Evaluation of Smart City Construction and Optimization of City Brand Model under Neural Networks

Yingji Li, Yufeng Qian, Qiang Li, Linna Li

The study aims to avoid the phenomenon that thousand cities seem the same in the construction of smart cities and the efforts of all walks of life are jointed to implement the construction of smart cities and the creation of city brands. First, the basic theory of smart city construction is introduced. Second, the restricting and promoting factors influencing smart city construction and development are analyzes, and the evaluation system of smart city development is established. Then, the model for smart city construction and development based on the neural network is implemented. Finally, some domestic cities are selected as the dataset to build a training model, and the city brand optimization strategy is proposed. On this basis, an evaluation system for smart city development based on the intelligent neural network and Grey relational analysis Back Propagation Neural Network (GRA-BPNN) is obtained. The entropy weight method (EWM), grey relational analysis (GRA) method and the evaluation method based on Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) are regarded as the members of the control group, and the results of different methods for evaluating the development of smart cities are compared. The results show that the modeling of smart city construction based on neural networks can help to implement an evaluation model for smart city construction and development, and it can help evaluate smart city construction and development accurately. And then the corresponding strategies are proposed to speed up the construction of smart cities with its local characteristics, and then city brands are built. Compared with other evaluation algorithms, the performance of the algorithm proposed is better and more stable and the evaluation results are more reasonable than those of the others, which can prove that the evaluation algorithm is feasible and scientific. This study provides a new idea for the application of deep learning to smart city construction and city brand building.