Traditional employment market analysis has some limitations, such as single data source, static analysis method and rough matching mechanism. The application of deep learning technology in employment market analysis mainly focuses on employment trend prediction, talent supply and demand matching and employment structure research. In terms of research methods, this study integrates structured data, unstructured text and spatio-temporal data, and builds a more comprehensive foundation for job market analysis. By designing a multi-modal encoder including text embedding, time series modeling and spatial graph embedding, the effective extraction and fusion of complex data features are realized. In the employment demand forecasting model, a framework of Transformer (ST-Transformer) with spatio-temporal awareness is proposed. By introducing spatio-temporal attention mechanism, the geographical adjacency matrix is integrated into the traditional self-attention calculation, and the joint modeling of regional employment trends is realized. In the talent supply-demand matching model, a quantum-inspired multi-constraint optimization algorithm is introduced, which solves the complex trade-off problem between skill adaptation, regional matching and retraining cost in the traditional matching mechanism. The experimental results show that the ST-Transformer proposed in this study shows significant advantages in employment demand forecasting. Compared with the traditional model, the forecasting accuracy is higher and the dynamic adaptability is stronger. In the task of talent supply and demand matching, Quantum-HGNN (Heterograph Neural Network) matching model is significantly better than the traditional method, with higher matching success rate, lower retraining cost and greatly reduced inter-provincial mismatch rate. In addition, the multimodal fusion framework and dynamic feedback mechanism further improve the prediction accuracy and matching efficiency of the model. This study provides new ideas and methods for realizing the dynamic balance between supply and demand in the job market, which has important theoretical and practical significance.
Tang et al. (Sun,) studied this question.