Zhongnan Zhao

In highly dynamic and high-concurrency urban traffic environments, intelligent systems must be capable of real-time perception, accurate reasoning, and agile scheduling to effectively manage complex traffic situations. However, prevailing approaches often suffer from fragmented perception, shallow reasoning, and delayed scheduling, leading to a lack of coordination among critical system modules. This deficiency significantly hinders holistic intelligent decision-making and real-time regulation under rapidly changing conditions. To address these challenges, this paper proposes a collaborative framework that integrates digital twins with metaverse-based semantic modeling. A three-layer architecture is constructed, consisting of the physical infrastructure layer, virtual twin resource layer, and traffic situation awareness layer, thereby forming a closed-loop mechanism of perception–reasoning–scheduling. The proposed system leverages the immersive semantic environment provided by the metaverse to enable contextual interpretation and intent recognition of traffic data. This semantic understanding drives the dynamic evolution and causal reasoning of digital twin entities. Based on the inferred results, a cloud–edge–end collaborative scheduling strategy is triggered to allocate resources adaptively. In addition, an interactive feedback mechanism is incorporated to support the real-time verification and continuous optimization of scheduling outcomes. Within this framework, we design a metaverse-driven Mixture-of-Experts perception network that enables multi-level semantic recognition and prediction of global traffic trends, regional congestion, and local anomalies. Furthermore, we introduce a multi-agent scheduling mechanism that combines virtualized resource mapping with structure-aware transfer strategies, thereby enhancing the generalization capacity and dynamic responsiveness of scheduling policies across heterogeneous infrastructure environments. Extensive experimental evaluations demonstrate that the proposed approach outperforms existing mainstream methods across several key metrics, including task acceptance rate, long-term revenue, congestion mitigation effectiveness, and resource utilization efficiency. These results validate the proposed framework’s superior adaptability and system-level of intelligence in complex traffic scenarios.

With the continuous advancement of urban transportation digitalization, the resources confronted by intelligent transportation system are exhibiting increasing diversity and scale, leading to a growing contradiction between resource demand and scheduling efficiency. To further enhance the operational efficiency of transportation systems, this article proposes a virtualization-based digital twin transportation resource scheduling model under a cloud–edge collaboration framework. This model leverages the characteristics of digital twin technology to achieve efficient resource operation through virtualized resources and a cloud–edge collaborative architecture, adapting to on-demand scheduling in various complex traffic scenarios. Specifically, this article integrates digital twin technology to perceive and map the physical and digital spaces of transportation through a virtual-real fusion approach. It employs a multiresource collaborative scheduling architecture based on cloud–edge collaboration to achieve effective allocation of transportation resources. Furthermore, it utilizes a virtualized resource representation to establish efficient and unified integrated resource management based on a digital global view. Additionally, to further optimize scheduling, this article proposes a value distribution policy gradient graph deep reinforcement learning model based on node importance strategy. Through deep learning of key nodes and relationships and adaptive feedback to scheduling demands, it achieves efficient collaboration and scheduling of digital cloud–edge integrated transportation resources. Experimental results demonstrate that the proposed model outperforms current mainstream resource scheduling models in terms of resource utilization, long-term average revenue, and revenue-cost ratio.

Network traffic anomaly detection, as an effective analysis method for network security, can identify differentiated traffic information and provide secure operation in complex and changing network environments. To avoid information loss caused when handling traffic data while improving the detection performance of traffic feature information, this paper proposes a multi-information fusion model based on a convolutional neural network and AutoEncoder. The model uses a convolutional neural network to extract features directly from the raw traffic data, and a AutoEncoder to encode the statistical features extracted from the raw traffic data, which are used to supplement the information loss due to cropping. These two features are combined to form a new integrated feature for network traffic, which has the load information from the original traffic data and the global information of the original traffic data obtained from the statistical features, thus providing a complete representation of the information contained in the network traffic and improving the detection performance of the model. The experiments show that the classification accuracy of network traffic anomaly detection using this model outperforms that of classical machine learning methods.

With the popularity of social media, opinion mining has gradually become a popular research field. Among these fields, sentiment analysis mining is an important research direction in the field of opinion mining. It aims to reveal the public's sentiment tendency, and attitude towards specific topics or events by analyzing text data generated by users on online platforms and digital media. However, the large amount of opinion data usually lacks effective annotation, which limits the learning and construction of opinion models. Therefore, focusing on the problem of the scarcity of labeled data in opinion analysis, this paper proposes a mining method for public opinion sentiment analysis based on multi-model fusion transfer learning, that can make full use of the limited labeled data to improve the learning efficiency of sentiment features by integrating the advantages of different models. Additionally, it introduces a transfer learning strategy to enable the models of the target domains to perform better in the absence of labeled data. Furthermore, the attention mechanism is combined to strengthen the acquisition of key features of the emotional colors and improve the accuracy of sentiment analysis. Specifically, the paper uses the ERNIE model to generate dynamic representations of the text word vectors in the dataset. It also uses TextCNN and BiGRU to construct a joint model for extracting local and overall features of the text word vectors. The parameters of the feature layer of the trained model are migrated to the target domain through transfer learning. The attention mechanism is combined with the model to identify the extreme elements of the sentiment. Finally, the local and overall features are fused to achieve comprehensive mining of public opinion and emotional information. This method can effectively improve the accuracy and generalization of public opinion analysis in cases of data scarcity. In the experimental part, the paper conducts comparisons and analyses in eight aspects: word embedding model, model combination, attention mechanism, transfer learning, source domain dataset, target domain dataset, model training, and baseline model. The four indicators, namely accuracy, precision, recall, and F1-measure are used to evaluate the performance of the method. The experiments are thorough and detailed, demonstrating the effective improvement of opinion mining performance.

The target tracking issue has always been the hotspot in wireless sensor network, and with the emergence of new application in multimedia and real-time transmission, new requirements are proposed for transmission performance of target tracking routing; therefore, a software-defined network–based hierarchical adaptive routing algorithm of wireless sensor network is proposed in this article. The algorithm takes into account both network energy and throughput, uses Hopfield neural network algorithm to calculate the optimal path among adjacent clusters as a local routing (LR), and builds the Multi-choice Knapsack Problem model based on local paths to realize end-to-end global routing, in order to realize the routing of tracking target information under multi-objective conditions. The test bed includes physical and simulation tests. Experimental results show that the proposed algorithm is superior to low energy adaptive clustering hierarchy (LEACH) and Sequential Assignment Routing under different test scenarios.