Cross-regional clothing supply management system and method

Abstract

The invention relates to the technical field of clothing supply chain management, and discloses a cross-regional clothing supply management system and method, and the method comprises the steps: obtaining the sales feature data, generated at each sales node, of a target clothing product from the generated sales volume; screening out a unique similar sales curve from N historical sales curves generated from each sales node based on the sales feature data, and obtaining the predicted sales volume of the target clothing product at the M sales nodes from the unique similar sales curve; calling the stock of all sales nodes about the target clothing product in the current time range, and obtaining the target sales nodes appearing in the predicted time range according to the quantitative relationship between the predicted sales and the stock; generating a scheduling strategy for each product shortage node by using a pre-configured genetic algorithm, and performing cross-regional clothing scheduling according to the scheduling strategy; the scheduling efficiency of the clothing supply chain can be effectively improved, and the management level of the clothing supply chain is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of clothing supply chain management, and more specifically, to a cross-regional clothing supply management system and method. Background Art

[0002] With the acceleration of globalization, branded clothing companies need to set up sales outlets and storage centers in multiple countries and regions to meet the market demands of different regions. However, the existing clothing supply management system faces many challenges in cross-regional scheduling. Existing technologies usually lack accurate sales forecasting mechanisms, resulting in clothing products at sales points often relying on manual requests for replenishment from the nearest storage center when inventory is short. This scheduling method has a strong lag and cannot respond to market demand in a timely manner, resulting in customers often facing insufficient inventory when purchasing, which in turn affects customer experience.

[0003] In addition, the existing technology generally uses the distance of geographical location as the basis for scheduling across regions, ignoring the comprehensive consideration of factors such as the actual inventory situation of each storage center, logistics and transportation costs, and storage capacity; clothing scheduling strategies that rely solely on distance will cause some storage centers to have excessive inventory pressure, while the resources of other storage centers cannot be fully utilized, resulting in inventory imbalance; at the same time, frequent cross-regional clothing transfers increase transportation costs and management complexity, significantly affecting the company's operating efficiency and the economy of overall supply chain management.

[0004] Therefore, there is an urgent need for a cross-regional clothing supply management system that can comprehensively consider multi-dimensional factors such as sales forecasts, inventory status, and logistics costs; by improving the intelligence and optimization level of scheduling, it can effectively reduce scheduling costs, improve supply chain efficiency, and improve customer experience, thereby enhancing the competitiveness of clothing companies in the market. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a cross-regional clothing supply management system and method.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A cross-regional clothing supply management system, the system comprising:

[0008] A data acquisition module is used to acquire the sales volume of the target clothing product generated in M ​​sales nodes within the current time range, and acquire the sales characteristic data generated by the target clothing product at each sales node from the generated sales volume, where M is an integer greater than zero;

[0009] The sales volume forecasting module is used to obtain N historical sales curves generated by the target clothing product at M sales nodes, screen out a unique similar sales curve from the N historical sales curves generated at each sales node based on the sales feature data, and obtain the predicted sales volume of the target clothing product at the M sales nodes from the unique similar sales curve, wherein the predicted sales volume is within a preset prediction time range, and N is an integer greater than zero;

[0010] The supply and demand comparison module is used to retrieve the inventory of the target clothing product in the current time range from all sales nodes, and obtain the target sales nodes that appear in the predicted time range according to the quantitative relationship between the predicted sales volume and the inventory; the target sales nodes include a product shortage node set including P product shortage nodes and a product surplus node set including H product surplus nodes, where P and H are integers greater than zero;

[0011] The supply management module is used to generate a scheduling strategy for each product shortage node using a preconfigured genetic algorithm, and perform cross-regional clothing scheduling based on the scheduling strategy; the scheduling strategy is the optimal scheduling sales node.

[0012] Furthermore, before acquiring the image to be searched, the sales characteristic data includes total sales volume, average sales volume, average sales growth rate, average growth amount, sales standard deviation, sales peak difference and coefficient of variation.

[0013] Furthermore, the step of selecting a unique similar sales curve from the N historical sales curves generated by each sales node includes:

[0014] a1: extract N historical sales curves generated by the target clothing product at the jth sales node, then extract the sales feature data contained in each historical sales curve, and use the sales feature data contained in each historical sales curve as the first feature set to obtain multiple first feature sets, where j is an integer greater than zero;

[0015] a2: extract the sales feature data generated by the target clothing product at the jth sales node, and use the sales feature data generated by the target clothing product at the jth sales node as the second feature set;

[0016] a3: Calculate the set similarity between the second feature set and each first feature set to obtain multiple set similarity coefficients;

[0017] a4: Sort multiple set similarity coefficients according to the values ​​from small to large, obtain the first feature set corresponding to the first ranked set similarity coefficient, mark the historical sales curve corresponding to the first feature set as the only similar sales curve, set j=j+1, and return to step a1;

[0018] a5: Repeat the above steps a1 to a4 until the loop ends when j=M, and obtain the unique similar sales curves of M sales nodes.

[0019] Furthermore, obtaining the predicted sales volume of the target clothing product at M sales nodes from the unique similar sales curve includes:

[0020] b1: Extract the unique similar sales curve of the v-th sales node, where v is an integer greater than zero;

[0021] b2: Input the preset forecast time range, and intercept the local curve part belonging to the forecast time range from the unique similar sales curve of the v-th sales node, and count the cumulative sales of the local curve part, and use the cumulative sales as the forecast sales of the target clothing product at the v-th sales node;

[0022] b3: Repeat the above steps b1 to b2 until v=M, and end the loop to obtain the predicted sales volume of the target clothing product at M sales nodes.

[0023] Furthermore, the step of obtaining the target sales node that occurs within the predicted time range includes:

[0024] c1: Extract the predicted sales volume and inventory of the target clothing product at the g-th sales node, where g is an integer greater than zero;

[0025] c2: Calculate the difference between the inventory and the predicted sales volume at the g-th sales node, and mark the difference between the inventory and the predicted sales volume at the g-th sales node as the supply-demand difference;

[0026] c3: Get the preset supply and demand quantity interval, and compare the supply and demand difference with the supply and demand quantity interval. If the supply and demand difference is greater than the maximum value of the supply and demand quantity interval, mark the g-th sales node as a product surplus node, set g=g+1, and return to step c1; if the supply and demand difference is less than the minimum value of the supply and demand quantity interval, mark the g-th sales node as a product shortage node, set g=g+1, and return to step c1;

[0027] c4: Repeat the above steps c1 to c3 until the loop ends when g=M, and obtain P product shortage nodes and H product surplus nodes.

[0028] Furthermore, the use of a preconfigured genetic algorithm to generate a scheduling strategy for each product shortage node includes:

[0029] d1: extract the xth product shortage node in the product shortage node set, and use the pre-configured genetic algorithm to select the best scheduling sales node from the product surplus node set, where x is an integer greater than zero;

[0030] d2: Eliminate the best scheduling sales node from the product surplus node set to obtain Z product surplus nodes, set x=x+1, and return to step d1, and update the elements of the product surplus node set in step d1 according to the Z product surplus nodes, Z<H, Z is an integer greater than zero;

[0031] d3: Repeat the above steps d1 to d2 until the loop ends when x=P, and obtain the scheduling strategy for each product shortage node, that is, each product shortage node obtains an optimal scheduling sales node.

[0032] Furthermore, the processing logic of the preconfigured genetic algorithm is as follows:

[0033] e1: Initialize the population: randomly generate an original population based on the product surplus node set, the original population contains R chromosomes, each chromosome represents a product surplus node, and R is an integer greater than zero;

[0034] e2: Fitness evaluation: Under each chromosome, obtain the spatial distance between the x-th product shortage node and each product surplus node, the supply-demand difference between the x-th product shortage node and each product surplus node, and the scheduling cost between the x-th product shortage node and each product surplus node; input the spatial distance and scheduling cost into the pre-built fitness function to calculate the fitness of each chromosome;

[0035] e3: Selection: Use the roulette wheel method to select two chromosomes with high fitness in the original population as the father and mother;

[0036] e4: Crossover: Perform crossover operation on the father and mother to generate new chromosomes;

[0037] e5: Mutation: Perform mutation operation on the new chromosomes to obtain Y new chromosomes, combine the Y new chromosomes into a new population, replace the original population with the new population, and return to step e2;

[0038] e6: Repeat steps e2 to e5 above until the fitness of the chromosome in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold, and then output the product surplus node represented by the corresponding chromosome as the optimal scheduling sales node corresponding to the x-th product shortage node.

[0039] Furthermore, the calculation formula of the pre-constructed fitness function is: Where: Fitness is fitness, Y is spatial distance, Y0 is reference spatial distance, D is scheduling cost, D0 is reference scheduling cost, S is the difference between supply and demand, α1, α2 and α3 are weight factors greater than zero, α1<α2<α3.

[0040] A cross-regional clothing supply management method, the method comprising:

[0041] In the current time range, the sales volume of the target clothing product generated in M ​​sales nodes is obtained, and the sales characteristic data generated by the target clothing product at each sales node is obtained from the generated sales volume, where M is an integer greater than zero;

[0042] Obtain N historical sales curves generated by the target clothing product at M sales nodes, screen out a unique similar sales curve from the N historical sales curves generated at each sales node based on the sales feature data, and obtain the predicted sales volume of the target clothing product at the M sales nodes from the unique similar sales curve, wherein the predicted sales volume is within a preset prediction time range, and N is an integer greater than zero;

[0043] Retrieve the inventory of the target clothing product in the current time range from all sales nodes, and obtain the target sales nodes that appear in the predicted time range according to the quantitative relationship between the predicted sales volume and the inventory; the target sales nodes include a product shortage node set including P product shortage nodes and a product surplus node set including H product surplus nodes, where P and H are integers greater than zero;

[0044] A preconfigured genetic algorithm is used to generate a scheduling strategy for each product shortage node, and cross-regional clothing scheduling is performed according to the scheduling strategy; the scheduling strategy is the optimal scheduling sales node.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] The present application discloses a cross-regional clothing supply management system and method, including: obtaining sales feature data generated by a target clothing product at each sales node from the generated sales volume; screening out a unique similar sales curve from N historical sales curves generated at each sales node based on the sales feature data, and obtaining the predicted sales volume of the target clothing product at M sales nodes from the unique similar sales curve; retrieving the inventory volume of the target clothing product at all sales nodes within the current time range, and obtaining the target sales node that appears within the predicted time range based on the quantitative relationship between the predicted sales volume and the inventory volume; generating a scheduling strategy for each product shortage node using a pre-configured genetic algorithm, and performing cross-regional service according to the scheduling strategy. Clothing scheduling, based on the above technical features, the present invention can more accurately predict the sales volume of target clothing products in the future time range. Compared with traditional empirical estimates, it can more accurately match historical trends and improve the accuracy of predictions, providing a reliable data basis for the formulation of inventory and scheduling strategies; in addition, by timely identifying which sales nodes have excess or shortage inventory, the risk of inventory accumulation or out-of-stock is avoided, thereby improving inventory turnover, reducing warehousing costs, and avoiding affecting customer experience. Furthermore, the optimal scheduling strategy is generated for product shortage nodes through a pre-configured genetic algorithm, which effectively reduces the scheduling cost. At the same time, the system takes into account the impact of the supply and demand gap on the scheduling cost in its design, making the scheduling more economical. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A schematic diagram of the module structure of a cross-regional clothing supply management system provided by the present invention;

[0048] Figure 2 The present invention provides a flow chart of a cross-regional clothing supply management method. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] Example 1

[0051] See also Figure 1 As shown, this embodiment discloses a cross-regional clothing supply management system, the system comprising:

[0052] The data acquisition module 101 is used to acquire the sales volume of the target clothing product generated in M ​​sales nodes within the current time range, and acquire the sales characteristic data generated by the target clothing product at each sales node from the generated sales volume, where M is an integer greater than zero;

[0053] The span of the current time range may be one week, two weeks, three weeks or one month, which is determined by the technicians. For example, if the current time is January 31, 2023, January can be used as the current time range, so as to retrieve the sales data generated by the target clothing product in different sales nodes in January.

[0054] It should be understood that branded clothing companies usually set up one or more sales nodes (such as sales points or storage centers) in multiple regions or areas to sell various clothing products under the brand. Various clothing products include but are not limited to shoes, socks and clothes, etc., and they exist in various forms. The target clothing products are determined by technicians after artificial selection from a variety of clothing products. Each clothing product can be used as a target clothing product to achieve the purpose of supply chain management of different clothing products;

[0055] Specifically, the sales characteristic data include but are not limited to total sales volume, average sales volume, average sales growth rate, average growth amount, sales standard deviation, sales peak difference and coefficient of variation, etc.;

[0056] The peak sales difference is obtained by calculating the difference between the maximum sales volume and the minimum sales volume of the target clothing product within the current time range; and the coefficient of variation is obtained by calculating the ratio of the standard deviation to the average sales volume of the target clothing product within the current time range.

[0057] The sales volume forecasting module 102 is used to obtain N historical sales curves generated by the target clothing product at M sales nodes, screen out a unique similar sales curve from the N historical sales curves generated at each sales node based on the sales feature data, and obtain the predicted sales volume of the target clothing product at the M sales nodes from the unique similar sales curve, wherein the predicted sales volume is within a preset prediction time range, and N is an integer greater than zero;

[0058] It should be noted that: the multiple historical sales curves are pre-stored in the system database. Further explanation is that the technical staff will collect the historical sales of each clothing product at each sales node in advance, and generate the historical sales curve of each clothing product at each sales node from the historical time and historical sales dimensions, and pre-store it in the system database. The historical sales curve of each clothing product at each sales node is usually divided into stages by quarter. For example, the annual sales data of each clothing product at each sales node is divided into four quarters (such as: January to March is a quarter) to establish a historical sales curve. If the number of sales nodes is 3, there are 12 historical sales curves for a single clothing product.

[0059] In implementation, the method of selecting a unique similar sales curve from the N historical sales curves generated by each sales node includes:

[0060] a1: extract N historical sales curves generated by the target clothing product at the jth sales node, then extract the sales feature data contained in each historical sales curve, and use the sales feature data contained in each historical sales curve as the first feature set to obtain multiple first feature sets, where j is an integer greater than zero;

[0061] a2: extract the sales feature data generated by the target clothing product at the jth sales node, and use the sales feature data generated by the target clothing product at the jth sales node as the second feature set;

[0062] Wherein, each of the second feature sets is consistent with the first feature set and contains the same sales feature data;

[0063] a3: Calculate the set similarity between the second feature set and each first feature set to obtain multiple set similarity coefficients;

[0064] The set similarity is calculated using the Euclidean distance algorithm, and its specific calculation formula is: Where: dis(A,B) is the set similarity coefficient, A i is the feature vector of the i-th sales feature data in the first feature set, B i is the feature vector of the i-th sales feature data in the second feature set, and n is the dimension of the feature, that is, the number of sales feature data;

[0065] a4: Sort multiple set similarity coefficients according to the values ​​from small to large, obtain the first feature set corresponding to the first ranked set similarity coefficient, mark the historical sales curve corresponding to the first feature set as the only similar sales curve, set j=j+1, and return to step a1;

[0066] a5: Repeat the above steps a1 to a4 until j=M, and the loop ends to obtain the unique similar sales curves of M sales nodes;

[0067] In implementation, the step of obtaining the predicted sales volume of the target clothing product at M sales nodes from the unique similar sales curve includes:

[0068] b1: Extract the unique similar sales curve of the v-th sales node, where v is an integer greater than zero;

[0069] b2: Input the preset forecast time range, and intercept the local curve part belonging to the forecast time range from the unique similar sales curve of the v-th sales node, and count the cumulative sales of the local curve part, and use the cumulative sales as the forecast sales of the target clothing product at the v-th sales node;

[0070] The span of the preset forecast time range is determined by the technicians after manual selection according to the actual forecast target, such as K days, one month or two months, where K is an integer greater than zero;

[0071] b3: Repeat steps b1 to b2 until v = M, and then end the loop to obtain the predicted sales volume of the target clothing product at M sales nodes;

[0072] Exemplarily, based on the above assumptions, the current time is January 31, 2023. If a certain type of down jacket is selected as the target clothing product, and the future sales volume of this type of down jacket at each sales node within the prediction time range (next month is artificially selected, i.e. February) is to be predicted; therefore, by extracting the sales volume of this type of down jacket at each sales node in January, and from the two dimensions of time and sales volume, the sales characteristic data generated by this type of down jacket at different sales nodes in January can be obtained; thereafter, by comparing the sales characteristic data generated by this type of down jacket at different sales nodes in January with the sales characteristic data of multiple historical sales curves, the unique similar sales curve for each sales node can be found, and finally, the sales data for February in the unique similar sales curve at each sales node is intercepted, and the predicted sales volume of this type of down jacket at M sales nodes in February can be obtained.

[0073] The supply-demand comparison module 103 is used to retrieve the inventory of the target clothing product in the current time range from all sales nodes, and obtain the target sales nodes that appear in the predicted time range according to the quantitative relationship between the predicted sales volume and the inventory; the target sales nodes include a product shortage node set including P product shortage nodes and a product surplus node set including H product surplus nodes, where P and H are integers greater than zero;

[0074] It should be noted that the inventory of the target clothing product in each sales node within the current time range can be determined by the person in charge of the local sales node after manually uploading data;

[0075] In implementation, obtaining the target sales node that occurs within the forecast time range includes:

[0076] c1: Extract the predicted sales volume and inventory of the target clothing product at the g-th sales node, where g is an integer greater than zero;

[0077] c2: Calculate the difference between the inventory and the predicted sales volume at the g-th sales node, and mark the difference between the inventory and the predicted sales volume at the g-th sales node as the supply-demand difference;

[0078] c3: Get the preset supply and demand quantity interval, and compare the supply and demand difference with the supply and demand quantity interval. If the supply and demand difference is greater than the maximum value of the supply and demand quantity interval, mark the g-th sales node as a product surplus node, set g=g+1, and return to step c1; if the supply and demand difference is less than the minimum value of the supply and demand quantity interval, mark the g-th sales node as a product shortage node, set g=g+1, and return to step c1;

[0079] It should be noted that: when the supply-demand difference is less than or equal to the maximum value of the supply-demand quantity interval, and greater than or equal to the minimum value of the supply-demand quantity interval, that is, when the supply-demand difference is within the supply-demand quantity interval, it means that the supply and demand of the corresponding sales node in the predicted (future) time range is balanced, but this situation is not within the actual consideration range, so it will not be described in detail;

[0080] c4: Repeat the above steps c1 to c3 until the loop ends when g=M, and obtain P product shortage nodes and H product surplus nodes.

[0081] The supply management module 104 is used to generate a scheduling strategy for each product shortage node using a pre-configured genetic algorithm, and perform cross-regional clothing scheduling according to the scheduling strategy; the scheduling strategy is the best scheduling sales node;

[0082] In implementation, the use of a preconfigured genetic algorithm to generate a scheduling strategy for each product shortage node includes:

[0083] d1: extract the xth product shortage node in the product shortage node set, and use the pre-configured genetic algorithm to select the best scheduling sales node from the product surplus node set, where x is an integer greater than zero;

[0084] The processing logic of the preconfigured genetic algorithm is as follows:

[0085] e1: Initialize the population: randomly generate an original population based on the product surplus node set, the original population contains R chromosomes, each chromosome represents a product surplus node, and R is an integer greater than zero;

[0086] e2: Fitness evaluation: Under each chromosome (i.e., each product surplus node in the original population), obtain the spatial distance between the xth product shortage node and each product surplus node, the supply-demand difference between the xth product shortage node and each product surplus node, and the scheduling cost between the xth product shortage node and each product surplus node; input the spatial distance and scheduling cost into the pre-constructed fitness function to calculate the fitness of each chromosome;

[0087] It is worth noting that the supply-demand difference is the difference between the inventory and the predicted sales volume, and in each chromosome (i.e., each product surplus node in the original population), what is obtained is the supply-demand difference between the xth product shortage node and each product surplus node. Therefore, it can be understood that the supply-demand difference between the xth product shortage node and each product surplus node is greater than or equal to zero;

[0088] It should also be understood that the smaller the difference between supply and demand, the smaller the cost of product scheduling. This is because, after the clothing is scheduled, if each sales point has a certain amount of clothing products left, these bulk clothing products are too low and too widely distributed. When they are scheduled again, the scheduling amount is small, which will cause the transport vehicles to travel back and forth between various sales nodes, increasing the scheduling cost.

[0089] The spatial distance between the x-th product shortage node and each product surplus node is obtained according to a pre-constructed node undirected graph;

[0090] It should be noted that: the node undirected graph is generated using graph theory technology and based on the geographic information of all sales nodes, the geographic information includes the spatial coordinates of each sales node and the distance between each sales node; the node undirected graph includes multiple vertices and multiple undirected edges, each vertex represents a sales node, and each undirected edge is formed according to the positional relationship between each sales node, and each undirected edge is given an edge attribute according to the distance between each sales node;

[0091] To further explain, the positions of the x-th product shortage node and each product surplus node in the node undirected graph can be obtained according to the spatial coordinates, and the paths of the x-th product shortage node and each product surplus node can be obtained according to the depth-first search, that is, multiple paths are formed, and the length of each path is obtained according to the undirected edges contained in each path and the distance attribute of the undirected edges, and the length of each path is used as the spatial distance;

[0092] It should also be noted that the dispatching cost of the xth product shortage node and each product surplus node is calculated according to the following formula: dispatching cost = unit transportation cost × transportation distance × dispatching quantity + fixed transportation fee; among which, the dispatching quantity is the difference between the inventory and the predicted sales volume, the transportation distance is obtained according to the spatial distance, and the unit transportation cost and fixed transportation fee are entered by the technicians according to the actual situation;

[0093] The calculation formula of the pre-constructed fitness function is: Where: Fitness is fitness, Y is spatial distance, Y0 is reference spatial distance, D is scheduling cost, D0 is reference scheduling cost, S is the difference between supply and demand, α1, α2 and α3 are weight factors greater than zero, α1<α2<α3;

[0094] Among them, the reference space distance and the reference scheduling cost are set by technical personnel based on specific experiments or experience;

[0095] e3: Selection: Use the roulette wheel method to select two chromosomes with high fitness in the original population as the father and mother;

[0096] The roulette wheel method is a commonly used selection method. It is used in genetic algorithms to select chromosomes with higher fitness to enter the next generation. It simulates the roulette wheel process. Each chromosome obtains a corresponding "roulette wheel" area according to its fitness. The higher the fitness of the chromosome, the larger its corresponding area, and the higher the probability of being selected.

[0097] e4: Crossover: Perform crossover operation on the father and mother to generate new chromosomes;

[0098] It should be noted that the crossover operation on the paternal parent and the maternal parent is implemented based on a crossover operation, and the crossover operation includes but is not limited to one of a single-point crossover, a uniform crossover or a sequential crossover, etc.;

[0099] e5: Mutation: Perform mutation operation on the new chromosomes to obtain Y new chromosomes, combine the Y new chromosomes into a new population, replace the original population with the new population, and return to step e2;

[0100] In the genetic algorithm, the mutation operation is to introduce gene diversity and prevent the algorithm from falling into the local optimum; the mutation operation on the new chromosome is implemented by uniform mutation or Gaussian mutation;

[0101] e6: Repeat the above steps e2 to e5 until the fitness of the chromosome in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold, and then output the product surplus node represented by the corresponding chromosome as the optimal scheduling sales node corresponding to the x-th product shortage node;

[0102] For example: Assume that the maximum number of iterations is 100 times, and record the chromosome with the highest fitness in the current population and its fitness value after each iteration; if it is found that the fitness value has not changed significantly in a certain generation, it is considered that the convergence condition is met, the iteration is stopped, and the product surplus node represented by the corresponding chromosome is output as the optimal scheduling sales node;

[0103] d2: Eliminate the best scheduling sales node from the product surplus node set to obtain Z product surplus nodes, set x=x+1, and return to step d1, and update the elements of the product surplus node set in step d1 according to the Z product surplus nodes, Z<H, Z is an integer greater than zero;

[0104] d3: Repeat the above steps d1 to d2 until x=P, and end the loop to obtain the scheduling strategy for each product shortage node, that is, each product shortage node obtains an optimal scheduling sales node;

[0105] It can be understood that, for a certain service product, by obtaining its predicted sales and inventory, and screening out product shortage nodes and product surplus nodes that will appear in the future based on the predicted sales and inventory, and finally using a genetic algorithm to match an optimal product surplus node for each product shortage node, and performing inventory scheduling based on it, the present invention makes up for the lag of existing clothing supply scheduling, overcomes the shortcomings of clothing scheduling strategies that simply rely on distance, effectively reduces scheduling costs, improves supply chain efficiency, improves customer experience, and enhances the competitiveness of enterprises in the market.

[0106] Example 2

[0107] See also Figure 2 As shown, based on the same inventive concept, this embodiment discloses a cross-regional clothing supply management method. For details not provided in this embodiment, please refer to the description of the relevant parts in Embodiment 1. The method includes:

[0108] S201: within the current time range, obtaining the sales volume of the target clothing product generated in M ​​sales nodes, and obtaining the sales characteristic data generated by the target clothing product at each sales node from the generated sales volume, where M is an integer greater than zero;

[0109] S202: Obtain N historical sales curves generated by the target clothing product at M sales nodes, filter out a unique similar sales curve from the N historical sales curves generated at each sales node based on the sales feature data, and obtain the predicted sales volume of the target clothing product at the M sales nodes from the unique similar sales curve, wherein the predicted sales volume is within a preset prediction time range, and N is an integer greater than zero;

[0110] S203: Retrieve the inventory of the target clothing product in the current time range from all sales nodes, and obtain the target sales nodes that appear in the predicted time range according to the quantitative relationship between the predicted sales volume and the inventory; the target sales nodes include a product shortage node set including P product shortage nodes and a product surplus node set including H product surplus nodes, where P and H are integers greater than zero;

[0111] S204: Generate a scheduling strategy for each product shortage node using a preconfigured genetic algorithm, and perform cross-regional clothing scheduling according to the scheduling strategy; the scheduling strategy is the best scheduling sales node.

[0112] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0113] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD) or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0114] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0115] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0116] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0117] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0118] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0119] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0120] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A cross-regional clothing supply management system, characterized in that: The system comprises: A data acquisition module is used to acquire the sales volume of the target clothing product generated in M ​​sales nodes within the current time range, and acquire the sales characteristic data generated by the target clothing product at each sales node from the generated sales volume, where M is an integer greater than zero; The sales volume forecasting module is used to obtain N historical sales curves generated by the target clothing product at M sales nodes, screen out a unique similar sales curve from the N historical sales curves generated at each sales node based on the sales feature data, and obtain the predicted sales volume of the target clothing product at the M sales nodes from the unique similar sales curve, wherein the predicted sales volume is within a preset prediction time range, and N is an integer greater than zero; The supply and demand comparison module is used to retrieve the inventory of the target clothing product in the current time range from all sales nodes, and obtain the target sales nodes that appear in the predicted time range according to the quantitative relationship between the predicted sales volume and the inventory; the target sales nodes include a product shortage node set including P product shortage nodes and a product surplus node set including H product surplus nodes, where P and H are integers greater than zero; The supply management module is used to generate a scheduling strategy for each product shortage node using a preconfigured genetic algorithm, and perform cross-regional clothing scheduling according to the scheduling strategy; the scheduling strategy is the optimal scheduling sales node.

2. The cross-regional clothing supply management system according to claim 1 is characterized in that: Before acquiring the image to be searched, the sales characteristic data includes total sales volume, average sales volume, average sales growth rate, average growth amount, sales standard deviation, sales peak difference and coefficient of variation.

3. The cross-regional clothing supply management system according to claim 2 is characterized in that: The method of selecting a unique similar sales curve from the N historical sales curves generated by each sales node includes: a1: extract N historical sales curves generated by the target clothing product at the jth sales node, then extract the sales feature data contained in each historical sales curve, and use the sales feature data contained in each historical sales curve as the first feature set to obtain multiple first feature sets, where j is an integer greater than zero; a2: extract the sales feature data generated by the target clothing product at the jth sales node, and use the sales feature data generated by the target clothing product at the jth sales node as the second feature set; a3: Calculate the set similarity between the second feature set and each first feature set to obtain multiple set similarity coefficients; a4: Sort multiple set similarity coefficients according to the values ​​from small to large, obtain the first feature set corresponding to the first ranked set similarity coefficient, mark the historical sales curve corresponding to the first feature set as the only similar sales curve, set j=j+1, and return to step a1; a5: Repeat the above steps a1 to a4 until the loop ends when j=M, and obtain the unique similar sales curves of M sales nodes.

4. The cross-regional clothing supply management system according to claim 1 is characterized in that: The step of obtaining the predicted sales volume of the target clothing product at M sales nodes from the unique similar sales curve includes: b1: Extract the unique similar sales curve of the v-th sales node, where v is an integer greater than zero; b2: Input the preset forecast time range, and intercept the local curve part belonging to the forecast time range from the unique similar sales curve of the v-th sales node, and count the cumulative sales of the local curve part, and use the cumulative sales as the forecast sales of the target clothing product at the v-th sales node; b3: Repeat the above steps b1 to b2 until v=M, and end the loop to obtain the predicted sales volume of the target clothing product at M sales nodes.

5. The cross-regional clothing supply management system according to claim 1 is characterized in that: The obtaining of the target sales node occurring within the forecast time range includes: c1: Extract the predicted sales volume and inventory of the target clothing product at the g-th sales node, where g is an integer greater than zero; c2: Calculate the difference between the inventory and the predicted sales volume at the g-th sales node, and mark the difference between the inventory and the predicted sales volume at the g-th sales node as the supply-demand difference; c3: Get the preset supply and demand quantity interval, and compare the supply and demand difference with the supply and demand quantity interval. If the supply and demand difference is greater than the maximum value of the supply and demand quantity interval, mark the g-th sales node as a product surplus node, set g=g+1, and return to step c1; if the supply and demand difference is less than the minimum value of the supply and demand quantity interval, mark the g-th sales node as a product shortage node, set g=g+1, and return to step c1; c4: Repeat the above steps c1 to c3 until the loop ends when g=M, and obtain P product shortage nodes and H product surplus nodes.

6. The cross-regional clothing supply management system according to claim 5, characterized in that: The method of using a preconfigured genetic algorithm to generate a scheduling strategy for each product shortage node includes: d1: extract the xth product shortage node in the product shortage node set, and use the pre-configured genetic algorithm to select the best scheduling sales node from the product surplus node set, where x is an integer greater than zero; d2: Eliminate the best scheduling sales node from the product surplus node set to obtain Z product surplus nodes, set x=x+1, and return to step d1, and update the elements of the product surplus node set in step d1 according to the Z product surplus nodes, Z<H, Z is an integer greater than zero; d3: Repeat the above steps d1 to d2 until the loop ends when x=P, and obtain the scheduling strategy for each product shortage node, that is, each product shortage node obtains an optimal scheduling sales node.

7. The cross-regional clothing supply management system according to claim 6, characterized in that: The processing logic of the preconfigured genetic algorithm is as follows: e1: Initialize the population: randomly generate an original population based on the product surplus node set, the original population contains R chromosomes, each chromosome represents a product surplus node, and R is an integer greater than zero; e2: Fitness evaluation: Under each chromosome, obtain the spatial distance between the x-th product shortage node and each product surplus node, the supply-demand difference between the x-th product shortage node and each product surplus node, and the scheduling cost between the x-th product shortage node and each product surplus node; input the spatial distance and scheduling cost into the pre-built fitness function to calculate the fitness of each chromosome; e3: Selection: Use the roulette wheel method to select two chromosomes with high fitness in the original population as the father and mother; e4: Crossover: Perform crossover operation on the father and mother to generate new chromosomes; e5: Mutation: Perform mutation operation on the new chromosomes to obtain Y new chromosomes, combine the Y new chromosomes into a new population, replace the original population with the new population, and return to step e2; e6: Repeat steps e2 to e5 above until the fitness of the chromosome in the original population or the new population is greater than or equal to the preset fitness threshold, or the number of iterations is greater than or equal to the preset maximum number of iterations threshold, and then output the product surplus node represented by the corresponding chromosome as the optimal scheduling sales node corresponding to the x-th product shortage node.

8. The cross-regional clothing supply management system according to claim 7, characterized in that: The calculation formula of the pre-constructed fitness function is: Where: Fitness is fitness, Y is spatial distance, Y0 is reference spatial distance, D is scheduling cost, D0 is reference scheduling cost, S is the difference between supply and demand, α1, α2 and α3 are weight factors greater than zero, α1<α2<α3.

9. A cross-regional clothing supply management method, characterized in that: The method comprises: In the current time range, the sales volume of the target clothing product generated in M ​​sales nodes is obtained, and the sales characteristic data generated by the target clothing product at each sales node is obtained from the generated sales volume, where M is an integer greater than zero; Obtain N historical sales curves generated by the target clothing product at M sales nodes, screen out a unique similar sales curve from the N historical sales curves generated at each sales node based on the sales feature data, and obtain the predicted sales volume of the target clothing product at the M sales nodes from the unique similar sales curve, wherein the predicted sales volume is within a preset prediction time range, and N is an integer greater than zero; Retrieve the inventory of the target clothing product in the current time range from all sales nodes, and obtain the target sales nodes that appear in the predicted time range according to the quantitative relationship between the predicted sales volume and the inventory; the target sales nodes include a product shortage node set including P product shortage nodes and a product surplus node set including H product surplus nodes, where P and H are integers greater than zero; A preconfigured genetic algorithm is used to generate a scheduling strategy for each product shortage node, and cross-regional clothing scheduling is performed according to the scheduling strategy; the scheduling strategy is the optimal scheduling sales node.

Images