A Research on High-Dimensional Data Processing Algorithm Based on Convolutional Neural Network Algorithm

This paper proposes a data recommendation method that integrates the DNN deep neural network and the multi-layer attention mechanism. The core of this method lies in using the convolutional neural network to perform multi-layer dimensional extraction of data information. At the same time, with the help of the multi-channel attention mechanism, the low-dimensional features obtained are summed with the non-linear features obtained from the deep network to achieve data feature fusion, complete the mining of peripheral data related to user preferences, and further improve the depth of data mining and the performance of data recommendation. In the era of the Internet and ultra-large data, quickly locating useful information in massive data is crucial for data recommendation systems. However, traditional data recommendation algorithms have problems such as low data dimensionality, unsatisfactory recommendation accuracy, and poor user matching. To verify the effectiveness of the new algorithm, Amazon's public data is used for simulation experiments, and the experimental data is compared with that of multiple models and algorithms. The results show that this algorithm can not only significantly improve the data recommendation performance but also effectively explore the potential information of the data.