Optimization of Teaching Management System Based on Association Rules Algorithm

Table 3

The pseudocode of the algorithm.

Input	Item Ai, weight wi, and transaction database D
Intermediate process	Sort the items in the set according to the size of the weight to form a linear order set.
	According to formula (1), obtain the support degree.
	According to formula (2), find the confidence Con.
	According to formula (3), find the interest degree Int.
	If Int > 1, correlated. If Int ≤ 1, negatively correlated.
	If Int ≥ min_Int, Int is the minimum interest.
	Split the transaction database D horizontally and send n data blocks to m nodes.
	Turn into the corresponding minimum interest in turn.
	Scan to get frequent itemsets.
	Generate a local frequent matrix.
	Compress the rows and columns of the matrix.
	Steps are transformed into local frequent itemsets.
	Combine key-value pairs with the same key <c, c.sup>
	Calculate the local support to form the union Lk.
Output	The association rules that meet the requirements are obtained.