Site selection and transportation method, site selection and transportation device, electronic device, and storage medium

Abstract

The application provides a site selection and transportation method, a site selection and transportation device, an electronic device and a storage medium, belongs to the technical field of data processing, and determines market demand data through market demand distribution, determines store distribution data according to the market demand data, obtains construction cost data according to site selection information, unit construction cost and store quantity, obtains production cost data according to production quantity, unit product production cost and store quantity, obtains transportation cost data according to unit product transportation cost data, store distribution data, store quantity and object quantity, determines sales quantity data according to the store distribution data, obtains product sold data according to unit product sales data and sales quantity data, constructs a multi-stage store site selection and transportation model according to the product sold data, the construction cost data, the production cost data and the transportation cost data, and obtains a store site selection and transportation scheme according to the multi-stage store site selection and transportation model, so that the accuracy of store site selection and store distribution quantity can be improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a location-selection transportation method, a location-selection transportation device, an electronic device, and a storage medium. Background Technology

[0002] In related technologies, manual methods are used for store site selection and subsequent delivery services. However, the accuracy of site selection is affected by subjective human factors. Even after a suitable location is chosen, uncertainties in market demand data can lead to insufficient delivery volume, impacting the store's subsequent delivery services. Therefore, improving the accuracy of store site selection and delivery volume is a pressing issue that needs to be addressed. Summary of the Invention

[0003] The main objective of this application is to provide a site selection and transportation method, a site selection and transportation device, an electronic device, and a storage medium, which aim to improve the accuracy of store site selection and store delivery volume.

[0004] To achieve the above objectives, a first aspect of this application proposes a location-based transportation method, the method comprising:

[0005] Market demand data within a preset time range is determined based on a preset market demand distribution; the preset time range includes multiple different time periods.

[0006] The store delivery data for the current time period is determined based on market demand data from multiple reference time periods; both the reference time periods and the current time period are within the preset time range, the reference time period is earlier than the current time period, and the store delivery data is used to characterize the delivery volume of the target store to the target object in the current time period;

[0007] Based on the location information, unit construction cost, and number of stores of the target store, the construction cost data of the target store within the preset time range is obtained;

[0008] Based on the production volume of the target store, the unit product production cost, and the number of stores, the production cost data of the target store within the preset time range is obtained;

[0009] Based on the unit product transportation cost data of the target store, the store delivery data, the number of stores, and the number of objects of the target object, the transportation cost data of the target store within the preset time range is obtained;

[0010] The sales volume data is determined based on the store delivery data.

[0011] Based on the unit product sales data and the sales quantity data of the target object, the product sales data of the target store within the preset time range are obtained;

[0012] A multi-stage store location and transportation model is constructed based on the product sales data, construction cost data, production cost data, and transportation cost data.

[0013] The store location and transportation plan is obtained based on the multi-stage store location and transportation model. The store location and transportation plan includes location strategy information and product transportation strategy information.

[0014] In some embodiments, obtaining the product sales data of the target store within the preset time range based on the unit product sales data and the sales quantity data of the target object includes:

[0015] The sales volume data is updated based on the store delivery data and the market demand data;

[0016] The product sales data is obtained based on the unit product sales data and the updated sales quantity data.

[0017] In some embodiments, updating the sales quantity data based on the store delivery data and the market demand data includes:

[0018] Compare the store delivery data with the market demand data;

[0019] If the store delivery data is less than or equal to the market demand data, then the sales quantity data is updated based on the store delivery data;

[0020] If the store delivery data is greater than the market demand data, then the sales quantity data is updated based on the market demand data.

[0021] In some embodiments, constructing a multi-stage store location and transportation model based on the product sales data, construction cost data, production cost data, and transportation cost data includes:

[0022] Inventory quantity data is obtained based on the store delivery data and the market demand data;

[0023] Inventory cost data is obtained based on the unit product inventory cost and the aforementioned inventory quantity data;

[0024] Based on the inventory quantity data of the previous time period and the store delivery data of the current time period, the available inventory data for the current time period is obtained.

[0025] The baseline demand fulfillment rate for the current time period is determined based on the available inventory data and the market demand data for the current time period.

[0026] Service level constraints are constructed based on the baseline demand satisfaction rate and the preset expected demand satisfaction rate.

[0027] The multi-stage store location and transportation model is constructed based on the product sales data, construction cost data, production cost data, transportation cost data, inventory cost data, and service level constraints.

[0028] In some embodiments, constructing the multi-stage store location transportation model based on the product sales data, construction cost data, production cost data, transportation cost data, inventory cost data, and service level constraints includes:

[0029] A multi-stage differential risk measurement model is constructed based on the aforementioned service level constraints;

[0030] A profit model is constructed based on the product sales data, construction cost data, production cost data, transportation cost data, and inventory cost data.

[0031] The multi-stage store location and transportation model is constructed based on the multi-stage differential risk measurement model and the profit model.

[0032] In some embodiments, constructing a multi-stage difference risk measurement model based on the service level constraints includes:

[0033] Obtain constraint data; the constraint data is used to characterize the degree to which the service level constraints are not met;

[0034] Based on the constraint data and the service level constraints, piecewise linear constraints are constructed to obtain risk measurement constraints;

[0035] The multi-stage differential risk measurement model is constructed based on the constraint data and the risk measurement constraints.

[0036] In some embodiments, obtaining the store location transportation plan based on the multi-stage store location transportation model includes:

[0037] The multi-stage store location and transportation model is transformed based on a pre-defined dual method to obtain a mixed integer programming model.

[0038] The mixed integer programming model is decomposed into a location selection sub-model and a transportation sub-model.

[0039] The location sub-model is solved using a preset solver to obtain the location strategy information for the target store.

[0040] The solution is used to solve the transportation sub-model to obtain the product transportation strategy information for the target store;

[0041] The store location and transportation plan is obtained based on the location strategy information and the product transportation strategy information.

[0042] To achieve the above objectives, a second aspect of this application provides a site selection transportation device, the device comprising:

[0043] The first data determination module is used to determine market demand data within a preset time range based on a preset market demand distribution; the preset time range includes multiple different time periods.

[0044] The second data determination module is used to determine the store delivery data for the current time period based on market demand data for multiple reference time periods; both the reference time periods and the current time period are within the preset time range, the reference time period is earlier than the current time period, and the store delivery data is used to characterize the delivery volume of the target store to the target object in the current time period;

[0045] The construction cost calculation module is used to obtain the construction cost data of the target store within the preset time range based on the site selection information, unit construction cost and number of stores of the target store;

[0046] The production cost calculation module is used to obtain the production cost data of the target store within the preset time range based on the production volume of the target store, the unit product production cost, and the number of stores.

[0047] The transportation cost calculation module is used to obtain the transportation cost data of the target store within the preset time range based on the unit product transportation cost data of the target store, the store delivery data, the number of stores, and the number of objects of the target object;

[0048] The third data determination module is used to determine sales quantity data based on the store delivery data;

[0049] The sales data calculation module is used to obtain the product sales data of the target store within the preset time range based on the unit product sales data and the sales quantity data of the target object.

[0050] The model building module is used to build a multi-stage store location and transportation model based on the product sales data, the construction cost data, the production cost data, and the transportation cost data.

[0051] The store location selection and transportation module is used to obtain a store location selection and transportation plan based on the multi-stage store location selection and transportation model. The store location selection and transportation plan includes location strategy information and product transportation strategy information.

[0052] To achieve the above objectives, a third aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect.

[0053] To achieve the above objectives, a fourth aspect of the present application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect.

[0054] The site selection and transportation method, device, electronic equipment, and computer-readable storage medium proposed in this application determine market demand data within a preset time range based on a preset market demand distribution. By using the market demand distribution to describe the uncertainty of the market demand data, this uncertainty can be quantitatively described, and market demand data can be used as an influencing factor affecting site selection and transportation, thereby improving the accuracy of site selection and transportation. Furthermore, store delivery data for the current time period is determined based on market demand data from multiple reference time periods. Since store delivery data is correlated with market demand data, obtaining store delivery data through market demand data from previous time periods leads to more accurate store delivery data. Furthermore, based on the target store's location information, unit construction cost, and number of stores, construction cost data for the target store within a preset time range is obtained. Based on the target store's production volume, unit product production cost, and number of stores, production cost data for the target store within a preset time range is obtained. Based on the target store's unit product transportation cost data, store delivery data, number of stores, and number of target objects, transportation cost data for the target store within a preset time range is obtained. Sales volume data is determined based on store delivery data. Based on the target object's unit product sales data and sales volume data, product sales data for the target store within a preset time range is obtained. By quantitatively representing the influencing factors in the location selection and transportation process through construction cost data, production cost data, transportation cost data, and product sales data, the accuracy of store location selection and store delivery volume can be quantitatively assessed based on these factors. Finally, a multi-stage store location and transportation model is constructed based on product sales data, construction cost data, production cost data, and transportation cost data. Store location and transportation solutions are obtained based on the multi-stage store location and transportation model. The multi-stage store location and transportation model can automatically obtain store location and transportation solutions in a scientific and objective way. Compared with manual methods, it reduces the influence of subjective human factors and improves the accuracy of store location selection and store delivery volume. Attached Figure Description

[0055] Figure 1 This is a flowchart of the location selection and transportation method provided in the embodiments of this application;

[0056] Figure 2 yes Figure 1 The flowchart of step S170 in the process;

[0057] Figure 3 yes Figure 2 The flowchart of step S210 in the process;

[0058] Figure 4 yes Figure 1 The flowchart of step S180 in the process;

[0059] Figure 5 yes Figure 4 The flowchart of step S460 in the middle;

[0060] Figure 6 yes Figure 5 The flowchart of step S510 in the text;

[0061] Figure 7 yes Figure 1 The flowchart of step S190 in the middle;

[0062] Figure 8 This is a schematic diagram of the structure of the site selection transportation device provided in the embodiments of this application;

[0063] Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0065] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0066] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0067] In related technologies, manual methods are used for store site selection and subsequent delivery services. However, the accuracy of site selection is affected by subjective human factors. Even after a suitable location is chosen, uncertainties in market demand data can lead to insufficient delivery volume, impacting the store's subsequent delivery services. Therefore, improving the accuracy of store site selection and delivery volume is a pressing issue that needs to be addressed.

[0068] Based on this, embodiments of this application provide a site selection and transportation method, a site selection and transportation device, an electronic device, and a computer-readable storage medium, aiming to improve the accuracy of store site selection and store delivery volume.

[0069] The location selection transportation method, location selection transportation device, electronic device, and computer-readable storage medium provided in the embodiments of this application are specifically described through the following embodiments. First, the location selection transportation method in the embodiments of this application is described.

[0070] The address selection and transportation method provided in this application relates to the field of data processing technology. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the address selection and transportation method, but is not limited to the above forms.

[0071] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0072] Figure 1 This is an optional flowchart of the location selection and transportation method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S110 to S190.

[0073] Step S110: Determine market demand data within a preset time range based on the preset market demand distribution; the preset time range includes multiple different time periods.

[0074] Step S120: Determine the store delivery data for the current time period based on market demand data for multiple reference time periods; both the reference time periods and the current time period are within a preset time range, with the reference time period being earlier than the current time period. The store delivery data is used to characterize the delivery volume of the target store to the target object in the current time period.

[0075] Step S130: Based on the location information of the target store, the unit construction cost and the number of stores, obtain the construction cost data of the target store within a preset time range;

[0076] Step S140: Based on the production volume of the target store, the unit product production cost, and the number of stores, obtain the production cost data of the target store within a preset time range;

[0077] Step S150: Based on the unit product transportation cost data of the target store, the store delivery data, the number of stores, and the number of objects of the target object, obtain the transportation cost data of the target store within a preset time range.

[0078] Step S160: Determine sales quantity data based on store delivery data;

[0079] Step S170: Based on the unit product sales data and sales quantity data of the target object, obtain the product sales data of the target store within a preset time range;

[0080] Step S180: Construct a multi-stage store location and transportation model based on product sales data, construction cost data, production cost data, and transportation cost data.

[0081] Step S190: Obtain a store location and transportation plan based on the multi-stage store location and transportation model. The store location and transportation plan includes location strategy information and product transportation strategy information.

[0082] Steps S110 to S190 of this application embodiment use market demand distribution to describe the uncertainty of market demand data, which can quantitatively describe this uncertainty and use market demand data as an influencing factor affecting site selection and transportation, thereby improving the accuracy of site selection and transportation. Furthermore, store delivery data for the current time period is determined based on market demand data from multiple reference time periods. Since store delivery data is related to market demand data, obtaining store delivery data through market demand data from previous time periods yields more accurate store delivery data. Even further, influencing factors in the site selection and transportation process are quantitatively represented using construction cost data, production cost data, transportation cost data, and product sales data, enabling quantitative assessment of the accuracy of store site selection and store delivery volume based on these factors. Finally, a multi-stage store site selection and transportation model is constructed based on product sales data, construction cost data, production cost data, and transportation cost data. A store site selection and transportation plan is obtained based on this model. The multi-stage store site selection and transportation model can automatically obtain a store site selection and transportation plan in a scientific and objective manner, reducing the influence of subjective human factors compared to manual methods and improving the accuracy of store site selection and store delivery volume.

[0083] In step S110 of some embodiments, the market demand for each time period in the site selection and transportation problem is an uncertain parameter. To characterize market demand, this application embodiment sets an upper bound, a lower bound, and a mean of market demand based on historical market demand data. Descriptive statistics such as the mean and upper / lower bounds are used to construct an uncertain set of market demand. This uncertain set, containing the upper bound, lower bound, and mean, is used as a market demand distribution to characterize market demand. This market demand distribution contains all possible distributions that satisfy both the upper / lower bound and mean requirements, including any possible distribution such as the true distribution and the normal distribution. Through this market demand distribution, the final store site selection and transportation solution is robust to all possible distributions that satisfy the mean and upper / lower bounds.

[0084] The definition of market demand distribution is shown in formula (1).

[0085]

[0086] Among them, market demand Let be an uncertain parameter, and let its description space be (R, B(R)), where R is any real number and B(R) is the probability that the market demand is that real number. Let be a sample element in this description space, representing the market demand for target object j in time period t. This description space has a real interval P, which is used to assign a probability to each element in B(R). P belongs to the distribution family F, which is a set of multiple probability distributions. ζ is the lower bound. The upper limit value represents the market demand. Greater than or equal to the lower bound or less than or equal to the upper bound. E P (.) represents the expected value of probability distribution P, where U is the mean. The market demand for target object j within a preset time frame. And probability distribution u is the expected mean of market demand for all target objects within a preset time range, σ is the standard deviation of market demand for all target objects within a preset time range, and δ is the expected threshold.

[0087] Based on the market demand distribution F, determine the market demand data for each target object j within multiple time periods t within a preset time range.

[0088] In step S120 of some embodiments, an affine decision rule is introduced to predict store delivery data. This decision rule, also known as a wait-and-see decision rule, allows for decisions to be made only after uncertainties from the previous period have materialized. In other words, the store delivery data for the current time period is an expression of uncertain parameters (market demand data) that have already materialized before the current time period. By using the affine decision rule, it is not necessary to make decisions about store delivery data for each time period within the entire timeframe at the initial stage of site selection and transportation. Instead, delivery volume decisions are made at the beginning of each time period based on market demand data from a reference time period, thus obtaining accurate store delivery data.

[0089] Specifically, based on the preset first decision variable, the preset second decision variable, and market demand data from multiple reference time periods (i.e., the previous t-1 time period), the store delivery data for the current time period is determined. This store delivery data is the delivery volume from target store i to target object j in time period t, where the store delivery data for time period t is a linear expression of the market demand data from the previous t-1 time period. The specific calculation method for the store delivery data is shown in formula (2).

[0090]

[0091] in, This refers to the store delivery data from target store i to target object j within the time period t. As the first decision variable, This is the second decision variable and also the optimization result that the multi-stage store location and transportation model needs to output. T is the number of time periods within the preset time range. Since the store delivery data for the current time period cannot be used to reference market demand data for future time periods, when t'≥t, It must be 0.

[0092] In step S130 of some embodiments, the site selection information indicates whether a certain location is selected to build the target store, including two cases: selection and non-selection. If the site selection information is 1, it means that the target store is selected to build at that location, and the cost of building the target store at that location needs to be paid. If the site selection information is 0, it means that the target store is not selected to build at that location, and the cost of building the target store at that location does not need to be paid. Based on the site selection information I of the target store, the unit construction cost F, and the number of stores M, the construction cost data J of the target store within a preset time range is obtained. The calculation method of the construction cost data is shown in formula (3).

[0093]

[0094] Among them, F i F represents the unit construction cost of target store i. i This refers to the location information for target store i.

[0095] In step S140 of some embodiments, the production volume of target store i during time period t is determined. Unit product production cost c i The production cost data of target store i in time period t is obtained. The production cost data of each target store in each time period within the preset time range are added together to obtain the production cost data p of the target store within the preset time range. The calculation method of production cost data p is shown in formula (4).

[0096]

[0097] Where p represents production cost data, M represents the number of stores, T represents the number of time periods within the preset time range, and Z represents the production capacity of the target store, indicating the maximum production volume of the target store. The production volume of the target store in time period t does not exceed its production capacity.

[0098] In step S150 of some embodiments, the unit product transportation cost data d from target store i to target object j is used. ij And the store delivery data Y from target store i to target object j in time period t. ij tThe transportation cost from target store i to target object j within time period t is obtained. The transportation costs from each target store to each target object within each time period within a preset time range are added together to obtain the transportation cost data. The delivery data from all target stores to the same target object within a certain time period does not exceed the market demand data of the target object within that time period. The delivery data from the same target store to all target objects within a certain time period does not exceed the production volume of the target store within that time period. Furthermore, the delivery data from any target store to any target object within any time period is a non-negative value. The calculation method for transportation cost data is shown in formula (5).

[0099]

[0100] Where N is the number of target objects.

[0101] In step S160 of some embodiments, sales quantity data is used to represent the sales quantity of the target object's products within a preset time range.

[0102] Please see Figure 2 In some embodiments, step S170 may include, but is not limited to, steps S210 to S220:

[0103] Step S210: Update sales volume data based on store delivery data and market demand data;

[0104] Step S220: Obtain product sales data based on unit product sales data and updated sales quantity data.

[0105] In step S210 of some embodiments, the store delivery data Y is... ij As sales volume data, based on the unit product sales data η and sales volume data of the target object, the product sales data of the target store within a preset time range is obtained, where the unit product sales data is the sales price of the product, and the product sales data is the total sales price of the product. The calculation method of product sales data S is shown in formula (6).

[0106]

[0107] In real-world scenarios, the actual sales volume data is the minimum of the market demand data and the store delivery data. To make the sales volume data closer to the actual value, the sales volume data is updated based on the store delivery data and the market demand data.

[0108] In step S220 of some embodiments, if the updated sales quantity data is represented as D jThat is, the sales quantity of target object j within a preset time range. The product sales data is obtained based on the unit product sales data, the updated sales quantity data, and the quantity of target objects. The calculation method of product sales data S is shown in formula (7).

[0109]

[0110] By using steps S210 to S220, the sales quantity data can be made closer to the actual sales quantity data, thereby improving the accuracy of product sales data.

[0111] Please see Figure 3 In some embodiments, step S210 may include, but is not limited to, steps S310 to S330:

[0112] Step S310: Compare store delivery data with market demand data;

[0113] Step S320: If the store delivery data is less than or equal to the market demand data, then update the sales quantity data based on the store delivery data.

[0114] Step S330: If the store delivery data is greater than the market demand data, then update the sales quantity data according to the market demand data.

[0115] In step S310 of some embodiments, the store delivery data of the target object within a preset time range is compared. and market demand data

[0116] In step S320 of some embodiments, if store delivery data Less than or equal to market demand data Then store delivery data Sales volume data D of the target object within a preset time range j .

[0117] In step S330 of some embodiments, if store delivery data Greater than market demand data Then market demand data Sales volume data D of the target object within a preset time range j .

[0118] Understandably, sales volume data D j For store delivery data and market demand data The minimum value, i.e.

[0119] Through the above steps S310 to S330, the sales quantity data can be made closer to the actual site selection and transportation scenario, thereby improving the accuracy of the sales quantity data.

[0120] Please see Figure 4 In some embodiments, step S180 may include, but is not limited to, steps S410 to S460:

[0121] Step S410: Obtain inventory quantity data based on store delivery data and market demand data;

[0122] Step S420: Obtain inventory cost data based on unit product inventory cost and inventory quantity data;

[0123] Step S430: Based on the inventory quantity data of the previous time period and the store delivery data of the current time period, obtain the available inventory data for the current time period.

[0124] Step S440: Determine the baseline demand fulfillment rate for the current time period based on available inventory data and market demand data for the current time period;

[0125] Step S450: Construct service level constraints based on the baseline demand satisfaction rate and the preset expected demand satisfaction rate;

[0126] Step S460: Construct a multi-stage store location and transportation model based on product sales data, construction cost data, production cost data, transportation cost data, inventory cost data, and service level constraints.

[0127] In step S410 of some embodiments, the market demand data in a real scenario is uncertain. Besides the case where the market demand data equals the store delivery data, there are also two other cases: the market demand data is less than the store delivery data and the market demand data is greater than the store delivery data. When the market demand data is less than the store delivery data, some products will not be sold and will remain in inventory. When the market demand data is greater than the store delivery data, the demand of some target objects will not be met, and these target objects will have repurchase behavior. Considering the product inventory and the repurchase behavior of target objects, this application embodiment adds inventory constraints to make the multi-stage store location and transportation model more in line with the real scenario. It can be understood that the inventory quantity data of target object j in time period t is equal to the inventory quantity data of target object in time period t-1 plus the store delivery data of all target stores from time period t to target object j, and then minus the market demand data of target object j in time period t, as shown in formula (8).

[0128]

[0129] according to Formula (8) is iteratively calculated to obtain the inventory quantity data of the target object in the current time period based on the delivery data of all target stores from the initial time period to the current time period to the same target object, and the market demand data of the target object within the time range. The calculation method of the inventory quantity data is shown in Formula (9).

[0130]

[0131] Since the inventory quantity data is non-negative, the inventory quantity data... Update the inventory data to obtain the updated inventory quantity data. Right now

[0132] In step S420 of some embodiments, the unit product inventory cost C of the target object j is determined. j And the inventory quantity data of target object j in time period t Obtain the inventory cost data of target object j in time period t. Based on the inventory cost data of each target object in each time period, the inventory cost data within the preset time range is obtained as follows:

[0133] In step S430 of some embodiments, the inventory quantity data of target object j in the previous time period t-1 is used as a reference. Delivery data from all target stores to target object j within the current time period t. The available inventory data of target object j in the current time period t is obtained as follows

[0134] In step S440 of some embodiments, based on available inventory data Compared with the current time period

[0135] Market demand data The percentage of the baseline demand satisfaction rate for the current time period is obtained. The baseline demand satisfaction rate is the actual demand satisfaction rate of target object j in time period t, representing the probability that the target object's demand can be satisfied.

[0136] In step S450 of some embodiments, based on the baseline demand satisfaction rate and the preset expected demand satisfaction rate Construct service level constraints as follows The expected demand satisfaction rate is the target demand satisfaction rate set by the user, and the service level constraint means that the actual demand satisfaction rate is not lower than the target demand satisfaction rate.

[0137] Will Substituting the service level constraints, the service level constraints are transformed into:

[0138] In step S460 of some embodiments, a multi-stage differential risk measurement model is constructed based on service level constraints, a profit model is constructed based on product sales data, construction cost data, production cost data, transportation cost data, and inventory cost data, and a multi-stage store location and transportation model is constructed based on the multi-stage differential risk measurement model and the profit model.

[0139] Through the above steps S410 to S460, an objective function oriented towards the target demand satisfaction rate can be constructed, so that the actual demand satisfaction rate is within the first range, thereby constructing a multi-stage store location and transportation model that conforms to the real scenario, and obtaining accurate location strategy information and product transportation strategy information.

[0140] Please see Figure 5 In some embodiments, step S460 may include, but is not limited to, steps S510 to S530:

[0141] Step S510: Construct a multi-stage difference risk measurement model based on service level constraints;

[0142] Step S520: Construct a profit model based on product sales data, construction cost data, production cost data, transportation cost data, and inventory cost data;

[0143] Step S530: Construct a multi-stage store location and transportation model based on the multi-stage differential risk measurement model and profit model.

[0144] In step S510 of some embodiments, maximizing only the probability that the actual demand satisfaction rate is greater than or equal to the target demand satisfaction rate may result in low profits for the target store because it requires significant costs to satisfy all demands. When only the target store's profit is maximized, the actual demand satisfaction rate will be very low. If both the actual demand satisfaction rate and the target demand satisfaction rate are to be greater than or equal to the target demand satisfaction rate, and high profits are also required, the multi-stage store location and transportation model will become unsolvable, failing to provide an accurate store location and transportation solution. To achieve a balance between profit and the actual demand satisfaction rate, this application introduces a multi-period shortfall risk criterion (MSR) model. The MSR model allows the actual demand satisfaction rate to be slightly lower than the target demand satisfaction rate, while maximizing the degree to which service level constraints are met when market demand data is uncertain. This allows for a better balance between profit and service level, resulting in an accurate store location and transportation solution.

[0145] In step S520 of some embodiments, product sales data is... Subtract construction cost data Production cost data Transportation cost data and inventory cost data Obtain the benchmark profit of the target store within a preset time range, and construct a profit model based on the benchmark profit and the preset target profit. The method for constructing the profit model is shown in formula (10).

[0146]

[0147] In this equation, the left side represents the baseline profit, which is the actual profit of the target store, and R represents the target profit set by the user, which can be set according to actual needs.

[0148] In step S530 of some embodiments, the multi-stage differential risk measurement model and the profit model are used as a multi-stage store location transportation model.

[0149] Steps S510 to S530 above, under the MSR metric, can balance profit and service level, and provide an accurate store location and transportation solution.

[0150] Please see Figure 6 In some embodiments, step S510 may include, but is not limited to, steps S610 to S630:

[0151] Step S610: Obtain constraint data; constraint data is used to characterize the degree to which service level constraints are not met.

[0152] Step S620: Construct piecewise linear constraints based on constraint data and service level constraints to obtain risk measurement constraints;

[0153] Step S630: Construct a multi-stage difference risk measurement model based on the constraint data and risk measurement constraints.

[0154] In step S610 of some embodiments, the original MSR measurement model is as shown in formula (11).

[0155]

[0156] Where inf denotes minimization, α t The constraint data represents the degree to which the service level constraint is not met, i.e., the probability of violating the service level constraint. A constraint data value greater than zero indicates that the MSR measurement model allows the service level constraint to not be met. μ is the risk utility function for the service level constraint not being met due to market demand uncertainty; it is a convex increasing function.

[0157] In step S620 of some embodiments, since the second constraint in the MSR measurement model, namely the composite function, is non-convex, the multi-stage differential risk measurement model cannot be solved efficiently. In order to improve the efficiency of obtaining the store location transportation plan, the embodiments of this application adopt a piecewise linear structure. By approximating the convex function μ, a new MSR measure model is obtained as shown in formula (12).

[0158]

[0159] in, Uncertain parameters The expression for (market demand data) and the target rule r, where the difference between the actual demand satisfaction rate and the target demand satisfaction rate is greater than zero, i.e., the service level constraint condition is met.

[0160] To minimize the risk of violating the target rule, i.e., to maximize the degree to which the target rule is achieved, constraint data α is established through a piecewise linear structure. t Service level constraints The constraints between them yield the risk measurement constraints as follows:

[0161] In step S630 of some embodiments, a multi-stage differential risk measurement model is constructed based on constraint data and risk measurement constraints as shown in formula (13).

[0162]

[0163] Steps S610 to S630 above, by adopting a linear MSR measurement model, can improve the efficiency of the model in obtaining store location and transportation solutions.

[0164] Please see Figure 7 In some embodiments, step S190 may include, but is not limited to, steps S710 to S750:

[0165] Step S710: Based on the preset dual method, the multi-stage store location transportation model is transformed to obtain a mixed integer programming model.

[0166] Step S720: Decompose the mixed integer programming model to obtain a site selection sub-model and a transportation sub-model;

[0167] Step S730: Solve the site selection sub-model according to the preset solver to obtain the site selection strategy information of the target store;

[0168] Step S740: Solve the transportation sub-model using the solver to obtain the product transportation strategy information for the target store;

[0169] Step S750: Obtain the store location and transportation plan based on the location strategy information and product transportation strategy information.

[0170] In step S710 of some embodiments, a multi-stage store location transportation model is obtained through a profit model and a multi-stage differential risk measurement model, as shown in formula (14).

[0171]

[0172] First of all and The expression is substituted into other constraints, and then the uncertain parameters in the multi-stage store location transportation model are removed by writing duality. The constraints containing uncertain parameters are transformed into linear constraints, resulting in a mixed integer programming model, which transforms the complex model into a mixed integer programming model with a better structure.

[0173] In step S720 of some embodiments, based on the characteristics of the mixed integer programming model, the location and transportation problem is decomposed into a location subproblem and a transportation planning subproblem using the Benders Decomposition algorithm. The location subproblem is an integer programming model, and the transportation subproblem is a linear programming model.

[0174] The location subproblem is represented as MP, and the transportation subproblem as DSP. Specifically, the initial solution for MP is given. Let the optimal solution be the initial feasible solution: Find the objective function value LB of MP, substitute the optimal solution of MP into DSP as a parameter, find the optimal solution and obtain the objective function value UB. If DSP has infinite solutions, it means that the original problem of DSP has no solution. At this time, add feasible cuts to the constraints of MP, as shown in formula (15).

[0175]

[0176] If the DSP has a solution, find the optimal solution and the objective function value UB. * If UB * -LB=0 or UB * If -LB < ε, the current solution is the optimal solution, stop the loop; if UB < ε, the current solution is the optimal solution, stop the loop; * -LB>0 or UB * -LB>ε, at this time, add the constraint of the optimal cut to MP, as shown in formula (16).

[0177]

[0178] Solve for MP with the added constraints. If MP has no solution, stop the loop. If MP has a solution, obtain LB, and continue to substitute the optimal solution of MP as a parameter into DSP until the loop stopping condition is met, then return the optimal solution I of MP.* By taking the dual values ​​of the constraints corresponding to the decision variables of the original problem in the DSP, we obtain the location sub-model and the transportation sub-model.

[0179] In step S730 of some embodiments, the location transportation problem is a problem that combines long-term and short-term decision-making. A built-in solver, such as Gurobi in Python, is called to solve the location sub-model in order to make long-term location decisions and obtain location strategy information.

[0180] In step S740 of some embodiments, a built-in solver, such as Gurobi in Python, is invoked to solve the transportation sub-model in order to make short-term delivery decisions and obtain product transportation strategy information for the target store.

[0181] In step S750 of some embodiments, the site selection strategy information and product transportation strategy information are used to obtain a store site selection and transportation plan.

[0182] By using the steps S710 to S750 described above, the accuracy and efficiency of obtaining site selection strategy information and product transportation strategy information can be improved.

[0183] This application combines a solver with large-scale numerical experiments to obtain a robust location-based transportation scheme. The following compares this scheme with other benchmark schemes. Specifically, RP is a robust model aiming to maximize profit; RPF is a robust model aiming to maximize profit with added service level constraints; RF is a robust model aiming to maximize the degree of achieving the target demand satisfaction rate; and RFD is a robust model aiming to maximize the degree of achieving the target demand satisfaction rate with added radial decision rules.

[0184] Table 1 Performance Comparison of Solutions

[0185]

[0186]

[0187] Where P is the probability that the actual demand satisfaction rate is less than the target demand satisfaction rate (the probability of violating the target rule), i.e., P{target demand satisfaction rate - actual demand satisfaction rate > 0}; P1 is the profit under the fixed demand model; P2 is the profit under the seasonal demand model; and E is the expected value of the gap between the target demand satisfaction rate and the actual demand satisfaction rate, i.e., E(v) = E P ((Target demand satisfaction rate - Actual demand satisfaction rate) + ), where + indicates taking the absolute value; STD is the standard deviation of the difference between the target demand satisfaction rate and the actual demand satisfaction rate, i.e., STD(v) = STD( ...). + );V 0.95This represents the Value at Risk (VaR) with a 95% confidence level; V 0.99 This represents the value at risk with a confidence level of 99%.

[0188] The RP model exhibits an extremely high violation rate of the target rule, failing to balance profit and store service levels. RPF, by introducing service level constraints on top of RP, successfully reduces the violation rate to zero, but profits decrease dramatically, also failing to achieve a balance between profit and store service levels. Compared to the extreme results exhibited by these two profit-oriented models, the demand satisfaction rate-oriented model designed in this solution effectively achieves a balance between profit and demand satisfaction rate. As shown in Table 1, both RF and RFD can achieve high profits while keeping the target violation rate at a low level. RFD, in particular, achieves a good balance of high profit and low violation rate regardless of whether demand is fixed or fluctuates seasonally. Through comparison of the four models, the demand satisfaction rate-oriented model incorporating decision rules performs best, balancing profit and service levels. If further requirements regarding inventory levels are needed, it is better not to introduce decision rules, but the performance of profit and demand satisfaction rate will be slightly reduced.

[0189] The location-based transportation method in this application effectively balances the profit of enterprise stores with the customer demand satisfaction rate, taking into account both store efficiency and service level. Regardless of whether the demand is fixed or fluctuates with the seasons, the target demand satisfaction rate violation rate of this solution is very low. If it is desired to keep inventory at a low level, the model that does not consider the radial decision rule has better performance. This solution transforms the complex model containing uncertain parameters into an equivalent model that can be solved efficiently, enabling the model to solve large-scale location-based transportation problems and improving the efficiency of obtaining location-based transportation solutions.

[0190] Please see Figure 8 This application also provides a site selection transportation device that can implement the above-described site selection transportation method. The device includes:

[0191] The first data determination module 810 is used to determine market demand data within a preset time range based on a preset market demand distribution; the preset time range includes multiple different time periods.

[0192] The second data determination module 820 is used to determine the store delivery data for the current time period based on market demand data for multiple reference time periods. Both the reference time periods and the current time period are within a preset time range, with the reference time period being earlier than the current time period. The store delivery data is used to characterize the delivery volume of the target store to the target object in the current time period.

[0193] The construction cost calculation module 830 is used to obtain the construction cost data of the target store within a preset time range based on the target store's location information, unit construction cost, and number of stores.

[0194] The production cost calculation module 840 is used to obtain the production cost data of the target store within a preset time range based on the production volume of the target store, the unit product production cost, and the number of stores.

[0195] The transportation cost calculation module 850 is used to obtain the transportation cost data of the target store within a preset time range based on the unit product transportation cost data of the target store, the store delivery data, the number of stores and the number of objects of the target object;

[0196] The third data determination module 860 is used to determine sales quantity data based on store delivery data;

[0197] The sales data calculation module 870 is used to obtain the product sales data of the target store within a preset time range based on the unit product sales data and sales quantity data of the target object.

[0198] Model building module 880 is used to build a multi-stage store location and transportation model based on product sales data, construction cost data, production cost data, and transportation cost data.

[0199] The store location selection and transportation module 890 is used to obtain a store location selection and transportation plan based on a multi-stage store location selection and transportation model. The store location selection and transportation plan includes location strategy information and product transportation strategy information.

[0200] The specific implementation method of this site selection transportation device is basically the same as the specific implementation method of the above-mentioned site selection transportation method, and will not be described again here.

[0201] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described location-based transportation method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0202] Please see Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0203] The processor 910 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0204] The memory 920 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 920 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 920 and is called and executed by the processor 910 using the address selection and transport method of the embodiments of this application.

[0205] The input / output interface 930 is used to implement information input and output;

[0206] The communication interface 940 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0207] Bus 950 transmits information between various components of the device (e.g., processor 910, memory 920, input / output interface 930, and communication interface 940);

[0208] The processor 910, memory 920, input / output interface 930 and communication interface 940 are connected to each other within the device via bus 950.

[0209] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described addressing and transportation method.

[0210] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0211] The site selection and transportation method, device, electronic equipment, and computer-readable storage medium provided in this application improve the accuracy of site selection and transportation by using market demand distribution to describe the uncertainty of market demand data and quantifying this uncertainty. Furthermore, market demand data is used as an influencing factor affecting site selection and transportation. Further, store delivery data for the current time period is determined based on market demand data from multiple reference time periods. Since store delivery data is correlated with market demand data, obtaining store delivery data from previous time periods yields more accurate data. Even further, influencing factors in the site selection and transportation process are quantitatively represented using construction cost data, production cost data, transportation cost data, and product sales data, enabling a quantitative assessment of the accuracy of store site selection and delivery volume. Finally, a multi-stage store site selection and transportation model is constructed based on product sales data, construction cost data, production cost data, and transportation cost data. A store site selection and transportation plan is obtained based on this model. This multi-stage model automatically and scientifically generates a store site selection and transportation plan, reducing the influence of subjective human factors compared to manual methods and improving the accuracy of store site selection and delivery volume.

[0212] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0213] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0214] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0215] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0216] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0217] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0218] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0219] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0220] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0221] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0222] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A site selection and transportation method, characterized in that, The method includes: Market demand data within a preset time range is determined based on a preset market demand distribution; the market demand data refers to the market demand quantity, and the preset time range includes multiple different time periods. The market demand distribution is represented as follows: ， Where F represents the market demand distribution, and F is a set containing multiple probability distributions; This represents market demand data, which is an uncertain parameter; P represents the probability distribution, belonging to the distribution family F. This is the lower bound value. The upper limit value represents market demand data. Greater than or equal to the lower bound or less than or equal to the upper bound; U represents the expected value of probability distribution P, and U is the mean; market demand data for target object j within a preset time range. And probability distribution ;u represents the expected mean value obtained based on market demand data for all target objects within a preset time range. The standard deviation is calculated based on market demand data for all target entities within a preset timeframe. The expected threshold; The store delivery data for the current time period is determined based on market demand data from multiple reference time periods; both the reference time periods and the current time period are within the preset time range, the reference time period is earlier than the current time period, and the store delivery data is used to characterize the delivery volume of the target store to the target object in the current time period; The formula for calculating the store delivery data is as follows: ， in, For the store delivery data from target store i to target object j in the time period t, As the first decision variable, As the second decision variable, when hour, =0; T is the number of time periods within the preset time range; This represents the market demand data for target object j in time period t; t represents the reference time period; t represents the current time period. Based on the location information, unit construction cost, and number of stores of the target store, the construction cost data of the target store within the preset time range is obtained; Based on the production volume of the target store, the unit product production cost, and the number of stores, the production cost data of the target store within the preset time range is obtained; Based on the unit product transportation cost data of the target store, the store delivery data, the number of stores, and the number of objects of the target object, the transportation cost data of the target store within the preset time range is obtained; Sales quantity data is determined based on the store delivery data; the sales quantity data is used to represent the number of products sold by the target object within the preset time range. The sales volume data is represented as follows: ， in, This represents sales volume data; Indicates the number of target stores; Indicates the number of time periods within a preset time range; Based on the unit product sales data and the sales quantity data of the target object, the product sales data of the target store within the preset time range are obtained; A multi-stage store location and transportation model is constructed based on the product sales data, construction cost data, production cost data, and transportation cost data. A store location and transportation plan is obtained based on the multi-stage store location and transportation model. The store location and transportation plan includes location strategy information and product transportation strategy information. The construction of a multi-stage store location and transportation model based on the product sales data, construction cost data, production cost data, and transportation cost data includes: Inventory quantity data is obtained based on the store delivery data and the market demand data; inventory cost data is obtained based on the unit product inventory cost and the inventory quantity data; available inventory data for the current time period is obtained based on the inventory quantity data of the previous time period and the store delivery data for the current time period; the baseline demand satisfaction rate for the current time period is determined based on the available inventory data and the market demand data for the current time period; service level constraints are constructed based on the baseline demand satisfaction rate and the preset expected demand satisfaction rate; and the multi-stage store location and transportation model is constructed based on the product sales data, the construction cost data, the production cost data, the transportation cost data, the inventory cost data, and the service level constraints.

2. The site selection and transportation method according to claim 1, characterized in that, The step of obtaining the product sales data of the target store within the preset time range based on the unit product sales data and the sales quantity data of the target object includes: The sales volume data is updated based on the store delivery data and the market demand data; The product sales data is obtained based on the unit product sales data and the updated sales quantity data.

3. The site selection and transportation method according to claim 2, characterized in that, The step of updating the sales quantity data based on the store delivery data and the market demand data includes: Compare the store delivery data with the market demand data; If the store delivery data is less than or equal to the market demand data, then the sales quantity data is updated based on the store delivery data; If the store delivery data is greater than the market demand data, then the sales quantity data is updated based on the market demand data.

4. The site selection and transportation method according to claim 1, characterized in that, The construction of the multi-stage store location and transportation model based on the product sales data, construction cost data, production cost data, transportation cost data, inventory cost data, and service level constraints includes: A multi-stage differential risk measurement model is constructed based on the aforementioned service level constraints; A profit model is constructed based on the product sales data, construction cost data, production cost data, transportation cost data, and inventory cost data. The multi-stage store location and transportation model is constructed based on the multi-stage differential risk measurement model and the profit model.

5. The site selection and transportation method according to claim 4, characterized in that, The construction of a multi-stage difference risk measurement model based on the service level constraints includes: Obtain constraint data; the constraint data is used to characterize the degree to which the service level constraints are not met; Based on the constraint data and the service level constraints, piecewise linear constraints are constructed to obtain risk measurement constraints; The multi-stage differential risk measurement model is constructed based on the constraint data and the risk measurement constraints.

6. The site selection and transportation method according to any one of claims 1 to 5, characterized in that, The process of obtaining a store location and transportation plan based on the multi-stage store location and transportation model includes: The multi-stage store location and transportation model is transformed based on a pre-defined dual method to obtain a mixed integer programming model. The mixed integer programming model is decomposed into a location selection sub-model and a transportation sub-model. The location sub-model is solved using a preset solver to obtain the location strategy information for the target store. The solution is used to solve the transportation sub-model to obtain the product transportation strategy information for the target store; The store location and transportation plan is obtained based on the location strategy information and the product transportation strategy information.

7. A site selection and transportation device, characterized in that, The device includes: The first data determination module is used to determine market demand data within a preset time range based on a preset market demand distribution; the market demand data is the market demand quantity, and the preset time range includes multiple different time periods. The market demand distribution is represented as follows: ， Where F represents the market demand distribution, and F is a set containing multiple probability distributions; This represents market demand data, which is an uncertain parameter; P represents the probability distribution, belonging to the distribution family F. This is the lower bound value. The upper limit value represents market demand data. Greater than or equal to the lower bound or less than or equal to the upper bound; U represents the expected value of probability distribution P, and U is the mean; market demand data for target object j within a preset time range. And probability distribution ;u represents the expected mean value obtained based on market demand data for all target objects within a preset time range. The standard deviation is calculated based on market demand data for all target entities within a preset timeframe. The expected threshold; The second data determination module is used to determine the store delivery data for the current time period based on market demand data for multiple reference time periods; both the reference time periods and the current time period are within the preset time range, the reference time period is earlier than the current time period, and the store delivery data is used to characterize the delivery volume of the target store to the target object in the current time period; The formula for calculating the store delivery data is as follows: ， in, For the store delivery data from target store i to target object j in the time period t, As the first decision variable, As the second decision variable, when hour, =0; T is the number of time periods within the preset time range; This represents the market demand data for target object j in time period t; t represents the reference time period; t represents the current time period. The construction cost calculation module is used to obtain the construction cost data of the target store within the preset time range based on the site selection information, unit construction cost and number of stores of the target store; The production cost calculation module is used to obtain the production cost data of the target store within the preset time range based on the production volume of the target store, the unit product production cost, and the number of stores. The transportation cost calculation module is used to obtain the transportation cost data of the target store within the preset time range based on the unit product transportation cost data of the target store, the store delivery data, the number of stores, and the number of objects of the target object; The third data determination module is used to determine sales quantity data based on the store delivery data; the sales quantity data is used to represent the product sales quantity of the target object within the preset time range. The sales volume data is represented as follows: ， in, This represents sales volume data; Indicates the number of target stores; Indicates the number of time periods within a preset time range; The sales data calculation module is used to obtain the product sales data of the target store within the preset time range based on the unit product sales data and the sales quantity data of the target object. The model building module is used to build a multi-stage store location and transportation model based on the product sales data, the construction cost data, the production cost data, and the transportation cost data. The store location selection and transportation module is used to obtain a store location selection and transportation plan based on the multi-stage store location selection and transportation model. The store location selection and transportation plan includes location strategy information and product transportation strategy information. The device is also used for: Inventory quantity data is obtained based on the store delivery data and the market demand data; inventory cost data is obtained based on the unit product inventory cost and the inventory quantity data; available inventory data for the current time period is obtained based on the inventory quantity data of the previous time period and the store delivery data for the current time period; the baseline demand satisfaction rate for the current time period is determined based on the available inventory data and the market demand data for the current time period; service level constraints are constructed based on the baseline demand satisfaction rate and the preset expected demand satisfaction rate; and the multi-stage store location and transportation model is constructed based on the product sales data, the construction cost data, the production cost data, the transportation cost data, the inventory cost data, and the service level constraints.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the location transportation method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the location transportation method according to any one of claims 1 to 6.

Images