Application of big data technology in visitor behavioral characteristics identification and energy efficiency assessment of intelligent scenic spots

Along with the ongoing enhancement of living standards, tourism has also sped up development. However, the large influx of visitors during holidays also brings serious challenges to the management of scenic spots. To efficiently carry out visitor management and energy efficiency management in scenic spots, the study realizes visitor behavior identification and scenic spot energy efficiency assessment based on big data technology. Firstly, the study introduces bidirectional mechanism, attention mechanism and dropout mechanism to build a visitor behavior recognition model based on improved long short-term memory network. Then, the study utilizes the pressure-state-response model to construct the indicator system, and conducts indicator screening through principal component analysis, and finally builds an intelligent scenic area energy efficiency assessment model based on the principal component analysis method. The results indicated that the accuracy rate of the proposed visitor behavior recognition model was 94.26% and the F1 value was 96.27%. The F1 value is used to measure the performance of a model while maintaining a balance between accuracy and recall. Its area under the curve for recognizing the four actions reached 97% and above. The model had the highest average accuracy rate, able to reach 96%, which had the fastest convergence rate. Observation 6 had the highest energy efficiency and observation 3 had the lowest. The suggested intelligent model for assessing the energy efficiency of scenic areas is capable of evaluating the overall energy efficiency of the region and examining the variables that influence it. The results of the study can contribute to improving the intelligent level of visitor and energy efficiency management in scenic spots and promoting the intelligent development of tourism.