SPD medical consumable whole life cycle traceability management method and device

Abstract

The application discloses a kind of SPD medical consumables full life cycle traceability management method and device, belong to medical consumables management technical field, by using the material properties of each medical consumable, the data of each link is uniformly managed by constructing medical consumables digital twin model using the preset storage and transportation environment parameters and clinical use scene, avoid key information loss, can restore the complete use path of consumable, simultaneously, medical consumables digital twin model is visualized, can intuitively and clearly understand the use of consumable, avoid the possibility of manual recording error, and use medical consumables full life cycle intelligent prediction model to predict medical consumables real-time working condition data, to generate corresponding strategy adjustment instruction according to prediction result, adjust execution unit according to strategy adjustment instruction, can timely recall problem consumable, reduce the probability of medical risk and adverse event occurrence, facilitate application and promotion.

Description

Technical Field

[0001] This invention belongs to the field of medical consumables management technology, specifically relating to a method and device for full lifecycle traceability management of SPD medical consumables. Background Technology

[0002] Medical consumables lifecycle management refers to the traceable management of medical consumables from the design and manufacturing process to their disposal as medical waste or their disposal due to expiration. In the traditional medical consumables management system, suppliers have access to the production data of consumables, warehouses are responsible for the storage and entry / exit records of consumables, and various departments generate relevant data in the actual use process and in their interaction with the warehouse. In the existing technology, the supervision of medical consumables has shortcomings, such as (1) the problem of data silos: under the traditional management model, there is a lack of effective integration and sharing mechanisms for data between various links. The recording of the flow of consumables largely depends on manual operation. From the supplier manually filling out the form when shipping, to the warehouse manually entering the information again when receiving the goods, and then to the department manually registering the goods after receiving them, there is a possibility of human error in each link. (1) This leads to the loss of key information, making it difficult to restore the complete usage path of consumables and creating information silos; (2) Regulatory lag: In the traditional model, the expiration date warning of consumables mainly relies on manual periodic inventory, which not only consumes a lot of manpower and time costs, but is also prone to omissions and oversights. If consumables nearing their expiration date are not discovered in time and are misused, it will seriously threaten the health and safety of patients. Moreover, the existing technology lacks information traceability methods, making it difficult to quickly and accurately locate the specific flow of all problematic consumables in a short period of time, which leads to delays in the best time for recall, thereby increasing the probability of medical risks and adverse events.

[0003] Therefore, how to provide an effective technical solution to address the problems of data silos and regulatory lag in existing technologies has become an urgent problem to be solved in existing technologies. Summary of the Invention

[0004] The purpose of this invention is to provide a method and device for full lifecycle traceability management of SPD medical consumables, in order to solve the above-mentioned problems existing in the prior art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for full lifecycle traceability management of SPD medical consumables, including: The material properties, preset storage and transportation environment parameters, and clinical usage scenarios of each medical consumable are obtained. Based on the material properties, preset storage and transportation environment parameters, and clinical usage scenarios, a digital twin model of the medical consumable is constructed. The digital twin model of the medical consumable is then driven to run a multi-condition simulation to obtain a simulation dataset. The TS fuzzy forest regression model was trained using a simulation dataset to obtain an intelligent prediction model for the entire life cycle of medical consumables. The intelligent prediction model for the entire life cycle of medical consumables is used to take real-time collected medical consumables operating condition data as input and output the predicted performance status of medical consumables at different stages and the interpretability rules of key variables related to the predicted performance status. Acquire real-time operating condition data of medical consumables, preprocess the real-time operating condition data of medical consumables to obtain preprocessed real-time operating condition data of medical consumables, use the intelligent prediction model of the whole life cycle of medical consumables to predict the preprocessed real-time operating condition data of medical consumables, and obtain performance risk prediction results and key variable interpretability rules. Based on the performance risk prediction results and the interpretability rules of key variables, policy adjustment instructions with causal relationships are obtained. These policy adjustment instructions are then sent to the corresponding execution units so that the execution units can adjust their policies before the risk occurs.

[0006] In one possible design, the digital twin model of the medical consumables includes a logistics stress simulation sub-model and a clinical use risk simulation sub-model; the construction of the digital twin model based on material properties, preset storage and transportation environment parameters, and clinical use scenarios drives the digital twin model to perform multi-condition simulation to obtain a simulation dataset, including: Based on preset storage and transportation environment parameters and material properties, a logistics stress simulation sub-model is constructed using finite element analysis. The logistics stress simulation sub-model is used to characterize the cumulative fatigue damage caused by medical consumables under different storage and transportation environments. A clinical use risk simulation sub-model is constructed based on clinical use scenarios. The clinical use risk simulation sub-model is used to characterize the probability of non-standard operation affecting the functional reliability of medical consumables under different operating procedures. Obtain operating parameters under different working conditions, and based on these parameters, drive the logistics stress simulation sub-model and the clinical use risk simulation sub-model to perform multi-condition simulations and obtain simulation results. A simulation dataset is constructed based on the operating parameters under different working conditions and the corresponding simulation results.

[0007] In one possible design, a TS fuzzy forest regression model is trained using a simulation dataset to obtain an intelligent prediction model for the entire lifecycle of medical consumables, including: Randomly sample the simulation dataset to obtain multiple training subsets. Filter and divide these training subsets to obtain a clear set. Use the TS fuzzy inference model to infer the relationships in the simulation dataset. Based on the relationships in the simulation dataset, a TS fuzzy regression tree is constructed for each training subset. All TS fuzzy regression trees are combined to obtain the TS fuzzy forest regression model. The weighted weights of each TS fuzzy regression tree output are calculated based on the ridge regression method. The TS fuzzy forest regression model is then summed based on the weighted weights to obtain an intelligent prediction model for the entire life cycle of medical consumables.

[0008] In one possible design, multiple training subsets are filtered and partitioned to obtain a clarifiable set. The TS fuzzy inference model is then used to infer the relationships in the simulation dataset, including: The mean squared error of the training subset is calculated, and the splitting node is determined based on the mean squared error of the training subset. The training subset is then split using the splitting node to obtain two sets, namely the left subset and the right subset. The data in the training subset is traversed, and the loss function value of the training subset is calculated based on the left and right subsets. The expression for the loss function value is as follows: ; In the formula, The value of the loss function. To minimize the parameter function, we need to find the set of independent variables that minimize the function. This is the mean square error value. For the left subset, It is the right subset; Repeat the above steps until the loss function value is less than the preset loss threshold to obtain a clear set. Input the clear set into the TS fuzzy inference model for inference, calculate the weights according to the preset membership function, obtain the upper part weights and lower part weights, and obtain the relationship in the simulation dataset based on the obtained upper part weights and lower part weights.

[0009] In one possible design, the real-time operating data of medical consumables is preprocessed to obtain preprocessed real-time operating data of medical consumables, including: Data cleaning is performed on the real-time operating data of medical consumables to remove outliers and blank values, resulting in cleaned real-time operating data of medical consumables. Based on preset standardization rules, the real-time operating data of cleaned medical consumables is standardized to obtain standardized real-time operating data of medical consumables. The standardized real-time operating data of medical consumables is normalized to obtain normalized real-time operating data of medical consumables.

[0010] In one possible design, based on performance risk prediction results and key variable interpretability rules, causal policy adjustment instructions are derived, including: The interpretability rules of key variables are analyzed and extracted to obtain the root causes of performance risks and their corresponding impact weights; An initial control strategy is obtained by matching the pre-built root cause strategy mapping database with the root cause variables and their corresponding influence weights. The initial control strategy is optimized based on the preset cost to obtain a strategy adjustment instruction, which includes the target object, specific operation, and causal basis.

[0011] In one possible design, after the execution unit adjusts its strategy before the risk occurs, it also includes: Obtain the execution results after strategy adjustment, and construct a global consumable circulation knowledge graph based on real-time medical consumable operating data, strategy adjustment instructions, and execution results; Big data analysis is performed on the global consumables circulation knowledge graph to obtain analysis results. Based on the analysis results, inventory optimization strategies and proactive replenishment strategies are generated. The big data analysis includes demand time-series forecasting and circulation anomaly diagnosis and early warning.

[0012] Secondly, the present invention provides an SPD medical consumable full life cycle traceability management device, comprising: The simulation unit is used to acquire the material properties, preset storage and transportation environment parameters, and clinical usage scenarios of each medical consumable. Based on the material properties, preset storage and transportation environment parameters, and clinical usage scenarios, it constructs a digital twin model of the medical consumable and drives the digital twin model of the medical consumable to perform multi-condition simulation to obtain a simulation dataset. The model training unit is used to train the TS fuzzy forest regression model using a simulation dataset to obtain an intelligent prediction model for the entire life cycle of medical consumables. The intelligent prediction model for the entire life cycle of medical consumables is used to take real-time collected medical consumables operating condition data as input and output the predicted performance status of medical consumables at different stages and the key variables related to the predicted performance status. The real-time prediction unit is used to acquire real-time operating data of medical consumables, preprocess the real-time operating data of medical consumables to obtain preprocessed real-time operating data of medical consumables, and use the intelligent prediction model of the entire life cycle of medical consumables to predict the preprocessed real-time operating data of medical consumables to obtain performance risk prediction results and key variables. The strategy adjustment unit is used to obtain strategy adjustment instructions with causal relationships based on performance risk prediction results and key variables, and send the strategy adjustment instructions to the corresponding execution unit so that the execution unit can adjust the strategy before the risk occurs.

[0013] Thirdly, the present invention provides a computer device comprising a memory, a processor, and a transceiver connected in sequence and in communication, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the SPD medical consumables full lifecycle traceability management method as described in the first aspect above.

[0014] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, perform the SPD medical consumables full lifecycle traceability management method as described in the first aspect above.

[0015] Fifthly, the present invention provides a computer program product containing instructions that, when the instructions are executed on a computer, cause the computer to perform the SPD medical consumables full lifecycle traceability management method as described in the first aspect above.

[0016] The beneficial effects of this invention are as follows: This invention discloses a method and device for full lifecycle traceability management of SPD medical consumables. It acquires the material attributes, preset storage and transportation environment parameters, and clinical usage scenarios of each medical consumable, and constructs a digital twin model of the medical consumables based on these parameters. The digital twin model is then driven to perform multi-condition simulation to obtain a simulation dataset. This dataset is used to train a TS fuzzy forest regression model, resulting in an intelligent prediction model for the full lifecycle of medical consumables. This intelligent prediction model takes real-time collected medical consumable operating condition data as input and outputs a medical consumable lifecycle prediction model. By using the predicted performance status values ​​of consumables at different stages and the interpretability rules of key variables related to these predicted performance status values, real-time operating condition data of medical consumables is obtained. The real-time operating condition data of medical consumables is preprocessed to obtain preprocessed real-time operating condition data of medical consumables. The preprocessed real-time operating condition data of medical consumables is then predicted using a full life cycle intelligent prediction model of medical consumables to obtain performance risk prediction results and interpretability rules of key variables. Based on the performance risk prediction results and interpretability rules of key variables, a strategy adjustment instruction with causal relationship is obtained. The strategy adjustment instruction is sent to the corresponding execution unit so that the execution unit can adjust the strategy before the risk occurs. This invention constructs a digital twin model of medical consumables by using the material properties of each consumable, preset storage and transportation environment parameters, and clinical usage scenarios. This model unifies the management of data from each stage, avoids the loss of critical information, and restores the complete usage path of the consumables. Furthermore, the digital twin model is visualized, providing a clear and intuitive understanding of the consumables' usage, avoiding the possibility of errors from manual recording. A smart prediction model covering the entire lifecycle of medical consumables is used to predict real-time operating data, generating corresponding strategy adjustment instructions based on the prediction results. Adjusting the execution unit according to these instructions allows for the timely recall of problematic consumables, reducing the probability of medical risks and adverse events, and facilitating application and promotion. Attached Figure Description

[0017] Figure 1 A flowchart illustrating a method for full lifecycle traceability management of SPD medical consumables provided in this embodiment of the invention; Figure 2 This is a structural diagram of an SPD medical consumable full life cycle traceability management device provided in an embodiment of the present invention. Detailed Implementation

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0019] It should be understood that although the terms first, second, etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, without departing from the scope of the exemplary embodiments of the invention.

[0020] It should be understood that the term "and / or" that may appear in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, and A and B exist simultaneously. The term " / and" that may appear in this document describes another relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this document generally indicates that the related objects before and after it are in an "or" relationship.

[0021] Example: like Figure 1 As shown, the first aspect of this embodiment provides a method for full lifecycle traceability management of SPD medical consumables, which can be executed, but is not limited to, by a computer device or virtual machine with certain computing resources, such as a personal computer or smartphone, or by a virtual machine; the method for full lifecycle traceability management of SPD medical consumables includes, but is not limited to, the following steps: S1. Obtain the material properties, preset storage and transportation environment parameters, and clinical usage scenarios of each medical consumable, and construct a digital twin model of the medical consumable based on the material properties, preset storage and transportation environment parameters, and clinical usage scenarios. Drive the digital twin model of the medical consumable to perform multi-condition simulation to obtain a simulation dataset. It should be noted that the material properties of each medical consumable in this embodiment include, but are not limited to, the original material composition, physical and mechanical properties, chemical characteristics, and packaging specifications of the medical consumable. The preset storage and transportation environment parameters include, but are not limited to, preset temperature, humidity, vibration spectrum, impact events, and stacking pressure. The clinical use scenarios include, but are not limited to, preset operating procedures and contact media. Among them, the original material composition includes polymer type and metal material, physical and mechanical properties can be exemplified by tensile strength and fatigue characteristics, chemical properties can be exemplified by compatibility with drugs and oxidative stability, packaging specifications include packaging materials and sealing methods, vibration spectrum is used to simulate transportation vehicles, impact events are used to simulate loading and unloading events, preset operating procedures include unpacking, assembly, and usage time, and contact media include blood and / or drugs. The digital twin model of medical consumables includes a logistics stress simulation sub-model and a clinical use risk simulation sub-model.

[0022] Among these methods, a digital twin model of medical consumables is constructed based on material properties, preset storage and transportation environment parameters, and clinical usage scenarios. This model is then used to drive multi-condition simulations, resulting in a simulation dataset, including: S11. Based on preset storage and transportation environment parameters and material properties, a logistics stress simulation sub-model is constructed using finite element analysis. The logistics stress simulation sub-model is used to characterize the cumulative fatigue damage caused by medical consumables under different storage and transportation environments. S12. Construct a clinical use risk simulation sub-model based on clinical use scenarios. The clinical use risk simulation sub-model is used to characterize the probability of non-standard operation affecting the functional reliability of medical consumables under different operating procedures. S13. Obtain operating parameters under different working conditions, and based on the operating parameters under different working conditions, drive the logistics stress simulation sub-model and the clinical use risk simulation sub-model to perform multi-working-condition simulation and obtain the simulation results; S14. Construct a simulation dataset based on the operating parameters under different working conditions and the corresponding simulation results.

[0023] In practice, based on preset storage and transportation environment parameters and the material properties of medical consumables, a logistics stress simulation sub-model is constructed using finite element analysis. Finite element analysis simulates the real physical system using mathematical approximation methods to obtain the logistics stress simulation sub-model. This model clearly shows the losses that medical consumables may experience under different storage and transportation environments. A clinical use risk simulation sub-model is also constructed based on clinical usage scenarios. This model reveals the probability of non-standard operations affecting the function of medical consumables under different clinical procedures. By acquiring operating parameters under different operating conditions and preset orthogonal experimental design data, multi-condition simulations are conducted to obtain simulation results. A simulation dataset is constructed using the operating parameters under different operating conditions and the corresponding simulation results, and this dataset is used as training data for subsequent model training.

[0024] S2. The TS fuzzy forest regression model is trained using a simulation dataset to obtain an intelligent prediction model for the entire life cycle of medical consumables. The intelligent prediction model for the entire life cycle of medical consumables is used to take real-time collected medical consumables operating condition data as input and output the predicted performance status of medical consumables at different stages and the interpretability rules of key variables related to the predicted performance status. Specifically, the TS fuzzy forest regression model is trained using a simulation dataset to obtain an intelligent prediction model for the entire lifecycle of medical consumables, including: S21. Randomly sample the simulation dataset to obtain multiple training subsets. Filter and divide the multiple training subsets to obtain a clear set. Use the TS fuzzy inference model to infer the relationship in the simulation dataset. S22. Based on the relationships in the simulation dataset, construct a TS fuzzy regression tree for each training subset, and combine all the TS fuzzy regression trees to obtain the TS fuzzy forest regression model; S23. Calculate the weighted weights of each TS fuzzy regression tree output based on the ridge regression method, and perform weighted summation on the TS fuzzy forest regression model based on the weighted weights to obtain the intelligent prediction model for the entire life cycle of medical consumables.

[0025] It should be noted that ridge regression is a biased estimation regression method for dealing with multicollinearity. By introducing an L2 regularization term on top of the traditional least squares method, it sacrifices some unbiasedness in exchange for higher numerical stability and computational efficiency of the regression coefficients, thus obtaining a more reliable model when the data contains collinearity or ill-conditioned matrices. The key variable interpretability rules refer to the key influencing factors and their contribution that are related to the performance status prediction value and have a causal relationship. For example, when the performance status prediction value is aseptic packaging damage, the key variable interpretability rules include the peak value of transportation vibration acceleration and the amplitude of storage temperature fluctuations.

[0026] In practice, the simulation dataset is randomly sampled to obtain multiple training subsets with features. These subsets are then filtered and divided to obtain a clear set. The TS fuzzy inference model is used to infer the relationships within the simulation dataset. Based on these relationships, a TS fuzzy regression tree is constructed for each training subset. All TS fuzzy regression trees are combined to obtain a TS fuzzy forest regression model. Ridge regression is used to calculate the weighted weights output by each TS fuzzy regression tree. The expression for the weighted weights is as follows: In the formula, For weighted weights, The matrix output for each TS fuzzy regression tree. For transpose, For regularization parameters, It is the identity matrix. Given the true value vector, the TS fuzzy forest regression model is weighted and summed based on the weighted values ​​to obtain an intelligent prediction model for the entire life cycle of medical consumables.

[0027] Furthermore, in step S21, multiple training subsets are filtered and divided to obtain a clear set. The TS fuzzy inference model is then used to infer the relationships in the simulation dataset, including: S21.1. Calculate the mean squared error value of the training subset, and determine the splitting node based on the mean squared error value of the training subset, so as to split the training subset using the splitting node to obtain two sets, the two sets being the left subset and the right subset; S21.2. Traverse the data in the training subset and calculate the loss function value of the training subset based on the left and right subsets. The expression for the loss function value is: ; In the formula, The value of the loss function. To minimize the parameter function, we need to find the set of independent variables that minimize the function. This is the mean square error value. For the left subset, It is the right subset; S21.3. Repeat steps S21.1 to S21.2 until the loss function value is less than the preset loss threshold to obtain a clear set. Input the clear set into the TS fuzzy inference model for inference, calculate the weights according to the preset membership function, obtain the upper part weights and lower part weights, and obtain the relationship in the simulation dataset based on the obtained upper part weights and lower part weights.

[0028] It should be noted that the membership function is preset to a Gaussian function in this embodiment; the relationship in the simulation dataset in this embodiment can be interpreted as a set of inference rules between input variables and output performance states. If the input variable satisfies a certain condition, the output performance state will be a certain value, which is specifically used to characterize the causal relationship implied in the simulation data.

[0029] S3. Obtain real-time operating data of medical consumables, preprocess the real-time operating data of medical consumables to obtain preprocessed real-time operating data of medical consumables, use the intelligent prediction model of the entire life cycle of medical consumables to predict the preprocessed real-time operating data of medical consumables, and obtain performance risk prediction results and key variable interpretability rules. It should be noted that the performance risk prediction results are the predicted performance status values ​​of medical consumables at different stages, and the key variable interpretability rule is the key variable that affects the predicted performance status value.

[0030] Specifically, in step S3, the real-time operating data of medical consumables is preprocessed to obtain preprocessed real-time operating data of medical consumables, including: S31. Perform data cleaning on the real-time operating data of medical consumables to remove outliers and blank values ​​from the real-time operating data of medical consumables, and obtain cleaned real-time operating data of medical consumables. S32. Based on preset standardization rules, standardize the real-time operating data of the cleaned medical consumables to obtain standardized real-time operating data of the medical consumables; S33. Normalize the standardized real-time operating data of medical consumables to obtain normalized real-time operating data of medical consumables.

[0031] In practice, the real-time operating data of medical consumables is cleaned to remove noise and outliers. The data is then standardized according to pre-defined standardization rules to unify its format for easier processing. The standardized data is then normalized to eliminate differences in different dimensions and improve the accuracy of medical consumables prediction.

[0032] S4. Based on the performance risk prediction results and the interpretability rules of key variables, obtain the strategy adjustment instructions with causal relationships, and send the strategy adjustment instructions to the corresponding execution units so that the execution units can adjust the strategy before the risk occurs.

[0033] Specifically, in step S4, based on the performance risk prediction results and the interpretability rules of key variables, causal policy adjustment instructions are obtained, including: S41. Analyze and extract the interpretability rules of key variables to obtain the root causes of performance risks and their corresponding impact weights; S42. Based on the pre-built root cause strategy mapping database, the root cause variables and their corresponding influence weights are matched to obtain the initial regulation strategy; S43. Optimize the initial control strategy based on the preset cost to obtain a strategy adjustment instruction, which includes the target object, specific operation, and causal basis.

[0034] It should be noted that the root cause strategy mapping database is a database of root cause variables and corresponding control strategies set manually based on historical experience. By parsing and extracting the obtained root cause variables and their corresponding influence weights, the root cause variables and their corresponding influence weights are matched to obtain the initial control strategy. The initial control strategy is optimized based on the set cost and other data to make it more suitable for the real-time situation of medical consumables, thereby obtaining the strategy adjustment instruction. Based on the strategy adjustment instruction, the target object (i.e., the execution unit) to be controlled can be clearly known, as well as the specific operation to be performed on the target object and why the adjustment operation is performed.

[0035] In one possible design, after the execution unit adjusts its strategy before the risk occurs, it also includes: Obtain the execution results after strategy adjustment, and construct a global consumable circulation knowledge graph based on real-time medical consumable operating data, strategy adjustment instructions, and execution results; Big data analysis is performed on the global consumables circulation knowledge graph to obtain analysis results. Based on the analysis results, inventory optimization strategies and proactive replenishment strategies are generated. The big data analysis includes demand time-series forecasting and circulation anomaly diagnosis and early warning.

[0036] It should be noted that big data analysis includes demand time-series forecasting and circulation anomaly diagnosis and early warning. An LSTM (Long Short-Term Memory) model trained on a historical consumables dataset is used to perform demand time-series forecasting and anomaly diagnosis on the global consumables circulation knowledge graph. Based on the forecast and diagnosis results, inventory optimization strategies and proactive replenishment strategies are generated. Based on an AI (Artificial Intelligence) big model, the diagnosis results are matched with a pre-built early warning database to issue corresponding early warnings. The historical consumables dataset is a collection composed of historical consumables data that has been manually labeled with labels, including demand data and anomaly data.

[0037] like Figure 2 As shown, the second aspect of this embodiment provides an SPD medical consumable full lifecycle traceability management device, including: The simulation unit is used to acquire the material properties, preset storage and transportation environment parameters, and clinical usage scenarios of each medical consumable. Based on the material properties, preset storage and transportation environment parameters, and clinical usage scenarios, it constructs a digital twin model of the medical consumable and drives the digital twin model of the medical consumable to perform multi-condition simulation to obtain a simulation dataset. The model training unit is used to train the TS fuzzy forest regression model using a simulation dataset to obtain an intelligent prediction model for the entire life cycle of medical consumables. The intelligent prediction model for the entire life cycle of medical consumables is used to take real-time collected medical consumables operating condition data as input and output the predicted performance status of medical consumables at different stages and the key variables related to the predicted performance status. The real-time prediction unit is used to acquire real-time operating data of medical consumables, preprocess the real-time operating data of medical consumables to obtain preprocessed real-time operating data of medical consumables, and use the intelligent prediction model of the entire life cycle of medical consumables to predict the preprocessed real-time operating data of medical consumables to obtain performance risk prediction results and key variables. The strategy adjustment unit is used to obtain strategy adjustment instructions with causal relationships based on performance risk prediction results and key variables, and send the strategy adjustment instructions to the corresponding execution unit so that the execution unit can adjust the strategy before the risk occurs.

[0038] The working process, working details and technical effects of the SPD medical consumables full life cycle traceability management device provided in the second aspect of this embodiment can be found in the SPD medical consumables full life cycle traceability management method described in the first aspect, and will not be repeated here.

[0039] This embodiment provides a computer device including a memory, a processor, and a transceiver connected in sequence. The memory stores a computer program, the transceiver sends and receives messages, and the processor reads the computer program to execute the SPD medical consumables full lifecycle traceability management method as described in the first aspect. Specifically, the memory may include, but is not limited to, random-access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out (FIFO) memory, and / or first-in-last-out (FILO) memory, etc.; the processor may include, but is not limited to, an STM32F105 series microprocessor. Furthermore, the computer device may also include, but is not limited to, a power module, a display screen, and other necessary components.

[0040] The working process, working details and technical effects of the aforementioned computer equipment provided in the third aspect of this embodiment can be found in the SPD medical consumables full life cycle traceability management method described in the first aspect, and will not be repeated here.

[0041] The fourth aspect of this embodiment provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, and when the instructions are executed on a computer, the SPD medical consumables full lifecycle traceability management method as described in the first aspect is performed. The computer-readable storage medium refers to a data storage carrier, and may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or Memory Sticks, etc. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0042] The working process, working details and technical effects of the aforementioned computer-readable storage medium provided in the fourth aspect of this embodiment can be found in the SPD medical consumables full life cycle traceability management method described in the first aspect, and will not be repeated here.

[0043] The fifth aspect of this embodiment provides a computer program product, including a computer program or instructions, which, when executed by a computer, are used to implement the SPD medical consumable full life cycle traceability management method as described in the first aspect.

[0044] The working process, working details, and technical effects of the aforementioned computer program product provided in this embodiment can be found in the SPD medical consumables full life cycle traceability management method described in the first aspect, and will not be repeated here.

[0045] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for full lifecycle traceability management of SPD medical consumables, characterized in that, include: The material properties, preset storage and transportation environment parameters, and clinical usage scenarios of each medical consumable are obtained. Based on the material properties, preset storage and transportation environment parameters, and clinical usage scenarios, a digital twin model of the medical consumable is constructed. The digital twin model of the medical consumable is then driven to run a multi-condition simulation to obtain a simulation dataset. The TS fuzzy forest regression model was trained using a simulation dataset to obtain an intelligent prediction model for the entire life cycle of medical consumables. The intelligent prediction model for the entire life cycle of medical consumables is used to take real-time collected medical consumables operating condition data as input and output the predicted performance status of medical consumables at different stages and the interpretability rules of key variables related to the predicted performance status. Acquire real-time operating condition data of medical consumables, preprocess the real-time operating condition data of medical consumables to obtain preprocessed real-time operating condition data of medical consumables, use the intelligent prediction model of the whole life cycle of medical consumables to predict the preprocessed real-time operating condition data of medical consumables, and obtain performance risk prediction results and key variable interpretability rules. Based on the performance risk prediction results and the interpretability rules of key variables, policy adjustment instructions with causal relationships are obtained. These policy adjustment instructions are then sent to the corresponding execution units so that the execution units can adjust their policies before the risk occurs.

2. The method for full lifecycle traceability management of SPD medical consumables according to claim 1, characterized in that, The digital twin model of medical consumables includes a logistics stress simulation sub-model and a clinical use risk simulation sub-model. The digital twin model of medical consumables is constructed based on material properties, preset storage and transportation environment parameters, and clinical use scenarios. This drives the digital twin model to perform multi-condition simulations, resulting in a simulation dataset, including: Based on preset storage and transportation environment parameters and material properties, a logistics stress simulation sub-model is constructed using finite element analysis. The logistics stress simulation sub-model is used to characterize the cumulative fatigue damage caused by medical consumables under different storage and transportation environments. A clinical use risk simulation sub-model is constructed based on clinical use scenarios. The clinical use risk simulation sub-model is used to characterize the probability of non-standard operation affecting the functional reliability of medical consumables under different operating procedures. Obtain operating parameters under different working conditions, and based on these parameters, drive the logistics stress simulation sub-model and the clinical use risk simulation sub-model to perform multi-condition simulations and obtain simulation results. A simulation dataset is constructed based on the operating parameters under different working conditions and the corresponding simulation results.

3. The method for full lifecycle traceability management of SPD medical consumables according to claim 1, characterized in that, The TS fuzzy forest regression model was trained using a simulation dataset to obtain an intelligent prediction model for the entire lifecycle of medical consumables, including: Randomly sample the simulation dataset to obtain multiple training subsets. Filter and divide these training subsets to obtain a clear set. Use the TS fuzzy inference model to infer the relationships in the simulation dataset. Based on the relationships in the simulation dataset, a TS fuzzy regression tree is constructed for each training subset. All TS fuzzy regression trees are combined to obtain the TS fuzzy forest regression model. The weighted weights of each TS fuzzy regression tree output are calculated based on the ridge regression method. The TS fuzzy forest regression model is then summed based on the weighted weights to obtain an intelligent prediction model for the entire life cycle of medical consumables.

4. The method for full lifecycle traceability management of SPD medical consumables according to claim 3, characterized in that, Multiple training subsets are filtered and divided to obtain a clear set. The TS fuzzy inference model is used to infer the relationships in the simulation dataset, including: The mean squared error of the training subset is calculated, and the splitting node is determined based on the mean squared error of the training subset. The training subset is then split using the splitting node to obtain two sets, namely the left subset and the right subset. The data in the training subset is traversed, and the loss function value of the training subset is calculated based on the left and right subsets. The expression for the loss function value is as follows: ； In the formula, The value of the loss function. To minimize the parameter function, we need to find the set of independent variables that minimize the function. This is the mean square error value. For the left subset, It is the right subset; Repeat the above steps until the loss function value is less than the preset loss threshold to obtain a clear set. Input the clear set into the TS fuzzy inference model for inference, calculate the weights according to the preset membership function, obtain the upper part weights and lower part weights, and obtain the relationship in the simulation dataset based on the obtained upper part weights and lower part weights.

5. The method for full lifecycle traceability management of SPD medical consumables according to claim 1, characterized in that, The real-time operating data of medical consumables is preprocessed to obtain preprocessed real-time operating data of medical consumables, including: Data cleaning is performed on the real-time operating data of medical consumables to remove outliers and blank values, resulting in cleaned real-time operating data of medical consumables. Based on preset standardization rules, the real-time operating data of cleaned medical consumables is standardized to obtain standardized real-time operating data of medical consumables. The standardized real-time operating data of medical consumables is normalized to obtain normalized real-time operating data of medical consumables.

6. The method for full lifecycle traceability management of SPD medical consumables according to claim 1, characterized in that, Based on performance risk prediction results and key variable interpretability rules, policy adjustment instructions with causal relationships are derived, including: The interpretability rules of key variables are analyzed and extracted to obtain the root causes of performance risks and their corresponding impact weights; An initial control strategy is obtained by matching the pre-built root cause strategy mapping database with the root cause variables and their corresponding influence weights. The initial control strategy is optimized based on the preset cost to obtain a strategy adjustment instruction, which includes the target object, specific operation, and causal basis.

7. The method for full lifecycle traceability management of SPD medical consumables according to claim 1, characterized in that, After the execution unit adjusts its strategy before the risk occurs, it also includes: Obtain the execution results after strategy adjustment, and construct a global consumable circulation knowledge graph based on real-time medical consumable operating data, strategy adjustment instructions, and execution results; Big data analysis is performed on the global consumables circulation knowledge graph to obtain analysis results. Based on the analysis results, inventory optimization strategies and proactive replenishment strategies are generated. The big data analysis includes demand time-series forecasting and circulation anomaly diagnosis and early warning.

8. A device for full lifecycle traceability management of SPD medical consumables, used to implement the method according to any one of claims 1 to 7, characterized in that, include: The simulation unit is used to acquire the material properties, preset storage and transportation environment parameters, and clinical usage scenarios of each medical consumable. Based on the material properties, preset storage and transportation environment parameters, and clinical usage scenarios, it constructs a digital twin model of the medical consumable and drives the digital twin model of the medical consumable to perform multi-condition simulation to obtain a simulation dataset. The model training unit is used to train the TS fuzzy forest regression model using a simulation dataset to obtain an intelligent prediction model for the entire life cycle of medical consumables. The intelligent prediction model for the entire life cycle of medical consumables is used to take real-time collected medical consumables operating condition data as input and output the predicted performance status of medical consumables at different stages and the key variables related to the predicted performance status. The real-time prediction unit is used to acquire real-time operating data of medical consumables, preprocess the real-time operating data of medical consumables to obtain preprocessed real-time operating data of medical consumables, and use the intelligent prediction model of the entire life cycle of medical consumables to predict the preprocessed real-time operating data of medical consumables to obtain performance risk prediction results and key variables. The strategy adjustment unit is used to obtain strategy adjustment instructions with causal relationships based on performance risk prediction results and key variables, and send the strategy adjustment instructions to the corresponding execution unit so that the execution unit can adjust the strategy before the risk occurs.

9. A computer device, characterized in that, The device includes a memory, a processor, and a transceiver that are sequentially and communicatively connected. The memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer programs and execute the SPD medical consumables full lifecycle traceability management method as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or the instructions are executed by the computer, they implement the SPD medical consumables full life cycle traceability management method as described in any one of claims 1 to 7.

Images