Intelligent receiving and sending cabinet system for medical clothing based on RFID technology and its management system

Abstract

The present invention relates to the field of medical management technology, and discloses a medical bedding intelligent receiving and sending cabinet system based on RFID technology and its management system. The system integrates an RFID identification module, a communication module, a cloud data processing module, an intelligent analysis module and an identity authentication module, and realizes the automated and intelligent management of medical bedding. Bedding information is collected in real time through RFID technology to ensure the accuracy and real-time nature of the data; the cloud data processing module analyzes and compares the collected data to optimize resource allocation; the intelligent analysis module uses machine learning algorithms to build demand forecasting models and inventory optimization models to achieve accurate demand forecasting and inventory control; the identity authentication module ensures the security of the system and data privacy. The system not only improves the management efficiency of medical bedding, but also reduces operating costs. It is an indispensable intelligent management tool in the modern medical system.

Description

Technical Field

[0001] The present invention relates to the technical field of medical management, in particular to an intelligent medical clothing transceiver cabinet system based on RFID technology and a management system thereof. Background Art

[0002] In the modern medical system, the management and distribution of medical linens is a crucial but tedious and complex task. The traditional medical linen management process usually relies on manual work, including the receipt, delivery, cleaning, disinfection, classification and storage of linens.

[0003] The current management method is that the tracking and identification of medical bedding mainly relies on manual marking and manual recording, such as using barcodes or handwritten labels. This method is not only inefficient, but also prone to errors, and it is difficult to ensure the accuracy and timeliness of bedding information. In a busy hospital environment, staff may miss or scan the wrong barcode due to negligence, resulting in confusion in bedding management information and even affecting the patient's experience.

[0004] Moreover, since it is impossible to monitor the usage status and inventory status of bedding in real time, it is difficult for hospitals to accurately grasp the actual demand and inventory of bedding, and shortages or surpluses of bedding often occur, which leads to unreasonable allocation of bedding resources. Some departments may face shortages of bedding due to lack of timely replenishment, while other departments may waste resources due to excessive reserves. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent medical clothing receiving and sending cabinet system based on RFID technology and its management system to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: an intelligent transceiver cabinet system for medical clothing based on RFID technology, the system comprising:

[0007] RFID identification module, integrated with RFID reading and writing equipment, is responsible for identifying the RFID tags attached to medical bedding, collecting and preliminarily processing the unique identification information and status data of medical bedding;

[0008] Communication module, responsible for data exchange with cloud data services;

[0009] The cloud data processing module is used to receive and store the medical bedding information from the smart transceiver cabinet, analyze and compare the collected data using cloud computing technology, automatically sort and filter the medical bedding according to the preset algorithm, and obtain the priority of bedding processing;

[0010] Intelligent analysis module, used to realize intelligent scheduling and early warning of medical bedding and optimize resource allocation; analyze historical data through machine learning algorithms to predict the use demand and inventory trend of medical bedding;

[0011] The identity authentication module is used to control the user's operation authority and data access authority to the smart transceiver cabinet according to the user's identity and authority settings.

[0012] Preferably, the medical bedding status data stored in the RFID tag includes the type, specification, washing times, cleaning status and circulation links of the medical bedding.

[0013] Preferably, the cloud data analysis module calculates the processing priority of medical bedding using a multi-index comprehensive evaluation method according to the type, frequency of use, cleaning status and urgency of the medical bedding.

[0014] Preferably, the cloud data analysis module calculates the processing priority of the bedding as follows: P=αT+βF+γC+δE; wherein P represents the processing priority, T represents the type coefficient of the medical bedding, and different coefficient values ​​are set according to different types of medical bedding, with higher coefficient values ​​set for surgical bedding and lower coefficient values ​​set for ordinary bedding;

[0015] F represents the frequency coefficient of use of medical bedding, which is calculated based on the historical use records of medical bedding. The higher the frequency of use, the greater the coefficient value;

[0016] C represents the cleanliness coefficient of medical bedding, which is set according to the cleanliness information recorded in the RFID tag. A lower coefficient value is set for uncleaned bedding, and a higher coefficient value is set for cleaned bedding;

[0017] E represents the urgency coefficient of medical bedding, which is set according to the actual needs of the hospital. A higher coefficient value is set for bedding that is urgently needed, and a lower coefficient value is set for bedding that is not urgently needed;

[0018] α, β, γ, and δ represent the weight values ​​of the type coefficient, the frequency of use coefficient, the cleaning status coefficient, and the urgency coefficient, respectively, and are set according to the actual situation and management strategy of the hospital, and α+β+γ+δ=1.

[0019] Preferably, the intelligent analysis module uses a machine learning algorithm to fit the usage demand and inventory changes of medical bedding, and constructs a demand forecasting model and an inventory optimization model respectively, and uses the residuals of the demand forecasting model and the inventory optimization model to construct a residual fitting model to estimate the causal effect of demand forecasting on inventory optimization; wherein the demand forecasting model is used to predict the future usage demand of medical bedding, and the inventory optimization model is used to determine the optimal inventory level and replenishment strategy.

[0020] Preferably, the method for the intelligent analysis module to obtain model training data is: collecting historical medical bedding usage records, inventory change data and related time series data, cleaning and preprocessing the data to form a basic data set for medical bedding; further, performing feature analysis on the basic data set, including usage frequency analysis, inventory turnover rate analysis and seasonal demand change analysis, and merging the analysis results with the basic data set to form a medical bedding training data set.

[0021] Preferably, the demand forecasting model and the inventory optimization model are both trained based on a long short-term memory network (LSTM) algorithm.

[0022] Preferably, the identity authentication module provides multiple identity authentication methods to control the user's operating authority and data access authority to the smart transceiver cabinet, including card swiping, fingerprint recognition, face recognition and password input.

[0023] Preferably, the communication module adopts 4G / 5G mobile communication technology or Wi-Fi wireless LAN technology to enable real-time data exchange between the medical bedding and clothing receiving and sending cabinet and the cloud data service.

[0024] Preferably, a management system of an intelligent sending and receiving cabinet system for medical bedding based on RFID technology comprises a background management system, a large-screen display interface and a terminal APP for senders and receivers; the background management system is provided for administrators to perform user management, inventory management, tracking query and system setting operations; the large-screen display interface is used to display the inventory status and usage of medical bedding in real time; the terminal APP for senders and receivers provides an operation interface for sending and receiving medical bedding, including the functions of real-time viewing of inventory, receipt records and receiving inventory warning information.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] The application of RFID identification modules makes the tracking and identification of medical bedding fast and accurate. Compared with the current manual marking and manual recording methods, RFID technology can automatically collect the unique identification information and status data of bedding, greatly reducing the occurrence of human errors and missed scans, and improving the accuracy and real-time nature of bedding information.

[0027] Through the collaborative work of the cloud data processing module and the intelligent analysis module, the system can monitor the usage status and inventory status of bedding in real time, and automatically sort and filter medical bedding according to preset algorithms to obtain the priority of bedding processing, which helps hospitals to accurately grasp the actual demand and inventory level of bedding, avoid shortages or surpluses of bedding, and achieve rational allocation and efficient use of resources.

[0028] The intelligent analysis module uses dual machine learning algorithms to analyze historical data, predict the usage demand and inventory trends of medical bedding, and provide hospitals with scientific scheduling and early warning basis. It can not only respond to possible shortages of bedding in advance, but also effectively reduce resource waste and improve the hospital's operational efficiency and service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a working principle diagram of the present invention;

[0030] Figure 2 A schematic diagram of the design for the cloud data analysis module to calculate the priority of the clothing processing;

[0031] Figure 3 Flowchart for model training for the intelligent analysis module;

[0032] Figure 4 This is a front view of the smart receiving and sending cabinet for medical bedding;

[0033] Figure 5 This is the actual picture of the back side of the smart sending and receiving cabinet for medical bedding. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments 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.

[0035] See also Figure 1-5 The present invention provides a technical solution: an intelligent transceiver cabinet system for medical clothing based on RFID technology, the system comprising:

[0036] RFID identification module, which integrates RFID reading and writing equipment, is responsible for identifying the RFID tags attached to medical bedding. Each RFID tag stores the unique identification information of medical bedding, such as serial number, type, size, etc., as well as status data, such as number of cleanings, cleaning status, disinfection status, etc. When medical bedding is placed in or taken out of the smart delivery cabinet, the RFID identification module will automatically read the tag information.

[0037] The communication module is responsible for data exchange between the smart transceiver cabinet and the cloud data service. This module uses stable and reliable communication protocols, such as HTTP, HTTPS or MQTT, to ensure the security and real-time nature of data transmission. When the RFID identification module collects the medical bedding information, the communication module will package this information and send it to the cloud data processing module for further processing. At the same time, the communication module is also responsible for receiving instructions and data issued by the cloud data processing module, such as bedding processing priority, inventory adjustment notification, etc., and passing this information to other modules of the smart transceiver cabinet to perform corresponding operations.

[0038] The communication module uses the following communication technologies: ①4G / 5G mobile communication technology: The transceiver cabinet has a built-in 4G / 5G communication module, which is connected to the cloud data service through the mobile communication network. This method is suitable for application scenarios that require strong mobility and wide coverage. ②Wi-Fi wireless LAN technology: The transceiver cabinet has a built-in Wi-Fi module, which is connected to the cloud data service through a wireless LAN. This method is suitable for application scenarios within hospitals or fixed places, and can provide higher data transmission speed and stability. The communication module selects a suitable communication method based on the actual application environment and needs to ensure real-time data exchange between the transceiver cabinet and the cloud data service.

[0039] The cloud data processing module receives and stores the medical bedding information from the smart transceiver cabinet and uses cloud computing technology to analyze and compare the collected data. Through the preset algorithm, the cloud data processing module can automatically sort and filter the medical bedding, and determine the priority of bedding processing according to factors such as the type, status, and frequency of use of the bedding.

[0040] The intelligent analysis module uses machine learning algorithms to analyze and mine historical data to predict the use demand and inventory trends of medical bedding. The module can learn and identify the demand patterns of bedding in different departments and time periods, so as to make decisions in advance on inventory adjustments and optimize resource allocation. When it is predicted that a department may have a shortage of bedding, the intelligent analysis module will issue a warning signal in time and recommend appropriate supplementary measures.

[0041] Authentication module: This module uses advanced authentication technologies, such as card swiping, fingerprint recognition, facial recognition or password verification, to verify the user's identity and permissions. Only authorized users can operate the smart delivery cabinet and access related data. The authentication module also supports hierarchical management of user permissions, and users of different levels have different operating permissions and data access permissions.

[0042] Card verification: Users authenticate by swiping their employee card or a dedicated RFID card. The system reads the unique identification information in the card and matches it with the user information in the backend database to confirm the user's identity.

[0043] Fingerprint recognition: The user places his finger on the fingerprint reader, and the system collects the fingerprint information and compares it with the pre-stored fingerprint template. If a match is successful, the verification is successful.

[0044] Face recognition: The system captures the user's facial image through the camera and uses the face recognition algorithm to extract and compare features. If it matches the pre-stored face template, the verification is successful.

[0045] Password input: The user enters the preset password through the keyboard or touch screen. The system verifies the correctness of the password to confirm the user's identity.

[0046] The identity authentication module can use the above authentication methods alone or in combination according to the security requirements and management policies of the system to improve the security of the system.

[0047] The present invention will be further described below in conjunction with Examples 1 to 3:

[0048] Embodiment 1:

[0049] The cloud data analysis module uses a multi-index comprehensive evaluation method to calculate the processing priority of medical bedding. Specifically, the module designs a comprehensive evaluation index system based on the type, frequency of use, cleaning status and urgency of medical bedding, and calculates the processing priority through the following formula:

[0050] P=αT+βF+γC+δE

[0051] Among them, P represents the priority of treatment, which is a comprehensive evaluation index; T represents the type coefficient of medical bedding, and different coefficient values ​​are set according to different types of medical bedding. For example, surgical bedding is set with a higher coefficient value, such as 0.8, due to its importance and the particularity of the use environment; while ordinary bedding is set with a lower coefficient value, such as 0.5.

[0052] F represents the frequency coefficient of medical bedding, which is calculated based on the historical usage records of medical bedding. Specifically, the number of times each type of bedding is used within a certain period of time (such as a month) can be counted, and different coefficient values ​​can be set according to the number of times it is used. The higher the frequency of use, the greater the demand for the bedding, so a higher coefficient value is set.

[0053] C represents the cleanliness coefficient of medical bedding, which is set according to the cleanliness information recorded in the RFID tag. Since uncleaned bedding cannot be used directly, a lower coefficient value, such as 0.1, is set; cleaned bedding is set to a higher coefficient value, such as 0.9.

[0054] E represents the urgency coefficient of medical bedding, which is set according to the actual needs of the hospital. For bedding that is urgently needed (such as bedding that needs to be used in large quantities during public health emergencies), a higher coefficient value, such as 0.9, is set; for bedding that is not urgently needed, a lower coefficient value, such as 0.3, is set.

[0055] α, β, γ, and δ represent the weight values ​​of the type coefficient, the frequency of use coefficient, the cleanliness coefficient, and the urgency coefficient, respectively. These weight values ​​are set according to the actual situation and management strategy of the hospital and meet the condition of α+β+γ+δ=1. For example, the hospital can set α=0.3, β=0.25, γ=0.2, and δ=0.25 according to the actual situation, indicating the importance of the four indicators of type, frequency of use, cleanliness, and urgency when calculating the processing priority.

[0056] The implementation process of the above implementation is described with a specific example:

[0057] Assume that the hospital has two types of medical bedding, A and B, of which A is surgical bedding and B is ordinary bedding. According to historical data, the frequency of use of type A bedding is 100 times per month, and the frequency of use of type B bedding is 50 times per month. Currently, 10 pieces of type A bedding are not cleaned, and 20 pieces of type B bedding are not cleaned. At the same time, the hospital receives an emergency notice and needs to immediately prepare 20 pieces of type A bedding for surgery.

[0058] According to the above information, we can set T_A = 0.8 (surgical bedding type coefficient), T_B = 0.5 (ordinary bedding type coefficient); F_A = 1 (A type of bedding is used frequently), F_B = 0.5 (B type of bedding is used relatively less frequently); C_uncleaned = 0.1 (uncleaned bedding coefficient), C_cleaned = 0.9 (cleaned bedding coefficient); E_A = 0.9 (A type of bedding is in urgent need), E_B = 0.3 (B type of bedding is not in urgent need). At the same time, we set the weight values ​​to α = 0.3, β = 0.25, γ = 0.2, and δ = 0.25.

[0059] For a piece of uncleaned bedding in type A bedding, its processing priority P_A_Uncleaned is calculated as follows:

[0060] P_A_Uncleaned = 0.30.8 + 0.251 + 0.20.1 + 0.250.9 = 0.645

[0061] For a piece of uncleaned bedding in type B bedding, its processing priority P_B_Uncleaned is calculated as follows:

[0062] P_B_Uncleaned = 0.30.5 + 0.250.5 + 0.20.1 + 0.250.3 = 0.355

[0063] According to the calculation results, P_A_Uncleaned>P_B_Uncleaned, which means that under the current circumstances, uncleaned bedding in type A has a higher processing priority and should be cleaned and processed first. At the same time, since there is an urgent need for type A bedding, the system can also automatically trigger the emergency processing process according to the set threshold or rules to ensure that the emergency needs of the hospital are met in a timely manner.

[0064] Embodiment 2:

[0065] The intelligent analysis module uses machine learning algorithms, especially the long short-term memory network (LSTM) algorithm, to accurately predict and optimize the demand and inventory changes of medical bedding. The following are the specific steps and implementation methods of model training:

[0066] Step 1: Collect historical medical bedding usage records and inventory change data, including but not limited to daily or weekly bedding usage, inventory, cleaning status, type, and urgency, etc. At the same time, collect relevant time series data, such as dates, holidays, special events, etc., which may affect the demand for bedding.

[0067] Step 2: Clean and preprocess the data, including removing outliers, filling missing values, and unifying data formats and units. The cleaned data forms the basic data set of medical clothing.

[0068] Step 3: Perform feature analysis on the basic data set to extract features that have a significant impact on the demand and inventory changes of bedding, including:

[0069] Frequency of use analysis: Calculate the frequency of use of various types of clothing over different time periods to identify high-demand and low-frequency periods.

[0070] Inventory turnover analysis: Calculate the turnover rate of inventory to evaluate the efficiency of inventory management.

[0071] Analysis of seasonal demand changes: Identify seasonal demand patterns, such as increased demand for thicker blankets in winter.

[0072] The above analysis results are combined with the basic data set to form a medical bedding training data set containing rich features.

[0073] Step 4: Based on the long short-term memory network (LSTM) algorithm, build a demand forecasting model and an inventory optimization model respectively.

[0074] Demand forecasting model: The goal of this model is to predict the future demand for medical bedding. Model inputs include historical usage records, time series features (such as dates, holidays, etc.), and other relevant features (such as bedding type, cleanliness status, etc.). The model output is the predicted future demand for bedding. During model training, the training data set is used for iterative learning, and the prediction error is minimized by adjusting the parameters in the LSTM network (such as weights and biases). After training, the model is able to predict future demand for bedding based on current and historical data.

[0075] Inventory Optimization Model: The goal of this model is to determine the optimal inventory level and replenishment strategy. The model input includes historical inventory change data, predicted clothing demand, and other relevant features (such as inventory cost, replenishment cycle, etc.). The model output is the optimal inventory level and replenishment strategy recommendation. Similarly, the LSTM network is trained using the training data set, and the model parameters are optimized through iterative learning. After training, the model is able to formulate the optimal inventory management strategy based on the current inventory status and predicted demand.

[0076] Residual fitting and causal effect estimation:

[0077] In order to more accurately evaluate the impact of demand forecasting on inventory optimization, a residual fitting model is constructed to estimate the causal effect between the residuals of the demand forecasting model and the inventory optimization model, which helps to understand how forecast errors affect inventory management decisions and further optimize model performance.

[0078] Specifically, the residuals between the actual and expected outputs of the demand forecasting model and inventory optimization model are first calculated. Then, using these residuals as input data, an additional LSTM network or linear regression model is trained to fit the relationship between the residuals. By analyzing the output of the residual fitting model, the causal effect of demand forecasting on inventory optimization can be evaluated, and the model parameters can be adjusted accordingly to improve the accuracy of forecasting and optimization.

[0079] Step 5: After the model training is completed, the model is validated using the validation data set to evaluate the model's prediction performance and optimization effect. During the validation process, the difference between the model prediction results and the actual data is compared, and indicators such as prediction error and accuracy are calculated. If the model performance meets the expected requirements, it is deployed in actual applications to support intelligent scheduling and inventory management decisions for medical bedding.

[0080] The model training process includes:

[0081] Model Training

[0082] Data preparation: Divide the preprocessed training data set into a training set and a validation set. The training set is used for model training, and the validation set is used for model verification and tuning.

[0083] Initialization parameters: Randomly initialize the weight matrix and bias terms in the LSTM network.

[0084] Forward propagation: For each time step, the input data is fed into the LSTM network to calculate the hidden state and output. For the demand forecasting model, the output is the predicted demand for clothing; for the inventory optimization model, the output is the inventory level and replenishment strategy recommendations.

[0085] Loss calculation: Use an appropriate loss function (such as mean squared error MSE) to calculate the difference between the model's prediction and the actual data. For demand forecasting models, the loss function can be expressed as the average of the sum of squared errors between the predicted demand and the actual demand; for inventory optimization models, the loss function can be expressed as the average of the sum of squared errors between the predicted inventory level and the actual inventory level plus a penalty for replenishment costs.

[0086] Backpropagation: Based on the gradient of the loss function, an optimization algorithm (such as the Adam optimizer) is used to update the weight matrix and bias terms in the LSTM network.

[0087] Iterative training: Repeat the process of forward propagation, loss calculation, and back propagation until the loss function converges or the preset number of iterations is reached.

[0088] Model validation: Evaluate the performance of the model on the validation set, such as accuracy, recall, and F1 score indicators. Adjust the model parameters and structure based on the validation results to improve the generalization ability of the model.

[0089] Embodiment 3:

[0090] This embodiment is used to describe a management system of the above-mentioned medical bedding intelligent receiving and sending cabinet system, which is the core part of the medical bedding intelligent receiving and sending cabinet system, including a background management system, a large-screen display interface and a receiving and sending terminal APP. The specific implementation method is as follows:

[0091] The functions of the backend management system include:

[0092] User management: Administrators can add, delete, and modify user information through the backend management system, including user name, work number, role, permissions, etc. At the same time, they can manage user identity authentication methods, such as setting or changing fingerprints, faces, passwords, etc.

[0093] Inventory management: The system updates the inventory information of medical bedding in real time, including the type, quantity, location, status (clean / unclean), etc. The administrator can query the inventory details and make inventory adjustments and counts.

[0094] Tracking and Query: The system records the use history of medical bedding, including the processes of collection, return, cleaning, disinfection, etc. The administrator can use the tracking and query function to quickly locate the location and status of the bedding to ensure the correct use and management of the bedding.

[0095] System Settings: Administrators can use the system settings function to configure the system's basic parameters, verification methods, alarm thresholds, etc. to meet the personalized needs of different hospitals or departments.

[0096] The functions of the large-screen display interface include: The large-screen display interface displays the inventory status and usage of medical bedding in real time in a graphical manner. Including bedding type distribution map, inventory quantity statistics table, and rolling display of collection records. Through the large-screen display, administrators and medical staff can intuitively understand the management status of medical bedding and find and solve problems in a timely manner.

[0097] The functions of the transceiver terminal APP include:

[0098] Check inventory in real time: The mail and mail staff can check the inventory information of medical bedding in real time through the terminal APP, including the type, quantity, location, etc. of the bedding, which is convenient for the mail and mail staff to carry out the sending and receiving operations in time according to the inventory situation.

[0099] Collection records: The system records the information of each collection operation, including the collection time, collection personnel, clothing type, quantity, etc. The mail and mail clerk can query the collection records through the terminal APP to check the collection status.

[0100] Receive inventory warning information: When the inventory of a certain type of medical clothing is lower than the preset threshold, the system sends inventory warning information to the mail and mail personnel through the terminal APP. The mail and mail personnel can replenish the inventory in time according to the warning information to ensure sufficient supply of medical clothing.

[0101] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0102] 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. The intelligent receiving and sending cabinet system for medical bedding based on RFID technology is characterized by: The system comprises: RFID identification module, integrated with RFID reading and writing equipment, is responsible for identifying the RFID tags attached to medical bedding, collecting and preliminarily processing the unique identification information and status data of medical bedding; Communication module, responsible for data exchange with cloud data services; The cloud data processing module is used to receive and store the medical bedding information from the smart transceiver cabinet, analyze and compare the collected data using cloud computing technology, automatically sort and filter the medical bedding according to the preset algorithm, and obtain the priority of bedding processing; Intelligent analysis module, used to realize intelligent scheduling and early warning of medical bedding and optimize resource allocation; analyze historical data through machine learning algorithms to predict the use demand and inventory trend of medical bedding; The identity authentication module is used to control the user's operation authority and data access authority to the smart transceiver cabinet according to the user's identity and authority settings.

2. The medical clothing intelligent transceiver cabinet system based on RFID technology according to claim 1 is characterized by: The medical bedding status data stored in the RFID tag includes the type, specification, number of washes, cleaning status and circulation links of the medical bedding.

3. The medical clothing intelligent transceiver cabinet system based on RFID technology according to claim 2 is characterized by: The cloud data analysis module calculates the processing priority of medical bedding using a multi-index comprehensive evaluation method according to the type, frequency of use, cleaning status and urgency of the medical bedding.

4. The medical clothing intelligent transceiver cabinet system based on RFID technology according to claim 3 is characterized in that: The cloud data analysis module calculates the priority of the medical bedding by the following formula: P = αT + βF + γC + δE; wherein P represents the priority of the medical bedding, and T represents the type coefficient of the medical bedding. Different coefficient values ​​are set according to different types of medical bedding, with higher coefficient values ​​set for surgical bedding and lower coefficient values ​​set for ordinary bedding. F represents the frequency coefficient of use of medical bedding, which is calculated based on the historical use records of medical bedding. The higher the frequency of use, the greater the coefficient value; C represents the cleanliness coefficient of medical bedding, which is set according to the cleanliness information recorded in the RFID tag. A lower coefficient value is set for uncleaned bedding, and a higher coefficient value is set for cleaned bedding; E represents the urgency coefficient of medical bedding, which is set according to the actual needs of the hospital. A higher coefficient value is set for bedding that is urgently needed, and a lower coefficient value is set for bedding that is not urgently needed; α, β, γ, and δ represent the weight values ​​of the type coefficient, the frequency of use coefficient, the cleaning status coefficient, and the urgency coefficient, respectively, and are set according to the actual situation and management strategy of the hospital, and α+β+γ+δ=1.

5. The medical clothing intelligent transceiver cabinet system based on RFID technology according to claim 1 is characterized by: The intelligent analysis module uses a machine learning algorithm to fit the usage demand and inventory changes of medical bedding, and constructs a demand forecasting model and an inventory optimization model respectively. The residuals of the demand forecasting model and the inventory optimization model are used to construct a residual fitting model to estimate the causal effect of demand forecasting on inventory optimization; wherein the demand forecasting model is used to predict the future usage demand of medical bedding, and the inventory optimization model is used to determine the optimal inventory level and replenishment strategy.

6. The medical clothing intelligent transceiver cabinet system based on RFID technology according to claim 5 is characterized in that: The method for the intelligent analysis module to obtain model training data is as follows: collect historical medical bedding usage records, inventory change data and related time series data, clean and preprocess the data to form a basic data set for medical bedding; further, perform feature analysis on the basic data set, including usage frequency analysis, inventory turnover rate analysis and seasonal demand change analysis, and merge the analysis results with the basic data set to form a medical bedding training data set.

7. The medical clothing intelligent transceiver cabinet system based on RFID technology according to claim 5 is characterized by: The demand forecasting model and inventory optimization model are both trained based on the long short-term memory network LSTM algorithm.

8. The medical clothing intelligent transceiver cabinet system based on RFID technology according to claim 1 is characterized by: The identity authentication module provides multiple identity authentication methods to control the user's operation authority and data access authority to the smart transceiver cabinet, including card swiping, fingerprint recognition, face recognition and password input.

9. The medical clothing intelligent transceiver cabinet system based on RFID technology according to claim 1 is characterized by: The communication module adopts 4G / 5G mobile communication technology or Wi-Fi wireless local area network technology to enable real-time data exchange between the medical bedding and clothing receiving and sending cabinet and the cloud data service.

10. A management system for the medical clothing intelligent receiving and sending cabinet system based on RFID technology applied to any one of claims 1 to 9, characterized in that: The management system includes a backend management system, a large-screen display interface, and a transceiver terminal APP; The backend management system allows administrators to perform user management, inventory management, tracking query and system setting operations; The large-screen display interface is used to display the inventory status and usage of medical bedding in real time; The terminal APP for mail and mail personnel provides an operation interface for sending and receiving medical bedding, including the functions of real-time inventory viewing, receipt records and receiving inventory warning information.

Images