Intelligent management system centered on artificial intelligence algorithms, cloud computing technology, mobile Internet technology, and big data applications have made remarkable achievements in various industries. The intelligent management system designed in this project is to apply these technologies to explore a vocational education development model that adapts to the current Internet society. Vocational education needs to be oriented to the professional needs of the society, it needs to be oriented to students' vocational choices, and it needs to be oriented to the skill range of teachers. This project collects students' learning data and teaches students in accordance with their aptitude in the course of students' daily classes, matches students with appropriate vocational and technical elective courses and teachers, and records students' feedback during their studies, and in the future career development of students, to help students make better career choices. At the same time, the needs of students, companies, and teachers in vocational education will be collected, and artificial intelligence algorithms will be used to process student data and corporate recruitment data, automatically matching the most suitable combination of students and companies. The biggest core innovation of this system is the latest deep learning algorithm, and according to the actual situation of vocational education, the residual neural network is improved to create an improved residual neural network suitable for students' professional development recommendations. The final result of this algorithm, the auxiliary role in the process of student vocational education and development is far greater than the traditional vocational education management system, and in the C University student education and professional development database, there is about 90% satisfaction rate and the 85% occupational matching accuracy rate is far higher than the performance of the traditional vocational education management system.

BP neural network has been gradually applied in the field of economic management. It has many advantages that traditional methods can’t achieve, but there are also disputes and problems. In this paper, the BP neural network model is established to analyze the credit risk indicators of listed companies, and the learning system of enterprise credit rating management is established to predict the future credit risk, so as to achieve the purpose of enterprise risk management, and the corresponding conclusions and suggestions are given to promote the development and innovation of enterprise management and artificial neural network.

In response to global climate change, harnessing the climate-adaptive wisdom of vernacular dwellings is crucial for sustainable architectural design. This study takes Haiyan Village in the Kunming plateau area as a case study, focusing on three typical vernacular dwelling types of Yikeyin—‘Half seal’, ‘One seal’, and ‘Two seals’. Using Ladybug and Honeybee within the Rhino Grasshopper platform, a quantitative comparative analysis was conducted to evaluate their natural ventilation efficiency (characterized by Air Changes per Hour, ACH) and indoor thermal comfort (characterized by Predicted Mean Vote, PMV, and Predicted Percentage of Dissatisfaction, PPD). The results indicate the following: (1) Throughout the year, the ‘Two seals’ dwelling type exhibits the most stable diurnal temperature variation, while the ‘Half seal’ dwelling type shows the greatest fluctuation in its diurnal temperature range. (2) The summer ACH values for ‘Half seal’, ‘One seal’, and ‘Two seals’ dwelling types are 3.8~4.5, 1.5~2.9, and 0.8~1.6, while the winter values are 1.9~2.6, 1.3~1.8, and 0.7~1.0. The ventilation efficiency in summer is generally higher than that in winter, and it shows a significant decreasing trend as building volume increases. (3) The summer PPD values for ‘Half seal’, ‘One seal’, and ‘Two seals’ dwelling types are 12%, 18%, and 35%, while the winter values are 22%, 15%, and 12%. (4) The ‘One seal’ dwelling type exhibits good ventilation and thermal comfort throughout the year. The ‘Half seal’ demonstrates the best ventilation and thermal comfort in summer but poorer thermal comfort in winter. The ‘Two seals‘ dwelling type achieves the best thermal comfort in winter, but lower ventilation efficiency, while in summer, both thermal comfort and ventilation are poor. This study not only addresses the gap in the quantitative assessment of climate adaptability in vernacular dwellings but also provides critical data support and a theoretical basis for the scientific preservation, adaptive renewal, and sustainable inheritance of vernacular architecture in the context of climate change.

Low-latitude plateau classrooms, such as those in Kunming, experience intense solar radiation that often causes insufficient far-window illumination, excessive near-window brightness, and viewing-direction glare under side-lighting conditions. To investigate this spatial imbalance, field surveys of nine classrooms were used to define realistic parameter ranges, while 100 parametric design cases were evaluated through annual simulation, machine learning, and SHAP analysis. The viewing-direction glare model achieved a test-set R² of 0.819, indicating adequate predictive performance for factor interpretation. Compared with simply increasing the window-to-wall ratio (WWR), coordinated control of classroom geometry, window configuration, and surface reflectance produced a more balanced luminous environment. Daylight availability and excessive illuminance were primarily governed by WWR and window reveal depth, whereas glare was more strongly influenced by seating position, viewing direction, window width, and orientation. Classroom-wide averages may therefore conceal localized glare experienced by students. A moderate WWR of 0.26–0.40 combined with a window reveal depth of 0.75–1.17 m emerged as a preferable strategy within the investigated design space. These findings support desktop-level daylight assessment and student-perspective glare evaluation in the design and renewal of ordinary side-lit classrooms in Kunming and comparable low-latitude plateau regions.

The traditional Yikeyin dwellings in central Yunnan exhibit a distinctive spatial layout and skywell design that passively adapt to the mild plateau monsoon climate through natural ventilation. Although their courtyard-based configuration and skylight design are widely recognized for climatic adaptability, the quantitative relationship between courtyard orientation and ventilation performance remains insufficiently explored. This study integrates on-site environmental monitoring with validated Computational Fluid Dynamics (CFD) simulations to investigate how different courtyard orientations influence airflow organization and the indoor thermal environment. Based on detailed field surveys and measured data, three representative orientation schemes were established. The RNG k-ε turbulence model was adopted, and one-way coupled simulations using OpenFOAM and EnergyPlus were conducted to evaluate seasonal ventilation behavior and indoor thermal comfort. The findings reveal synergistic design principles between building orientation and courtyard spatial configuration, as well as spatial differentiation patterns contributing to thermal environment stability. Three orientation types—leeward, windward, and transitional—were identified, each demonstrating distinct advantages and limitations. The study quantitatively confirms the effectiveness of Yikeyin dwellings in utilizing natural ventilation for environmental regulation during both summer and winter seasons. These results provide scientific evidence and design support for modern buildings seeking to achieve enhanced ventilation performance and climatic adaptability.