Due to the short development time of cultural and tourism towns in China, local governments and investors lack experience in building cultural and tourism towns and do not pay enough attention to the positioning of towns. Alternatively, this issue results in chaos in domestic cultural and tourism towns and even a large number of empty towns in some provinces. Therefore, how to accurately locate cultural tourism towns is a problem that must be studied in depth at present. This paper uses the regional economic theory to collect the influencing factors of cultural tourism town positioning. Based on the BP neural network and the improved genetic algorithm, a genetic neural network model is constructed to train and predict the samples of cultural tourism towns. Taking a small town in the East as a case, the data were collected and analyzed. Established on the prediction outcomes of the genetic neural network, the best location of a small town was selected according to the actual situation of the region. In terms of accuracy and training time, our experimental evaluation confirmed that the neural network enhanced by genetic algorithms outperforms the conventional BP neural network. Furthermore, we observed that besides the classification capabilities of the BP neural network-based model, the classical BP neural network improved by the genetic algorithm also exhibits great macrosearch capabilities and good global optimization performance.

Aiming at the defect that the click-through rate of marketing advertisements cannot provide accurate prediction results for the company in time in the marketing strategy of Internet companies, this paper uses a deep learning algorithm to establish a prediction model for the click-through rate of marketing advertisements. The suggested model is called high-order cross-feature network (HCN). Furthermore, this paper also introduces the combination of feature vectors into the graph structure and as the nodes in the graph; therefore, the graph neural network (GNN) is used to obtain the high-level representation ability of structured data more fully. Through numerical simulations, we observed that HCN has the capability to provide Internet companies with more accurate advertising business information, user information, and advertising content. Moreover, HCN model is more reasonable to adjust the advertising strategy and can provide better user experience. The simulation outcomes indicate that the suggested HCN approach has noble adaptability and high correctness in forecasting the click-through rate of marketing advertisements. We observed that this improvement, in terms of predictions precisions and accuracies, can be as high as 17.52% higher than the deep neural network (DNN) method and 10.45% higher than the factorization network (FM) approach.