Method for detecting behaviors and mentalities of students based on homomorphic encryption federated learning

Abstract

The invention provides a method for detecting behaviors and mentalities of students based on homomorphic encryption federated learning. The method comprises the following steps: acquiring mutually independent data sets A and B; selecting intersection data through the consistency of data corresponding to the same feature items between the data sets A and B by adopting an encryption-based user sample alignment technology, and distinguishing a to-be-tested data set with the difference between the data sets B and A; encrypting the selected intersection data of the data set A and the data set B through the homomorphic encryption technology; constructing a convolutional recurrent neural network, and training intersection data of the homomorphic encrypted data sets A and B through federated learning to obtain a model for predicting the psychological state of the student; and predicting the psychological state in the model for predicting the psychological state of the student by taking each piece of data in the to-be-tested data set as the to-be-tested data. By implementing the method, the requirements of student behavior and psychological detection are met on the premise of protecting data privacy, and the problems in the prior art are solved by adopting a convergent homomorphic encryption federated learning algorithm.

Description

technical field [0001] The invention relates to the technical field of big data mining, in particular to a method for detecting student behavior and psychology based on homomorphic encryption federated learning. Background technique [0002] Many colleges and universities use campus behavior big data to carry out many applications for management and teacher-student services, relying on big data mining methods to support campus management and decision-making in the field of education and the analysis of student behavior patterns. Although many data analysis methods have been proposed in recent years, the analysis of university behavioral big data is still a challenging research field, and there are still many problems worthy of in-depth exploration and urgent solutions. [0003] At present, many colleges and universities have accumulated a large amount of teaching resources and management data, thus forming a large-scale and complex data set, which provides strong support for...

AI Technical Summary

Problems solved by technology

[0007] However, there are deficiencies in the two existing federated learning frameworks. The disadvantages are: in the first federated learning framework, federated learning usually faces the problem of statistical heterogeneity

Since the global model training results of classic federated learning may tend to update parameters uploaded by some clients, the data-related complexity calculation is used for the target learning of the model, and it is difficult to meet the task-agnostic federated learning requirements, and the algorithm The convergence under the assumption of convex loss function and hypothesis set is uncertain; in the second federated learning framework, on the one hand, if there is no additional monitoring, data pool and other information and only one round of communication is performed, the generated global neural The effect of the network model is not necessarily reliable, resulting in data growth accompanied by distributed storage. It is very difficult to protect data privacy while ensuring enough data for modeling; on the other hand, in federated learning problems, even if only in the client There is still the risk of exposing user privacy if the update information of the model is transmitted between the central server and the central server without transmitting the client’s local data, especially when the traditional methods for local privacy protection are too strict in practical applications, modern high-dimensional It is often not applicable in statistical and machine learning problems

Images