Hospital material management server and method

Abstract

The invention relates to the field of medical material management, and discloses a hospital material management server, which comprises a data collection module used for collecting material consumption data, the number of patients and operation plans of all departments from a hospital information system and an electronic medical record system, and transmitting the collected data to a prediction analysis module; the prediction analysis module is connected with the data collection module, and the invention also discloses a hospital material management method which comprises the following steps: S1, collecting material consumption data of each department from a hospital information system and an electronic medical record system through the data collection module; by using an adaptive neural network and a virtual twinning technology, accurate demand prediction, inventory dynamic adjustment, distribution optimization, global monitoring and environment simulation adjustment are realized; the interactive feedback module forms closed-loop optimization, the meta-universe cooperation module supports virtualization operation and training, and the defects of a traditional system in prediction, scheduling, monitoring and cooperation are overcome.

Description

Technical Field

[0001] The present invention relates to the field of medical material management, and in particular to a hospital material management server and method. Background Art

[0002] Hospital material management is a critical link in the operation of medical institutions. Materials including medicines, equipment and consumables are not only diverse, but also in high demand and change rapidly. Traditional hospital material management methods usually rely on experience and historical data to forecast demand and manage inventory. However, with the continuous growth of medical needs and the frequent occurrence of emergencies, the traditional management model has exposed obvious shortcomings in practical applications.

[0003] First, the accuracy of material demand forecasting is a prominent problem. Existing technologies mainly rely on manual experience and static historical data for demand forecasting. This method cannot respond to changes in the internal and external environment of the hospital in real time, such as seasonal epidemics, public health emergencies, etc., which makes it difficult to accurately predict changes in material demand, which in turn causes instability in inventory management. Material shortages may affect the quality of medical services, while excessive stockpiling will increase operating costs and waste.

[0004] Secondly, in the material management process, the lack of coordination between inventory scheduling and environmental control is also a problem that needs to be solved urgently. Traditional inventory management methods mainly rely on regular inventory and preset warning lines for monitoring, and lack the ability to reflect and adjust inventory status in real time. In addition, environmental monitoring usually only focuses on parameters in a single dimension, such as temperature monitoring, and cannot fully guarantee the quality of materials during storage. The lag in the scheduling process and the limitations of environmental control may cause the quality of materials to decline or fail to meet clinical needs during actual use.

[0005] Therefore, in view of the above-mentioned deficiencies, the present invention proposes a hospital material management server and method. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a hospital material management server and method, which solves the problems of inaccurate demand forecasting and insufficient coordination between inventory scheduling and environmental control in traditional hospital material management.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: A hospital material management server, comprising:

[0008] The data collection module is used to collect the material consumption data, number of patients and surgical plans of each department from the hospital information system and electronic medical record system, and transmit the collected data to the predictive analysis module;

[0009] A prediction and analysis module, connected to the data collection module, is used to analyze the data through an adaptive neural network model, predict the future material demand of each department, and send the prediction results to the material scheduling module and the inventory management module;

[0010] A material dispatching module, connected to the forecasting and analysis module, is used to optimize the distribution path of materials according to the forecasting results and formulate a dispatching plan;

[0011] An inventory management module, connected to the forecasting analysis module and the material scheduling module, is used to monitor the inventory status in real time through the Internet of Things devices and automatically adjust the inventory level according to the forecast results;

[0012] An environmental monitoring and control module, connected to the inventory management module, is used to collect data on the material storage environment in real time and adaptively adjust storage conditions according to instructions from the inventory management module;

[0013] An interactive feedback module, connected to the inventory management module, is used to collect real-time feedback from medical staff on the use of supplies and send the feedback information to the forecast analysis module for analysis to further optimize demand forecasting;

[0014] A virtual twin module, connected to the inventory management module and the environmental monitoring and control module, is used to build a virtual model of hospital material management, map the material status in real time and simulate abnormal situations, and feed the simulation data back to the inventory management module;

[0015] The metaverse collaboration module is connected to the virtual twin module and is used to create a virtual material management space in the metaverse, realize collaboration and training drills, and feed back the drill results to the virtual twin module to improve the model.

[0016] Preferably, the data collection module includes:

[0017] Historical data collection unit, used to collect historical consumption data of each department;

[0018] Real-time data collection unit for obtaining patient numbers and surgical plans from hospital information systems and electronic medical record systems in real time.

[0019] Preferably, the prediction analysis module includes:

[0020] Adaptive neural network unit, used to analyze historical and real-time data to predict future material requirements of each department;

[0021] The dynamic adjustment unit is used to dynamically adjust the prediction model parameters according to real-time data changes.

[0022] Preferably, the material dispatch module includes:

[0023] The route optimization unit is used to simulate and select the optimal material distribution route based on the prediction results;

[0024] The scheduling execution unit is used to automatically execute the material scheduling plan according to the optimization results.

[0025] Preferably, the inventory management module includes:

[0026] Inventory status monitoring unit, used to monitor the inventory status of each storage point in real time through IoT devices;

[0027] An automated ordering unit that automatically generates and executes ordering plans based on inventory levels and forecasted demand;

[0028] A virtual twin simulation unit to simulate inventory management strategies in a virtual environment.

[0029] Preferably, the environment monitoring and control module includes:

[0030] Multi-dimensional environmental monitoring unit, used to collect and store environmental data such as temperature, humidity, and light through a sensor network;

[0031] an adaptive control unit for adjusting storage conditions based on real-time environmental data;

[0032] The anomaly detection unit is used to issue an alarm and take countermeasures when an abnormal environmental state is detected.

[0033] Preferably, the interactive feedback module includes:

[0034] Feedback collection unit, used to collect real-time feedback from medical staff through mobile applications or voice assistants;

[0035] The feedback analysis unit is used to analyze and classify the feedback information using natural language processing technology.

[0036] Preferably, the virtual twin module includes:

[0037] A data mapping unit, used to map the actual material status into the virtual twin model;

[0038] Simulation unit, used to simulate material flows, storage processes and abnormal situations in a virtual environment.

[0039] The metaverse collaboration module includes:

[0040] Virtual space creation unit, used to build material management space in the metaverse;

[0041] Virtual interaction unit, used to support medical staff to collaborate on material management through virtual reality equipment;

[0042] Training and Rehearsal Module, used for material management training and emergency drills in a virtual environment.

[0043] A hospital material management method comprises the following steps:

[0044] S1. Collect material consumption data of each department from the hospital information system and electronic medical record system through the data collection module;

[0045] S2. Analyze the data using the adaptive neural network model in the prediction and analysis module to predict the future material demand of each department;

[0046] S3. Based on the prediction results, use the material dispatch module to optimize the material distribution path and formulate a dispatch plan;

[0047] S4. Monitor inventory status in real time through the inventory management module and automatically adjust inventory levels based on demand forecasts and current inventory status;

[0048] S5. Use the environmental monitoring and control module to collect material storage environment data and adjust storage conditions according to environmental changes;

[0049] S6. Collect real-time feedback from medical staff on the use of supplies in the interactive feedback module and analyze the feedback;

[0050] S7, map the material status in real time in the virtual twin module, and simulate the material flow and abnormal conditions;

[0051] S8. Use the Metaverse Collaboration Module to conduct material management operations and training drills in virtual space.

[0052] The present invention provides a hospital material management server and method, which have the following beneficial effects:

[0053] 1. The present invention uses an adaptive neural network model to accurately predict material demand and dynamically adjusts the prediction model according to real-time data. When combined with an inventory management module, it can adjust inventory levels in real time according to the prediction results to achieve automatic ordering and replenishment, solving the problems of inaccurate demand forecasting, insufficient inventory or backlog caused by reliance on historical data and manual experience in the prior art. At the same time, through real-time monitoring and dynamic adjustment of inventory, it reduces material shortages and surpluses and improves inventory utilization.

[0054] 2. The present invention optimizes the distribution path of materials through the linkage between the prediction and analysis module and the material scheduling module, ensuring that the materials can be delivered to the destination in a timely and accurate manner. The virtual twin module provides global visualization and simulation functions, maps the material status in real time, and discovers potential scheduling problems in advance. It solves the problem in the prior art that material scheduling relies on manual or fixed rules and lacks the ability to respond to real-time demand changes. It also improves the efficiency and accuracy of material scheduling through global monitoring and abnormal warning.

[0055] 3. The present invention integrates multi-dimensional environmental data collection and adaptive control through the environmental monitoring and control module to ensure that materials are stored under optimal environmental conditions. This design, combined with virtual twin technology, can simulate and adjust environmental parameters in a virtual environment to ensure the optimization of actual storage conditions. At the same time, it solves the problems of incomplete environmental monitoring and untimely manual control in the existing system, and prevents damage to materials due to poor storage conditions.

[0056] 4. The interactive feedback module in the present invention enables medical staff to provide real-time feedback on the use of materials. The system uses natural language processing to analyze the feedback and uses the analysis results to adjust demand forecasting and inventory management strategies. This function forms a closed-loop optimization process with the forecasting analysis and inventory management modules, which solves the problem of delayed feedback processing and inability to quickly respond to changes in demand in traditional systems, and enhances the flexibility and adaptability of material management.

[0057] 5. The present invention provides a virtualized operating platform for material management through the metaverse collaboration module, supports real-time cross-departmental collaboration and training drills, and combined with the virtual twin module, medical staff can perform material management simulation operations and emergency drills in the virtual space, solving the problems of inconvenient cross-departmental collaboration and limited training resources in the prior art, and providing a low-cost, high-efficiency virtual collaboration and training environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a framework diagram of the server of the present invention;

[0059] Figure 2 It is a framework diagram of the data collection module of the present invention;

[0060] Figure 3 It is a framework diagram of the prediction and analysis module of the present invention;

[0061] Figure 4 It is a framework diagram of the material dispatching module of the present invention;

[0062] Figure 5 It is a framework diagram of the inventory management module of the present invention;

[0063] Figure 6 It is a framework diagram of the environment monitoring and control module of the present invention;

[0064] Figure 7 is a framework diagram of the interactive feedback module of the present invention;

[0065] Figure 8 It is a framework diagram of the virtual twin module of the present invention;

[0066] Fig. 9 This is a framework diagram of the Metaverse collaboration module of the present invention;

[0067] Fig.10 The figure is a flow chart of the management method of the present invention. DETAILED DESCRIPTION

[0068] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0069] Please refer to the attached Figure 1 The embodiment of the present invention provides a hospital material management server, including:

[0070] The data collection module is used to collect the material consumption data, number of patients and surgical plans of each department from the hospital information system and electronic medical record system, and transmit the collected data to the predictive analysis module;

[0071] The prediction and analysis module is connected to the data collection module and is used to analyze the data through the adaptive neural network model, predict the future material demand of each department, and send the prediction results to the material scheduling module and the inventory management module;

[0072] The material dispatching module is connected with the forecasting and analysis module to optimize the material distribution path according to the forecasting results and formulate a dispatching plan;

[0073] The inventory management module is connected with the forecast analysis module and the material scheduling module to monitor the inventory status in real time through IoT devices and automatically adjust the inventory level according to the forecast results;

[0074] The environment monitoring and control module is connected to the inventory management module to collect data on the material storage environment in real time and adaptively adjust the storage conditions according to the instructions of the inventory management module;

[0075] The interactive feedback module is connected to the inventory management module to collect real-time feedback from medical staff on the use of supplies and send the feedback information to the forecasting analysis module for analysis to further optimize demand forecasting;

[0076] The virtual twin module is connected to the inventory management module and the environmental monitoring and control module to build a virtual model of hospital material management, map the material status in real time and simulate abnormal situations, and feed the simulation data back to the inventory management module;

[0077] The metaverse collaboration module is connected to the virtual twin module and is used to create a virtual material management space in the metaverse, realize collaboration and training drills, and feed back the drill results to the virtual twin module to improve the model.

[0078] Please refer to the attached Figure 2 , the data collection modules include:

[0079] Historical data collection unit, used to collect historical consumption data of each department;

[0080] Real-time data collection unit for obtaining patient numbers and surgical plans from hospital information systems and electronic medical record systems in real time.

[0081] Please refer to the attached Figure 3 , the predictive analysis module includes:

[0082] Adaptive neural network unit, used to analyze historical and real-time data to predict future material requirements of each department;

[0083] The dynamic adjustment unit is used to dynamically adjust the prediction model parameters according to real-time data changes.

[0084] Specifically, the data processing flow of the adaptive neural network unit is:

[0085] First, collect historical material consumption data and real-time data, including material usage records of each department, number of patients, surgical plans, etc.

[0086] After data preprocessing, it is input into the adaptive neural network, and the input layer receives various variables that affect demand (such as seasonal changes and disease epidemic trends).

[0087] The hidden layer performs complex nonlinear mapping on these input variables, capturing the deep features and patterns in the data through multi-layer processing.

[0088] The output layer generates forecast results and gives the material demand of each department in the future.

[0089] Adaptive learning: Neural networks self-adjust and learn through the back-propagation algorithm. Initially, the network outputs a predicted value based on the input data, compares it with the actual demand, and calculates the error. Based on the size of the error, the network adjusts the connection weights between neurons to keep getting closer to the actual demand. This adaptive learning mechanism enables the neural network to continuously improve the accuracy of predictions.

[0090] Adjustment process of dynamic adjustment unit:

[0091] Real-time data monitoring: The system continuously monitors the real-time data changes of the hospital, including the number of admissions, disease epidemic trends, seasonal changes, etc.

[0092] Parameter adjustment: When the system detects significant changes in the data, the dynamic adjustment unit triggers the parameter adjustment process of the neural network model. By adjusting the weights and bias parameters of the network, the model can adapt to the new data characteristics in a timely manner.

[0093] Model update: After adjustment, the system will be retrained to ensure that the network can still maintain high-accuracy prediction performance in the new data environment.

[0094] Please refer to the attached Figure 4 , the material dispatch module includes:

[0095] The route optimization unit is used to simulate and select the optimal material distribution route based on the prediction results;

[0096] The scheduling execution unit is used to automatically execute the material scheduling plan according to the optimization results.

[0097] Specifically, the path optimization process:

[0098] Input data: The route optimization unit receives the material demand forecast results from the forecast analysis module and relevant information such as the current hospital departments, warehouses, and delivery vehicles.

[0099] Model establishment: Based on the input data, a delivery route optimization model is established and the objective function is set, such as minimizing delivery time, minimizing delivery cost, minimizing vehicle driving distance, etc.

[0100] Solving and Optimizing: Use the above optimization algorithm to simulate and solve the distribution path, select the best distribution path, and consider factors such as department priority, material urgency, road conditions, and the load capacity of the distribution vehicle.

[0101] The process of scheduling execution units includes:

[0102] Task generation: Generate specific delivery tasks based on the optimized delivery route, including the selection of delivery vehicles, the loading order of materials, the priority of delivery, etc.

[0103] Real-time monitoring: During the dispatch execution process, the system monitors the delivery progress in real time and uses IoT devices to track information such as vehicle location and material status.

[0104] Dynamic adjustment: If unexpected situations occur during the distribution process (such as traffic jams, vehicle breakdowns), the dispatch execution unit can dynamically adjust the distribution route and dispatch plan based on real-time data to ensure that materials are delivered in a timely manner.

[0105] Feedback and Recording: Record the execution status of the distribution process and provide feedback to the system to optimize future scheduling strategies.

[0106] Please refer to the attached Figure 5 , the inventory management module includes:

[0107] Inventory status monitoring unit, used to monitor the inventory status of each storage point in real time through IoT devices;

[0108] An automated ordering unit that automatically generates and executes ordering plans based on inventory levels and forecasted demand;

[0109] A virtual twin simulation unit to simulate inventory management strategies in a virtual environment.

[0110] Specifically, the inventory status monitoring unit uses the Internet of Things technology to achieve real-time monitoring and data collection of inventory through sensors and RFID devices deployed at each storage point. The Internet of Things devices communicate wirelessly with the server and transmit real-time inventory data to the inventory management module.

[0111] Data collection and transmission:

[0112] Sensor network: Sensors are placed at various material storage points to monitor the quantity, location, environmental conditions and other information of the materials in real time.

[0113] RFID and barcode scanning: Assign a unique ID to each material through RFID tags or barcodes, and use RFID readers or barcode scanners to track the entry and exit of materials in real time.

[0114] Data transmission: IoT devices transmit the collected inventory data to the inventory management module through wireless networks (such as Wi-Fi, Zigbee) to ensure real-time update of inventory information.

[0115] Real-time monitoring and alarm: The inventory status monitoring unit compares inventory data with preset inventory warning lines. When the inventory level is lower than or higher than the set threshold, the system will automatically issue an alarm to indicate the need for replenishment or inventory adjustment.

[0116] Order plan generation in automatic ordering unit:

[0117] Ordering algorithm: Based on inventory levels, demand forecasts, material consumption rates, and supplier delivery cycles, the automatic ordering unit uses algorithms (such as the economic order quantity EOQ model) to calculate the optimal order quantity and ordering time.

[0118] Safety stock level: Considering the urgency of the materials and the reliability of the supply chain, set the safety stock level to ensure that the ordering plan can meet the minimum inventory requirements and avoid supply interruptions.

[0119] Order execution:

[0120] Order generation and approval: The system automatically generates purchase orders based on calculation results and can set approval procedures; once the order is approved, it is automatically sent to the supplier.

[0121] Order tracking and feedback: The system tracks order status in real time, monitors the procurement, transportation and warehousing process of materials, and ensures the smooth execution of the ordering plan.

[0122] Virtual environment construction:

[0123] Data mapping: Obtain real-time inventory data from the inventory status monitoring unit and the automatic ordering unit, map it into the virtual twin model, and create a real-time synchronized virtual inventory environment.

[0124] Model parameters: The virtual model contains parameters such as material type, quantity, storage location, consumption rate, supply cycle, etc., which are used to simulate the execution effect of inventory management strategy.

[0125] Inventory strategy simulation:

[0126] Strategy testing and optimization: Simulate different inventory management strategies (such as different order batches and replenishment cycles) in a virtual environment, evaluate their impact on inventory levels, costs, and service levels, and find the optimal strategy.

[0127] Anomaly detection and prediction: Simulate potential anomalies in material flow, such as sudden demand or supply chain disruptions, and take countermeasures in advance to ensure inventory safety.

[0128] Data feedback and adjustment: The virtual twin simulation unit feeds back the simulation results to the inventory management module to guide the adjustment and optimization of the actual inventory strategy.

[0129] Please see attached Figure 6 , the environmental monitoring and control module includes:

[0130] Multi-dimensional environmental monitoring unit, used to collect and store environmental data such as temperature, humidity, and light through a sensor network;

[0131] an adaptive control unit for adjusting storage conditions based on real-time environmental data;

[0132] The anomaly detection unit is used to issue an alarm and take countermeasures when an abnormal environmental state is detected.

[0133] Specifically, the adaptive control mechanism in the adaptive control unit:

[0134] Data analysis and decision-making: The system uses real-time monitoring data and preset environmental parameter thresholds to determine whether the current storage environment is in the best state. If a parameter exceeds the set range, the system will make an adjustment decision.

[0135] Actuator control: The system sends control instructions to the corresponding actuators based on the decision results. For example, if the temperature exceeds the standard, the system will start the cooling device; if the humidity is too low, the system will start the humidifier.

[0136] Closed-loop feedback: The adjusted environmental data will continue to be fed back to the system to form a closed-loop control to ensure that the environmental parameters are adjusted within the set range.

[0137] Anomaly Detection and Alerting:

[0138] Anomaly identification: The system uses algorithms to analyze the changing trends of real-time data and triggers abnormal alarms when environmental parameters deviate from the normal range (for example, a sudden rise in temperature or a sharp drop in humidity).

[0139] Multi-level alarms: The system sets different levels of alarms according to the severity of the abnormality. For example, a minor abnormality triggers an early warning prompt, and a serious abnormality triggers an emergency alarm and initiates corresponding response measures.

[0140] Response measures: For serious environmental anomalies, the system can automatically execute emergency measures, such as starting backup power supplies, shutting down affected areas, etc. At the same time, the system will notify relevant personnel to handle on-site.

[0141] Please refer to the attached Figure 7 , the interactive feedback module includes:

[0142] Feedback collection unit, used to collect real-time feedback from medical staff through mobile applications or voice assistants;

[0143] The feedback analysis unit is used to analyze and classify the feedback information using natural language processing technology.

[0144] Specifically, the analysis process:

[0145] Text preprocessing: preprocess the collected feedback information, including noise removal, word segmentation, part-of-speech tagging, etc., to prepare for subsequent analysis.

[0146] Sentiment analysis: Use sentiment analysis models to identify the sentiment in the feedback (such as positive, negative, neutral) and determine the satisfaction of medical staff with the supplies. This helps to quickly identify supplies with more problems.

[0147] Keyword extraction and topic classification: Use keyword extraction and topic classification technology to classify feedback information according to specific topics (such as quality issues, inconvenience in use, improper packaging, etc.) for subsequent targeted processing.

[0148] Abnormality identification and report generation: Identify and classify abnormal issues mentioned in the feedback, generate corresponding reports, and provide decision-making references for managers.

[0149] Please see attached Figure 8 , the virtual twin module includes:

[0150] A data mapping unit, used to map the actual material status into the virtual twin model;

[0151] Simulation unit, used to simulate material flows, storage processes and abnormal situations in a virtual environment.

[0152] Specifically, the simulation unit uses a virtual twin model to simulate the flow of materials, storage processes, and possible abnormal situations in a digital environment. Through simulation, material management strategies can be tested and optimized, and potential abnormalities can be warned and handled in advance.

[0153] Simulation process:

[0154] Material flow simulation: simulate the flow path of materials within the hospital, including the distribution process from the warehouse to each department. Through simulation, different scheduling strategies can be tested to optimize the efficiency of material circulation.

[0155] Storage process simulation: Simulate the storage process of materials in the warehouse in a virtual environment, consider the impact of various storage conditions (such as temperature and humidity) on the quality of materials, and ensure that the materials are stored under optimal conditions.

[0156] Abnormal situation simulation: Simulate possible abnormal situations, such as inventory shortages, abnormal storage environment, delivery delays, etc. Through simulation, potential problems can be discovered in advance and corresponding response strategies can be formulated.

[0157] Strategy optimization and verification: Use simulation results to optimize the current material management strategy and verify the impact of different strategies on material management efficiency and safety, so as to develop the best management plan.

[0158] Please see attached Fig. 9 , the Metaverse collaboration modules include:

[0159] Virtual space creation unit, used to build material management space in the metaverse;

[0160] Virtual interaction unit, used to support medical staff to collaborate on material management through virtual reality equipment;

[0161] Training and Rehearsal Module, used for material management training and emergency drills in a virtual environment.

[0162] Specifically, virtual space construction:

[0163] 3D modeling: Using 3D modeling technology, the hospital's storage facilities, department layout, material types and locations and other information are digitally reconstructed to form a highly simulated 3D virtual environment.

[0164] Data integration: Integrate the real-time material status data collected by IoT devices with the virtual space, so that the virtual environment can reflect the status and location changes of actual materials in real time.

[0165] Environmental presentation: Use VR / AR devices (such as VR helmets and AR glasses) to present virtual space, allowing users to observe and operate material management processes in an immersive manner.

[0166] Interaction process:

[0167] Real-time collaboration: Supports multiple users to enter the virtual space at the same time to perform collaborative operations, such as viewing inventory, planning delivery routes, allocating materials, etc., and realizes remote collaboration through virtual reality devices.

[0168] Voice and gesture control: Using voice recognition and gesture recognition technology, users can complete operations in the virtual environment through natural voice commands or gesture movements, such as selecting, dragging, and placing materials, improving the intuitiveness and efficiency of interaction.

[0169] Data interaction and display: Through visualization tools in the virtual space, users can view data such as the real-time status of materials, inventory levels, delivery progress, and conduct analysis and decision-making.

[0170] Training and drill process:

[0171] Daily operation training: Simulate daily material management operations in a virtual environment, such as material receiving, inventory counting, distribution scheduling, etc., for medical staff to conduct operation training and improve their material management skills.

[0172] Emergency drills: Simulate emergencies (such as material shortages, emergency allocation needs, abnormal storage environment, etc.) to allow medical staff and managers to conduct emergency drills to cultivate their emergency response and teamwork capabilities.

[0173] Feedback and evaluation: The system automatically evaluates the user's operating process and response performance, and provides feedback reports to help users improve material management operations.

[0174] Please see attached Fig.10 , a hospital material management method, comprising the following steps:

[0175] S1. Collect material consumption data of each department from the hospital information system and electronic medical record system through the data collection module;

[0176] S2. Analyze data using the adaptive neural network model in the prediction and analysis module to predict the future material demand of each department;

[0177] S3. Based on the prediction results, use the material dispatch module to optimize the material distribution path and formulate a dispatch plan;

[0178] S4. Monitor inventory status in real time through the inventory management module and automatically adjust inventory levels based on demand forecasts and current inventory status;

[0179] S5. Use the environmental monitoring and control module to collect material storage environment data and adjust storage conditions according to environmental changes;

[0180] S6. Collect real-time feedback from medical staff on the use of supplies in the interactive feedback module and analyze the feedback;

[0181] S7, map the material status in real time in the virtual twin module, and simulate the material flow and abnormal conditions;

[0182] S8. Use the Metaverse Collaboration Module to conduct material management operations and training drills in virtual space.

[0183] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A hospital material management server, characterized in that: include: The data collection module is used to collect the material consumption data, number of patients and surgical plans of each department from the hospital information system and electronic medical record system, and transmit the collected data to the predictive analysis module; A prediction and analysis module, connected to the data collection module, is used to analyze the data through an adaptive neural network model, predict the future material demand of each department, and send the prediction results to the material scheduling module and the inventory management module; A material dispatching module, connected to the forecasting and analysis module, is used to optimize the distribution path of materials according to the forecasting results and formulate a dispatching plan; An inventory management module, connected to the forecasting analysis module and the material scheduling module, is used to monitor the inventory status in real time through the Internet of Things devices and automatically adjust the inventory level according to the forecast results; An environmental monitoring and control module, connected to the inventory management module, is used to collect data on the material storage environment in real time and adaptively adjust storage conditions according to instructions from the inventory management module; An interactive feedback module, connected to the inventory management module, is used to collect real-time feedback from medical staff on the use of supplies and send the feedback information to the forecast analysis module for analysis to further optimize demand forecasting; A virtual twin module, connected to the inventory management module and the environmental monitoring and control module, is used to build a virtual model of hospital material management, map the material status in real time and simulate abnormal situations, and feed the simulation data back to the inventory management module; The metaverse collaboration module is connected to the virtual twin module and is used to create a virtual material management space in the metaverse, realize collaboration and training drills, and feed back the drill results to the virtual twin module to improve the model.

2. A hospital material management server according to claim 1, characterized in that: The data collection module includes: Historical data collection unit, used to collect historical consumption data of each department; Real-time data collection unit for obtaining patient numbers and surgical plans from hospital information systems and electronic medical record systems in real time.

3. A hospital material management server and method according to claim 1, characterized in that: The prediction analysis module includes: Adaptive neural network unit, used to analyze historical and real-time data to predict future material requirements of each department; The dynamic adjustment unit is used to dynamically adjust the prediction model parameters according to real-time data changes.

4. A hospital material management server and method according to claim 1, characterized in that: The material dispatching module includes: The route optimization unit is used to simulate and select the optimal material distribution route based on the prediction results; The scheduling execution unit is used to automatically execute the material scheduling plan according to the optimization results.

5. A hospital material management server and method according to claim 1, characterized in that: The inventory management module includes: Inventory status monitoring unit, used to monitor the inventory status of each storage point in real time through IoT devices; An automated ordering unit that automatically generates and executes ordering plans based on inventory levels and forecasted demand; A virtual twin simulation unit to simulate inventory management strategies in a virtual environment.

6. A hospital material management server and method according to claim 1, characterized in that: The environmental monitoring and control module includes: Multi-dimensional environmental monitoring unit, used to collect and store environmental data such as temperature, humidity, and light through a sensor network; an adaptive control unit for adjusting storage conditions based on real-time environmental data; The anomaly detection unit is used to issue an alarm and take countermeasures when an abnormal environmental state is detected.

7. A hospital material management server and method according to claim 1, characterized in that: The interactive feedback module includes: Feedback collection unit, used to collect real-time feedback from medical staff through mobile applications or voice assistants; The feedback analysis unit is used to analyze and classify the feedback information using natural language processing technology.

8. A hospital material management server and method according to claim 1, characterized in that: The virtual twin module includes: A data mapping unit, used to map the actual material status into the virtual twin model; Simulation unit, used to simulate material flows, storage processes and abnormal situations in a virtual environment.

9. A hospital material management server and method according to claim 1, characterized in that: The metaverse collaboration module includes: Virtual space creation unit, used to build material management space in the metaverse; Virtual interaction unit, used to support medical staff to collaborate on material management through virtual reality equipment; Training and Rehearsal Module, used for material management training and emergency drills in a virtual environment.

10. A hospital material management method, characterized in that: The following steps are involved: S1. Collect material consumption data of each department from the hospital information system and electronic medical record system through the data collection module; S2. Analyze the data using the adaptive neural network model in the prediction and analysis module to predict the future material demand of each department; S3. Based on the prediction results, use the material dispatch module to optimize the material distribution path and formulate a dispatch plan; S4. Monitor inventory status in real time through the inventory management module and automatically adjust inventory levels based on demand forecasts and current inventory status; S5. Use the environmental monitoring and control module to collect material storage environment data and adjust storage conditions according to environmental changes; S6. Collect real-time feedback from medical staff on the use of supplies in the interactive feedback module and analyze the feedback; S7, map the material status in real time in the virtual twin module, and simulate the material flow and abnormal conditions; S8. Use the Metaverse Collaboration Module to conduct material management operations and training drills in virtual space.

Images