With the rapid development of prominent models, NL2SQL has made many breakthroughs, but customers still hope that the accuracy of NL2SQL can be continuously improved through optimization. The method based on large models has brought revolutionary changes to NL2SQL. This paper innovatively proposes a new NL2SQL method based on a large language model (LLM), which could be adapted to an edge-cloud computing platform. First, natural language is converted into Python language, and then SQL is generated through Python. At the same time, considering the traceability characteristics of financial industry regulatory requirements, this paper uses the open-source big model DeepSeek. After testing on the BIRD dataset, compared with most NL2SQL models based on large language models, EX is at least 2.73% higher than the original method, F1 is at least 3.72 higher than the original method, and VES is 6.34% higher than the original method. Through this innovative algorithm, the accuracy of NL2SQL in the financial industry is greatly improved, which can provide business personnel with a robust database access mode.

Cardiovascular disease is a typical chronic disease. The incidence of cardiovascular disease in the elderly population has grown to exceed 50%. The further aging of the current population has brought additional pressure on public health services. Therefore, to reduce the service pressure of medical institutions, accurate prediction of cardiovascular disease risk has become an essential task in intelligent elderly care. In order to achieve accurate prediction of cardiovascular disease risk, we propose a cardiovascular disease risk prediction model Acdim (a cardiovascular disease risk prediction model) based on ResNet (Residual Network), zebra optimization algorithm (ZOA), TabNet (Attentive Interpretable Tabular Learning), and AdaBoost (Adaptive Boosting) algorithms. In training the Acdim model, we used the dat set of the World Health Organization (WHO) Behavioral Risk Factor Monitoring System records. In the experiment, the Acdim model achieved an accuracy of 96%, a precision of 94%, a recall of 93%, a specificity of 95%, an F1 score of 91%, and an AUC of 95%. The experimental results show that the proposed Acdim model can enable elderly care institutions to accurately predict the risk of cardiovascular disease in the absence of doctors.

Human-database interaction is inevitable in intelligent system applications, and accurately converting user-entered natural language into database query language is a critical step. To improve the accuracy, generalization, and robustness of text-to-SQL, we propose Nabil (a model for natural language conversion query language based on brain-inspired computing technology and a large language model). This model first leverages the spatiotemporal encoding capabilities of spiking neural networks to capture semantic features of natural language, then fuses these features with those generated by a large language model. Finally, a champion model is designed to select the optimal query from multiple candidate SQLs. Experiments were conducted on three database engines, DuckDB, MySQL, and PostgreSQL, and the model’s effectiveness was verified on benchmark datasets such as BIRD. The results show that Nabil outperforms existing baseline methods in both execution accuracy and effective efficiency scores. Furthermore, our proposed normalization and syntax tree abstraction algorithms further enhance the champion model’s discriminative capabilities, providing new insights for text-to-SQL research.

To reduce the pressure on public health services caused by the aging population, nursing homes need to predict disease risks for the elderly periodically. To improve the disease risks predicting ability of nursing homes, we designed Anston (An Attention Mechanism Network Model for Structured Data Classification) in the application scenario of innovative elderly care. The Anston model can use the physiological indicators and pathogenic factors easily collected by nursing homes to predict disease risks. In the study of disease risk prediction based on physiological indicators and pathogenic factors for thoughtful elderly care, we designed a data enhancement method, a feature weight automatic update method, and a multi-layer perceptron neural network to solve the problems of sample shortage, inconsistent feature weights, and sample imbalance. At the same time, we designed an attention mechanism network model for structured data classification based on the multi-layer perceptron neural network developed in this paper. To fit the application scenario of competent elderly care, we propose a disease risk prediction model, Anston, based on the data enhancement method, feature automatic update method, and structured data classification attention mechanism network designed in this paper. We use public data sets and subject data as sample data in the experiment. The experimental results show that the Anston model has an accuracy of 95%, a precision of 92%, a recall of 91%, a specificity of 93%, an F1 score of 91%, and an AUC of 93% in predicting disease risks in the experiment, which have achieved the SOTA result.

Skin cancer risk prediction plays a critical role in early diagnosis and personalized healthcare. However, existing approaches often struggle to achieve both rich feature representation and computational efficiency. To address these issues, this study proposes Bicom, a brain-inspired framework for skin cancer risk prediction that integrates efficient attention mechanisms, multi-scale feature fusion, and confidence-aware refinement. Specifically, we develop F-ResNeSt, a multi-scale feature-extraction architecture that enhances the ResNeSt backbone by incorporating a Feature Pyramid Network (FPN) and Linformer-based linear-complexity attention. In addition, we propose L-CoAtNet, an optimized classification network that replaces conventional relative attention with Linformer-based attention to achieve scalable global contextual modeling. Furthermore, a brain-inspired Spiking Neural Network (SNN) module is introduced as a confidence-aware refinement mechanism to enhance prediction reliability for ambiguous samples. Comprehensive experiments on public and subject datasets demonstrate that the proposed framework achieves consistently competitive performance across multiple evaluation metrics, indicating its effectiveness, robustness, and scalability for assisted skin cancer risk prediction.