Intelligent medical equipment management system and method

Abstract

This invention discloses an intelligent medical equipment management system and method. This system leverages blockchain technology to achieve decentralized and trusted storage of equipment usage records, using SHA-256 salted hashing and Merkle tree structures to ensure data security and traceability. It integrates smart contracts to automate inventory policy execution and combines an ARIMA-LSTM hybrid model with a linear programming algorithm to construct an intelligent scheduling system. The system encompasses core modules such as data acquisition, blockchain storage, smart contracts, and predictive optimization. It addresses data security risks, inventory inefficiencies, and scheduling blindness inherent in traditional management. It is suitable for intelligent management of medical equipment throughout its entire lifecycle, significantly improving medical resource utilization efficiency and management compliance.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical equipment management, and specifically relates to an intelligent medical equipment management system and method. Background Art

[0002] In the medical industry, medical equipment usage record management, inventory scheduling, and resource optimization are key links in ensuring medical safety and efficiency. Traditional management methods have the following shortcomings:

[0003] Insufficient data security and traceability: Relying on a centralized database to store device usage records, it is vulnerable to tampering and leakage risks, and difficult to share across institutions, which cannot meet the high security requirements of medical data.

[0004] Inefficient inventory management: Inventory management dominated by manual experience leads to backlogs or shortages, lacks dynamic adjustments driven by real-time data, and results in low equipment utilization.

[0005] Lack of intelligent scheduling strategies: The existing system relies on manual intervention and cannot perform intelligent scheduling based on historical data and real-time demand, resulting in unreasonable resource allocation.

[0006] While existing technologies such as electronic health record (EHR) systems, medical asset management systems, and enterprise resource planning (ERP) systems provide basic data management, they lack significant capabilities in data security, intelligent analysis, and automated processes. Therefore, a medical device management system that integrates blockchain technology and intelligent algorithms is urgently needed to address these challenges. Summary of the Invention

[0007] The purpose of the present invention is to provide an intelligent medical equipment management system and method to solve the problems in the prior art mentioned in the background art, which have significant deficiencies in data security, intelligent analysis and automated processes.

[0008] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0009] An intelligent medical equipment management system, comprising:

[0010] The data collection module is used to collect medical device usage data in real time through IoT devices, including device ID, timestamp, operating status, usage duration, and fault records; and generate basic information about medical devices through the device management module, including device ID, type, and usage status;

[0011] A blockchain storage module is used to encrypt the usage data and basic information and store them in the blockchain. The encryption process includes adding a randomly generated salt value to each record and then performing hash encryption using the SHA-256 algorithm. The encrypted data is encapsulated into blocks and the data on the blockchain is managed using a Merkle tree structure.

[0012] A smart contract module for defining rules for medical device usage records and inventory management, enabling automated creation and verification of device usage records and automated execution of inventory scheduling policies. The rules include defining the format of device usage records, setting minimum inventory levels, and implementing replenishment and scheduling policies.

[0013] An inventory management module, which is used to manage the inventory information of medical devices, including device type, quantity, and storage location, based on the rules set by the smart contract module, optimize the inventory structure through a first-in-first-out algorithm and a minimum inventory level algorithm, and trigger a replenishment operation when the inventory falls below the minimum inventory level;

[0014] A scheduling optimization module is used to optimize the equipment scheduling strategy through a linear programming algorithm based on the real-time data obtained by the data acquisition module and the prediction results of the prediction analysis module to achieve the optimal configuration of equipment resources;

[0015] Predictive analysis module, which uses historical equipment usage data to predict changes in equipment demand through time series analysis and machine learning algorithms, assisting in inventory management and scheduling decisions;

[0016] The data query and traceability module allows authorized users to query the usage records and inventory scheduling records of medical equipment, and supports traceability by time, equipment type, equipment ID and other conditions;

[0017] The user management module is used to implement user rights management, ensuring that only authorized users can access and operate the system, and combining the identity authentication mechanism to ensure data access security;

[0018] Furthermore, the intelligent medical equipment management system also includes a consensus mechanism module; the consensus mechanism module is used to adopt an improved proof of authority mechanism (PoA) to ensure the real-time update and consistency of data in the blockchain network, and to verify and broadcast transactions by randomly selecting a master verification node to achieve balanced participation of each node and data synchronization.

[0019] According to the above technical solution, the encrypted device usage records and inventory change records are used as leaf nodes, and the root hash value is generated by hashing and merging layer by layer. By verifying the root hash value and the hash value of the sibling nodes on the path from the leaf node to the root node, the data integrity is quickly verified.

[0020] According to the above technical solution, the device usage record format defined by the smart contract module includes device ID, operator ID, usage time, and operation type, and the operation types include startup, shutdown, maintenance, scheduling, and replenishment; the smart contract module automatically receives a record request when the device operation is completed, uses a mapping data structure to map the device ID to the corresponding operation record list, hashes the record, and inserts it into the blockchain through a Merkle tree, and triggers a synchronous update to push the data to all nodes.

[0021] According to the above technical solution, the IoT device of the data acquisition module includes a sensor for real-time collection of the device's power on / off time, operating status, operating hours, and fault records; the data acquisition module cleans and preprocesses the raw data, including removing duplicate data, filling missing values, detecting and eliminating outliers, and standardizing data.

[0022] According to the above technical solution, the time series analysis algorithm used by the predictive analysis module includes the ARIMA model, and the machine learning algorithm includes the LSTM network. The model is trained through historical equipment usage data to predict future equipment demand.

[0023] According to the above technical solution, the linear programming algorithm of the scheduling optimization module takes minimizing the equipment scheduling cost as the objective function and equipment availability and demand as the constraints to solve the optimal scheduling solution.

[0024] According to the above technical solution, the identity authentication mechanism of the user management module includes biometric recognition, password verification or digital certificate verification, ensuring that only authorized personnel can access device data and perform inventory scheduling operations.

[0025] A medical equipment management method comprises the following steps:

[0026] Data collection steps: Use IoT devices to collect real-time usage data of medical devices, and generate basic information of medical devices through the device management module;

[0027] Data processing steps: Clean and pre-process the collected usage data, and identify device usage patterns through clustering algorithms;

[0028] Data storage step: The processed usage data and basic information are added with a salt value and then SHA-256 hashed and encrypted. The data is then encapsulated into blocks and stored in the blockchain using a Merkle tree structure.

[0029] Smart contract execution steps: Define equipment usage record rules and inventory management rules through smart contracts, automatically create and verify equipment usage records, and trigger replenishment operations based on inventory levels;

[0030] Predictive analysis step: Use historical data to predict equipment demand through time series analysis and machine learning algorithms;

[0031] Scheduling optimization steps: Generate the optimal scheduling plan through linear programming algorithm based on real-time data and prediction results;

[0032] Query and trace steps: Authorized users can query equipment usage records and inventory scheduling records through the data query and traceability module.

[0033] Furthermore, the medical device management method also includes a consensus verification step: the consensus verification step ensures the real-time update and consistency of data in the blockchain network through an improved PoA mechanism. After the main verification node verifies the transaction, it broadcasts it to other nodes to complete synchronization.

[0034] According to the above technical solution, the clustering algorithm adopts the K-means algorithm to cluster the equipment according to its usage time, frequency, number of failures and other characteristics, and identify high-frequency used equipment, idle equipment and moderately used equipment.

[0035] According to the above technical solution, in the data storage step, the root node of the Merkle tree contains the hash values ​​of all device records. The root hash value is generated by hashing the records into leaf nodes and gradually merging them upward. Data integrity verification is achieved by verifying the root hash value and the verification path.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] In this invention, through blockchain decentralized storage and salted hash algorithm, tamper-proof and non-repudiation of device records are achieved, meeting medical data security compliance requirements such as HIPAA; the Merkle tree structure reduces the data verification complexity to O(logN), improving the efficiency of integrity verification in large-scale data scenarios.

[0038] Dynamic monitoring of minimum inventory based on real-time data and intelligent replenishment using the EOQ model increase inventory turnover by 40%-60%, effectively reducing inventory holding costs. The combination of the FIFO algorithm and expiration date management controls the equipment expiration loss rate to below 1%. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 Schematic diagram of the system structure of the present invention;

[0040] Figure 2 This is a flow chart of the medical equipment management method of the present invention. DETAILED DESCRIPTION

[0041] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0042] Example 1

[0043] like Figure 1 As shown, an intelligent medical equipment management system includes:

[0044] Data collection module, used to collect medical equipment usage data in real time through IoT devices and generate basic information about medical equipment;

[0045] A blockchain storage module is used to encrypt the usage data and basic information and store them in the blockchain, and to manage the data on the blockchain using a Merkle tree structure;

[0046] Smart contract module, used to define the rules for medical device usage records and inventory management, to automate the creation and verification of device usage records and the execution of inventory scheduling strategies;

[0047] An inventory management module, configured to manage inventory information of medical devices based on the rules set by the smart contract module;

[0048] A scheduling optimization module, configured to use the real-time data acquired by the data acquisition module and the prediction results of the prediction analysis module;

[0049] Predictive analysis module, which uses historical equipment usage data to predict changes in equipment demand through time series analysis and machine learning algorithms, assisting in inventory management and scheduling decisions;

[0050] Data query and traceability module, used to allow authorized users to query the usage records and inventory scheduling records of medical equipment;

[0051] The user management module is used to implement user rights management, ensuring that only authorized users can access and operate the system, and combined with the identity authentication mechanism to ensure data access security.

[0052] In this invention, through blockchain decentralized storage and salted hash algorithm, tamper-proof and non-repudiation of device records are achieved, meeting medical data security compliance requirements such as HIPAA; the Merkle tree structure reduces the data verification complexity to O(logN), improving the efficiency of integrity verification in large-scale data scenarios.

[0053] Dynamic monitoring of minimum inventory based on real-time data and intelligent replenishment using the EOQ model increase inventory turnover by 40%-60%, effectively reducing inventory holding costs. The combination of the FIFO algorithm and expiration date management controls the equipment expiration loss rate to below 1%.

[0054] Example 2

[0055] This embodiment is a further refinement of the first embodiment.

[0056] System Architecture Overview: The intelligent medical device management system constructed in this embodiment integrates multiple modules, including data collection, storage, analysis, scheduling, and user management, aiming to improve the efficiency, security, and intelligence of medical device management. The system primarily includes a data collection module, a blockchain storage module, a smart contract module, an inventory management module, a scheduling optimization module, a predictive analysis module, a data query and traceability module, and a user management module. These modules work together to achieve intelligent management of medical devices throughout their entire lifecycle.

[0057] In a specific embodiment, the data acquisition module is specifically:

[0058] This system is being implemented in a large general hospital. Medical equipment in various hospital departments, such as CT machines, MRI machines, and monitors, are equipped with IoT sensors. These sensors collect device data at regular intervals (e.g., 5-minute intervals), including device ID, timestamp, operating status (operating, faulty, idle), usage duration, and fault history. For example, for a monitor with the device ID "001-JHY-01," at 10:00:00 on October 1, 2024, the sensor collected the following data: timestamp "2024-10-01 10:00:00," operating status "operating," usage duration "3 hours 20 minutes," and fault history "none."

[0059] The collected raw data is first stored in a time series database. Before storage, it is cleaned and preprocessed: a program is written to detect and remove duplicate data; missing values, if the usage duration is missing, are filled with the median of the device's historical usage duration; the Z-Score method is used to detect outliers, with a threshold of 3. If the Z-Score value of a device's usage duration is greater than 3, it is identified as an outlier and removed or corrected; a normalization formula is used to scale the data to the range of 0-1 to facilitate subsequent analysis. The normalization formula is as follows:

[0060]

[0061] Where, It means subtracting the minimum value min(D) of the data set from the data D so that the minimum value of the original data is adjusted to 0. It means calculating the range of a data set (the difference between the maximum and minimum values) and is used to standardize the scaling range of the data.

[0062] In a specific embodiment, the blockchain storage module is specifically:

[0063] An improved encryption storage method is used for cleaned and preprocessed device data. During the encryption phase, a randomly generated salt value is appended to each device usage record. The salt generation algorithm is: salt = HMAC-SHA256(timestamp||deviceID, secretKey). For example, the salt value "abc123" is added to the records of the aforementioned monitor, and then encrypted using the SHA-256 algorithm. The encryption process involves first padding the complete data, including the device ID, timestamp, operating status, usage duration, fault records, and salt value, to a length multiple of 512. The data is then divided into 512-bit blocks, and the hash value of each block is recursively calculated using the SHA-256 hash function.

[0064] Encrypted data is encapsulated into blocks and added to a Merkle tree. The Merkle tree construction process involves treating each encrypted device record as a leaf node, merging the hash values ​​of adjacent leaf nodes to calculate a new hash value, and so on, until the root node is generated. When querying or verifying data, the root hash value and the hash values ​​of sibling nodes along the path from the leaf node to the root node can be used to quickly verify data integrity. Specifically, the Merkle tree data structure is constructed, and the root hash value is generated through layer-by-layer hash aggregation (parentHash = SHA-256(leftChild||rightChild)), supporting efficient integrity verification.

[0065] For example, when the integrity of a record of a monitor needs to be verified, the hash value of the record's leaf node and the hash value of the sibling node on the path are provided and compared with the root hash value. If they are consistent, it proves that the data is complete and has not been tampered with.

[0066] The consensus mechanism module adopts an improved Proof of Authority (PoA) algorithm and selects the main verification node through a random number generator (seed = SHA-256 (blockNumber||systemTime)). The verification process includes three stages: transaction preprocessing, hash value broadcasting, and node synchronization to ensure low-latency data consistency of the blockchain network.

[0067] In a specific embodiment, the smart contract module is specifically:

[0068] Smart contracts are written in Solidity and deployed on the Ethereum blockchain. They define a structured data model for device operation records (including device ID, operator digital certificate, Unix timestamp, and operation type enumeration). A mapping (bytes32=>Record[]) data structure is used to establish an index mapping from device ID to operation records. Precompiled functions are integrated to verify record legitimacy. This ensures business logic consistency by comparing adjacent record timestamps (Δt>0) and state transition matrices (e.g., "idle→running" is legal, "fault→shutdown" is illegal).

[0069] In the contract, the standard format of medical equipment usage records is defined, such as the device ID is a string type with a length not exceeding 32 bits; the operator ID is in the Ethereum address format; the usage time is in the timestamp format; the operation type is an enumeration type, including "start", "shutdown", "maintenance", "scheduling", "replenishment", etc.

[0070] When a device is operated, such as when a CT machine is activated by an operator using the command "0x1234567890abcdef..." at 9:00 AM on October 2, 2024, the smart contract automatically receives a record request. Using a mapping data structure, the CT machine's device ID is mapped to a corresponding list of operation records. This record is hashed and inserted into the blockchain via a Merkle tree, triggering a synchronized update to push the data to all nodes. The smart contract also compares the timestamps and device status of the preceding and following records to verify the order and logical consistency of the records. If the CT machine was idle before the activation and the timestamps are in logical order, the record is successful. If the state was running or the timestamp is unreasonable, the record is rejected and an error message is returned.

[0071] In terms of inventory management, the smart contract sets the minimum stock level for each device. For example, for a certain model of syringe, the minimum stock level is set at 100 syringes. When the inventory management module detects that the stock of this model of syringe falls below 100 syringes, the replenishment logic in the smart contract is triggered. The required replenishment quantity is calculated as shown in the following formula:

[0072]

[0073] Assuming that the current inventory Icurrent is 80 pieces, then ΔI=100-80=20 pieces, and then initiate a purchase or replenishment operation.

[0074] In a specific embodiment, the inventory management module is specifically:

[0075] The hospital has a dedicated equipment warehouse, and the inventory management module manages the medical equipment in the warehouse. This module utilizes a FIFO algorithm and a minimum inventory level algorithm to ensure inventory rationality. During inventory management, equipment is entered into the warehouse in the order of arrival, and the entry time is recorded. For example, a batch of 50 scalpels of a certain model entered the warehouse at 10:00 on October 3, 2024, and the entry time is recorded as "2024-10-03 10:00."

[0076] When managing outbound shipments, priority is given to the earliest incoming devices. When a surgical procedure requires a scalpel, the system prioritizes the outbound shipment of scalpels that arrived on October 3, 2024, according to a first-in-first-out (FIFO) algorithm. Furthermore, inventory levels are continuously monitored. When a device's inventory falls below the minimum level, such as the aforementioned syringe model with fewer than 100 units, a replenishment process is immediately triggered, executing according to the replenishment policy defined by the smart contract to ensure adequate inventory and minimize equipment stockouts.

[0077] In a specific embodiment, the scheduling optimization module is:

[0078] The scheduling optimization module performs equipment scheduling based on a linear programming algorithm. Taking the scheduling of surgical equipment in a hospital as an example, the objective function is defined as minimizing the equipment scheduling cost, as shown in the following formula:

[0079]

[0080] in The dispatch cost for each surgical device (such as equipment transfer costs, debugging costs, etc.), is the dispatch quantity of the corresponding equipment, is the delay cost, is the demand delay. Set constraints including equipment availability (e.g. whether a surgical device is idle within a specific time period and whether it can be used normally) and demand (The quantity of equipment required will be determined based on the surgical schedule).

[0081] By solving a linear programming problem, we can obtain the optimal scheduling solution. Assume that within a certain time period, three different types of surgical equipment are available for scheduling. The scheduling costs of different equipment and the equipment requirements of each surgery vary. Through linear programming calculations, we prioritize the equipment combination with the lowest scheduling cost and the best performance for each surgery. This achieves the optimal allocation of equipment resources, improves equipment utilization efficiency, and reduces equipment idle time.

[0082] In a specific embodiment, the prediction analysis module is specifically:

[0083] The predictive analysis module uses historical equipment usage data to forecast equipment demand. The module collects medical equipment usage data from the hospital over the past year, including the frequency and duration of use of each device, and demand over different time periods. It uses the ARIMA model and LSTM network for forecasting.

[0084] Taking a high-frequency electric knife as an example, we first use the ARIMA model to perform time series analysis on its historical usage data. According to the formula:

[0085]

[0086] in is the predicted value, For the data used in the previous period, The random error term, α, reflects the difference between the actual value and the model-based prediction at time t. The model coefficients α and β are obtained by fitting historical data and parameter estimation. α represents the model's constant term, and β represents the autoregressive coefficient. The trained LSTM network then uses historical usage data as input to learn the time series characteristics and trends in the data. Combining the results of the ARIMA model and the LSTM network, the demand for the high-frequency electrosurgical unit is predicted for the next week. This forecast can assist in inventory management and scheduling decisions, allowing for early preparation for equipment deployment and inventory replenishment.

[0087] In a specific embodiment, the data query and tracing module is specifically:

[0088] When hospital staff (such as equipment managers and medical staff) need to query equipment information, they enter query criteria such as equipment ID, time range, and equipment type through the system's user interface. For example, if an equipment manager wants to query the usage records of all CT machines from October 1 to October 10, 2024, they would select "CT machine" as the equipment type and "2024-10-01 to 2024-10-10" as the time range on the query interface and click the query button.

[0089] The system uses the data query and traceability module to query data within the blockchain storage module using an indexing mechanism. This indexing mechanism utilizes a B+ tree structure, indexed by information such as device ID and timestamp. During a query, the system quickly locates the corresponding record in the B+ tree based on the query criteria entered. The system then retrieves the encrypted data from the blockchain, decrypts it, and displays it to the user. This allows for full traceability of device usage and inventory scheduling records, facilitating staff's understanding of device history and providing a basis for device management and maintenance.

[0090] In a specific embodiment, the user management module is specifically:

[0091] The hospital assigns a unique ID to each person with access to the system, using a combination of password and digital certificate authentication. When logging into the system, staff members must enter their username and password and insert their digital certificate for identity verification.

[0092] The system assigns different permissions based on user roles (such as equipment administrator, medical staff, and department director). Equipment administrators have full permissions for equipment information management, inventory management, and scheduling management; medical staff only have the ability to query equipment usage records and apply for equipment loans; and department directors have the ability to query equipment usage statistics and approve some scheduling. Strict permission management ensures the security of system data and the standardization of operations, preventing unauthorized access and data tampering.

[0093] In a specific embodiment, this implementation provides an overall system operation process.

[0094] like Figure 2 As shown in the figure, during daily operation, the data acquisition module continuously collects usage data and basic information about medical devices, and performs cleaning and preprocessing. The processed data is encrypted and stored on the blockchain by the blockchain storage module. Simultaneously, the smart contract module automatically manages and verifies device usage records. The inventory management module uses the FIFO algorithm and minimum inventory level algorithm to manage inventory and ensure timely replenishment based on the rules set by the smart contract and device usage.

[0095] The Scheduling Optimization Module combines real-time data from the Data Acquisition Module with forecasts from the Predictive Analysis Module to generate an optimal scheduling plan using a linear programming algorithm, enabling the proper allocation of equipment. The Predictive Analysis Module continuously leverages historical data to forecast equipment demand, providing support for inventory management and scheduling decisions.

[0096] Staff can query device-related information through the data query and traceability module, while the user management module ensures secure system access and standardized operations. The entire system uses an improved PoA consensus mechanism to ensure real-time data updates and consistency within the blockchain network. The master verification node verifies transactions and broadcasts them to other nodes for synchronization, ensuring the accuracy and consistency of data across all modules and enabling intelligent and efficient medical device management.

[0097] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0098] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. An intelligent medical equipment management system, characterized by: include: Data collection module, used to collect medical equipment usage data in real time through IoT devices and generate basic information about medical equipment; A blockchain storage module is used to encrypt the usage data and basic information and store them in the blockchain, and to manage the data on the blockchain using a Merkle tree structure; The Merkle tree structure management method includes: using encrypted device usage records and inventory change records as leaf nodes, generating a root hash value through layer-by-layer hashing, and quickly verifying data integrity by verifying the root hash value and the hash values ​​of sibling nodes on the path from the leaf node to the root node; The smart contract module is used to define the rules for medical equipment usage records and inventory management, enabling automated creation and verification of equipment usage records and automated execution of inventory scheduling strategies. The equipment usage record format defined by the smart contract module includes device ID, operator ID, usage time, and operation type, with operation types including startup, shutdown, maintenance, scheduling, and replenishment. The smart contract module automatically receives a record request when a device operation is completed, uses a mapping data structure to map the device ID to the corresponding operation record list, hashes the record, and inserts it into the blockchain through a Merkle tree. It then triggers a synchronous update to push the data to all nodes. An inventory management module, configured to manage inventory information of medical devices based on the rules set by the smart contract module; A scheduling optimization module, configured to use the real-time data acquired by the data acquisition module and the prediction results of the prediction analysis module; Predictive analysis module, which uses historical equipment usage data to predict changes in equipment demand through time series analysis and machine learning algorithms, assisting in inventory management and scheduling decisions; Data query and traceability module, used to allow authorized users to query the usage records and inventory scheduling records of medical equipment; The user management module is used to implement user rights management, ensuring that only authorized users can access and operate the system, and combined with the identity authentication mechanism to ensure data access security.

2. The intelligent medical equipment management system according to claim 1, characterized in that: The IoT devices of the data acquisition module include sensors, which are used to collect the power on / off time, operating status, operating hours, and fault records of the equipment in real time; The data acquisition module cleans and preprocesses the raw data, including removing duplicate data, filling missing values, detecting and eliminating outliers, and data standardization.

3. The intelligent medical equipment management system according to claim 1, characterized in that: The time series analysis algorithms used in the predictive analysis module include the ARIMA model, and the machine learning algorithms include the LSTM network. The model is trained through historical equipment usage data to predict future equipment demand.

4. The intelligent medical equipment management system according to claim 1, characterized in that: The linear programming algorithm of the scheduling optimization module takes minimizing the equipment scheduling cost as the objective function and equipment availability and demand as constraints to obtain the optimal scheduling solution.

5. The intelligent medical equipment management system according to claim 1, characterized in that: The user management module's authentication mechanisms include biometric recognition, password verification, or digital certificate verification, ensuring that only authorized personnel can access device data and perform inventory scheduling operations.

6. A medical equipment management method, characterized in that: The intelligent medical equipment management system according to any one of claims 1 to 5 is characterized by comprising the following steps: Data collection steps: Use IoT devices to collect real-time usage data of medical devices, and generate basic information of medical devices through the device management module; Data processing steps: Clean and pre-process the collected usage data, and identify device usage patterns through clustering algorithms; Data storage steps: The processed usage data and basic information are encrypted with a salt value and then hashed with SHA-256. The data is then encapsulated into blocks and stored in the blockchain via a Merkle tree structure. During the encryption phase, a randomly generated salt value is added to each device usage record. The salt value generation algorithm is: salt = HMAC-SHA256(timestamp||deviceID, secretKey). The encrypted data is encapsulated into blocks and added to the Merkle tree. The Merkle tree data structure is constructed, and the root hash value is generated by layer-by-layer hash aggregation (parentHash = SHA-256(leftChild||rightChild)), supporting efficient integrity verification. Smart contract execution steps: define equipment usage record rules and inventory management rules through smart contracts, automatically create and verify equipment usage records, and trigger replenishment operations based on inventory levels; specifically, define a structured data model for equipment operation records containing equipment ID, operator digital certificate, Unix timestamp, and operation type enumeration value, using mapping The data structure establishes an index mapping from device ID to operation record; the precompiled function is integrated to verify the legitimacy of the record by comparing the timestamps of adjacent records. and state transition matrix; In terms of inventory management, the smart contract sets the minimum inventory level for each device and calculates the required replenishment quantity as shown in the following formula: in, Indicates the minimum inventory, Indicates the current inventory, Indicates the difference between the minimum inventory and the current inventory; Predictive analysis steps: Use historical data through time series analysis and machine learning algorithms to predict equipment demand. The predictive analysis module uses historical equipment usage data to predict equipment demand. Collect medical equipment usage data from the past year, including the frequency of use of each device, usage duration, and demand in different time periods, and use the ARIMA model for prediction: in is the predicted value, For the data used in the previous period, Represents the random error term, which reflects the difference between the actual value and the model-based predicted value at time t; the coefficient of the model is obtained by fitting historical data and parameter estimation ;in, represents the constant term of the model, represents the autoregressive coefficient; Scheduling optimization steps: Based on real-time data and prediction results, the optimal scheduling plan is generated through the linear programming algorithm. The scheduling optimization module performs equipment scheduling based on the linear programming algorithm and defines the objective function as minimizing the equipment scheduling cost, as shown in the following formula: in For each surgical device dispatch cost, is the dispatch quantity of the corresponding equipment, is the delay cost, Delay amount for the demand; set constraints including equipment availability and demand ; Query and trace steps: Authorized users can query equipment usage records and inventory scheduling records through the data query and traceability module.

7. A medical equipment management method according to claim 6, characterized in that: The clustering algorithm adopts the K-means algorithm to cluster the equipment according to its usage time, frequency, and number of failures, and identify high-frequency used equipment, idle equipment, and moderately used equipment.

8. A medical equipment management method according to claim 6, characterized in that: In the data storage step, the root node of the Merkle tree contains the hash values ​​of all device records. The root hash value is generated by hashing the records into leaf nodes and gradually merging them upwards. Data integrity verification is achieved by verifying the root hash value and the verification path.

Images