Urban data is a imperative resource for urban computing, which can promote the establishment of urban knowledge, the collection of urban information and the construction of smart cities. Seen that the urban data collected through hardware sensors and crowdsourcing has the limitations of uneven information distribution, poor data comprehensiveness and high resource costs, we turn to the Internet resources of real-time updates and extensive information coverage. Therefore, we propose an approach to Sensing Urban text Data from Internet Resources (SUDIR). We put forward innovative work on two key issues: urban data recognition for Chinese context and urban data sensing for multi-source web resources. On one hand, we design a Chinese urban data recognition model based on Whole Word Masking for Bidirectional Encoder Representations from Transformers (BERT-WWM) embedding model and Bidirectional Long-Short Term Memory with a Conditional Random Field (BLSTM-CRF) sequence labeling model. We introduce Chinese Word Segmentaion (CWS) concept in BERT embedding model to make the text embedding effect better represent semantic information on Chinese context. BLSTM-CRF model based on deep learning is used to achieve high-quality coding and prediction. On the other hand, we propose a method of Extracting Urban text data based on Web page features and Clustering operation (EUWC). EUWC is used to correct the false negative samples labeled by BERT-WWM+BLSTM-CRF recognition model and enable SUDIR to sense more accurate and comprehensive city data from multi-source web resources. The experimental results show that our work outperforms the other baseline methods, and it also proves that SUDIR using Internet resources and deep learning technology has the advantages of low-cost, high-quality urban data sensing.
31 December 2025 in Journal of Physics: Complexity
In emergency evacuation scenes, environmental uncertainties and information deficits often trigger panic among individuals, which in turn impairs their ability to make sound judgments and decisions. To address this problem, this study proposes a heterogeneous crowd evacuation model (HCEMMP), aiming to accurately simulate the behavior of crowds influenced by panic factors and reveal the correlation between behavior and different factors. HCEMMP integrates a multi-dimensional panic analysis framework with an enhanced social force model. The framework conceptualizes panic as the joint outcome of environmental stress, individual characteristics, and social group influence, allowing quantitative representation of emotional dynamics under complex conditions. The improved social force model adaptively modulates individual movement intentions through emotional feedback, yielding coordinated and realistic evacuation behaviors. Simulation results across diverse scenes reveal nonlinear, hierarchically regulated patterns in crowd behavior driven by coupled panic factors. Individual traits, environmental stress, and social group influence jointly shape emotional dynamics, forming complex feedback that governs evacuation performance. The findings confirm that HCEMMP outperforms baseline models in evacuation efficiency, behavioral realism, and crowd stability, providing a robust foundation for real-world evacuation strategy optimization.
Accurate tourist flow forecast can provide important support and guarantee for scenic spot staff and tourists to make decisions or plans. Aiming at the current situation that most of the existing forecasting methods are tourist flow forecasting of a single scenic spot and cannot fully mine spatial dependency information between various scenic spots, this paper proposes AMGCN model, a multi-graph convolution-based tourist flow prediction model for multiple scenic spots. First, AMGCN defines different non-Euclidean correlations between attractions, encoded as different graphs respectively, and uses multi-graph convolution to extract spatial correlation features. Then, a channel-wise attention mechanism incorporating global spatial context information is used to improve the performance of a long short-term memory network (LSTM), which is used to learn temporal correlation features. AMGCN is evaluated on a real-world large-scale urban multi-spot tourist flow historical dataset, the results show that the model outperforms the baseline model on regression evaluation metrics such as MAE, RMSE, MAPE, and SMAPE.