Cargo loading management method and device, computer readable storage medium, computer program product, chip and terminal equipment

Abstract

This application provides a cargo loading management method and apparatus, a computer-readable storage medium, a computer program product, a chip, and a terminal device. The cargo loading management method includes: acquiring attribute information of the cargo to be loaded and information of at least one truck; inputting the attribute information of the cargo to be loaded and the information of at least one truck into a loading model to output a target loading scheme. The loading model has an objective function, which is determined based on the space utilization rate of at least one truck and multiple constraints. The multiple constraints include a load limit for at least one truck, a volume limit for at least one truck, a size limit for at least one truck, and a loading priority for the cargo to be loaded. This application provides a cargo loading scheme that reduces empty load rate, improves loading balance, and increases loading efficiency.

Description

Technical Field

[0001] This application relates to the field of logistics technology, and in particular to a cargo loading management method and apparatus, a computer-readable storage medium, a computer program product, a chip, and a terminal device. Background Technology

[0002] Traditional logistics operations typically involve multiple trucks carrying different goods. However, in practice, some trucks often have high "empty load rates" or uneven loading, leading to low overall transportation efficiency and high costs. With the rapid development of modern logistics and e-commerce, the demand for freight transportation is increasing year by year. To improve transportation efficiency and reduce logistics costs, carpooling (sharing truck resources) and loading optimization have become important areas of research and application.

[0003] Currently, many logistics companies still rely on manual product selection and loading planning. This method typically involves experienced loaders or dispatchers manually selecting and arranging goods based on attributes such as volume, weight, and shape.

[0004] However, existing technical solutions have obvious limitations in dealing with large-scale and complex logistics needs, and there is an urgent need for a more efficient and intelligent loading optimization method to solve these problems. Summary of the Invention

[0005] This application provides a cargo loading management method and apparatus, and provides a cargo loading scheme that reduces empty load rate, improves loading balance and loading efficiency.

[0006] To achieve the above objectives, this application provides the following technical solution:

[0007] Firstly, a cargo loading management method is provided, which is applied to a terminal device, or a chip or chip module in the terminal device. The cargo loading management method includes: acquiring attribute information of the cargo to be loaded and information of at least one truck; inputting the attribute information of the cargo to be loaded and the information of at least one truck into a loading model to output a target loading scheme, wherein the loading model has an objective function, the objective function being determined based on the space utilization rate of the at least one truck and multiple constraints; wherein the multiple constraints include the load limit of the at least one truck, the volume limit of the at least one truck, the size limit of the at least one truck, and the loading priority of the cargo to be loaded.

[0008] Optionally, the goods to be loaded are selected from at least one of the following: a reference container, a non-reference container, goods in the temporary storage area, and goods in the inventory area, wherein the volume of the reference container is larger than the volume of the non-reference container, the distance between the goods in the inventory area and the truck is greater than the distance between the goods in the temporary storage area and the truck, and the goods in the inventory area and the goods in the temporary storage area are non-container goods; the loading priority of the goods to be loaded, from high to low, is as follows: the reference container, the non-reference container, the goods in the temporary storage area, and the goods in the inventory area.

[0009] Optionally, the objective function is Maximize Z = w1×x1 + w2×x2 + w3×x3 + w4×x4, where x1 represents the space utilization rate, x2 represents the cargo loading sequence score, x3 represents the total volume of cargo in the loading scheme, x4 represents the total weight of cargo in the loading scheme, and w... 1、 w2, w3, and w4 are weighting coefficients.

[0010] Optionally, the cargo loading order score is determined by calculating the difference between the weight of the cargo that is first in the cargo loading order and the total weight of the other cargoes, and the cargo loading order score is positively correlated with the difference.

[0011] Optionally, inputting the attribute information of the goods to be loaded and the information of at least one truck into the loading model to output the target loading scheme includes: initializing the loading model to generate an initial loading scheme; iteratively optimizing the initial loading scheme based on selection, crossover, and mutation operations of a genetic algorithm until the iteration termination condition is met to obtain an optimized loading scheme; and selecting the loading scheme with the largest objective function value from the optimized loading scheme as the target loading scheme.

[0012] Optionally, before selecting the loading scheme with the largest objective function value from the optimized loading scheme as the target loading scheme, the method further includes: repairing the optimized loading scheme to ensure that the optimized loading scheme satisfies at least one of the following: the load limit of the at least one truck, the volume limit of the at least one truck, and the size limit of the at least one truck.

[0013] Optionally, the step of repairing the optimized loading scheme includes: in response to the total weight of the goods in the optimized loading scheme exceeding the load limit of the truck, removing a portion of the goods, wherein the portion of the goods is the goods with the smallest unit quantity in the optimized loading scheme, and / or, the portion of the goods is the goods with the lowest loading priority in the optimized loading scheme; or, in response to the size of the goods in the optimized loading scheme exceeding the size limit of the truck, reordering the arrangement order of the goods in the optimized loading scheme.

[0014] Optionally, the attribute information of the goods to be loaded includes combination indication information. After obtaining the attribute information of the goods to be loaded, the method further includes: combining the goods that are combined according to the combination indication information to form combined goods, and the attribute information of the combined goods is used to input into the loading model.

[0015] Secondly, this application also discloses a cargo loading management device, which includes: an acquisition module for acquiring attribute information of cargo to be loaded and information of at least one truck; and a loading scheme determination module for inputting the attribute information of the cargo to be loaded and the information of at least one truck into a loading model to output a target loading scheme. The loading model has an objective function, which is determined based on the space utilization rate of the at least one truck and multiple constraints. The multiple constraints include the load limit of the at least one truck, the volume limit of the at least one truck, the size limit of the at least one truck, and the loading priority of the cargo to be loaded.

[0016] Thirdly, a computer-readable storage medium is provided having a computer program stored thereon, the computer program being executed by a processing module to perform any one of the methods provided in the first or second aspect.

[0017] Fourthly, a communication device is provided, including a storage module and a processing module, wherein the storage module stores a computer program that can run on the processing module, and the processing module runs the computer program to perform any of the methods provided in the first aspect.

[0018] Fifthly, a computer program product is provided, on which a computer program is stored, the computer program being executed by a processing module to perform any one of the methods provided in the first or second aspect.

[0019] Sixthly, embodiments of this application also provide a chip that stores a computer program, which, when executed by the chip, implements the steps of the above-described method.

[0020] In a seventh aspect, embodiments of this application also provide a system chip for use in a terminal. The system chip includes at least one processing module and an interface circuit. The interface circuit and the at least one processing module are interconnected via a line. The at least one processing module is used to execute instructions to perform any one of the methods provided in the first or second aspect.

[0021] Compared with the prior art, the technical solution of this application has the following beneficial effects:

[0022] In this technical solution, a loading model is constructed, and the objective function of the loading model is determined based on the space utilization rate of at least one truck and multiple constraints. The target loading scheme output by the loading model can maximize the space utilization of the trucks while satisfying various constraints, namely, the load limit of at least one truck, the volume limit of at least one truck, the size limit of at least one truck, and the loading priority of the goods to be loaded. This achieves higher performance and efficiency, reduces vehicle empty load rate, and improves overall transportation efficiency. Furthermore, through multiple constraints, problems such as unreasonable cargo placement or damage caused by human error can be avoided, thus improving loading safety.

[0023] Furthermore, the technical solution of this application uses selection, crossover, and mutation operations of a genetic algorithm to iteratively optimize the initial loading scheme until the iteration termination condition is met, so as to obtain an optimized loading scheme. By introducing a genetic algorithm into the generation of the target loading scheme, the rationality of the loading scheme can be guaranteed, and the space utilization of the truck and the balanced loading of goods can be further maximized.

[0024] Furthermore, the technical solution of this application modifies the optimized loading scheme to ensure that it satisfies at least one of the following: a load limit for at least one truck, a volume limit for at least one truck, and a size limit for at least one truck. To prevent the loading model from exceeding truck limits in its output loading scheme due to the pursuit of maximizing the objective function, the optimized loading scheme can be further modified to ensure that the target loading scheme meets all constraints, thereby guaranteeing its rationality and feasibility. Attached Figure Description

[0025] Figure 1 This is a flowchart of a cargo loading management method provided in an embodiment of this application;

[0026] Figure 2 This is a flowchart of another cargo loading management method provided in the embodiments of this application;

[0027] Figure 3 This is a schematic diagram illustrating a specific application scenario provided in an embodiment of this application;

[0028] Figure 4 This is a schematic diagram of a loading scheme provided in an embodiment of this application;

[0029] Figure 5 This is a schematic diagram of a cargo loading configuration provided in an embodiment of this application. Detailed Implementation

[0030] As described in the background section, existing technical solutions exhibit significant limitations in addressing large-scale and complex logistics demands, necessitating a more efficient and intelligent loading optimization method to resolve these issues.

[0031] The applicant analyzed that, in order to meet the needs of large-scale and complex logistics, there are several main limitations:

[0032] (1) In large-scale order scenarios, traditional or simple heuristic methods often cannot quickly provide high-quality loading solutions, and it is easy to waste the remaining space of the truck due to improper loading order and unreasonable placement of goods.

[0033] (2) Not only should the space utilization of trucks be maximized, but also the requirements of load limits, loading methods (such as non-invertible and fragile goods) and loading and unloading convenience should be met at the same time. The multi-objective and multi-constraint situation further increases the complexity of the problem.

[0034] (3) The internal structures of trucks of different models and sizes vary greatly. Without a common algorithm framework and parameter adjustment mechanism, it is difficult to quickly switch and deploy between various transportation tasks and actual business needs.

[0035] In this technical solution, a loading model is constructed, and the objective function of the loading model is determined based on the space utilization rate of at least one truck and multiple constraints. The target loading scheme output by the loading model can maximize the space utilization of the trucks while satisfying various constraints, namely, the load limit of at least one truck, the volume limit of at least one truck, the size limit of at least one truck, and the loading priority of the goods to be loaded. This achieves higher performance and efficiency, reduces vehicle empty load rate, and improves overall transportation efficiency. Furthermore, through multiple constraints, problems such as unreasonable cargo placement or damage caused by human error can be avoided, thus improving loading safety.

[0036] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, specific embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0037] This application provides a cargo loading management method, referring to... Figure 1 The following will provide a detailed explanation through specific steps.

[0038] It is understood that, in specific implementation, the cargo loading management method can be implemented using software programs, which run within a processing module integrated into a chip or chip module. This method can also be implemented using a combination of software and hardware; this application does not impose any limitations on this approach. The following description uses a terminal device as the executing entity.

[0039] Step 101: Obtain the attribute information of the goods to be loaded and the information of at least one truck;

[0040] Step 102: Input the attribute information of the goods to be loaded and the information of at least one truck into the loading model to output the target loading plan. The loading model has an objective function, which is determined based on the space utilization rate of at least one truck and multiple constraints.

[0041] Several constraints include a load limit for at least one truck, a volume limit for at least one truck, a size limit for at least one truck, and a loading priority for the goods to be loaded.

[0042] It should be noted that the sequence number of each step in this embodiment does not represent a limitation on the execution order of each step.

[0043] In this embodiment, the goods to be loaded refer to the goods that need to be loaded into the truck. Specifically, the goods to be loaded can refer to packaged items, such as containers, cardboard boxes, wooden crates, etc.

[0044] Specifically, different goods to be loaded have different attribute information. In order to better design the loading plan, it is necessary to obtain the attribute information of the goods to be loaded. The attribute information of the goods to be loaded includes the size of the goods, the loading priority of the goods, and the quantity of the goods. Among them, the loading priority of the goods indicates the loading order of the goods. For example, large goods need to be loaded into the truck first, while small goods can be loaded into the truck last.

[0045] In one specific embodiment, the cargo to be loaded is selected from at least one of the following: a reference container, a non-reference container, cargo in the temporary storage area, and cargo in the inventory area, wherein the volume of the reference container is larger than that of the non-reference container, the distance between the cargo in the inventory area and the truck is greater than the distance between the cargo in the temporary storage area and the truck, and the cargo in the inventory area and the cargo in the temporary storage area are non-container cargo. For example, the reference container is a large container, and the non-reference container is a small container.

[0046] Accordingly, the loading priority of goods to be loaded, from highest to lowest, is as follows: base container, non-base container, goods in temporary storage area, and goods in inventory area. A higher loading priority indicates that the goods will be loaded into the truck earlier in the order they appear.

[0047] Specifically, when loading goods, larger items are prioritized to maximize truck space utilization. Therefore, standard containers have a higher loading priority than non-standard containers. Goods in temporary storage areas and inventory areas are non-container goods, smaller in size than non-standard containers, and thus have a lower loading priority. Furthermore, warehouses typically have temporary storage areas and inventory areas. Temporary storage areas are used for temporary storage of goods, while inventory areas are used for long-term storage. When loading is required, trucks are closer to the temporary storage area than to the inventory area, so goods in the temporary storage area are loaded first. In other words, goods in the temporary storage area have a higher transfer priority than goods in the inventory area.

[0048] It should be noted that the distinction between reference cabinets and non-reference cabinets can be customized by the user according to the actual application scenario, and this application does not impose any restrictions on this.

[0049] In this embodiment, a truck refers to a vehicle used for loading goods. Examples include box trucks, stake trucks, and refrigerated trucks. Different trucks have different capacities and can accommodate different quantities of goods. To better design loading plans, it is necessary to obtain truck information. Specifically, truck information may include at least one of the following: load limits, volume limits, and size limits.

[0050] Specifically, there can be one or more trucks, and the number of goods to be loaded can be multiple. In particular, the number of trucks and the number of goods to be loaded vary depending on the loading mode. For example, a loading mode of "2-to-1 container" means there are 2 containers to be loaded and 1 truck; a loading mode of "3-to-2 container" means there are 3 containers to be loaded and 2 trucks; and a loading mode of "LCL" means the goods to be loaded are less than cargo and 1 truck.

[0051] In this embodiment, the attribute information of the goods to be loaded and the information of at least one truck are the inputs to the loading model, which can be used to output the target loading scheme. The loading model is pre-built. The loading model has an objective function; by maximizing the objective function, the target loading scheme can be determined.

[0052] Specifically, the goal of the loading model is to generate an optimal or near-optimal loading scheme. The objective function of the loading model maximizes the space utilization of the truck, i.e., minimizes the remaining space, which can be measured by the ratio of the total volume of loaded cargo to the total volume of the truck. It also ensures that the loading scheme satisfies multiple constraints. For example, the loading scheme needs to meet the truck's load capacity, volume, and size restrictions, as well as the loading priority of the cargo to be loaded.

[0053] More specifically, the loading plan may include cargo identification, cargo quantity, and cargo loading priority.

[0054] In a non-limiting embodiment, the objective function of the loading model is Maximum Z = w1×x1 + w2×x2 + w3×x3 + w4×x4, where x1 represents space utilization, x2 represents the cargo loading order score, x3 represents the total volume of cargo in the loading scheme, x4 represents the total weight of cargo in the loading scheme, and w 1、 w2, w3, and w4 are the corresponding weighting coefficients.

[0055] Specifically, by maximizing the value of Z, the loading model can determine the target loading scheme. The value of Z is related to space utilization, cargo loading sequence score, total cargo volume, and total cargo weight.

[0056] Furthermore, the cargo loading sequence score reflects the rationality of the cargo loading sequence. Generally speaking, the cargo loading sequence score is positively correlated with space utilization; that is, the higher the cargo loading sequence score, the higher the space utilization. Specifically, the cargo loading sequence score can be calculated as follows: calculate the difference between the weight of the first cargo in the loading sequence and the total weight of the other cargoes; the cargo loading sequence score is positively correlated with this difference.

[0057] For example, for four types of goods a, b, c, and d, when they are loaded in the order of a, b, c, and d, the loading order score is the difference between the total weight of goods b, c, and d and the weight of goods a.

[0058] For example, the cargo loading order score can be obtained by converting the above difference into an exponential form.

[0059] In one specific embodiment, the loading model can output the target loading scheme through the following steps: abstracting the actual loading problem into a mathematical model, clarifying the decision variables, objective function and constraints; defining all possible arrangements of the products to form a search space and providing an optimization algorithm for search; comprehensively considering multiple objectives such as space utilization, transportation costs, loading and unloading sequence to form a balanced loading scheme; and transforming the optimization results into a specific loading scheme.

[0060] The embodiments of this application can simultaneously take into account multiple constraints such as space utilization, load limits, cargo stacking, loading and unloading sequence, and transportation safety, thereby improving the performance of the loading scheme.

[0061] Specifically, the weight of a constraint represents the degree of influence of that constraint on the objective function. By setting combinations of weight coefficients with different values, the degree of influence of different space utilization rates or different constraints on the objective function can be adjusted.

[0062] In a specific example, the weighting coefficients are w1=0.4, w2=0.3, w3=0.2, and w4=0.1. The objective function can be expressed as: Maximize Z=0.4×x1+0.3×x2+0.2×x3+0.1×x4. Assume the target loading scheme has a space utilization rate of x1=0.85 (meaning a space utilization rate of 85%), a loading order score of x2=0.9 (assuming a maximum score of 1, indicating a good loading order), a total cargo volume of x3=50 (cubic meters), and a total cargo weight of x4=100 (tons). Substituting these values ​​into the objective function, we get: Z=0.4×0.85+0.3×0.9+0.2×50+0.1×100 Z=0.34+0.27+10+10 Z=20.61. That is, the objective function value for this target loading scheme is 20.61.

[0063] It should be noted that the weighting coefficients can be adaptively adjusted according to the needs of the actual application scenario, and this application does not impose any restrictions on this. In a non-limiting embodiment, to obtain a better loading scheme, the target loading scheme can also be determined through multiple iterative optimizations. Please refer to [link / reference] for details. Figure 2 , Figure 2 The flowchart of a cargo loading management method is shown.

[0064] In step 201, the loading model is initialized to generate an initial loading scheme.

[0065] Specifically, the initial loading plan includes the identification, quantity, and arrangement order of each cargo to be loaded.

[0066] In step 202, the initial loading scheme is iteratively optimized based on the selection, crossover, and mutation operations of the genetic algorithm until the iteration termination condition is met, so as to obtain the optimized loading scheme.

[0067] Specifically, first, individuals with high fitness, such as loading schemes with space utilization >90%, are selected and retained as high-quality genes. This can be achieved using roulette wheel selection (allocating probabilities based on fitness) or tournament selection (selecting locally optimal individuals). Then, two parent gene segments are swapped; for example, the weight and volume combinations are rearranged to reorder the loading process. Next, the parent loading order is retained, and unfilled cargo is loaded. Finally, the mutation rate is dynamically adjusted based on the number of iterations; for example, the mutation rate is 5% for iterations 1-500 and 1% for iterations 501-2000.

[0068] More specifically, fitness can be defined based on indicators such as space utilization, loading sequence feasibility, and cargo integrity. Fitness can be calculated using the following formula: v1×x1 + v2×x2 + v3×x5, where x1 represents space utilization, x2 represents cargo loading sequence score, x5 represents cargo integrity score, and v... 1、 v2 and v3 are weighting coefficients. The cargo integrity score indicates whether the cargo has been split. A higher integrity score indicates that the cargo has not been split, while a lower score indicates that the cargo has been split into more parts. For example, a container that has not been split has a cargo integrity score of 100 points; a container that has been split into two parts and loaded onto two trucks has a cargo integrity score of 50 points.

[0069] In a specific example, v 1、 v2, v3 are 60%, 20%, and 20%, respectively.

[0070] The embodiments of this application can achieve better space utilization and lower transportation costs while ensuring the safety of truck loading and the integrity of the goods.

[0071] Furthermore, after each iteration of the genetic algorithm, local searches or fine-tuning can be performed on individuals with higher fitness to obtain a better loading scheme. Specifically, fine-tuning can be performed in the following ways:

[0072] First, neighborhood swapping optimization is performed on individuals with high fitness. Specifically, two items with high fitness can be randomly selected to swap locations.

[0073] Then, constraint repair and optimization are performed. Specifically, goods that violate the constraints can be corrected. For example, if the loading plan exceeds the truck's load limit, the goods can be redistributed so that the target loading plan meets the constraints of each condition, ensuring the rationality and feasibility of the target loading plan.

[0074] Finally, dynamic perturbation is performed, and the coefficient of variation is dynamically adjusted according to the number of iterations. For example, the coefficient of variation for iterations 1-500 is >=7, and the coefficient of variation for iterations 501-2000 is <=2.

[0075] This embodiment, by introducing a genetic algorithm into the generation of the target loading scheme, can ensure the rationality of the loading scheme, further maximize the space utilization of the truck, and balance the loading of goods.

[0076] In step 203, the loading scheme with the largest objective function value is selected from the optimized loading schemes as the target loading scheme.

[0077] Furthermore, prior to step 203, the optimized loading scheme may be repaired to ensure that the optimized loading scheme meets at least one of the following: a load limit for at least one truck, a volume limit for at least one truck, or a size limit for at least one truck.

[0078] Specifically, in response to the total weight of goods in the optimized loading plan exceeding the truck's load limit, some goods are removed. These removed goods are those with the smallest unit quantity in the optimized loading plan, and / or, some goods have the lowest loading priority in the optimized loading plan. In other words, when the goods loaded onto the truck are overweight, removing the goods with the smallest unit quantity in the loading plan ensures the integrity of the loaded goods; removing the goods with the lowest loading priority, such as goods in the storage area, ensures the convenience of loading the goods.

[0079] Specifically, in response to the situation where the size of the cargo in the optimized loading scheme exceeds the size limit of the truck, the arrangement order of the cargo in the optimized loading scheme is reordered until the size of the cargo in the loading scheme meets the size limit of the truck.

[0080] Furthermore, if changing the order of goods in the loading scheme still exceeds the size limit of the truck, some goods can be removed to make the size of the goods in the loading scheme meet the size limit of the truck.

[0081] The embodiments of this application can flexibly adapt to changes in different vehicle models, cargo types, and transportation needs, and meet diverse logistics scenarios.

[0082] In a non-limiting embodiment, the attribute information of the goods to be loaded includes combination indication information. The combination indication information is used to indicate whether the goods to be loaded need to be combined.

[0083] This embodiment can combine goods with combination indication information to form combined goods, and the attribute information of the combined goods is used to input into the loading model. Combined goods indicate that the goods cannot be separated and need to be loaded and unloaded as a whole.

[0084] Specifically, if the attribute information of cargo 1 and cargo 2 to be loaded indicates that they need to be combined, then when designing the loading plan, the loading plan is determined by taking the combined cargo 1 and cargo 2 to be loaded as a whole.

[0085] Furthermore, the combination instruction information may also include a combination ratio value, that is, the ratio of the goods to be loaded that need to be combined. For example, for a combination of goods, if two goods to be loaded 1 and one goods to be loaded 2 are required, then the combination ratio value is 2.

[0086] In a specific example, the front-end interface returns a product list, which contains the attribute information of the goods to be loaded. Goods indicated as "combined" are then combined. Based on the product combination ratio, the quantities of the goods to be loaded are calculated to determine the total quantity of the combined goods. In other words, the quantity of the combined goods is the ratio of the maximum quantity of the goods to be combined to the combination ratio, and the minimum value of this ratio plus the quantities of other goods to be combined is used to determine the total quantity of the combined goods.

[0087] For example, if the goods to be combined are headphones and headphone cases, with 100 headphones and 60 headphone cases, and a ratio of 2, then the quantity of goods to be combined is min(50,60)=50.

[0088] Traditional model parameter optimization typically employs a grid search approach. Grid search requires traversing all preset parameter combinations (e.g., enumerating learning rates from 0.1 to 0.001 with exponential steps), and the computational cost increases exponentially with the number of parameters (N parameters require k...). N (Number of calculations).

[0089] In a non-limiting embodiment, in order to reduce the efficiency of parameter optimization of the loading model, this embodiment improves the optimization efficiency through grid search.

[0090] Specifically, firstly, the parameters are divided into multiple grids, and coarse screening is performed in each grid to select the optimal K parameter combinations, where K is a positive integer.

[0091] Then, genetic optimization is performed on the K parameter combinations. The results of the coarse screening are used as the initial population. The genetic algorithm is used for iterative optimization to adjust parameters such as mutation probability, number of mutations, and number of crossovers within a small range.

[0092] The embodiments of this application optimize parameters through grid search, which can complete parameter iteration optimization faster and improve model optimization efficiency.

[0093] In a non-limiting embodiment, please refer to Figure 3 , Figure 3 This illustrates an application scenario of a cargo loading management method.

[0094] The front end (e.g., a logistics system) can generate loading instructions and send them to the acquisition module 301. The loading instructions may include the loading mode, attribute information of the goods to be loaded, and information about at least one truck. The acquisition module 301 receives the loading instructions. The acquisition module 301 then sends the loading mode, attribute information of the goods to be loaded, and information about at least one truck to the loading model 302, which outputs the target loading plan.

[0095] Specifically, loading model 302 initializes the algorithm parameters and population, and generates an initial loading scheme, i.e., an initial cargo arrangement sequence, through the set genetic algorithm parameters. Loading model 302 performs local search optimization on the initial loading scheme, performing neighborhood exchanges or dynamic perturbations on individuals with high fitness. Loading model 302 determines whether the stopping condition is met (i.e., reaching the maximum number of iterations or the fitness reaching a preset threshold). If the stopping condition is met, the current optimal solution is output, and the target loading scheme is obtained.

[0096] Specifically, loading model 302 determines the target loading scheme based on a genetic algorithm iteratively. Specifically, it can calculate fitness based on selection, crossover, and mutation operations of the genetic algorithm, and then repair the loading scheme to ensure that it meets at least one of the following: a load limit for at least one truck, a volume limit for at least one truck, or a size limit for at least one truck, thus obtaining the target loading scheme.

[0097] This embodiment reduces overall transportation costs by optimizing carpooling and loading schemes, thereby reducing empty truck rates and uneven loading.

[0098] like Figure 4 As shown, Figure 4 A schematic diagram of a loading scheme is shown.

[0099] Specifically, the target loading plan can be displayed on the interface. The target loading plan includes the following information for each cargo: container number, first-leg plan, inventory type, minimum stock keeping unit (SKU) of the Logistics Enterprise Resource Planning System, quantity, number of boxes, carton length (L-CM, i.e., length in centimeters), carton width (W-CM), and carton height (H-CM), etc.

[0100] Figure 4 The information above is shown for container numbers BLHU1340921 and BLHU9982759.

[0101] It should be noted that in practical application scenarios, the goods in the loading scheme can also be any other feasible form of goods, such as cardboard boxes, wooden boxes, etc., and this application does not impose any restrictions on this.

[0102] Please refer to Figure 5 , Figure 5 A cargo loading management device 50 is shown, which may include:

[0103] The acquisition module 501 is used to acquire the attribute information of the goods to be loaded and the information of at least one truck.

[0104] The loading scheme determination module 502 is used to input the attribute information of the goods to be loaded and the information of at least one truck into the loading model to output the target loading scheme.

[0105] Furthermore, the loading scheme determination module 502 also includes:

[0106] The initial unit is used to initialize the loading model and generate an initial loading scheme;

[0107] The optimization unit is used to iteratively optimize the initial loading scheme based on the selection, crossover and mutation operations of the genetic algorithm until the iteration termination condition is met, so as to obtain the optimized loading scheme.

[0108] The loading scheme determination unit is used to select the loading scheme with the largest objective function value from the optimized loading schemes as the target loading scheme.

[0109] Furthermore, the loading scheme determination module 502 also includes a repair module for repairing the optimized loading scheme so that the optimized loading scheme meets at least one of the following: the load limit of at least one truck, the volume limit of at least one truck, and the size limit of at least one truck.

[0110] Furthermore, the repair module is also used to remove some cargo in response to the total weight of the cargo in the optimized loading scheme exceeding the truck's load limit. Some of the cargo is the cargo with the smallest unit quantity in the optimized loading scheme, and / or, some of the cargo is the cargo with the lowest loading priority in the optimized loading scheme.

[0111] Furthermore, the repair module is also used to reorder the cargo arrangement in the optimized loading scheme in response to the cargo size exceeding the truck size limit.

[0112] Furthermore, the loading scheme determination module 502 also includes a combination module, used to combine the goods that are combined according to the combination instruction information, to form combined goods, and the attribute information of the combined goods is used to input into the loading model.

[0113] In specific implementation, the aforementioned cargo loading management device 50 may correspond to a chip in the terminal device that has cargo loading management function, such as a system-on-a-chip (SOC), a baseband chip, etc.; or correspond to a chip module in the terminal device that includes a cargo loading management function; or correspond to a chip module with a data processing function chip; or correspond to the terminal device.

[0114] This application embodiment constructs a loading model and determines the objective function of the loading model based on the space utilization rate of at least one truck and multiple constraints. The target loading scheme output by the loading model can maximize the space utilization of the trucks while satisfying various constraints, namely, the load limit of at least one truck, the volume limit of at least one truck, the size limit of at least one truck, and the loading priority of the goods to be loaded. This achieves higher performance and efficiency, reduces vehicle empty load rate, and improves overall transportation efficiency. In addition, through multiple constraints, it can also avoid problems such as unreasonable placement or damage of goods due to human judgment errors, thereby improving loading safety.

[0115] Other relevant descriptions of the cargo loading management device 50 can be found in the descriptions in the foregoing embodiments, and will not be repeated here.

[0116] Regarding the modules / units included in the various devices and products described in the above embodiments, they can be software modules / units, hardware modules / units, or a combination of both. For example, for various devices and products applied to or integrated into a chip, all of their modules / units can be implemented using hardware methods such as circuits, or at least some modules / units can be implemented using software programs that run within a processing module integrated into the chip, while the remaining (if any) modules / units can be implemented using hardware methods such as circuits. For various devices and products applied to or integrated into a chip module, all of their modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components of the chip module, or at least some modules / units can be implemented using hardware methods such as circuits. The implementation can be done through software programs, which run within the processing module integrated into the chip module. The remaining modules / units (if any) can be implemented using hardware methods such as circuits. For various devices and products applied to or integrated into terminal devices, each of their modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components within the terminal device. Alternatively, at least some modules / units can be implemented through software programs, which run within the processing module integrated into the terminal device. The remaining modules / units (if any) can be implemented using hardware methods such as circuits.

[0117] This application also discloses a storage medium, which is a computer-readable storage medium storing a computer program thereon. When the computer program is executed, it can perform the steps of the method shown in the foregoing embodiments. The storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc. The storage medium may also include a non-volatile or non-transitory storage module, etc.

[0118] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article indicates that the preceding and following related objects have an "or" relationship.

[0119] In the embodiments of this application, "multiple" refers to two or more.

[0120] The descriptions of "first," "second," etc., appearing in the embodiments of this application are for illustrative purposes and to distinguish the objects being described. They have no order and do not indicate any special limitation on the number of devices in the embodiments of this application, nor do they constitute any limitation on the embodiments of this application.

[0121] In this application, the term "connection" refers to various connection methods, such as direct connection or indirect connection, to achieve communication between devices. This application does not impose any limitations on this.

[0122] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means.

[0123] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0124] In the several embodiments provided in this application, it should be understood that the disclosed methods, apparatuses, and systems can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for example, the division of units is merely a logical functional division, and other division methods may exist in actual implementation; 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, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0125] The units described 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.

[0126] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can be physically included separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0127] The integrated unit implemented as a software functional unit described above can be stored in a computer-readable storage medium. This software functional unit, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute some steps of the methods described in the various embodiments of this application.

[0128] While this application discloses the above information, it is not limited thereto. Any person skilled in the art can make various modifications and alterations without departing from the spirit and scope of this application; therefore, the scope of protection of this application shall be determined by the scope defined in the claims.

Claims

1. A cargo loading management method, characterized in that, include: Obtain the attribute information of the cargo to be loaded and the information of at least one truck; The attribute information of the goods to be loaded and the information of at least one truck are input into the loading model to output the target loading scheme. The loading model has an objective function, which is determined based on the space utilization rate of the at least one truck and multiple constraints. The multiple constraints include the load limit of the at least one truck, the volume limit of the at least one truck, the size limit of the at least one truck, and the loading priority of the cargo to be loaded.

2. The cargo loading management method according to claim 1, characterized in that, The goods to be loaded are selected from at least one of the following: standard container, non-standard container, temporary storage area goods, and inventory area goods, wherein the volume of the standard container is larger than the volume of the non-standard container, the distance between the inventory area goods and the truck is greater than the distance between the temporary storage area goods and the truck, and the inventory area goods and the temporary storage area goods are non-container goods; the loading priority of the goods to be loaded, from high to low, is as follows: standard container, non-standard container, temporary storage area goods, and inventory area goods.

3. The cargo loading management method according to claim 1, characterized in that, The objective function is Maximum Z = w1×x1 + w2×x2 + w3×x3 + w4×x4, where x1 represents the space utilization rate, x2 represents the cargo loading sequence score, x3 represents the total volume of cargo in the loading scheme, x4 represents the total weight of cargo in the loading scheme, and w... 1、 w2, w3, and w4 are weighting coefficients.

4. The cargo loading management method according to claim 3, characterized in that, The cargo loading order score is determined in the following way: The difference between the weight of the first item in the loading sequence and the total weight of the other items is calculated, and the loading sequence score is positively correlated with the difference.

5. The cargo loading management method according to claim 1, characterized in that, The step of inputting the attribute information of the goods to be loaded and the information of at least one truck into the loading model to output the target loading plan includes: The loading model is initialized to generate an initial loading scheme; Based on the selection, crossover, and mutation operations of the genetic algorithm, the initial loading scheme is iteratively optimized until the iteration termination condition is met, so as to obtain the optimized loading scheme. The loading scheme with the largest objective function value is selected from the optimized loading schemes as the target loading scheme.

6. The cargo loading management method according to claim 5, characterized in that, Before selecting the loading scheme with the largest objective function value from the optimized loading schemes as the target loading scheme, the method further includes: The optimized loading scheme is modified to satisfy at least one of the following: the load limit of the at least one truck, the volume limit of the at least one truck, and the size limit of the at least one truck.

7. The cargo loading management method according to claim 6, characterized in that, The repair of the optimized loading scheme includes: In response to the total weight of the cargo in the optimized loading scheme exceeding the truck's load limit, a portion of the cargo is removed. This portion of cargo consists of the cargo with the smallest unit quantity in the optimized loading scheme, and / or, the portion of cargo consists of the cargo with the lowest loading priority in the optimized loading scheme; or... In response to the cargo size exceeding the truck size limit in the optimized loading scheme, the cargo arrangement order in the optimized loading scheme is reordered.

8. The cargo loading management method according to claim 1, characterized in that, The attribute information of the goods to be loaded includes combined indication information. After obtaining the attribute information of the goods to be loaded, the process further includes: The goods indicated by the combination information are combined to form combined goods, and the attribute information of the combined goods is used to input into the loading model.

9. A cargo loading management device, characterized in that, include: The acquisition module is used to acquire attribute information of the goods to be loaded and information of at least one truck. The loading scheme determination module is used to input the attribute information of the goods to be loaded and the information of at least one truck into the loading model to output the target loading scheme. The loading model has an objective function, which is determined based on the space utilization rate of the at least one truck and multiple constraints. The multiple constraints include the load limit of the at least one truck, the volume limit of the at least one truck, the size limit of the at least one truck, and the loading priority of the cargo to be loaded.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program, when run by the processing module, executes the steps of the cargo loading management method according to any one of claims 1 to 8.

11. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processing module, it implements the steps of the cargo loading management method according to any one of claims 1 to 8.

12. A chip, the chip comprising at least one processing module and an interface circuit, the interface circuit being connected to the at least one processing module, characterized in that, The processing module executes the steps of the cargo loading management method according to any one of claims 1 to 8 by running program instructions.

13. A terminal device, comprising a storage module and a processing module, wherein the storage module stores a computer program executable on the processing module, characterized in that, When the processing module runs the computer program, it performs the steps of the cargo loading management method according to any one of claims 1 to 8.