A personalized Eye Massager Design Model Integrating Deep Semantic Network and Multi-Objective Optimization

In order to solve the problem of slow response to user's perceptual needs and poor differentiation in the design process of traditional eye massagers, this paper proposes a personalized design model based on deep semantic network (DSNN) and multi-objective particle swarm optimization algorithm (MOPSO). The experiment constructs a DSNN model based on 12,573 user data, and deploys the model and conducts user testing in three real products. The results show that user satisfaction is improved by 22.8% on average. After applying the system recommendation solution in the three products, the average product morphology reconstruction time is reduced from the traditional manual collaboration cycle (14 days) to 9 days, and the efficiency is improved by about 35.7%, which verifies the efficiency of the system driven by multi-objective modeling. This study breaks through the limitations of traditional qualitative analysis and opens up a new path for computable emotion-driven design.