Material inventory management method and device, equipment and storage medium

Abstract

The invention provides a material inventory management method and device, equipment and a storage medium, and the method comprises the steps: determining the total cost of a storage supply chain based on the storage supply chain data of at least one material and to-be-optimized parameters through employing a mayfly naiad algorithm integrated with at least one strategy, such as a position optimization strategy, a speed optimization strategy and a search range optimization strategy; according to the method, the storage supply chain total cost is optimized, the to-be-optimized parameters are iteratively optimized with the minimum storage supply chain total cost as the optimization target, inventory management operation is driven based on the optimized parameter values after iteration is finished, automatic optimization of multi-node and multi-category material inventory parameters is achieved, the inventory collaboration requirement of a complex supply chain can be met, and the inventory cost in the supply chain is reduced.

Description

Technical Field

[0001] This disclosure relates to artificial intelligence technology, and in particular to a material inventory management method, apparatus, equipment, and storage medium. Background Technology

[0002] In the warehousing supply chain, inventory management requires managers to handle the dynamic scheduling of multiple categories of materials. For example, in the home decoration industry, the warehousing supply chain involves multiple nodes such as suppliers, regional warehouses, and store warehouses to coordinate the scheduling of multiple categories of materials such as boards, hardware, and lighting fixtures.

[0003] Traditional inventory management methods rely on the experience of managers or simple rules, which are difficult to adapt to scenarios such as home decoration where demand fluctuates greatly (such as seasonal decoration peaks), material characteristics vary significantly (such as the different transportation and storage costs of fragile items and general parts), and inventory costs are sensitive (including warehousing, transportation, and stockout losses). This can easily lead to inventory backlog or material shortages, resulting in high warehousing costs. Summary of the Invention

[0004] This disclosure provides a material inventory management method that can meet the inventory coordination needs of complex supply chains, reduce inventory backlog and lower stockout rates, thereby reducing inventory costs in the supply chain.

[0005] One aspect of this disclosure provides a material inventory management method, including: Acquire warehousing supply chain data for at least one material, wherein the warehousing supply chain data includes demand, warehousing cost information, and the current inventory of the material at at least one node in the warehousing supply chain; The optimization parameters corresponding to the at least one material are encoded as position vectors of mayfly individuals. Using the mayfly algorithm, with the goal of minimizing the total cost of the warehousing supply chain, the position vectors are iteratively optimized based on a pre-configured optimization strategy. The optimization parameters include at least one of the material transportation volume and node inventory threshold corresponding to the supply chain node. The total cost of the warehousing supply chain is calculated based on the warehousing supply chain data and the optimization parameters. The pre-configured optimization strategy includes at least one of a position optimization strategy, a speed optimization strategy, and a search range optimization strategy. The position optimization strategy updates the search speed of mayfly individuals using the median of the mayfly population position vector as the population reference position. The speed optimization strategy optimizes the search direction of mayfly individuals using dynamically changing coefficient enhancement factors. The search range optimization strategy expands the search range and refines the search of mayfly individuals through sine and cosine operations. In response to the completion of the iteration, the inventory management operation is driven based on the parameter values ​​of the parameters to be optimized output by the mayfly algorithm.

[0006] Optionally, the step of using the mayfly algorithm to iteratively optimize the location vector based on a pre-configured optimization strategy, with the goal of minimizing the total cost of the warehousing supply chain, includes: For any mayfly individual, based on the warehousing supply chain data and the t-th position vector obtained in the t-th iteration, calculate the t-th function value of the fitness function, where the function value of the fitness function represents the total cost of the warehousing supply chain, and t is a positive integer; The individual reference position of any mayfly individual is updated based on the t-th function value, where the individual reference point is the point corresponding to the position vector with the smallest function value of the fitness function among the first t position vectors of the mayfly individual; For any individual mayfly, the (t+1)th velocity vector of the individual mayfly is determined based on the individual reference position and the group reference position; Based on the (t+1)th velocity vector, the position of each mayfly individual is updated to obtain the (t+1)th position vector.

[0007] Optionally, the at least one optimization strategy includes the position optimization strategy, wherein determining the (t+1)th velocity vector of the mayfly individual based on the individual reference position and the group reference position includes: Based on the t-th position vector of each mayfly in the mayfly population after the t-th iteration, update the median of the position vector of the mayfly population; The median of the position vector is used as the group reference position. Based on the individual reference position and the group reference position, the (t+1)th velocity vector of the mayfly individual is determined.

[0008] Optionally, the at least one optimization strategy includes the velocity optimization strategy, wherein determining the (t+1)th velocity vector of the mayfly individual based on the individual reference position and the group reference position includes: The individual reference position and the group reference position are input into the velocity calculation formula to obtain the (t+1)th velocity vector. The (t+1)th velocity vector in the velocity calculation formula is the sum of a first calculation term, a second calculation term, and a third calculation term. The first calculation term is the product of the nonlinear gravity coefficient and the t-th velocity vector. The second calculation term is the product of a first attraction enhancement coefficient and a first position difference. The third calculation term is the product of a second attraction enhancement coefficient and a second position difference. The nonlinear gravity coefficient decreases as the iteration number t increases. The first position difference is the difference between the individual reference position and the t-th position vector. The second position difference is the difference between the group reference position and the t-th position vector. An attraction enhancement factor is embedded in the first attraction enhancement coefficient and the second attraction enhancement coefficient. The attraction enhancement factor decreases as the distance between the mayfly individual and the group reference position increases.

[0009] Optionally, the at least one optimization strategy includes the search range optimization strategy, wherein updating the position of each mayfly individual based on the (t+1)th velocity vector to obtain the (t+1)th position vector includes: In response to t being less than the number of times threshold, the sum of the t-th position vector and the (t+1)-th velocity vector is determined as the (t+1)-th position vector; The method further includes: In response to t being greater than or equal to the number threshold, the sum of the t-th position vector and the sine and cosine formulas is determined as the (t+1)-th position vector, where the sine and cosine formulas are either the sine function of the target distance or the cosine function of the target distance, and the target distance is the distance between the point corresponding to the t-th position vector and the group reference position.

[0010] Optionally, the mayfly population includes female and male populations, the node inventory threshold in the parameters to be optimized includes the replenishment threshold from the upstream node to the intermediate node and the safety stock of the downstream node, and the material transportation volume includes the material transportation batch from the intermediate node to the downstream node. The determination of the (t+1)th velocity vector of any individual mayfly, based on the individual's reference position and the group's reference position, includes: In response to the fact that the mayfly individual is male, the individual reference point and the group reference position are input into the male velocity calculation formula to obtain the (t+1)th velocity vector of the mayfly individual; In response to the fact that the mayfly individual is female, the individual reference position and the group reference position are input into the female velocity calculation formula to obtain the (t+1)th velocity vector of the mayfly individual; In the male speed calculation formula, the weight of the first speed component is greater than the weight of the second speed component. In the female speed calculation formula, the weight of the second speed component is greater than the weight of the first speed component. The first speed component includes the speed component corresponding to the replenishment threshold from the upstream node to the intermediate node. The second speed component includes the speed component corresponding to the material transportation batch from the intermediate node to the downstream node and the speed component corresponding to the safety stock of the downstream node.

[0011] Optionally, after updating the position of each mayfly individual based on the (t+1)th velocity vector to obtain the (t+1)th position vector, the method further includes: In response to reaching the mating cycle, target female individuals and target male individuals are determined. The target female individuals include the n female individuals with the smallest corresponding function value at the (t+1)th digit, and the target male individuals include the n male individuals with the smallest corresponding function value at the (t+1)th digit, where n is a positive integer. The target female individual and the target male individual are paired according to a preset method to generate m offspring mayfly individuals, thus obtaining a candidate mayfly population. The position vector of the offspring mayfly individual is the weighted average of the position vectors of the corresponding target male individual and the target female individual, where m is a positive integer. The m mayfly individuals with the largest function value at the (t+1)th t- ...

[0012] In another aspect of this disclosure, a material inventory management device is provided, comprising: The acquisition module is used to acquire warehousing supply chain data corresponding to at least one material. The warehousing supply chain data includes demand, warehousing cost information, and the current inventory of the material at at least one node in the warehousing supply chain. An iterative module is used to encode the optimization parameters corresponding to the at least one material into the position vector of an individual mayfly. Using the mayfly algorithm, with the goal of minimizing the total cost of the warehousing supply chain, the module iteratively optimizes the position vector based on a pre-configured optimization strategy. The optimization parameters include at least one of the material transportation volume and node inventory threshold corresponding to the supply chain node. The total cost of the warehousing supply chain is calculated based on the warehousing supply chain data and the optimization parameters. The pre-configured optimization strategy includes at least one of a position optimization strategy, a speed optimization strategy, and a search range optimization strategy. The position optimization strategy updates the search speed of an individual mayfly using the median of the mayfly population's position vector as the population reference position. The speed optimization strategy optimizes the search direction of an individual mayfly using dynamically changing coefficient enhancement factors. The search range optimization strategy expands the search range and refines the search of an individual mayfly through sine and cosine operations. The management module is used to drive inventory management operations based on the parameter values ​​of the parameters to be optimized output by the optimized mayfly algorithm in response to the achievement of the iteration termination condition.

[0013] In another aspect of this disclosure, an electronic device is provided, comprising: Memory, used to store computer programs; A processor is configured to execute a computer program stored in the memory, wherein, when the computer program is executed, it implements the methods described above.

[0014] In another aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the methods described above.

[0015] In another aspect of this disclosure, a computer program is provided, including computer program instructions that, when executed by a processor, implement the method described above.

[0016] Based on the embodiments of this disclosure, the mayfly algorithm, which integrates at least one strategy such as position optimization, speed optimization, and search range optimization, determines the total cost of the warehousing supply chain based on the warehousing supply chain data of at least one material and the parameters to be optimized. The algorithm then iteratively optimizes the parameters to be optimized with the goal of minimizing the total cost of the warehousing supply chain. After iteration, the optimized parameter values ​​drive inventory management operations, achieving automatic optimization of inventory parameters for multiple nodes and multiple material categories. Specifically, the position optimization strategy updates the individual mayfly speeds using the median position of the individual mayfly's location as the group reference position, which can balance the inventory of multiple material categories and avoid parameter dominance for a single material category. The optimization and speed optimization strategies utilize dynamically changing coefficients to enhance the search direction of individual mayflies, balancing global exploration and local development. The search range optimization strategy expands the search range and granularity of individual mayflies through sine and cosine operations, addressing both sudden demand expansion and refined local parameters. Considering the characteristics of the home improvement industry—large demand fluctuations and significant material-specific differences—the mayfly algorithm can dynamically balance global search capabilities with local optimization capabilities. This meets the inventory coordination needs of complex supply chains, improves supply chain response speed, reduces inventory backlog, and lowers stockout rates, thereby reducing inventory costs in the supply chain.

[0017] The technical solutions of this disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0018] The accompanying drawings, which form part of this specification, illustrate embodiments of this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0019] This disclosure will become clearer with reference to the accompanying drawings and the following detailed description, wherein: Figure 1 A flowchart of one embodiment of the material inventory management method disclosed herein; Figure 2 This is a flowchart of another embodiment of the material inventory management method disclosed herein; Figure 3 This is a flowchart of another embodiment of the material inventory management method disclosed herein; Figure 4 This is a schematic diagram of the structure of one embodiment of the material inventory management device disclosed herein; Figure 5 This is a schematic diagram of another embodiment of the material inventory management device disclosed herein; Figure 6This is a schematic diagram of the structure of an application embodiment of the electronic device disclosed herein. Detailed Implementation

[0020] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present disclosure.

[0021] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of this disclosure are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.

[0022] It should also be understood that in the embodiments disclosed herein, "a plurality of" may refer to two or more, and "at least one" may refer to one, two or more.

[0023] It should also be understood that any component, data or structure mentioned in the embodiments of this disclosure can generally be understood as one or more unless expressly defined or given to the contrary in the context.

[0024] Furthermore, the term "and / or" in this disclosure is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this disclosure generally indicates that the preceding and following related objects have an "or" relationship.

[0025] It should also be understood that the description of the various embodiments in this disclosure emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0026] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0027] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0028] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0029] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0030] Swarm intelligence algorithms (such as the mayfly algorithm) are algorithms that optimize parameters by simulating the behavior of biological groups, offering new ideas for inventory parameter optimization. However, the basic mayfly algorithm suffers from weak global search capabilities and a tendency to get trapped in local optima, making it difficult to directly apply to the complex scenarios of home improvement warehousing. Specifically, applying the traditional mayfly algorithm to the home improvement warehousing supply chain will encounter the following problems: 1. Inefficient use of input data: The input data of home improvement warehousing (such as inventory data at each node, material demand forecasts, transportation costs, etc.) is scattered and has many dimensions. Traditional algorithms have difficulty integrating multi-source data for global optimization, and the overall strategy is prone to failure due to deviations in data from a single node (such as temporary stockouts at stores). 2. Insufficient precision in parameter optimization: Home decoration inventory parameters (such as replenishment threshold and transportation batch) need to be adapted to the characteristics of multiple categories of materials. The basic mayfly algorithm is prone to getting stuck in local optima in multi-peak cost functions (such as the intersection of inventory cost curves of different materials) (such as over-optimizing the inventory of a certain type of material while ignoring the global). 3. Weak dynamic response capability: When faced with sudden demand (such as a surge in orders during the peak season for home renovation), traditional algorithms converge slowly and cannot quickly adjust inventory strategies, resulting in a lag in supply chain response.

[0031] To address the aforementioned issues, this disclosure provides a solution for inventory management based on an improved mayfly algorithm. The improved mayfly algorithm, which incorporates at least one strategy, including location optimization, speed optimization, and search range optimization, enables automatic optimization of inventory parameters for multiple nodes and multiple product categories.

[0032] Figure 1 A flowchart illustrating a material inventory management method provided for an exemplary embodiment of this disclosure. Figure 1 As shown, the method includes the following steps: Step 101: Obtain warehousing supply chain data for at least one material. The warehousing supply chain data includes demand, warehousing cost information, and the current inventory of the material at at least one node in the warehousing supply chain.

[0033] The data includes the current inventory of materials at at least one node in the warehousing supply chain, such as supplier inventory, regional warehouse inventory, and store inventory, to characterize the current inventory status of each node. Demand represents the estimated material demand over a preset period (e.g., predicted customer order volume for the next 7 days). Warehousing cost information includes various parameters used to calculate the total cost of the warehousing supply chain, such as, but not limited to, storage fees, transportation costs, stockout losses, and material attributes (e.g., volume, turnover rate). This warehousing supply chain data is used to optimize the mayfly algorithm, calculating the total warehousing supply chain cost corresponding to the location of each mayfly individual after one iteration.

[0034] Optionally, warehousing and supply chain data can be acquired separately for different categories of materials to optimize inventory parameters for each category of materials precisely using the Ephemeral Algorithm. Alternatively, inventory parameter optimization can be performed simultaneously for multiple categories of materials, i.e., warehousing and supply chain data for multiple categories of materials can be acquired synchronously.

[0035] Step 102: Encode the parameters to be optimized for at least one material into the position vector of an individual mayfly. Using the mayfly algorithm, with the goal of minimizing the total cost of the warehousing supply chain, iteratively optimize the position vector based on a pre-configured optimization strategy.

[0036] The parameters to be optimized include at least one of the material transportation volume and node inventory threshold corresponding to each supply chain node. The total cost of the warehousing supply chain is calculated based on the warehousing supply chain data and the parameters to be optimized. The pre-configured optimization strategies include at least one of the location optimization strategy, speed optimization strategy, and search range optimization strategy. The total cost of the warehousing supply chain refers to the material storage and transportation costs on the warehousing supply chain when material scheduling is performed according to the parameter values ​​of the parameters to be optimized.

[0037] Among them, the position optimization strategy updates the search speed of mayfly individuals by using the median position of the individual mayfly's position as the group reference position; the speed optimization strategy optimizes the search direction of mayfly individuals by using dynamically changing coefficient enhancement factors; and the search range optimization strategy expands the search range and search precision of mayfly individuals through sine and cosine operations.

[0038] In one possible implementation, the parameters to be optimized can be encoded as the position vector of a mayfly individual. The initial values ​​of each component in this position vector can be random numbers. The position vector of the mayfly individual is iteratively optimized using the mayfly algorithm to obtain the optimal parameters. Illustratively, the supply chain nodes in the warehousing supply chain include suppliers, regional warehouses, and stores. Correspondingly, the parameters to be optimized may include, but are not limited to, the supplier's replenishment threshold Ts (i.e., the threshold that triggers the supplier to replenish the regional warehouse when the inventory is below this value), the transportation batch Qw from the regional warehouse to the store (i.e., the quantity of materials transported each time replenishment), and the store's safety stock Sr (the basic inventory reserved to cope with sudden demand). Then, the position vector X of the mayfly individual can be represented as X = (Ts, Qw, Sr). Furthermore, the parameters to be optimized may also include other parameters such as the supplier's transportation batch to the regional warehouse and the store's inventory threshold. This disclosure does not limit the specific parameter type of the target optimization parameters.

[0039] Compared to the traditional mayfly algorithm, the mayfly algorithm with pre-configured optimization strategies uses at least one of the aforementioned optimization strategies to iteratively optimize the position vector of individual mayflies. Specifically, when employing a position optimization strategy, the median position of all mayfly individuals in the population is used as the group reference position to update the individual velocities. This replaces the traditional mayfly algorithm which uses the optimal mayfly position (e.g., the position with the minimum fitness function value) as the group reference position. Alternatively, the median and optimal mayfly positions can be combined as group reference positions to update individual velocities. The median mayfly position can be obtained based on the median values ​​of each dimension component in the position vector. For example, the median mayfly position Pm = (Tsm, Qwm, Srm), where Tsm is the median value of Ts, Qwm is the median value of Qw, and Srm is the median value of Sr. For example, for the Ts dimension, the median mayfly position is calculated based on the Ts value (e.g., the position of all mayfly individuals from the first iteration to the current iteration). The position vectors of mayfly individuals are sorted in descending order of the Ts values ​​corresponding to all position vectors, and the median value of Ts or the average of at least two median values ​​is taken as Tsm. When a speed optimization strategy is adopted, the search direction of mayfly individuals is optimized by embedding dynamically changing coefficient enhancement factors in the speed update formula. In the early stage of iteration, the movement speed of the mayfly group can be controlled to conduct a rapid large-scale search. In the later stage of iteration, the movement speed can be slowed down to control the mayfly group to conduct fine search and fine adjustment near the group reference position and the individual reference position. During the search process, the attraction between different populations is strengthened to find the global optimal solution of the entire supply chain. When a search range optimization strategy is adopted, sine and cosine operations are used. The search range can be expanded by using the sine function to cope with sudden demand, and the parameters can be finely adjusted by using the cosine function.

[0040] Step 103: In response to the completion of the iteration, the inventory management operation is driven by the parameter values ​​of the parameters to be optimized output by the mayfly algorithm.

[0041] The iteration termination condition may include, but is not limited to, at least one of the following conditions: the number of iterations reaches a preset number, the iteration duration reaches a preset duration, and the minimum total supply chain warehousing cost corresponding to the position vector of each mayfly is less than a preset cost threshold.

[0042] Optionally, after the iteration termination condition is met, the mayfly algorithm outputs the optimal solution for the parameters. That is, after the last iteration, the optimized mayfly algorithm outputs the position vector of the mayfly individual in the mayfly population that has the minimum total cost of the warehousing supply chain. This position vector is the optimized parameter to be optimized. The parameter values ​​of this set of parameters to be optimized are synchronized to the warehouse management system, driving the warehouse management system to automatically perform inventory management operations such as replenishment and transfer.

[0043] To illustrate, the optimal position vector Xbest output by the Ephemeral Algorithm is (80, 50, 30), which means that the replenishment threshold from the supplier to the regional warehouse is 80 sets, the transportation batch from the regional warehouse to the store is 50 sets, and the safety stock of the store is 30 sets. Correspondingly, if the current inventory of a certain regional warehouse is detected to be 60 sets, the supplier is triggered to replenish the regional warehouse.

[0044] Based on the embodiments of this disclosure, the mayfly algorithm, which integrates at least one strategy such as position optimization, speed optimization, and search range optimization, determines the total cost of the warehousing supply chain based on the warehousing supply chain data of at least one material and the parameters to be optimized. The algorithm then iteratively optimizes the parameters to be optimized with the goal of minimizing the total cost of the warehousing supply chain. After iteration, the optimized parameter values ​​drive inventory management operations, achieving automatic optimization of inventory parameters for multiple nodes and multiple material categories. Specifically, the position optimization strategy updates the individual mayfly speeds using the median position of the individual mayfly's location as the group reference position, which can balance the inventory of multiple material categories and avoid parameter dominance for a single material category. The optimization and speed optimization strategies utilize dynamically changing coefficients to enhance the search direction of individual mayflies, balancing global exploration and local development. The search range optimization strategy expands the search range and granularity of individual mayflies through sine and cosine operations, addressing both sudden demand expansion and refined local parameters. Considering the characteristics of the home improvement industry—large demand fluctuations and significant material-specific differences—the mayfly algorithm can dynamically balance global search capabilities with local optimization capabilities. This meets the inventory coordination needs of complex supply chains, improves supply chain response speed, reduces inventory backlog, and lowers stockout rates, thereby reducing inventory costs in the supply chain.

[0045] In one possible implementation, after completing one iteration, the optimized mayfly algorithm updates the velocity based on the obtained position vectors of each mayfly individual to obtain the velocity of each mayfly individual in the next iteration. Then, based on the velocity, it updates the position to obtain the position vector of each mayfly individual in the next iteration, thus completing the next iteration. Figure 2 As shown, step 102 above may specifically include the following steps: Step 201: For any mayfly individual, calculate the t-th function value of the fitness function based on the warehousing supply chain data and the t-th position vector obtained in the t-th iteration.

[0046] Here, the fitness function value represents the total cost of the warehousing supply chain, the components of different dimensions in the location vector are different parameters to be optimized, and t is a positive integer.

[0047] After completing the t-th iteration, the t-th position vector of each mayfly individual can be obtained, and then the t-th function value of the fitness function can be calculated for each mayfly individual.

[0048] The fitness function f(X) is illustrated below: f(X)=(Is +Iw +Ir)×Cs +Qw×Ct+(Dc-Ir)×Co (when Dc>Ir) (1) Where Is is the supplier inventory, Iw is the regional warehouse inventory, Ir is the store inventory, Cs is the storage fee, Qw is the transportation batch from the regional warehouse to the store, Ct is the transportation fee, Dc is the material demand forecast, and Co is the stockout loss fee. Qw is a parameter to be optimized. For the supplier replenishment threshold Ts and the store safety stock Sr, Ts affects the supplier inventory Is and the regional warehouse inventory Iw, while Sr affects the store inventory Ir and the stockout item (Dc-Ir), thus indirectly affecting the fitness function value.

[0049] Step 202: Update the individual reference position corresponding to any mayfly individual based on the t-th function value.

[0050] The individual reference position is the position vector that minimizes the fitness function value among the first t position vectors of the mayfly individual.

[0051] For any mayfly individual, after t iterations, t position vectors will be obtained. The position vector with the smallest function value is determined as the individual reference position Pbest of that mayfly individual.

[0052] Step 203: For any mayfly individual, determine the (t+1)th velocity vector of the mayfly individual based on the individual reference position and the group reference position.

[0053] Optionally, if the optimized mayfly algorithm does not employ position optimization and velocity optimization strategies, its group reference position can be the optimal mayfly individual position after the t-th iteration (e.g., the position with the minimum fitness function value). Correspondingly, the velocity update formula is as follows: (2) in, Let a1 and a2 be the velocity of the i-th mayfly individual in the t-th iteration along dimension j, and a1 and a2 be learning factors (e.g., a1=a2=1.5). For visibility parameters, The current location of the mayfly and its reference location. The Euclidean distance between them This represents the current individual position of the mayfly and its best position in the global historical data. The Euclidean distance between them Let be the position of the i-th mayfly individual in dimension j during the t-th iteration. The global historical best position refers to the best position (i.e., the position corresponding to the minimum function value) among all positions reached by the mayfly individual in the mayfly population after t iterations.

[0054] Optionally, if the optimization strategy used in the mayfly optimization algorithm includes at least one position optimization strategy, step 203 may specifically include the following steps: Based on the t-th position vector of each mayfly in the mayfly population after the t-th iteration, the median of the position vector of the mayfly population is determined; using the median of the position vector as the population reference position, the (t+1)-th velocity vector of the mayfly individual is determined based on the individual reference position and the population reference position.

[0055] The median of the position vector is the median of all positions reached by all mayfly individuals in the mayfly population after t iterations. The median of the position vector can be obtained by taking the median of each component of each dimension and combining them.

[0056] In one possible implementation, the group reference position is the median of the position vector, and the corresponding velocity update formula is as follows: (3) Where a3 is the median coefficient (e.g., a3=0.8). The median of the current mayfly's individual position and its position vector. The Euclidean distance between them Let be the component of the median of the position vector in dimension j.

[0057] In another possible implementation, the group reference position includes the median of the position vectors and the global historical best position. The optimized mayfly algorithm combines the individual reference position, the median of the position vectors, and the global historical best position to update the velocity of individual mayflies. Accordingly, the velocity update formula is as follows: (4) Optionally, if the optimization strategy used in the mayfly optimization algorithm includes at least one speed optimization strategy, step 203 may specifically include the following steps: Inputting the individual reference position and the group reference position into the velocity calculation formula yields the (t+1)th velocity vector. In the velocity calculation formula, the (t+1)th velocity vector is the sum of the first, second, and third calculation terms. The first calculation term is the product of the nonlinear gravity coefficient and the t-th velocity vector. The second calculation term is the product of the first attraction enhancement coefficient and the first position difference. The third calculation term is the product of the second attraction enhancement coefficient and the second position difference. The nonlinear gravity coefficient decreases as the iteration number t increases. The first position difference is the difference between the individual reference position and the t-th position vector. The second position difference is the difference between the group reference position and the t-th position vector. An attraction enhancement factor is embedded in the first and second attraction enhancement coefficients. The attraction enhancement factor decreases as the distance between the mayfly individual and the group reference positions increases.

[0058] Alternatively, the expression for the nonlinear gravity coefficient g(t) is as follows: (5) in, The maximum number of iterations is set in advance, and t is the current number of iterations.

[0059] The expression for the attraction enhancement factor is as follows: (6) Where h and b are constants, The current location of the mayfly and its median location. The Euclidean distance between them.

[0060] If both position optimization and velocity optimization strategies are used simultaneously, the velocity update formula is illustrated below: (7) The nonlinear gravity coefficient plays a role in balancing global search capability and local exploitation capability during the iteration process, and it gradually decreases as the number of iterations t increases. In the early stage of iteration, the value of g(t) is relatively large, giving mayfly individuals a strong global search capability, which can fully explore various possible stock parameters and avoid getting trapped in local optima too early. In the later stage of iteration, the value of g(t) is relatively small, and the movement of mayfly individuals is more affected by the attraction between the individual reference position and the group reference position, allowing for fine-tuning and precise searching near possible optimal solutions.

[0061] The attraction enhancement factor decreases as the distance between the mayfly individual and the median location increases. This prevents the attraction between mayflies from rapidly declining with increasing distance, avoiding ineffective iterations in the algorithm. Especially in the warehousing supply chain of the home improvement industry, the exchange of inventory information between nodes is crucial. Introducing the attraction enhancement factor ensures that the information transmission capability and attraction between mayflies remain intact even when they are far apart. For example, when optimizing upstream node parameters such as supplier replenishment thresholds and transportation batches from suppliers to regional warehouses through the male group, and downstream node parameters such as transportation batches from regional warehouses to stores and store safety stock through the female group, the attraction enhancement factor can strengthen the mutual attraction between different groups, searching for parameter combinations that can work collaboratively from the perspective of the entire supply chain.

[0062] The speed optimization strategy combines a nonlinear gravity coefficient and an attraction enhancement factor. In the early stages of iteration, the nonlinear gravity coefficient is relatively large, and the attraction enhancement factor has a relatively weak effect, allowing different populations to conduct large-scale explorations and find possible optimal solutions at their respective stages. In the middle stages of iteration, the nonlinear gravity coefficient gradually decreases, the inertia of individual mayflies weakens, and the effect of the attraction enhancement factor gradually strengthens. Based on exploring the optimal solutions for parameters at their respective stages, different mayfly populations attract and cooperate with each other to collaboratively find the optimal solution for the overall supply chain parameters. In the later stages of iteration, the nonlinear gravity coefficient is small, and the attraction enhancement factor continues to act, allowing individual mayflies to fine-tune near possible optimal solutions. Through the above process, the mayfly population can balance global exploration capabilities with local development capabilities.

[0063] Step 204: Based on the (t+1)th velocity vector, update the position of each mayfly individual to obtain the (t+1)th position vector.

[0064] Optionally, if the mayfly optimization algorithm does not employ a search range optimization strategy, then for each mayfly individual, the (t+1)th position vector can be directly obtained based on the t-th position vector and the (t+1)th velocity vector. The corresponding position vector update formula is as follows: (8) Optionally, if the optimization strategy employed in the mayfly optimization algorithm includes at least one search range optimization strategy, step 204 may specifically include the following steps: In response to t being less than the number of times threshold, the sum of the t-th position vector and the (t+1)-th velocity vector is determined as the (t+1)-th position vector.

[0065] Accordingly, the material inventory management method provided in this disclosure also includes the following steps: In response to t being greater than or equal to the number of times threshold, the sum of the t-th position vector and the sine and cosine formulas is determined as the (t+1)-th position vector. The sine and cosine formulas are either the sine function or the cosine function of the target distance, and the target distance is the distance between the point corresponding to the t-th position vector and the group reference position.

[0066] When using a search range optimization strategy, in the early stages of iteration, the above formula (8) can be directly used to update the position vector based on the (t+1)th velocity vector. For example, if the maximum number of iterations is 100 and the threshold number is 71, then in the 1st to 70th iterations, the sum of the t-th position vector and the (t+1)th velocity vector is determined as the (t+1)th position vector. In the later stages of iteration, the position vector is updated through sine or cosine operations, as shown in the following formula: (9) Among them, r1-r4 are all random numbers.

[0067] In the search range optimization strategy, the sine operation updates the position by oscillating between positive and negative values, which can expand the search range for sudden demands, such as exploring larger transportation batches. This allows the final output parameters to cope with sudden demands during peak seasons to a certain extent. The cosine operation oscillates around the optimal solution, refining local parameters and enabling fine-tuning of parameters (such as fine-tuning store safety stock) to minimize total costs. By introducing sine and cosine operations in the later stages of iteration, the optimization mayfly algorithm maintains sufficient vitality at the end of convergence, seizing opportunities for strategy adjustments brought about by sudden demands and fine-tuning existing better solutions, thereby comprehensively improving the robustness and accuracy of the inventory strategy.

[0068] Optionally, in one possible implementation, the optimization algorithm for the mayfly can employ different optimization strategies at different stages. Illustratively, a position optimization strategy is used in the early stages of iteration (e.g., iterations 1-30); a position optimization strategy and a velocity optimization strategy are used in the middle stages of iteration (e.g., iterations 30-70); and a position optimization strategy, a velocity optimization strategy, and a search range optimization strategy are used in the late stages of iteration (e.g., iterations 71-100), thereby maximizing the advantages of each optimization strategy.

[0069] Based on the embodiments of this disclosure, by combining at least one of the strategies of location optimization, speed optimization, and search range optimization, and comprehensively considering the inventory parameters of multiple nodes, global optimization is performed. When dealing with complex situations such as demand fluctuations and large differences in material characteristics, the improved mayfly algorithm can dynamically adjust the search strategy, escape local optima, find a better combination of inventory parameters, and minimize inventory costs. Furthermore, this optimized mayfly algorithm is not limited to the warehousing stage but takes a holistic approach to the supply chain, coordinating all nodes to improve overall operational efficiency, and is more effective in reducing inventory costs and improving supply chain responsiveness.

[0070] In one possible implementation, the mayfly population includes female and male populations. The node inventory thresholds in the parameters to be optimized include the replenishment threshold from upstream nodes to intermediate nodes and the safety stock of downstream nodes. The material transport volume includes the material transport batch from intermediate nodes to downstream nodes. The male population focuses on optimizing upstream node parameters (e.g., the replenishment threshold from upstream nodes to intermediate nodes), while the female population focuses on optimizing downstream node parameters (e.g., the transport batch from intermediate nodes to downstream nodes and the safety stock of downstream nodes). Step 203 above may further include the following steps: Step 203a: In response to the fact that the mayfly is male, the individual reference point and the group reference position are input into the male velocity calculation formula to obtain the (t+1)th velocity vector of the mayfly.

[0071] In step 203b, in response to the fact that the mayfly is female, the individual reference position and the group reference position are input into the female velocity calculation formula to obtain the (t+1)th velocity vector of the mayfly.

[0072] In the male speed calculation formula, the weight of the first speed component is greater than the weight of the second speed component. In the female speed calculation formula, the weight of the second speed component is greater than the weight of the first speed component. The first speed component includes the speed component corresponding to the replenishment threshold from the upstream node to the intermediate node. The second speed component includes the speed component corresponding to the transportation batch from the intermediate node to the downstream node and the speed component corresponding to the safety stock of the downstream node.

[0073] The illustrative formula for calculating male speed is as follows: (10) The formula for calculating the female's speed is as follows: (11) Where Aj is the weight of the j-th velocity component of the male individual, and Bj is the weight of the j-th velocity component of the female individual.

[0074] Assuming the parameters to be optimized include the supplier's replenishment threshold Ts to the regional warehouse, the transportation batch Qw from the regional warehouse to the store, and the store's safety stock Sr, then the first velocity component includes the velocity component corresponding to the supplier's replenishment threshold Ts to the regional warehouse, and the second velocity component includes the velocity component corresponding to the transportation batch Qw from the regional warehouse to the store and the velocity component corresponding to the store's safety stock Sr. For male individuals, the weight A1 of the velocity component corresponding to Ts is greater than the weight A2 of the velocity components corresponding to Qw and Sr, for example, A1 is 0.8 and A2 is 0.2; for female individuals, the weight B2 of the velocity components corresponding to Qw and Sr is greater than the weight B1 of the velocity component corresponding to Ts, for example, B1 is 0.2 and B2 is 0.8.

[0075] Based on the embodiments of this disclosure, by setting different weight allocations for the velocity update formulas of female and male individuals, male individuals focus on optimizing upstream parameters, while female individuals focus on optimizing downstream parameters. This improves the exploration efficiency of mayfly individuals, avoids the population from prematurely converging into local optima or overexploring and failing to find a stable solution for a long time, and ensures that the position and velocity vectors of female and male individuals have the same dimension, thus taking into account the synergy of parameter optimization at different stages.

[0076] In one possible implementation, the optimized mayfly algorithm periodically controls female and male individuals to mate and reproduce during the iteration process, generating new parameter combinations. After step 204 above, as... Figure 3 As shown in the embodiments of this disclosure, the inventory management method may further include the following steps: Step 301: In response to reaching the mating cycle, identify the target female and target male individuals.

[0077] The target female individuals include the n female individuals with the smallest corresponding function value at the (t+1)th digit, and the target male individuals include the n male individuals with the smallest corresponding function value at the (t+1)th digit, where n is a positive integer. That is, the target female individuals are the n best individuals in the female population, and the target male individuals are the n best individuals in the male population.

[0078] Optionally, the mating cycle of the mayfly population can be preset, for example, mating once every 10 iterations. When the mating cycle is reached, target females are selected from the female population and target males are selected from the male population.

[0079] Step 302: Pair the target female individuals and target male individuals according to a preset method and generate m offspring mayfly individuals to obtain a candidate mayfly population.

[0080] The position vector of the offspring mayfly is the weighted average of the position vectors of the corresponding target male and target female individuals, where m is a positive integer.

[0081] Optionally, the pairing of target females and target males can be random or by sorting them in ascending order of their function values ​​at the (t+1)th t- ...

[0082] The formula for the mating of a target male and a target female to produce offspring is illustrated below: off1=L×male+(1-L)×female (12) Where L is a random number greater than 0 and less than 1, off1 is the position vector of the offspring mayfly individual, male is the position vector of the target male individual, and female is the position vector of the target female individual.

[0083] Step 303: Remove the m mayfly individuals with the largest function value at the (t+1)th t- ...

[0084] To ensure a consistent population size, after the mayfly individuals are produced, the m mayfly individuals with the largest function value at the (t+1)th t- ...

[0085] Based on the embodiments of this disclosure, when male and female individuals have different optimization focuses, periodically screening target male and female individuals to mate and produce offspring can further improve the synergy of upstream and downstream parameters in the supply chain and accelerate the search efficiency for the global optimal solution.

[0086] Please refer to Figure 4 This illustration shows a structural block diagram of an inventory management apparatus provided in an exemplary embodiment of the present disclosure. The inventory management apparatus provided in this embodiment includes: The acquisition module 401 is used to acquire warehousing supply chain data corresponding to at least one material. The warehousing supply chain data includes demand, warehousing cost information, and the current inventory of the material at at least one supply chain node in the warehousing supply chain. The iteration module 402 is used to encode the optimization parameters corresponding to at least one material into the position vector of a mayfly individual. Using the mayfly algorithm, with the goal of minimizing the total cost of the warehousing supply chain, the position vector is iteratively optimized based on a pre-configured optimization strategy. The optimization parameters include at least one of the material transportation volume corresponding to the supply chain node and the node inventory threshold. The total cost of the warehousing supply chain is calculated based on the warehousing supply chain data obtained by the acquisition module 401 and the optimization parameters. The pre-configured optimization strategy includes at least one of the position optimization strategy, speed optimization strategy, and search range optimization strategy. The position optimization strategy updates the search speed of the mayfly individual with the median of the position vector of the mayfly group as the group reference position. The speed optimization strategy optimizes the search direction of the mayfly individual by using a dynamically changing coefficient enhancement factor. The search range optimization strategy expands the search range and refines the search of the mayfly individual through sine and cosine operations. The management module 403 is used to drive inventory management operations based on the parameter values ​​of the parameters to be optimized output by the mayfly algorithm in response to the achievement of the iteration termination condition.

[0087] In one possible implementation, the above-described iteration module 402 can be further used for: For any mayfly individual, based on the warehousing supply chain data and the t-th position vector obtained in the t-th iteration, calculate the t-th function value of the fitness function. The function value of the fitness function represents the total cost of the warehousing supply chain, where t is a positive integer. The individual reference position of any mayfly is updated based on the t-th function value. This individual reference position is the point corresponding to the position vector with the smallest fitness function value among the first t position vectors of the mayfly individual. For any individual mayfly, determine the (t+1)th velocity vector of the mayfly based on the individual reference position and the group reference position; Based on the (t+1)th velocity vector, update the position of each mayfly individual to obtain the (t+1)th position vector.

[0088] In one possible implementation, at least one optimization strategy includes a position optimization strategy, and the aforementioned iterative module 402 can be further used to: Based on the t-th position vector of each mayfly in the mayfly population after the t-th iteration, update the median of the position vector of the mayfly population; Using the median of the position vector as the group reference position, the velocity vector of the mayfly individual during the (t+1)th iteration is determined based on the individual reference position and the group reference position.

[0089] In one possible implementation, at least one optimization strategy includes a speed optimization strategy, and the aforementioned iterative module 402 can be further used for: Inputting the individual reference position and the group reference position into the velocity calculation formula yields the (t+1)th velocity vector. In the velocity calculation formula, the (t+1)th velocity vector is the sum of the first, second, and third calculation terms. The first calculation term is the product of the nonlinear gravity coefficient and the t-th velocity vector. The second calculation term is the product of the first attraction enhancement coefficient and the first position difference. The third calculation term is the product of the second attraction enhancement coefficient and the second position difference. The nonlinear gravity coefficient decreases as the iteration number t increases. The first position difference is the difference between the individual reference position and the t-th position vector. The second position difference is the difference between the group reference position and the t-th position vector. An attraction enhancement factor is embedded in the first and second attraction enhancement coefficients. The attraction enhancement factor decreases as the distance between the mayfly individual and the group reference positions increases.

[0090] In one possible implementation, at least one optimization strategy includes a search range optimization strategy, and the aforementioned iterative module 402 can be further used to: In response to t being less than the number of times threshold, the sum of the t-th position vector and the (t+1)-th velocity vector is determined as the (t+1)-th position vector; In response to t being greater than or equal to the number of times threshold, the sum of the t-th position vector and the sine and cosine formulas is determined as the t+1-th position vector. The sine and cosine formulas are either the sine function or the cosine function of the target distance, and the target distance is the distance between the point corresponding to the t-th position vector and the group reference position.

[0091] In one possible implementation, the mayfly population includes female and male populations, and the node inventory threshold in the parameters to be optimized includes the replenishment threshold from upstream nodes to intermediate nodes and the safety stock of downstream nodes. The material transportation volume includes the material transportation batch from intermediate nodes to downstream nodes. The aforementioned iterative module 402 can be further used for: In response to the fact that the mayfly is male, the individual reference position and the group reference position are input into the male velocity calculation formula to obtain the (t+1)th velocity vector of the mayfly; In response to the fact that the mayfly is female, the individual reference position and the group reference position are input into the female velocity calculation formula to obtain the (t+1)th velocity vector of the mayfly; In the male speed calculation formula, the weight of the first speed component is greater than the weight of the second speed component. In the female speed calculation formula, the weight of the second speed component is greater than the weight of the first speed component. The first speed component includes the speed component corresponding to the replenishment threshold from the upstream node to the intermediate node. The second speed component includes the speed component corresponding to the transportation batch from the intermediate node to the downstream node and the speed component corresponding to the safety stock of the downstream node.

[0092] In one possible implementation, such as Figure 5 As shown, the inventory management device provided in this embodiment of the disclosure further includes: The determination module 501 is used to determine the target female individuals and target male individuals in response to reaching the mating cycle. The target female individuals include the n female individuals with the smallest corresponding function value at the (t+1)th digit, and the target male individuals include the n male individuals with the smallest corresponding function value at the (t+1)th digit, where n is a positive integer. The breeding module 502 is used to pair target female individuals and target male individuals according to a preset method and generate m offspring mayfly individuals to obtain a candidate mayfly population. The position vector of the offspring mayfly individuals is the weighted average of the position vectors of the corresponding target male individuals and target female individuals, where m is a positive integer. The update module 503 is used to remove the m mayfly individuals with the largest function value at the (t+1)th t- ...

[0093] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar, identical, or corresponding parts between embodiments can be referred to mutually. Since the method, apparatus, and device embodiments are basically corresponding, relevant parts can be referred to the corresponding descriptions. The methods, apparatus, and devices in the embodiments of this disclosure also correspond to each other in specific implementation and beneficial technical effects; related content can be referred to mutually and will not be repeated here.

[0094] In addition, embodiments of this disclosure also provide an electronic device, including: Memory, used to store computer programs; A processor is configured to execute a computer program stored in the memory, wherein when the computer program is executed, it implements the material inventory management method described in any of the above embodiments of the present disclosure.

[0095] Figure 6 This is a schematic diagram illustrating the structure of an application embodiment of the electronic device disclosed herein. Below, reference is made to… Figure 6 This describes an electronic device according to embodiments of the present disclosure. The electronic device may be either or both of a first device and a second device, or a standalone device independent of them, which may communicate with the first device and the second device to receive acquired input signals from them.

[0096] like Figure 6 As shown, the electronic device includes one or more processors and memory.

[0097] A processor can be a central processing unit (CPU) or other form of processing unit with data processing and / or instruction execution capabilities, and can control other components in an electronic device to perform desired functions.

[0098] The memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and a processor may execute the program instructions to implement the material inventory management methods of the various embodiments of this disclosure described above, and / or other desired functions.

[0099] In one example, the electronic device may also include input devices and output devices, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0100] In addition, the input device may include, for example, a keyboard, a mouse, etc.

[0101] This output device can output various information to the outside, including determined distance information, direction information, etc. The output device may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0102] Of course, for the sake of simplicity, Figure 6Only some of the components of the electronic device relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device may include any other suitable components depending on the specific application.

[0103] In addition to the methods and apparatus described above, embodiments of this disclosure may also be computer program products, including computer program instructions that, when executed by a processor, cause the processor to perform the steps in the material inventory management methods according to various embodiments of this disclosure as described in the foregoing portions of this specification.

[0104] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this disclosure. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0105] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the material inventory management method according to various embodiments of this disclosure as described in the foregoing portion of this specification.

[0106] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0107] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as ROM, RAM, magnetic disk, or optical disk.

[0108] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0109] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0110] The block diagrams of devices, apparatuses, devices, and systems disclosed herein are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0111] The methods and apparatus of this disclosure may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of this disclosure are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, this disclosure may also be implemented as a program recorded on a recording medium, the program including machine-readable instructions for implementing the methods according to this disclosure. Thus, this disclosure also covers recording media storing programs for performing the methods according to this disclosure.

[0112] It should also be noted that in the apparatus, devices, and methods of this disclosure, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions to this disclosure.

[0113] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0114] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A material inventory management method, characterized in that, include: Acquire warehousing supply chain data for at least one material, wherein the warehousing supply chain data includes demand, warehousing cost information, and the current inventory of the material at at least one node in the warehousing supply chain; The optimization parameters corresponding to the at least one material are encoded as position vectors of mayfly individuals. Using the mayfly algorithm, with the goal of minimizing the total cost of the warehousing supply chain, the position vectors are iteratively optimized based on a pre-configured optimization strategy. The optimization parameters include at least one of the material transportation volume and node inventory threshold corresponding to the supply chain node. The total cost of the warehousing supply chain is calculated based on the warehousing supply chain data and the optimization parameters. The pre-configured optimization strategy includes at least one of a position optimization strategy, a speed optimization strategy, and a search range optimization strategy. The position optimization strategy updates the search speed of mayfly individuals using the median of the mayfly population position vector as the population reference position. The speed optimization strategy optimizes the search direction of mayfly individuals using dynamically changing coefficient enhancement factors. The search range optimization strategy expands the search range and search precision of mayfly individuals through sine and cosine operations. In response to the completion of the iteration, the inventory management operation is driven based on the parameter values ​​of the parameters to be optimized output by the optimized mayfly algorithm.

2. The method according to claim 1, characterized in that, The step involves using the mayfly algorithm to optimize the location vector iteratively, with the goal of minimizing the total cost of the warehousing supply chain, based on a pre-configured optimization strategy. This includes: For any mayfly individual, based on the warehousing supply chain data and the t-th position vector obtained in the t-th iteration, calculate the t-th function value of the fitness function, where the function value of the fitness function represents the total cost of the warehousing supply chain, and t is a positive integer; The individual reference position of any mayfly individual is updated based on the t-th function value, where the individual reference position is the position vector with the smallest function value of the fitness function among the first t position vectors of the mayfly individual; For any individual mayfly, the (t+1)th velocity vector of the individual mayfly is determined based on the individual reference position and the group reference position; Based on the (t+1)th velocity vector, the position of each mayfly individual is updated to obtain the (t+1)th position vector.

3. The method according to claim 2, characterized in that, The at least one optimization strategy includes the position optimization strategy, wherein determining the (t+1)th velocity vector of the mayfly individual based on the individual reference position and the group reference position includes: Based on the t-th position vector of each mayfly in the mayfly population after the t-th iteration, update the median of the position vector of the mayfly population; The median of the position vector is used as the group reference position. Based on the individual reference position and the group reference position, the (t+1)th velocity vector of the mayfly individual is determined.

4. The method according to claim 2, characterized in that, The at least one optimization strategy includes the velocity optimization strategy, wherein determining the (t+1)th velocity vector of the mayfly individual based on the individual reference position and the group reference position includes: The individual reference position and the group reference position are input into the velocity calculation formula to obtain the (t+1)th velocity vector. The (t+1)th velocity vector in the velocity calculation formula is the sum of a first calculation term, a second calculation term, and a third calculation term. The first calculation term is the product of the nonlinear gravity coefficient and the t-th velocity vector. The second calculation term is the product of a first attraction enhancement coefficient and a first position difference. The third calculation term is the product of a second attraction enhancement coefficient and a second position difference. The nonlinear gravity coefficient decreases as the iteration number t increases. The first position difference is the difference between the individual reference position and the t-th position vector. The second position difference is the difference between the group reference position and the t-th position vector. An attraction enhancement factor is embedded in the first attraction enhancement coefficient and the second attraction enhancement coefficient. The attraction enhancement factor decreases as the distance between the mayfly individual and the group reference position increases.

5. The method according to claim 2, characterized in that, The at least one optimization strategy includes the search range optimization strategy, wherein updating the position of each mayfly individual based on the (t+1)th velocity vector to obtain the (t+1)th position vector includes: In response to t being less than the number of times threshold, the sum of the t-th position vector and the (t+1)-th velocity vector is determined as the (t+1)-th position vector; The method further includes: In response to t being greater than or equal to the number threshold, the sum of the t-th position vector and the sine and cosine formulas is determined as the (t+1)-th position vector, where the sine and cosine formulas are either the sine function of the target distance or the cosine function of the target distance, and the target distance is the distance between the point corresponding to the t-th position vector and the group reference position.

6. The method according to any one of claims 2 to 5, characterized in that, The mayfly population includes female and male populations, the node inventory threshold in the parameters to be optimized includes the replenishment threshold from the upstream node to the intermediate node and the safety stock of the downstream node, and the material transportation volume includes the material transportation batch from the intermediate node to the downstream node. The determination of the (t+1)th velocity vector of any individual mayfly, based on the individual's reference position and the group's reference position, includes: In response to the fact that the mayfly individual is male, the individual reference position and the group reference position are input into the male velocity calculation formula to obtain the (t+1)th velocity vector of the mayfly individual; In response to the fact that the mayfly individual is female, the individual reference position and the group reference position are input into the female velocity calculation formula to obtain the (t+1)th velocity vector of the mayfly individual; In the male speed calculation formula, the weight of the first speed component is greater than the weight of the second speed component. In the female speed calculation formula, the weight of the second speed component is greater than the weight of the first speed component. The first speed component includes the speed component corresponding to the replenishment threshold from the upstream node to the intermediate node. The second speed component includes the speed component corresponding to the material transportation batch from the intermediate node to the downstream node and the speed component corresponding to the safety stock of the downstream node.

7. The method according to claim 6, characterized in that, After updating the position of each mayfly individual based on the (t+1)th velocity vector to obtain the (t+1)th position vector, the method further includes: In response to reaching the mating cycle, target female individuals and target male individuals are determined. The target female individuals include the n female individuals with the smallest corresponding function value at the (t+1)th digit, and the target male individuals include the n male individuals with the smallest corresponding function value at the (t+1)th digit, where n is a positive integer. The target female individual and the target male individual are paired according to a preset method to generate m offspring mayfly individuals, thus obtaining a candidate mayfly population. The position vector of the offspring mayfly individual is the weighted average of the position vectors of the corresponding target male individual and the target female individual, where m is a positive integer. The m mayfly individuals with the largest function value at the (t+1)th t- ...

8. A material inventory management device, characterized in that, include: The acquisition module is used to acquire warehousing supply chain data corresponding to at least one material. The warehousing supply chain data includes demand, warehousing cost information, and the current inventory of the material at at least one node in the warehousing supply chain. An iterative module is used to encode the optimization parameters corresponding to the at least one material into the position vector of an individual mayfly. Using the mayfly algorithm, with the goal of minimizing the total cost of the warehousing supply chain, the module iteratively optimizes the position vector based on a pre-configured optimization strategy. The optimization parameters include at least one of the material transportation volume and node inventory threshold corresponding to the supply chain node. The total cost of the warehousing supply chain is calculated based on the warehousing supply chain data and the optimization parameters. The pre-configured optimization strategy includes at least one of a position optimization strategy, a speed optimization strategy, and a search range optimization strategy. The position optimization strategy updates the search speed of an individual mayfly using the median of the mayfly population's position vector as the population reference position. The speed optimization strategy optimizes the search direction of an individual mayfly using dynamically changing coefficient enhancement factors. The search range optimization strategy expands the search range and refines the search of an individual mayfly through sine and cosine operations. The management module is used to drive inventory management operations based on the parameter values ​​of the parameters to be optimized output by the mayfly algorithm in response to the achievement of the iteration termination condition.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing a computer program stored in the memory, wherein when the computer program is executed, it implements the method described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-7.

11. A computer program product, characterized in that, It includes computer program instructions that, when executed by a processor, implement the method described in any one of claims 1 to 7.

Images