Aiming at the problems of difficult disease spot recognition and slow detection speed caused by complex backgrounds in rice images, this paper proposes an improved YOLOv10 target detection algorithm for automatic identification of rice diseases. Firstly, the backbone network of YOLOv10 is improved by introducing Large Separable Kernel Attention (LSKA) to replace the original Polarized Self-Attention (PSA), which improves the sensitivity to features, enhances the generalization ability and efficiency of the network. In addition, the loss function is replaced by the Normalized Wasserstein Distance (NWD) loss function, which re‐ duces the feature map while preserving more information as much as possible, improving the processing efficiency. Experiments con‐ ducted on the rice dataset show that the improved YOLOv10 algorithm achieves 97.95% on the mAP50 indicator, representing a 1.08% increase compared to the original YOLOv10; and it achieves 78.74% on the mAP50-95 indicator, representing a 1.52% in‐ crease compared to the original YOLOv10.

Artificial Intelligence-enabled vocational education brings new demands for compound talents in the process of intelligent training, but it still faces many challenges in the process of integrating Artificial Intelligence and vocational education. In order to promote the deep integration of Artificial Intelligence and vocational education and meet the needs of economic development and so‐ ciety for diversified technical and skilled talents, on the basis of summarizing the mechanism of action and analyzing the practical problems, this paper puts forward the combination of Artificial Intelligence and professional curriculum construction, giving full play to the potential of teachers to use intelligent technology, and promoting the development of students' personality based on Artifi‐ cial Intelligence to implement the application of Artificial Intelligence in vocational education. 

The application of various AI products or technologies in the field of education will drive a more profound digital transfor‐ mation and innovation in education, which is an inevitable requirement for advancing high-quality education development in the era of Artificial Intelligence. The intervention of AI large language model technology in higher vocational education has overturned the traditional paradigms and methods of educational technology intervention in this field from multiple dimensions such as precise modeling, intelligent interaction, emotional identification, and has facilitated the transformation and sublimation of the educational model in higher vocational education. However, the inherent weaknesses of AI large language models also pose potential risks and challenges to higher vocational education and teaching in areas such as ideology, values, scientific ethics, and more. Therefore, while integrating AI large language model technology and seizing the opportunity for high-quality development in higher vocational educa‐ tion, it is also crucial to establish design norms for technology application. This study puts forward the construction method of inte‐ grating AI technology into the curriculum system of higher vocational education from three dimensions: curriculum content, learning mode and curriculum environment. On the basis of analyzing the potential risks, this paper implements the path of promoting the digital transformation of higher vocational education through top-level design, content construction, audit algorithm and strengthen‐ ing supervision by implementing AI large language model.

With the rapid development of AI large models, the demand for computing power has sharply increased. Focusing on the pain points of low utilization of computing power resources and security concerns caused by sensitive data leaving the park, this ar‐ ticle proposes a solution based on storage and lossless network technology. By constructing an intelligent computing experimental network and adopting an innovative mode of simultaneous transmission and training, real-time data processing and rapid model up‐ dates have been achieved. The experimental results show that this scheme significantly improves the efficiency of computing power usage, reduces single task training time by 50%, increases data transmission rate to 7.3 Gbps, and can still maintain efficient opera‐ tion under 200 KM distance conditions. However, challenges such as data security and privacy protection still need to be addressed in the future. This study provides new ideas and methods for addressing the computing power demand in the era of large models.