Detection consumable allocation method and system based on comprehensive efficiency optimization, and storage medium

Abstract

The application relates to the technical field of laboratory automation management and data processing, in particular to a detection consumable allocation method and system based on comprehensive efficiency optimization and a storage medium, a predicted sample quantity in a future early warning period is output by calling a sample quantity prediction model, and a single-specification reservation coefficient is dynamically determined accordingly, so that safe inventory control considering current task execution and future demand shortage prevention is realized; on the basis, a plurality of candidate allocation schemes are generated within the limitation, multi-dimensional efficiency calculation is carried out in combination with a single-specification unit cost, a to-be-detected sample quantity, a fixed control site quantity and real-time residual effective time, a consumable cost performance, actual utilization rate and inventory turnover efficiency obtained are fused into a comprehensive efficiency value for final decision, the limitation of traditional single-dimensional extensive allocation is avoided, on the premise of meeting the absolute well site demand of single detection, the overall high procurement cost is reduced, well site vacancy waste is reduced and near-efficiency period consumables are accelerated.

Description

Technical Field

[0001] This application relates to the field of laboratory automation management and data processing technology, and more specifically, to a method, system and storage medium for distributing testing consumables based on comprehensive efficiency optimization. Background Technology

[0002] With the increasing automation of clinical testing and laboratories, the refined management of testing consumables such as reagent kits and reaction plates has become a crucial aspect of reducing operating costs and ensuring the continuity of testing tasks. In actual testing scenarios, consumables typically exist in various specifications and have strict expiration dates.

[0003] First, existing consumable allocation methods rely heavily on manual experience-based assessment. However, when faced with complex testing needs and fluctuating inventory levels, these methods typically only round up the specifications based on the current number of samples to be tested, failing to consider the fixed control positions required during testing, or the vacancy rate of test wells under different specification combinations. This results in the underutilization of effective test wells, leading to resource waste. Second, the unit cost per person for testing consumables often decreases as packaging size increases. Existing allocation logic often lacks analysis of the unit cost per specification, failing to balance reducing well waste with lower procurement costs. In practice, it is common to requisition large quantities of higher-priced, smaller-specification consumables to avoid a small number of wasted wells, resulting in high overall operating costs and a limited scope for cost optimization. Furthermore, existing management rules are mostly reactive allocations, meaning that requisition is based solely on existing inventory and current tasks, failing to incorporate historical sample size characteristics to predict future testing needs. This results in reserved quantities often being fixed proportions based on experience. When facing potential sample peaks in the future, there is a risk of consumable shortages, which can affect the normal conduct of testing tasks. Conversely, during periods of low demand, consumables nearing their expiration date may not be used up in time, leading to their expiration and disposal.

[0004] Therefore, finding a suitable method for distributing testing consumables is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] Based on this, in view of the technical problems existing in the prior art, such as the single distribution rules of testing consumables, waste of orifice positions, lack of inventory reservation, and easy expiration and scrapping of near-expiry consumables, the purpose of this invention is to provide a testing consumable distribution method, system and computer-readable storage medium based on comprehensive efficiency optimization. It aims to improve the orifice utilization rate and inventory turnover efficiency of consumables while reducing the overall cost of consumable use by introducing a sample prediction mechanism and a multi-dimensional evaluation model.

[0006] Firstly, this application provides a method for allocating testing consumables based on comprehensive efficiency optimization, applicable to testing consumables allocation scenarios. The method includes the following steps: The system obtains the number of samples to be tested, the number of fixed control positions, historical sample size characteristics, and current status data for the current testing task. The current status data includes the unit cost per specification of each consumable, real-time inventory balance, and real-time remaining effective time. The sample size prediction model is called to analyze the characteristics of historical sample size, and the predicted sample size in the future warning period is output. Based on the predicted sample size, the single specification reservation coefficient of each specification of consumable is determined. The total number of test positions is determined by combining the number of samples to be tested and the number of fixed control positions. The inventory safety requirement and the reserve requirement are determined by combining the real-time inventory balance, the single specification reservation coefficient and the predicted sample size, so as to construct the constraints for consumable allocation. Under the premise of meeting the constraints, multiple candidate allocation schemes are generated, and each candidate allocation scheme consists of the expected usage quantity of consumables of each specification. Based on the expected usage quantity in each of the candidate allocation schemes, and combined with the unit cost per specification, the number of samples to be tested, the number of fixed control positions, and the real-time remaining effective time, multiple evaluation indicators are calculated to obtain the consumable cost-effectiveness, actual utilization rate, and inventory turnover efficiency corresponding to each candidate allocation scheme. The cost-effectiveness of the consumables, the actual utilization rate, and the inventory turnover efficiency are comprehensively calculated to obtain the comprehensive efficiency value of each candidate allocation scheme. Based on the comprehensive efficiency value, the target allocation scheme is determined among the candidate allocation schemes to output the corresponding consumable allocation instruction.

[0007] Furthermore, the historical sample size features include core time-series features and time-period features. The core time-series features are the continuous historical sample size within a preset time window, and the time-period features include weekday identifiers, week identifiers, and month identifiers. The method of calling the sample size prediction model to analyze the characteristics of the historical sample size and output the predicted sample size for the future warning period includes: The core temporal features and the time periodic features are concatenated to construct a multidimensional input feature vector; The multidimensional input feature vector is input into the sample size prediction model constructed based on the improved LSTM network, and temporal relationships are extracted through at least two hidden layers of the sample size prediction model; wherein, the activation function of the hidden layer is the hyperbolic tangent function; The fully connected output layer of the sample size prediction model outputs continuous values ​​based on the extracted temporal relationships, which serve as the predicted sample size for the future warning period; wherein the activation function of the fully connected output layer is a linear adaptation function.

[0008] Furthermore, the calculation of multiple evaluation indicators yields the cost-effectiveness, actual utilization rate, and inventory turnover efficiency of each candidate allocation scheme, including: According to the formula Calculate the actual utilization rate ;in, The number of samples to be tested. The number of fixed control positions. This refers to the number of tests performed per specification for consumables of the corresponding specification. The expected usage quantity of the corresponding specification consumables; According to the formula Calculate the cost-effectiveness of the consumables ;in, This is the theoretical minimum amount of consumables required, calculated based on the number of samples to be tested, the number of fixed control sites, and the maximum number of doses of the largest-sized consumables. The unit cost corresponding to the largest specification consumable. The unit cost per specification of the corresponding consumable; According to the formula Calculate the inventory turnover efficiency ;in, This refers to the real-time remaining valid time for consumables of the corresponding specifications.

[0009] Furthermore, the process of determining the total testing position requirement by combining the number of samples to be tested and the number of fixed control positions, and determining the inventory safety requirement and reserve requirement by combining the real-time inventory balance, the single-specification reservation coefficient, and the predicted sample size, in order to construct the constraints for consumable allocation, includes: Construct the total detection bit constraint conditions corresponding to the total detection bit requirement. ; Construct the inventory constraints corresponding to the stated inventory safety requirements: ; Construct the reservation constraints corresponding to the reservation requirements: ;in, The expected usage quantity for the corresponding specification of consumables. This refers to the number of tests performed per specification for consumables of the corresponding specification. The number of samples to be tested. The number of fixed control positions. The real-time inventory balance for the corresponding specifications of consumables. The single-specification reserve coefficient for the corresponding consumable specifications. This refers to the maximum daily predicted sample size within the future early warning period, extracted based on the predicted sample size.

[0010] Further, determining the single-specification reservation coefficient for each specification of consumable based on the predicted sample size includes: Based on the predicted sample size, a first reservation coefficient and a second reservation coefficient are determined; wherein the first reservation coefficient is less than the second reservation coefficient. Determine whether the real-time remaining effective time of each specification of consumable is less than a preset near-expiration threshold; If it is less than, then the first reserve coefficient is configured for the consumable of that specification; if it is not less than, then the second reserve coefficient is configured for the consumable of that specification. The generation of multiple candidate allocation schemes also includes: Consumables of each specification are allocated priority sorted according to the real-time remaining effective time of each specification in ascending order; During the traversal search process to generate the candidate allocation scheme, the expected usage quantity is allocated first to the specifications of consumables with smaller remaining effective time in real time, based on the allocation priority.

[0011] Further, the step of comprehensively calculating the cost-effectiveness of the consumables, the actual utilization rate, and the inventory turnover efficiency to obtain the comprehensive efficiency value of each candidate allocation scheme, and determining the target allocation scheme from the candidate allocation schemes based on the comprehensive efficiency value, includes: The cost-effectiveness of the consumables, the actual utilization rate, and the inventory turnover efficiency are multiplied to obtain the comprehensive efficiency value corresponding to each candidate allocation scheme. From the multiple candidate allocation schemes, the candidate allocation scheme with the largest comprehensive efficiency value is selected as the preliminary target scheme; If the number of preliminary target schemes is one, then the preliminary target scheme is determined as the target allocation scheme; If there are multiple preliminary target schemes, the total cost of consumables for each preliminary target scheme is calculated based on the expected usage quantity and the unit cost per specification. From all the preliminary target schemes, the scheme with the lowest total cost of consumables is determined as the target allocation scheme. The total cost of consumables is determined according to the formula... Calculations show that The expected usage quantity for the corresponding specification of consumables. The unit cost per specification of the corresponding consumable.

[0012] Furthermore, the output corresponding to the consumable allocation instruction includes: Extract the preset number of test samples for each specification of consumables; Based on the real-time inventory balance of each specification of consumables, the single specification reservation coefficient, and the preset number of single specification testing units, calculate the total number of reserved testing positions for all specifications of consumables. Determine whether the total number of reserved detection positions is less than the maximum required detection positions; wherein, the maximum required detection positions are the sum of the maximum value in the predicted sample size and the number of fixed control positions; If the value is less than the target allocation scheme, a consumable shortage warning message will be output simultaneously when the consumable allocation instruction is output based on the target allocation scheme; the consumable shortage warning message is used to prompt the replenishment of consumables of a specific specification. After the consumable allocation instruction is executed, the real-time inventory balance corresponding to each consumable specification is synchronously deducted according to the expected usage quantity of each consumable specification in the target allocation scheme, so as to update the current status data.

[0013] Furthermore, the theoretical minimum consumable usage calculated based on the number of samples to be tested, the number of fixed control sites, and the maximum number of doses of the largest-sized consumable is... The calculation process includes: From the preset set of consumable specifications, select the consumable with the largest number of tests per specification as the target maximum specification consumable, and record the number of tests per specification corresponding to the target maximum specification consumable as the maximum specification consumable test count. ; Calculate the sum of the number of samples to be tested N and the number of fixed control sites C to obtain the theoretical total number of well sites required for a single test; Divide the theoretical total number of apertures by the number of units of the maximum specification consumable. The quotient obtained by division is then rounded up to obtain the theoretical minimum amount of consumables required. ; Theoretical minimum material usage Satisfies the calculation formula: ;in, This represents the function for rounding up.

[0014] Secondly, this application provides a testing consumables distribution system based on comprehensive efficiency optimization, used to apply the testing consumables distribution method based on comprehensive efficiency optimization as described in any one of the first aspects, the system comprising: The acquisition unit acquires the number of samples to be tested, the number of fixed control positions, historical sample size characteristics, and current status data for the current testing task. The current status data includes the unit cost per specification of each consumable, real-time inventory balance, and real-time remaining effective time. The calling unit calls the sample size prediction model to analyze the characteristics of historical sample size, outputs the predicted sample size in the future warning period, and determines the single specification reservation coefficient of each specification of consumable based on the predicted sample size. The construction unit determines the total detection position requirement by combining the number of samples to be tested and the number of fixed control positions, and determines the inventory safety requirement and reserve requirement by combining the real-time inventory balance, the single specification reservation coefficient and the predicted sample size, so as to construct the constraints for consumable allocation. Under the premise of meeting the constraints, multiple candidate allocation schemes are generated, and each candidate allocation scheme consists of the expected usage quantity of consumables of each specification. The evaluation unit calculates multiple evaluation indicators based on the expected usage quantity in each candidate allocation scheme, combined with the unit cost per specification, the number of samples to be tested, the number of fixed control positions, and the real-time remaining effective time, to obtain the consumable cost-effectiveness, actual utilization rate, and inventory turnover efficiency corresponding to each candidate allocation scheme. The output unit performs a comprehensive calculation on the cost-effectiveness of the consumables, the actual utilization rate, and the inventory turnover efficiency to obtain the comprehensive efficiency value of each candidate allocation scheme. Based on the comprehensive efficiency value, it determines the target allocation scheme from the candidate allocation schemes and outputs the corresponding consumable allocation instruction.

[0015] Thirdly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of the method as described in any of the first aspects.

[0016] Fourthly, this application provides a computer device including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method as described in any of the first aspects.

[0017] The beneficial effects of the testing consumable allocation method, system, and storage medium based on comprehensive efficiency optimization provided in this application are as follows: By calling the sample size prediction model to output the predicted sample size within the future warning period, and dynamically determining the single-specification reservation coefficient accordingly, a safety stock management system that balances current task execution and future demand to prevent shortages is achieved when constructing consumable allocation constraints in conjunction with real-time inventory. On this basis, multiple candidate allocation schemes are generated within the constraints, and multi-dimensional efficiency calculations are performed by combining the unit cost of a single specification, the number of samples to be tested, the number of fixed control positions, and the real-time remaining effective time. The obtained consumable cost-effectiveness, actual utilization rate, and inventory turnover efficiency are integrated into a comprehensive efficiency value for final decision-making. This avoids the limitations of traditional single-dimensional extensive allocation and achieves three major business objectives—reducing overall high procurement costs, reducing empty position waste, and accelerating the digestion of near-expiration consumables—while meeting the absolute position requirements for a single test. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are 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.

[0019] Figure 1 This is a flowchart illustrating a testing consumable allocation method based on comprehensive efficiency optimization in one embodiment; Figure 2 This is a structural block diagram of a testing consumables distribution system based on comprehensive efficiency optimization in one embodiment; Figure 3 This is a structural block diagram of a computer device in one embodiment. Detailed Implementation

[0020] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] Example 1 Current consumable allocation methods primarily rely on manual experience-based assessment. However, when faced with complex testing needs and fluctuating inventory levels, these methods often simply round up the specifications based on the current number of samples to be tested, failing to consider the fixed control positions required during testing, or the vacancy rate of test wells under different specification combinations. This results in the underutilization of effective test wells, leading to resource waste. Secondly, the unit cost per person for testing consumables often decreases as packaging size increases. Current allocation logic often lacks analysis of the unit cost per specification, failing to balance reducing well waste with lower procurement costs. In practice, it's common to see large quantities of higher-priced, smaller-specification consumables being requisitioned to avoid a small number of wasted wells, resulting in high overall operating costs and a limited scope for cost optimization. Furthermore, existing management rules are mostly reactive allocations, meaning that requisition is based solely on existing inventory and current tasks, failing to incorporate historical sample size characteristics to predict future testing needs. This results in reserved quantities often being fixed proportions based on experience. When facing potential sample peaks in the future, there is a risk of consumable shortages, which can affect the normal conduct of testing tasks. Conversely, during periods of low demand, consumables nearing their expiration date may not be used up in time, leading to their expiration and disposal.

[0022] See Figure 1 As shown, this embodiment provides a testing consumable allocation method based on comprehensive efficiency optimization, applied to testing consumable allocation scenarios. The method includes the following steps: S1. Obtain the number of samples to be tested, the number of fixed control positions, historical sample size characteristics, and current status data for the current testing task. The current status data includes the unit cost per specification of each consumable, real-time inventory balance, and real-time remaining effective time. In step S1, the total number of patient samples to be tested in the current batch is captured in real time, i.e., the number of samples to be tested. The number of quality control wells or calibration wells that must be reserved as specified in the standard operating procedure of the test item is read, i.e., the number of fixed control positions. At the same time, the sample business volume records of a certain period of time in the past are retrieved as historical sample volume characteristics. The status data of various packaging specifications of consumables in the current warehouse are also checked, such as large packaging, medium packaging, small packaging, etc., including their unit cost per specification, real-time inventory balance, and real-time remaining effective time.

[0023] S2. Call the sample size prediction model to analyze the characteristics of historical sample size, output the predicted sample size in the future warning period, and determine the single specification reservation coefficient of each specification of consumable based on the predicted sample size. In step S2, the historical sample volume characteristics obtained in step S1 are input into the pre-trained sample volume prediction model. This model learns the fluctuation patterns in historical data to deduce the predicted daily sample volume within a set period in the future, such as a period of 3 or 7 days. Based on the deduced future sample demand pressure, different single-specification reservation coefficients are dynamically allocated to consumables of different specifications. For example, if the predicted future sample volume surges, the reservation coefficient can be appropriately increased to retain more available inventory; if the predicted future is a business trough, the reservation coefficient can be decreased to release inventory.

[0024] S3. Combine the number of samples to be tested and the number of fixed control positions to determine the total number of test positions. Combine the real-time inventory balance, the single specification reservation coefficient and the predicted sample size to determine the inventory safety requirement and reservation requirement, so as to construct the constraints for consumable allocation. Under the premise of meeting the constraints, generate multiple candidate allocation schemes. Each candidate allocation scheme consists of the expected usage quantity of consumables of each specification. In step S3, the number of samples to be tested is added to the number of fixed control sites to obtain the total number of test sites required for the current test. The minimum number of test sites required for this test is then calculated by subtracting the proportion calculated based on the single-specification reserve coefficient from the real-time inventory balance, resulting in the current maximum safety stock boundary for inventory safety requirements. Simultaneously, it is necessary to verify whether the remaining consumables in stock after deduction have sufficient total number of test sites to cover the reserve requirements for future warning cycles. Based on these three constraints, compliant reagent kit combinations are generated to obtain candidate allocation schemes.

[0025] S4. Based on the expected usage quantity in each of the candidate allocation schemes, and combined with the unit cost per specification, the number of samples to be tested, the number of fixed control positions, and the real-time remaining effective time, multiple evaluation indicators are calculated to obtain the consumable cost-effectiveness, actual utilization rate, and inventory turnover efficiency corresponding to each candidate allocation scheme. In step S4, for each candidate solution selected in S3, a quantitative score is performed from three independent dimensions: Regarding the cost-effectiveness of consumables, the economics of the solution is calculated based on the expected usage quantity of each specification and its corresponding unit cost per specification, and solutions that rely heavily on expensive small packages are avoided as much as possible.

[0026] Regarding the actual utilization rate, the proportion of vacant and wasted well positions in this combination scheme is calculated by combining the number of samples to be tested and the fixed control positions. The less vacant positions, the higher the score.

[0027] Regarding inventory turnover efficiency, the real-time remaining effective time of consumables is introduced to evaluate whether the scheme has played a positive role in digesting consumables that are about to expire.

[0028] S5. The cost-effectiveness of the consumables, the actual utilization rate, and the inventory turnover efficiency are comprehensively calculated to obtain the comprehensive efficiency value of each candidate allocation scheme. Based on the comprehensive efficiency value, the target allocation scheme is determined among the candidate allocation schemes to output the corresponding consumable allocation instruction.

[0029] In step S5, the three evaluation indicators mentioned above are comprehensively calculated using a set logic to assign a comprehensive efficiency value that reflects the overall performance of each candidate solution. The solution with the best comprehensive efficiency value among all candidate solutions is selected and locked as the target allocation solution. Finally, based on the specific quantities of each type of consumable determined in the target allocation solution, structured machine instructions are generated to guide laboratory personnel or automated robotic arms to perform the outbound operation.

[0030] It should be noted that by calling the sample size prediction model to output the predicted sample size for the future warning period, and dynamically determining the single-specification reservation coefficient accordingly, a safety stock management system that balances current task execution and future demand to prevent shortages is achieved when constructing consumable allocation constraints in conjunction with real-time inventory. On this basis, multiple candidate allocation schemes are generated within the constraints. Multi-dimensional efficiency calculations are performed by combining the unit cost of a single specification, the number of samples to be tested, the number of fixed control positions, and the real-time remaining effective time. The resulting consumable cost-effectiveness, actual utilization rate, and inventory turnover efficiency are integrated into a comprehensive efficiency value for final decision-making. This avoids the limitations of traditional single-dimensional extensive allocation. Under the premise of meeting the absolute hole position requirements for a single test, it achieves three major business objectives: reducing overall high procurement costs, reducing hole position vacancy waste, and accelerating the digestion of near-expiration consumables.

[0031] Example 2 This embodiment provides a further technical solution based on Embodiment 1.

[0032] In this embodiment, the historical sample size features include core time-series features and time-period features. The core time-series features are the continuous historical sample size within a preset time window, and the time-period features include weekday identifiers, week identifiers, and month identifiers. The method of calling the sample size prediction model to analyze the characteristics of the historical sample size and output the predicted sample size for the future warning period includes: The core temporal features and the time periodic features are concatenated to construct a multidimensional input feature vector; The multidimensional input feature vector is input into the sample size prediction model constructed based on the improved LSTM network, and temporal relationships are extracted through at least two hidden layers of the sample size prediction model; wherein, the activation function of the hidden layer is the hyperbolic tangent function; The fully connected output layer of the sample size prediction model outputs continuous values ​​based on the extracted temporal relationships, which serve as the predicted sample size for the future warning period; wherein the activation function of the fully connected output layer is a linear adaptation function.

[0033] Specifically, the actual number of detected samples for each day within a preset time window is extracted from the database. For each day within the time window, corresponding time-cycle features are extracted. Numerical encoding is used to distinguish whether the date is a legal working day, which day of the week it belongs to, and which month of the year it belongs to. These numerically encoded periodic features are then concatenated across dimensions with the original continuous historical sample volume to generate a structured multidimensional input feature vector. The concatenated multidimensional input feature vector is then input into an LSTM network step by step. This embodiment employs a deep network structure containing at least a first hidden layer and a second hidden layer. The multidimensional feature vector propagates forward in the network. The first hidden layer initially extracts the basic patterns of sample volume fluctuations, while the second hidden layer further performs higher-order abstraction and compression of these basic patterns. During this process, the neurons within the hidden layers use the hyperbolic tangent function as the activation function, nonlinearly mapping the output signal of each layer to the interval [-1, 1]. The high-order temporal relationship feature vector extracted through deep processing in the hidden layers is finally passed to the fully connected output layer of the prediction model. After the fully connected layer performs a weighted summation of the input features, it outputs a continuous real scalar that is not constrained by a fixed interval through the linear function. This value represents the model's prediction of the sample size within the future warning period.

[0034] In this embodiment, the calculation of evaluation indicators for each candidate allocation scheme yields the cost-effectiveness, actual utilization rate, and inventory turnover efficiency of the consumables, including: According to the formula Calculate the actual utilization rate ;in, The number of samples to be tested. The number of fixed control positions. This refers to the number of tests performed per specification for consumables of the corresponding specification. The expected usage quantity of the corresponding specification consumables; Specifically, the calculation logic of this evaluation index isolates the indispensable hard loss of fixed control positions.

[0035] According to the formula Calculate the cost-effectiveness of the consumables ;in, This is the theoretical minimum amount of consumables required, calculated based on the number of samples to be tested, the number of fixed control sites, and the maximum number of doses of the largest-sized consumables. The unit cost corresponding to the largest specification consumable. The unit cost per specification of the corresponding consumable; Specifically, this evaluation metric resolves the conflict between port utilization and procurement costs. In real-world medical scenarios, while smaller-sized packaging consumables effectively reduce port waste, their unit cost per person is often significantly higher than that of larger packaging. If allocation focuses solely on eliminating port waste, it can easily lead to the overuse of expensive smaller-sized consumables, increasing costs. The optimal strategy is to assume that all port requirements are met using the largest-sized consumable with the lowest unit price, and then calculate the lowest total cost based on this.

[0036] According to the formula Calculate the inventory turnover efficiency ;in, This refers to the real-time remaining valid time for consumables of the corresponding specifications.

[0037] Specifically, when calculating evaluation weights, the inverse of the remaining effective time of consumables increases non-linearly as they approach their expiration date. This means that if a candidate solution allocates a large number of consumables that are about to expire, the total score of that evaluation indicator will be drastically increased. This mechanism enables the system to prioritize consumables nearing their expiration date when making optimal decisions among a massive number of allocation combinations. It can proactively guide laboratories to prioritize the disposal of high-risk stockpiled materials nearing their expiration date, eliminating the risk of reagents being wasted due to stockpiling without the need for frequent manual inventory checks.

[0038] In this embodiment, the process of determining the total testing position requirement by combining the number of samples to be tested and the number of fixed control positions, and determining the inventory safety requirement and reserve requirement by combining the real-time inventory balance, the single-specification reservation coefficient, and the predicted sample size, in order to construct the constraints for consumable allocation, includes: Construct the total detection bit constraint conditions corresponding to the total detection bit requirement. ; Construct the inventory constraints corresponding to the stated inventory safety requirements: ; Construct the reservation constraints corresponding to the reservation requirements: ;in, The expected usage quantity for the corresponding specification of consumables. This refers to the number of tests performed per specification for consumables of the corresponding specification. The number of samples to be tested. The number of fixed control positions. The real-time inventory balance for the corresponding specifications of consumables. The single-specification reserve coefficient for the corresponding consumable specifications. This refers to the maximum daily predicted sample size within the future early warning period, extracted based on the predicted sample size.

[0039] It is important to note that all consumable combinations generated by the system must ensure that the total capacity of the available well positions covers the current number of test samples and the necessary quality control control positions, thus preventing experimental interruptions or missed detections due to insufficient allocation. By introducing a single-specification reserve coefficient to intercept available inventory, a certain proportion of safety buffer inventory is reserved for any specification of consumable when allocating it, avoiding the risk of sudden supply shortages of single-item materials due to indiscriminate consumption. Furthermore, all pre-locked safety stockpiles in the warehouse must have a total testing capacity sufficient to withstand the most extreme sudden sample peaks within the future warning period.

[0040] In this embodiment, determining the single-specification reservation coefficient for each specification of consumable based on the predicted sample size includes: Based on the predicted sample size, a first reservation coefficient and a second reservation coefficient are determined; wherein the first reservation coefficient is less than the second reservation coefficient. Specifically, based on the total demand predicted in step S2 for the future early warning period, two different levels of reserve ratio red lines are set. For example, the system determines the regular reserve ratio to be 0.3, i.e. the second reserve coefficient, based on the average sample demand for the next 7 days, while setting a lower reserve ratio of 0.1, i.e. the first reserve coefficient, for situations where inventory needs to be released urgently.

[0041] Determine whether the real-time remaining effective time of each specification of consumable is less than a preset near-expiration threshold; Specifically, the expiration date of each specification of consumables in the inventory is monitored in real time. For example, if the near-expiration threshold is set to 7 days, the system will automatically compare the real-time remaining validity time of each specification of consumables with the value of this threshold.

[0042] If it is less than, then the first reserve coefficient is configured for the consumable of that specification; if it is not less than, then the second reserve coefficient is configured for the consumable of that specification. Specifically, if a certain type of consumable has less than 7 days remaining on its shelf life, it is considered to be at risk of expiring. Therefore, a relatively small first reservation coefficient of 0.1 is assigned to it, which means that only 10% of the inventory of this consumable is locked, and 90% of the inventory is released for use in the current task. Conversely, for consumables with sufficient shelf life, a higher second reservation coefficient of 0.3 is assigned, locking 30% of the inventory to ensure long-term supply.

[0043] The generation of multiple candidate allocation schemes also includes: Consumables of each specification are allocated priority sorted according to the real-time remaining effective time of each specification in ascending order; Specifically, before executing the allocation algorithm, the system will establish a priority queue based on the expiration date of the consumables. The shorter the remaining expiration date and the closer the consumables are to expiration, the higher their weight in the sorting and the front of the queue.

[0044] During the traversal search process to generate the candidate allocation scheme, the expected usage quantity is allocated first to the specifications of consumables with smaller remaining effective time in real time, based on the allocation priority.

[0045] Specifically, when the system searches for feasible consumable combination schemes in step S3, the algorithm will follow the priority queue mentioned above. It will first try to consume the allocation quota of consumables with near expiration dates. Only after the consumables with near expiration dates have been allocated or the inventory constraint red line has been reached will it start to consider allocating regular consumables with longer expiration dates.

[0046] In this embodiment, the step of comprehensively calculating the cost-effectiveness of the consumables, the actual utilization rate, and the inventory turnover efficiency to obtain the comprehensive efficiency value of each candidate allocation scheme, and determining the target allocation scheme from the candidate allocation schemes based on the comprehensive efficiency value, includes: The cost-effectiveness of the consumables, the actual utilization rate, and the inventory turnover efficiency are multiplied to obtain the comprehensive efficiency value corresponding to each candidate allocation scheme. From the multiple candidate allocation schemes, the candidate allocation scheme with the largest comprehensive efficiency value is selected as the preliminary target scheme; If the number of preliminary target schemes is one, then the preliminary target scheme is determined as the target allocation scheme; If there are multiple preliminary target schemes, the total cost of consumables for each preliminary target scheme is calculated based on the expected usage quantity and the unit cost per specification. From all the preliminary target schemes, the scheme with the lowest total cost of consumables is determined as the target allocation scheme. The total cost of consumables is determined according to the formula... Calculations show that The expected usage quantity for the corresponding specification of consumables. The unit cost per specification of the corresponding consumable.

[0047] In this embodiment, the output corresponding consumable allocation instruction includes: Extract the preset number of test samples for each specification of consumables; Based on the real-time inventory balance of each specification of consumables, the single specification reservation coefficient, and the preset number of single specification testing units, calculate the total number of reserved testing positions for all specifications of consumables. Specifically, after the target allocation plan is determined, not only should the current requisition instructions be issued, but the safety stock remaining in the warehouse should also be checked. First, the real-time inventory balance of each specification of consumables is multiplied by the corresponding single-specification reservation coefficient to obtain the number of boxes of each specification that are frozen for protection. Then, these box numbers are multiplied by their corresponding single-specification testing capacity, for example, 10 tests for large packages and 5 tests for small packages, and then summed. This calculation process transforms the number of consumable inventory items into the total number of testing positions that can be accommodated in the future, i.e., the total number of reserved testing positions.

[0048] Determine whether the total number of reserved detection positions is less than the maximum required detection positions; wherein, the maximum required detection positions are the sum of the maximum value in the predicted sample size and the number of fixed control positions; Specifically, from the daily predicted sample size of the future early warning period output in step S2, the day with the largest value is extracted as the extreme peak value. The number of fixed control positions that must be consumed in a single experiment is added to this peak value to calculate the maximum number of detection positions that the laboratory will face on the busiest day in the future. Then, the total number of reserved detection positions calculated in the first step is compared with the maximum number of detection positions that are in demand.

[0049] If the value is less than the target allocation scheme, a consumable shortage warning message will be output simultaneously when the consumable allocation instruction is output based on the target allocation scheme; the consumable shortage warning message is used to prompt the replenishment of consumables of a specific specification. Specifically, if the comparison reveals that the total reserved quantity is less than the maximum demand, it indicates that although the current testing reagents are sufficient, the safety stock in the warehouse is insufficient for the potential business peak in the next few days. At this time, while issuing the current consumable allocation instructions to automated equipment or personnel, a consumable shortage warning will be simultaneously triggered and output through system interface pop-ups, SMS, or emails, prompting purchasing or warehouse personnel to urgently replenish specific specifications of consumables.

[0050] After the consumable allocation instruction is executed, the real-time inventory balance corresponding to each consumable specification is synchronously deducted according to the expected usage quantity of each consumable specification in the target allocation scheme, so as to update the current status data.

[0051] Specifically, after the consumables are issued according to the allocation instructions, the real-time inventory balance of the corresponding consumables is automatically subtracted from the expected usage quantity of each specification in the target allocation plan. The updated inventory data will be used as the current status data to directly support the optimization calculation for the next batch of testing tasks.

[0052] It should be noted that by benchmarking this carrying capacity against predicted future extreme demand peaks across dimensions, the system can anticipate shortages several days in advance, avoiding gaps caused by sudden surges in samples. At the execution level, this solution not only provides suggestions but also stipulates a synchronized linkage mechanism between instruction issuance and underlying inventory deduction. This ensures a high-frequency and accurate mapping between the book inventory in the model and the actual inventory, avoiding the data lag and error risks associated with manual post-event record-keeping in traditional models. This significantly improves the operational capacity of the entire consumables allocation system.

[0053] Example 3 This embodiment provides a further technical solution based on Embodiment 1 or Embodiment 2.

[0054] In this embodiment, the theoretical minimum consumable usage calculated based on the number of samples to be tested, the number of fixed control sites, and the maximum number of doses of the largest-sized consumable is... The calculation process includes: From the preset set of consumable specifications, select the consumable with the largest number of tests per specification as the target maximum specification consumable, and record the number of tests per specification corresponding to the target maximum specification consumable as the maximum specification consumable test count. ; Specifically, before evaluating the economics of the plan, a comprehensive scan of all consumable specifications currently configured in the laboratory or preset by the system will be performed to automatically identify the packaging specification that can accommodate the most test doses per test. For example, among specifications such as 10 doses, 50 doses, and 96 doses, the 96-dose specification will be identified and defined as the target maximum consumable specification, and its capacity value will be extracted as the baseline denominator. .

[0055] Calculate the sum of the number of samples to be tested N and the number of fixed control sites C to obtain the theoretical total number of well sites required for a single test; Specifically, the basic total number of wells required for this experiment is calculated by adding the number of patient samples N that actually need to be tested in this task to the number of wells C occupied by the quality control / calibrators that are required to be consumed according to the standard operating procedure.

[0056] Divide the theoretical total number of apertures by the number of units of the maximum specification consumable. The quotient obtained by division is then rounded up to obtain the theoretical minimum amount of consumables required. ; Theoretical minimum material usage Satisfies the calculation formula: ;in, This represents the function for rounding up.

[0057] Specifically, the total required number of pores obtained above is used as the numerator, divided by the maximum number of parts of the maximum specification determined in the first step. In most real-world scenarios, the total number of holes cannot be perfectly divided by the maximum size. For example, dividing the requirement of 100 holes by the size for 96 servings yields a quotient of 1.04. By introducing a rounding function, the decimal quotient is rounded up to the next adjacent positive integer, i.e., 1.04 is rounded up to 2. This calculated value of 2 represents the minimum number of boxes required to cover the hole requirement under the ideal scenario of using the maximum packaging size. This value will be directly used as the core multiplier of the numerator cost when calculating the cost-effectiveness of consumables.

[0058] It should be noted that in the pricing principles of medical consumables, the larger the packaging size, the lower the marginal cost per unit. This example constructs a virtual extreme scenario assuming all demand is met by the largest packaging size with the lowest unit price, and calculates a minimum number of boxes required. .based on The calculated total cost is equivalent to drawing an absolutely optimal cost baseline for all allocation schemes. Any scheme that attempts to reduce waste by piecing together a large number of small-sized, high-priced reagents will reveal a cost premium when compared with this baseline, and will thus be identified and penalized in subsequent evaluations.

[0059] Example 4 See Figure 2 As shown, this embodiment provides a testing consumables distribution system based on comprehensive efficiency optimization, used to apply the testing consumables distribution method based on comprehensive efficiency optimization as described in any one of Embodiments 1, 2, or 3. The system includes: The acquisition unit 100 acquires the number of samples to be tested, the number of fixed control positions, historical sample size characteristics, and current status data for the current testing task. The current status data includes the unit cost per specification of each consumable, the real-time inventory balance, and the real-time remaining effective time. Calling unit 200 calls the sample size prediction model to analyze the characteristics of historical sample size, outputs the predicted sample size in the future warning period, and determines the single specification reservation coefficient of each specification of consumable based on the predicted sample size. The construction unit 300 determines the total detection position requirement by combining the number of samples to be tested and the number of fixed control positions, and determines the inventory safety requirement and reserve requirement by combining the real-time inventory balance, the single specification reservation coefficient and the predicted sample size, so as to construct the constraints for consumable allocation. Under the premise of meeting the constraints, multiple candidate allocation schemes are generated, and each candidate allocation scheme consists of the expected usage quantity of consumables of each specification. Evaluation unit 400 calculates multiple evaluation indicators based on the expected usage quantity in each candidate allocation scheme, combined with the unit cost of a single specification, the number of samples to be tested, the number of fixed control positions, and the real-time remaining effective time, to obtain the consumable cost-effectiveness, actual utilization rate, and inventory turnover efficiency corresponding to each candidate allocation scheme. The output unit 500 performs a comprehensive calculation on the cost-effectiveness of the consumables, the actual utilization rate, and the inventory turnover efficiency to obtain the comprehensive efficiency value of each candidate allocation scheme. Based on the comprehensive efficiency value, it determines the target allocation scheme from the candidate allocation schemes and outputs the corresponding consumable allocation instruction.

[0060] The testing consumable allocation system based on comprehensive efficiency optimization provided in this embodiment has the following advantages: By calling the sample size prediction model to output the predicted sample size within the future warning period, and dynamically determining the single-specification reservation coefficient accordingly, a safety stock management system that balances current task execution and future demand to prevent shortages is achieved when constructing consumable allocation constraints in conjunction with real-time inventory. On this basis, multiple candidate allocation schemes are generated within the constraints, and multi-dimensional efficiency calculations are performed by combining the unit cost of a single specification, the number of samples to be tested, the number of fixed control positions, and the real-time remaining effective time. The obtained consumable cost-effectiveness, actual utilization rate, and inventory turnover efficiency are integrated into a comprehensive efficiency value for final decision-making. This avoids the limitations of traditional single-dimensional extensive allocation and achieves three major business objectives—reducing overall high procurement costs, reducing empty position waste, and accelerating the digestion of near-expiration consumables—while meeting the absolute position requirements for a single test.

[0061] Example 5 This embodiment provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the steps of the method as described in any one of Embodiment 1, Embodiment 2, or Embodiment 3.

[0062] Example 6 See Figure 3 As shown, this embodiment provides a computer device, including a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the method as described in any one of Embodiment 1, Embodiment 2, or Embodiment 3.

[0063] It should be noted that "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature specified with "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" or "several" means two or more, unless otherwise explicitly specified.

[0064] It should be noted that the structures, proportions, sizes, etc., shown in the accompanying drawings of this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed in the specification, and are not intended to limit the conditions under which this application can be implemented. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportions, or adjustments to the size should still fall within the scope of the technical content disclosed in this application, provided that they do not affect the effects and purposes that this application can produce.

[0065] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0066] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0067] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for allocating testing consumables based on comprehensive efficiency optimization, characterized in that, Applied to scenarios involving the distribution of consumables, the method includes the following steps: The system obtains the number of samples to be tested, the number of fixed control positions, historical sample size characteristics, and current status data for the current testing task. The current status data includes the unit cost per specification of each consumable, real-time inventory balance, and real-time remaining effective time. The sample size prediction model is called to analyze the characteristics of historical sample size, and the predicted sample size in the future warning period is output. Based on the predicted sample size, the single specification reservation coefficient of each specification of consumable is determined. The total number of test positions is determined by combining the number of samples to be tested and the number of fixed control positions. The inventory safety requirement and the reserve requirement are determined by combining the real-time inventory balance, the single specification reservation coefficient and the predicted sample size, so as to construct the constraints for consumable allocation. Under the premise of meeting the constraints, multiple candidate allocation schemes are generated, and each candidate allocation scheme consists of the expected usage quantity of consumables of each specification. Based on the expected usage quantity in each of the candidate allocation schemes, and combined with the unit cost per specification, the number of samples to be tested, the number of fixed control positions, and the real-time remaining effective time, multiple evaluation indicators are calculated to obtain the consumable cost-effectiveness, actual utilization rate, and inventory turnover efficiency corresponding to each candidate allocation scheme. The cost-effectiveness of the consumables, the actual utilization rate, and the inventory turnover efficiency are comprehensively calculated to obtain the comprehensive efficiency value of each candidate allocation scheme. Based on the comprehensive efficiency value, the target allocation scheme is determined among the candidate allocation schemes to output the corresponding consumable allocation instruction.

2. The method for allocating testing consumables based on comprehensive efficiency optimization according to claim 1, characterized in that, The historical sample size features include core time-series features and time-period features. The core time-series features are the continuous historical sample size within a preset time window. The time-period features include weekday identifiers, week identifiers, and month identifiers. The method of calling the sample size prediction model to analyze the characteristics of the historical sample size and output the predicted sample size for the future warning period includes: The core temporal features and the time periodic features are concatenated to construct a multidimensional input feature vector; The multidimensional input feature vector is input into the sample size prediction model constructed based on the improved LSTM network, and temporal relationships are extracted through at least two hidden layers of the sample size prediction model; wherein, the activation function of the hidden layer is the hyperbolic tangent function; The fully connected output layer of the sample size prediction model outputs continuous values ​​based on the extracted temporal relationships, which serve as the predicted sample size for the future warning period; wherein the activation function of the fully connected output layer is a linear adaptation function.

3. The method for allocating testing consumables based on comprehensive efficiency optimization according to claim 1, characterized in that, The calculation of multiple evaluation indicators yields the cost-effectiveness, actual utilization rate, and inventory turnover efficiency of each candidate allocation scheme, including: According to the formula Calculate the actual utilization rate ;in, The number of samples to be tested. The number of fixed control positions. This refers to the number of tests performed per specification for consumables of the corresponding specification. The expected usage quantity of the corresponding specification consumables; According to the formula Calculate the cost-effectiveness of the consumables ;in, This is the theoretical minimum amount of consumables required, calculated based on the number of samples to be tested, the number of fixed control sites, and the maximum number of doses of the largest-sized consumables. The unit cost corresponding to the largest specification consumable. The unit cost per specification of the corresponding consumable; According to the formula Calculate the inventory turnover efficiency ;in, This refers to the real-time remaining valid time for consumables of the corresponding specifications.

4. The method for allocating testing consumables based on comprehensive efficiency optimization according to claim 1, characterized in that, The total testing slot requirement is determined by combining the number of samples to be tested and the number of fixed control slots. The inventory safety requirement and reserve requirement are determined by combining the real-time inventory balance, the single-specification reserve coefficient, and the predicted sample size, thus constructing the constraints for consumable allocation, including: Construct the total detection bit constraint conditions corresponding to the total detection bit requirement. ; Construct the inventory constraints corresponding to the stated inventory safety requirements: ; Construct the reservation constraints corresponding to the reservation requirements: ;in, The expected usage quantity for the corresponding specification of consumables. This refers to the number of tests performed per specification for consumables of the corresponding specification. The number of samples to be tested. The number of fixed control positions. The real-time inventory balance for the corresponding specifications of consumables. The single-specification reserve coefficient for the corresponding consumable specifications. This refers to the maximum daily predicted sample size within the future early warning period, extracted based on the predicted sample size.

5. The method for allocating testing consumables based on comprehensive efficiency optimization according to claim 1, characterized in that, The determination of the single-specification reserve coefficient for each specification of consumables based on the predicted sample size includes: Based on the predicted sample size, a first reservation coefficient and a second reservation coefficient are determined; wherein the first reservation coefficient is less than the second reservation coefficient. Determine whether the real-time remaining effective time of each specification of consumable is less than a preset near-expiration threshold; If it is less than, then the first reserve coefficient is configured for the consumable of that specification; if it is not less than, then the second reserve coefficient is configured for the consumable of that specification. The generation of multiple candidate allocation schemes also includes: Consumables of each specification are allocated priority sorted according to the real-time remaining effective time of each specification in ascending order; During the traversal search process to generate the candidate allocation scheme, the expected usage quantity is allocated first to the specifications of consumables with smaller remaining effective time in real time, based on the allocation priority.

6. The method for allocating testing consumables based on comprehensive efficiency optimization according to claim 1, characterized in that, The process of comprehensively calculating the cost-effectiveness of the consumables, the actual utilization rate, and the inventory turnover efficiency to obtain a comprehensive efficiency value for each candidate allocation scheme, and determining the target allocation scheme from the candidate allocation schemes based on the comprehensive efficiency value, includes: The cost-effectiveness of the consumables, the actual utilization rate, and the inventory turnover efficiency are multiplied to obtain the comprehensive efficiency value corresponding to each candidate allocation scheme. From the multiple candidate allocation schemes, the candidate allocation scheme with the largest comprehensive efficiency value is selected as the preliminary target scheme; If the number of preliminary target schemes is one, then the preliminary target scheme is determined as the target allocation scheme; If there are multiple preliminary target schemes, the total cost of consumables for each preliminary target scheme is calculated based on the expected usage quantity and the unit cost per specification. From all the preliminary target schemes, the scheme with the lowest total cost of consumables is determined as the target allocation scheme. The total cost of consumables is determined according to the formula... Calculations show that The expected usage quantity for the corresponding specification of consumables. The unit cost per specification of the corresponding consumable.

7. The method for allocating testing consumables based on comprehensive efficiency optimization according to claim 1, characterized in that, The output corresponding consumable allocation instruction includes: Extract the preset number of test samples for each specification of consumables; Based on the real-time inventory balance of each specification of consumables, the single specification reservation coefficient, and the preset number of single specification testing units, calculate the total number of reserved testing positions for all specifications of consumables. Determine whether the total number of reserved detection positions is less than the maximum required detection positions; wherein, the maximum required detection positions are the sum of the maximum value in the predicted sample size and the number of fixed control positions; If the value is less than the target allocation scheme, a consumable shortage warning message will be output simultaneously when the consumable allocation instruction is output based on the target allocation scheme; the consumable shortage warning message is used to prompt the replenishment of consumables of a specific specification. After the consumable allocation instruction is executed, the real-time inventory balance corresponding to each consumable specification is synchronously deducted according to the expected usage quantity of each consumable specification in the target allocation scheme, so as to update the current status data.

8. The method for allocating testing consumables based on comprehensive efficiency optimization according to claim 3, characterized in that, The theoretical minimum consumable usage calculated based on the number of samples to be tested, the number of fixed control sites, and the maximum number of doses of the largest consumable size. The calculation process includes: From the preset set of consumable specifications, select the consumable with the largest number of tests per specification as the target maximum specification consumable, and record the number of tests per specification corresponding to the target maximum specification consumable as the maximum specification consumable test count. ; Calculate the sum of the number of samples to be tested N and the number of fixed control sites C to obtain the theoretical total number of well sites required for a single test; Divide the theoretical total number of apertures by the number of units of the maximum specification consumable. The quotient obtained by division is then rounded up to obtain the theoretical minimum amount of consumables required. ; Theoretical minimum material usage Satisfies the calculation formula: ;in, This represents the function for rounding up.

9. A testing consumables distribution system based on comprehensive efficiency optimization, characterized in that, The system for applying the detection consumable allocation method based on comprehensive efficiency optimization as described in any one of claims 1 to 8, the system comprising: The acquisition unit acquires the number of samples to be tested, the number of fixed control positions, historical sample size characteristics, and current status data for the current testing task. The current status data includes the unit cost per specification of each consumable, real-time inventory balance, and real-time remaining effective time. The calling unit calls the sample size prediction model to analyze the characteristics of historical sample size, outputs the predicted sample size in the future warning period, and determines the single specification reservation coefficient of each specification of consumable based on the predicted sample size. The construction unit determines the total detection position requirement by combining the number of samples to be tested and the number of fixed control positions, and determines the inventory safety requirement and reserve requirement by combining the real-time inventory balance, the single specification reservation coefficient and the predicted sample size, so as to construct the constraints for consumable allocation. Under the premise of meeting the constraints, multiple candidate allocation schemes are generated, and each candidate allocation scheme consists of the expected usage quantity of consumables of each specification. The evaluation unit calculates multiple evaluation indicators based on the expected usage quantity in each candidate allocation scheme, combined with the unit cost per specification, the number of samples to be tested, the number of fixed control positions, and the real-time remaining effective time, to obtain the consumable cost-effectiveness, actual utilization rate, and inventory turnover efficiency corresponding to each candidate allocation scheme. The output unit performs a comprehensive calculation on the cost-effectiveness of the consumables, the actual utilization rate, and the inventory turnover efficiency to obtain the comprehensive efficiency value of each candidate allocation scheme. Based on the comprehensive efficiency value, it determines the target allocation scheme from the candidate allocation schemes and outputs the corresponding consumable allocation instruction.

10. A computer-readable storage medium, characterized in that, The device stores a computer program that, when executed by a processor, causes the processor to perform the steps of the method as described in any one of claims 1 to 8.

Images