Medical instrument digital supply chain batch intelligent management method and device

Abstract

The embodiment of the invention provides a medical instrument digital supply chain batch intelligent management method and device, and the method comprises the steps: guaranteeing the data safety in combination with a block chain technology, achieving the accurate demand prediction through deep learning, achieving the intelligent inventory optimization capability, enabling a system to quickly respond to the market change, and enabling the system to be more intelligent. Automation and intelligence of replenishment decision are realized; the overall operation efficiency of the medical instrument supply chain is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and specifically to a method and device for intelligent batch management of a digital supply chain of medical devices. Background Art

[0002] Batch management of medical devices faces many challenges in the current medical supply chain. Traditional management methods mainly rely on manual experience and fixed rules. When faced with complex and changing medical needs, there are often problems of inventory backlog or shortage. Although some institutions have begun to adopt information systems for management, there are still obvious deficiencies in data security, forecast accuracy and inventory optimization.

[0003] Current batch management systems generally have problems such as low data credibility and single prediction models. Most systems lack effective data tamper-proof mechanisms, making it difficult to ensure the authenticity and traceability of information. At the same time, existing demand forecasting methods are often too simple and fail to fully consider time series characteristics and the integration of multi-source data, resulting in a large deviation between the forecast results and actual demand.

[0004] It is particularly noteworthy that the existing systems are weak in handling medical device returns and inventory optimization. Most systems cannot accurately identify and classify the status of returned devices, and lack intelligent replenishment decision-making mechanisms, which leads to inefficient inventory management and high operating costs. At the same time, when faced with sudden demand or seasonal fluctuations, the system's adaptability and response speed are insufficient.

[0005] Therefore, the medical industry urgently needs a smarter and safer batch management solution. Summary of the invention

[0006] In response to the problems in the prior art, the present application provides a method and device for intelligent batch management of a digital supply chain of medical devices, which can effectively improve the overall operational efficiency of the medical device supply chain.

[0007] In order to solve at least one of the above problems, the present application provides the following technical solutions:

[0008] In a first aspect, the present application provides a method for intelligent batch management of a digital supply chain of medical devices, comprising:

[0009] Construct a unique box set ID based on the classification code of the medical device, encrypt the box set ID using the elliptic curve digital signature algorithm, perform a hash operation on the digital signature and the medical device information using a symmetric key to generate an information summary, store the information summary in a tamper-proof blockchain database, and establish a mapping relationship between the box set ID and the tamper-proof blockchain database;

[0010] Write the box set ID and the medical device information into a multi-level index structure, verify data consistency based on the historical consumption data stored in the multi-level index structure and the information summary in the tamper-proof blockchain database, construct a time series sample in units of days for the verified historical consumption data, perform sliding window segmentation on the time series sample and extract time series features, input the time series feature data into the input layer of the long short-term memory neural network model, perform maximum and minimum value normalization on the time series feature data through a forget gate and an input gate, use an adaptive moment estimation optimizer to train the hidden layer parameters of the long short-term memory neural network model, and determine the future average daily consumption and fluctuation range of medical devices based on the trained long short-term memory neural network model;

[0011] The medical device information is bound to the box set ID in a batch matching manner, feature extraction and image classification are performed on the returned medical devices based on the residual deep convolutional neural network, and the image classification result is fused with the output value of the long short-term memory neural network model by evidence theory data to obtain the time series correlation coefficient and the root mean square error value of the fused data, and a dynamic weight allocation matrix based on a genetic algorithm is constructed according to the time series correlation coefficient and the root mean square error value, and the weight parameters of the long short-term memory neural network model are updated online according to the dynamic weight allocation matrix, and the updated weight parameters and their corresponding distribution strategies and replenishment opportunities are recorded in the tamper-proof blockchain database, and the trigger probability of the replenishment opportunity is calculated based on the distribution strategy recorded in the tamper-proof blockchain database combined with the safety inventory threshold of each type of medical device, and when the trigger probability exceeds the preset threshold, a replenishment list is automatically generated.

[0012] Furthermore, the unique box set ID is constructed based on the classification code of the medical device, the box set ID is encrypted using the elliptic curve digital signature algorithm, the digital signature and the medical device information are hashed using a symmetric key to generate an information summary, the information summary is stored in a tamper-proof blockchain database, and a mapping relationship between the box set ID and the tamper-proof blockchain database is established, including:

[0013] Taking the box set ID as input, obtaining a binary data block, mapping the binary data block to a point on an elliptic curve, generating a public key pair based on a base point P on the elliptic curve and a random number k, calculating a signature value using the public key pair, and outputting an encrypted digital signature according to the binary data block and the signature value;

[0014] The production date, expiration date, product batch number, and sterilization batch number of the medical device are read as medical device information, the medical device information and the digital signature are merged into a string to be processed, the hash value of the string to be processed is iteratively calculated through the SHA-256 hash function, the hash value and timestamp are organized into a block information summary using a Merkle tree structure, and the block information summary is encrypted based on an asymmetric encryption algorithm and written into a tamper-proof blockchain database.

[0015] Furthermore, the box set ID and the medical device information are written into a multi-level index structure, and data consistency is verified according to the historical consumption data stored in the multi-level index structure and the information summary in the tamper-proof blockchain database, including:

[0016] Construct a three-layer index structure, where the top-layer index records the storage location pointer of the box set ID, the middle-layer index stores the category and specification information of the medical device, and the bottom-layer index records the consumption record of the medical device according to the timestamp. The association relationship between the indexes of each layer is organized through the B+ tree structure, and the data validity flag is set in the bottom-layer index. The bitmap index technology is used to compress and store the medical device information;

[0017] Read the historical consumption data with timestamp from the underlying index, obtain the block information summary of the corresponding timestamp from the tamper-proof blockchain database, decrypt the block information summary using the public key of the elliptic curve digital signature algorithm, perform hash calculation on the decrypted information summary and the historical consumption data, and compare whether the calculation result is consistent with the hash value stored in the block information summary.

[0018] Furthermore, the verified historical consumption data is used to construct a time series sample in units of days, the time series sample is segmented into sliding windows and time series features are extracted, including:

[0019] The historical consumption data is aggregated by day according to the timestamp to calculate the average daily consumption, the standard deviation of the average daily consumption is normalized to eliminate the dimension effect, the missing time point data is supplemented by a linear interpolation method, and the high-frequency noise in the average daily consumption is removed by a low-pass filter to construct a multidimensional time series sample containing consumption, time periodicity and seasonal characteristics;

[0020] The length of the sliding window is set to 14 days and the step length is 1 day. The statistical characteristics of the data in each window, including the mean, variance, kurtosis, and skewness, are calculated. The frequency domain characteristics of the window data are extracted by wavelet transform. The periodic characteristics of the window data are obtained through autocorrelation analysis. The statistical characteristics, frequency domain characteristics, and periodic characteristics are combined to form a feature vector to construct a time series feature data set.

[0021] Furthermore, the time series feature data is input into the input layer of the long short-term memory neural network model, the time series feature data is normalized to the maximum and minimum values ​​through a forget gate and an input gate, an adaptive moment estimation optimizer is used to train the hidden layer parameters of the long short-term memory neural network model, and the future average daily consumption and fluctuation range of medical devices are determined based on the trained long short-term memory neural network model, including:

[0022] The time series feature data is divided into 80% training set and 20% validation set, and the maximum and minimum value intervals are calculated for each feature dimension. The MinMax normalization method is used to map the feature value to the [0,1] interval. The sigmoid activation function is set in the forget gate of the long short-term memory neural network to perform nonlinear transformation on the feature data. The weight distribution of the feature data is adjusted through the tanh activation function of the input gate, and the dropout mechanism is used to randomly inactivate some neurons to prevent overfitting.

[0023] The bidirectional long short-term memory neural network structure contains two hidden layers. The number of neurons in each layer is set to 128. The xavier initialization method is used to initialize the hidden layer parameters. The Adam optimizer is used to iteratively update the network parameters. The loss function is built based on the root mean square error. The learning rate is set to 0.001. When the loss value of the validation set does not decrease for 5 consecutive epochs, the early stopping mechanism is activated. The trained model parameters are saved for predicting the consumption range in the next 30 days.

[0024] Furthermore, the medical device information is bound to the box set ID in a batch matching manner, feature extraction and image classification are performed on the returned medical devices based on the residual deep convolutional neural network, and the image classification results are fused with the output values ​​of the long short-term memory neural network model by evidence theory data to obtain the time series correlation coefficient and root mean square error value of the fused data, including:

[0025] Build a 50-layer residual deep convolutional neural network structure, set a 3×3 convolution kernel to extract local features of medical device images, enhance feature expression capabilities through batch normalization layers and ReLU activation functions, add short-circuit connections in residual blocks to alleviate the gradient vanishing problem, use a global average pooling layer to reduce feature dimensions, output the probability distribution of the integrity of medical devices in the fully connected layer, and output the probability distribution as the image classification result;

[0026] Based on the DS evidence theory, the basic probability distribution function of the two evidence sources is constructed. The support function and likelihood function are calculated to represent the credibility of the image classification result and the predicted output value respectively. The Dempster combination rule is used to perform orthogonal sum operations on the two evidence sources. The Pearson correlation coefficient and root mean square error value of the fused data and the original data are calculated to evaluate the fusion effect.

[0027] Furthermore, a dynamic weight allocation matrix based on a genetic algorithm is constructed according to the time series correlation coefficient and the root mean square error value, and the weight parameters of the long short-term memory neural network model are updated online according to the dynamic weight allocation matrix, and the updated weight parameters and their corresponding distribution strategies and replenishment opportunities are recorded in the tamper-proof blockchain database. Based on the distribution strategies recorded in the tamper-proof blockchain database and the safety inventory thresholds of various medical devices, the trigger probability of the replenishment opportunity is calculated. When the trigger probability exceeds the preset threshold, a replenishment list is automatically generated, including:

[0028] The time series correlation coefficient and the root mean square error value are used as input variables of the fitness function. The population individuals are initialized using real number coding, the crossover probability is set to 0.8 and the mutation probability is set to 0.1. The tournament selection strategy is used to select high-quality individuals. A new generation of population is generated through the arithmetic crossover operator and the Gaussian mutation operator. The weight allocation scheme is iteratively optimized until the maximum number of iterations is reached. The optimal individual is decoded into a dynamic weight allocation matrix for updating the weight parameters of the long short-term memory neural network model.

[0029] A replenishment decision model is constructed based on a Bayesian network. The current inventory, predicted consumption, safety stock threshold and historical replenishment records of medical devices are used as input nodes of conditional probability. The maximum likelihood estimation method is used to learn network parameters. The posterior probability distribution of replenishment timing is calculated through the variable elimination algorithm. The posterior probability distribution is normalized to obtain the trigger probability. When the trigger probability is greater than 0.8, the replenishment demand is written into the tamper-proof blockchain database.

[0030] In a second aspect, the present application provides a medical device digital supply chain batch intelligent management device, comprising:

[0031] An information encryption module, used to construct a unique box set ID based on the classification code of the medical device, encrypt the box set ID using an elliptic curve digital signature algorithm, perform a hash operation on the digital signature and the medical device information using a symmetric key to generate an information summary, store the information summary in a tamper-proof blockchain database, and establish a mapping relationship between the box set ID and the tamper-proof blockchain database;

[0032] A consumption prediction module is used to write the box set ID and the medical device information into a multi-level index structure, verify data consistency based on the historical consumption data stored in the multi-level index structure and the information summary in the tamper-proof blockchain database, construct a time series sample in units of days for the verified historical consumption data, perform sliding window segmentation on the time series sample and extract time series features, input the time series feature data into the input layer of the long short-term memory neural network model, perform maximum and minimum value normalization processing on the time series feature data through a forget gate and an input gate, use an adaptive moment estimation optimizer to train the hidden layer parameters of the long short-term memory neural network model, and determine the future average daily consumption and fluctuation range of medical devices based on the trained long short-term memory neural network model;

[0033] A replenishment monitoring module is used to bind the medical device information with the box set ID in a batch matching manner, perform feature extraction and image classification on the returned medical devices based on a residual deep convolutional neural network, perform evidence theory data fusion on the image classification result and the output value of the long short-term memory neural network model to obtain a time series correlation coefficient and a root mean square error value of the fused data, construct a dynamic weight allocation matrix based on a genetic algorithm according to the time series correlation coefficient and the root mean square error value, and perform online update of the weight parameters of the long short-term memory neural network model according to the dynamic weight allocation matrix, record the updated weight parameters and their corresponding distribution strategies and replenishment opportunities in the tamper-proof blockchain database, calculate the trigger probability of the replenishment opportunity based on the distribution strategies recorded in the tamper-proof blockchain database combined with the safety inventory thresholds of various medical devices, and automatically generate a replenishment list when the trigger probability exceeds a preset threshold.

[0034] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for batch intelligent management of a digital supply chain of medical devices are implemented.

[0035] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the medical device digital supply chain batch intelligent management method.

[0036] In a fifth aspect, the present application provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the medical device digital supply chain batch intelligent management method.

[0037] From the above technical solution, it can be seen that this application provides a method and device for batch intelligent management of medical device digital supply chain, which ensures data security by combining blockchain technology, realizes accurate demand forecasting through deep learning, and has intelligent inventory optimization capabilities. At the same time, the system can also quickly respond to market changes, realize the automation and intelligence of replenishment decisions, thereby effectively improving the overall operational efficiency of the medical device supply chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 This is one of the flow charts of the medical device digital supply chain batch intelligent management method in the embodiment of the present application;

[0040] Figure 2 This is the second flow chart of the medical device digital supply chain batch intelligent management method in the embodiment of the present application;

[0041] Figure 3 This is the third flow chart of the medical device digital supply chain batch intelligent management method in the embodiment of the present application;

[0042] Figure 4 This is a fourth flow chart of the medical device digital supply chain batch intelligent management method in the embodiment of the present application;

[0043] Figure 5 This is the fifth flow chart of the medical device digital supply chain batch intelligent management method in the embodiment of the present application;

[0044] Figure 6 This is the sixth flow chart of the medical device digital supply chain batch intelligent management method in the embodiment of the present application;

[0045] Figure 7 This is the seventh flow chart of the medical device digital supply chain batch intelligent management method in the embodiment of the present application;

[0046] Figure 8 This is a structural diagram of a medical device digital supply chain batch intelligent management device in an embodiment of the present application;

[0047] Fig. 9 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application.

[0048] Reference numerals:

[0049] Electronic device 9600, central processing unit 9100, memory 9140, communication module 9110, input unit 9120, audio processor 9130, display 9160, power supply 9170, buffer memory 9141, application / function storage unit 9142, data storage unit 9143, driver program storage unit 9144, antenna 9111, speaker 9131, microphone 9132. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0051] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0052] Considering the problems existing in the prior art, this application provides a method and device for intelligent batch management of a medical device digital supply chain, which ensures data security by combining blockchain technology, achieves accurate demand forecasting through deep learning, and has intelligent inventory optimization capabilities. At the same time, the system can also quickly respond to market changes, realize the automation and intelligence of replenishment decisions, and effectively improve the overall operational efficiency of the medical device supply chain.

[0053] In order to effectively improve the overall operational efficiency of the medical device supply chain, this application provides an embodiment of a medical device digital supply chain batch intelligent management method, see Figure 1 The medical device digital supply chain batch intelligent management method specifically includes the following contents:

[0054] Step S101: construct a unique box set ID based on the classification code of the medical device, encrypt the box set ID using the elliptic curve digital signature algorithm, perform a hash operation on the digital signature and the medical device information using a symmetric key to generate an information summary, store the information summary in a tamper-proof blockchain database, and establish a mapping relationship between the box set ID and the tamper-proof blockchain database;

[0055] Optionally, in this embodiment, this step realizes the unique identification generation and tamper-proof storage mechanism of the medical device box set. First, the system constructs the box set ID based on the classification code of the medical device, and uses a hierarchical coding method to encode the device category, specification model, production batch and other information into a fixed-length string to ensure uniqueness and traceability in the entire supply chain system.

[0056] During the encryption process, the system uses the Elliptic Curve Digital Signature Algorithm (ECDSA) for security processing. This algorithm is based on the elliptic curve discrete logarithm problem. Compared with the traditional RSA algorithm, it has a shorter key length and higher computational efficiency at the same security strength. The system first generates a pair of public and private keys. The private key is used to generate a digital signature, and the public key is used to verify the validity of the signature.

[0057] The generation of symmetric keys uses a high-intensity key derivation function to generate key materials of sufficient length through random number seeds and key expansion algorithms. The system uses the symmetric key to encrypt digital signatures and key information of medical devices, and then calculates the information summary through the SHA-256 hash algorithm. The hash process is one-way and collision-resistant, which can effectively prevent information from being tampered with.

[0058] The storage of information summaries uses distributed ledger technology to write data into a tamper-proof blockchain database. Each block contains multiple transaction records, and each record contains fields such as timestamp, previous block hash, and information summary. Blocks are linked by cryptographic hashes to form an unalterable chain structure. The system uses a consensus mechanism to ensure data consistency and uses smart contracts to automatically perform data verification and update operations.

[0059] In order to improve data retrieval efficiency, the system establishes a mapping relationship between the box set ID and the blockchain database. The mapping table uses a distributed hash table structure to support fast positioning and access to specific records. The system uses a consistent hashing algorithm to achieve uniform distribution of data and ensures high data availability through a replica mechanism.

[0060] This technical solution effectively solves the unique identification and information security storage problems of medical device identification through the combination of encryption algorithms and blockchain technology. The system realizes the immutability and traceability of data, providing reliable technical support for the full life cycle management of medical devices. At the same time, the efficient computing characteristics based on elliptic curve encryption ensure the performance of the system in large-scale application scenarios.

[0061] In addition, the distributed characteristics and consensus mechanism of the solution effectively avoid the risk of single point failure and improve the reliability of the system. The storage structure based on the hash chain and the automatic execution mechanism of the smart contract reduce human intervention and improve the automation level of data management. The establishment of mapping relationships optimizes data retrieval efficiency and provides a convenient data access interface for upper-level applications.

[0062] Step S102: writing the box set ID and the medical device information into a multi-level index structure, verifying data consistency based on the historical consumption data stored in the multi-level index structure and the information summary in the tamper-proof blockchain database, constructing a time series sample in units of days for the verified historical consumption data, performing sliding window segmentation on the time series sample and extracting time series features, inputting the time series feature data into the input layer of the long short-term memory neural network model, performing maximum and minimum value normalization processing on the time series feature data through a forget gate and an input gate, training the hidden layer parameters of the long short-term memory neural network model using an adaptive moment estimation optimizer, and determining the future average daily consumption and fluctuation range of medical devices based on the trained long short-term memory neural network model;

[0063] Optionally, in this embodiment, this step implements the multi-level index storage of medical device consumption data and the LSTM-based time series prediction mechanism. The system first builds a multi-level index structure, using the B+ tree as the basic data structure to organize the box set ID and medical device information into a hierarchical index system. Each index node contains a key-value pair and a pointer, supporting efficient range query and data update operations.

[0064] During the data consistency verification process, the system extracts historical consumption data from the multi-level index structure and obtains the information summary of the corresponding time period from the blockchain database. By comparing the hash values ​​of the two, it ensures that the data has not been tampered with. The verified data is collected by day to construct a time series sample containing consumption, timestamps and other relevant features.

[0065] The time series feature extraction uses sliding window technology, and the window size is dynamically adjusted according to the periodic characteristics of the data. In each window, the system calculates statistical features (mean, variance, kurtosis, etc.) and frequency domain features (Fourier transform coefficients), and captures the periodic pattern of the data through autocorrelation analysis. These features together constitute the feature vector that describes the consumption pattern of medical devices.

[0066] The input layer of the LSTM neural network model receives the processed time series feature data. Through the forget gate mechanism, the model can adaptively decide the degree to which historical information should be retained or discarded. The input gate is responsible for controlling the proportion of new information entering the memory unit. The feature data is normalized to the maximum and minimum values, and the value range is uniformly mapped to the [0,1] interval, eliminating the dimension effect and improving the stability of model training.

[0067] The model training process uses the adaptive moment estimation (AMSGrad) optimizer, which is an improved version of the Adam algorithm. It adaptively adjusts the learning rate of each parameter by recording the exponential moving average of historical gradients. This mechanism effectively prevents drastic fluctuations in the learning rate and improves the stability of model convergence. The back propagation algorithm is used to update the hidden layer parameters to optimize the network weights by minimizing the mean square error between the predicted value and the actual value.

[0068] The trained LSTM model can capture the long-term dependency and short-term fluctuation characteristics of medical device consumption. By performing probability distribution analysis on the model output, the system can predict the average daily consumption in the future and estimate its fluctuation range. This provides reliable data support for subsequent inventory management and replenishment decisions.

[0069] This technical solution solves the problem of efficient storage and accurate prediction of medical device consumption data. The multi-level index structure provides fast data access capabilities, blockchain verification ensures the credibility of the data, and the LSTM-based deep learning model achieves accurate modeling of complex time series patterns. The system has good scalability and prediction accuracy, providing strong support for the intelligent management of medical devices.

[0070] Step S103: The medical device information is bound to the box set ID by batch matching, feature extraction and image classification are performed on the returned medical devices based on the residual deep convolutional neural network, and the image classification result is fused with the output value of the long short-term memory neural network model by evidence theory data to obtain the time series correlation coefficient and the root mean square error value of the fused data, and a dynamic weight allocation matrix based on a genetic algorithm is constructed according to the time series correlation coefficient and the root mean square error value, and the weight parameters of the long short-term memory neural network model are updated online according to the dynamic weight allocation matrix, and the updated weight parameters and their corresponding distribution strategies and replenishment opportunities are recorded in the tamper-proof blockchain database, and the trigger probability of the replenishment opportunity is calculated based on the distribution strategy recorded in the tamper-proof blockchain database and the safety inventory threshold of each type of medical device, and when the trigger probability exceeds the preset threshold, a replenishment list is automatically generated.

[0071] Optionally, in this embodiment, this step realizes the complete process of intelligent distribution and replenishment management of medical devices. First, the system uses batch matching technology to bind the medical device information with the box set ID, and ensures the traceability of the device by establishing a unique mapping relationship. The matching process adopts a parallel processing mechanism to improve the efficiency of large-scale data processing.

[0072] In the process of returning the device, the system uses a residual deep convolutional neural network for image analysis. The network structure contains multiple residual blocks, each of which consists of a convolution layer, a batch normalization layer, and an activation function. The introduction of residual connections effectively alleviates the gradient vanishing problem of the deep network and improves the accuracy of feature extraction. The convolution operation uses convolution kernels of different scales to capture the multi-scale features of the device image and achieve accurate classification of the device integrity and usage status.

[0073] The evidence theory data fusion process combines the image classification results with the prediction results of the LSTM model. The system constructs a basic probability distribution function based on the Dempster-Shafer theory, and obtains the fused decision results by calculating the evidence conflict degree and combination rules. This fusion mechanism makes full use of the complementarity of multi-source data and improves the reliability of prediction.

[0074] Based on the time series correlation coefficient and root mean square error calculated by fusion data as evaluation indicators, the system constructs a dynamic weight allocation matrix. Genetic algorithm is used to optimize the weight allocation scheme, and continuously evolves better weight combinations through operations such as encoding, crossover, and mutation. The fitness function comprehensively considers the prediction accuracy and model complexity, controlling the risk of overfitting while ensuring performance.

[0075] The online update of the LSTM model adopts an incremental learning method to adjust the network parameters according to the dynamic weight matrix. The sliding window mechanism is used in the update process to maintain the balance between historical data and new data to ensure the adaptability and stability of the model. The updated weight parameters and corresponding distribution strategies are recorded in the blockchain database to ensure the immutability of the data.

[0076] The timing of replenishment is determined based on a comprehensive evaluation of multi-dimensional indicators. The system calculates the safety stock threshold for each type of medical device, and builds a probability model to estimate the probability of replenishment triggering, based on the predicted consumption trend and fluctuation range. When the trigger probability exceeds the preset threshold, the system automatically generates a replenishment list containing the device type, quantity, and priority.

[0077] This technical solution realizes the intelligent and automated management of medical device replenishment through the organic combination of deep learning, evidence theory and genetic algorithm. The system has strong environmental adaptability and decision-making reliability, and effectively solves the subjectivity and lag problems in traditional replenishment management. At the same time, blockchain-based data storage ensures the traceability and transparency of the decision-making process, providing an innovative technical solution for medical device supply chain management.

[0078] The implementation of this solution has significantly improved the accuracy of medical device inventory management, reduced inventory backlogs and shortage risks, and optimized supply chain operational efficiency. The adaptive nature of the system enables it to continuously optimize decision-making models, providing strong support for the refined management of medical institutions.

[0079] From the above description, it can be seen that the medical device digital supply chain batch intelligent management method provided by the embodiment of the present application can ensure data security by combining blockchain technology, achieve accurate demand forecasting through deep learning, and have intelligent inventory optimization capabilities. At the same time, the system can also quickly respond to market changes, realize the automation and intelligence of replenishment decisions, thereby effectively improving the overall operational efficiency of the medical device supply chain.

[0080] In one embodiment of the medical device digital supply chain batch intelligent management method of the present application, see Figure 2 , and can also include the following:

[0081] Step S201: Taking the box set ID as input, obtaining a binary data block, mapping the binary data block to a point on an elliptic curve, generating a public key pair based on a base point P on the elliptic curve and a random number k, calculating a signature value using the public key pair, and outputting an encrypted digital signature according to the binary data block and the signature value;

[0082] Step S202: Read the production date, expiration date, product batch number, and sterilization batch number of the medical device as medical device information, merge the medical device information and the digital signature into a string to be processed, iteratively calculate the hash value of the string to be processed through the SHA-256 hash function, organize the hash value and timestamp into a block information summary using a Merkle tree structure, encrypt the block information summary based on an asymmetric encryption algorithm, and write it into a tamper-proof blockchain database.

[0083] Optionally, in this embodiment, these two steps realize the digital signature generation and blockchain storage mechanism of the medical device box set. In step S201, the system first converts the box set ID into a binary data block, and uses a point compression algorithm to map the data to a point on the elliptic curve. The elliptic curve uses the P-256 curve recommended by NIST, which has good security and computational efficiency. The base point P is a generator on the curve, with a large prime order, which ensures the difficulty of the discrete logarithm problem.

[0084] The random number k is generated using a cryptographically secure random number generator, which collects system noise as a random source through an entropy pool. Based on the random number k and the base point P, the system calculates a temporary public key R = kP, and generates a private key d and the corresponding public key Q = dP. The signature value is calculated using an improved ECDSA algorithm, which contains two components (r, s), where r is the x-coordinate of the temporary public key R, and s is calculated using the message hash value, the random number k, and the private key d.

[0085] In step S202, the system processes the key attribute information of the medical device. After being standardized, this information is concatenated with the digital signature to form a string to be processed. The SHA-256 hash function iteratively calculates the string, using its avalanche effect characteristics to ensure that the output hash value is highly sensitive to even the slightest change in the input.

[0086] The Merkle tree is constructed in a bottom-up manner, with hash values ​​as leaf nodes. Every two nodes are combined to calculate the hash value of the parent node until the root hash is generated. The timestamp is in UTC format, accurate to milliseconds, and together with the hash value, it forms a summary of the block information. This tree structure supports efficient data verification and partial update operations.

[0087] The encryption of block information summary adopts RSA-2048 asymmetric encryption algorithm. The system generates independent key pairs for each participant, with public key used for encryption and private key used for decryption. The OAEP padding scheme is used in the encryption process to enhance the resistance to chosen ciphertext attacks. The encrypted data is written into the blockchain database, and each block is linked to the previous block through a hash pointer, forming an unalterable chain structure.

[0088] This technical solution realizes the secure storage and tamper-proof mechanism of medical device information through the combination of elliptic curve cryptography and blockchain technology. The ECDSA digital signature ensures the authenticity and integrity of the data, while the block structure based on the Merkle tree provides efficient data verification capabilities. The system supports distributed storage and access control, effectively solving the security risks of traditional centralized storage.

[0089] The implementation of this solution has significantly improved the security and reliability of medical device information management. The dual mechanisms of cryptographic protection and blockchain storage ensure the security of data during transmission and storage. The system has good scalability and interoperability, providing reliable technical support for the full life cycle management of medical devices. At the same time, the efficient verification mechanism based on the Merkle tree reduces the computational overhead of data verification and improves the response performance of the system.

[0090] In one embodiment of the medical device digital supply chain batch intelligent management method of the present application, see Figure 3 , and can also include the following:

[0091] Step S301: construct a three-layer index structure, where the top-layer index records the storage location pointer of the box set ID, the middle-layer index stores the category and specification information of the medical device, and the bottom-layer index records the consumption record of the medical device according to the timestamp. The association relationship between the indexes of each layer is organized by a B+ tree structure, and a data validity flag is set in the bottom-layer index. The bitmap index technology is used to compress and store the medical device information;

[0092] Step S302: Read the historical consumption data with timestamp from the underlying index, obtain the block information summary of the corresponding timestamp from the tamper-proof blockchain database, decrypt the block information summary using the public key of the elliptic curve digital signature algorithm, perform hash calculation on the decrypted information summary and the historical consumption data, and compare whether the calculation result is consistent with the hash value stored in the block information summary.

[0093] Optionally, in this embodiment, these two steps establish an efficient multi-layer index system for medical device information and its data verification mechanism. In step S301, the system uses a three-layer index architecture to organize and manage medical device information. The top-level index uses a sparse index structure to store the mapping relationship between the box set ID and the physical storage location. Each index item contains an ID value and a pointer to the actual data block. This design reduces the number of index items and optimizes memory usage.

[0094] The middle-level index uses a dense indexing method to record the categories and specifications of medical devices in detail. The index items are sorted by category code, and each category contains sub-items with specific specifications, forming a hierarchical organizational structure. This layer of index supports range query and fuzzy matching, which improves retrieval efficiency. The bottom-level index uses the storage mode of a time series database to record the use of medical devices in timestamp order. Each record contains information such as timestamp, operation type, quantity change, etc.

[0095] The B+ tree structure is used to organize the association between the three layers of indexes. The non-leaf nodes of the B+ tree store index key values ​​and child node pointers. The leaf nodes contain pointers to actual data records and are connected to each other through linked lists. This structure supports efficient interval queries and sequential access. The data validity flag in the bottom-level index uses one byte to indicate the status of the record, including valid, deleted, expired, and other states.

[0096] Bitmap indexing technology converts medical device information into a compressed binary format by establishing a mapping relationship between attribute values ​​and bit vectors. For attributes with a limited range of values, such as specifications and models, dictionary encoding is used before establishing a bitmap index, which significantly reduces storage space. Bitmap indexing supports fast Boolean operations and improves the processing efficiency of complex queries.

[0097] In step S302, the system implements a data integrity verification mechanism. First, the historical consumption data is read from the underlying index, including the complete time series information. The system retrieves the corresponding block information summary from the blockchain database based on the timestamp. This process uses the time index to speed up the search and ensure the rapid location of the target block.

[0098] The block information summary is decrypted using the public key of the elliptic curve digital signature algorithm. The decryption process uses batch mode to process verification requests for multiple blocks at the same time to improve system throughput. The decrypted information summary contains the hash value, timestamp and other metadata of the original data.

[0099] The system uses the same hash algorithm to hash the historical consumption data and generate a new hash value. The hash calculation process takes into account all key fields of the data to ensure the comprehensiveness of data integrity verification. By comparing the newly generated hash value with the original hash value stored in the block, the system can detect whether the data has been tampered with.

[0100] This technical solution solves the data organization efficiency and integrity verification problems in medical device information management. The multi-layer index structure provides a flexible data access method, and the bitmap index technology achieves efficient data compression and query. At the same time, the blockchain-based verification mechanism ensures the credibility of the data.

[0101] The implementation effect is remarkable, the system query performance is improved, the storage space utilization rate is increased, and the data integrity is reliably guaranteed. This solution is particularly suitable for handling the storage and management of large-scale medical device information, providing medical institutions with efficient and reliable information management methods.

[0102] In one embodiment of the medical device digital supply chain batch intelligent management method of the present application, see Figure 4 , and can also include the following:

[0103] Step S401: Calculate the daily average consumption by collecting historical consumption data by day according to the timestamp, normalize the daily average consumption by standard deviation to eliminate the dimension effect, use linear interpolation method to supplement the missing time point data, use low-pass filter to remove high-frequency noise in the daily average consumption, and construct a multidimensional time series sample containing consumption, time periodicity and seasonal characteristics;

[0104] Step S402: Set the length of the sliding window to 14 days and the step length to 1 day, calculate the statistical characteristics of the data in each window including the mean, variance, kurtosis, and skewness, use wavelet transform to extract the frequency domain characteristics of the window data, and obtain the periodic characteristics of the window data through autocorrelation analysis. The statistical characteristics, frequency domain characteristics and periodic characteristics are combined to form a feature vector to construct a time series feature data set.

[0105] Optionally, in this embodiment, these two steps construct a time series feature extraction system for medical device consumption data. In step S401, the historical consumption data is first aggregated at the daily level according to the timestamp. The system uses a weighted average method to calculate the average daily consumption, and the weight is dynamically adjusted according to the credibility and integrity of the data. For records across days, the system allocates them to the corresponding dates according to the time ratio.

[0106] The standard deviation standardization process uses the Z-score method to convert the average daily consumption into a standard normal distribution. The specific calculation formula is z = (x-μ) / σ, where x is the original value, μ is the mean, and σ is the standard deviation. This processing method eliminates the dimensional differences between different medical devices and makes the data comparable. For missing time point data, the system uses piecewise linear interpolation to supplement and maintain data continuity. The interpolation calculation takes into account the trend of adjacent data points to ensure the rationality of the interpolation results.

[0107] The low-pass filter uses a Butterworth filter, and the cutoff frequency is dynamically set according to the characteristics of the data. Zero-phase filtering technology is used in the filtering process to avoid phase distortion. The filtered data retains the main trend changes and removes the influence of random fluctuations and abnormal fluctuations. The construction of multidimensional time series samples considers three dimensions: basic consumption, cyclical changes, and seasonal characteristics. The cyclical characteristics are extracted through Fourier analysis, and the seasonal characteristics are obtained through moving average decomposition.

[0108] In step S402, the 14-day sliding window is set based on the typical cycle of the medical device usage pattern. The window sliding step is 1 day to ensure the continuity and integrity of feature extraction. In each window, the system calculates four basic statistics: the mean reflects the overall level, the variance indicates the degree of fluctuation, the kurtosis describes the peak degree of the distribution, and the skewness represents the symmetry of the distribution.

[0109] Wavelet transform uses the discrete wavelet transform (DWT) method and the Daubechies wavelet basis function. Through 5-layer decomposition, the frequency domain features at different scales are obtained. The wavelet coefficients reflect the energy distribution of the time series in different frequency bands and can capture the local characteristics and mutation characteristics of the data.

[0110] Autocorrelation analysis uses the partial autocorrelation function (PACF), and the maximum lag period is set to half the window length. By analyzing the change pattern of the autocorrelation coefficient, the periodic components of the time series are identified. Significant autocorrelation coefficients correspond to important periodic features.

[0111] The feature vector is constructed by feature cascading, combining different types of features in a predefined order. The statistical features occupy 4 dimensions, the frequency domain features retain 10 main components after dimensionality reduction through principal component analysis, and the periodic features select the 5 most significant autocorrelation coefficients. Finally, a 19-dimensional feature vector is formed.

[0112] This technical solution solves the problem of feature extraction and representation of medical device consumption data. Through multi-level feature extraction, the system can comprehensively capture various characteristics of consumption patterns and provide a reliable data basis for subsequent predictive analysis.

[0113] The implementation results show that the scheme can effectively extract the key features of time series, and the feature vector has good distinguishability and stability. The system has high processing efficiency, moderate computing overhead, and good practicality. The extracted features can effectively support various analysis tasks such as anomaly detection and trend prediction.

[0114] In one embodiment of the medical device digital supply chain batch intelligent management method of the present application, see Figure 5 , and can also include the following:

[0115] Step S501: divide the time series feature data into 80% training set and 20% validation set, calculate the maximum and minimum value intervals for each feature dimension, use the MinMax normalization method to map the feature value to the [0,1] interval, set the sigmoid activation function in the forget gate of the long short-term memory neural network to perform nonlinear transformation on the feature data, adjust the weight distribution of the feature data through the tanh activation function of the input gate, and use the dropout mechanism to randomly inactivate some neurons to prevent overfitting;

[0116] Step S502: construct a bidirectional long short-term memory neural network structure including two hidden layers, set the number of neurons in each layer to 128, initialize the hidden layer parameters using the xavier initialization method, use the Adam optimizer to iteratively update the network parameters, build a loss function based on the root mean square error, set the learning rate to 0.001, and start the early stopping mechanism when the loss value of the validation set has not decreased for 5 consecutive epochs, and save the trained model parameters for predicting the consumption range in the next 30 days.

[0117] Optionally, in this embodiment, these two steps construct a medical device consumption prediction system based on deep learning. In step S501, the time series feature data is first divided into a training set and a validation set using a stratified random sampling method to maintain the consistency of the time distribution in the two data sets. The time continuity is taken into account when dividing the data to avoid the time series feature breaks that may be caused by random division.

[0118] Feature normalization uses the MinMax method to calculate the maximum value max(f) and minimum value min(f) of each feature dimension f, and then convert the feature value x to (x-min(f)) / (max(f)-min(f)). This normalization method maintains the shape of the feature distribution and maps all features to the same value range, which is conducive to the training convergence of the neural network.

[0119] The forget gate in the long short-term memory network uses the sigmoid activation function to convert the input into a value between 0 and 1, controlling the degree of retention of historical information. The nonlinear characteristics of the sigmoid function enable the network to learn complex temporal dependencies. The input gate uses the tanh activation function to map the data to the range of -1 to 1. This symmetric activation function helps alleviate the gradient vanishing problem.

[0120] The Dropout mechanism randomly disconnects the connections between neurons during training, with the disconnection probability set to 0.2. This regularization technique introduces randomness, forcing the network to learn more robust feature representations, effectively preventing overfitting. Dropout changes dynamically in each training batch, but is turned off during prediction to ensure stability.

[0121] In step S502, the design of the bidirectional LSTM network allows the model to consider both past and future contextual information. The two hidden layers process the input sequence from the forward and reverse directions respectively, and then merge the outputs from the two directions. The setting of 128 neurons in each layer is determined based on the input feature dimension and the complexity of the prediction task.

[0122] The Xavier initialization method sets the initial values ​​of the weights according to the input and output dimensions of the layer, ensuring that the variance of the output of each layer is approximately equal. Specifically, the weights are sampled from a uniform distribution with mean 0 and variance 2 / (nin+nout), where nin and nout are the input and output dimensions of the layer, respectively.

[0123] The Adam optimizer combines the advantages of the momentum method and the adaptive learning rate method to maintain an independent learning rate for each parameter. The hyperparameters of the optimizer are set to: β1 = 0.9 (exponential decay rate of the first-order moment estimate), β2 = 0.999 (exponential decay rate of the second-order moment estimate). The root mean square error loss function can penalize the size of the prediction error, which is particularly suitable for regression prediction tasks.

[0124] The learning rate is set to 0.001, which is a relatively conservative choice to ensure training stability. The early stopping mechanism monitors the change of loss value on the validation set. When the loss value does not improve for 5 consecutive epochs, the current best model parameters are saved and training is stopped. This mechanism effectively prevents overfitting and saves computing resources.

[0125] This technical solution solves the time series modeling problem in the forecast of medical device consumption, and captures complex time dependencies through deep learning methods. The bidirectional LSTM structure can make full use of contextual information and improve forecast accuracy.

[0126] The implementation results show that the solution has achieved good results in both prediction accuracy and model generalization ability. The system can accurately predict the consumption range in the next 30 days and provide reliable decision support for medical device inventory management. The model training is stable, the calculation efficiency is high, and it has good practical value.

[0127] In one embodiment of the medical device digital supply chain batch intelligent management method of the present application, see Figure 6 , and can also include the following:

[0128] Step S601: construct a 50-layer residual deep convolutional neural network structure, set a 3×3 convolution kernel to extract local features of the medical device image, enhance the feature expression ability through a batch normalization layer and a ReLU activation function, add a short-circuit connection in the residual block to alleviate the gradient vanishing problem, use a global average pooling layer to reduce the feature dimension, output the classification probability distribution of the integrity of the medical device in the fully connected layer, and output the probability distribution as the image classification result;

[0129] Step S602: Based on the DS evidence theory, the basic probability distribution function of the two evidence sources is constructed, and the support function and the likelihood function are calculated to represent the credibility of the image classification result and the predicted output value respectively. The Dempster combination rule is used to perform orthogonal sum operations on the two evidence sources, and the Pearson correlation coefficient and root mean square error value of the fused data and the original data are calculated to evaluate the fusion effect.

[0130] Optionally, in this embodiment, these two steps construct a medical device integrity assessment system based on deep learning and its result fusion mechanism. In step S601, a 50-layer residual deep convolutional neural network is used for image feature extraction and classification. The network structure draws on the design concept of ResNet, and each residual block contains two 3×3 convolutional layers, a batch normalization layer, and a ReLU activation function.

[0131] The 3×3 convolution kernel can effectively capture local features such as texture and edges of medical device images while maintaining a moderate receptive field. The convolution operation uses a sliding method with a step size of 1, and the edges are zero-filled to maintain the size of the feature map. The batch normalization layer standardizes the output of each feature channel to accelerate the convergence of network training and has a regularization effect. The ReLU activation function introduces nonlinear transformation to enhance the feature expression ability of the network.

[0132] The short-circuit connection in the residual block implements identity mapping, allowing the network to directly learn the residual part. This design significantly alleviates the gradient vanishing problem of deep networks. The global average pooling layer compresses the spatial dimension of the feature map, retains the information of the channel dimension, and reduces the number of parameters. The fully connected layer maps the features to the classification space, and the number of output nodes is equal to the number of categories of integrity. The output is converted into a probability distribution through the softmax function, indicating the probability that the image belongs to each category.

[0133] In step S602, a data fusion framework is constructed based on the DS evidence theory. Basic probability distribution functions are constructed for image classification results and predicted output values. The basic probability of image classification is determined based on the probability value of the softmax output, and the basic probability of the predicted value is calculated based on the confidence of the prediction interval.

[0134] The support function represents the strength of evidence that directly supports a hypothesis, and the accuracy and reliability of the data are taken into account when calculating it. The support of image classification mainly comes from the classification confidence of the model, and the support of the predicted output is based on the historical prediction accuracy. The likelihood function represents the strength of evidence that indirectly supports a hypothesis, which is calculated through conditional probability.

[0135] Dempster's combination rule is used to merge information from two sources of evidence. The combination process first calculates the conflict factor K, which represents the degree of contradiction between the sources of evidence. Then, the basic probability distribution after fusion is calculated through orthogonal sum operations. This process takes into account the reliability weight of the evidence source and dynamically adjusts the influence of information from different sources.

[0136] The fusion effect is evaluated using two indicators: the Pearson correlation coefficient measures the correlation between the fusion result and the original data, and the root mean square error reflects the accuracy of the fusion result. The closer the correlation coefficient is to 1, the better the fusion result maintains the change trend of the original data. The smaller the root mean square error is, the closer the fusion result is to the true value.

[0137] This technical solution solves the accuracy and reliability issues of medical device integrity assessment. The deep learning model provides powerful image feature extraction and classification capabilities, and the evidence theory framework realizes the effective fusion of multi-source information.

[0138] The implementation results show that the solution can accurately identify the intact state of medical devices, and the fusion results have a high degree of credibility. The system runs stably, has high processing efficiency, and can meet the needs of actual applications. Multi-source information fusion significantly improves the reliability of evaluation results and provides strong support for medical device management.

[0139] In one embodiment of the medical device digital supply chain batch intelligent management method of the present application, see Figure 7 , and can also include the following:

[0140] Step S701: Use the time series correlation coefficient and the root mean square error value as input variables of the fitness function, use real number coding to initialize the population individuals, set the crossover probability to 0.8 and the mutation probability to 0.1, use the tournament selection strategy to select high-quality individuals, generate a new generation of populations through arithmetic crossover operator and Gaussian mutation operator, iteratively optimize the weight allocation scheme until the maximum number of iterations is reached, and decode the obtained optimal individuals into a dynamic weight allocation matrix for updating the weight parameters of the long short-term memory neural network model;

[0141] Step S702: A replenishment decision model is constructed based on a Bayesian network. The current inventory, predicted consumption, safety stock threshold and historical replenishment records of medical devices are used as input nodes of conditional probability. The maximum likelihood estimation method is used to learn network parameters. The posterior probability distribution of replenishment timing is calculated through a variable elimination algorithm. The posterior probability distribution is normalized to obtain the trigger probability. When the trigger probability is greater than 0.8, the replenishment demand is written into the tamper-proof blockchain database.

[0142] Optionally, in this embodiment, these two steps construct a medical device intelligent replenishment decision system. In step S701, a weight optimization scheme based on a genetic algorithm is designed. The fitness function comprehensively considers the time series correlation coefficient and the root mean square error, and calculates the individual fitness value by weighted summation. The weight coefficient is determined by cross-validation.

[0143] Real number encoding uses floating point numbers to represent individual chromosomes, and each gene position corresponds to a weight parameter in the neural network. The initial population is generated by random sampling, and the sampling range is determined according to the statistical distribution of the weight parameter. The population size is set to 100 to maintain population diversity while controlling computational overhead.

[0144] The tournament selection strategy randomly selects k individuals (k=3) each time and selects the individuals with the highest fitness to enter the next generation. This selection method maintains a certain selection pressure while preventing dominant individuals from occupying the population too quickly. The arithmetic crossover operator linearly combines the corresponding gene positions of the two parent individuals, and the combination coefficient is randomly generated from the interval [0,1]. The Gaussian mutation operator adds random perturbations that follow a normal distribution to the selected gene positions, and the standard deviation decreases with the number of iterations, realizing the transition from global exploration to local fine search.

[0145] The maximum number of iterations is set to 200, and the convergence condition is set: the iteration is terminated early when the relative change of the optimal fitness for 20 consecutive generations is less than 0.001. The optimal individual is decoded into a weight matrix through linear transformation and used to update the parameters of the LSTM model.

[0146] In step S702, the Bayesian network model adopts a directed acyclic graph structure, and the edges between nodes represent the conditional dependencies between variables. The network structure is determined by combining expert knowledge and data-driven methods to ensure that the model reflects the key factors and logical relationships of medical device replenishment decisions.

[0147] The parameter learning of the conditional probability table uses the maximum likelihood estimation method, and the expectation maximization algorithm is used to handle the missing values ​​that may exist in the data. For continuous variables, the Gaussian mixture model is used for probability density estimation. The variable elimination algorithm calculates the posterior probability through dynamic programming, and the algorithm complexity is related to the width of the network structure.

[0148] The trigger probability is normalized using the softmax function to ensure that the probability value is in the interval [0,1] and the sum is 1. The trigger threshold is set to 0.8 based on a cost-benefit analysis to strike a balance between preventing inventory shortages and avoiding excessive inventory.

[0149] The tamper-proof blockchain database adopts a consortium chain architecture, and the consensus mechanism uses a practical Byzantine fault-tolerant algorithm. Replenishment demand information is packaged into transaction blocks, which contain key information such as timestamps, prediction basis, and decision-making process. Blockchain technology ensures the transparency and immutability of replenishment decisions.

[0150] This technical solution solves the problem of intelligent and reliable decision-making for medical device replenishment. Genetic algorithm optimization improves the accuracy of the prediction model, and Bayesian network provides explainable decision support.

[0151] The implementation results show that the solution can accurately grasp the timing of replenishment and effectively reduce inventory costs. The system has good adaptive capabilities and can dynamically adjust decision-making strategies according to actual conditions. The introduction of blockchain technology ensures the traceability and data security of the decision-making process, providing an innovative solution for medical device supply chain management.

[0152] In order to effectively improve the overall operational efficiency of the medical device supply chain, the present application provides an embodiment of a medical device digital supply chain batch intelligent management device for implementing all or part of the content of the medical device digital supply chain batch intelligent management method, see Figure 8 The medical device digital supply chain batch intelligent management device specifically includes the following contents:

[0153] An information encryption module 10 is used to construct a unique box set ID based on the classification code of the medical device, encrypt the box set ID using an elliptic curve digital signature algorithm, perform a hash operation on the digital signature and the medical device information using a symmetric key to generate an information summary, store the information summary in a tamper-proof blockchain database, and establish a mapping relationship between the box set ID and the tamper-proof blockchain database;

[0154] The consumption prediction module 20 is used to write the box set ID and the medical device information into a multi-level index structure, verify the data consistency according to the historical consumption data stored in the multi-level index structure and the information summary in the tamper-proof blockchain database, construct a time series sample in units of days for the verified historical consumption data, perform sliding window segmentation on the time series sample and extract time series features, input the time series feature data into the input layer of the long short-term memory neural network model, perform maximum and minimum value normalization processing on the time series feature data through a forget gate and an input gate, use an adaptive moment estimation optimizer to train the hidden layer parameters of the long short-term memory neural network model, and determine the future average daily consumption and fluctuation range of medical devices based on the trained long short-term memory neural network model;

[0155] The replenishment monitoring module 30 is used to bind the medical device information with the box set ID in a batch matching manner, perform feature extraction and image classification on the returned medical devices based on the residual deep convolutional neural network, perform evidence theory data fusion on the image classification results and the output value of the long short-term memory neural network model to obtain the time series correlation coefficient and the root mean square error value of the fused data, construct a dynamic weight allocation matrix based on a genetic algorithm according to the time series correlation coefficient and the root mean square error value, and update the weight parameters of the long short-term memory neural network model online according to the dynamic weight allocation matrix, record the updated weight parameters and their corresponding distribution strategies and replenishment opportunities in the tamper-proof blockchain database, calculate the trigger probability of the replenishment opportunity based on the distribution strategies recorded in the tamper-proof blockchain database combined with the safety inventory thresholds of various medical devices, and automatically generate a replenishment list when the trigger probability exceeds the preset threshold.

[0156] From the above description, it can be seen that the medical device digital supply chain batch intelligent management device provided by the embodiment of the present application can ensure data security by combining blockchain technology, achieve accurate demand forecasting through deep learning, and have intelligent inventory optimization capabilities. At the same time, the system can also quickly respond to market changes, realize the automation and intelligence of replenishment decisions, thereby effectively improving the overall operational efficiency of the medical device supply chain.

[0157] From the hardware level, in order to effectively improve the overall operational efficiency of the medical device supply chain, the present application provides an embodiment of an electronic device for implementing all or part of the content of the medical device digital supply chain batch intelligent management method, and the electronic device specifically includes the following content:

[0158] Processor, memory, communication interface and bus; wherein the processor, memory and communication interface communicate with each other through the bus; the communication interface is used to realize information transmission between the medical device digital supply chain batch intelligent management device and the core business system, user terminal and related databases and other related equipment; the logic controller can be a desktop computer, a tablet computer and a mobile terminal, etc., but the present embodiment is not limited thereto. In the present embodiment, the logic controller can be implemented with reference to the embodiment of the medical device digital supply chain batch intelligent management method and the embodiment of the medical device digital supply chain batch intelligent management device in the embodiment, and the contents thereof are incorporated herein, and the repeated parts are not repeated.

[0159] It is understandable that the user terminal may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Among them, the smart wearable device may include smart glasses, a smart watch, a smart bracelet, etc.

[0160] In practical applications, part of the medical device digital supply chain batch intelligent management method can be executed on the electronic device side as described above, or all operations can be completed in the client device. The specific selection can be based on the processing capability of the client device and the limitations of the user's usage scenario. This application does not limit this. If all operations are completed in the client device, the client device may also include a processor.

[0161] The client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission with the server. The server may include a server on the task scheduling center side, and other implementation scenarios may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, or a server cluster consisting of multiple servers, or a server structure of a distributed device.

[0162] Fig. 9 FIG. 9 is a schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Fig. 9 As shown, the electronic device 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. It is worth noting that Fig. 9 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0163] In one embodiment, the function of the medical device digital supply chain batch intelligent management method can be integrated into the central processor 9100. The central processor 9100 can be configured to perform the following control:

[0164] Step S101: construct a unique box set ID based on the classification code of the medical device, encrypt the box set ID using the elliptic curve digital signature algorithm, perform a hash operation on the digital signature and the medical device information using a symmetric key to generate an information summary, store the information summary in a tamper-proof blockchain database, and establish a mapping relationship between the box set ID and the tamper-proof blockchain database;

[0165] Step S102: writing the box set ID and the medical device information into a multi-level index structure, verifying data consistency based on the historical consumption data stored in the multi-level index structure and the information summary in the tamper-proof blockchain database, constructing a time series sample in units of days for the verified historical consumption data, performing sliding window segmentation on the time series sample and extracting time series features, inputting the time series feature data into the input layer of the long short-term memory neural network model, performing maximum and minimum value normalization processing on the time series feature data through a forget gate and an input gate, training the hidden layer parameters of the long short-term memory neural network model using an adaptive moment estimation optimizer, and determining the future average daily consumption and fluctuation range of medical devices based on the trained long short-term memory neural network model;

[0166] Step S103: The medical device information is bound to the box set ID by batch matching, feature extraction and image classification are performed on the returned medical devices based on the residual deep convolutional neural network, and the image classification result is fused with the output value of the long short-term memory neural network model by evidence theory data to obtain the time series correlation coefficient and the root mean square error value of the fused data, and a dynamic weight allocation matrix based on a genetic algorithm is constructed according to the time series correlation coefficient and the root mean square error value, and the weight parameters of the long short-term memory neural network model are updated online according to the dynamic weight allocation matrix, and the updated weight parameters and their corresponding distribution strategies and replenishment opportunities are recorded in the tamper-proof blockchain database, and the trigger probability of the replenishment opportunity is calculated based on the distribution strategy recorded in the tamper-proof blockchain database and the safety inventory threshold of each type of medical device, and when the trigger probability exceeds the preset threshold, a replenishment list is automatically generated.

[0167] From the above description, it can be seen that the electronic device provided in the embodiment of the present application ensures data security by combining blockchain technology, realizes accurate demand forecasting through deep learning, and has intelligent inventory optimization capabilities. At the same time, the system can also quickly respond to market changes, realize the automation and intelligence of replenishment decisions, thereby effectively improving the overall operational efficiency of the medical device supply chain.

[0168] In another embodiment, the medical device digital supply chain batch intelligent management device can be configured separately from the central processor 9100. For example, the medical device digital supply chain batch intelligent management device can be configured as a chip connected to the central processor 9100, and the function of the medical device digital supply chain batch intelligent management method can be realized through the control of the central processor.

[0169] like Fig. 9 As shown, the electronic device 9600 may also include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Fig. 9 In addition, the electronic device 9600 may also include Fig. 9 For components not shown, reference may be made to the prior art.

[0170] like Fig. 9 As shown, the central processing unit 9100 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor device and / or logic device. The central processing unit 9100 receives input and controls the operation of various components of the electronic device 9600.

[0171] The memory 9140 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices. The above-mentioned information related to the failure may be stored, and a program for executing the relevant information may also be stored. The CPU 9100 may execute the program stored in the memory 9140 to implement information storage or processing, etc.

[0172] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display may be, for example, an LCD display, but is not limited thereto.

[0173] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that saves information even when the power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROMs, etc. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142, which is used to store application programs and function programs or processes for executing the operation of the electronic device 9600 through the central processor 9100.

[0174] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0175] The communication module 9110 is a transmitter / receiver that sends and receives signals via the antenna 9111. The communication module 9110 (transmitter / receiver) is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0176] Based on different communication technologies, multiple communication modules 9110 may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless LAN module, etc. The communication module 9110 (transmitter / receiver) is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby realizing a common telecommunication function. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 9130 is also coupled to the central processor 9100, so that recording can be performed on the local machine through the microphone 9132, and the sound stored on the local machine can be played through the speaker 9131.

[0177] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps of the method for batch intelligent management of a digital supply chain of medical devices in the above-mentioned embodiments, wherein the execution subject is a server or a client. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, all the steps of the method for batch intelligent management of a digital supply chain of medical devices in the above-mentioned embodiments are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0178] Step S101: construct a unique box set ID based on the classification code of the medical device, encrypt the box set ID using the elliptic curve digital signature algorithm, perform a hash operation on the digital signature and the medical device information using a symmetric key to generate an information summary, store the information summary in a tamper-proof blockchain database, and establish a mapping relationship between the box set ID and the tamper-proof blockchain database;

[0179] Step S102: writing the box set ID and the medical device information into a multi-level index structure, verifying data consistency based on the historical consumption data stored in the multi-level index structure and the information summary in the tamper-proof blockchain database, constructing a time series sample in units of days for the verified historical consumption data, performing sliding window segmentation on the time series sample and extracting time series features, inputting the time series feature data into the input layer of the long short-term memory neural network model, performing maximum and minimum value normalization processing on the time series feature data through a forget gate and an input gate, training the hidden layer parameters of the long short-term memory neural network model using an adaptive moment estimation optimizer, and determining the future average daily consumption and fluctuation range of medical devices based on the trained long short-term memory neural network model;

[0180] Step S103: The medical device information is bound to the box set ID by batch matching, feature extraction and image classification are performed on the returned medical devices based on the residual deep convolutional neural network, and the image classification result is fused with the output value of the long short-term memory neural network model by evidence theory data to obtain the time series correlation coefficient and the root mean square error value of the fused data, and a dynamic weight allocation matrix based on a genetic algorithm is constructed according to the time series correlation coefficient and the root mean square error value, and the weight parameters of the long short-term memory neural network model are updated online according to the dynamic weight allocation matrix, and the updated weight parameters and their corresponding distribution strategies and replenishment opportunities are recorded in the tamper-proof blockchain database, and the trigger probability of the replenishment opportunity is calculated based on the distribution strategy recorded in the tamper-proof blockchain database and the safety inventory threshold of each type of medical device, and when the trigger probability exceeds the preset threshold, a replenishment list is automatically generated.

[0181] From the above description, it can be seen that the computer-readable storage medium provided in the embodiment of the present application ensures data security by combining blockchain technology, realizes accurate demand forecasting through deep learning, and has intelligent inventory optimization capabilities. At the same time, the system can also quickly respond to market changes, realize the automation and intelligence of replenishment decisions, thereby effectively improving the overall operational efficiency of the medical device supply chain.

[0182] The embodiments of the present application also provide a computer program product capable of implementing all the steps of the medical device digital supply chain batch intelligent management method in the above embodiments, where the execution subject is a server or a client. When the computer program / instruction is executed by a processor, the steps of the medical device digital supply chain batch intelligent management method are implemented. For example, the computer program / instruction implements the following steps:

[0183] Step S101: construct a unique box set ID based on the classification code of the medical device, encrypt the box set ID using the elliptic curve digital signature algorithm, perform a hash operation on the digital signature and the medical device information using a symmetric key to generate an information summary, store the information summary in a tamper-proof blockchain database, and establish a mapping relationship between the box set ID and the tamper-proof blockchain database;

[0184] Step S102: writing the box set ID and the medical device information into a multi-level index structure, verifying data consistency based on the historical consumption data stored in the multi-level index structure and the information summary in the tamper-proof blockchain database, constructing a time series sample in units of days for the verified historical consumption data, performing sliding window segmentation on the time series sample and extracting time series features, inputting the time series feature data into the input layer of the long short-term memory neural network model, performing maximum and minimum value normalization processing on the time series feature data through a forget gate and an input gate, training the hidden layer parameters of the long short-term memory neural network model using an adaptive moment estimation optimizer, and determining the future average daily consumption and fluctuation range of medical devices based on the trained long short-term memory neural network model;

[0185] Step S103: The medical device information is bound to the box set ID by batch matching, feature extraction and image classification are performed on the returned medical devices based on the residual deep convolutional neural network, and the image classification result is fused with the output value of the long short-term memory neural network model by evidence theory data to obtain the time series correlation coefficient and the root mean square error value of the fused data, and a dynamic weight allocation matrix based on a genetic algorithm is constructed according to the time series correlation coefficient and the root mean square error value, and the weight parameters of the long short-term memory neural network model are updated online according to the dynamic weight allocation matrix, and the updated weight parameters and their corresponding distribution strategies and replenishment opportunities are recorded in the tamper-proof blockchain database, and the trigger probability of the replenishment opportunity is calculated based on the distribution strategy recorded in the tamper-proof blockchain database and the safety inventory threshold of each type of medical device, and when the trigger probability exceeds the preset threshold, a replenishment list is automatically generated.

[0186] From the above description, it can be seen that the computer program product provided in the embodiment of the present application ensures data security by combining blockchain technology, realizes accurate demand forecasting through deep learning, and has intelligent inventory optimization capabilities. At the same time, the system can also quickly respond to market changes, realize the automation and intelligence of replenishment decisions, thereby effectively improving the overall operational efficiency of the medical device supply chain.

[0187] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0188] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (apparatus), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0189] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0190] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0191] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for intelligent batch management of a medical device digital supply chain, characterized in that: The method comprises: Construct a unique box set ID based on the classification code of the medical device, encrypt the box set ID using the elliptic curve digital signature algorithm, perform a hash operation on the digital signature and the medical device information using a symmetric key to generate an information summary, store the information summary in a tamper-proof blockchain database, and establish a mapping relationship between the box set ID and the tamper-proof blockchain database; Write the box set ID and the medical device information into a multi-level index structure, verify data consistency based on the historical consumption data stored in the multi-level index structure and the information summary in the tamper-proof blockchain database, construct a time series sample in units of days for the verified historical consumption data, perform sliding window segmentation on the time series sample and extract time series features, input the time series feature data into the input layer of the long short-term memory neural network model, perform maximum and minimum value normalization on the time series feature data through a forget gate and an input gate, use an adaptive moment estimation optimizer to train the hidden layer parameters of the long short-term memory neural network model, and determine the future average daily consumption and fluctuation range of medical devices based on the trained long short-term memory neural network model; The medical device information is bound to the box set ID in a batch matching manner, feature extraction and image classification are performed on the returned medical devices based on the residual deep convolutional neural network, and the image classification result is fused with the output value of the long short-term memory neural network model by evidence theory data to obtain the time series correlation coefficient and the root mean square error value of the fused data, and a dynamic weight allocation matrix based on a genetic algorithm is constructed according to the time series correlation coefficient and the root mean square error value, and the weight parameters of the long short-term memory neural network model are updated online according to the dynamic weight allocation matrix, and the updated weight parameters and their corresponding distribution strategies and replenishment opportunities are recorded in the tamper-proof blockchain database, and the trigger probability of the replenishment opportunity is calculated based on the distribution strategy recorded in the tamper-proof blockchain database combined with the safety inventory threshold of each type of medical device, and when the trigger probability exceeds the preset threshold, a replenishment list is automatically generated.

2. The medical device digital supply chain batch intelligent management method according to claim 1 is characterized in that: The unique box set ID is constructed based on the classification code of the medical device, the box set ID is encrypted using the elliptic curve digital signature algorithm, the digital signature and the medical device information are hashed using a symmetric key to generate an information summary, the information summary is stored in a tamper-proof blockchain database, and a mapping relationship between the box set ID and the tamper-proof blockchain database is established, including: Taking the box set ID as input, obtaining a binary data block, mapping the binary data block to a point on an elliptic curve, generating a public key pair based on a base point P on the elliptic curve and a random number k, calculating a signature value using the public key pair, and outputting an encrypted digital signature according to the binary data block and the signature value; The production date, expiration date, product batch number, and sterilization batch number of the medical device are read as medical device information, the medical device information and the digital signature are merged into a string to be processed, the hash value of the string to be processed is iteratively calculated through the SHA-256 hash function, the hash value and timestamp are organized into a block information summary using a Merkle tree structure, and the block information summary is encrypted based on an asymmetric encryption algorithm and written into a tamper-proof blockchain database.

3. The medical device digital supply chain batch intelligent management method according to claim 1 is characterized in that: The step of writing the box set ID and the medical device information into a multi-level index structure and verifying data consistency based on the historical consumption data stored in the multi-level index structure and the information summary in the tamper-proof blockchain database includes: Construct a three-layer index structure, where the top-layer index records the storage location pointer of the box set ID, the middle-layer index stores the category and specification information of the medical device, and the bottom-layer index records the consumption record of the medical device according to the timestamp. The association relationship between the indexes of each layer is organized through the B+ tree structure, and the data validity flag is set in the bottom-layer index. The bitmap index technology is used to compress and store the medical device information; Read the historical consumption data with timestamp from the underlying index, obtain the block information summary of the corresponding timestamp from the tamper-proof blockchain database, decrypt the block information summary using the public key of the elliptic curve digital signature algorithm, perform hash calculation on the decrypted information summary and the historical consumption data, and compare whether the calculation result is consistent with the hash value stored in the block information summary.

4. The medical device digital supply chain batch intelligent management method according to claim 1 is characterized in that: The process of constructing a time series sample in units of days for the verified historical consumption data, performing sliding window segmentation on the time series sample and extracting time series features includes: The historical consumption data is aggregated by day according to the timestamp to calculate the average daily consumption, the standard deviation of the average daily consumption is normalized to eliminate the dimension effect, the missing time point data is supplemented by a linear interpolation method, and the high-frequency noise in the average daily consumption is removed by a low-pass filter to construct a multidimensional time series sample containing consumption, time periodicity and seasonal characteristics; The length of the sliding window is set to 14 days and the step length is 1 day. The statistical characteristics of the data in each window, including the mean, variance, kurtosis, and skewness, are calculated. The frequency domain characteristics of the window data are extracted by wavelet transform. The periodic characteristics of the window data are obtained through autocorrelation analysis. The statistical characteristics, frequency domain characteristics, and periodic characteristics are combined to form a feature vector to construct a time series feature data set.

5. The medical device digital supply chain batch intelligent management method according to claim 1 is characterized in that: The method of inputting the time series feature data into the input layer of the long short-term memory neural network model, performing maximum and minimum value normalization processing on the time series feature data through a forget gate and an input gate, training the hidden layer parameters of the long short-term memory neural network model using an adaptive moment estimation optimizer, and determining the future average daily consumption and fluctuation range of medical devices based on the trained long short-term memory neural network model includes: The time series feature data is divided into 80% training set and 20% validation set, and the maximum and minimum value intervals are calculated for each feature dimension. The MinMax normalization method is used to map the feature value to the [0,1] interval. The sigmoid activation function is set in the forget gate of the long short-term memory neural network to perform nonlinear transformation on the feature data. The weight distribution of the feature data is adjusted through the tanh activation function of the input gate, and the dropout mechanism is used to randomly inactivate some neurons to prevent overfitting. The bidirectional long short-term memory neural network structure contains two hidden layers. The number of neurons in each layer is set to 128. The xavier initialization method is used to initialize the hidden layer parameters. The Adam optimizer is used to iteratively update the network parameters. The loss function is built based on the root mean square error. The learning rate is set to 0.

001. When the loss value of the validation set does not decrease for 5 consecutive epochs, the early stopping mechanism is activated. The trained model parameters are saved for predicting the consumption range in the next 30 days.

6. The medical device digital supply chain batch intelligent management method according to claim 1 is characterized in that: The batch matching method is used to bind the medical device information with the box set ID, feature extraction and image classification are performed on the returned medical devices based on the residual deep convolutional neural network, and the image classification results are fused with the output value of the long short-term memory neural network model by evidence theory data to obtain the time series correlation coefficient and root mean square error value of the fused data, including: Build a 50-layer residual deep convolutional neural network structure, set a 3×3 convolution kernel to extract local features of medical device images, enhance feature expression capabilities through batch normalization layers and ReLU activation functions, add short-circuit connections in residual blocks to alleviate the gradient vanishing problem, use a global average pooling layer to reduce feature dimensions, output the probability distribution of the integrity of medical devices in the fully connected layer, and output the probability distribution as the image classification result; Based on the DS evidence theory, the basic probability distribution function of the two evidence sources is constructed. The support function and likelihood function are calculated to represent the credibility of the image classification result and the predicted output value respectively. The Dempster combination rule is used to perform orthogonal sum operations on the two evidence sources. The Pearson correlation coefficient and root mean square error value of the fused data and the original data are calculated to evaluate the fusion effect.

7. The medical device digital supply chain batch intelligent management method according to claim 1 is characterized in that: The method constructs a dynamic weight allocation matrix based on a genetic algorithm according to the time series correlation coefficient and the root mean square error value, and performs online updating of the weight parameters of the long short-term memory neural network model according to the dynamic weight allocation matrix, records the updated weight parameters and their corresponding distribution strategies and replenishment opportunities in the tamper-proof blockchain database, calculates the trigger probability of the replenishment opportunity based on the distribution strategies recorded in the tamper-proof blockchain database and the safety inventory thresholds of various medical devices, and automatically generates a replenishment list when the trigger probability exceeds a preset threshold, including: The time series correlation coefficient and the root mean square error value are used as input variables of the fitness function. The population individuals are initialized using real number coding, the crossover probability is set to 0.8 and the mutation probability is set to 0.

1. The tournament selection strategy is used to select high-quality individuals. A new generation of population is generated through the arithmetic crossover operator and the Gaussian mutation operator. The weight allocation scheme is iteratively optimized until the maximum number of iterations is reached. The optimal individual is decoded into a dynamic weight allocation matrix for updating the weight parameters of the long short-term memory neural network model. A replenishment decision model is constructed based on a Bayesian network. The current inventory, predicted consumption, safety stock threshold and historical replenishment records of medical devices are used as input nodes of conditional probability. The maximum likelihood estimation method is used to learn network parameters. The posterior probability distribution of replenishment timing is calculated through the variable elimination algorithm. The posterior probability distribution is normalized to obtain the trigger probability. When the trigger probability is greater than 0.8, the replenishment demand is written into the tamper-proof blockchain database.

8. A medical device digital supply chain batch intelligent management device, characterized in that: The device comprises: An information encryption module, used to construct a unique box set ID based on the classification code of the medical device, encrypt the box set ID using an elliptic curve digital signature algorithm, perform a hash operation on the digital signature and the medical device information using a symmetric key to generate an information summary, store the information summary in a tamper-proof blockchain database, and establish a mapping relationship between the box set ID and the tamper-proof blockchain database; A consumption prediction module is used to write the box set ID and the medical device information into a multi-level index structure, verify data consistency based on the historical consumption data stored in the multi-level index structure and the information summary in the tamper-proof blockchain database, construct a time series sample in units of days for the verified historical consumption data, perform sliding window segmentation on the time series sample and extract time series features, input the time series feature data into the input layer of the long short-term memory neural network model, perform maximum and minimum value normalization processing on the time series feature data through a forget gate and an input gate, use an adaptive moment estimation optimizer to train the hidden layer parameters of the long short-term memory neural network model, and determine the future average daily consumption and fluctuation range of medical devices based on the trained long short-term memory neural network model; A replenishment monitoring module is used to bind the medical device information with the box set ID in a batch matching manner, perform feature extraction and image classification on the returned medical devices based on a residual deep convolutional neural network, perform evidence theory data fusion on the image classification result and the output value of the long short-term memory neural network model to obtain a time series correlation coefficient and a root mean square error value of the fused data, construct a dynamic weight allocation matrix based on a genetic algorithm according to the time series correlation coefficient and the root mean square error value, and perform online update of the weight parameters of the long short-term memory neural network model according to the dynamic weight allocation matrix, record the updated weight parameters and their corresponding distribution strategies and replenishment opportunities in the tamper-proof blockchain database, calculate the trigger probability of the replenishment opportunity based on the distribution strategies recorded in the tamper-proof blockchain database combined with the safety inventory thresholds of various medical devices, and automatically generate a replenishment list when the trigger probability exceeds a preset threshold.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the medical device digital supply chain batch intelligent management method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the medical device digital supply chain batch intelligent management method described in any one of claims 1 to 7 are implemented.

Images