Privacy protection and acceleration algorithms of quantum convolutional neural networks for big data

The rapid development of artificial intelligence has made the application of quantum convolutional neural networks increasingly widespread. Aiming at the privacy protection problem of data information in quantum convolutional neural networks, the fully homomorphic encryption algorithm is embedded in the structure of the quantum convolutional neural network to encrypt the data information, and the particle swarm optimization algorithm is adopted to improve the convergence speed and accuracy of the network. In the performance analysis experiment, the accuracy curve of the proposed model reached the convergent state after 40 iterations, and its average loss rate was 0.23 and the average accuracy rate was 0.97, demonstrating good accuracy and convergence speed. The experimental results show that the model proposed in the study can well protect the data information and has good accuracy and convergence speed.