Intelligent system integrating medical staff workload monitoring and patient psychological support

Abstract

The invention provides an innovative integrated system which aims at monitoring the workload of medical staff and providing psychological support for patients at the same time. The system collects physiological and behavioral data of medical staff and physiological and psychological state information of a patient in real time through a multi-modal data acquisition technology. And by utilizing an advanced machine learning algorithm, the system can intelligently evaluate the workload of the medical personnel and predict the overwork risk. Meanwhile, according to individual requirements of the patient, the system generates customized psychological support schemes including emotion recognition, psychological education, social support and professional consultation. In addition, the system has the real-time feedback and intervention functions, and it is ensured that medical workers and patients get attention and help in time. The intelligent user interface design improves the user experience, and strict data security and privacy protection measures guarantee the security of user information. According to the design of the system, the efficiency and quality of medical care work are improved, the overwork risk of medical staff is reduced, comprehensive psychological care is provided for patients, the psychological welfare of the patients is enhanced, and overall rehabilitation of the patients is promoted.

Description

Technical field:

[0001] The present invention relates to the field of medical health, in particular to intelligent monitoring of the workload of medical staff and real-time support technology for the psychological state of patients. The technical field includes but is not limited to sub-fields such as medical monitoring, data analysis, artificial intelligence, machine learning, human-computer interaction, mobile health applications, psychological assessment and intervention, and data security and privacy protection. By integrating these technologies, the present invention aims to provide a comprehensive solution to reduce the workload of medical staff while enhancing the psychological well-being of patients, improving the overall quality and efficiency of medical services, and promoting the overall recovery of patients. Background technology:

[0002] In the field of medical health, workload management of medical staff and psychological support for patients are two crucial aspects. Traditional medical workload monitoring mainly relies on manual records and subjective evaluations, which is not only inefficient but also may be biased. At the same time, in addition to the impact of the disease itself, patients are often accompanied by psychological problems such as anxiety and depression when facing the disease, and the existing psychological support services often lack personalization and real-time, and it is difficult to meet the specific needs of different patients. For the patient-centered medical health concept, it is far from enough to focus only on the disease itself, and the patient's mental health is equally important. Therefore, when treating the disease, medical staff should also pay attention to the patient's mental state and provide personalized psychological support in a timely manner. However, for medical staff, busy clinical work has long brought a huge workload, and they often ignore providing timely psychological support for patients. Therefore, how to balance the workload of medical staff and provide timely psychological support for patients is an urgent problem to be solved in the field of medical health.

[0003] With the development of science and technology, some intelligent systems have been introduced to solve these problems. For example, wearable devices and mobile applications are used to collect physiological data, and some basic data analysis tools are used to assess workload and psychological state. However, these systems often have single functions and lack the ability to comprehensively consider the workload of medical staff and the psychological state of patients. In addition, existing systems also have shortcomings in real-time, personalized services, user interaction, and data security.

[0004] Therefore, it is necessary to develop an intelligent integrated system that can not only monitor the workload of medical staff in real time and accurately, but also provide personalized psychological support programs according to the specific conditions of patients. Such a system will help improve the efficiency of medical work, reduce the pressure of medical staff, and at the same time improve the psychological well-being of patients and promote their overall recovery. It is in this context that the present invention is proposed, aiming to solve the deficiencies in the prior art through technological innovation and provide a more comprehensive and efficient solution.

[0005] Technical solution:

[0006] The present invention proposes an intelligent system that integrates workload monitoring of medical staff and psychological support for patients. The system includes a multimodal data acquisition module, an intelligent load assessment algorithm, a personalized psychological support program generation module, a real-time feedback and intervention module, an intelligent user interface, a data security and privacy protection module, and detailed steps of system integration and testing, deployment and maintenance, and usage methods. Through this technical solution, the system can monitor the physiological and behavioral data of medical staff in real time, assess workload and predict overwork risks, and provide patients with personalized psychological support programs based on their psychological state. In addition, the system also has real-time feedback and intervention capabilities, interacts with users through an intuitive user interface, and ensures the security and privacy of all data. The implementation of the present invention will greatly improve the quality and efficiency of medical services, improve the welfare of patients, protect the physical and mental health of medical staff, and ensure the data security of medical staff and patients.

[0007] Preferably, a multimodal data collection module: a set of data collection tools including wearable devices and mobile applications are developed to monitor the physiological indicators (such as heart rate, blood pressure, activity level) and behavioral data (such as working hours, work intensity) of medical staff in real time. In addition, through the patient's self-assessment questionnaire, physiological monitoring equipment and environmental sensors, the system can collect the patient's psychological state and physiological data. Figure 1 As shown, the design and implementation process of the multimodal data acquisition module of the present invention is as follows:

[0008] 1) Selection and deployment of wearable devices: Fitbit Charge 4 wristbands were selected to monitor the heart rate and activity of medical staff. The wristbands collect data once a minute to ensure the real-time and continuity of the data. Each medical staff member was equipped with an Omron HEM-7120 blood pressure monitor, which was set to automatically measure and record blood pressure every two hours to monitor the cardiovascular health of medical staff.

[0009] 2) Development and integration of mobile applications: Develop a mobile application that can be integrated into the medical staff's smartphone or tablet to record working hours, work intensity, and rest intervals. The application includes a work log module that allows medical staff to manually enter special circumstances or work details that the system cannot automatically record.

[0010] 3) Design of patient self-assessment questionnaire: Design a standardized self-assessment questionnaire that includes questions to assess the patient's psychological state, such as anxiety, depression, and sleep quality. The questionnaire is distributed through a mobile application, and patients can complete the questionnaire at any time and submit it directly to the system database.

[0011] 4) Integration of physiological monitoring equipment: Use existing physiological monitoring equipment, such as electrocardiographs (ECGs) and pulse oximeters, to collect the patient's physiological data. Ensure that these devices are compatible with the data acquisition module and transmit data to the central database in real time.

[0012] 5) Deployment of environmental sensors: Environmental sensors are deployed in wards and work areas to monitor environmental factors such as light intensity, sound level, and indoor temperature. Sensor data will assist in assessing the physiological comfort of patients and the quality of the working environment for medical staff.

[0013] 6) Data synchronization and preprocessing: Establish a data synchronization mechanism to ensure that all collected data can be transmitted to the central server in real time and undergo preliminary cleaning and formatting. Preprocess the data, including removing outliers, filling in missing values, and standardizing the data to improve the accuracy of subsequent analysis.

[0014] 7) Data security measures: Use encryption protocols such as TLS during data transmission to ensure the security of data transmission. Encrypt data stored on the server to prevent unauthorized access and data leakage.

[0015] 8) Feedback mechanism of user interface: Provide real-time data feedback on mobile applications and medical staff’s workstations, including individual workload indicators and an overview of the patient’s psychological state. Design a user-friendly interface so that medical staff can easily view data and adjust work plans based on feedback.

[0016] Preferably, intelligent workload assessment algorithm: a machine learning-based algorithm is designed to preprocess the work data of medical staff, extract features, and train the model to assess workload. The algorithm can identify work patterns, predict overwork risks, and issue early warnings. Figure 2 As shown in the figure, the detailed implementation process of the intelligent load assessment algorithm is as follows:

[0017] 1) Data preprocessing: The collected raw data is first cleaned to remove outliers caused by signal interference and equipment errors, and the Z-Score or IQR (interquartile range) method is used to identify and process outliers. The data is normalized, and data of different dimensions such as heart rate and activity are converted to the [0,1] interval to ensure the consistency of model input.

[0018] 2) Feature selection and extraction: Apply statistical methods, such as correlation coefficient analysis, to select features that are highly correlated with workload, such as average heart rate, maximum heart rate, HRV, average daily activity, etc. Use time series analysis to extract trends and periodic features, and use Fourier transform or wavelet transform to identify the periodicity of work patterns.

[0019] 3) Machine learning model selection and training: Select a machine learning model suitable for classification and regression tasks, such as random forest, gradient boosted tree (GBDT) or deep neural network (DNN). Use Python's Scikit-learn library or TensorFlow framework to build the model, and adjust the hyperparameters through grid search and cross-validation methods.

[0020] 4) Model training and validation: The data set was divided into a training set and a test set in a ratio of 70:30, and the model was trained using the training set data. K-fold cross validation (e.g., K = 5) was used to evaluate the stability and generalization ability of the model, and the mean square error (MSE) and determination coefficient (R 2 ) as a performance indicator.

[0021] 5) Work mode identification and risk assessment: The training model identifies different work modes, such as "high load", "medium load" and "low load", and assigns a risk level to each mode. By analyzing the continuous working hours and the changing trends of physiological indicators, the overwork risk is assessed and the risk warning threshold is set.

[0022] 6) Real-time monitoring and early warning mechanism: Develop a real-time data stream processing system and use Apache Kafka or Apache Flink to collect and process real-time data. When the workload index predicted by the model exceeds the preset threshold, the system automatically triggers an early warning and notifies relevant personnel through the system interface, SMS or application push.

[0023] 7) Model update and maintenance: Regularly (e.g. quarterly) retrain the model with new data to adapt to changes in the work patterns of medical staff. Set up a monitoring panel to monitor the accuracy of model predictions and early warning responses in real time to ensure the continued effectiveness of the model.

[0024] 8) User feedback and model iteration: Integrate a user feedback module into the system to allow medical staff to evaluate the accuracy and timeliness of early warnings. Based on user feedback and model performance monitoring results, continuously iterate the model to optimize feature selection and parameter settings.

[0025] 9) Report generation and decision support: The system can automatically generate workload reports, including daily, weekly and monthly workload statistics and trend analysis. It provides decision support tools.

[0026] Help management adjust human resource allocation and work plans based on workload data.

[0027] Preferably, the module for generating personalized psychological support programs: first, collect the patient's psychological state data through mobile applications and physiological monitoring devices, including key indicators such as mood swings and sleep quality; then, apply natural language processing technology to analyze the self-assessment questionnaire, and combine physiological data to evaluate the patient's emotional stability and stress level; then, determine the intervention measures suitable for the patient based on psychological principles such as cognitive behavioral therapy; then, automatically generate a personalized psychological support program containing emotion recognition tools, psychological education materials, social activity suggestions and professional consultation appointments; then, dynamically adjust the program content based on the patient's feedback and participation, and use machine learning algorithms to optimize recommended resources; at the same time, implement real-time monitoring and establish a feedback loop mechanism to ensure timely updates of the program; in addition, collaborate with a professional mental health team to ensure the service quality of professional consultation; finally, strictly protect the privacy and security of patient data throughout the process and comply with data protection regulations. Through this series of orderly steps, ensure that patients are provided with comprehensive, accurate and personalized psychological support.

[0028] Preferably, the real-time feedback and intervention module: first, monitor the physiological indicators of medical staff and the psychological state of patients in real time through integrated sensors and mobile applications; second, integrate and clean the collected data in preparation for analysis; then, use intelligent algorithms to evaluate the workload of medical staff and the psychological state of patients, and generate personalized feedback information; then, automatically trigger the decision support tool based on the evaluation results to recommend appropriate intervention measures; then, send intervention suggestions to medical staff and patients through the user interface and track the implementation; at the same time, establish an interactive feedback system to adjust intervention measures based on user evaluation; in addition, develop a tracking mechanism to monitor the long-term effects of intervention measures, and provide support for management decisions through automatically generated reports and logs; finally, implement a self-learning mechanism so that the system can be continuously optimized based on new data and feedback, and improve the level of intelligence and user satisfaction. This process ensures that medical staff and patients receive timely attention and appropriate support, improves the efficiency and quality of medical services, and enhances the psychological well-being of patients.

[0029] Preferably, the intelligent user interface: first, designs an intuitive and user-friendly interface, through reasonable layout and clear information hierarchy, so that users can quickly understand how to operate; second, divides the interface into functional modules such as workload display, psychological support plan recommendation, real-time feedback, etc., and provides clear instructions for each module; then, integrates multiple interaction methods such as touch screen and voice command to adapt to the operation habits of different users; then, develops real-time data display function to dynamically display the workload of medical staff and the psychological support plan of patients; in addition, provides personalized setting options to allow users to adjust the interface according to their preferences; at the same time, establishes a user feedback mechanism to continuously collect and respond to user opinions to optimize the interface design; in addition, develops auxiliary functions such as night mode and voice reading to enhance the user experience; ensures the adaptability of the interface on different devices, and helps users master the usage through user education and help systems such as operation manuals and online tutorials; conducts comprehensive testing in actual use and optimizes according to feedback; finally, regularly updates the interface and adds new functions to adapt to technological development and changes in user needs to ensure that the user interface always provides an efficient and easy-to-use interactive experience.

[0030] Preferably, the data security and privacy protection module: first, all sensitive data are encrypted using the AES-256 strong encryption standard during transmission and storage to ensure the confidentiality of the data; secondly, by implementing the TLS1.2 or higher security protocol, the data transmission process is encrypted to prevent the data from being intercepted or tampered with during transmission; then, the role-based access control (RBAC) strategy ensures that only authorized personnel can access the corresponding data, and the multi-factor authentication (MFA) mechanism is combined to enhance the security of user identity authentication; in addition, the system records the audit logs of all data access and operations in detail to provide a basis for post-audit and monitoring; at the same time, regular security audits are conducted to check the effectiveness of data security measures and promptly repair security vulnerabilities; formulate a clear data privacy protection policy, clarify the rules for handling user data, and provide users with the right to access, correct and delete their own data; in addition, formulate a data breach emergency plan to ensure that a quick response and measures can be taken when a data breach occurs; conduct regular data security awareness training for employees to improve their awareness of data protection; finally, ensure that the system complies with domestic and international data protection regulations such as GDPR, and obtain corresponding compliance certification. Through these comprehensive measures, the data security and privacy protection module of the present invention provides users with a safe and reliable data processing environment.

[0031] Preferably, system integration and testing: Integrate the above modules into a complete system and conduct rigorous testing to ensure the stability, reliability and user-friendliness of the system. Testing includes unit testing, integration testing and user testing to collect feedback and optimize system performance.

[0032] Preferably, deployment and maintenance: deploy the system in medical institutions and provide continuous technical support and system maintenance services. Ensure that the system can adapt to different medical environments and be iteratively updated based on user feedback.

[0033] Preferably, if Figure 3 The specific steps for use are as follows:

[0034] S1. Start multimodal data collection: In the initial step, the multimodal data collection module is started, which includes deploying devices such as Fitbit Charge 4 wristband, Omron HEM-7120 blood pressure monitor and Jawbone UP3 activity tracker, as well as configuring environmental sensors in the ward to collect physiological and behavioral data of medical staff, as well as the physiological and psychological status of patients in real time.

[0035] S2. Intelligent workload assessment: The collected data is then processed using an intelligent workload assessment algorithm, which uses a machine learning model to analyze the workload of medical staff, assess their work intensity and potential risk of burnout, and generate a workload report.

[0036] S3. Generate personalized psychological support plan: Based on the patient's psychological state assessment results, the system automatically generates a personalized psychological support plan, including emotion management tools, mental health education resources, social activity suggestions and professional consultation appointments when necessary.

[0037] S4. Real-time monitoring and feedback: Through the real-time feedback and intervention module, the system continuously monitors the working status of medical staff and the psychological state of patients. Once high-risk or abnormal situations are detected, the system will automatically issue an early warning and recommend corresponding intervention measures.

[0038] S5. User interface interaction: With the intelligent user interface, medical staff and patients can easily view workload assessment results, psychological support plans and real-time feedback information. The interface supports touch screen operation and voice commands, and provides personalized settings and auxiliary functions such as night mode and font size adjustment.

[0039] S6. Data security and privacy protection: Throughout the process, the data security and privacy protection module ensures that all collected and processed data is encrypted with AES-256 and securely transmitted via the TLS protocol. Implement role-based access control and multi-factor authentication, record detailed audit logs, conduct regular security audits, and comply with data privacy protection policies.

[0040] By implementing the technical solution of the present invention, the workload of medical staff can be effectively monitored, and personalized patient psychological support programs can be provided to improve the quality and efficiency of medical services while ensuring the data security and privacy of users.

[0041] The present invention successfully solves key technical problems in the medical field, including achieving real-time and objective evaluation of the workload of medical staff, providing psychological support programs tailored to the individual needs of different patients, implementing continuous monitoring and timely intervention of the physical and mental state of medical staff and patients, designing a user-friendly and intuitive intelligent user interface, ensuring the security and privacy of medical data, and ensuring the high integration, stability, adaptability and maintainability of the system in a changing medical environment. These technological breakthroughs have significantly improved the quality and efficiency of medical services, while ensuring the data security of medical staff and patients, and meeting the high standards of modern medical and health fields.

[0042] The core protection points of this invention focus on two key areas: first, the intelligent load assessment algorithm, which uses machine learning technology to conduct in-depth analysis of the work data of medical staff, realizes real-time and accurate assessment of workload, and effectively predicts the risk of overwork; second, the personalized psychological support program generation module, which provides customized psychological support and intervention measures according to the patient's specific psychological state and needs, ensuring the pertinence and effectiveness of psychological support services. These two innovative points are the focus of the technical protection of this invention, and together they constitute the key technical foundation for the system to improve medical quality and patient psychological well-being.

[0043] The beneficial effects of the present invention are reflected in multiple aspects: First, through the intelligent load assessment algorithm, the workload of medical staff is monitored in real time and accurately, which helps to timely detect and prevent overwork, thereby improving the overall work efficiency and job satisfaction of medical staff. Secondly, the generation of personalized psychological support programs provides patients with targeted, timely and effective psychological intervention, significantly improving the psychological well-being and overall rehabilitation quality of patients. In addition, the real-time feedback and intervention module of the system ensures that medical staff and patients can receive timely attention and help, enhancing the responsiveness and personalization of medical services. The design of the intelligent user interface improves the user experience and makes the system easy to operate and access. Finally, the implementation of data security and privacy protection measures ensures the security of user information and enhances the user's trust in the system. On the whole, the present invention not only optimizes the allocation of medical resources, but also improves the quality of medical services and patient satisfaction, which is of great significance to promoting technological progress in the field of medical health. Description of the drawings:

[0044] Figure 1 This is the operation flow chart of the multimodal data acquisition module of the present invention

[0045] Figure 2 This is a flowchart of the implementation of the intelligent load assessment algorithm of the present invention.

[0046] Figure 3 Flow chart of the method for using the system of the present invention Specific implementation method:

[0047] In the specific implementation of the present invention, we will describe in detail how to build and use an intelligent system that integrates workload monitoring of medical staff and psychological support for patients. The following are specific implementation steps, including specific equipment names, parameter settings, and expected results, to ensure that they correspond to the content in the claims.

[0048] S1: Multimodal Data Acquisition

[0049] Deploy a series of advanced wearable devices, including Fitbit Charge 4 heart rate monitoring bracelet, which can track the heart rate changes of medical staff in real time at a high frequency of once a minute; Omron HEM-7120 blood pressure monitor, which is set to automatically measure blood pressure every two hours to ensure continuous monitoring; and Jawbone UP3 activity tracker, which is used to record the number of steps and sleep quality of medical staff 24 hours a day. These devices will work together to provide our intelligent system with comprehensive and detailed physiological and behavioral data of medical staff, laying a solid foundation for subsequent workload assessment.

[0050] S2: Intelligent load assessment algorithm development

[0051] Develop an intelligent workload assessment algorithm based on the IBM Watson machine learning platform. This algorithm will use heart rate variability (HRV) as a key indicator and set the threshold to 68 milliseconds to scientifically assess the physiological stress state of medical staff. At the same time, we set the activity level as at least 10,000 steps per day, and the overwork warning threshold for working hours is set to 8 hours. Through in-depth analysis of these parameters and training of machine learning models, it is expected that the algorithm will be able to assess the workload of medical staff in real time with an accuracy rate of more than 95%, and effectively predict the risk of overwork.

[0052] S3: Generation of personalized psychological support plans

[0053] A customized mobile application is used to collect patients' self-assessment data on their mental state. The application contains a 10-question mental state self-assessment questionnaire, with each question scoring 5 points and a total score of 50 points. The system will automatically recommend personalized psychological support plans based on the patient's self-assessment score. For example, for patients with mild anxiety who score 30-39 points, the system will recommend a series of deep breathing relaxation exercises; for patients with moderate depression who score 20-29 points, professional psychological counseling services will be recommended. Such personalized plans can more accurately meet the psychological needs of different patients.

[0054] S4: Real-time feedback and intervention implementation

[0055] Provide real-time feedback to medical staff and patients through smart watches and mobile applications. The system will set up an early warning mechanism when the workload index exceeds 70. At the same time, when the patient's psychological state score is less than 20 points, the system will automatically recommend corresponding intervention measures. These intervention measures may include adjusting the work plan of medical staff or recommending specific psychological counseling activities for patients. In this way, the system can ensure that medical staff and patients receive the necessary support and adjustments at critical moments.

[0056] S5: Intelligent User Interface Design

[0057] Apple iPad is used as the main display device for the user interface. The interface design will include three main areas: a workload display area that updates the workload index and related physiological data of medical staff in real time; a psychological support program recommendation area that displays personalized psychological support content and recommended activities; and user interaction buttons that facilitate medical staff and patients to quickly access required functions. This design aims to provide an intuitive and easy-to-use user interface to ensure that all users can easily obtain information and perform operations.

[0058] S6: Data security and privacy protection implementation

[0059] We use Amazon Web Services (AWS) cloud services to store and process all collected data. To ensure data security and privacy, we will use TLS1.2 encryption protocol to protect data security during transmission and use AES-256 bit encryption algorithm to encrypt data stored in cloud services. In addition, we will implement role-based access control policies and record detailed audit logs of all data access and system operations for easy supervision and auditing.

[0060] System integration and testing

[0061] The system will be deployed in a general hospital, involving 100 medical staff and 200 patients, for a 30-day field test. The test will include unit testing, integration testing, and user testing to ensure that all functional modules work together, meet design requirements, and provide stable and reliable services. The test results are expected to demonstrate the system's efficiency and user satisfaction.

[0062] Deployment and maintenance

[0063] The system will be fully deployed in selected medical institutions, and a professional technical support team will provide one-year system maintenance services. We will continue to optimize based on user feedback to ensure that the system can adapt to different medical environments and needs and provide the best user experience. It is expected that the system will be successfully deployed and run stably, significantly improving the work efficiency of medical staff, enhancing the psychological well-being of patients, and enhancing the overall quality of medical services.

Claims

1. An intelligent system integrating workload monitoring of medical staff and psychological support for patients, characterized in that: include: Multimodal data collection module, used to collect physiological data, behavioral data of medical staff and physiological and psychological status data of patients in real time; Intelligent workload assessment algorithm, which uses machine learning technology to assess the workload of medical staff based on their work data and predict potential burnout risks; The module for generating personalized psychological support plans provides personalized psychological support plans based on the patient's psychological state and disease type; Real-time feedback and intervention module, which monitors the working status of medical staff and the psychological status of patients, and provides timely feedback and intervention measures; Intelligent user interface, designed to be intuitive and easy to use, allowing medical staff and patients to easily access and use system functions; The data security and privacy protection module uses advanced data encryption and access control technologies to ensure the security and privacy of user data.

2. The system according to claim 1, characterized in that The multimodal data acquisition module comprises: Wearable devices to monitor health care workers’ physiological indicators, such as heart rate, blood pressure, and activity level; A mobile application to collect medical staff’s work logs and patients’ self-assessment of their mental status; Environmental sensors to monitor patient room conditions such as light, sound, and temperature.

3. The system according to claim 1, characterized in that The intelligent load assessment algorithm includes: Data preprocessing unit, used to clean and standardize the collected data; A feature extraction unit, used to extract workload-related features from raw data; Model training unit, used to train machine learning models to evaluate workloads; The risk prediction unit is used to predict the risk of overwork of medical staff and provide early warning.

4. The system according to claim 1, characterized in that The personalized psychological support program generation module includes: The psychological state analysis unit is used to analyze the patient's self-assessment data and physiological data to identify their psychological needs; Support content recommendation unit, which is used to recommend corresponding psychoeducational materials, social activities and professional consultation services according to the psychological needs of patients; Emotion Regulation Tools Integration Unit, which is used to provide emotion regulation tools such as meditation, relaxation training and mindfulness.

5. The system according to claim 1, characterized in that The real-time feedback and intervention module includes: Status monitoring unit, used to monitor the working status of medical staff and the psychological status of patients in real time; A feedback generating unit, used for generating feedback information according to the monitoring result; The intervention execution unit is used to implement intervention measures such as adjusting work plans or providing psychological counseling.

6. The system according to claim 1, characterized in that The intelligent user interface comprises: The medical staff workload display interface is used to display workload assessment results and overwork warnings; Patient psychological support interface, used to display personalized psychological support programs and emotion regulation tools; User interface, used to receive user input and feedback, and to provide help and guidance.

7. The system according to claim 1, characterized in that The data security and privacy protection module includes: A data encryption unit, used to encrypt stored and transmitted data; Access control unit to manage user access rights and ensure only authorized personnel can access sensitive data; Audit log unit, used to record data access and operation logs for security auditing and monitoring.

8. A method for using the system according to any one of claims 1 to 7, characterized in that: The following steps are involved: S1. Start the multimodal data collection module to collect relevant data of medical staff and patients; S2. Use intelligent workload assessment algorithm to assess the workload of medical staff; S3. Generate personalized psychological support plan for patients; S4. Monitor and provide timely feedback on the status of medical staff and patients through real-time feedback and intervention modules; S5. Display relevant information through an intelligent user interface and interact with users; S6. Ensure data security and privacy through data security and privacy protection modules.

Images