Research on Association Mining Method of Frequent Itemsets in High-dimensional Multi-source Big Data

The conventional association mining method of frequent itemsets in high-dimensional multi-source big data mainly uses the framework of Parameter Server to solve the problem, which is easily influenced by the change of data attribute relationship, resulting in low accuracy of data association mining. Therefore, it is necessary to design a new association mining method of frequent itemsets in high-dimensional multi-source big data. That is, the association mining strategy of high-dimensional big data frequent itemsets is generated, and the association mining algorithm of high-dimensional multi-source big data frequent itemsets is designed, thus realizing the association mining of high-dimensional multi-source big data frequent itemsets. The experimental results show that the designed association mining method for frequent itemsets of high-dimensional multi-source big data has high accuracy, which proves that the designed association mining method has good mining effect, reliability and certain application value, and has made certain contributions to improving the processing efficiency of high-dimensional multi-source big data.