The study aims to effectively reduce building energy consumption, improve the utilization efficiency of building resources, reduce the emission of pollutants and greenhouse gases, and protect the ecological environment. A prediction model of heating ventilation air conditioning (HVAC) energy consumption is established by using back propagation neural network (BPNN) and adapted boosting (Adaboost) algorithm. Then, the HVAC system is optimized by building information modeling (BIM). Finally, the effectiveness of the urban intelligent HVAC optimization prediction model based on BIM and artificial intelligence (AI) is further verified by simulation experiments. The research shows that the error of the prediction model is reduced, the accuracy is higher after the Adaboost algorithm is added to BPNN, and the average prediction accuracy is 86%. When the BIM is combined with the prediction model, the HVAC programme of hybrid cooling beam + variable air volume reheating is taken as the optimal programme of HVAC system. The power consumption and gas consumption of the programme are the least, and the CO2 emission is also the lowest. Programme 1 is compared with programme 3, and the cost is saved by 37% and 15%, respectively. Through the combination of BIM technology and AI technology, the energy consumption of HVAC is effectively reduced, and the resource utilization rate is significantly improved, which can provide theoretical basis for the research of energy-saving equipment.
This study conducts in-depth research on geographic information visualization and the sustainable development of low-carbon rural slow tourism under artificial intelligence (AI) to analyze and discuss the visualization of geographic information and the sustainable development of low-carbon slow tourism in rural areas. First, the development options related to low-carbon tourism in rural areas are discussed. Then, a low-carbon rural slow tourism recommendation method based on AI and a low-carbon rural tourism scene recognition method based on Cross-Media Retrieval (CMR) data are proposed. Finally, the proposed scheme is tested. The test results show that the carbon dioxide emissions of one-day tourism projects account for less than 10% of the total tourism industry. From the proportion, it is found that air transport accounts for the largest proportion, more than 40%. With the development of time, the number of rural slow tourists in Guizhou has increased the most, while the number of rural slow tourists in Yunnan has increased to a lesser extent. In the K-means clustering model, the accuracy of scenario classification based on the semantic features of scene attributes is 5.26% higher than that of attribute likelihood vectors. On the Support Vector Machine classifier, the scene classification accuracy based on the semantic features of scene attributes is 19.2% higher than that of the scene classification based on attribute likelihood vector features. CMR techniques have also played a satisfying role in identifying rural tourism scenarios. They enable passengers to quickly identify tourist attractions to save preparation time and provide more flexible time for the tour process. The research results have made certain contributions to the sustainable development of low-carbon rural slow tourism.
This work aims to explore reform methods for Japanese classroom teaching modes in an informationized environment. Addressing issues such as monotonous classroom content and low student engagement in traditional teaching, this work introduces deep learning technology and constructs a personalized recommendation model based on the Bidirectional Encoder Representations from Transformer (BERT) fused with the Graph Convolutional Neural Network (GCNN). Furthermore, this model is applied to Japanese flipped classroom teaching, and a personalized recommendation system-supported Japanese flipped classroom mode is designed. The performance of the constructed model is finally verified. The results show that the personalized recommendation model constructed here has achieved good application effects in Japanese teaching, with a recommendation recognition accuracy of 95.96% and an F1 value of 90.12%. The constructed model exceeds the precision of the baseline algorithm Convolutional Neural Network (CNN) by over 4%. Through questionnaire surveys and empirical analysis of controlled experimental designs, it is found that the Japanese flipped classroom mode supported by the personalized recommendation system demonstrates significant advantages in enhancing student learning abilities and satisfaction. The improvement rates of experimental group students in various indicators all exceed 18%. Therefore, the Japanese teaching mode proposed can significantly improve the teaching effectiveness of Japanese classrooms and provide experimental references for educational mode reforms.