Big data-based commodity cross-region supply chain management method, device and medium

Abstract

The application discloses a commodity cross-region supply chain management method and device based on big data, and a medium, comprising obtaining a plurality of historical sales data of each sales region of a commodity, determining the level of the corresponding sales region according to the priority and value weight of each historical sales data; obtaining inventory data of each sales region, and judging whether the inventory data matches the preset inventory of the sales region; if not, obtaining total inventory data of each sales region, and based on the level and inventory of each sales region, the inventory supply of the sales region is adjusted based on a supply management model. The application determines the level of each sales region through historical sales data of the region, sets the corresponding preset inventory based on the level, and adjusts the inventory of the sales region based on the supply management model, so that all sales regions are compared horizontally in the supply chain at the same time, cross-region rapid response of commodity supply is realized, and then linkage management of the supply chain of multiple sales regions is realized.

Description

Technical Field

[0001] This invention belongs to the field of supply chain management technology, specifically relating to a method, device, and medium for cross-regional supply chain management of goods based on big data. Background Technology

[0002] With technological advancements, supply chain management across various industries is increasingly becoming more information-based and intelligent. Supply chain management involves not only integrating upstream and downstream resources, but also requires extremely meticulous, precise, and accurate scientific planning and decision-making; otherwise, it will directly impact the normal production and operation of enterprises. For example, the stability and sustainable development of the supply chain gives insulation material distribution companies strong vitality and competitiveness in market competition. Therefore, more and more insulation material distribution companies are beginning to focus on related supply chain management.

[0003] A supply chain, a network structure formed by supply and demand relationships among enterprises, is a network structure composed of raw material suppliers, manufacturers, distributors, retailers, and end consumers involved in the production and distribution of products, connected with upstream and downstream members. In today's highly information-driven market, massive amounts of information are generated among members themselves and between them. How to manage and monitor supply chain information across regions to achieve rapid cross-regional response for goods has become a pressing issue. Summary of the Invention

[0004] The purpose of this invention is to provide a method, apparatus, and medium for cross-regional supply chain management of goods based on big data, in order to solve the technical problem of how to manage and monitor information of various supply chains across regions.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] The first aspect provides a big data-based approach to cross-regional supply chain management of goods, including:

[0007] Obtain various historical sales data for different sales regions of the product, and determine the level of the corresponding sales region based on the priority and value weight of each type of historical sales data;

[0008] Obtain inventory data for each sales region and determine whether the inventory data matches the preset inventory for the corresponding sales region level;

[0009] If not, obtain the total inventory data for each sales region, and allocate the inventory supply for each sales region based on the level and inventory status of each sales region and the supply management model.

[0010] In one possible design, the historical sales data includes at least product sales data, product positive review data, product complaint data, product repeat purchase data, and / or product return and exchange data.

[0011] In one possible design, the level of the corresponding sales region is determined based on the priority and value weight of each type of historical sales data, including:

[0012] Calculate the posterior probability of each historical sales data relative to each level of sales region, compare the posterior probabilities of any two historical sales data pairwise, and mark the historical sales data with the larger posterior probability, until the comparison between all historical sales data is completed.

[0013] Count the total number of tags for each type of historical sales data, and sort all historical sales data according to the total number of tags to determine the priority of each type of historical sales data based on the sorting results;

[0014] The value weight is calculated based on the priority of each type of historical sales data, and the level of the corresponding sales region is then determined.

[0015] In one possible design, the posterior probabilities of any two historical sales data are compared pairwise, and the historical sales data with the higher posterior probability is labeled, including:

[0016] The dual triangle arrangement method is used to arrange and combine M types of historical sales data in m-1 rows and m-1 columns; where each row of historical sales data contains multiple pairs of historical sales data.

[0017] The posterior probabilities of one pair of data in each row of historical sales data are compared, and the data with the higher posterior probability is marked.

[0018] In one possible design, a value weight is calculated based on the priority of each type of historical sales data, and the corresponding sales region level is calculated, including:

[0019] Based on the priority of each type of historical sales data, the weight position of that type of historical sales data is determined. The weight position corresponding to the historical sales data with priority level i is s+1-i, where s represents the type of historical sales data.

[0020] The value weight of each type of historical sales data is calculated based on its weighted position, using the following formula:

[0021]

[0022] Where Wi represents the value weight of historical sales data with priority level i, and Di represents the weight position;

[0023] Based on the value weight of each type of historical sales data, the corresponding sales region level H is calculated. k The calculation formula is as follows:

[0024]

[0025] Where k represents the k-th sales region, S g Let g represent the type of sales data, and N represent the total number of types of sales data in the k-th sales region.

[0026] In one possible design, inventory data for each sales region is obtained, and it is determined whether the inventory data matches the preset inventory for the corresponding sales region level, including:

[0027] Obtain the total number of warehouse inventory items and the total number of orders awaiting shipment in each sales region;

[0028] Based on the total number of goods in warehouse inventory and the total number of orders awaiting shipment, the inventory coefficient corresponding to the actual unsold inventory in this area is determined using the following formula:

[0029] Fj=e×(Cj×b1-Dj×b2); (2)

[0030] Where Fj represents the inventory coefficient corresponding to the actual unsold inventory in the region, e represents the correction coefficient, Cj represents the total number of goods in the warehouse, Dj represents the total number of orders to be shipped, b1 and b2 represent the preset ratio coefficients, and j represents the j-th sales region.

[0031] Determine whether the inventory coefficient corresponding to the actual consignment inventory in the region matches the preset inventory coefficient of the corresponding sales region.

[0032] In one possible design, the supply management model is constructed as follows:

[0033] Assuming that inventory is managed and scheduled across different sales regions, the management strategy matrix for the k-th sales region in the supply chain system is as follows:

[0034]

[0035] Where 'a' represents the strategy point for allocating inventory management in the k-th sales region;

[0036] The fit of the supply management model is as follows:

[0037] k0 = P max / P min (4)

[0038]

[0039] P′0=(k0+k)P max (6)

[0040] Where k0 represents the initial fit of the joint management model, P min and P max Let P represent the minimum and maximum profit obtained in the k-th sales region, P represent the total profit, P0 represent the calculated residual profit, and P′0 represent the residual profit after improving the fit.

[0041] Based on the adaptability of the supply management model, the supply management model is established as follows:

[0042]

[0043] The second aspect provides a big data-based cross-regional supply chain management device for goods, including:

[0044] The level determination module is used to obtain various historical sales data of products in different sales regions and determine the level of the corresponding sales region based on the priority and value weight of each type of historical sales data.

[0045] The inventory matching module is used to obtain inventory data for each sales region and determine whether the inventory data matches the preset inventory of the corresponding sales region.

[0046] The supply allocation module is used to obtain the total inventory data of each sales region if no, and to allocate the inventory supply of each sales region based on the level and inventory status of each sales region and the supply management model.

[0047] In one possible design, the historical sales data includes at least product sales data, product positive review data, product complaint data, product repeat purchase data, and / or product return and exchange data.

[0048] In one possible design, when determining the level of a corresponding sales region based on the priority and value weight of each type of historical sales data, the level determination module is specifically used for:

[0049] Calculate the posterior probability of each historical sales data relative to each level of sales region, compare the posterior probabilities of any two historical sales data pairwise, and mark the historical sales data with the larger posterior probability, until the comparison between all historical sales data is completed.

[0050] Count the total number of tags for each type of historical sales data, and sort all historical sales data according to the total number of tags to determine the priority of each type of historical sales data based on the sorting results;

[0051] The value weight is calculated based on the priority of each type of historical sales data, and the level of the corresponding sales region is then determined.

[0052] In one possible design, when comparing the posterior probabilities of any two historical sales data pairs and marking the historical sales data with the higher posterior probability, the level determination module is specifically used for:

[0053] The dual triangle arrangement method is used to arrange and combine M types of historical sales data in m-1 rows and m-1 columns; where each row of historical sales data contains multiple pairs of historical sales data.

[0054] The posterior probabilities of one pair of data in each row of historical sales data are compared, and the data with the higher posterior probability is marked.

[0055] In one possible design, when calculating the corresponding value weight based on the priority of each type of historical sales data and determining the level of the corresponding sales region, the level determination module is specifically used for:

[0056] Based on the priority of each type of historical sales data, the weight position of that type of historical sales data is determined. The weight position corresponding to the historical sales data with priority level i is s+1-i, where s represents the type of historical sales data.

[0057] The value weight of each type of historical sales data is calculated based on its weighted position, using the following formula:

[0058]

[0059] Where Wi represents the value weight of historical sales data with priority level i, and Di represents the weight position;

[0060] Based on the value weight of each type of historical sales data, the corresponding sales region level H is calculated. k The calculation formula is as follows:

[0061]

[0062] Where k represents the k-th sales region, S g Let g represent the type of sales data, and N represent the total number of types of sales data in the k-th sales region.

[0063] In one possible design, when acquiring inventory data for each sales region and determining whether the inventory data matches the preset inventory for the corresponding sales region, the inventory matching module is specifically used for:

[0064] Obtain the total number of warehouse inventory items and the total number of orders awaiting shipment in each sales region;

[0065] Based on the total number of goods in warehouse inventory and the total number of orders awaiting shipment, the inventory coefficient corresponding to the actual unsold inventory in this area is determined using the following formula:

[0066] Fj=e×(Cj×b1-Dj×b2); (2)

[0067] Where Fj represents the inventory coefficient corresponding to the actual unsold inventory in the region, e represents the correction coefficient, Cj represents the total number of goods in the warehouse, Dj represents the total number of orders to be shipped, b1 and b2 represent the preset ratio coefficients, and j represents the j-th sales region.

[0068] Determine whether the inventory coefficient corresponding to the actual consignment inventory in the region matches the preset inventory coefficient of the corresponding sales region.

[0069] In one possible design, the supply management model is constructed as follows:

[0070] Assuming that inventory is managed and scheduled across different sales regions, the management strategy matrix for the k-th sales region in the supply chain system is as follows:

[0071]

[0072] Where 'a' represents the strategy point for allocating inventory management in the k-th sales region;

[0073] The fit of the supply management model is as follows:

[0074] k0 = P max / P min (4)

[0075]

[0076] P′0=(k0+k)P max (6)

[0077] Where k0 represents the initial fit of the joint management model, P min and P max Let P represent the minimum and maximum profit obtained in the k-th sales region, P represent the total profit, P0 represent the calculated residual profit, and P′0 represent the residual profit after improving the fit.

[0078] Based on the adaptability of the supply management model, the supply management model is established as follows:

[0079]

[0080] Thirdly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, perform the big data-based cross-regional supply chain management method for goods as described in any possible design of the first aspect.

[0081] Fourthly, the present invention provides a computer device comprising a memory, a processor, and a transceiver that are sequentially and communicatively connected, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the big data-based cross-regional supply chain management method for goods as described in any possible design of the first aspect.

[0082] Fifthly, the present invention provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform a big data-based cross-regional supply chain management method for goods as described in any possible design of the first aspect.

[0083] The advantages of this invention compared to the prior art are:

[0084] This invention acquires historical sales data from various sales regions of a product and determines the level of the corresponding sales region based on the priority and value weight of each historical sales data point. It then acquires inventory data from each sales region and determines whether the inventory data matches the preset inventory for the corresponding level of the sales region. If not, it acquires the total inventory data for each sales region and allocates inventory supply for that sales region based on its level and inventory status, using a supply chain management model. In other words, this invention determines the level of each sales region using historical sales data and sets corresponding preset inventory levels. When the current inventory of a sales region does not match the preset inventory, the supply chain management model allocates inventory for that sales region, thereby simultaneously incorporating all sales regions into the supply chain for horizontal comparison to determine their priorities. This enables rapid cross-regional response in product supply and facilitates the coordinated management of supply chains across multiple sales regions. Attached Figure Description

[0085] Figure 1 This is a flowchart of a cross-regional supply chain management method for goods based on big data, as described in this application embodiment. Detailed Implementation

[0086] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0087] Example

[0088] To address the technical challenges of managing and monitoring supply chain information across regions, this application provides a big data-based method for cross-regional commodity supply chain management. This method determines the level of each sales region based on historical sales data and sets corresponding preset inventory levels. When the current inventory of a sales region does not match the preset inventory, the inventory of that sales region is adjusted based on a supply chain management model. This allows all sales regions to be simultaneously included in the supply chain for horizontal comparison to determine their priorities, enabling rapid cross-regional response in commodity supply and thus achieving coordinated management of supply chains across multiple sales regions.

[0089] The following will provide a detailed description of the cross-regional supply chain management method for goods based on big data provided in the embodiments of this application.

[0090] It should be noted that the big data-based cross-regional supply chain management method for goods provided in this application can be applied to terminal devices with any operating system to execute the method's process. These terminal devices include, but are not limited to, industrial computers, iPads, personal computers, and smartphones, etc., and are not limited here. For ease of description, unless otherwise specified, this application's embodiments are described using an industrial computer as the execution subject. It is understood that the execution subject does not constitute a limitation on the embodiments of this application; in other embodiments, smartphones or other types of terminal devices may be used as the execution subject.

[0091] like Figure 1 The diagram shown is a flowchart of a cross-regional supply chain management method for goods based on big data, provided in an embodiment of this application. This method includes, but is not limited to, steps S1 to S4.

[0092] Step S1. Obtain various historical sales data for each sales region of the product, and determine the level of the corresponding sales region based on the priority and value weight of each type of historical sales data;

[0093] It should be noted that, in step S1, the historical sales data includes at least product sales data, product positive review data, product complaint data, product repurchase data, and / or product return and exchange data. Of course, it is understood that, in order to make the subsequent analysis results more comprehensive and accurate, the historical sales data in this embodiment is not limited to the above-mentioned data. Other commonly used sales data, such as product browsing data and product pending shipment data, are all within the protection scope of this application embodiment and are not limited here.

[0094] Preferably, after obtaining various historical sales data for different sales regions of the product, the method further includes:

[0095] After preprocessing, historical sales data is categorized and stored in the corresponding databases.

[0096] The data preprocessing includes, but is not limited to, data cleaning of incomplete and / or erroneous data in historical sales data. Incomplete data mainly refers to data with missing information, such as supplier names, branch names, customer regional information, or mismatches between the main table and detailed tables in the business system. Data cleaning filters this type of data and then completes it according to the missing data items, for example, by requesting data completion from the data source. Erroneous data mainly refers to data with incorrect date formats or dates outside the specified range. This type of data will cause ETL (Extract-Transform-Load, data warehouse) to fail. Therefore, it needs to be selected from the business system database using SQL and sent to the corresponding department for correction within a specified timeframe, and the corrected data is then extracted. It should be noted that this embodiment creates corresponding databases for different types of historical sales data. After data cleaning, business behavior data can be stored in the corresponding databases according to categories for subsequent data analysis.

[0097] In one specific implementation of step S1, the level of the corresponding sales region is determined based on the priority and value weight of each type of historical sales data, including:

[0098] Step S11. Calculate the posterior probability of each historical sales data relative to each level of sales region. Compare the posterior probabilities of any two historical sales data pairwise and mark the historical sales data with the larger posterior probability until the comparison between all historical sales data is completed.

[0099] It should be noted that when calculating the posterior probability of each historical sales data point relative to each sales region level, the existing posterior probability calculation formula is used, which will not be elaborated here.

[0100] Specifically, the posterior probabilities of any two historical sales data sets are compared pairwise, including:

[0101] The dual triangle arrangement method is used to arrange and combine M types of historical sales data in m-1 rows and m-1 columns; where each row of historical sales data contains multiple pairs of historical sales data.

[0102] The posterior probabilities of one pair of data in each row of historical sales data are compared, and the data with the higher posterior probability is marked.

[0103] More specifically, data with higher posterior probabilities are marked; preferably, this is done by drawing circles to mark the data with higher posterior probabilities. For example, when comparing the first row of historical sales data, the specific comparison process is as follows:

[0104] Interchange O1 with O2, O3, O4, ..., O n-1 O n The posterior probability is compared; similarly, when comparing the historical sales data in the second row, the specific comparison process includes: comparing O2 with O3, O4, ..., O... in sequence. n-1 O n The posterior probabilities are compared, and so on, until all risk factors have been compared pairwise. For example, if O1 is determined to be better than O2, a circle is added to O1; otherwise, a circle is added to O2. Similarly, O2 is compared with O3, and so on, until the first row is compared. Comparisons are performed in each row in this manner, continuing until the (n-1)th row. The total number of comparisons is the cumulative combination count, i.e., Next. Then when all After comparing all the data in a combination, the priority of each data can be determined based on the number of times it has been circled. The data with the most circles is the best, and so on down to the least. If two or more data have the same number of circles, their priority is equal.

[0105] Step S12. Count the total number of tags for each type of historical sales data, and sort all historical sales data according to the total number of tags, so as to determine the priority of each type of historical sales data based on the sorting results;

[0106] Step S13. Calculate the corresponding value weight based on the priority of each type of historical sales data, and calculate the level of the corresponding sales region.

[0107] In one possible design, when calculating the corresponding value weight based on the priority of each type of historical sales data and determining the level of the corresponding sales region, the specific steps include:

[0108] Based on the priority of each type of historical sales data, the weight position of that type of historical sales data is determined. The weight position corresponding to the historical sales data with priority level i is s+1-i, where s represents the type of historical sales data.

[0109] The value weight of each type of historical sales data is calculated based on its weighted position, using the following formula:

[0110]

[0111] Where Wi represents the value weight of historical sales data with priority level i, and Di represents the weight position;

[0112] Based on the value weight of each type of historical sales data, the corresponding sales region level H is calculated. k The calculation formula is as follows:

[0113]

[0114] Where k represents the k-th sales region, S g Let g represent the type of sales data, and N represent the total number of types of sales data in the k-th sales region.

[0115] Step S2. Obtain inventory data for each sales region and determine whether the inventory data matches the preset inventory for the corresponding sales region.

[0116] In one specific implementation of step S2, inventory data for each sales region is acquired, and it is determined whether the inventory data matches the preset inventory for the corresponding level of sales region, including:

[0117] Obtain the total number of warehouse inventory items and the total number of orders awaiting shipment in each sales region;

[0118] Based on the total number of goods in warehouse inventory and the total number of orders awaiting shipment, the inventory coefficient corresponding to the actual unsold inventory in this area is determined using the following formula:

[0119] Fj=e×(Cj×b1-Dj×b2); (2)

[0120] Where Fj represents the inventory coefficient corresponding to the actual unsold inventory in the region, e represents the correction coefficient, Cj represents the total number of goods in the warehouse, Dj represents the total number of orders to be shipped, b1 and b2 represent the preset ratio coefficients, and j represents the j-th sales region.

[0121] Determine whether the inventory coefficient corresponding to the actual consignment inventory in the region matches the preset inventory coefficient of the corresponding sales region.

[0122] Specifically, this embodiment sets a preset inventory for each sales region level and calculates a coefficient for the preset inventory based on the total inventory. When the inventory coefficient corresponding to the actual sales inventory in the region is less than the preset inventory coefficient, the inventory is considered insufficient; otherwise, the inventory is considered sufficient. It is understood that there may be multiple preset inventory coefficients, such as a first preset inventory coefficient and a second preset inventory coefficient, where the first preset inventory coefficient is less than the second preset inventory coefficient. Therefore, when the inventory coefficient corresponding to the actual sales inventory in the region is less than the first preset inventory coefficient, the inventory is considered insufficient. If the inventory coefficient corresponding to the actual sales inventory in the region is not less than the first preset inventory coefficient and is less than the second preset inventory coefficient, the inventory is considered to just meet the demand. When the inventory coefficient corresponding to the actual sales inventory in the region is not less than the second preset inventory coefficient, the inventory is considered very sufficient. It is understood that in this embodiment, the level of each sales region and the corresponding preset inventory coefficient can be dynamically adjusted based on historical sales data; their values ​​are not limited here.

[0123] Step S3. If not, obtain the total inventory data for each sales region, and allocate the inventory supply for each sales region based on the supply management model according to the level and inventory status of each sales region.

[0124] In step S3, the construction process of the supply management model is as follows:

[0125] Assuming that inventory is managed and scheduled across different sales regions, the management strategy matrix for the k-th sales region in the supply chain system is as follows:

[0126]

[0127] Where 'a' represents the strategy point for allocating inventory management in the k-th sales region;

[0128] The fit of the supply management model is as follows:

[0129] k0 = P max / P min (4)

[0130]

[0131] P′0=(k0+k)P max (6)

[0132] Where k0 represents the initial fit of the joint management model, P min and P max Let P represent the minimum and maximum profit obtained in the k-th sales region, P represent the total profit, P0 represent the calculated residual profit, and P′0 represent the residual profit after improving the fit.

[0133] Based on the adaptability of the supply management model, the supply management model is established as follows:

[0134]

[0135] Based on the above disclosure, this application's embodiments obtain various historical sales data from different sales regions of the product and determine the corresponding sales region's level according to the priority and value weight of each historical sales data. By obtaining inventory data from each sales region, it determines whether the inventory data matches the preset inventory of the corresponding level of the sales region. If not, it obtains the total inventory data for each sales region and allocates the inventory supply for that sales region based on the level and inventory status of each sales region using a supply management model. In other words, this invention determines the level of each sales region through historical sales data and sets corresponding preset inventory based on the level. When the current inventory of a sales region does not match the preset inventory, the inventory of that sales region is allocated based on the supply management model. This allows all sales regions to be simultaneously included in the supply chain for horizontal comparison to determine their priority, achieving rapid cross-regional response in product supply and thus realizing the coordinated management of supply chains across multiple sales regions.

[0136] The second aspect provides a big data-based cross-regional supply chain management device for goods, including:

[0137] The level determination module is used to obtain various historical sales data of products in different sales regions and determine the level of the corresponding sales region based on the priority and value weight of each type of historical sales data.

[0138] The inventory matching module is used to obtain inventory data for each sales region and determine whether the inventory data matches the preset inventory of the corresponding sales region.

[0139] The supply allocation module is used to obtain the total inventory data of each sales region if no, and to allocate the inventory supply of each sales region based on the level and inventory status of each sales region and the supply management model.

[0140] In one possible design, the historical sales data includes at least product sales data, product positive review data, product complaint data, product repeat purchase data, and / or product return and exchange data.

[0141] In one possible design, when determining the level of a corresponding sales region based on the priority and value weight of each type of historical sales data, the level determination module is specifically used for:

[0142] Calculate the posterior probability of each historical sales data relative to each level of sales region, compare the posterior probabilities of any two historical sales data pairwise, and mark the historical sales data with the larger posterior probability, until the comparison between all historical sales data is completed.

[0143] Count the total number of tags for each type of historical sales data, and sort all historical sales data according to the total number of tags to determine the priority of each type of historical sales data based on the sorting results;

[0144] The value weight is calculated based on the priority of each type of historical sales data, and the level of the corresponding sales region is then determined.

[0145] In one possible design, when comparing the posterior probabilities of any two historical sales data pairs and marking the historical sales data with the higher posterior probability, the level determination module is specifically used for:

[0146] The dual triangle arrangement method is used to arrange and combine M types of historical sales data in m-1 rows and m-1 columns; where each row of historical sales data contains multiple pairs of historical sales data.

[0147] The posterior probabilities of one pair of data in each row of historical sales data are compared, and the data with the higher posterior probability is marked.

[0148] In one possible design, when calculating the corresponding value weight based on the priority of each type of historical sales data and determining the level of the corresponding sales region, the level determination module is specifically used for:

[0149] Based on the priority of each type of historical sales data, the weight position of that type of historical sales data is determined. The weight position corresponding to the historical sales data with priority level i is s+1-i, where s represents the type of historical sales data.

[0150] The value weight of each type of historical sales data is calculated based on its weighted position, using the following formula:

[0151]

[0152] Where Wi represents the value weight of historical sales data with priority level i, and Di represents the weight position;

[0153] Based on the value weight of each type of historical sales data, the corresponding sales region level H is calculated. k The calculation formula is as follows:

[0154]

[0155] Where k represents the k-th sales region, Sg Let g represent the type of sales data, and N represent the total number of types of sales data in the k-th sales region.

[0156] In one possible design, when acquiring inventory data for each sales region and determining whether the inventory data matches the preset inventory for the corresponding sales region, the inventory matching module is specifically used for:

[0157] Obtain the total number of warehouse inventory items and the total number of orders awaiting shipment in each sales region;

[0158] Based on the total number of goods in warehouse inventory and the total number of orders awaiting shipment, the inventory coefficient corresponding to the actual unsold inventory in this area is determined using the following formula:

[0159] Fj=e×(Cj×b1-Dj×b2); (2)

[0160] Where Fj represents the inventory coefficient corresponding to the actual unsold inventory in the region, e represents the correction coefficient, Cj represents the total number of goods in the warehouse, Dj represents the total number of orders to be shipped, b1 and b2 represent the preset ratio coefficients, and j represents the j-th sales region.

[0161] Determine whether the inventory coefficient corresponding to the actual consignment inventory in the region matches the preset inventory coefficient of the corresponding sales region.

[0162] In one possible design, the supply management model is constructed as follows:

[0163] Assuming that inventory is managed and scheduled across different sales regions, the management strategy matrix for the k-th sales region in the supply chain system is as follows:

[0164]

[0165] Where 'a' represents the strategy point for allocating inventory management in the k-th sales region;

[0166] The fit of the supply management model is as follows:

[0167] k0 = P max / P min (4)

[0168]

[0169] P′0=(k0+k)P max (6)

[0170] Where k0 represents the initial fit of the joint management model, P min and P maxLet P represent the minimum and maximum profit obtained in the k-th sales region, P represent the total profit, P0 represent the calculated residual profit, and P′0 represent the residual profit after improving the fit.

[0171] Based on the adaptability of the supply management model, the supply management model is established as follows:

[0172]

[0173] The working process, working details and technical effects of the aforementioned device provided in the second aspect of this embodiment can be found in the method described in the first aspect or any possible design of the first aspect, and will not be repeated here.

[0174] Thirdly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, perform the big data-based cross-regional supply chain management method for goods as described in any possible design of the first aspect.

[0175] The computer-readable storage medium refers to a carrier for storing data, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives and / or memory sticks, etc. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0176] The working process, working details and technical effects of the aforementioned computer-readable storage medium provided in the third aspect of this embodiment can be found in the method described in the first aspect or any possible design of the first aspect, and will not be repeated here.

[0177] Fourthly, the present invention provides a computer device comprising a memory, a processor, and a transceiver that are sequentially and communicatively connected, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the big data-based cross-regional supply chain management method for goods as described in any possible design of the first aspect.

[0178] Specifically, the memory may include, but is not limited to, Random-Access Memory (RAM), Read-Only Memory (ROM), Flash Memory, First-In-First-Out (FIFO) Memory, and / or First-In-Last-Out (FILO) Memory, etc.; the processor may not be limited to the STM32F105 series microprocessor; the transceiver may be, but is not limited to, a WiFi (Wireless Fidelity) wireless transceiver, a Bluetooth wireless transceiver, a GPRS (General Packet Radio Service) wireless transceiver, and / or a ZigBee (a low-power LAN protocol based on the IEEE 802.15.4 standard) wireless transceiver, etc. Furthermore, the computer device may also include, but is not limited to, a power module, a display screen, and other necessary components.

[0179] The working process, working details and technical effects of the aforementioned computer device provided in the fourth aspect of this embodiment can be found in the method described in the first aspect or any possible design of the first aspect, and will not be repeated here.

[0180] Fifthly, the present invention provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform a big data-based cross-regional supply chain management method for goods as described in any possible design of the first aspect.

[0181] The working process, working details and technical effects of the aforementioned computer program product containing instructions provided in the fifth aspect of this embodiment can be found in the method described in the first aspect or any possible design of the first aspect, and will not be repeated here.

[0182] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for cross-regional supply chain management of goods based on big data, characterized in that: include: Obtain various historical sales data for different sales regions of the product, and determine the level of the corresponding sales region based on the priority and value weight of each type of historical sales data; Obtain inventory data for each sales region and determine whether the inventory data matches the preset inventory for the corresponding sales region level; If not, obtain the total inventory data for each sales region, and allocate the inventory supply for each sales region based on the supply management model according to the level and inventory status of each sales region. The process of constructing the supply management model is as follows: Assuming inventory is managed and scheduled across different sales regions, then the [number]th [unit] in the supply chain system... The management strategy matrix for each sales region is as follows: ；（3） Where a represents the first... The strategy points for allocating inventory management within each sales region; The fit of the supply management model is as follows: ；(4) ；(5) ；(6) in, This indicates the initial fit of the joint management model. and Indicates the first The minimum and maximum profits that can be obtained in each sales region. Represents total profit. This represents the calculated residual profit. This represents the remaining profit after improving the fit. Based on the adaptability of the supply management model, the supply management model is established as follows: - （7）。 2. The method for cross-regional supply chain management of goods based on big data according to claim 1, characterized in that, The historical sales data includes at least product sales data, product positive review data, product complaint data, product repeat purchase data, and / or product return and exchange data.

3. The method for cross-regional supply chain management of goods based on big data according to claim 2, characterized in that, The level of the corresponding sales region is determined based on the priority and value weight of each type of historical sales data, including: Calculate the posterior probability of each historical sales data relative to each level of sales region, compare the posterior probabilities of any two historical sales data pairwise, and mark the historical sales data with the larger posterior probability, until the comparison between all historical sales data is completed. Count the total number of tags for each type of historical sales data, and sort all historical sales data according to the total number of tags to determine the priority of each type of historical sales data based on the sorting results; The value weight is calculated based on the priority of each type of historical sales data, and the level of the corresponding sales region is then calculated.

4. The method for cross-regional supply chain management of goods based on big data according to claim 3, characterized in that, Compare the posterior probabilities of any two historical sales data pairs pairwise, and mark the historical sales data with the higher posterior probability, including: The dual triangle arrangement method is used to arrange and combine M types of historical sales data in m-1 rows and m-1 columns; where each row of historical sales data contains multiple pairs of historical sales data. The posterior probabilities of one pair of data in each row of historical sales data are compared, and the data with the higher posterior probability is marked.

5. The method for cross-regional supply chain management of goods based on big data according to claim 3, characterized in that, The value weight is calculated based on the priority of each type of historical sales data, and the corresponding sales region level is determined, including: Based on the priority of each type of historical sales data, the weight position of that type of historical sales data is determined. The weight position corresponding to the historical sales data with priority level i is s+1-i, where s represents the type of historical sales data. The value weight of each type of historical sales data is calculated based on its weighted position, using the following formula: ；（1） in, This represents the value weight of historical sales data with priority level i. Indicates the weight position; The corresponding sales region level is calculated based on the value weight of each type of historical sales data. The calculation formula is as follows: in, Indicates the first Sales regions This represents the g-th type of sales data. Indicates the first The total number of types of sales data for each sales region.

6. The method for cross-regional supply chain management of goods based on big data according to claim 1, characterized in that, Obtain inventory data for each sales region and determine whether the inventory data matches the preset inventory for the corresponding sales region level, including: Obtain the total number of warehouse inventory items and the total number of orders awaiting shipment in each sales region; Based on the total number of goods in warehouse inventory and the total number of orders awaiting shipment, the inventory coefficient corresponding to the actual unsold inventory in this area is determined using the following formula: ；（2） in, This represents the inventory coefficient corresponding to the actual unsold inventory in the region. This represents the correction factor. This indicates the total number of goods in the warehouse inventory. This indicates the total number of orders awaiting shipment. and This represents the preset proportional coefficient, and j represents the j-th sales region; Determine whether the inventory coefficient corresponding to the actual consignment inventory in the region matches the preset inventory coefficient of the corresponding sales region.

7. A cross-regional supply chain management device for goods based on big data, characterized in that: The apparatus is used to execute the big data-based cross-regional supply chain management method for goods as described in any one of claims 1 to 6, wherein the apparatus comprises: The level determination module is used to obtain various historical sales data of products in different sales regions and determine the level of the corresponding sales region based on the priority and value weight of each type of historical sales data. The inventory matching module is used to obtain inventory data for each sales region and determine whether the inventory data matches the preset inventory of the corresponding sales region. The supply allocation module is used to obtain the total inventory data of each sales region if no, and to allocate the inventory supply of each sales region based on the level and inventory status of each sales region and the supply management model.

8. The cross-regional supply chain management device for commodities based on big data according to claim 7, characterized in that, The historical sales data includes at least product sales data, product positive review data, product complaint data, product repeat purchase data, and / or product return and exchange data.

9. A storage medium, characterized in that, The storage medium stores instructions that, when executed on a computer, perform the cross-regional supply chain management method for goods based on big data as described in any one of claims 1 to 6.

Images