A method, system, device and storage medium for warehouse goods allocation and cabinets

Abstract

The present invention relates to a method, system, device and storage medium for warehouse goods allocation and cabinet division, including the following steps: collecting the goods data stored in the warehouse, preprocessing the goods data and constructing it into a goods data set; constructing an inventory consumption prediction model, inputting the goods data set into the inventory consumption prediction model for training to obtain a trained inventory consumption prediction model, and predicting the inventory consumption of the warehouse goods through the trained inventory consumption prediction model; constructing a warehouse goods allocation priority model, calculating the goods allocation priority of each warehouse based on the predicted inventory consumption of the goods in each warehouse, and allocating goods to each warehouse according to the order of the goods allocation priority; constructing a warehouse cabinet loading model, when the goods are allocated to the corresponding warehouse, calculating the cabinet loading priority of the goods through the warehouse cabinet loading model, and storing the goods according to the cabinet loading priority.

Description

Technical Field

[0001] The present invention relates to a method, system, device and storage medium for warehouse goods allocation and cabinet division, belonging to the technical field of warehouse management. Background Art

[0002] With the rapid development of globalization and e-commerce, the scale of the cross-border e-commerce logistics industry has been continuously growing, and significant progress has been made in the construction of cross-border e-commerce overseas warehouses. These overseas warehouses not only improve the speed and efficiency of cross-border logistics, but also greatly reduce transportation costs and enhance the shopping experience of consumers. Among them, supply chain management has become increasingly important. In the supply chain, warehouse allocation is also a crucial link.

[0003] Reasonable inventory allocation enables the supply chain to process orders more efficiently, improve the inventory turnover rate of the warehouse and the competitiveness of the enterprise. In supply chain management, different enterprises may adopt different inventory allocation methods, which depend on factors such as the strategic goals of the enterprise, product characteristics, and market conditions. Therefore, inventory allocation should comprehensively consider various factors and be adjusted and optimized according to the actual situation of the enterprise. Summary of the Invention

[0004] In order to solve the problems existing in the above-mentioned prior art, the present invention proposes a method, system, device and storage medium for warehouse goods allocation and cabinet division.

[0005] The technical solution of the present invention is as follows:

[0006] On the one hand, the present invention provides a method for warehouse goods allocation and cabinet division, including the following steps:

[0007] Collect the goods data stored in the warehouse and preprocess the goods data to construct a goods data set;

[0008] Construct an inventory consumption prediction model, input the goods data set into the inventory consumption prediction model for training to obtain a trained inventory consumption prediction model, and predict the inventory consumption of the warehouse goods through the trained inventory consumption prediction model;

[0009] Construct a warehouse goods allocation priority model, calculate the goods allocation priority of each warehouse based on the predicted inventory consumption of the goods in each warehouse, and allocate goods to each warehouse according to the order of the goods allocation priority;

[0010] Construct a warehouse cabinet loading model. When the goods are allocated to the corresponding warehouse, calculate the cabinet loading priority of the goods through the warehouse cabinet loading model and store the goods according to the cabinet loading priority.

[0011] As a preferred embodiment of the present invention, the inventory consumption prediction model is constructed based on a long short-term memory model and an extreme gradient boosting model;

[0012] The goods dataset is respectively input into the long short-term memory model and the extreme gradient boosting model for training. The output results of the two models are weighted and summed to obtain the predicted value. After each training is completed, the loss is calculated through the following loss function Calculate the loss:

[0013] ;

[0014] Where: Represents the cost of insufficient inventory; Represents the cost of excessive inventory; Represents the predicted value; Represents the actual value; Represents the indicator function;

[0015] Then, the posterior distribution of the predicted value is modeled through a Bayesian network to obtain the uncertainty of the prediction result;

[0016] When the loss and the uncertainty of the prediction result reach the preset threshold, the trained inventory consumption prediction model is obtained, and the inventory consumption of the warehouse goods is predicted through the trained inventory consumption prediction model.

[0017] As a preferred embodiment of the present invention, the warehouse goods allocation priority model includes a market priority model, a warehouse priority model, and a transportation priority model;

[0018] Allocate goods to each warehouse according to the order of transportation priority, market priority, and warehouse priority.

[0019] As a preferred embodiment of the present invention, the market priority model is specifically shown as the following formula:

[0020] ;

[0021] Where: Represents the market priority of the warehouse; Represents the market demand for goods in the warehouse; Represents the seasonal adjustment factor; Represents the competition intensity of goods in the warehouse; Represents the current inventory level of the warehouse; Represents the future inventory growth rate of the warehouse; Represents the market risk index; , , , , Represents the weight coefficient of the market priority model.

[0022] As a preferred embodiment of the present invention, the warehouse priority model is specifically shown as the following formula:

[0023] ;

[0024] Wherein: represents the warehouse priority; represents the safety factor of the goods in the warehouse; represents the utilization rate of the warehouse; represents the transportation cost of the warehouse; represents the turnover rate of the warehouse; represents the risk factor of the warehouse; , , , , represent the weight coefficients of the warehouse priority model.

[0025] As a preferred embodiment of the present invention, the transportation priority model constructs an objective function to minimize the transportation cost and the warehousing cost , specifically as shown in the following formula:

[0026] ;

[0027] Wherein: represents the transportation cost from location to warehouse ; represents the quantity of goods transported from location to warehouse ; represents the quantity of goods in warehouse ; represents the warehousing cost per unit of goods in warehouse ;

[0028] At the same time, the following constraint conditions are set:

[0029] ;

[0030] ;

[0031] ;

[0032] Wherein: represents the demand quantity of goods in warehouse ; represents the supply quantity of location ; represents the maximum storage quantity of warehouse ; represents the usage status of the warehouse;

[0033] After solving the objective function using a linear programming or integer programming solver, the transportation priority of each warehouse is obtained according to the solution result.

[0034] As a preferred embodiment of the present invention, the warehouse stuffing model is specifically shown as the following formula:

[0035] ;

[0036] ;

[0037] Where: represents the stuffing priority of the current goods; represents the deviation of the weight - volume ratio of the current goods to the container; represents the weight of the current goods; represents the volume of the current goods; represents the maximum load - bearing weight of the container; represents the maximum volume of the container; represents the maximum weight among all goods; represents the maximum volume among all goods;

[0038] All goods are stuffed according to the calculated stuffing priority of the goods.

[0039] On the other hand, the present invention also provides a warehouse goods allocation and stuffing system, including a data acquisition module, an inventory consumption prediction module, a warehouse goods allocation module, and a goods stuffing module;

[0040] The data acquisition module is used to collect the goods data stored in the warehouse and pre - process the goods data to construct a goods data set;

[0041] The inventory consumption prediction module is used to construct an inventory consumption prediction model, input the goods data set into the inventory consumption prediction model for training, obtain the trained inventory consumption prediction model, and predict the inventory consumption of the warehouse goods through the trained inventory consumption prediction model;

[0042] The warehouse goods allocation module is used to construct a warehouse goods allocation priority model, calculate the goods allocation priority of each warehouse based on the predicted inventory consumption of the goods in each warehouse, and allocate goods to each warehouse according to the order of the goods allocation priority;

[0043] The goods stuffing module is used to construct a warehouse stuffing model. When the goods are allocated to the corresponding warehouse, calculate the stuffing priority of the goods through the warehouse stuffing model, and store the goods according to the stuffing priority.

[0044] On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the method described in any embodiment of the present invention is implemented.

[0045] On the other hand, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method described in any embodiment of the present invention is implemented.

[0046] The present invention has the following beneficial effects:

[0047] 1. The present invention uses the long short-term memory model and the extreme gradient boosting model to accurately predict inventory consumption, and models the posterior distribution of the predicted value through a Bayesian network to reduce uncertainty.

[0048] 2. The present invention constructs a market priority model, a warehouse priority model, and a transportation priority model to ensure balanced goods allocation in multiple dimensions such as market demand, transportation cost, and warehouse utilization rate, improving the overall response speed and decision-making efficiency of the supply chain.

[0049] 3. The present invention realizes the dual optimal allocation of the weight and volume of the container through the goods loading container priority model, reduces space waste and overloading risks, and improves the automation and intelligence level of the container loading process. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in 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. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0052] It should be understood that the step numbers used herein are only for convenience of description and do not limit the execution order of the steps.

[0053] It should be understood that the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0054] The terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0055] The term "and / or" refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0056] Example 1:

[0057] See Figure 1 , a method for allocating goods in a warehouse into cabinets, comprising the following steps:

[0058] Collect the goods data stored in the warehouse and preprocess the goods data and then construct it into a goods data set;

[0059] Construct an inventory consumption prediction model, input the goods data set into the inventory consumption prediction model for training, obtain the trained inventory consumption prediction model, and predict the inventory consumption of the goods in the warehouse through the trained inventory consumption prediction model;

[0060] Construct a warehouse goods allocation priority model, calculate the goods allocation priority of each warehouse based on the predicted inventory consumption of the goods in each warehouse, and allocate goods to each warehouse according to the order of the goods allocation priority;

[0061] Construct a warehouse cabinet loading model. When the goods are allocated to the corresponding warehouse, calculate the cabinet loading priority of the goods through the warehouse cabinet loading model and store the goods according to the cabinet loading priority.

[0062] As a preferred implementation manner of this implementation, the inventory consumption prediction model is constructed based on a long short-term memory model and an extreme gradient boosting model;

[0063] Input the goods data set into the long short-term memory model and the extreme gradient boosting model for training respectively, perform weighted summation on the output results of the two models to obtain a predicted value, and calculate the loss through the following loss function after each training is completed Calculate the loss:

[0064] ;

[0065] Where: represents the cost of insufficient inventory; represents the cost of excessive inventory; represents the predicted value; represents the actual value; represents the indicator function;

[0066] The cost of insufficient inventory consists of direct losses (such as the loss of sales opportunities due to out-of-stock, the profit loss or opportunity cost brought by unfulfilled sales orders) and indirect losses (such as the decline in customer satisfaction, the damage to brand reputation, the loss of subsequent customers, etc.);

[0067] The cost of excessive inventory consists of holding costs (such as warehousing costs, insurance costs, labor and equipment costs brought by extra inventory), capital occupation (excessive inventory occupies the enterprise's operating funds, causing opportunity costs and affecting cash flow), and possible depreciation or expiration (such as fresh food, medicine or time-sensitive goods, and excessive inventory expires or becomes unsalable, resulting in greater losses);

[0068] If it is estimated that: for each item less stocked, the profit loss is 20 yuan (including the effect conversion of subsequent customer loss, etc.), and for each item more stocked, the average expenditure is 5 yuan (converted from warehousing, capital occupation, etc.), then it can be initially set , ;

[0069] Then, through the Bayesian network, the posterior distribution of the predicted value is modeled to obtain the uncertainty of the prediction result;

[0070] When the losses and the uncertainty of the prediction result reach the preset threshold, a trained inventory consumption prediction model is obtained, and the inventory consumption of the warehouse goods is predicted through the trained inventory consumption prediction model.

[0071] As a preferred implementation of this embodiment, the warehouse goods allocation priority model includes a market priority model, a warehouse priority model, and a transportation priority model;

[0072] Goods are allocated to each warehouse according to the order of transportation priority, market priority, and warehouse priority, that is, transportation priority > market priority > warehouse priority;

[0073] In this embodiment, in order to ensure the uniformity of distribution, a minimum distribution principle is set to ensure the balanced distribution of materials among regions, so as to avoid local supply shortages or surpluses.

[0074] As a preferred implementation of this embodiment, the market priority model is specifically shown as the following formula:

[0075] ;

[0076] Where: represents the market priority of the warehouse; represents the market demand for goods in the warehouse; represents the seasonal adjustment factor; represents the competition intensity of goods in the warehouse; represents the current inventory level of the warehouse (available inventory / ideal inventory); Represents the future inventory growth rate of the warehouse; Represents the market risk indicators (such as economic fluctuations, policy impacts, etc.); 、 、 、 、 Represents the weight coefficient of the market priority model.

[0077] The market demand for the goods in the warehouse The calculation formula is:

[0078] ;

[0079] Where: Represents the historical sales data (sales volume within a unit time) of the th kind of goods in the warehouse; Represents the weight coefficient of the th kind of goods (based on the importance, profit margin, or market share of the goods. For example, goods with high profit or high turnover rate may have a higher weight); Represents the change in demand growth of the th kind of goods (based on market trends, seasonality, or new product promotion); Represents the types of goods in the warehouse;

[0080] ;

[0081] Where: Represents the market demand for the goods in the th quarter of the warehouse (for example, the sales volume of air conditioners is high in summer, and the sales volume of heaters is high in winter); Represents the benchmark market demand in the th quarter (using the average sales volume of the whole year or for multiple years as the benchmark demand);

[0082] The competition intensity of the goods in the warehouse The calculation formula is:

[0083] ;

[0084] Where: Represents the market price of the goods in the warehouse; Represents the average price of the same goods in the market; Represents the market share of the warehouse (the proportion of the total market demand); Represents the total demand of the target market; Represents the inventory level of the warehouse; Represents the maximum storage capacity of the warehouse; Indicates the degree of product differentiation in the warehouse (e.g., by examining product differences and the availability of substitutes); Indicates the degree of barriers for goods in the warehouse to enter the market (such as laws and regulations, technical thresholds, capital requirements, etc.); Indicates brand loyalty (the degree of preference of consumers for the warehouse brand or supplier);

[0085] ;

[0086] Among them: Indicates the inventory consumption at time ; Indicates the inventory consumption at time ; Indicates the number of time periods (e.g., the past 12 months).

[0087] As a preferred implementation manner of this embodiment, the warehouse priority model is specifically shown as the following formula:

[0088] ;

[0089] Among them: Indicates the warehouse priority; Indicates the goods safety factor of the warehouse; Indicates the utilization rate of the warehouse (the proportion of available space in the total space, the lower the value, the better); Indicates the transportation cost of the warehouse (which can be calculated through the transportation priority model); Indicates the turnover rate of the warehouse (reflecting the flow efficiency of goods in the warehouse, the higher the value, the better); Indicates the risk factor of the warehouse (such as natural disasters, theft risks, etc., the lower the value, the better); , , , , Indicates the weight coefficient of the warehouse priority model;

[0090] ;

[0091] Among them: Indicates the goods value, the economic value per unit of goods; Indicates the transportation risk level, the degree of risk related to the transportation of goods, which can usually be evaluated through historical data; Indicates the storage environment level, the environmental risk for storing goods, including factors such as humidity, temperature, pollution, etc.; Indicates the packaging quality level, specifically the packaging strength of the goods and its protection ability; Indicates the goods insurance coverage rate; Represents the special cargo risk factor, an additional risk factor for special cargo such as perishable goods and flammable goods, and the range can be set from 0 (no impact) to 10 (high impact);

[0092] ;

[0093] Among them: The cost of goods sold represents the total cost of the goods sold within a certain period of time (usually one year or a quarter); Average inventory = (beginning inventory + ending inventory) / 2;

[0094] As a preferred implementation mode of this embodiment, the transportation priority model constructs an objective function to minimize transportation costs and warehousing costs , specifically as shown in the following formula:

[0095] ;

[0096] Among them: Represents the transportation cost from location to warehouse ; Represents the quantity of goods transported from location to warehouse ; Represents the quantity of goods in warehouse ; Represents the warehousing cost per unit of goods in warehouse ;

[0097] At the same time, set the following constraint conditions:

[0098] ;

[0099] ;

[0100] ;

[0101] Among them: Represents the demand for goods in warehouse ; Represents the supply quantity from location ; Represents the maximum storage quantity in warehouse ; Represents the usage status of the warehouse;

[0102] After solving the objective function through a linear programming or integer programming solver, the transportation priority of each warehouse is obtained according to the solution result.

[0103] As a preferred implementation mode of this embodiment, the warehouse stuffing model is specifically as shown in the following formula:

[0104] ;

[0105] ;

[0106] Wherein: represents the container loading priority of the current goods; represents the deviation of the weight - volume ratio of the current goods to the container; represents the weight of the current goods; represents the volume of the current goods; represents the maximum load - bearing weight of the container; represents the maximum volume of the container; represents the maximum weight among all goods; represents the maximum volume among all goods;

[0107] Load all goods according to the calculated container loading priority of the goods. When all goods are loaded, it may be that the weight of the container reaches the threshold but there is remaining volume. In this embodiment, the simulated annealing algorithm is used to optimize both the container load - bearing and the container volume. Specifically:

[0108] Preset the weight range, volume range, and the number range of goods of the container. Through the simulated annealing algorithm, loop - calculate whether the container reaches the preset weight range, volume range, and the number range of goods;

[0109] For the container that does not reach the requirements, when the weight of the container exceeds the weight range, take out the heaviest goods, and then recalculate the placement position of the goods through the simulated annealing algorithm. Similarly, when the volume of the container exceeds the volume range, take out the goods with the largest volume, and then recalculate the placement position of the goods through the simulated annealing algorithm.

[0110] Embodiment 2:

[0111] A warehouse goods - allocation and container - loading system, including a data acquisition module, an inventory consumption prediction module, a warehouse goods - allocation module, and a goods container - loading module;

[0112] The data acquisition module is used to collect the goods data stored in the warehouse and pre - process the goods data to construct a goods data set;

[0113] The inventory consumption prediction module is used to construct an inventory consumption prediction model, input the goods data set into the inventory consumption prediction model for training, obtain a trained inventory consumption prediction model, and predict the inventory consumption of the warehouse goods through the trained inventory consumption prediction model;

[0114] The warehouse goods - allocation module is used to construct a warehouse goods - allocation priority model, calculate the goods - allocation priority of each warehouse based on the predicted inventory consumption of the goods in each warehouse, and allocate goods to each warehouse according to the order of the goods - allocation priority;

[0115] The goods container loading module is used to construct a warehouse container loading model. When goods are allocated to the corresponding warehouse, the container loading priority of the goods is calculated through the warehouse container loading model, and the goods are stored according to the container loading priority.

[0116] This system is used to implement the method in the first embodiment, which will not be elaborated here.

[0117] Embodiment 3:

[0118] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the method described in any embodiment of the present invention is implemented.

[0119] Embodiment 4:

[0120] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method described in any embodiment of the present invention is implemented.

[0121] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent the cases of A existing alone, A and B existing simultaneously, and B existing alone. Where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one of the following" and its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, and 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.

[0122] Those of ordinary skill in the art can realize that the units and algorithm steps described in the embodiments disclosed herein can be implemented by a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0123] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be elaborated here.

[0124] In several embodiments provided by the present application, if any function is implemented in the form of 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 the present application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs that can store program codes.

[0125] The above are only the embodiments of the present invention, and thus do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall equally be included in the patent protection scope of the present invention.

Claims

1. A method for warehouse distribution and cabinet distribution, characterized in that: The following steps are involved: Collect the cargo data stored in the warehouse and construct the cargo data set after preprocessing the cargo data; Construct an inventory consumption prediction model, input the cargo data set into the inventory consumption prediction model for training, obtain a trained inventory consumption prediction model, and use the trained inventory consumption prediction model to predict the inventory consumption of warehouse cargo; Build a warehouse distribution priority model, calculate the distribution priority of each warehouse based on the predicted inventory consumption of the goods in each warehouse, and distribute goods to each warehouse according to the distribution priority order; Build a warehouse loading model. When goods are delivered to the corresponding warehouse, the loading priority of the goods is calculated through the warehouse loading model, and the goods are stored according to the loading priority. The inventory consumption prediction model is constructed based on the long short-term memory model and the extreme gradient boosting model; The cargo data set is input into the long short-term memory model and the extreme gradient boosting model for training respectively. The output results of the two models are weighted summed to obtain the predicted value. After each training is completed, the following loss function is used Calculate the loss: ； in: Indicates the cost of insufficient inventory; represents the cost of excess inventory; represents the predicted value; Indicates actual value; represents the indicator function; Then, the posterior distribution of the predicted value is modeled through the Bayesian network to obtain the uncertainty of the prediction result; When the uncertainty of the loss and the prediction result reaches a preset threshold, a trained inventory consumption prediction model is obtained, and the inventory consumption of the warehouse goods is predicted by the trained inventory consumption prediction model; The warehouse distribution priority model includes a market priority model, a warehouse priority model and a transportation priority model; Allocate goods to each warehouse in the order of transportation priority, market priority, and warehouse priority; The market priority model is specifically shown as follows: ； in: Indicates the market priority of the warehouse; Represents the market demand for goods in the warehouse; represents the seasonal adjustment factor; Indicates the intensity of competition for goods in the warehouse; Indicates the current inventory level in the warehouse; Indicates the future inventory growth rate of the warehouse; It represents the market risk indicator; , , , , represents the weight coefficient of the market priority model; The warehouse priority model is specifically shown in the following formula: ； in: Indicates warehouse priority; Indicates the cargo safety factor of the warehouse; Indicates the utilization rate of the warehouse; represents the transportation cost of the warehouse; Indicates the warehouse turnover rate; Indicates the risk factor of the warehouse; , , , , Represents the weight coefficient of the warehouse priority model; The transportation priority model constructs the objective function by minimizing transportation cost and storage cost. , as shown in the following formula: ； in: Indicates from location To warehouse transportation costs; Indicates from location To warehouse The amount of cargo transported; Represents warehouse Quantity of goods; Represents warehouse The storage cost per unit of goods; At the same time, set the following constraints: ； ； ； in: Represents warehouse The demand for goods; Indicate location Supply volume; Represents warehouse Maximum storage quantity; Indicates the usage status of the warehouse; After solving the objective function through a linear programming or integer programming solver, the transportation priority of each warehouse is obtained according to the solution result; The warehouse loading model is specifically shown as follows: ； ； in: Indicates the loading priority of the current goods; Indicates the weight and volume ratio deviation of the current cargo and container; Indicates the current cargo weight; Indicates the current cargo volume; Indicates the maximum load weight of the container; Indicates the maximum volume of the container; Indicates the maximum weight of all cargo; Indicates the largest volume among all cargoes; All cargoes are loaded into the container according to the calculated cargo loading priority.

2. A warehouse distribution cabinet system, characterized in that: It includes data collection module, inventory consumption forecasting module, warehouse distribution module and cargo loading module; The data collection module is used to collect the cargo data stored in the warehouse and construct the cargo data set after preprocessing the cargo data; The inventory consumption prediction module is used to build an inventory consumption prediction model, input the cargo data set into the inventory consumption prediction model for training, obtain the trained inventory consumption prediction model, and predict the inventory consumption of warehouse cargo through the trained inventory consumption prediction model; The warehouse distribution module is used to build a warehouse distribution priority model, calculate the distribution priority of each warehouse based on the inventory consumption of goods predicted by each warehouse, and distribute goods to each warehouse according to the distribution priority order; The cargo loading module is used to construct a warehouse loading model. When the cargo is delivered to the corresponding warehouse, the loading priority of the cargo is calculated through the warehouse loading model, and the cargo is stored according to the loading priority. The inventory consumption prediction model is constructed based on the long short-term memory model and the extreme gradient boosting model; The cargo data set is input into the long short-term memory model and the extreme gradient boosting model for training respectively. The output results of the two models are weighted summed to obtain the predicted value. After each training is completed, the following loss function is used Calculate the loss: ； in: Indicates the cost of insufficient inventory; represents the cost of excess inventory; represents the predicted value; Indicates actual value; represents the indicator function; Then, the posterior distribution of the predicted value is modeled through the Bayesian network to obtain the uncertainty of the prediction result; When the uncertainty of the loss and the prediction result reaches a preset threshold, a trained inventory consumption prediction model is obtained, and the inventory consumption of the warehouse goods is predicted by the trained inventory consumption prediction model; The warehouse distribution priority model includes a market priority model, a warehouse priority model and a transportation priority model; Allocate goods to each warehouse in the order of transportation priority, market priority, and warehouse priority; The market priority model is specifically shown as follows: ； in: Indicates the market priority of the warehouse; Represents the market demand for goods in the warehouse; represents the seasonal adjustment factor; Indicates the intensity of competition for goods in the warehouse; Indicates the current inventory level in the warehouse; Indicates the future inventory growth rate of the warehouse; It represents the market risk indicator; , , , , represents the weight coefficient of the market priority model; The warehouse priority model is specifically shown in the following formula: ； in: Indicates warehouse priority; Indicates the cargo safety factor of the warehouse; Indicates the utilization rate of the warehouse; represents the transportation cost of the warehouse; Indicates the warehouse turnover rate; Indicates the risk factor of the warehouse; , , , , Represents the weight coefficient of the warehouse priority model; The transportation priority model constructs the objective function by minimizing transportation cost and storage cost. , as shown in the following formula: ； in: Indicates from location To warehouse transportation costs; Indicates from location To warehouse The amount of cargo transported; Represents warehouse Quantity of goods; Represents warehouse The storage cost per unit of goods; At the same time, set the following constraints: ； ； ； in: Represents warehouse The demand for goods; Indicate location Supply volume; Represents warehouse Maximum storage quantity; Indicates the usage status of the warehouse; After solving the objective function through a linear programming or integer programming solver, the transportation priority of each warehouse is obtained according to the solution result; The warehouse loading model is specifically shown as follows: ； ； in: Indicates the loading priority of the current goods; Indicates the weight and volume ratio deviation of the current cargo and container; Indicates the current cargo weight; Indicates the current cargo volume; Indicates the maximum load weight of the container; Indicates the maximum volume of the container; Indicates the maximum weight of all cargo; Indicates the largest volume among all cargoes; All cargoes are loaded into the container according to the calculated cargo loading priority.

3. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to claim 1 is implemented.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to claim 1 is implemented.

Images