Multi-Objective Differential Evolution Algorithm for Personalized and Adaptive Training in Sports Education

In sports education and training, the existing training model fails to consider the individual differences of athletes, resulting in unsatisfactory training results. In addition, the training items are often single, ignoring the necessity of multi-objective training. In the implementation process, there is a lack of dynamic adjustment of the athlete’s state, and the adaptability of the training plan is poor. This paper proposed a molecular docking algorithm based on multi-objective differential evolution (MODE). Through data collection and analysis, it identified athletes’ physiological and psychological characteristics and constructed an individual difference model to guide the formulation of training goals. According to the individual difference model, a variety of training goals were set, such as strength, endurance and flexibility, to ensure the comprehensive improvement of the comprehensive quality of athletes. Combined with the molecular docking algorithm, the optimal training plan was found by optimizing the training combination, maximizing the training effect and reducing the risk of sports injuries. A dynamic feedback mechanism is established during the training process to monitor the status of athletes in real time and adjust the training plan according to their physiological data and performance to improve training adaptability. The experimental results show that the average maximum oxygen uptake of athletes in group A, group B and group C increased to 63[Formula: see text]mL/kg/min, 52[Formula: see text]mL/kg/min and 67[Formula: see text]mL/kg/min, respectively, and the average muscle strength increased to 110[Formula: see text]kg, 92[Formula: see text]kg and 101[Formula: see text]kg. Compared with the traditional program, the strength, endurance and flexibility scores were 8.5, 8.0 and 9.3 points, respectively. The training model proposed in this paper effectively solves the problems of insufficient personalization, a single goal and a lack of dynamic adjustment.