Construction and Optimization of Mental Health Education Consultation Management System Based on Decision Tree Association Rule Mining

This paper studies association rule mining and decision tree algorithm, focusing on the extended research of association rule mining, including the number of generated rules, mining association rules of long itemsets with low support, attribute selection criteria and multivalue attributes in decision tree algorithm. This paper conducts in-depth research and analysis on the design and optimization of the mental health education consultation management system using the association rule decision tree algorithm. This paper analyzes the meaning of parameters under the support-confidence-interest model, and uses regression method to design equations between the number of rules and parameters. We use the multiple correlation coefficient to test the fitting effect of the equation, and use the significance test to verify whether the coefficient of the parameter is significantly zero. On the one hand, the widely used psychological crisis prevention measures generally include the screening of the SCL psychological scale in the early stage of first-year enrolment, the holding of general psychological knowledge lectures and courses, and the opening of psychological counselling rooms with a low penetration rate, but these practices are to a certain extent. In other words, it cannot enable the student administrator to grasp the psychological status of the students in a timely, effective, and dynamic manner, to timely intervene in the possible crisis. Not only the number of attribute values of the current node is considered but also the size of the variable precision clear area of the lower node is considered, that is, the two-layer nodes of the tree are considered at the same time. The new attribute selection method not only overcomes the shortcomings of the original algorithm, but also has the advantages of variable precision rough sets. This paper uses a new criterion for attribute selection, weighted roughness and complexity, which comprehensively considers the classification accuracy and the number of branches. In order to reduce the influence of noisy data and missing values, the algorithm uses a class prediction method based on matching degree. Through comparative experiments, the effectiveness of the method proposed in this paper is verified. We propose a new calculation formula for the similarity of the child nodes of the label set to evaluate the effect of attribute classification, and comprehensively consider the situation that the elements in the two multilabel sets appear or not appear at the same time, so that the calculation of the similarity of the label set is more comprehensive. The experimental results show that the model proposed in this paper can excavate the dialectical combination of multiple factors. By comparing with the existing algorithms, the classification effect of the proposed algorithm is verified. The classification algorithm proposed in this paper is more suitable for dealing with multi-value attributes and multiclass data classification problems. The psychological evaluation and counselling system designed in this paper has achieved the expected goal. The results of this paper can improve the problems existing in the work of psychological counselling services.