Data processing method and device for consignment model of digital supply chain of medical devices

Abstract

An embodiment of the present application provides a data processing method and device for a consignment model of a digital supply chain for medical devices, the method comprising: creating a consignment order for the medical devices, establishing a multi-level traceability structure including primary product source information, secondary inventory status information, and tertiary flow information; establishing a mapping relationship table between cargo flow data and account period data, retrieving updated tertiary flow information based on a traceability identification code, inputting time series consumption data into a long-short-term memory network, dynamically adjusting a time decay factor using an adaptive mechanism, determining a fluctuation benchmark value by calculating the standard deviation of recent consumption data, weighting historical data based on the updated time decay factor, predicting an optimal account period and generating a settlement statement, and synchronously updating cargo flow data and account period data through a mapping relationship table; the present application can achieve full product traceability, possesses intelligent account period management capabilities, and can accurately predict consumption based on historical data.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and specifically to a data processing method and device for a medical device digital supply chain consignment model. Background Art

[0002] Medical device consignment management is a crucial component of the medical device supply chain, but current data processing solutions still have numerous shortcomings. Traditional consignment management systems often rely on simple inventory records and periodic inventory checks, lacking effective tracking of the product's entire lifecycle. This results in inefficient inventory management and slow capital turnover.

[0003] Existing systems have significant shortcomings in data traceability and flow management. Most systems focus solely on single-dimensional data records, failing to effectively link product origin, inventory status, and flow information. This makes it difficult to quickly pinpoint the source of anomalies. Furthermore, existing account management methods are overly rigid, typically employing fixed settlement cycles that fail to dynamically adjust based on actual consumption, resulting in inefficient capital utilization.

[0004] Another prominent issue is insufficient data forecasting capabilities. Current systems mostly rely on simple statistical methods to predict consumption trends, failing to fully leverage the temporal characteristics inherent in historical data. This results in low forecast accuracy. This is particularly true when dealing with seasonal fluctuations or sudden changes in demand, resulting in significant deviations from actual results. Summary of the Invention

[0005] In response to the problems in the existing technology, the present application provides a data processing method and device for the consignment model of the digital supply chain of medical devices, which can achieve full product traceability, have intelligent account management capabilities, and can accurately predict consumption based on historical data.

[0006] In order to solve at least one of the above problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides a data processing method for a medical device digital supply chain consignment model, comprising:

[0008] Create a consignment order for medical devices, establish a multi-level traceability structure including primary product source information, secondary inventory status information, and tertiary flow direction information, generate a unique traceability identification code, split the traceability identification code into a product source identification segment, an inventory status identification segment, and a flow direction identification segment, establish a first association index between the product source identification segment and the inventory status identification segment, establish a second association index between the inventory status identification segment and the flow direction identification segment, and set a data integrity check;

[0009] Retrieving the secondary inventory status information corresponding to the inventory status identification segment according to the first association index, registering the consumption of the consignment inventory of the medical device, generating a consumption record including the consumption time and the consumption quantity, and updating the consumption record to the tertiary flow direction information through the second association index;

[0010] A mapping relationship table between cargo flow data and billing period data is established, updated three-level flow direction information is retrieved based on the traceability identification code, time series consumption data is input into the long short-term memory network, and the time decay factor is dynamically adjusted using an adaptive mechanism. The fluctuation benchmark value is determined by calculating the standard deviation of recent consumption data, and the decay rate parameter is updated in real time according to the fluctuation benchmark value. The historical data is weighted based on the updated time decay factor, the optimal billing period is predicted and a settlement statement is generated, and the cargo flow data and billing period data are synchronously updated through the mapping relationship table.

[0011] Furthermore, the creation of a consignment order for medical devices establishes a multi-level traceability structure including primary product source information, secondary inventory status information, and tertiary flow information, and generates a unique traceability identification code, including:

[0012] Generate a 36-bit unique identification code based on the basic information of the medical device, the unique identification code including the device number, production batch number and timestamp information, and create a consignment order based on the unique identification code;

[0013] Medical devices are classified according to supplier, production date and model to establish a product source information database, classified according to inventory location, storage conditions and quantity to establish an inventory status information database, classified according to use department, consumption record and flow destination to establish a flow information database, and the product source information database, inventory status information database and flow information database are combined to form a multi-level traceability structure.

[0014] Furthermore, the step of splitting the traceability identification code into a product source identification segment, an inventory status identification segment, and a flow direction identification segment, establishing a first association index between the product source identification segment and the inventory status identification segment, establishing a second association index between the inventory status identification segment and the flow direction identification segment, and setting a data integrity check includes:

[0015] The 36-digit traceability identification code is split into a fixed-length format of 12-12-12 digits. The first 12 digits are used as the product source identification segment to store supplier and production information, the middle 12 digits are used as the inventory status identification segment to store inventory location and status information, and the last 12 digits are used as the flow identification segment to store use department and consumption information.

[0016] A first association index value is generated by performing a bit-by-bit exclusive OR operation on the product source identification segment and the inventory status identification segment, a second association index value is generated by performing a bit-by-bit exclusive OR operation on the inventory status identification segment and the flow direction identification segment, and a cyclic redundancy check algorithm is used to perform data verification on the first association index value and the second association index value.

[0017] Furthermore, the step of retrieving the secondary inventory status information corresponding to the inventory status identification segment according to the first association index, registering the consumption of the consignment inventory of the medical device, generating a consumption record including the consumption time and the consumption quantity, and updating the consumption record to the tertiary flow direction information through the second association index includes:

[0018] Obtaining an inventory status identification segment through the first associated index value, comparing and matching the inventory status identification segment with a corresponding record in an inventory status information database, reading inventory status information of the medical device, and recording a usage time point and a specific usage quantity of the medical device in the inventory status information;

[0019] The usage records in the inventory status information of the medical device are associated with the second association index value, the corresponding position in the three-level flow information library is located based on the mapping relationship, and the usage time point and usage quantity are written into the consumption record field of the flow information library to complete data synchronization.

[0020] Furthermore, the time series consumption data is input into the long short-term memory network, and the time decay factor is dynamically adjusted using an adaptive mechanism, including:

[0021] Constructing a time series data structure based on a 64-bit floating-point format, writing medical device consumption data into the data structure according to the time dimension, normalizing the data through the input gate of a long short-term memory network, and setting a recurrent neuron structure with three hidden layers in the long short-term memory network;

[0022] The consumption data difference between adjacent time nodes is calculated to obtain a time interval matrix, which is input into an exponential function to generate an initial time decay factor. The cardinality parameter of the exponential function is adjusted in real time according to the prediction error of the long short-term memory network, so that the time decay factor decreases exponentially with the increase of the time interval.

[0023] Furthermore, the method of determining a fluctuation reference value by calculating the standard deviation of recent consumption data and updating the decay rate parameter in real time according to the fluctuation reference value includes:

[0024] Forming a statistical sample from the medical device consumption data for nearly 30 days, calculating the mean of the consumption and the sum of squares of deviations of each sampling point based on the statistical sample, dividing the sum of squares of deviations by the number of sampling points and taking the square root to obtain a fluctuation standard deviation, and comparing the fluctuation standard deviation with a preset threshold to obtain a fluctuation reference value;

[0025] The fluctuation reference value is substituted into the sigmoid function to calculate the initial value of the attenuation rate, the slope coefficient of the sigmoid function is adjusted based on the changing trend of the fluctuation reference value, and the updated attenuation rate parameter is output through the dynamically adjusted sigmoid function.

[0026] Furthermore, the historical data is weighted based on the updated time decay factor, the optimal billing period is predicted and a settlement statement is generated, and the cargo flow data and billing period data are synchronously updated through the mapping relationship table, including:

[0027] Performing a dot product operation on the historical consumption data of medical devices and the updated time decay factor to obtain a weighted sequence, inputting the weighted sequence into the output layer of the long short-term memory network, calculating the optimal billing period based on the output result, and generating settlement data including consumption summary, amount calculation, and billing period time limit based on the optimal billing period;

[0028] Construct a two-dimensional mapping table containing cargo flow records and billing period data, establish a key-value pair index for the two-dimensional mapping table according to the cargo number, locate the target record in the two-dimensional mapping table through the key-value pair index, write the settlement data into the billing period field of the target record and update the corresponding cargo flow status.

[0029] In a second aspect, the present application provides a data processing device for a medical device digital supply chain consignment model, comprising:

[0030] A multi-level traceability module is used to create consignment orders for medical devices, establish a multi-level traceability structure including primary product source information, secondary inventory status information, and tertiary flow direction information, generate a unique traceability identification code, split the traceability identification code into a product source identification segment, an inventory status identification segment, and a flow direction identification segment, establish a first association index between the product source identification segment and the inventory status identification segment, establish a second association index between the inventory status identification segment and the flow direction identification segment, and set a data integrity check;

[0031] a consumption registration module, configured to retrieve the secondary inventory status information corresponding to the inventory status identification segment according to the first association index, register the consumption of the consignment inventory of the medical device, generate a consumption record including the consumption time and the consumption quantity, and update the consumption record to the tertiary flow direction information according to the second association index;

[0032] The account period prediction module is used to establish a mapping relationship table between cargo flow data and account period data, retrieve the updated three-level flow direction information based on the traceability identification code, input the time series consumption data into the long short-term memory network, dynamically adjust the time decay factor using an adaptive mechanism, determine the fluctuation benchmark value by calculating the standard deviation of recent consumption data, and update the decay rate parameter in real time according to the fluctuation benchmark value, weight the historical data based on the updated time decay factor, predict the optimal account period and generate a settlement statement, and synchronously update the cargo flow data and account period data through the mapping relationship table.

[0033] 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 data processing method of the medical device digital supply chain consignment model are implemented.

[0034] 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 data processing method of the medical device digital supply chain consignment model.

[0035] In a fifth aspect, the present application provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the data processing method of the medical device digital supply chain consignment model.

[0036] It can be seen from the above technical solution that the present application provides a data processing method and device for the consignment model of the digital supply chain of medical devices. By creating consignment orders for medical devices, a multi-level traceability structure including primary product source information, secondary inventory status information and tertiary flow information is established; a mapping relationship table between cargo flow data and account period data is established, and the updated tertiary flow information is retrieved based on the traceability identification code. The time series consumption data is input into the long-short-term memory network, and an adaptive mechanism is used to dynamically adjust the time decay factor. The fluctuation benchmark value is determined by calculating the standard deviation of recent consumption data, and the historical data is weighted based on the updated time decay factor. The optimal account period is predicted and a settlement statement is generated. The cargo flow data and account period data are synchronously updated through the mapping relationship table, thereby realizing full traceability of the product, having intelligent account period management capabilities, and being able to make accurate consumption predictions based on historical data. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 any creative work.

[0038] Figure 1 This is one of the flow charts of the data processing method of the medical device digital supply chain consignment model in the embodiment of the present application;

[0039] Figure 2 This is a second flow chart of the data processing method for the medical device digital supply chain consignment model in an embodiment of the present application;

[0040] Figure 3 This is a third flow chart of the data processing method for the medical device digital supply chain consignment model in the embodiment of the present application;

[0041] Figure 4 This is a fourth flow chart of the data processing method for the medical device digital supply chain consignment model in an embodiment of the present application;

[0042] Figure 5 This is a fifth flow chart of the data processing method for the medical device digital supply chain consignment model in the embodiment of the present application;

[0043] Figure 6 This is a sixth flow chart of the data processing method for the medical device digital supply chain consignment model in the embodiment of the present application;

[0044] Figure 7 This is the seventh flow chart of the data processing method for the medical device digital supply chain consignment model in the embodiment of the present application;

[0045] Figure 8 This is a structural diagram of a data processing device for a medical device digital supply chain consignment model in an embodiment of the present application;

[0046] Figure 9 Schematic diagram of the structure of the electronic device in the embodiment of the present application.

[0047] Reference numerals:

[0048] 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

[0049] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0050] The acquisition, storage, use, and processing of data in this application's technical solution comply with relevant national laws and regulations.

[0051] Taking into account the problems existing in the prior art, the present application provides a data processing method and device for a consignment model of a digital supply chain for medical devices. By creating a consignment order for medical devices, a multi-level traceability structure including primary product source information, secondary inventory status information, and tertiary flow information is established; a mapping relationship table between cargo flow data and account period data is established, and the updated tertiary flow information is retrieved based on the traceability identification code. The time series consumption data is input into a long-short-term memory network, and an adaptive mechanism is used to dynamically adjust the time decay factor. The fluctuation benchmark value is determined by calculating the standard deviation of recent consumption data, and the historical data is weighted based on the updated time decay factor. The optimal account period is predicted and a settlement statement is generated. The cargo flow data and account period data are synchronously updated through the mapping relationship table, thereby achieving full product traceability, having intelligent account period management capabilities, and being able to make accurate consumption predictions based on historical data.

[0052] In order to achieve full product traceability, intelligent account management capabilities, and accurate consumption forecasting based on historical data, this application provides an embodiment of a data processing method for a medical device digital supply chain consignment model, see Figure 1 The data processing method of the medical device digital supply chain consignment model specifically includes the following contents:

[0053] Step S101: Create a consignment order for a medical device, establish a multi-level traceability structure including primary product source information, secondary inventory status information, and tertiary flow direction information, generate a unique traceability identification code, split the traceability identification code into a product source identification segment, an inventory status identification segment, and a flow direction identification segment, establish a first association index between the product source identification segment and the inventory status identification segment, establish a second association index between the inventory status identification segment and the flow direction identification segment, and set a data integrity check;

[0054] Optionally, in this embodiment, this step implements the data traceability structure establishment and identification coding process for medical device consignment management, ensuring data integrity and traceability through a hierarchical design and associated indexing mechanism. First, the system creates a 36-digit unique identification code based on basic medical device information, such as device model, specifications, and production batch. This code consists of a 12-digit device number, a 12-digit batch information, and a 12-digit timestamp. This fixed-length encoding method ensures uniqueness and standardization of the identification.

[0055] The data structure is designed using a three-tiered architecture to store relevant information. Level 1 product source information includes basic data such as supplier qualifications, production date, model specifications, etc.; level 2 inventory status information records dynamic data such as inventory location, storage conditions, and quantity changes; and level 3 flow information tracks terminal data such as the department using the product, consumption records, and destination. This hierarchical information organization makes data query and management more efficient and facilitates data linkage between different levels.

[0056] In terms of identification code processing, the system splits the 36-digit traceability identification code into a fixed 12-12-12 format. The first 12-digit product source identification segment is used to store supplier and production information, with the first 4 digits representing the supplier code, the middle 4 digits representing the product type, and the last 4 digits representing the production batch. The middle 12-digit inventory status identification segment is used to store inventory location and status information, including a 4-digit inventory location code, a 4-digit storage condition code, and a 4-digit status identifier. The last 12-digit flow direction identification segment is used to store usage information, including a 4-digit department code, a 4-digit usage type, and a 4-digit flow direction identifier.

[0057] To establish an efficient data indexing mechanism, the system performs bitwise operations on adjacent level identification segments. Specifically, an XOR operation is performed on the product source identification segment and the inventory status identification segment to generate a first associated index value, while an XOR operation is performed on the inventory status identification segment and the flow direction identification segment to generate a second associated index value. This bitwise operation-based indexing mechanism is not only computationally efficient but also effectively verifies data integrity.

[0058] To verify data integrity, the system uses a cyclic redundancy check (CRC) algorithm to validate associated index values. CRC generates a checksum using polynomial division, effectively detecting errors during data transmission and storage. If data anomalies are detected, the system triggers a check failure warning and logs the anomaly to ensure data accuracy and reliability.

[0059] This technical solution effectively addresses the data traceability challenges in medical device consignment management through a multi-level data structure design and an associative indexing mechanism. The system implements standardized data storage and efficient indexing, significantly improving data query efficiency. Furthermore, an integrity verification mechanism ensures data reliability, laying a solid foundation for subsequent inventory management and flow tracking. Furthermore, this solution is highly scalable and can adapt to the management needs of different types of medical devices, providing reliable technical support for medical device consignment management.

[0060] Step S102: Retrieving the secondary inventory status information corresponding to the inventory status identification segment according to the first association index, registering the consumption of the consignment inventory of the medical device, generating a consumption record including the consumption time and consumption quantity, and updating the consumption record to the tertiary flow direction information through the second association index;

[0061] Optionally, in this embodiment, this step implements consumption management and data updates for medical device consignment inventory, achieving real-time synchronization of inventory status and flow information through an associated index mechanism. The system first uses the first associated index value as a search key and reversely deconstructs the inventory status identification segment through bitwise operations. This process utilizes the reversible nature of the XOR operation to ensure accurate data restoration.

[0062] After obtaining the inventory status identifier, the system matches it with records in the inventory status database. This matching process uses a binary search algorithm to quickly locate the corresponding inventory status record by comparing the inventory location code, storage condition code, and status identifier. This efficient retrieval mechanism significantly reduces the time overhead of data queries.

[0063] During the consumption registration process, the system records medical device usage in real time. Specifically, when a medical device is used, the system automatically captures the usage timestamp and records the specific quantity consumed. This information is organized into structured data with time and quantity dimensions. The system also checks whether the consumption quantity exceeds the inventory threshold. If the threshold is approaching, a replenishment alert mechanism will be automatically triggered.

[0064] To ensure synchronous data updates, the system uses a second associative index to establish a mapping between inventory status information and flow direction information. This mapping is implemented using a hash table structure. The index value obtained by XORing the inventory status identification segment and the flow direction identification segment is used as the hash key, enabling rapid data location and update.

[0065] Once a consumption record is generated, the system automatically locates the corresponding record in the third-level flow information repository using the secondary association index. The update process utilizes a transaction mechanism to ensure data atomicity and consistency. Specifically, the system first packages the new consumption record into an update transaction and then uses a two-phase commit protocol to ensure reliable data writes. If an exception occurs during the update process, the system automatically rolls back to the state before the update to ensure data integrity.

[0066] This technical solution effectively addresses data consistency issues during the medical device consignment process through associated indexing and real-time synchronization mechanisms. It enables real-time tracking and automatic synchronization of inventory consumption data, significantly improving data timeliness and accuracy. Furthermore, transaction mechanisms and exception handling ensure reliable data updates, providing strong support for refined medical device management. Furthermore, the solution's high level of automation reduces manual operations and the risk of data entry errors, laying the foundation for standardized medical device consignment management.

[0067] Through the comprehensive application of these technologies, this step not only achieves precise inventory management during the medical device consignment process but also provides a reliable data foundation for subsequent data analysis and decision support. The system's scalability and fault tolerance further enhance the practical value of the solution, making it adaptable to the needs of medical institutions of varying sizes and types.

[0068] Step S103: Establish a mapping relationship table between cargo flow data and billing period data, retrieve the updated three-level flow direction information based on the traceability identification code, input the time series consumption data into the long short-term memory network, dynamically adjust the time decay factor using an adaptive mechanism, determine the fluctuation benchmark value by calculating the standard deviation of recent consumption data, and update the decay rate parameter in real time according to the fluctuation benchmark value, weight the historical data based on the updated time decay factor, predict the optimal billing period and generate a settlement statement, and synchronously update the cargo flow data and billing period data through the mapping relationship table.

[0069] Optionally, in this embodiment, this step implements an intelligent billing period forecasting and data synchronization update mechanism for medical device consignment management. First, the system establishes a bidirectional mapping relational table structure to store the correspondence between goods flow data and billing period data. This mapping table uses a key-value pair format, where the key is a traceability identification code and the value is a composite data structure containing flow status and billing period information.

[0070] The system uses the traceability identification code as an index key to retrieve the latest consumption records from the three-level flow information repository. The retrieval process employs a multi-level caching mechanism, caching frequently accessed data in memory, significantly improving data access efficiency. Retrieved consumption records are organized chronologically into time series data, containing key features such as consumption time and quantity.

[0071] In the data processing phase, the system uses a long short-term memory (LSTM) network for time series analysis. The LSTM network consists of three control units: an input gate, a forget gate, and an output gate. It effectively captures long-term data dependencies. The input layer receives normalized time series consumption data, extracts time series features through multiple layers of nonlinear transformations, and the output layer generates predictions.

[0072] To improve the model's adaptability, the system introduces an adaptive time decay mechanism. First, the standard deviation of a sliding window of recent consumption data is calculated as a quantitative indicator of data volatility. A larger standard deviation indicates more volatile data, and the system increases the time decay factor accordingly, reducing the weight of historical data. The decay rate parameter is linked to the volatility baseline through an exponential function, enabling dynamic adjustment of the decay intensity.

[0073] During the billing period forecasting process, the system applies a time-weighted approach to historical data. The weighting coefficient is determined by the updated time decay factor, with more recent data receiving a higher weight. This weighted data is then fed into an LSTM network for training and forecasting, resulting in an optimal billing period estimate. Based on the forecast results, the system automatically generates a settlement statement containing information such as the billing period and amount.

[0074] Finally, the system synchronizes data through a mapping table. When the cargo flow status changes, the system automatically updates the corresponding billing period record; conversely, when the billing period data is updated, the related flow status is also adjusted synchronously. This two-way synchronization mechanism ensures data consistency.

[0075] This technical solution effectively addresses the issue of billing period forecasting in the medical device consignment process through an adaptive time decay mechanism and intelligent forecasting model. The system implements intelligent data analysis and automatic synchronization, significantly improving the accuracy and efficiency of billing period management. Furthermore, the adaptive mechanism enhances the model's responsiveness to market changes, providing reliable support for companies' capital management decisions. Furthermore, the solution's high degree of automation reduces manual intervention, improves management efficiency, and provides technical support for the standardized operation of the medical device consignment business.

[0076] From the above description, it can be seen that the data processing method of the medical device digital supply chain consignment model provided in the embodiment of the present application can establish a multi-level traceability structure including primary product source information, secondary inventory status information and tertiary flow information by creating consignment orders for medical devices; establish a mapping relationship table between cargo flow data and account period data, retrieve the updated tertiary flow information based on the traceability identification code, input the time series consumption data into the long short-term memory network, dynamically adjust the time decay factor using an adaptive mechanism, determine the fluctuation benchmark value by calculating the standard deviation of recent consumption data, weight the historical data based on the updated time decay factor, predict the optimal account period and generate a settlement statement, and synchronously update the cargo flow data and account period data through the mapping relationship table, thereby realizing full traceability of the product, having intelligent account period management capabilities, and being able to make accurate consumption predictions based on historical data.

[0077] In one embodiment of the data processing method of the medical device digital supply chain consignment model of the present application, see Figure 2 , and can also include the following:

[0078] Step S201: Generate a 36-bit unique identification code based on the basic information of the medical device, the unique identification code including the device number, production batch number and timestamp information, and create a consignment order based on the unique identification code;

[0079] Step S202: Classify medical devices according to supplier, production date and model to establish a product source information database, classify them according to inventory location, storage conditions and quantity to establish an inventory status information database, and classify them according to use department, consumption record and flow destination to establish a flow information database. The product source information database, inventory status information database and flow information database are combined to form a multi-level traceability structure.

[0080] Optionally, in this embodiment, these two steps together implement the process of creating a medical device consignment order and constructing a data structure. First, the system generates a standardized unique identification code based on the basic information of the medical device. The identification code is designed with a fixed length of 36 bits, of which the device number occupies 12 bits to identify the specific medical device model and specifications; the production batch number occupies 12 bits, including the production date and batch information; the timestamp information occupies 12 bits to record the time the device was put into storage, using a time coding format accurate to the second. This coding scheme ensures that each medical device has a unique identity.

[0081] The identification code generation process uses a segmented combination approach. The system first converts the device number into a 12-digit string, where the first four digits represent the device category, the middle four digits represent the subcategory, and the last four digits represent the specific model. Of the 12 digits of the production batch number, the first six digits represent the production date, and the last six digits represent the batch number. The timestamp information is converted to a 12-digit number using Unix timestamps. These three segments are directly concatenated to form a complete 36-bit identification code. This encoding method not only ensures uniqueness but also facilitates subsequent information extraction and parsing.

[0082] In terms of database structure design, the system adopts a three-level hierarchical architecture. The first-level product source information database organizes data in a tree structure, with supplier information as the root node, production date as the second-level node, and model information as the leaf node. Each node contains detailed attribute information, such as supplier qualifications, production license, and quality certification. This hierarchical data organization facilitates rapid information retrieval and updating.

[0083] The secondary inventory status database utilizes a matrix structure, with inventory locations as rows, storage conditions as columns, and quantity information as matrix elements. Each inventory location is equipped with an environmental monitoring module that records storage parameters such as temperature and humidity in real time. Through matrix operations, the system enables rapid inventory statistics and allocation, improving inventory management efficiency.

[0084] The three-level flow information database uses a time-series database storage structure to record the use of medical devices over time. This data includes detailed information such as the department of use, operator, and time of use. The system utilizes time indexing technology to support efficient historical data query and statistical analysis.

[0085] The three databases form a complete multi-level traceability structure through linked fields. The system uses a primary key-foreign key mechanism to establish inter-database linkages, using unique identification codes as the linkage keys to achieve vertical linkage and horizontal expansion of data. This multidimensional data structure design provides a solid foundation for subsequent data analysis and decision support.

[0086] This technical solution effectively addresses data organization and traceability issues in medical device consignment management through a standardized coding system and multi-level data structure. The system enables standardized data storage and efficient retrieval, providing reliable technical support for the full lifecycle management of medical devices. Furthermore, the layered data structure improves system scalability and maintainability, adapting to the management needs of medical institutions of varying sizes.

[0087] In one embodiment of the data processing method of the medical device digital supply chain consignment model of the present application, see Figure 3 , and can also include the following:

[0088] Step S301: Split the 36-digit traceability identification code into a fixed-length format of 12-12-12 digits. The first 12 digits are used as the product source identification segment to store supplier and production information. The middle 12 digits are used as the inventory status identification segment to store inventory location and status information. The last 12 digits are used as the flow direction identification segment to store using department and consumption information.

[0089] Step S302: Perform a bit-by-bit XOR operation on the product source identification segment and the inventory status identification segment to generate a first association index value, perform a bit-by-bit XOR operation on the inventory status identification segment and the flow direction identification segment to generate a second association index value, and use a cyclic redundancy check algorithm to perform data verification on the first association index value and the second association index value.

[0090] Optionally, in this embodiment, these two steps realize the segmentation processing and associated index establishment process of the medical device traceability identification code. The system first performs a standardized splitting of the 36-bit traceability identification code, using a three-segment structure of fixed length. The product source identification segment occupies the first 12 bits and adopts a 4-4-4 internal division method. The first 4 digits store the supplier code, the middle 4 digits store the product type code, and the last 4 digits store the production batch number. The inventory status identification segment occupies the middle 12 bits and also adopts a 4-4-4 structure to store the inventory location code, storage condition code and status identification in sequence. The flow direction identification segment occupies the last 12 bits and is divided into 4-4-4 bits to store the use department code, use type code and flow direction identification respectively.

[0091] The identification code segmentation process is implemented using bitwise operations. The system extracts each segment through shift and mask operations, ensuring accurate and efficient data extraction. Each identification segment uses independent encoding rules, ensuring data uniqueness and traceability. This fixed-length segmented storage method not only facilitates data parsing and processing, but also improves storage efficiency.

[0092] When establishing the association index, the system uses an exclusive-or operation to generate the index value. For the first association index, the system performs a bit-by-bit exclusive-or operation on the 12-bit binary data of the product source identification segment and the 12-bit data of the inventory status identification segment. The exclusive-or operation is reversible and commutative, which ensures the uniqueness and traceability of the index value. Similarly, the second association index is generated by performing an exclusive-or operation on the inventory status identification segment and the flow direction identification segment. This indexing mechanism establishes a logical association between adjacent data segments, facilitating rapid data location and association queries.

[0093] To ensure data integrity and reliability, the system uses a cyclic redundancy check (CRC) algorithm to verify the associated index value. The CRC process first treats the index value as a binary polynomial coefficient and performs a modulo-2 division on a specific generator polynomial to generate a checksum. The system appends the checksum to the original data to form a complete checksum packet. This verification mechanism effectively detects bit errors during data transmission and storage.

[0094] When a data anomaly is detected, the system automatically triggers a verification failure warning and records the anomaly log. Simultaneously, the system attempts to reconstruct the original data using the reversible nature of the XOR operation, enabling automatic data repair. If the repair fails, an alert is sent to the administrator, requesting manual intervention.

[0095] This technical solution effectively addresses data association and integrity issues in medical device consignment management through standardized data segmentation and association indexing mechanisms. The system enables efficient data storage and rapid retrieval, significantly improving data processing efficiency. Furthermore, a CRC checksum mechanism ensures reliable data transmission and storage, providing technical support for refined medical device management. Furthermore, the solution's high fault tolerance enables timely detection and resolution of data anomalies, ensuring stable system operation.

[0096] In one embodiment of the data processing method of the medical device digital supply chain consignment model of the present application, see Figure 4 , and can also include the following:

[0097] Step S401: obtaining an inventory status identification segment through a first associated index value, comparing and matching the inventory status identification segment with a corresponding record in an inventory status information database, reading inventory status information of the medical device, and recording the usage time and specific usage quantity of the medical device in the inventory status information;

[0098] Step S402: Associatively map the usage record in the inventory status information of the medical device with the second association index value, locate the corresponding position in the three-level flow information library based on the mapping relationship, and write the usage time point and usage quantity into the consumption record field of the flow information library to complete data synchronization.

[0099] Optionally, in this embodiment, these two steps implement an inventory status update and data synchronization mechanism during the use of medical devices. First, the system uses the first associated index value as a search key and restores the inventory status identification segment through reverse parsing. This process uses bitwise operations to restore the original inventory status identification information by performing the inverse XOR operation on the 12-bit index value. The system uses a caching mechanism to optimize retrieval efficiency, storing frequently accessed index values ​​in memory to reduce the number of database accesses.

[0100] After obtaining the inventory status identification segment, the system performs a comparison and matching operation. This matching process utilizes multi-level indexing technology, first quickly locating the data interval using the inventory location code, then performing a secondary screening using the storage condition code, and finally accurately locating the target record using the status identification. This multi-level indexing strategy significantly improves data retrieval efficiency. Upon a successful match, the system immediately retrieves the complete inventory status information for the medical device.

[0101] Usage records are updated using an atomic operation mechanism. The system first obtains a millisecond-accurate timestamp as the usage point and also records the specific usage amount. This information is organized into structured data, including fields such as operation time, operator, and usage amount. The system uses copy-on-write technology to ensure the atomicity and consistency of data updates.

[0102] During data synchronization, the system first establishes a mapping between usage records and associated index values. This mapping is implemented using a hash table structure, using the index value as the hash key and the associated usage record as the value. The hash table design takes load factors and conflict resolution into account, ensuring efficient mapping operations.

[0103] Based on the established mapping relationships, the system can quickly locate the target record in the third-level flow information repository. This location process utilizes a B+ tree index structure, supporting efficient range queries and precise searches. The system writes information such as usage time and quantity into the corresponding fields of the flow information repository, completing data synchronization. The synchronization process utilizes a transaction mechanism to ensure data consistency and integrity.

[0104] To prevent data loss, the system implements a multi-level backup mechanism. Every data update generates an operation log, detailing the update content and timestamp. If a system anomaly occurs, the log records allow for rapid data restoration. The system also implements an incremental backup strategy, regularly synchronizing updated data to a backup server.

[0105] This technical solution effectively addresses data consistency issues during the use of medical devices through an efficient indexing mechanism and reliable synchronization strategy. The system achieves real-time synchronization of inventory status and flow information, significantly improving data timeliness and accuracy. Furthermore, multiple security mechanisms ensure data reliability, providing strong support for the management of medical device usage. Furthermore, the solution's high degree of automation reduces manual intervention, improves management efficiency, and provides technical support for the standardized operation of medical device consignment services.

[0106] In one embodiment of the data processing method of the medical device digital supply chain consignment model of the present application, see Figure 5 , and can also include the following:

[0107] Step S501: Constructing a time series data structure based on a 64-bit floating point format, writing the consumption data of medical devices into the data structure according to the time dimension, normalizing the data through the input gate of a long short-term memory network, and setting a recurrent neuron structure with three hidden layers in the long short-term memory network;

[0108] Step S502: Calculate the difference in consumption data between adjacent time nodes to obtain a time interval matrix, input the time interval matrix into an exponential function to generate an initial time decay factor, and adjust the cardinality parameter of the exponential function in real time according to the prediction error of the long short-term memory network, so that the time decay factor decreases exponentially with the increase of the time interval.

[0109] Optionally, in this embodiment, these two steps implement the time series processing and dynamic decay mechanism for medical device consumption data. The system first constructs a time series data structure using the IEEE 754 standard 64-bit floating-point format, with 1 bit for the sign, 11 bits for the exponent, and 52 bits for the mantissa. This format provides sufficient precision and range to accurately represent the numerical characteristics and temporal information of the consumption data. The system writes the consumption data into this data structure in timestamp order, forming an ordered time series.

[0110] During data preprocessing, the system performs normalization through the LSTM network's input gate. This normalization uses the min-max method to map the data to the interval [0, 1]. This processing method not only preserves the relative size of the data but also effectively eliminates dimensionality effects, improving model training effectiveness. The input gate uses a sigmoid activation function to control the inflow of information, enabling adaptive data filtering.

[0111] The core structure of the LSTM network utilizes a three-hidden layer design. The first hidden layer is responsible for feature extraction and contains 128 neurons; the second hidden layer performs feature fusion and uses 64 neurons; and the third hidden layer performs feature mapping and has 32 neurons. Each layer of neurons uses a recurrent connection structure to maintain long-term memory of historical information. The network uses a backpropagation algorithm for parameter updates and the Adam optimizer for weight adjustment.

[0112] To implement the time decay mechanism, the system first calculates the difference in consumption data between adjacent time points. This difference calculation uses a sliding window approach, with the window size dynamically adjusted based on data characteristics. The resulting time interval matrix reflects the time span relationship between data points. This matrix structure facilitates subsequent batch calculations and parallel processing.

[0113] The system feeds the time interval matrix into an exponential function to generate an initial time decay factor. The exponential function is based on the natural logarithm, with the initial value of the base parameter determined by historical data statistics. The decay factor calculation takes into account the nonlinear effects of time spans, with the weight of long-term data decaying exponentially.

[0114] To improve the model's adaptability, the system monitors the LSTM network's prediction error in real time. When the prediction error exceeds a preset threshold, an adjustment mechanism is triggered to adjust the exponential function's cardinality parameter. This adjustment process uses a gradient descent method to optimize the cardinality parameter by minimizing the prediction error. This adaptive mechanism ensures that the decay factor accurately reflects the timeliness of the data.

[0115] This technical solution effectively addresses the timeliness issue in medical device consumption forecasting through sophisticated data structure design and an intelligent decay mechanism. The system achieves high-precision data storage and intelligent processing, significantly improving forecast accuracy. Furthermore, the adaptive decay mechanism enhances the model's responsiveness to market changes, providing reliable support for companies' inventory management decisions. Furthermore, the solution's high computational efficiency meets the needs of real-time forecasting, providing technical support for the intelligent management of medical device consignment sales.

[0116] In one embodiment of the data processing method of the medical device digital supply chain consignment model of the present application, see Figure 6 , and can also include the following:

[0117] Step S601: Statistical samples are generated from the medical device consumption data for the past 30 days. Based on the statistical samples, the mean of the consumption amount and the sum of squared deviations of each sampling point are calculated. The sum of squared deviations is divided by the number of sampling points and the square root is taken to obtain a standard deviation of fluctuations. The standard deviation of fluctuations is compared with a preset threshold to obtain a reference value of fluctuations.

[0118] Step S602: Substitute the fluctuation reference value into the sigmoid function to calculate the initial value of the attenuation rate, adjust the slope coefficient of the sigmoid function based on the changing trend of the fluctuation reference value, and output the updated attenuation rate parameter through the dynamically adjusted sigmoid function.

[0119] Optionally, in this embodiment, these two steps implement statistical analysis of medical device consumption data and a dynamic attenuation rate adjustment mechanism. First, the system collects consumption data from the last 30 days as a statistical sample. The sampling process uses a uniform time interval, sampling data at fixed points each day to ensure a uniform temporal distribution of the samples. The system preprocesses these sample data, including outlier detection and missing value processing, to improve data quality.

[0120] During the statistical calculation phase, the system first calculates the arithmetic mean of consumption. This calculation utilizes a sliding window approach, enabling dynamic updates of the mean. Next, the system calculates the difference between each sampling point and the mean and squares these differences to produce a series of squared deviations. The system then divides the sum of these squared deviations by the number of sampling points and takes the square root to obtain the standard deviation of the fluctuation. This standard deviation reflects the degree of dispersion in the consumption data.

[0121] The system compares the calculated standard deviation of fluctuations with a preset threshold. This threshold is determined based on historical data analysis and reflects the normal range of fluctuations. Through this comparison, the system generates a fluctuation baseline value. This baseline value comprehensively considers the relationship between actual and expected fluctuations and provides a basis for subsequent adjustments to the decay rate.

[0122] During the decay rate calculation process, the system uses the sigmoid function as the basic conversion function. The sigmoid function has excellent nonlinear properties and can map inputs to the (0, 1) interval, making it suitable as the basis for decay rate calculation. The system uses the fluctuation baseline value as the input of the sigmoid function and calculates the initial value of the decay rate through the function operation.

[0123] To improve system adaptability, the system monitors the changing trend of the fluctuation baseline in real time. When a trend change is detected, the system automatically adjusts the slope coefficient of the sigmoid function. This adjustment process uses a gradient descent method to optimize the slope coefficient by minimizing the prediction error. This adaptive mechanism enables the decay rate to better reflect the dynamic characteristics of the data.

[0124] The system calculates the updated decay rate parameters in real time using the adjusted sigmoid function. The update process utilizes an atomic operation mechanism to ensure consistent parameter updates. The system also implements parameter smoothing to prevent sudden changes in the decay rate from adversely affecting predictions.

[0125] This technical solution effectively addresses the dynamic adaptation problem in medical device consumption forecasting through precise statistical analysis and a flexible rate adjustment mechanism. The system accurately quantifies fluctuation characteristics and intelligently adjusts the decay rate, significantly improving the adaptability of the forecasting model. Furthermore, the adaptive parameter adjustment mechanism enhances the model's responsiveness to changes in consumption patterns, providing reliable decision-making support for medical device inventory management. Furthermore, the solution's high computational efficiency meets the needs of real-time forecasting, providing technical support for the intelligent management of medical device consignment sales. The implementation of this solution has reduced inventory management costs, improved supply chain efficiency, and delivered significant economic benefits.

[0126] In one embodiment of the data processing method of the medical device digital supply chain consignment model of the present application, see Figure 7, and can also include the following:

[0127] Step S701: Performing a dot product operation on the historical consumption data of medical devices and the updated time decay factor to obtain a weighted sequence, inputting the weighted sequence into the output layer of the long short-term memory network, calculating the optimal billing period based on the output result, and generating settlement data including consumption summary, amount calculation, and billing period time limit based on the optimal billing period;

[0128] Step S702: Construct a two-dimensional mapping table containing cargo flow records and billing period data, establish a key-value pair index for the two-dimensional mapping table according to the cargo number, locate the target record in the two-dimensional mapping table through the key-value pair index, write the settlement data into the billing period field of the target record and update the corresponding cargo flow status.

[0129] Optionally, in this embodiment, these two steps implement the generation and status update mechanism for medical device settlement data. First, the system performs a dot product operation on historical consumption data and the updated time decay factor. This dot product operation uses vectorized calculations and parallel processing technology to improve computational efficiency. Through this weighted process, the system effectively balances the influence of recent and long-term data, making the prediction results more consistent with actual conditions.

[0130] The weighted sequence is input to the output layer of the LSTM network for processing. The output layer uses a fully connected architecture and a softmax activation function to predict probability distributions. At this stage, the network considers long-term dependencies among time series features, filtering important information through a gating mechanism to generate predictions. Based on these predictions, the system uses a dynamic programming algorithm to calculate the optimal payment period.

[0131] During the optimization process for payment periods, the system considers multiple factors, including capital costs, inventory turnover, and market demand fluctuations. The optimization goal is to maximize capital efficiency while ensuring supply chain stability. The system uses a sliding time window approach to dynamically adjust the payment period range to adapt to market changes.

[0132] The settlement data generation process adopts a modular design. The consumption summary module is responsible for calculating usage within a specific time period, the amount calculation module calculates expenses based on pricing policies, and the payment period module determines the payment node. These modules are loosely coupled through a message queue mechanism, improving the system's maintainability.

[0133] For data storage, the system constructs a two-dimensional mapping structure based on a hash table. This structure stores cargo flow records in rows and account period data in columns, enabling efficient data organization and fast retrieval. The system assigns a unique hash key to each cargo item and establishes a key-value index, supporting O(1) time complexity lookup operations.

[0134] Key-value indexing is implemented using distributed hash table technology, which uses a consistent hashing algorithm to achieve uniform data distribution. The system uses a two-tier index structure, with the first tier locating data shards and the second tier locating specific records, significantly improving the efficiency of large-scale data processing.

[0135] During data updates, the system uses an optimistic locking mechanism to handle concurrent access. Updates first obtain the record's version number and only execute the write operation if the version numbers match. If a version conflict occurs, the system automatically retries the update. This mechanism ensures data consistency while avoiding lengthy lock waits.

[0136] This technical solution effectively addresses the complexities of medical device consignment settlement through intelligent billing period optimization and efficient data management. The system automatically generates settlement data and updates status in real time, significantly improving settlement efficiency. Furthermore, its distributed storage structure and concurrency control mechanism ensure high system availability, providing technical support for the large-scale application of medical device consignment services. Furthermore, the solution's strong scalability allows it to adapt to business growth, providing reliable support for the company's long-term development.

[0137] In order to achieve full product traceability, intelligent account management capabilities, and accurate consumption forecasting based on historical data, the present application provides an embodiment of a data processing device for a medical device digital supply chain consignment model that implements all or part of the data processing method for the medical device digital supply chain consignment model, see Figure 8 The data processing device of the medical device digital supply chain consignment model specifically includes the following contents:

[0138] The multi-level traceability module 10 is used to create a consignment order for medical devices, establish a multi-level traceability structure including primary product source information, secondary inventory status information, and tertiary flow direction information, generate a unique traceability identification code, split the traceability identification code into a product source identification segment, an inventory status identification segment, and a flow direction identification segment, establish a first association index between the product source identification segment and the inventory status identification segment, establish a second association index between the inventory status identification segment and the flow direction identification segment, and set a data integrity check;

[0139] a consumption registration module 20 configured to retrieve the secondary inventory status information corresponding to the inventory status identification segment according to the first association index, register the consumption of the consignment inventory of the medical device, generate a consumption record including the consumption time and the consumption quantity, and update the consumption record to the tertiary flow direction information according to the second association index;

[0140] The billing period prediction module 30 is used to establish a mapping relationship table between cargo flow data and billing period data, retrieve the updated three-level flow direction information based on the traceability identification code, input the time series consumption data into the long short-term memory network, dynamically adjust the time decay factor using an adaptive mechanism, determine the fluctuation reference value by calculating the standard deviation of recent consumption data, and update the decay rate parameter in real time according to the fluctuation reference value, weight the historical data based on the updated time decay factor, predict the optimal billing period and generate a settlement statement, and synchronously update the cargo flow data and billing period data through the mapping relationship table.

[0141] From the above description, it can be seen that the data processing device of the medical device digital supply chain consignment model provided in the embodiment of the present application can establish a multi-level traceability structure including primary product source information, secondary inventory status information and tertiary flow information by creating consignment orders for medical devices; establish a mapping relationship table between cargo flow data and account period data, retrieve the updated tertiary flow information based on the traceability identification code, input the time series consumption data into the long short-term memory network, dynamically adjust the time decay factor using an adaptive mechanism, determine the fluctuation benchmark value by calculating the standard deviation of recent consumption data, weight the historical data based on the updated time decay factor, predict the optimal account period and generate a settlement statement, and synchronously update the cargo flow data and account period data through the mapping relationship table, thereby realizing full traceability of the product, having intelligent account period management capabilities, and being able to make accurate consumption predictions based on historical data.

[0142] From a hardware perspective, in order to achieve full product traceability, possess intelligent billing management capabilities, and accurately predict consumption based on historical data, this application provides an embodiment of an electronic device for implementing all or part of the data processing method for the medical device digital supply chain consignment model. The electronic device specifically includes the following:

[0143] A processor, a memory, a communications interface, and a bus; wherein the processor, the memory, and the communications interface communicate with each other via the bus; the communications interface is used to implement information transmission between the data processing device of the medical device digital supply chain consignment model and related devices such as the core business system, user terminals, and related databases; the logic controller can be a desktop computer, a tablet computer, a mobile terminal, etc., but this embodiment is not limited thereto. In this embodiment, the logic controller can be implemented with reference to the embodiment of the data processing method of the medical device digital supply chain consignment model and the embodiment of the data processing device of the medical device digital supply chain consignment model in the embodiment, and their contents are incorporated herein, and repeated parts are not repeated.

[0144] 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.

[0145] In practical applications, part of the data processing method for the medical device digital supply chain consignment model can be executed on the electronic device side as described above, or all operations can be completed on the client device. The specific selection can be based on the processing capabilities of the client device and the limitations of the user's usage scenario. This application does not limit this. If all operations are completed on the client device, the client device may also include a processor.

[0146] The client device may include a communication module (i.e., a communication unit) that can establish a communication connection with a remote server to implement data transmission with the server. The server may include a server on the task scheduling center side, and in 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, a server cluster consisting of multiple servers, or a server structure of a distributed device.

[0147] Figure 9 Schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Figure 9 As shown, the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It is worth noting that the Figure 9 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0148] In one embodiment, the data processing method function of the medical device digital supply chain consignment model can be integrated into the central processing unit 9100. The central processing unit 9100 can be configured to perform the following control:

[0149] Step S101: Create a consignment order for a medical device, establish a multi-level traceability structure including primary product source information, secondary inventory status information, and tertiary flow direction information, generate a unique traceability identification code, split the traceability identification code into a product source identification segment, an inventory status identification segment, and a flow direction identification segment, establish a first association index between the product source identification segment and the inventory status identification segment, establish a second association index between the inventory status identification segment and the flow direction identification segment, and set a data integrity check;

[0150] Step S102: Retrieving the secondary inventory status information corresponding to the inventory status identification segment according to the first association index, registering the consumption of the consignment inventory of the medical device, generating a consumption record including the consumption time and consumption quantity, and updating the consumption record to the tertiary flow direction information through the second association index;

[0151] Step S103: Establish a mapping relationship table between cargo flow data and billing period data, retrieve the updated three-level flow direction information based on the traceability identification code, input the time series consumption data into the long short-term memory network, dynamically adjust the time decay factor using an adaptive mechanism, determine the fluctuation benchmark value by calculating the standard deviation of recent consumption data, and update the decay rate parameter in real time according to the fluctuation benchmark value, weight the historical data based on the updated time decay factor, predict the optimal billing period and generate a settlement statement, and synchronously update the cargo flow data and billing period data through the mapping relationship table.

[0152] From the above description, it can be seen that the electronic device provided in the embodiment of the present application creates a consignment order for medical devices, establishes a multi-level traceability structure including primary product source information, secondary inventory status information and tertiary flow information; establishes a mapping relationship table between cargo flow data and account period data, retrieves the updated tertiary flow information based on the traceability identification code, inputs the time series consumption data into the long short-term memory network, adopts an adaptive mechanism to dynamically adjust the time decay factor, determines the fluctuation reference value by calculating the standard deviation of recent consumption data, weights the historical data based on the updated time decay factor, predicts the optimal account period and generates a settlement statement, and synchronously updates the cargo flow data and account period data through the mapping relationship table, thereby realizing full traceability of the product, possessing intelligent account period management capabilities, and being able to make accurate consumption predictions based on historical data.

[0153] In another embodiment, the data processing device of the medical device digital supply chain consignment model can be configured separately from the central processor 9100. For example, the data processing device of the medical device digital supply chain consignment model can be configured as a chip connected to the central processor 9100, and the data processing method function of the medical device digital supply chain consignment model is realized through the control of the central processor.

[0154] like Figure 9 As shown, the electronic device 9600 may further 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 Figure 9 In addition, the electronic device 9600 may also include all components shown in Figure 9 For components not shown, reference may be made to the prior art.

[0155] like Figure 9 As shown, the central processing unit 9100 is sometimes also referred to as a controller or 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.

[0156] Memory 9140 can be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It can store the aforementioned failure-related information and also store programs that execute the relevant information. The CPU 9100 can execute the programs stored in memory 9140 to implement information storage or processing.

[0157] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 may be, for example, a keypad or touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display objects such as images and text. The display may be, for example, an LCD display, but is not limited thereto.

[0158] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), or a SIM card. Alternatively, it may be a memory that retains information even when power is off, can be selectively erased, and is provided with more data. Examples of such memory are sometimes referred to as EPROMs. 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 for storing application programs and function programs or processes for executing the operation of the electronic device 9600 by the central processing unit 9100.

[0159] 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 driver programs 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.).

[0160] The communication module 9110 is a transmitter / receiver that transmits 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.

[0161] Based on different communication technologies, multiple communication modules 9110 can be provided in the same electronic device, such as a cellular network module, a Bluetooth module, and / or a wireless local area network module. The communication module 9110 (transmitter / receiver) is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby implementing typical telecommunication functions. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. Furthermore, the audio processor 9130 is also coupled to the central processing unit 9100, enabling local recording via the microphone 9132 and playback of stored audio via the speaker 9131.

[0162] Embodiments of the present application also provide a computer-readable storage medium capable of implementing all steps of the data processing method for a medical device digital supply chain consignment model in the above-mentioned embodiment, where the execution subject is a server or a client. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, all steps of the data processing method for a medical device digital supply chain consignment model in the above-mentioned embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0163] Step S101: Create a consignment order for a medical device, establish a multi-level traceability structure including primary product source information, secondary inventory status information, and tertiary flow direction information, generate a unique traceability identification code, split the traceability identification code into a product source identification segment, an inventory status identification segment, and a flow direction identification segment, establish a first association index between the product source identification segment and the inventory status identification segment, establish a second association index between the inventory status identification segment and the flow direction identification segment, and set a data integrity check;

[0164] Step S102: Retrieving the secondary inventory status information corresponding to the inventory status identification segment according to the first association index, registering the consumption of the consignment inventory of the medical device, generating a consumption record including the consumption time and consumption quantity, and updating the consumption record to the tertiary flow direction information through the second association index;

[0165] Step S103: Establish a mapping relationship table between cargo flow data and billing period data, retrieve the updated three-level flow direction information based on the traceability identification code, input the time series consumption data into the long short-term memory network, dynamically adjust the time decay factor using an adaptive mechanism, determine the fluctuation benchmark value by calculating the standard deviation of recent consumption data, and update the decay rate parameter in real time according to the fluctuation benchmark value, weight the historical data based on the updated time decay factor, predict the optimal billing period and generate a settlement statement, and synchronously update the cargo flow data and billing period data through the mapping relationship table.

[0166] From the above description, it can be seen that the computer-readable storage medium provided in the embodiment of the present application establishes a multi-level traceability structure including primary product source information, secondary inventory status information and tertiary flow information by creating a consignment order for medical devices; establishes a mapping relationship table between cargo flow data and account period data, retrieves the updated tertiary flow information based on the traceability identification code, inputs the time series consumption data into the long short-term memory network, adopts an adaptive mechanism to dynamically adjust the time decay factor, determines the fluctuation benchmark value by calculating the standard deviation of recent consumption data, weights the historical data based on the updated time decay factor, predicts the optimal account period and generates a settlement statement, and synchronously updates the cargo flow data and account period data through the mapping relationship table, thereby realizing full traceability of the product, having intelligent account period management capabilities, and being able to make accurate consumption predictions based on historical data.

[0167] The embodiments of the present application also provide a computer program product capable of implementing all steps of the data processing method for the medical device digital supply chain consignment model in the above-mentioned embodiments, where the execution subject is a server or a client. When the computer program / instructions are executed by a processor, the computer program / instructions implement the steps of the data processing method for the medical device digital supply chain consignment model. For example, the computer program / instructions implement the following steps:

[0168] Step S101: Create a consignment order for a medical device, establish a multi-level traceability structure including primary product source information, secondary inventory status information, and tertiary flow direction information, generate a unique traceability identification code, split the traceability identification code into a product source identification segment, an inventory status identification segment, and a flow direction identification segment, establish a first association index between the product source identification segment and the inventory status identification segment, establish a second association index between the inventory status identification segment and the flow direction identification segment, and set a data integrity check;

[0169] Step S102: Retrieving the secondary inventory status information corresponding to the inventory status identification segment according to the first association index, registering the consumption of the consignment inventory of the medical device, generating a consumption record including the consumption time and consumption quantity, and updating the consumption record to the tertiary flow direction information through the second association index;

[0170] Step S103: Establish a mapping relationship table between cargo flow data and billing period data, retrieve the updated three-level flow direction information based on the traceability identification code, input the time series consumption data into the long short-term memory network, dynamically adjust the time decay factor using an adaptive mechanism, determine the fluctuation benchmark value by calculating the standard deviation of recent consumption data, and update the decay rate parameter in real time according to the fluctuation benchmark value, weight the historical data based on the updated time decay factor, predict the optimal billing period and generate a settlement statement, and synchronously update the cargo flow data and billing period data through the mapping relationship table.

[0171] From the above description, it can be seen that the computer program product provided in the embodiment of the present application creates a consignment order for medical devices, establishes a multi-level traceability structure including primary product source information, secondary inventory status information and tertiary flow information; establishes a mapping relationship table between cargo flow data and account period data, retrieves the updated tertiary flow information based on the traceability identification code, inputs the time series consumption data into the long short-term memory network, adopts an adaptive mechanism to dynamically adjust the time decay factor, determines the fluctuation reference value by calculating the standard deviation of recent consumption data, weights the historical data based on the updated time decay factor, predicts the optimal account period and generates a settlement statement, and synchronously updates the cargo flow data and account period data through the mapping relationship table, thereby realizing full traceability of the product, having intelligent account period management capabilities, and being able to make accurate consumption predictions based on historical data.

[0172] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatus, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, 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 magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0173] 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 a 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 produce 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.

[0174] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0175] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device 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.

[0176] Specific embodiments are used in the present invention 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 ideas. At the same time, for those skilled in the art, according to the ideas of the present invention, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present invention.

Claims

1. A data processing method for a medical device digital supply chain consignment model, characterized in that: The method comprises: Create a consignment order for medical devices, establish a multi-level traceability structure including primary product source information, secondary inventory status information, and tertiary flow direction information, generate a unique traceability identification code, split the traceability identification code into a product source identification segment, an inventory status identification segment, and a flow direction identification segment, establish a first association index between the product source identification segment and the inventory status identification segment, establish a second association index between the inventory status identification segment and the flow direction identification segment, and set a data integrity check; Retrieving the secondary inventory status information corresponding to the inventory status identification segment according to the first association index, registering the consumption of the consignment inventory of the medical device, generating a consumption record including the consumption time and the consumption quantity, and updating the consumption record to the tertiary flow direction information through the second association index; A mapping relationship table between cargo flow data and billing period data is established, updated three-level flow direction information is retrieved based on the traceability identification code, time series consumption data is input into the long short-term memory network, and the time decay factor is dynamically adjusted using an adaptive mechanism. The fluctuation benchmark value is determined by calculating the standard deviation of recent consumption data, and the decay rate parameter is updated in real time according to the fluctuation benchmark value. The historical data is weighted based on the updated time decay factor, the optimal billing period is predicted and a settlement statement is generated, and the cargo flow data and billing period data are synchronously updated through the mapping relationship table.

2. The data processing method for the medical device digital supply chain consignment model according to claim 1 is characterized in that: The above-mentioned process of creating a consignment order for medical devices, establishing a multi-level traceability structure including primary product source information, secondary inventory status information, and tertiary flow information, and generating a unique traceability identification code includes: Generate a 36-bit unique identification code based on the basic information of the medical device, the unique identification code including the device number, production batch number and timestamp information, and create a consignment order based on the unique identification code; Medical devices are classified according to supplier, production date and model to establish a product source information database, classified according to inventory location, storage conditions and quantity to establish an inventory status information database, classified according to use department, consumption record and flow destination to establish a flow information database, and the product source information database, inventory status information database and flow information database are combined to form a multi-level traceability structure.

3. The data processing method for the medical device digital supply chain consignment model according to claim 1, characterized in that: The step of splitting the traceability identification code into a product source identification segment, an inventory status identification segment, and a flow direction identification segment, establishing a first association index between the product source identification segment and the inventory status identification segment, establishing a second association index between the inventory status identification segment and the flow direction identification segment, and setting a data integrity check comprises: The 36-digit traceability identification code is split into a fixed-length format of 12-12-12 digits. The first 12 digits are used as the product source identification segment to store supplier and production information, the middle 12 digits are used as the inventory status identification segment to store inventory location and status information, and the last 12 digits are used as the flow identification segment to store use department and consumption information. A first association index value is generated by performing a bit-by-bit exclusive OR operation on the product source identification segment and the inventory status identification segment, a second association index value is generated by performing a bit-by-bit exclusive OR operation on the inventory status identification segment and the flow direction identification segment, and a cyclic redundancy check algorithm is used to perform data verification on the first association index value and the second association index value.

4. The data processing method for the medical device digital supply chain consignment model according to claim 1 is characterized in that: The step of retrieving the secondary inventory status information corresponding to the inventory status identification segment according to the first association index, registering the consumption of the consignment inventory of the medical device, generating a consumption record including the consumption time and the consumption quantity, and updating the consumption record to the tertiary flow direction information through the second association index includes: Obtaining an inventory status identification segment through the first associated index value, comparing and matching the inventory status identification segment with a corresponding record in an inventory status information database, reading inventory status information of the medical device, and recording a usage time point and a specific usage quantity of the medical device in the inventory status information; The usage records in the inventory status information of the medical device are associated with the second association index value, the corresponding position in the three-level flow information library is located based on the mapping relationship, and the usage time point and usage quantity are written into the consumption record field of the flow information library to complete data synchronization.

5. The data processing method for the medical device digital supply chain consignment model according to claim 1 is characterized in that: The time series consumption data is input into the long short-term memory network, and the time decay factor is dynamically adjusted using an adaptive mechanism, including: Constructing a time series data structure based on a 64-bit floating-point format, writing medical device consumption data into the data structure according to the time dimension, normalizing the data through the input gate of a long short-term memory network, and setting a recurrent neuron structure with three hidden layers in the long short-term memory network; The consumption data difference between adjacent time nodes is calculated to obtain a time interval matrix, which is input into an exponential function to generate an initial time decay factor. The cardinality parameter of the exponential function is adjusted in real time according to the prediction error of the long short-term memory network, so that the time decay factor decreases exponentially with the increase of the time interval.

6. The data processing method for the medical device digital supply chain consignment model according to claim 1 is characterized in that: The method of determining the fluctuation reference value by calculating the standard deviation of recent consumption data and updating the decay rate parameter in real time according to the fluctuation reference value includes: Forming a statistical sample from the medical device consumption data for nearly 30 days, calculating the mean of the consumption and the sum of squares of deviations of each sampling point based on the statistical sample, dividing the sum of squares of deviations by the number of sampling points and taking the square root to obtain a fluctuation standard deviation, and comparing the fluctuation standard deviation with a preset threshold to obtain a fluctuation reference value; The fluctuation reference value is substituted into the sigmoid function to calculate the initial value of the attenuation rate, the slope coefficient of the sigmoid function is adjusted based on the changing trend of the fluctuation reference value, and the updated attenuation rate parameter is output through the dynamically adjusted sigmoid function.

7. The data processing method for the medical device digital supply chain consignment model according to claim 1, characterized in that: The method weights the historical data based on the updated time decay factor, predicts the optimal billing period and generates a settlement statement, and synchronously updates the cargo flow data and billing period data through the mapping relationship table, including: Performing a dot product operation on the historical consumption data of medical devices and the updated time decay factor to obtain a weighted sequence, inputting the weighted sequence into the output layer of the long short-term memory network, calculating the optimal billing period based on the output result, and generating settlement data including consumption summary, amount calculation, and billing period time limit based on the optimal billing period; Construct a two-dimensional mapping table containing cargo flow records and billing period data, establish a key-value pair index for the two-dimensional mapping table according to the cargo number, locate the target record in the two-dimensional mapping table through the key-value pair index, write the settlement data into the billing period field of the target record and update the corresponding cargo flow status.

8. A data processing device for a medical device digital supply chain consignment model, characterized in that: The device comprises: A multi-level traceability module is used to create consignment orders for medical devices, establish a multi-level traceability structure including primary product source information, secondary inventory status information, and tertiary flow direction information, generate a unique traceability identification code, split the traceability identification code into a product source identification segment, an inventory status identification segment, and a flow direction identification segment, establish a first association index between the product source identification segment and the inventory status identification segment, establish a second association index between the inventory status identification segment and the flow direction identification segment, and set a data integrity check; a consumption registration module, configured to retrieve the secondary inventory status information corresponding to the inventory status identification segment according to the first association index, register the consumption of the consignment inventory of the medical device, generate a consumption record including the consumption time and the consumption quantity, and update the consumption record to the tertiary flow direction information according to the second association index; The account period prediction module is used to establish a mapping relationship table between cargo flow data and account period data, retrieve the updated three-level flow direction information based on the traceability identification code, input the time series consumption data into the long short-term memory network, dynamically adjust the time decay factor using an adaptive mechanism, determine the fluctuation benchmark value by calculating the standard deviation of recent consumption data, and update the decay rate parameter in real time according to the fluctuation benchmark value, weight the historical data based on the updated time decay factor, predict the optimal account period and generate a settlement statement, and synchronously update the cargo flow data and account period data through the mapping relationship table.

9. 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 data processing method for the medical device digital supply chain consignment model according to 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 data processing method of the medical device digital supply chain consignment model according to any one of claims 1 to 7 are implemented.

Images