Research on optimization of talent cultivation mode of industry-teaching integration for mechanical majors in higher vocational colleges based on genetic algorithm

Abstract Many researchers and educational institutions are committed to exploring the modes and strategies of industry-education integration, which promotes the close connection between education and industrial needs by jointly carrying out teaching, research, and practice activities. This paper proposes a multi-objective optimization strategy based on genetic algorithms, which aims to enhance and optimize the talent cultivation model through adjustments to the resource matching scheme and teaching task allocation scheme for industry-education integration. The mechanical specialty of a higher vocational college puts forward 10 kinds of industry-teaching integration teaching resource allocation schemes based on teaching tasks, combined with enterprise demand and students’ ability, and substitutes them into the constructed multi-objective integration model, and solves them by genetic algorithm to arrive at the optimal resource allocation scheme G, which has an adaptability value of 0.571, and the matching degree of teaching task 6 under the industry-teaching integration teaching resource allocation scheme G is the highest, which means that the mechanical specialty needs to strengthen the professional knowledge teaching about task 6. Teaching of specialized knowledge about task 6. Additionally, the satisfaction distribution graph from the questionnaire data indicates that students feel more content with the construction and development of the mechanical specialty during the optimized talent cultivation mode of industry-teaching integration. The results of the expert evaluation demonstrate that the integration of industry and education not only yields outstanding outcomes in collaborative education and training (4.32 points) but also partially addresses the talent shortage in positions (4.13 points). However, it still requires enhancement in the professional environment (3.13 points).