Supply chain ecological collaborative management method and system applied to medical industry

Abstract

The invention discloses a supply chain ecological collaborative management method and system applied to the medical industry, and relates to the technical field of medical material management. The method comprises the following steps: firstly, aiming at each target medical material, estimating according to single-day demand quantity time sequence data of a plurality of target medical materials to obtain a single-day demand quantity predicted value of the corresponding material in each day in current recent multiple days in the future; a material distribution scheme used for distributing each material from the upstream side of a medical industry supply chain to the downstream side of the medical industry supply chain in each day in recent future at present is optimized based on a genetic optimization algorithm, and an optimal material distribution scheme with the highest fitness is obtained. And finally, the optimal scheme is pushed to the upstream side of the supply chain for implementation, so that the inventory and logistics cooperation capability between upstream and downstream enterprises of the supply chain and the supply chain efficiency in the medical industry can be improved under the condition of comprehensively considering the medical material demand condition and the logistics cost condition.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical supplies management, and particularly relates to a supply chain ecological collaborative management method and system applied to the medical industry. Background Art

[0002] Supply chain ecological collaborative management refers to achieving close cooperation among upstream and downstream enterprises in the supply chain through means such as information sharing, resource integration, and business collaboration, so as to improve the overall efficiency and competitiveness of the supply chain. Specifically, supply chain ecological collaborative management includes several aspects such as information sharing, resource integration, business collaboration, risk management, and performance evaluation. Among them, the business collaboration refers to realizing business cooperation among upstream and downstream enterprises in the supply chain, including order collaboration, production collaboration, inventory collaboration, and logistics collaboration, etc., to improve the efficiency and collaborative ability of the supply chain.

[0003] Currently, medical supplies such as drugs, medical devices, and / or surgical consumables generally require strict expiration date management, making it not suitable to hoard a large amount of medical supplies on the downstream side of the medical industry supply chain such as in hospitals or clinics. Instead, dynamic replenishment needs to be carried out according to real-time consumption. However, existing dynamic replenishment solutions for medical supplies generally perform dynamic replenishment based on the inventory balance of medical supplies on the downstream side of the medical industry supply chain, without considering the demand situation and logistics cost situation of medical supplies in future periods, resulting in deficiencies in the inventory collaborative ability and logistics collaborative ability between upstream and downstream enterprises in the supply chain, and being unfavorable for improving the supply chain efficiency in the medical industry. Therefore, how to provide a new supply chain ecological collaborative management solution applied to the medical industry to improve the inventory collaborative ability and logistics collaborative ability between upstream and downstream enterprises in the supply chain and the supply chain efficiency in the medical industry while comprehensively considering the demand situation and logistics cost situation of medical supplies in future periods is an urgent research topic for those skilled in the art. Summary of the Invention

[0004] The purpose of the present invention is to provide a supply chain ecological collaborative management method, system, computer-readable storage medium, and computer program product applied to the medical industry to solve the problems of deficiencies in the inventory collaborative ability and logistics collaborative ability existing in existing dynamic replenishment solutions for medical supplies and the limitation of the supply chain efficiency in the medical industry.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions:

[0006] In the first aspect, a supply chain ecological collaborative management method applied to the medical industry is provided, including:

[0007] Obtain the time-series data of the single-day demand for multiple target medical supplies on the downstream side of the medical industry supply chain. Among them, the single-day demand time-series data includes the current most recent historical multi-days in sequence in time series and the single-day demand of the corresponding supplies on each day of the current most recent historical multi-days and on the downstream side of the medical industry supply chain;

[0008] For each target medical supply among the multiple target medical supplies, based on the single-day demand time-series data of the multiple target medical supplies, estimate the predicted value of the single-day demand of the corresponding supply on each day in the current most recent future multi-days and on the downstream side of the medical industry supply chain;

[0009] According to the inventory balance of each target medical supply on the current day and on the downstream side of the medical industry supply chain and the predicted values of the single-day demand on each day in the current most recent future multi-days and on the downstream side of the medical industry supply chain, optimize the material distribution plan for delivering each target medical supply from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain on each day in the current most recent future multi-days based on the genetic optimization algorithm, and obtain the optimal material distribution plan with the highest fitness. Among them, the material distribution plan is represented by an X×Y-dimensional vector corresponding to each day in the current most recent future multi-days and each target medical supply. The element c at the x-th row and y-th column in the X×Y-dimensional vector x,y represents the material distribution volume of the y-th target medical supply from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain on the x-th day in the current most recent future multi-days. X represents the total number of days in the current most recent future multi-days, Y represents the total number of target medical supplies, x represents a positive integer less than or equal to X, y represents a positive integer less than or equal to Y, and the fitness function is designed based on being negatively correlated with the logistics cost corresponding to the material distribution plan;

[0010] Push the optimal material distribution plan to the upstream side of the medical industry supply chain for implementation.

[0011] Based on the above inventive concept, a new supply chain ecological collaborative management solution for inventory and logistics collaborative optimization between the upstream and downstream of the supply chain is provided. First, for each target medical material, the predicted values of the single-day demand for each day in the current nearest future days of the corresponding material are estimated according to the time series data of the single-day demand for multiple target medical materials. Then, combined with the inventory balance of each material on the current day, based on the genetic optimization algorithm, the material distribution plan for delivering each material from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain in each day of the current nearest future days is optimized to obtain the optimal material distribution plan with the highest fitness. Finally, the optimal plan is pushed to the upstream side of the supply chain for implementation. In this way, considering the demand situation of medical materials in the future period and the logistics cost, the inventory collaborative ability and logistics collaborative ability between upstream and downstream enterprises in the supply chain and the supply chain efficiency in the medical industry can be improved, which is convenient for practical application and promotion.

[0012] In a possible design, for each target medical material among the multiple target medical materials, according to the time series data of the single-day demand for the multiple target medical materials, estimating the predicted value of the single-day demand for each day in the current nearest future days and on the downstream side of the medical industry supply chain for the corresponding material includes:

[0013] For any one of the multiple target medical materials, based on the STL algorithm and the Prophet model, the first predicted value of the single-day demand for each day in the current nearest future days and on the downstream side of the medical industry supply chain for the corresponding material is estimated according to the corresponding time series data of the single-day demand;

[0014] For each of the other medical materials relative to the any one of the multiple target medical materials, the correlation coefficient between the corresponding material and the any one of the target medical materials is calculated according to the corresponding time series data of the single-day demand and the time series data of the single-day demand of the any one of the target medical materials, and the second predicted value of the single-day demand for each day in the current nearest future days and on the downstream side of the medical industry supply chain for the corresponding and the any one of the target medical materials is estimated by using a machine learning algorithm;

[0015] According to the first predicted value of the single-day demand for each day in the current nearest future days and on the downstream side of the medical industry supply chain for the any one of the target medical materials and the second predicted value of the single-day demand for each day in the current nearest future days and on the downstream side of the medical industry supply chain for the corresponding and the any one of the target medical materials for each of the other medical materials, combined with the correlation coefficient between each of the other medical materials and the any one of the target medical materials, the final predicted value of the single-day demand for each day in the current nearest future days and on the downstream side of the medical industry supply chain for the any one of the target medical materials is calculated.

[0016] In a possible design, for any one of the multiple target medical supplies, based on the corresponding single-day demand time series data, the predicted value of the first single-day demand for each day in the current nearest future multi-day for the corresponding supply on the downstream side of the medical industry supply chain is estimated based on the STL algorithm and the Prophet model, including:

[0017] For any one of the multiple target medical supplies, the STL algorithm is used to decompose the corresponding single-day demand time series data to obtain the corresponding single-day demand trend term component time series data. Among them, the single-day demand trend term component time series data includes the current nearest historical multi-day and the single-day demand trend term component for each day of the any one target medical supply in the current nearest historical multi-day on the downstream side of the medical industry supply chain;

[0018] According to the single-day demand trend term component time series data, the predicted value of the first single-day demand trend term component for each day in the current nearest future multi-day for the any one target medical supply on the downstream side of the medical industry supply chain is calculated based on the dynamic exponential weighting method. Among them, the dynamic exponential weighting method assigns weights to the single-day demand trend term components in different periods according to the following rules: a larger weight is assigned to the nearer single-day demand trend term component, and a smaller weight is assigned to the earlier single-day demand trend term component;

[0019] According to the single-day demand trend term component time series data, the prediction model is trained based on the Prophet model, and the predicted value of the second single-day demand trend term component, the predicted value of the single-day demand seasonal effect term component, the predicted value of the single-day demand holiday effect term component, and the predicted value of the single-day demand error term component for each day in the current nearest future multi-day for the any one target medical supply on the downstream side of the medical industry supply chain are predicted by applying the trained prediction model;

[0020] For each day in the current nearest future multi-day, the predicted value sp1 of the first single-day demand for the any one target medical supply on the corresponding day on the downstream side of the medical industry supply chain is calculated according to the following formula:

[0021] sp1 = w s ×g sp,1 + w p ×g sp,2 + s prophet + h prophet + ε prophet

[0022] In the formula, g sp,1 represents the predicted value of the first single-day demand trend term component, g sp,2Denote the predicted value of the second single-day demand trend item component as s prophet Denote the predicted value of the single-day demand seasonal effect item component as h prophet Denote the predicted value of the single-day demand holiday effect item component as ε prophet Denote the predicted value of the single-day demand error item component as w s and w p respectively denote preset weight coefficients and there is w s +w p = 1.

[0023] In a possible design, when the current most recent historical multi-days are all the days of the current most recent consecutive multi-weeks in time sequence and the current most recent future multi-days are all the days of the next week after the current one, based on the single-day demand trend item component time series data, the first predicted value of the single-day demand trend item component of any target medical supply for each day in the current most recent future multi-days and on the downstream side of the medical industry supply chain is calculated based on the dynamic exponential weighting method, including:

[0024] Divide the single-day demand trend item component time series data into multiple arrays corresponding one by one to the current most recent multi-weeks, and aggregate the multiple arrays to obtain the following matrix G:

[0025]

[0026] In the formula, n represents the total number of weeks of the current most recent multi-weeks, n′ represents a positive integer less than or equal to n, m′ represents a positive integer less than or equal to 7, and g n′,m′ represents the single-day demand trend item component of any target medical supply on the m′-th day in the n′-th week of the current most recent multi-weeks and on the downstream side of the medical industry supply chain;

[0027] For each day in the next week after the current one, calculate the corresponding first predicted value of the single-day demand trend item component according to the following formula:

[0028]

[0029] In the formula, represents the first predicted value of the single-day demand trend item component of any target medical supply on the m′-th day in the next week after the current one and on the downstream side of the medical industry supply chain, n″ represents a positive integer less than or equal to n, and g n″,m′ represents the single-day demand trend item component of any target medical supply on the m′-th day in the n′-th week of the current most recent multi-weeks and on the downstream side of the medical industry supply chain, and α represents a preset smoothing factor and α ∈ (0, 1).

[0030] In a possible design, for each of the other medical supplies relative to any one of the multiple target medical supplies, according to the corresponding single-day demand time-series data and the single-day demand time-series data of any one of the target medical supplies, the correlation coefficient between the corresponding supply and any one of the target medical supplies is calculated, including:

[0031] For a certain other medical supply relative to any one of the multiple target medical supplies, a most recent time-series data segment is extracted from the corresponding single-day demand time-series data to form a first sample S1, and another time-series data segment synchronous with the first sample S1 is extracted from the single-day demand time-series data of any one of the target medical supplies to form a second sample S2;

[0032] Perform a normal distribution KS test on the first sample S1 to calculate a first test statistic p-value p1, and also perform the normal distribution KS test on the second sample S2 to calculate a second test statistic p-value p2;

[0033] If both the first test statistic p-value p1 and the second test statistic p-value p2 are greater than a preset threshold, the correlation coefficient r between the first sample S1 and the sample S2 is calculated according to the following formula q :

[0034]

[0035] In the formula, i represents a positive integer, x i represents the i-th sample value in the first sample S1, y i represents the i-th sample value in the second sample S2, represents the sample mean of the first sample S1, represents the sample mean of the second sample S2;

[0036] Take the correlation coefficient r q as the correlation coefficient between the certain other medical supply and any one of the target medical supplies.

[0037] In a possible design, according to the first single-day demand prediction values of any one of the target medical supplies for each day in the current nearest future days and on the downstream side of the medical industry supply chain, and the second single-day demand prediction values corresponding to each of the other medical supplies and for each day in the current nearest future days and on the downstream side of the medical industry supply chain of any one of the target medical supplies, and combining the correlation coefficients between each of the other medical supplies and any one of the target medical supplies, the final single-day demand prediction values of any one of the target medical supplies for each day in the current nearest future days and on the downstream side of the medical industry supply chain are calculated, including:

[0038] For each day in the current recent future multi - days, the predicted value of the final single - day demand of any target medical material on the corresponding day and on the downstream side of the medical industry supply chain is calculated according to the following formula:

[0039]

[0040] In the formula, x represents a positive integer, P x represents the predicted value of the final single - day demand of any target medical material on the x - th day in the current recent future multi - days and on the downstream side of the medical industry supply chain, Y represents the total number of the target medical material, y' represents a positive integer less than or equal to Y - 1, η y′ represents the influence weight coefficient corresponding to the y'-th other medical material, r q,y′ represents the correlation coefficient corresponding to the y'-th other medical material, y'' represents a positive integer less than or equal to Y - 1, r q,y″ represents the correlation coefficient corresponding to the y''-th other medical material, P 1,x represents the predicted value of the first single - day demand of any target medical material on the x - th day in the current recent future multi - days and on the downstream side of the medical industry supply chain, P y′,x represents the predicted value of the second single - day demand of any target medical material on the x - th day in the current recent future multi - days and on the downstream side of the medical industry supply chain corresponding to the y'-th other medical material.

[0041] In a possible design, based on the inventory balance of each target medical material on the current day and on the downstream side of the medical industry supply chain and the predicted values of the single - day demand of each target medical material on each day in the current recent future multi - days and on the downstream side of the medical industry supply chain, the material distribution plan for delivering each target medical material from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain on each day in the current recent future multi - days is optimized by using a genetic optimization algorithm to obtain an optimal material distribution plan with the highest fitness, including the following steps S31 - S35:

[0042] S31. Initialize the genetic optimization algorithm with algorithm parameters including the population size N and the maximum number of iterations T max and initialize the current number of iterations T = 0, then execute step S32;

[0043] S32. Randomly generate N material distribution plans that respectively meet the constraints of the distribution plan and are used to distribute each of the target medical materials from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain on each day of the current nearest future multi - days, and use the N material distribution plans as N individuals one - to - one to form an initial population, and then execute step S33. Among them, the material distribution plan is represented by an X×Y - dimensional vector corresponding to each day of the current nearest future multi - days and each of the target medical materials. The element c at the x - th row and y - th column in the X×Y - dimensional vector x,y represents the material distribution volume of the y - th target medical material from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain on the x - th day of the current nearest future multi - days. X represents the total number of days in the current nearest future multi - days, Y represents the total number of the target medical materials, x represents a positive integer less than or equal to X, y represents a positive integer less than or equal to Y. The distribution plan constraints include the following: P x′+1,y ≤I b,x′,y +c x′,y -P x′,y ≤I b,max,y , where x′ represents a positive integer less than or equal to X - 1, P x′+1,y represents the predicted value of the single - day demand of the y - th target medical material on the (x′ + 1) - th day in the current nearest future multi - days and on the downstream side of the medical industry supply chain. I b,x′,y represents the inventory balance of the y - th target medical material on the x′ - th day in the current nearest future multi - days and on the downstream side of the medical industry supply chain. c x′,y represents the material distribution volume of the y - th target medical material from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain on the x′ - th day in the current nearest future multi - days. P x′,y represents the predicted value of the single - day demand of the y - th target medical material on the x′ - th day in the current nearest future multi - days and on the downstream side of the medical industry supply chain. I b,max,y represents the maximum allowable inventory of the y - th target medical material on the downstream side of the medical industry supply chain;

[0044] S33. For each individual in the current population, determine the corresponding logistics cost according to the corresponding material distribution plan, and calculate the corresponding fitness according to this logistics cost, and then execute step S34. Among them, the fitness function is designed based on being negatively correlated with the logistics cost corresponding to the material distribution plan;

[0045] S34. Judge whether the current iteration number T has reached the maximum iteration number T maxIf so, select the individual corresponding to the highest fitness from the current population as the optimal work order allocation plan; otherwise, increment the current iteration count T by 1, and then execute step S35;

[0046] S35. According to each individual and the fitness of each individual, through the selection operation, crossover operation, and mutation operation in the genetic optimization algorithm, obtain N new individuals that respectively meet the constraints of the distribution plan to form a new population, and then return to execute step S33.

[0047] In a possible design, the constraints of the distribution plan further include: c x,y is a natural multiple of c stp,y where c stp,y represents the unit material distribution volume for delivering the y-th target medical material from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain by a transport vehicle;

[0048] For each individual in the current population, determine the corresponding logistics cost according to the corresponding material distribution plan, including:

[0049] For any individual in the current population, determine the corresponding required number of transport vehicle trips according to the corresponding material distribution plan and the single trip carrying capacity of the transport vehicle;

[0050] Calculate the logistics cost corresponding to any individual according to the required number of transport vehicle trips corresponding to the individual, where the logistics cost is positively correlated with the required number of transport vehicle trips.

[0051] In a second aspect, a supply chain ecological collaborative management system applied to the medical industry is provided, including a time series data acquisition unit, a material demand forecasting unit, a distribution plan optimization unit, and an optimal plan pushing unit that are sequentially communicatively connected;

[0052] The time series data acquisition unit is configured to acquire the single-day demand time series data of multiple target medical materials on the downstream side of the medical industry supply chain, where the single-day demand time series data includes the current recent historical multi-days that are sequentially continuous in time series and the single-day demand of the corresponding materials on each day in the current recent historical multi-days and on the downstream side of the medical industry supply chain;

[0053] The material demand forecasting unit is configured to estimate the single-day demand forecast value of the corresponding material on each day in the current recent future multi-days and on the downstream side of the medical industry supply chain for each target medical material among the multiple target medical materials according to the single-day demand time series data of the multiple target medical materials;

[0054] The delivery plan optimization unit is configured to optimize the material delivery plan for delivering each target medical material from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain in each of the current nearest future days based on a genetic optimization algorithm according to the inventory balance of each target medical material on the current day and on the downstream side of the medical industry supply chain, and the predicted value of the single-day demand in each of the current nearest future days and on the downstream side of the medical industry supply chain, so as to obtain an optimal material delivery plan with the highest fitness. Wherein, the material delivery plan is represented by an X×Y-dimensional vector corresponding to each of the current nearest future days and each target medical material. The element c at the x-th row and the y-th column in the X×Y-dimensional vector x,y represents the material delivery quantity of the y-th target medical material from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain on the x-th day in the current nearest future days. X represents the total number of days in the current nearest future days. Y represents the total number of the target medical materials. x represents a positive integer less than or equal to X. y represents a positive integer less than or equal to Y. The fitness function is designed based on being negatively correlated with the logistics cost corresponding to the material delivery plan;

[0055] The optimal plan pushing unit is configured to push the optimal material delivery plan to the upstream side of the medical industry supply chain for implementation.

[0056] In a third aspect, the present invention provides a computer system, including a memory, a processor, and a transceiver that are communicatively connected in sequence. 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 supply chain ecological collaborative management method as described in the first aspect or any possible design in the first aspect.

[0057] In a fourth aspect, the present invention provides a computer-readable storage medium, on which instructions are stored. When the instructions are run on a computer, the supply chain ecological collaborative management method as described in the first aspect or any possible design in the first aspect is executed.

[0058] In a fifth aspect, the present invention provides a computer program product, including a computer program or instructions, and when the computer program or the instructions are executed by a computer, the supply chain ecological collaborative management method as described in the first aspect or any possible design in the first aspect is implemented.

[0059] The beneficial effects of the above solution:

[0060] (1) The present invention provides a new supply chain ecological collaborative management solution for inventory and logistics collaborative optimization between upstream and downstream of the supply chain. That is, for each target medical material, the predicted value of the single-day demand for each day in the next few days of the corresponding material is estimated based on the time-series data of the single-day demand of multiple target medical materials. Then, combined with the inventory balance of each material on the current day, the genetic optimization algorithm is used to optimize the material distribution plan for delivering each material from the upstream side to the downstream side of the medical industry supply chain in the next few days, so as to obtain the optimal material distribution plan with the highest fitness. Finally, the optimal plan is pushed to the upstream side of the supply chain for implementation. In this way, considering the demand of medical materials in the future period and the logistics cost, the inventory collaborative ability and logistics collaborative ability between upstream and downstream enterprises of the supply chain can be improved, as well as the supply chain efficiency in the medical industry, which is convenient for practical application and promotion. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0062] Figure 1 It is a flowchart of the supply chain ecological collaborative management method applied to the medical industry provided by the embodiment of the present application.

[0063] Figure 2 It is a schematic structural diagram of the supply chain ecological collaborative management system applied to the medical industry provided by the embodiment of the present application.

[0064] Figure 3 It is a schematic structural diagram of the computer system provided by the embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0065] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the present invention in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structural drawings is only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other embodiments can be obtained based on these embodiments. It should be noted here that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation to the present invention.

[0066] It should be understood that although terms such as first and second may be used herein to describe various objects, these objects should not be limited by these terms. These terms are only used to distinguish one object from another. For example, the first object may be referred to as the second object, and similarly, the second object may be referred to as the first object, without departing from the scope of the exemplary embodiments of the present invention.

[0067] It should be understood that for the term "and / or" that may appear herein, it is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, B exists alone, or A and B exist simultaneously, etc.; for another example, A, B, and / or C may represent any one of A, B, and C or any combination of them; for the term " / and" that may appear herein, it is a description of another association object relationship, indicating that two relationships may exist. For example, A / and B may represent: A exists alone or A and B exist simultaneously, etc.; in addition, for the character " / " that may appear herein, generally, it represents that the associated objects before and after are in an "or" relationship.

[0068] Embodiment

[0069] As Figure 1 shown, the supply chain ecological collaborative management method provided in the first aspect of this embodiment and applied to the medical industry can be, but is not limited to, executed by a computer device with certain computing resources, such as a management server, a platform server, a personal computer (Personal Computer, PC, referring to a multi-purpose computer suitable for personal use in terms of size, price, and performance; desktop computers, laptops, small laptops, tablet computers, and ultrabooks, etc. all belong to personal computers), a smart phone, a personal digital assistant (Personal Digital Assistant, PDA), or a wearable device, etc. As Figure 1 shown, the supply chain ecological collaborative management method can be, but is not limited to, including the following steps S1 to S4.

[0070] S1. Obtain the time series data of the single-day demand of multiple target medical supplies on the downstream side of the medical industry supply chain. Among them, the time series data of the single-day demand includes, but is not limited to, the most recent consecutive multiple days in time series and the single-day demand of the corresponding supplies on each day of the most recent consecutive multiple days on the downstream side of the medical industry supply chain.

[0071] In the step S1, the downstream side of the medical industry supply chain may include, but is not limited to, medical material consumption units such as hospitals or clinics. The multiple target medical materials include, but are not limited to, specific drugs, medical devices, and / or surgical consumables, etc. Their corresponding single-day demand time series data can be obtained through regular statistics based on the historical consumption data of medical materials.

[0072] S2. For each of the multiple target medical materials, based on the single-day demand time series data of the multiple target medical materials, estimate the predicted value of the single-day demand for each day in the current nearest future days and on the downstream side of the medical industry supply chain for the corresponding material.

[0073] In the step S2, for example, if the current nearest historical days are from January 6th to February 16th (i.e., 6 consecutive weeks), then the current nearest future days can be from February 17th to February 23rd (i.e., the next week after the 6 consecutive weeks). Considering that there is a certain correlation in the demand for different medical materials, in order to improve the prediction accuracy of the single-day demand for each of the multiple target medical materials in the future days, preferably, for each of the multiple target medical materials, based on the single-day demand time series data of the multiple target medical materials, estimate the predicted value of the single-day demand for each day in the current nearest future days and on the downstream side of the medical industry supply chain, including but not limited to the following steps S21 - S23.

[0074] S21. For any one of the multiple target medical materials, based on the corresponding single-day demand time series data, estimate the first predicted value of the single-day demand for each day in the current nearest future days and on the downstream side of the medical industry supply chain for the corresponding material based on the STL algorithm and the Prophet model.

[0075] In the step S21, the STL (Seasonal and Trend decomposition using LOESS) algorithm is a non-parametric time series decomposition method based on locally weighted scatterplot smoothing (LOESS). It can decompose time series data into three parts: trend, seasonality, and residuals. The STL algorithm has flexibility and robustness and can adapt to the characteristics of various time series, including complex seasonal patterns and non-linear trends. Its core idea is to decompose the time series y stl (t) into a trend g stl (t), seasonality s stl (t), and residuals ∈ t and other three parts:

[0076] y stl (t) = g stl (t) + s stl (tl(t) + ∈ t

[0077] The STL algorithm mainly uses LOESS to smooth the time series to extract the trend component. Among them, LOESS is a local regression method that fits a smooth curve by performing weighted regression on the data points near each time point, without relying on a pre - assumed trend model or seasonal model. Therefore, it can handle various types of time series data, including non - linear trends and complex seasonal patterns, etc.

[0078] In step S21, the Prophet model is an existing data prediction tool based on Python and R languages, suitable for handling time series data with strong seasonal patterns and historical trends. The Prophet model is constructed based on an additive model, which is composed of trend, seasonality, holiday effects, and errors. The mathematical representation of the corresponding algorithm is:

[0079] P(t) = g(t) + s(t) + h(t) + ∈ t

[0080] In the formula, g(t) represents the trend component of the time series, s(t) is used to capture the seasonal effect of the time series, h(t) is used to reflect the holiday effect, and ∈ t is the error term, representing the noise in the data. The Prophet algorithm specifically includes two trend methods: using a non - linear saturation growth method and a piece - wise linear method to represent the trend component. Among them, the mathematical representation of the non - linear saturation growth method is:

[0081]

[0082] This method is used for the case where the data shows a saturation growth pattern. C represents the carrying capacity, and k and m are respectively used to control the growth rate and the mid - point. The mathematical representation of the piece - wise linear method is:

[0083] g(t) = (k + a(t) T δ)t + (m + a(t) T γ)

[0084] This method assumes that the trend can be described by a linear model and that the slope changes at certain time points (i.e., change points). k is the initial slope, m is the offset, a(t) is an indicator function indicating whether a change point has been passed, δ is the slope change at each change point, and γ is used to adjust the intercept at each change point. The seasonal component s(t) is used to capture the periodic fluctuations in the data. The Prophet model allows multiple seasonal components with different periods (such as weekly or daily) to coexist, that is, the seasonal effect can be represented by a Fourier series:

[0085]

[0086] where P is the period of seasonality. In the 120 emergency call volume data, the weekly seasonality P = 7×24, and the daily seasonality P = 24. a n and b n are Fourier coefficients, and N represents the maximum number of terms in the Fourier series. The holiday effect h(t) is used to simulate the impact on the time series when a specific event or holiday occurs. It can be modeled by dummy variables to represent the occurrence of holidays and can include lead or lag effects to account for behavioral changes before and after the event. Its mathematical representation is:

[0087]

[0088] where D i (t) is the indicator function for holiday i, and λ i represents the magnitude of the holiday effect. The error term ∈ t is used to capture the data noise that cannot be explained by the trend, seasonality, or holiday effect. It is usually assumed to follow a normal distribution with a mean of zero, that is, ∈ t ~N(0, σ 2 (t)), and the variance may vary with time t.

[0089] In step S21, considering that the consumption of each target medical supply is closely related to medical data such as morbidity data and 120 emergency incident data, and these medical data have significant daily and weekly seasonality, but the trend is usually affected by the interaction of multiple complex factors such as weather, urban traffic, and urban population growth. Therefore, although the Prophet model can quickly extract seasonal features and holiday effects from time series data, in the extraction of the trend of time series, only the piecewise linear method is used, and it is difficult to accurately extract the complex trend features in medical data when the trend change point occurs. The STL trend prediction method based on exponential weighting uses LOESS to smooth the time series to extract the trend component, and fits a smooth curve by weighted regression of the data points near each time point. Finally, by exponentially weighted aggregation of the trends of each past day, complex non-linear trend features can be extracted from the time series data. Therefore, in order to further improve the predicted value of the first single-day demand for each day in the current near future for any target medical supply on the downstream side of the medical industry supply chain, preferably, for any target medical supply among the multiple target medical supplies, based on the corresponding single-day demand time series data, the predicted value of the first single-day demand for each day in the current near future for the corresponding supply on the downstream side of the medical industry supply chain is estimated based on the STL algorithm and the Prophet model, including but not limited to the following steps S211 to S213.

[0090] S211. For any target medical supply among the multiple target medical supplies, use the STL algorithm to decompose the corresponding single-day demand time series data to obtain the corresponding single-day demand trend item component time series data, where the single-day demand trend item component time series data includes the current recent historical days and the single-day demand trend item components for each day of any target medical supply in the current recent historical days on the downstream side of the medical industry supply chain.

[0091] In step S211, specifically, for any target medical supply among the multiple target medical supplies, use the STL algorithm to decompose the corresponding single-day demand time series data to obtain the corresponding single-day demand trend item component time series data, including but not limited to the following steps S2111 to S2114.

[0092] S2111. Estimate and remove the seasonal component in the single-day demand time series data y stl (t) of any target medical supply based on the loop process in the STL algorithm to obtain the new time series data x stl (t), where t represents the time node.

[0093] In the step S2111, the loop process in the STL algorithm is a prior art means and will not be elaborated herein. In addition, if the seasonal component is represented by s stl (t), then the new time series data x stl (t) = y stl (t) - s stl (t).

[0094] S2112. Based on the cubic weight function W i (t), perform locally weighted least squares regression on the new time series data x stl (t) to obtain the following local quadratic polynomial z(t):

[0095] z(t) = β0 + β1×(i - t) + β2×(i - t) 2

[0096] In the formula, β0, β1, and β2 respectively represent coefficients and are obtained through the following minimization formula:

[0097]

[0098] In the formula, d represents a preset smoothing parameter, and i ∈ [t - d, t + d].

[0099] In the step S2112, W i (t) is the regression weight. The smoothing parameter d determines the width of the regression window and can be set as a positive integer with the unit of day. In addition, the specific solution process of the minimization formula is a prior mathematical process and will not be elaborated herein.

[0100] S2113. For each day in the current recent historical multi - days, use the value on the local quadratic polynomial z(t) at the corresponding time node t as the single - day demand trend item component of the any target medical supply on the corresponding day and on the downstream side of the medical industry supply chain.

[0101] S2114. Aggregate the single - day demand trend item components of the any target medical supply on each day in the current recent historical multi - days and on the downstream side of the medical industry supply chain to obtain the single - day demand trend item component time series data of the any target medical supply.

[0102] S212. Based on the single - day demand trend item component time - series data, calculate the predicted value of the first single - day demand trend item component of any target medical supplies for each day in the current nearest future multi - days and on the downstream side of the medical industry supply chain using the dynamic exponential weighting method. In the dynamic exponential weighting method, weights are assigned to the single - day demand trend item components in different periods according to the following rules: a larger weight is assigned to the more recent single - day demand trend item component, and a smaller weight is assigned to the relatively earlier single - day demand trend item component.

[0103] In step S212, specifically, when the current nearest historical multi - days are all the days in the current nearest consecutive multi - weeks in time series and the current nearest future multi - days are all the days in the next week of the current time, based on the single - day demand trend item component time - series data, calculate the predicted value of the first single - day demand trend item component of any target medical supplies for each day in the current nearest future multi - days and on the downstream side of the medical industry supply chain. This includes, but is not limited to, the following steps S2121 - S2122.

[0104] S2121. Divide the single - day demand trend item component time - series data into multiple arrays corresponding one - to - one with the current nearest multi - weeks, and aggregate the multiple arrays to obtain the following matrix G:

[0105]

[0106] In the formula, n represents the total number of weeks in the current nearest multi - weeks, n′ represents a positive integer less than or equal to n, m′ represents a positive integer less than or equal to 7, and g n′,m′ represents the single - day demand trend item component of any target medical supplies on the m′ - th day in the n′ - th week of the current nearest multi - weeks and on the downstream side of the medical industry supply chain.

[0107] S2122. For each day in the next week of the current time, calculate the corresponding predicted value of the first single - day demand trend item component according to the following formula:

[0108]

[0109] In the formula, represents the predicted value of the first single - day demand trend item component of any target medical supplies on the m′ - th day in the next week of the current time and on the downstream side of the medical industry supply chain, n″ represents a positive integer less than or equal to n, and g n″,m′ represents the single - day demand trend item component of any target medical supplies on the m′ - th day in the n′ - th week of the current nearest multi - weeks and on the downstream side of the medical industry supply chain, and α represents a preset smoothing factor with α ∈ (0, 1).

[0110] In the step S2122, as can be seen from the above formula, for the single-day demand trend item component on the m'-th day, the corresponding weight is That is, it conforms to the following rule of the dynamic exponential weighting method for assigning weights to the single-day demand trend item components in different periods: a larger weight is assigned to the single-day demand trend item component closer to the current time, while a smaller weight is assigned to the single-day demand trend item component in the earlier period.

[0111] S213. Based on the time series data of the single-day demand trend item components, train a prediction model based on the Prophet model, and use the trained prediction model to predict the predicted values of the second single-day demand trend item components, single-day demand seasonal effect item components, single-day demand holiday effect item components, and single-day demand error item components for each day in the current nearest future days and on the downstream side of the medical industry supply chain for any target medical material.

[0112] In the step S213, since the Prophet model is an existing data prediction tool based on Python and R languages and is suitable for processing time series data with strong seasonal patterns and historical trends, the aforementioned prediction model training process and the specific process of obtaining the predicted values of the second single-day demand trend item components, single-day demand seasonal effect item components, single-day demand holiday effect item components, and single-day demand error item components for each day in the current nearest future days and on the downstream side of the medical industry supply chain for any target medical material through model application can all be routinely derived based on existing technical means and will not be elaborated here.

[0113] S214. For each day in the current nearest future days, calculate the predicted value sp1 of the first single-day demand quantity for any target medical material on the corresponding day and on the downstream side of the medical industry supply chain according to the following formula:

[0114] sp1 = w s × g sp,1 + w p × g sp,2 + s prophet + h prophet + ε prophet

[0115] In the formula, g sp,1 represents the predicted value of the first single-day demand trend item component, g sp,2 represents the predicted value of the second single-day demand trend item component, s prophet represents the predicted value of the single-day demand seasonal effect item component, h prophet represents the predicted value of the single-day demand holiday effect item component, ε prophetdenote the predicted value of the single-day demand error term component, w s and w p respectively denote preset weight coefficients and w s +w p = 1.

[0116] Based on the above steps S211 - S214, by combining the advantages of Prophet in quickly extracting seasonal features and holiday effects and the advantages of STL decomposition in quickly extracting non-linear trend features, the prediction accuracy can be effectively improved.

[0117] S22. For each of the other medical supplies relative to any one of the multiple target medical supplies, according to the corresponding single-day demand time series data and the single-day demand time series data of any one of the target medical supplies, calculate the correlation coefficient between the corresponding supply and any one of the target medical supplies, and use a machine learning algorithm to estimate the predicted value of the second single-day demand for each day in the current nearest future multi-day and on the downstream side of the medical industry supply chain for the corresponding and any one of the target medical supplies.

[0118] In step S22, in order to ensure the accuracy of the subsequent comprehensive prediction results based on the correlation coefficient, preferably, for each of the other medical supplies relative to any one of the multiple target medical supplies, calculate the correlation coefficient between the corresponding supply and any one of the target medical supplies according to the corresponding single-day demand time series data and the single-day demand time series data of any one of the target medical supplies, including but not limited to the following steps S221 - S224.

[0119] S221. For a certain other medical supply relative to any one of the multiple target medical supplies, extract a recent time series data segment from the corresponding single-day demand time series data to form a first sample S1, and also extract another time series data segment synchronous with the first sample S1 from the single-day demand time series data of any one of the target medical supplies to form a second sample S2.

[0120] S222. Perform a normal distribution KS test on the first sample S1 to calculate the first test statistic p-value p1, and also perform the normal distribution KS test on the second sample S2 to calculate the second test statistic p-value p2.

[0121] S223. If both the first test statistic p-value p1 and the second test statistic p-value p2 are greater than a preset threshold, then calculate the correlation coefficient r between the first sample S1 and the sample S2 according to the following formula q :

[0122]

[0123] In the formula, i represents a positive integer, and x i represents the i-th sample value in the first sample S1, and y i represents the i-th sample value in the second sample S2. represents the sample mean of the first sample S1. represents the sample mean of the second sample S2.

[0124] In the step S223, the preset threshold can be exemplified as 0.05.

[0125] S224. Use the correlation coefficient r q as the correlation coefficient between the certain other medical supply and any target medical supply.

[0126] In the step S22, the machine learning algorithm is a core artificial intelligence algorithm that specifically studies how a computer simulates or implements human learning behaviors to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve its own performance. It is the fundamental way to make a computer intelligent. Thus, the specific process of corresponding to each of the other medical supplies and the predicted value of the second single-day demand of any target medical supply on each day in the current nearest future multi-day and on the downstream side of the medical industry supply chain can be routinely derived based on existing technical means such as sample selection, model training, and model application, and will not be elaborated here. In addition, the machine learning algorithm can specifically but is not limited to adopting artificial intelligence algorithms based on LSTM models, Bi-LSTM models, or Attention-LSTM models, etc. The aforementioned LSTM (Long Short-Term Memory) models, Bi-LSTM models, or Attention-LSTM models, etc. are all existing machine learning models. Among them, the Attention-LSTM model is an improved model that adds an attention mechanism to the existing LSTM model (which is commonly used for time series data prediction), and the added attention mechanism is used to allow the LSTM model to dynamically focus on partial information during training so as to be able to capture more important information and improve the performance of the model. Therefore, in this embodiment, the Attention-LSTM model is preferably used as the prediction model, and this prediction model is applied to estimate the predicted value of the second single-day demand of each of the other medical supplies corresponding to and any target medical supply on each day in the current nearest future multi-day and on the downstream side of the medical industry supply chain.

[0127] S23. Based on the predicted value of the single-day demand of any of the target medical supplies on each day in the current near future and on the downstream side of the medical industry supply chain, and the predicted value of the single-day demand of the corresponding other medical supplies and the target medical supplies on each day in the current near future and on the downstream side of the medical industry supply chain, and combining the correlation coefficients between the other medical supplies and the target medical supplies, calculate the predicted value of the final single-day demand of the target medical supplies on each day in the current near future and on the downstream side of the medical industry supply chain.

[0128] In step S23, specifically, based on the predicted value of the single-day demand of any of the target medical supplies on each day in the current near future and on the downstream side of the medical industry supply chain, and the predicted value of the single-day demand of the corresponding other medical supplies and the target medical supplies on each day in the current near future and on the downstream side of the medical industry supply chain, and combining the correlation coefficients between the other medical supplies and the target medical supplies, calculating the predicted value of the final single-day demand of the target medical supplies on each day in the current near future and on the downstream side of the medical industry supply chain includes, but is not limited to: for each day in the current near future, calculate the predicted value of the final single-day demand of the target medical supplies on the corresponding day and on the downstream side of the medical industry supply chain according to the following formula:

[0129]

[0130] In the formula, x represents a positive integer, P x represents the predicted value of the final single-day demand of the target medical supplies on the x-th day in the current near future and on the downstream side of the medical industry supply chain, Y represents the total number of the target medical supplies, y' represents a positive integer less than or equal to Y - 1, η y′ represents the influence weight coefficient corresponding to the y'-th other medical supply, r q,y′ represents the correlation coefficient corresponding to the y'-th other medical supply, y'' represents a positive integer less than or equal to Y - 1, r q,y″ represents the correlation coefficient corresponding to the y''-th other medical supply, P 1,x represents the predicted value of the single-day demand of the target medical supplies on the x-th day in the current near future and on the downstream side of the medical industry supply chain, P y′,x represents the predicted value of the single-day demand of the target medical supplies on the x-th day in the current near future and on the downstream side of the medical industry supply chain corresponding to the y'-th other medical supply.

[0131] S3. Based on the inventory balance of each target medical supply on the current day and on the downstream side of the medical industry supply chain, and the predicted values of the daily demand on each day in the current near future and on the downstream side of the medical industry supply chain, optimize the material distribution plan for delivering each target medical supply from the upstream side of the medical industry supply chain to the downstream side on each day in the current near future based on the genetic optimization algorithm, to obtain the optimal material distribution plan with the highest fitness. Among them, the material distribution plan is represented by an X×Y-dimensional vector corresponding to each day in the current near future and each target medical supply. The element c in the X×Y-dimensional vector located in the x-th row and the y-th column x,y represents the material distribution volume of the y-th target medical supply from the upstream side of the medical industry supply chain to the downstream side on the x-th day in the current near future. X represents the total number of days in the current near future, Y represents the total number of the target medical supplies, x represents a positive integer less than or equal to X, y represents a positive integer less than or equal to Y, and the fitness function is designed based on being negatively correlated with the logistics cost corresponding to the material distribution plan.

[0132] In step S3, the inventory balance of each target medical supply on the current day and on the downstream side of the medical industry supply chain can be obtained through regular inventory at the end of the current day. The genetic optimization algorithm (Genetic Algorithm, GA) is an optimization algorithm that simulates the natural selection and genetic mechanism, that is, it solves the optimization problem by simulating the inheritance and variation in the biological evolution process. Its basic idea is to use genetic operations such as selection, crossover, and mutation to search for the optimal solution. To achieve the purpose of quickly optimizing the material distribution plan based on the genetic optimization algorithm, preferably, based on the inventory balance of each target medical supply on the current day and on the downstream side of the medical industry supply chain, and the predicted values of the daily demand on each day in the current near future and on the downstream side of the medical industry supply chain, optimize the material distribution plan for delivering each target medical supply from the upstream side of the medical industry supply chain to the downstream side on each day in the current near future based on the genetic optimization algorithm, to obtain the optimal material distribution plan with the highest fitness, including but not limited to the following steps S31 to S35.

[0133] S31. Initialize the genetic optimization algorithm and include algorithm parameters such as the population size N and the maximum number of iterations T max and initialize the current iteration number T = 0, and then execute step S32.

[0134] S32. Randomly generate N material distribution plans that respectively meet the constraints of the distribution plan and are used to distribute each of the target medical materials from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain on each day of the current nearest future multi-days, and use the N material distribution plans as N individuals one by one to form an initial population, and then execute step S33. Among them, the material distribution plan is represented by an X×Y-dimensional vector corresponding to each day of the current nearest future multi-days and each of the target medical materials. The element c in the X×Y-dimensional vector at the x-th row and the y-th column x,y represents the material distribution volume of the y-th target medical material from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain on the x-th day of the current nearest future multi-days. X represents the total number of days in the current nearest future multi-days, Y represents the total number of the target medical materials, x represents a positive integer less than or equal to X, y represents a positive integer less than or equal to Y. The distribution plan constraints include but are not limited to the following: P x′+1,y ≤I b,x′,y +c x′,y -P x′,y ≤I b,max,y , where x′ represents a positive integer less than or equal to X - 1, P x′+1,y represents the predicted value of the daily demand of the y-th target medical material on the (x′ + 1)-th day in the current nearest future multi-days and on the downstream side of the medical industry supply chain. I b,x′,y represents the inventory balance of the y-th target medical material on the x′-th day in the current nearest future multi-days and on the downstream side of the medical industry supply chain. c x′,y represents the material distribution volume of the y-th target medical material from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain on the x′-th day in the current nearest future multi-days. P x′,y represents the predicted value of the daily demand of the y-th target medical material on the x′-th day in the current nearest future multi-days and on the downstream side of the medical industry supply chain.

[0135] I b,max,y represents the maximum allowable inventory of the y-th target medical material on the downstream side of the medical industry supply chain.

[0136] In step S32, the distribution plan constraints are used to ensure that while not exceeding the maximum inventory, the inventory balances of each of the target medical materials respectively meet the consumption demands in the next day; specifically, when x′ is equal to 1,

[0137] I b,x′,y is the inventory balance of the y-th target medical material on that day and on the downstream side of the medical industry supply chain, and can be based on the formula Ib,x′+1,y = I b,x′,y + c x′,y - P x′,y Successively calculate to obtain the inventory balance I of the y-th target medical supply on the day before the (x'+1)-th day in the current nearest future multi-day period and on the downstream side of the medical industry supply chain b,x′+1,y (that is, the inventory balance of the y-th target medical supply on the x'-th day in the current nearest future multi-day period and on the downstream side of the medical industry supply chain). In addition, in order to ensure that the material delivery volume is not too scattered, specifically, the delivery plan constraint conditions also include but are not limited to: c x,y is a natural multiple of c stp,y , where c stp,y represents the unit material delivery volume of transporting the y-th target medical supply from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain by a transport vehicle; for example, if the y-th target medical supply is a drug and the corresponding minimum transport packaging box contains 100 boxes of drugs, then 100 boxes here is the unit material delivery volume, and at this time c x,y needs to be 0 boxes, 100 boxes, 200 boxes, 300 boxes, etc.).

[0138] S33. For each individual in the current population, determine the corresponding logistics cost according to the corresponding material delivery plan, calculate the corresponding fitness according to this logistics cost, and then execute step S34, where the fitness function is designed based on being negatively correlated with the logistics cost corresponding to the material delivery plan.

[0139] In step S33, specifically, for each individual in the current population, determining the corresponding logistics cost according to the corresponding material delivery plan includes but is not limited to the following steps S331 to S332.

[0140] S331. For any individual in the current population, determine the corresponding required number of transport vehicle trips according to the corresponding material delivery plan and the single-load capacity of the transport vehicle.

[0141] In step S331, the specific process of determining the required number of transport vehicle trips according to the material delivery plan and the single-load capacity of the transport vehicle is a prior art means. For example, if the material delivery plan indicates that 50 boxes, 60 boxes, 52 boxes, 30 boxes, 45 boxes, 67 boxes, and 44 boxes of medical supplies need to be delivered on each day of the next week, then the required number of transport vehicle trips can be determined to be 3 + 3 + 3 + 2 + 3 + 4 + 3 = 21 vehicle trips.

[0142] S332. Calculate the logistics cost corresponding to any one of the individuals according to the required number of transport vehicle trips corresponding to the individual, where the logistics cost is positively correlated with the required number of transport vehicle trips.

[0143] In step S332, the positive correlation function between the logistics cost and the required number of transport vehicle trips can be obtained by conventional fitting based on historical transportation situations (such as starting from fuel consumption costs and labor costs, etc.).

[0144] S34. Determine whether the current iteration number T has reached the maximum iteration number T max If so, select the individual corresponding to the highest fitness from the current population as the optimal work order allocation plan; otherwise, increment the current iteration number T by 1, and then execute step S35.

[0145] After step S34, if the current highest fitness exceeds the preset fitness threshold, the individual corresponding to the current highest fitness can also be directly used as the optimal material distribution plan, and the process can be ended in advance.

[0146] S35. According to each individual and the fitness of each individual, through the selection operation, crossover operation and mutation operation in the genetic optimization algorithm, obtain N new individuals that meet the constraints of the distribution plan respectively to form a new population, and then return to execute step S33.

[0147] In step S35, the selection operation, the crossover operation and the mutation operation (that is, randomly changing some gene positions in the chromosome at a certain mutation rate to increase the diversity of the population), etc. are all conventional operations in the existing genetic optimization algorithm. For example, the selection operation can adopt roulette wheel selection or tournament selection, etc., and the crossover operation can adopt single-point crossover or two-point crossover, etc. Specific details are not elaborated here.

[0148] S4. Push the optimal material distribution plan to the upstream side of the medical industry supply chain for implementation.

[0149] Based on the supply chain ecological collaborative management method described in the foregoing steps S1 to S4, a new supply chain ecological collaborative management solution for inventory and logistics collaborative optimization between the upstream and downstream of the supply chain is provided. That is, for each target medical material, the predicted value of the single-day demand for each day in the current nearest future multi-day of the corresponding material is estimated according to the time-series data of the single-day demand of multiple target medical materials. Then, combined with the current inventory balance of each material, the material distribution plan for delivering each material from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain in each day of the current nearest future multi-day is optimized based on the genetic optimization algorithm to obtain the optimal material distribution plan with the highest fitness. Finally, the optimal plan is pushed to the upstream side of the supply chain for implementation. In this way, considering the demand situation of medical materials in the future period and the logistics cost, the inventory collaborative ability and logistics collaborative ability between upstream and downstream enterprises in the supply chain and the supply chain efficiency in the medical industry can be improved, which is convenient for practical application and promotion.

[0150] As Figure 2 shown, in the second aspect of this embodiment, a virtual system for implementing the supply chain ecological collaborative management method described in the first aspect is provided, including but not limited to a time-series data acquisition unit, a material demand prediction unit, a distribution plan optimization unit, and an optimal plan push unit that are sequentially communicatively connected;

[0151] The time-series data acquisition unit is used to acquire the time-series data of the single-day demand of multiple target medical materials on the downstream side of the medical industry supply chain. Among them, the time-series data of the single-day demand includes the current nearest historical multi-day that are sequentially continuous in time series and the single-day demand of the corresponding materials on each day in the current nearest historical multi-day and on the downstream side of the medical industry supply chain;

[0152] The material demand prediction unit is used to estimate the predicted value of the single-day demand of each target medical material in the multiple target medical materials on each day in the current nearest future multi-day and on the downstream side of the medical industry supply chain according to the time-series data of the single-day demand of the multiple target medical materials;

[0153] The delivery plan optimization unit is configured to optimize the material delivery plan for delivering each of the target medical supplies from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain in each of the current nearest future days based on a genetic optimization algorithm according to the inventory balance of each of the target medical supplies on the current day and on the downstream side of the medical industry supply chain, and the predicted value of the single-day demand in each of the current nearest future days and on the downstream side of the medical industry supply chain, so as to obtain an optimal material delivery plan with the highest fitness. Wherein, the material delivery plan is represented by an X×Y-dimensional vector corresponding to each of the current nearest future days and each of the target medical supplies, and the element c at the x-th row and the y-th column in the X×Y-dimensional vector x,y represents the material delivery volume of the y-th target medical supply from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain on the x-th day in the current nearest future days. X represents the total number of days in the current nearest future days, Y represents the total number of the target medical supplies, x represents a positive integer less than or equal to X, and y represents a positive integer less than or equal to Y. The fitness function is designed based on being negatively correlated with the logistics cost corresponding to the material delivery plan;

[0154] The optimal plan pushing unit is configured to push the optimal material delivery plan to the upstream side of the medical industry supply chain for implementation.

[0155] For the working process, working details and technical effects of the foregoing system provided in the second aspect of this embodiment, reference may be made to the supply chain ecological collaborative management method described in the first aspect, which will not be elaborated herein.

[0156] As Figure 3As shown in the figure, in the third aspect of this embodiment, a computer system for executing the supply chain ecological collaborative management method described in the first aspect is provided, including a memory, a processor, and a transceiver that are communicatively connected in sequence. Among them, 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 supply chain ecological collaborative management method described in the first aspect. Specifically, for example, the memory may include, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a flash memory, a first input first output (FIFO), and / or a first input last output (FILO), etc.; the processor may be, but is not limited to, a microprocessor of the STM32F105 series. In addition, the computer device may also include, but is not limited to, a power module, a display screen, and other necessary components.

[0157] For the working process, working details, and technical effects of the foregoing computer system provided in the third aspect of this embodiment, reference may be made to the supply chain ecological collaborative management method described in the first aspect, which will not be elaborated here.

[0158] In the fourth aspect of this embodiment, a computer-readable storage medium storing instructions including the supply chain ecological collaborative management method described in the first aspect is provided, that is, instructions are stored on the computer-readable storage medium, and when the instructions are run on a computer, the supply chain ecological collaborative management method described in the first aspect is executed. Among them, the computer-readable storage medium refers to a carrier for storing data, which may include, but is not limited to, a floppy disk, an optical disc, a hard disk, a flash memory, a USB flash drive, and / or a memory stick, etc. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0159] For the working process, working details, and technical effects of the foregoing computer-readable storage medium provided in the fourth aspect of this embodiment, reference may be made to the supply chain ecological collaborative management method described in the first aspect, which will not be elaborated here.

[0160] In the fifth aspect of this embodiment, a computer program product is provided, including a computer program or instructions, and the computer program or the instructions, when executed by a computer, implement the supply chain ecological collaborative management method described in the first aspect. Among them, the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0161] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A supply chain ecological collaborative management method applied to the medical industry, characterized in that, Including: Obtaining the time-series data of the single-day demand for multiple target medical supplies on the downstream side of the medical industry supply chain. Among them, the time-series data of the single-day demand includes the most recent consecutive multiple days in time sequence and the single-day demand for the corresponding supplies on each of these days on the downstream side of the medical industry supply chain; For each of the multiple target medical supplies, based on the time-series data of the single-day demand for the multiple target medical supplies, estimating the predicted value of the single-day demand for the corresponding supply on each of the most recent future multiple days on the downstream side of the medical industry supply chain; Based on the inventory balance of each target medical supply on the current day and on the downstream side of the medical industry supply chain, as well as the predicted values of the daily demand on each day in the current near future and on the downstream side of the medical industry supply chain, the material distribution plan for delivering each target medical supply from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain on each day in the current near future is optimized based on a genetic optimization algorithm to obtain an optimal material distribution plan with the highest fitness. Among them, the material distribution plan is represented by an X×Y-dimensional vector corresponding to each day in the current near future and each target medical supply. The element c at the x-th row and y-th column in the X×Y-dimensional vector x,y represents the material distribution volume of the y-th target medical supply from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain on the x-th day in the current near future. X represents the total number of days in the current near future, Y represents the total number of the target medical supplies, x represents a positive integer less than or equal to X, and y represents a positive integer less than or equal to Y. The fitness function is designed based on being negatively correlated with the logistics cost corresponding to the material distribution plan; Pushing the optimal material distribution plan to the upstream side of the medical industry supply chain for implementation.

2. The supply chain ecological collaborative management method according to claim 1, wherein For each of the multiple target medical supplies, based on the time-series data of the single-day demand for the multiple target medical supplies, estimating the predicted value of the single-day demand for the corresponding supply on each of the most recent future multiple days on the downstream side of the medical industry supply chain, including: For any one of the multiple target medical supplies, based on the corresponding time-series data of the single-day demand, estimating the first predicted value of the single-day demand for the corresponding supply on each of the most recent future multiple days on the downstream side of the medical industry supply chain based on the STL algorithm and the Prophet model; For each of the other medical supplies relative to any one of the multiple target medical supplies, calculating the correlation coefficient between the corresponding supply and the any one target medical supply according to the corresponding time-series data of the single-day demand and the time-series data of the single-day demand of the any one target medical supply, and estimating the second predicted value of the single-day demand for the corresponding and the any one target medical supply on each of the most recent future multiple days on the downstream side of the medical industry supply chain using a machine learning algorithm; According to the first predicted value of the single-day demand for the any one target medical supply on each of the most recent future multiple days on the downstream side of the medical industry supply chain and the second predicted value of the single-day demand for the corresponding and the any one target medical supply on each of the most recent future multiple days on the downstream side of the medical industry supply chain for each of the other medical supplies, and combining the correlation coefficients between each of the other medical supplies and the any one target medical supply, calculating the final predicted value of the single-day demand for the any one target medical supply on each of the most recent future multiple days on the downstream side of the medical industry supply chain.

3. The supply chain ecological collaborative management method according to claim 2, characterized in that For any one of the multiple target medical supplies, based on the corresponding time-series data of the single-day demand, estimating the first predicted value of the single-day demand for the corresponding supply on each of the most recent future multiple days on the downstream side of the medical industry supply chain based on the STL algorithm and the Prophet model, including: For any one of the multiple target medical supplies, use the STL algorithm to decompose the corresponding single-day demand time series data to obtain the corresponding single-day demand trend component time series data, where the single-day demand trend component time series data includes the current most recent historical multi-days and the single-day demand trend component of each day of the any one target medical supply in the current most recent historical multi-days and on the downstream side of the medical industry supply chain; Based on the single-day demand trend component time series data, calculate the first single-day demand trend component prediction value of the any one target medical supply for each day in the current most recent future multi-days and on the downstream side of the medical industry supply chain by using the dynamic exponential weighting method, where the dynamic exponential weighting method assigns weights to the single-day demand trend components in different periods according to the following rules: assign a larger weight to the more recent single-day demand trend component and a smaller weight to the earlier single-day demand trend component; Based on the single-day demand trend component time series data, train a prediction model using the Prophet model, and apply the trained prediction model to predict the second single-day demand trend component prediction value, the single-day demand seasonal effect component prediction value, the single-day demand holiday effect component prediction value, and the single-day demand error component prediction value of the any one target medical supply for each day in the current most recent future multi-days and on the downstream side of the medical industry supply chain; For each day in the current most recent future multi-days, calculate the first single-day demand prediction value sp1 of the any one target medical supply for the corresponding day and on the downstream side of the medical industry supply chain according to the following formula: sp1 = w s × g sp,1 + w p × g sp,2 + s prophet + h prophet + ε prophet where g sp,1 represents the predicted value of the first single-day demand trend item component, g sp,2 represents the predicted value of the second single-day demand trend item component, s prophet represents the predicted value of the single-day demand seasonal effect item component, h prophet represents the predicted value of the single-day demand holiday effect item component, ε prophet represents the predicted value of the single-day demand error item component, w s and w p respectively represent preset weight coefficients and w s +w p = 1.

4. The supply chain ecological collaborative management method according to claim 3, wherein, When the current most recent historical multi-days are all the days of the current most recent consecutive multi-weeks in time series and the current most recent future multi-days are all the days of the next week, based on the single-day demand trend component time series data, calculate the first single-day demand trend component prediction value of the any one target medical supply for each day in the current most recent future multi-days and on the downstream side of the medical industry supply chain, including: Divide the single-day demand trend component time series data into multiple arrays corresponding one by one to the current most recent multi-weeks, and aggregate the multiple arrays to obtain the following matrix G: Wherein, n represents the total number of weeks of the current most recent multiple weeks, n' represents a positive integer less than or equal to n, m' represents a positive integer less than or equal to 7, and g n′,m′ represents the single-day demand trend item component of any one of the target medical supplies on the m'-th day in the n'-th week of the current most recent multiple weeks and on the downstream side of the medical industry supply chain; For each day in the next week, calculate the corresponding first single-day demand trend component prediction value according to the following formula: In the formula, represents the predicted value of the first single-day demand trend item component of any of the target medical supplies on the m'-th day within the current next week and on the downstream side of the medical industry supply chain. n″ represents a positive integer less than or equal to n, and g n″,m′ represents the single-day demand trend item component of any of the target medical supplies on the m'-th day within the n'-th week among the current most recent multiple weeks and on the downstream side of the medical industry supply chain. α represents a preset smoothing factor and α ∈ (0, 1).

5. The supply chain ecological collaborative management method according to claim 2, wherein For each of the other medical supplies relative to the any one target medical supply among the multiple target medical supplies, calculate the correlation coefficient between the corresponding medical supply and the any one target medical supply according to the corresponding single-day demand time series data and the single-day demand time series data of the any one target medical supply, including: For a certain other medical material among the multiple target medical materials relative to any of the target medical materials, extract the latest time series data from the corresponding single-day demand time series data to form a first sample S1, and further extract another time series data of the same period as the first sample S1 from the single-day demand time series data of any of the target medical materials to form a second sample S2; Performing a normal distribution KS check on the first sample S1 to calculate a first check statistic p value p1, and also performing the normal distribution KS check on the second sample S2 to calculate a second check statistic p value p2; If both the p-value p1 of the first check statistic and the p-value p2 of the second check statistic are greater than a preset threshold, the correlation coefficient r between the first sample S1 and the sample S2 is calculated according to the following formula q : where \(i\) represents a positive integer, \(x\) i represents the \(i\)-th sample value in the first sample \(S1\), \(y\) i represents the \(i\)-th sample value in the second sample \(S2\), represents the sample mean of the first sample \(S1\), represents the sample mean of the second sample \(S2\); Take the correlation coefficient r q as the correlation coefficient between a certain other medical supply and any one of the target medical supplies.

6. The supply chain ecological collaborative management method according to claim 2, wherein According to the first daily demand forecast value of any target medical material on each of the current, recent and future multiple days and on the downstream side of the medical industry supply chain and the second daily demand forecast value corresponding to each other medical material and any target medical material on each of the current, recent and future multiple days and on the downstream side of the medical industry supply chain, combined with the correlation coefficient between each other medical material and any target medical material, the final daily demand forecast value of any target medical material on each of the current, recent and future multiple days and on the downstream side of the medical industry supply chain is calculated, including: For each of the current and recent future days, the final daily demand forecast value of any target medical supplies on the corresponding day and at the downstream side of the medical industry supply chain is calculated according to the following formula: Where x represents a positive integer, P x represents the predicted value of the final single-day demand of any one of the target medical supplies on the x-th day in the current nearest future multi-day period and on the downstream side of the medical industry supply chain. Y represents the total number of the target medical supplies, y' represents a positive integer less than or equal to Y - 1, and η y′ represents the influence weight coefficient corresponding to the y'-th other medical supply, r q,y′ represents the correlation coefficient corresponding to the y'-th other medical supply, y'' represents a positive integer less than or equal to Y - 1, and r q,y″ represents the correlation coefficient corresponding to the y''-th other medical supply, P 1,x represents the predicted value of the first single-day demand of any one of the target medical supplies on the x-th day in the current nearest future multi-day period and on the downstream side of the medical industry supply chain. P y′,x represents the predicted value of the second single-day demand of any one of the target medical supplies on the x-th day in the current nearest future multi-day period and on the downstream side of the medical industry supply chain corresponding to the y'-th other medical supply.

7. The supply chain ecological collaborative management method according to claim 1, wherein According to the inventory balance of each target medical material on the current day and at the downstream side of the medical industry supply chain and the daily demand forecast value on each of the current and recent future days and at the downstream side of the medical industry supply chain, the material distribution plan for distributing each target medical material from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain on each of the current and recent future days is optimized based on a genetic optimization algorithm to obtain an optimal material distribution plan with the highest fitness, including the following steps S31 to S35: S31. Initialize the genetic optimization algorithm with algorithm parameters including the population size N and the maximum number of iterations T, initialize the current number of iterations T = 0, and then execute step S32; max The algorithm parameters, and initialize the current number of iterations T = 0, and then execute step S32; S32. Randomly generate N material distribution plans that respectively meet the constraints of the distribution plan and are used to distribute each of the target medical materials from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain on each day of the current nearest future multi - days, and use the N material distribution plans as N individuals one - to - one to form an initial population, and then execute step S33. Wherein, the material distribution plan is represented by an X×Y - dimensional vector corresponding to each day of the current nearest future multi - days and each of the target medical materials. The element c in the X×Y - dimensional vector at the x - th row and y - th column x,y represents the material distribution volume of the y - th target medical material from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain on the x - th day of the current nearest future multi - days. X represents the total number of days in the current nearest future multi - days, Y represents the total number of the target medical materials, x represents a positive integer less than or equal to X, y represents a positive integer less than or equal to Y. The distribution plan constraints include the following: P x′+1,y ≤I b,x′,y +c x′,y -P x′,y ≤I b,max,y , wherein, x′ represents a positive integer less than or equal to X - 1, P x′+1,y represents the predicted value of the single - day demand of the y - th target medical material on the (x′ + 1) - th day in the current nearest future multi - days and on the downstream side of the medical industry supply chain, I b,x′,y represents the remaining inventory balance of the y - th target medical material on the x′ - th day in the current nearest future multi - days and on the downstream side of the medical industry supply chain, c x′,y represents the material distribution volume of the y - th target medical material from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain on the x′ - th day of the current nearest future multi - days, P x′,y represents the predicted value of the single - day demand of the y - th target medical material on the x′ - th day in the current nearest future multi - days and on the downstream side of the medical industry supply chain I b,max,y represents the maximum allowable inventory of the y-th target medical supply on the downstream side of the medical industry supply chain; S33. For each individual in the current population, determine the corresponding logistics cost according to the corresponding material distribution plan, and calculate the corresponding fitness according to the logistics cost, and then execute step S34, wherein the fitness function is designed based on the negative correlation with the logistics cost corresponding to the material distribution plan; S34. Determine whether the current iteration count T has reached the maximum iteration count T max , and if so, select the individual corresponding to the highest fitness from the current population as the optimal work order allocation scheme; otherwise, increment the current iteration count T by 1, and then execute step S35; S35. According to the individuals and their fitness, through the selection operation, crossover operation and mutation operation in the genetic optimization algorithm, N new individuals that respectively meet the constraints of the distribution plan are obtained to form a new population, and then return to execute step S33.

8. The supply chain ecological collaborative management method according to claim 7, characterized in that The constraints of the delivery plan further include: c x,y is a natural multiple of c stp,y , where c stp,y represents the unit material delivery volume for delivering the y-th target medical material from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain by a transport vehicle; For each individual in the current population, the corresponding logistics cost is determined according to the corresponding material distribution plan, including: For any individual in the current population, the number of required transport trips is determined according to the corresponding material distribution plan and the single carrying capacity of the transport vehicle; According to the required number of transport vehicle trips corresponding to any one of the individuals, the logistics cost corresponding to any one of the individuals is calculated, wherein the logistics cost is positively correlated with the required number of transport vehicle trips.

9. A supply chain ecological collaborative management system applied to the medical industry, characterized in that, It includes a time series data acquisition unit, a material demand forecasting unit, a distribution plan optimization unit, and an optimal plan pushing unit that are sequentially communicatively connected; The time series data acquisition unit is configured to acquire the time series data of the single-day demand of multiple target medical materials on the downstream side of the medical industry supply chain. Among them, the time series data of the single-day demand includes the current recent consecutive days in time sequence and the single-day demand of the corresponding materials on each day of the current recent consecutive days and on the downstream side of the medical industry supply chain; The material demand forecasting unit is configured to estimate the predicted value of the single-day demand of each corresponding material on each day of the current recent future days and on the downstream side of the medical industry supply chain for each target medical material among the multiple target medical materials according to the time series data of the single-day demand of the multiple target medical materials; The delivery plan optimization unit is configured to optimize the material delivery plan for delivering each target medical material from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain in each of the current nearest future days based on a genetic optimization algorithm according to the inventory balance of each target medical material on the current day and on the downstream side of the medical industry supply chain and the predicted value of the single-day demand in each of the current nearest future days and on the downstream side of the medical industry supply chain, so as to obtain an optimal material delivery plan with the highest fitness. Wherein, the material delivery plan is represented by an X×Y-dimensional vector corresponding to each of the current nearest future days and each target medical material, and the element c at the x-th row and y-th column in the X×Y-dimensional vector x,y represents the material delivery volume of the y-th target medical material from the upstream side of the medical industry supply chain to the downstream side of the medical industry supply chain on the x-th day in the current nearest future days, X represents the total number of days in the current nearest future days, Y represents the total number of the target medical materials, x represents a positive integer less than or equal to X, y represents a positive integer less than or equal to Y, and the fitness function is designed based on being negatively correlated with the logistics cost corresponding to the material delivery plan; The optimal plan pushing unit is configured to push the optimal material distribution plan to the upstream side of the medical industry supply chain for implementation.

10. A computer system, characterized in that, It includes a memory, a processor, and a transceiver that are sequentially communicatively connected. Among them, 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 supply chain ecological collaborative management method according to any one of claims 1 to 8.

Images