Finished cigarette warehouse net layout optimization method and system based on multi-model collaboration

Abstract

The invention relates to the technical field of warehouse logistics optimization, in particular to a finished cigarette warehouse network layout optimization method and system based on multi-model collaboration. According to the finished cigarette warehouse network layout optimization method based on multi-model collaboration, basic information, transportation data and production plan data of each warehouse are collected and preprocessed; designing a slack season conventional delivery mode and a zero delivery mode; a weekly plan-based warehouse transfer model, a storage-sales ratio-based warehouse transfer model, a safe inventory-based warehouse transfer model and a warehouse capacity early-warning warehouse transfer model are constructed, and an intelligent warehouse selection model and a warehouse transfer scheduling model are autonomously switched and cooperatively used, so that comprehensive optimization of the finished cigarette warehouse network layout is realized. According to the finished cigarette warehouse network layout optimization method and system based on multi-model collaboration, the intelligent warehouse selection model and the warehouse transfer scheduling model are cooperatively used according to different business scenes and requirements, and comprehensive optimization of multiple factors such as logistics cost, delivery efficiency and inventory availability is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of warehousing logistics optimization, and particularly to a method and system for optimizing the layout of a finished cigarette warehouse network based on multi-model collaboration. Background Art

[0002] Currently, in the warehousing logistics management of finished cigarettes, the optimization of warehouse layout mostly adopts a single model, making it difficult to comprehensively consider various factors and complex business scenarios.

[0003] For example, some methods only focus on logistics costs and do not fully consider factors such as shipping efficiency and inventory availability; when dealing with different shipping modes (such as regular shipping in the off-season and zero-point shipping), there is a lack of a flexible model switching and collaboration mechanism; at the same time, for the demand of transfer scheduling between warehouses, existing methods cannot achieve dynamic and accurate inventory management and optimization.

[0004] In addition, during the data processing and model construction process, there are problems such as inaccurate data matching and parameter setting relying on manual experience, resulting in the need to improve the accuracy and reliability of the optimization results.

[0005] In order to solve the problems of single-model limitations, insufficient comprehensive consideration of multiple factors, poor adaptability to shipping modes, inaccurate transfer scheduling, and data processing and parameter setting in the existing methods for optimizing the layout of the finished cigarette warehouse network, the present invention proposes a method and system for optimizing the layout of the finished cigarette warehouse network based on multi-model collaboration. Summary of the Invention

[0006] The present invention provides a simple and efficient method and system for optimizing the layout of a finished cigarette warehouse network based on multi-model collaboration to make up for the defects of the existing technology.

[0007] The present invention is realized through the following technical solutions: A method for optimizing the layout of a finished cigarette warehouse network based on multi-model collaboration, comprising the following steps: Step S1, data collection and collation For the existing warehouse distribution, collect the basic information, transportation data, and production plan data of each warehouse, and perform preprocessing to provide data support for model construction; the preprocessing means are as follows: Clean the collected data to remove outliers and incorrect data; Perform standardization processing to unify the data units; Fill in the missing data with the mean value or perform manual processing; Step S2, construct an intelligent warehouse selection model Determine the basic information and design the regular shipping mode in the off-season and the zero-point shipping mode; For the regular delivery mode in the off-season, establish an objective function model with the lowest logistics cost, clarify the functional relationships and constraints of the total cost, transportation cost, and warehousing cost, and output the optimal delivery warehouse and delivery mode; For the zero-point delivery mode, establish an objective function model with the highest delivery efficiency, and clarify the relationships and constraints between the delivery efficiency, delivery mileage, and outbound efficiency; In the step S2, the objective function model with the lowest logistics cost considers the transportation cost and the warehousing cost; The calculation formula for the logistics cost is as follows: , where C is the total cost, is the transportation cost, is the warehousing cost; is the cargo transportation volume of the kth vehicle transporting goods from warehouse i to distribution center j, with the unit of ton; is the mileage from location i to location j; is the charging standard per unit volume of goods per unit distance, with the unit of yuan / ton-kilometer; represents the number of transportation times from warehouse i to distribution center j; M is the number of warehouses; N is the number of distribution centers; is the handling cost per unit quantity of goods in warehouse i; is the total quantity of goods in warehouse i, ; is the storage cost per unit quantity of goods in warehouse i; The constraints include transportation lead time, outbound method, production plan, outbound capacity, and storage capacity, which are specifically as follows: Inventory limit: The total sales volume does not exceed the total quantity of goods in warehouse i , expressed as ; Lead time constraint: The time notified for early transportation is not lower than the transportation lead time , expressed as ; Outbound capacity constraint: The outbound speed of warehouse i is not lower than the ratio of the total sales volume and the time notified for early transportation , expressed as ; Vehicle constraint: The total number of transportation vehicles Not less than the total sales volume The ratio with the vehicle transportation volume is expressed as ; Driver restraint: The total number of drivers P is not less than the total number of transport vehicles V, expressed as .

[0008] In the step S2, in the zero-point delivery mode, the highest delivery efficiency is taken as the optimization goal; the objective function considers the time cost, and the influencing factors include the delivery mileage and the outbound efficiency; The calculation formula of the time logistics cost is as follows: , where is the loading and unloading time, is the transportation time; is the transportation time of the kth vehicle transporting goods from warehouse i to distribution center j; is the loading time of the kth vehicle in warehouse i; is the unloading time of the kth vehicle in distribution center j; is the number of transportation times from warehouse i to distribution center j; M is the number of warehouses; N is the number of distribution centers; The constraint conditions include the availability of transport vehicles and the warehouse operation time, as follows: Transport capacity limit: The total amount of goods transported to distribution center j shall not exceed the total amount of goods in warehouse i and the maximum receiving capacity of distribution center j, expressed as: , , Warehouse outbound speed constraint: The speed of transporting goods from the warehouse to distribution center j does not exceed the outbound speed of warehouse i, expressed as: , Distribution center receiving speed constraint: The speed of transporting goods of the kth vehicle from warehouse i to the distribution center does not exceed the receiving speed of distribution center j, expressed as: , Vehicle quantity limit: The total number of transportation times from the warehouse to the distribution center does not exceed the total number of transport vehicles, expressed as: , where is the total amount of goods in warehouse i, ; is the maximum receiving capacity of distribution center j, ; is the cargo transportation volume of the kth vehicle transporting goods from warehouse i to distribution center j, with the unit of ton; is the outbound speed of warehouse i; is the receiving speed of distribution center j; is the total number of transport vehicles.

[0009] Step S3: Construct the inventory transfer scheduling model Construct the weekly plan-based inventory transfer model, inventory-sales ratio-based inventory transfer model, safety stock-based inventory transfer model, and storage capacity warning-based inventory transfer model. For different inventory transfer requirements, calculate the inventory transfer volume, inventory transfer destination, and required arrival date; In the said step S3, the weekly plan-based inventory transfer model uses the marketing weekly plan as data support. According to the principle of replenishing goods at fixed times but in variable quantities, calculate the normal replenishment quantity and the minimum replenishment quantity every week, considering the minimum economic batch and the optimal vehicle routing. It is applicable to the replenishment requirements of the central warehouse, out-of-province front warehouses, and shared warehouses; Inventory-sales ratio-based inventory transfer model: Based on the ABC classification of cigarettes, customize the upper and lower limits of the inventory-sales ratio for different product specifications. When the inventory-sales ratio is lower than the lower limit, trigger the replenishment mechanism to achieve dynamic replenishment. It is applicable to the replenishment requirements of the central warehouse, out-of-province front warehouses, and shared warehouses; Safety stock-based inventory transfer model: Customize the safety stock threshold. When the inventory level is lower than the safety stock threshold, trigger replenishment to replenish the inventory to the highest inventory or target inventory level. It is applicable to the replenishment requirements of the central warehouse, out-of-province front warehouses, and shared warehouses; Storage capacity warning-based inventory transfer model: Real-time monitor the storage capacity of the warehouse. When the inventory level reaches or exceeds the customized warning threshold, trigger the inventory transfer mechanism to calculate the inventory transfer quantity and direction. It is applicable to the inventory transfer requirements from the factory warehouse to the central warehouse and from the factory warehouse to the factory warehouse.

[0010] Step S4: Establish a multi-model collaboration mechanism According to different business scenarios and requirements, independently switch and collaboratively use the intelligent warehouse selection model and the inventory transfer scheduling model to achieve a comprehensive optimization of the finished cigarette warehouse network layout.

[0011] A finished cigarette warehouse network layout optimization system based on multi-model collaboration for implementing the above method, including A data collection and collation module, responsible for collecting the basic information, transportation data, and production plan data of each warehouse for the existing warehouse distribution, and performing preprocessing to provide data support for model construction; The preprocessing means of the said data collection and collation module are as follows: Clean the collected data to remove outliers and incorrect data; Perform standardization to unify the data units; Fill in the missing data with the mean value or perform manual processing; The intelligent warehouse selection model construction module is responsible for determining the basic information and designing the regular delivery mode and zero-point delivery mode during the off-season; For the regular delivery mode during the off-season, establish an objective function model with the lowest logistics cost, clarify the functional relationships and constraints of the total cost, transportation cost, and warehousing cost, and output the optimal delivery warehouse and delivery mode; For the zero-point delivery mode, establish an objective function model with the highest delivery efficiency, clarify the relationships between the delivery efficiency, delivery mileage, and outbound efficiency, and the constraints; The stock transfer scheduling model construction module is responsible for constructing the weekly plan stock transfer model, the stock transfer model based on the inventory-sales ratio, the stock transfer model based on the safety stock, and the stock transfer model for capacity warning. For different stock transfer requirements, calculate the stock transfer quantity, stock transfer destination, and required arrival date; The multi-model collaboration module is responsible for automatically switching and collaborating with the intelligent warehouse selection model and the stock transfer scheduling model according to different business scenarios and requirements, and realizing the comprehensive optimization of the finished tobacco warehouse network layout.

[0012] An optimized device for the finished tobacco warehouse network layout based on multi-model collaboration includes a memory and a processor; the memory is used to store a computer program, and the processor is used to implement the above method steps when executing the computer program.

[0013] A readable storage medium stores a computer program, and the computer program implements the above method steps when executed by a processor.

[0014] The beneficial effects of the present invention are as follows: The optimized method and system for the finished tobacco warehouse network layout based on multi-model collaboration collaborate with the intelligent warehouse selection model and the stock transfer scheduling model according to different business scenarios and requirements, have strong adaptability to business scenarios, more scientific data processing and parameter setting, dynamic and accurate inventory management, and realize the comprehensive optimization of multiple factors such as logistics cost, delivery efficiency, and inventory availability. Description of the Drawings

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Appendix Figure 1Schematic diagram of the optimized method for the finished tobacco warehouse network layout based on multi-model collaboration in the present invention.

[0017] Appendix Figure 2 Schematic diagram of the optimized process for the finished tobacco warehouse network layout based on multi-model collaboration in the present invention.

[0018] Appendix Figure 3 Schematic diagram of the strategy of the inventory transfer scheduling model in the present invention. Detailed implementation manners

[0019] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0020] As shown in the appendix Figure 1 The optimized method for the finished tobacco warehouse network layout based on multi-model collaboration includes the following steps: Step S1: Data collection and collation For the existing warehouse distribution, collect the basic information, transportation data, and production plan data of each warehouse, and perform preprocessing to provide data support for model construction; the preprocessing means are as follows: Clean the collected data to remove outliers and incorrect data; Perform standardization processing to unify the data units; Fill in the missing data with the mean value or perform manual processing; Step S2: Build an intelligent warehouse selection model Determine the basic information, and design the regular shipping mode and zero-point shipping mode in the off-season; For the regular shipping mode in the off-season, establish an objective function model with the lowest logistics cost, clarify the functional relationships and constraint conditions of the total cost, transportation cost, and warehousing cost, and output the optimal shipping warehouse and shipping mode; For the zero-point shipping mode, establish an objective function model with the highest shipping efficiency, and clarify the relationships and constraint conditions between the shipping efficiency, delivery mileage, and outbound efficiency; In the above step S2, the objective function model with the lowest logistics cost considers the transportation cost (positively correlated with sales volume and mileage, negatively correlated with vehicle transportation efficiency and driver professional level, including in-transit loss cost) and the warehousing cost (positively correlated with sales volume and rental cost, negatively correlated with loading and unloading efficiency and storage level, including in-warehouse loss cost); The calculation formula for the logistics cost is as follows: , Among them, C is the total cost, is the transportation cost, is the warehousing cost; is the quantity of goods transported by the k-th vehicle from warehouse i to distribution center j, with the unit of ton; is the mileage from location i to location j; is the charging standard per unit quantity of goods per unit distance, with the unit of yuan / ton-kilometer; represents the number of transportation times from warehouse i to distribution center j; M is the number of warehouses; N is the number of distribution centers; is the handling cost per unit quantity of goods in warehouse i; is the total quantity of goods in warehouse i, ; is the storage cost per unit quantity of goods in warehouse i; The described constraint conditions include transportation lead time, outbound mode, production plan, outbound capacity, and storage capacity, specifically as follows: Inventory limit: The total sales volume does not exceed the total quantity of goods in warehouse i , expressed as ; Lead time constraint: The time notified in advance for transportation is not lower than the transportation lead time , expressed as ; Outbound capacity constraint: The outbound speed of warehouse i is not lower than the ratio of the total sales volume and the time notified in advance for transportation , expressed as ; Vehicle constraint: The total number of transport vehicles is not lower than the ratio of the total sales volume and the vehicle transportation volume , expressed as ; Driver constraint: The total number of drivers P is not lower than the total number of transport vehicles V, expressed as .

[0021] In the step S2, in the zero-point delivery mode, the highest delivery efficiency is taken as the optimization goal; the objective function considers the time cost, and the influencing factors include the delivery mileage and the outbound efficiency; The calculation formula for the time logistics cost is as follows: , in, For loading and unloading time, For transportation time; is the transportation time of the kth vehicle transporting goods from warehouse i to distribution center j; is the loading time of the kth vehicle at warehouse i; is the unloading time of the kth vehicle at distribution center j; represents the number of transportations from warehouse i to distribution center j; M is the number of warehouses; N is the number of distribution centers; The constraints include transportation vehicle availability and warehouse operation time, as follows: Transport capacity limit: The total amount of goods shipped to distribution center j must not exceed the total amount of goods in warehouse i and the maximum receiving capacity of distribution center j, expressed as: , , Warehouse delivery speed constraint: The delivery speed of goods from warehouse i to distribution center j must not exceed the delivery speed of warehouse i, which can be expressed as: , Distribution center receiving speed constraint: The delivery speed of the kth vehicle transporting goods from warehouse i to the distribution center must not exceed the receiving speed of distribution center j, which is expressed as: , Vehicle quantity limit: The total number of transports from the warehouse to the distribution center shall not exceed the total number of transport vehicles, expressed as: , in, is the total amount of goods in warehouse i, ; is the maximum receiving quantity of distribution center j, ; is the cargo transport volume of the kth vehicle transporting goods from warehouse i to distribution center j, in tons; is the outbound speed of warehouse i; is the receiving speed of distribution center j; is the total number of transport vehicles.

[0022] Step S3: Build the inventory transfer scheduling model Build the weekly plan-based inventory transfer model, the inventory-sales ratio-based inventory transfer model, the safety stock-based inventory transfer model, and the storage capacity warning-based inventory transfer model. For different inventory transfer requirements, calculate the inventory transfer quantity, the destination of the inventory transfer, and the required arrival date; As shown in the appendix Figure 3 As shown in the figure, in step S3, the weekly plan-based inventory transfer model uses the marketing weekly plan as data support. According to the principle of replenishing goods at a fixed time but not a fixed quantity, calculate the normal replenishment quantity and the minimum replenishment quantity every week, considering the minimum economic batch and the optimal vehicle routing. It is applicable to the replenishment requirements of the central warehouse, the out-of-province front warehouse, and the shared warehouse; Inventory-sales ratio-based inventory transfer model: Based on the ABC classification of cigarettes, customize the upper and lower limits of the inventory-sales ratio for different product specifications. When the inventory-sales ratio is lower than the lower limit, trigger the replenishment mechanism to achieve dynamic replenishment. It is applicable to the replenishment requirements of the central warehouse, the out-of-province front warehouse, and the shared warehouse; Safety stock-based inventory transfer model: Customize the safety stock threshold. When the inventory level is lower than the safety stock threshold, trigger replenishment to replenish the inventory to the maximum inventory or the target inventory level. It is applicable to the replenishment requirements of the central warehouse, the out-of-province front warehouse, and the shared warehouse; Storage capacity warning-based inventory transfer model: Real-time monitor the storage capacity of the warehouse. When the inventory level reaches or exceeds the customized warning threshold, trigger the inventory transfer mechanism to calculate the inventory transfer quantity and direction. It is applicable to the inventory transfer requirements from the factory warehouse to the central warehouse and from the factory warehouse to the factory warehouse.

[0023] Table 1 Correspondence table of different inventory transfer requirements for inventory transfer scheduling

[0024] Step S4: Establish a multi-model collaboration mechanism According to different business scenarios and requirements, independently switch and collaboratively use the intelligent warehouse selection model and the inventory transfer scheduling model to achieve a comprehensive optimization of the finished cigarette warehouse network layout. The optimized process is as shown in the appendix Figure 2 as shown

[0025] Automatically switch the core model according to the peak sales season (such as holidays) or the off-season.

[0026] Peak season scenario: Take the zero-point delivery model as the core to ensure the delivery efficiency. Through the storage capacity warning-based inventory transfer model (example), replenish the front warehouse in advance to shorten the delivery time. For example, when the inventory in the factory warehouse exceeds the storage capacity threshold (such as 80%), trigger the inventory transfer to the central warehouse to ensure a quick response to zero-point orders.

[0027] Off-season scenario: Take the off-season regular model as the core and balance the inventory according to the weekly plan-based inventory transfer model (example). For example, calculate the replenishment quantity according to the marketing plan every week and transfer the goods from the central warehouse to the shared warehouse to reduce the warehousing cost.

[0028] Through multi - model collaboration, comprehensively optimize the layout of the finished tobacco storage network.

[0029] The finished tobacco storage network layout optimization system based on multi - model collaboration is used to implement the above - mentioned method, including A data collection and collation module, which is responsible for collecting the basic information, transportation data, and production plan data of each warehouse according to the existing warehouse distribution, and performing pre - processing to provide data support for model construction; The pre - processing means of the data collection and collation module are as follows: Clean the collected data to remove outliers and incorrect data; Perform standardization processing to unify the data units; Fill in the missing data with the mean value or perform manual processing; An intelligent warehouse selection model construction module, which is responsible for determining the basic information and designing the regular shipping mode and zero - point shipping mode in the off - season; For the regular shipping mode in the off - season, establish an objective function model with the lowest logistics cost, clarify the functional relationships and constraints of the total cost, transportation cost, and warehousing cost, and output the optimal shipping warehouse and shipping mode; For the zero - point shipping mode, establish an objective function model with the highest shipping efficiency, clarify the relationships and constraints between the shipping efficiency, delivery mileage, and outbound efficiency; A transfer scheduling model construction module, which is responsible for constructing a weekly - plan transfer model, a transfer model based on inventory - sales ratio, a transfer model based on safety stock, and a transfer model for storage capacity warning. For different transfer requirements, calculate the transfer quantity, transfer destination, and required arrival date; A multi - model collaboration module, which is responsible for autonomously switching and collaboratively using the intelligent warehouse selection model and the transfer scheduling model according to different business scenarios and requirements, to achieve comprehensive optimization of the layout of the finished tobacco storage network.

[0030] The finished tobacco storage network layout optimization device based on multi - model collaboration includes a memory and a processor; the memory is used to store computer programs, and the processor is used to implement the above - mentioned method steps when executing the computer programs.

[0031] The readable storage medium stores a computer program, and the computer program implements the above - mentioned method steps when executed by a processor.

[0032] The finished tobacco storage network layout optimization method and system based on multi - model collaboration, according to different business scenarios and requirements, collaboratively use the intelligent warehouse selection model and the transfer scheduling model, and achieve comprehensive optimization of multiple factors such as logistics cost, shipping efficiency, and inventory availability.

[0033] The comprehensive optimization effect is remarkable: Through the collaboration of multiple models, comprehensively considering multiple factors such as logistics costs, delivery efficiency, and inventory availability, the overall optimization of the finished tobacco warehouse network layout is achieved.

[0034] Strong adaptability to business scenarios: For different delivery modes (regular delivery in the off-season, zero-point delivery) and transfer requirements (transfer from the front warehouse, transfer from the central warehouse, transfer from the out-of-province front warehouse, transfer from the shared warehouse, internal transfer between factories), corresponding models and strategies are provided to ensure the optimal warehouse network layout and inventory management in various business scenarios.

[0035] Data processing and parameter setting are more scientific: Through data preprocessing and parameter calculation based on historical data, the accuracy of data and the scientific nature of parameter setting are improved, reducing the dependence on manual experience and making the model more reliable and accurate.

[0036] Dynamic and precise inventory management: The transfer scheduling model realizes the dynamic monitoring and precise management of inventory, timely triggers the replenishment and transfer mechanisms, ensures inventory balance, reduces the risks of inventory backlog and out-of-stock, and improves inventory turnover.

[0037] The embodiments described above are only one of the specific implementation manners of the present invention. The general changes and substitutions made by those skilled in the art within the scope of the technical solution of the present invention should be included in the protection scope of the present invention.

Claims

1. An optimization method for the layout of the finished cigarette warehouse network based on multi-model collaboration, characterized in that: It includes the following steps: Step S1, data collection and collation For the existing warehouse distribution, collect the basic information, transportation data and production plan data of each warehouse, and perform preprocessing to provide data support for model construction; the preprocessing means are as follows: Clean the collected data to remove outliers and incorrect data; Perform standardization processing to unify the data units; Fill in the missing data with the mean value or perform manual processing; Step S2, construct an intelligent warehouse selection model Determine the basic information and design the regular shipping mode and zero-point shipping mode in the off-season; For the regular shipping mode in the off-season, establish an objective function model with the lowest logistics cost, clarify the functional relationships and constraints of the total cost, transportation cost, and warehousing cost, and output the optimal shipping warehouse and shipping mode; For the zero-point shipping mode, establish an objective function model with the highest shipping efficiency, and clarify the relationships and constraints between the shipping efficiency, delivery mileage, and outbound efficiency; Step S3, construct an inventory transfer scheduling model Construct an inventory transfer model according to the weekly plan, an inventory transfer model according to the inventory-sales ratio, an inventory transfer model according to the safety inventory, and an inventory transfer model for storage capacity warning. For different inventory transfer requirements, calculate the inventory transfer quantity, inventory transfer destination, and required arrival date; Step S4, establish a multi-model collaboration mechanism According to different business scenarios and requirements, independently switch and collaboratively use the intelligent warehouse selection model and the inventory transfer scheduling model to achieve a comprehensive optimization of the finished tobacco warehouse network layout.

2. The method for optimizing the layout of the finished cigarette warehouse network based on multi-model collaboration according to claim 1, wherein: In the said step S2, the objective function model with the lowest logistics cost considers the transportation cost and the warehousing cost; The logistics cost calculation formula is as follows: ， Among them, C is the total cost, is the transportation cost, and is the warehousing cost; The cargo transportation volume of the k-th vehicle for transporting goods from warehouse i to distribution center j, with the unit of ton; is the mileage from location i to location j; It is the charging standard per unit distance for each unit quantity of goods, with the unit being yuan / ton-kilometer; To represent the number of transportation times from warehouse i to distribution center j; M is the number of warehouses; N is the number of distribution centers; It is the handling cost for unit quantity of goods in warehouse i; is the total quantity of goods in warehouse i, ; It is the storage cost for i unit quantity of goods in the warehouse; The said constraints include the transportation lead time, outbound method, production plan, outbound capacity, and storage capacity, specifically as follows: Inventory limit: total sales volume shall not exceed the total quantity of goods in warehouse i , expressed as ; Lead time constraint: Notify the time of early shipment Not less than the shipping lead time , expressed as ; Outbound capacity constraint: The outbound speed of warehouse i shall not be lower than the total sales volume and the time of advance transportation notified The ratio is expressed as ; Vehicle restraint: Total number of transport vehicles Not less than the total sales volume Ratio to vehicle transportation volume Expressed as ; Driver restraint: The total number of drivers P is not less than the total number of transport vehicles V, expressed as .

3. The method for optimizing the layout of the finished cigarette warehouse network based on multi-model collaboration according to claim 1, characterized in that: In the said step S2, in the zero-point shipping mode, the optimization objective is the highest shipping efficiency; the objective function considers the time cost, and the influencing factors include the delivery mileage and the outbound efficiency; The time logistics cost calculation formula is as follows: ， Among them, is the loading and unloading time, is the transportation time; The transportation time of the k-th vehicle for transporting goods from warehouse i to distribution center j; is the loading time of the k-th vehicle in warehouse i; is the unloading time of the k-th vehicle at the distribution center j; To represent the number of transportation times from warehouse i to distribution center j; M is the number of warehouses; N is the number of distribution centers; The constraints include the availability of transportation vehicles and the warehouse operation time, specifically as follows: Transportation capacity limit: The total transportation volume to distribution center j shall not exceed the total quantity of goods in warehouse i and the maximum receiving quantity of distribution center j, expressed as: ， ， Warehouse outbound speed constraint: The transportation speed of goods from warehouse i to distribution center j does not exceed the outbound speed of warehouse i, expressed as: ， Distribution center receiving speed constraint: The transportation speed of goods from warehouse i to the kth vehicle of distribution center j does not exceed the receiving speed of distribution center j, expressed as: ， Vehicle quantity limit: The total number of transportation times from the warehouse to the distribution center does not exceed the total number of transportation vehicles, expressed as: ， Among them, is the total quantity of goods in warehouse i, ; is the maximum receiving volume of distribution center j, ; The cargo transportation volume of the k-th vehicle for transporting goods from warehouse i to distribution center j, with the unit of ton; is the outbound speed of warehouse i; is the receiving speed of distribution center j; is the total number of transport vehicles.

4. The method for optimizing the layout of the finished cigarette bin network based on multi-model collaboration according to claim 1, characterized in that: In the said step S3, the inventory transfer model according to the weekly plan uses the marketing weekly plan as data support, calculates the normal replenishment quantity and the minimum replenishment quantity according to the principle of regular but variable quantity replenishment every week, considers the minimum economic batch and the optimal vehicle routing, and is applicable to the replenishment requirements of the central warehouse, the out-of-province front warehouse, and the shared warehouse.

5. The method for optimizing the layout of the finished cigarette warehouse network based on multi-model collaboration according to claim 1, characterized in that: The said inventory transfer model according to the inventory-sales ratio: Based on the ABC classification of cigarettes, custom-set the upper and lower limits of the inventory-sales ratio for different product specifications. When the inventory-sales ratio is lower than the lower limit, trigger the replenishment mechanism to achieve dynamic replenishment, and is applicable to the replenishment requirements of the central warehouse, the out-of-province front warehouse, and the shared warehouse.

6. The method for optimizing the layout of the finished cigarette bin network based on multi-model collaboration according to claim 1, wherein: The inventory transfer model based on safety stock: Customize and set the safety stock threshold. When the inventory level is lower than the safety stock threshold, replenishment is triggered to replenish the inventory to the maximum inventory or target inventory level, which is applicable to the replenishment requirements of the central warehouse, out-of-province front warehouses, and shared warehouses.

7. The method for optimizing the layout of the finished cigarette warehouse network based on multi-model collaboration according to claim 1, characterized in that: The inventory capacity warning transfer model: Real-time monitor the warehouse storage capacity. When the inventory level reaches or exceeds the customized warning threshold, the transfer mechanism is triggered to calculate the transfer quantity and direction, which is applicable to the transfer requirements from the factory warehouse to the central warehouse and from the factory warehouse to the factory warehouse.

8. A finished cigarette warehouse network layout optimization system based on multi-model collaboration, characterized in that: For implementing the method described in any one of claims 1 to 7, including: A data collection and collation module, responsible for collecting the basic information, transportation data, and production plan data of each warehouse according to the existing warehouse distribution, and performing preprocessing to provide data support for model construction; The preprocessing means of the data collection and collation module are as follows: Clean the collected data to remove outliers and incorrect data; Perform standardization processing to unify the data units; Fill in the missing data with the mean value or perform manual processing; An intelligent warehouse selection model construction module, responsible for determining the basic information and designing the regular shipping mode and zero-point shipping mode during the off-season; For the regular shipping mode during the off-season, establish an objective function model with the lowest logistics cost, clarify the functional relationships and constraints of the total cost, transportation cost, and warehousing cost, and output the optimal shipping warehouse and shipping mode; For the zero-point shipping mode, establish an objective function model with the highest shipping efficiency, clarify the relationships and constraints between the shipping efficiency, delivery mileage, and outbound efficiency; A transfer scheduling model construction module, responsible for constructing the weekly plan-based transfer model, inventory-sales ratio-based transfer model, safety stock-based transfer model, and inventory capacity warning transfer model, and calculating the transfer quantity, transfer destination, and required arrival date for different transfer requirements; A multi-model collaboration module, responsible for autonomously switching and collaborating with the intelligent warehouse selection model and the transfer scheduling model according to different business scenarios and requirements to achieve a comprehensive optimization of the finished tobacco warehouse network layout.

9. An optimized device for the layout of the finished cigarette storage network based on multi-model collaboration, characterized in that: Including a memory and a processor; the memory is used to store a computer program, and the processor is used to implement the method described in any one of claims 1 to 7 when executing the computer program.

10. A readable storage medium, characterized in that: A computer program is stored on the readable storage medium, and when the computer program is executed by the processor, it implements the method described in any one of claims 1 to 7.

Images