In medical retrieval scenarios, accurate identification of user query intent is pivotal for enhancing retrieval relevance and knowledge augmentation effectiveness. However, existing approaches exhibit polarized performance: traditional shallow models (e.g., TF-IDF, Bag-of-Words) struggle to capture contextual semantics, while pre-trained language models, despite their strong deep semantic representation capabilities, often overlook keyword weighting and category-specific priors. This leads to suboptimal accuracy for long-tail categories and susceptibility to confusion from emotional or colloquial query formulations. To address these challenges, this study proposes a hybrid model integrating RoBERTa-wwm-ext with sentence-level TF-IDF and category-centroid TF-IDF via a three-branch attention fusion mechanism. The model employs adaptive attention mechanisms to dynamically weight deep-shallow features at the sample level, while incorporating category-centroid vectors as explicit semantic anchors to mitigate class imbalance issues. Experimental evaluations on the KUAKE-QIC dataset demonstrate that our approach achieves an accuracy of 0.824 and a Macro-F1 score of 0.800, outperforming all baseline models by 2.3% points. These results highlight the synergistic benefits of deep-shallow feature interaction, ensuring robust recall for dominant categories while significantly improving precision for minority classes. This work provides a generalizable framework for medical intent classification that balances semantic integrity with keyword-driven priors, laying a more reliable foundation for applications such as clinical question-answering systems, medical search ranking, and intelligent triage systems.

This paper established a numerical simulation model to analyze the pressure transient and rate transient behaviors in reservoir with complex fracture network. Firstly, the fractures are introduced into the coordinate system through the position, angle, and length. Secondly, a mathematical model is established by using unstable seepage model. Thirdly, the central difference method was used to solve the model and local grid refinement method is introduced to describe the network fractures. Finally, we compared the results obtained from this paper’s model with the production data. The results show acceptable and reasonable matches for typical well. Meanwhile, the sensitivity of two properties is discussed. The model solution is verified with an analytical method thoroughly. The novelty of this paper is to introduce each fracture in fracture network into the coordinate system. Then, the grid refinement is achieved according to the fracture information. The presented new model simplifies the analysis of the pressure transient and rate transient of the reservoir with complex fracture network, and it is more efficient than the conventional numerical method. Compared with the analytical methods, the new model describes the fractures system in more detail. However, the new model treats fractures as reservoirs with higher permeability in the central difference method, which is simpler and rougher than traditional numerical methods.

This paper proposes a new model of collaborative filtering that introduces a user difference factor to address the issue of less pronounced similarity performance in traditional algorithms. The algorithm is applied to the recommendation of pilots’ core competency behavior indicators to support pilots’ daily training arrangements, improve their core competencies, and ensure civil aviation flight safety. Firstly, based on traditional collaborative filtering methods, a user difference factor is introduced to improve the Pearson similarity calculation model. Secondly, the advantages and disadvantages of collaborative filtering recommendation models were evaluated using various methods such as average absolute error, accuracy, recall, and diversity. Finally, the new model is applied to the recommendation of PLM core competency behavior indicators, providing a recommendation list of different pilot behavior indicators to support their rehabilitation or enhanced training plans and arrangements. The calculation results show that the new model of collaborative filtering demonstrates better advantages, not only reducing the MAE value, but also improving the accuracy, recall, and diversity of the calculation results, providing effective guidance and theoretical support for pilots’ flight training and safe flight.

With the rapid advancement of the civil aviation sector and the concurrent expansion of pilot training programs, a pressing need arises for more efficient assessment methodologies during the pilot training process. Traditional written evaluations conducted by flight instructors are often marred by subjectivity and inefficiency, rendering them inadequate to satisfy the stringent demands of Competency-Based Training and Assessment (CBTA) frameworks. To address this challenge, this study presents a novel multi-label classification model that seamlessly integrates RoBERTa, a robust language model, with Graph Convolutional Networks (GCNs). By simultaneously modeling text features and label interdependencies, this model enables the automated, multi-dimensional classification of instructor evaluations. It incorporates a dynamic weight fusion strategy, which intelligently adjusts the output weights of RoBERTa and GCNs based on label correlations. Additionally, it introduces a label co-occurrence graph convolution layer, designed to capture intricate higher-order dependencies among labels. This study is based on a real-world dataset comprising 1078 evaluations and 158 labels, covering six major dimensions, including operational capabilities and communication skills. To provide context for the improvement, the proposed RoBERTa + GCN model is compared with key baseline models, such as BERT and LSTM. The results show that the RoBERTa + GCN model achieves an F1 score of 0.9737, representing an average improvement of 4.73% over these traditional methods. This approach enhances the consistency and efficiency of flight training assessments and provides new insights into integrating natural language processing and graph neural networks, demonstrating broad application prospects.

The key performance parameters of proppant are mainly the crushing rate and fracture conductivity, which are usually evaluated using physical experimental methods. However, the testing method for fracture conductivity has limitations, such as its long time-consumption, high testing costs, instability, and even the presence of large errors in testing results under the same conditions. The purpose of this paper is to propose a calculation method that can replace physical experiments. Firstly, we analyze the random and deterministic phenomena in the contact relationship between proppant particles from a microscopic perspective. Subsequently, we develop a physical model of the microscopic arrangement of these particles, enabling us to conduct further computer simulations of their microscopic configuration. Secondly, we conduct a microscopic mechanical analysis of the contact between proppant particles and between particles and boundaries and establish a corresponding mathematical model. Then, utilizing the simulation and mechanical analysis results of the proppant, we calculate the crushing rate. Considering the crushing rate of proppant, we improve the Kozeny–Carmen equation to determine the fracture permeability, and subsequently calculate the fracture conductivity. Finally, the calculated results are compared with the experimental results. The results show that the calculated values for the proppant crushing rate and fracture conductivity matched well with experimental data, and that the model’s calculation values were more accurate. As the number of simulations increased, the accuracy of the calculation results became higher. Research shows that the fracture conductivity is influenced by factors such as the particle size, microstructure, and crushing rate. Numerical calculation methods can replace physical experiments and provide theoretical support for engineering applications of hydraulic fracturing proppant materials.