data mining based on improved Apriori algorithm is proposed to collect, clean and reduce massive data. Calculate the reader?s interest distance by analyzing the borrowed historical data, and use the Apriori algorithm to find the association rules in the frequent itemsets of the data. In order to make up for the shortcomings of the current method, while filtering out infrequent candidate sets, the corresponding transaction set is also collaboratively filtered, which can reduce the amount of calculation and time consumption. Experimental results show that the proposed method can mine more valuable rules. The improved execution time is only 10 s, the CPU utilization exceeds 90%, and the acceleration ratio exceeds 1.81 s, which can better meet the needs of decision makers.