This paper starts from the application scenarios and pain points in the financial industry, focusing on the synthesis of financial technology (Fintech) product risk data. By integrating existing research in the field of data synthesis, we propose a novel Fintech Data Synthesis System (FinDS2). To implement this system, we have designed and developed a data synthesis product that leverages cloud computing and micro-services. The product includes a cloud-native data lake, an intelligent algorithm engine, and a SAAS tool engine. It collects data on regulatory rules and penalties in the finance industry and offers highly configurable and automated features. By tailoring the synthesis process to Fintech application scenarios, our proposed FinDS2 generates high-quality synthetic data efficiently. Through practical validation, we demonstrate that the synthesized data closely resembles the original data, effectively meeting the data synthesis needs for managing Fintech product risk.

The Internet of Things is a network of interconnected devices that communicate with each other and use the Internet to send and receive data to users. The Internet of Things is widely used in applications such as automobiles, energy, logistics, transportation, government affairs, and campuses. During our research on network security of campus video surveillance systems, we found that the IoT devices of campus video surveillance systems have long been scanned and invaded by the engines of various search devices. This situation brings great hidden dangers and considerable risks to campus surveillance network security. In order to maintain the network security of IoT devices in the campus video surveillance system, we propose a network intrusion security detection model Niect (Network Intrusion Security Detection Model) based on the convolutional neural network, energy valley optimization algorithm, LightGBM, and CatBoost algorithm. We use the Edge-IIoTset, an integrated real-world cybersecurity dataset for IoT and Industrial IoT applications. The Niect model we proposed achieved an accuracy of 96.35%, a precision of 95.87%, a recall of 93.57%, and an AUC value of 91.68% in the experiment. This experimental result shows that the proposed Niect model can provide strong technical support for network security intrusion detection of IoT devices in campus video surveillance systems.

While population aging has sharply increased the demand for nursing staff, it has also increased the workload of nursing staff.Although some nursing homes use robots to perform part of the work, such robots are the type of robots that perform set tasks.The requirements in actual application scenarios often change, so robots that perform set tasks cannot effectively reduce the workload of nursing staff.In order to provide practical help to nursing staff in nursing homes, we innovatively combine the LightGBM algorithm with the machine learning interpretation framework SHAP (Shapley Additive exPlanations) and use comprehensive data analysis methods to propose a service demand prediction model Fidan (Forecast service demand model).This model analyzes and predicts the demand for elderly services in nursing homes based on relevant health management data (including physiological and sleep data), ward round data, and nursing service data collected by IoT devices.We optimise the model parameters based on Grid Search during the training process.The experimental results show that the Fidan model has an accuracy rate of 86.61% in predicting the demand for elderly services.