In modern society, user behavior data analysis and product design optimization have become one of the key factors for the success of enterprises. Traditional methods are usually based on human experience and intuition, and cannot accurately analyze and optimize user behavior data. To solve these problems, a user behavior data analysis and product design optimization model based on improved Convolutional neural network is studied and constructed. Firstly, it utilizes neural networks to extract user behavior features, and then obtains corresponding attention and satisfaction through emotional analysis of the behavior. Finally, comparative algorithms and simulation experiments are used to verify the performance of the model. The results show that the average accuracy rates of text extraction between the model algorithm and the comparison algorithm are 95.07%, 91.26%, and 83.92%, respectively. In the same classifier, the average recognition accuracy of both algorithms is 91.85%, 84.16%, and 81.22%. In the design optimization of mobile phone and laptop products, the difference between the model method and the actual value does not exceed 5%. This demonstrates high robustness and accuracy in analyzing user behavior data and optimizing product design. Additionally, it has a significant auxiliary effect on generating design optimization. This study aims to provide a new research direction for user behavior data analysis and product design optimization.