Innovation and Practical Exploration of the Education Path of Industry-Education Integration in the Automotive Industry Chain Based on Natural Language Processing Technology

Abstract

As the automotive industry chain accelerates its transformation towards intelligence, electrification, and networking, the importance of industry-education integration in talent training and technological innovation has become increasingly prominent. However, the existing industry-education integration model still has problems such as imperfect cooperation mechanisms and disconnection between educational content and industry needs. This study uses natural language processing (NLP) technology as the core tool to deeply mine text data (policy formulation, market analysis, technology research and development, production and manufacturing, sales and service) of the automotive industry chain through sentiment analysis and topic modeling to reveal industry sentiment trends and hot topics. The study found that negative emotions accounted for the highest proportion in policy texts (342 articles), focusing on regulatory constraints and new energy promotion; market analysis and technology research and development were dominated by positive emotions (1742 and 2178 articles, respectively), reflecting the industry's support for innovation and development; negative emotions were prominent in the sales and service field (784 articles), reflecting the concentration of user pain points. Based on the empirical results, this paper proposes an optimization plan for the industry-education integration education path from six dimensions: policy response, technology research and development, intelligent manufacturing, market services, interdisciplinary training, and dynamic adjustment, aiming to promote the precise connection between educational content and industry needs and provide theoretical and practical support for the cultivation of compound talents in the automotive industry chain.