Goods transportation method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a cargo transportation method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps that the cargo weight and the cargo volume corresponding to a target waybill and the load upper limit value and the volume upper limit value corresponding to each transportation tool are acquired from a waybill data set; under the condition that the load upper limit value is not smaller than the cargo weight and the volume upper limit value is not smaller than the cargo volume, determining the transportation tool as a candidate transportation tool; randomly selecting a target transportation tool from the at least one obtained candidate transportation tool, inputting the cargo weight, the cargo volume, and the load upper limit value and the volume upper limit value of the target transportation tool into the trained genetic model, and outputting the adaptation degree between the target waybill and the target transportation tool; and under the condition that the adaptation degree is greater than the adaptation degree threshold value, controlling the target transportation tool to transport goods corresponding to the target waybill. According to the method provided by the invention, the cargo transportation efficiency can be effectively improved.

Description

Technical Field

[0001] The present application relates to the field of logistics and transportation technology, and in particular to a cargo transportation method, device, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] In the logistics and transportation industry, dispatchers currently select the means of transportation for transporting goods based on the weight and volume of the goods according to their work experience. This method of manually determining the means of transportation may result in a mismatch between the selected means of transportation and the goods, thereby reducing transportation efficiency. Summary of the invention

[0003] Based on this, it is necessary to provide a cargo transportation method, device, computer equipment, computer-readable storage medium and computer program product that can improve transportation efficiency in response to the above-mentioned technical problems.

[0004] In a first aspect, the present application provides a method for transporting goods, the method comprising:

[0005] Obtain the cargo weight and cargo volume corresponding to the target waybill from the waybill data set, and obtain the corresponding upper load limit and upper volume limit of each of the multiple means of transport;

[0006] For each means of transport, if the upper limit of the load capacity is not less than the weight of the cargo and the upper limit of the volume capacity is not less than the volume of the cargo, the means of transport is determined as a candidate means of transport;

[0007] Randomly select a target transport tool from at least one candidate transport tool obtained, input the cargo weight, cargo volume, upper limit value of the load and upper limit value of the volume of the target transport tool into the trained genetic model, and output the fitness between the target waybill and the target transport tool;

[0008] When the degree of fitness is greater than the threshold value of the degree of fitness, the target transport vehicle is controlled to transport the goods corresponding to the target waybill.

[0009] In one embodiment, the waybill data set includes cargo weights and cargo volumes corresponding to a plurality of initial waybills; and the process of determining the target waybill includes:

[0010] For each initial waybill's transportation start time, obtain the latest allowed time corresponding to the transportation start time;

[0011] Sort multiple initial waybills in order from the latest allowed time;

[0012] The first initial waybill in the sorting result is determined as the target waybill.

[0013] In one embodiment, when the degree of fit is greater than a threshold value of the degree of fit, after controlling the target transport vehicle to transport the goods corresponding to the target waybill, the method further includes:

[0014] The first initial waybill after the target waybill in the sorting result is determined as the new target waybill;

[0015] Return to the step of obtaining the cargo weight and cargo volume corresponding to the target waybill from the waybill dataset, and continue executing until all the cargo corresponding to the initial waybill has been transported.

[0016] In one embodiment, the method further comprises:

[0017] When the fitness is not greater than the fitness threshold, for the remaining transportation means other than the target transportation means in at least one candidate transportation means, randomly select a transportation means from the remaining transportation means as a new target transportation means;

[0018] Return to the step of inputting the cargo weight, cargo volume, upper limit value of the load and upper limit value of the volume of the target transportation tool into the trained genetic model, and continue to execute until the fitness is greater than the fitness threshold.

[0019] In one embodiment, the fitness is output by the trained genetic model based on the difference between the upper limit value of the target transportation vehicle and the weight of the cargo, and the difference between the upper limit value of the capacity of the target transportation vehicle and the volume of the cargo.

[0020] In one embodiment, the training process of the genetic model includes:

[0021] Obtain the sample cargo weight and sample cargo volume corresponding to the sample waybill, as well as the sample load upper limit and sample volume upper limit corresponding to the sample transport vehicle, and obtain the sample compatibility between the sample waybill and the sample transport vehicle;

[0022] Input the sample cargo weight, sample cargo volume, sample load upper limit value, sample volume upper limit value and sample fitness into the pre-trained genetic model, and output the loss value;

[0023] For each training round, when the number of training times corresponding to the training round reaches a preset number of times, or the loss value is within a preset loss value range, the genetic model obtained in the training round is determined as the trained genetic model.

[0024] In a second aspect, the present application also provides a cargo transportation device, the device comprising:

[0025] An acquisition module is used to obtain the cargo weight and cargo volume corresponding to the target waybill from the waybill data set, and obtain the corresponding upper load limit value and upper volume limit value of each of the multiple means of transport;

[0026] A determination module, for determining, for each transport means, a transport means as a candidate transport means when the upper limit value of the load is not less than the weight of the goods and the upper limit value of the volume is not less than the volume of the goods;

[0027] A selection module is used to randomly select a target transport tool from at least one candidate transport tool obtained, input the cargo weight, cargo volume, upper load limit value and volume upper limit value of the target transport tool into the trained genetic model, and output the fitness between the target waybill and the target transport tool;

[0028] The control module is used to control the target transport vehicle to transport the goods corresponding to the target waybill when the fitness is greater than the fitness threshold.

[0029] In a third aspect, the present application further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method in any one of the above embodiments when executing the computer program.

[0030] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method in any one of the above embodiments are implemented.

[0031] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the method in any one of the above embodiments are implemented.

[0032] The cargo transportation method, device, computer equipment, computer-readable storage medium and computer program product described above obtain the cargo weight and cargo volume corresponding to the target waybill from the waybill data set, and obtain the corresponding upper load limit value and upper volume limit value of each transport tool among multiple transport tools; for each transport tool, when the upper load limit value is not less than the cargo weight and the upper volume limit value is not less than the cargo volume, the transport tool is determined as a candidate transport tool; a target transport tool is randomly selected from at least one candidate transport tool obtained, and the cargo weight, cargo volume, upper load limit value and upper volume limit value of the target transport tool are input into the trained genetic model, and the fitness between the target waybill and the target transport tool is output; when the fitness is greater than the fitness threshold, the target transport tool is controlled to transport the cargo corresponding to the target waybill. The method provided by the present application determines that the target transport tool is the transport tool that best matches the target waybill, which can effectively improve the efficiency of transporting goods. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0034] Figure 1 A schematic diagram of a flow chart of a cargo transportation method in one embodiment;

[0035] Figure 2 Schematic diagram of a flow chart of a method for determining a target waybill in one embodiment;

[0036] Figure 3 A schematic diagram of a flow chart of a cargo transportation method in another embodiment;

[0037] Figure 4 is a structural block diagram of a cargo transport device in one embodiment;

[0038] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0040] In one embodiment, Figure 1 As shown, a cargo transportation method is provided. This embodiment takes the method applied to a terminal as an example. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0041] S102: Obtain the cargo weight and cargo volume corresponding to the target waybill from the waybill data set, and obtain the corresponding upper load limit value and upper volume limit value of each of the multiple means of transport.

[0042] Optionally, at least one of the upper limit values ​​of load capacity or upper limit values ​​is different between every two means of transportation.

[0043] Optionally, the means of transportation may include, but are not limited to, vehicles and drones.

[0044] S104. For each means of transport, if the upper limit of the load capacity is not less than the weight of the cargo and the upper limit of the volume capacity is not less than the volume of the cargo, the means of transport is determined as a candidate means of transport.

[0045] Optionally, if there is no means of transport whose upper load limit is not less than the weight of the goods and whose upper volume limit is not less than the volume of the goods, it means that no means of transport can transport the goods corresponding to the target waybill alone. At this time, other means of transport with larger upper load limit and larger upper volume limit can be dispatched to transport the goods corresponding to the target waybill. If the goods corresponding to the target waybill are decomposable goods, multiple means of transport can also be used to transport the goods corresponding to the target waybill together. The embodiments of the present application do not make specific limitations on this.

[0046] S106. Randomly select a target transport tool from at least one candidate transport tool obtained, input the cargo weight, cargo volume, upper limit value of the load and upper limit value of the volume of the target transport tool into the trained genetic model, and output the degree of fit between the target waybill and the target transport tool.

[0047] Optionally, the genetic model can be a genetic algorithm. A genetic algorithm (GA) is a search heuristic algorithm that imitates the biological evolution process of natural selection and genetic mechanisms. A genetic algorithm belongs to a broader category of evolutionary algorithms (EAs), which use mechanisms in biological evolution, such as inheritance, mutation, selection, and crossover (also called recombination) to solve optimization and search problems; fitness is used to characterize the degree of match between a target waybill and a target means of transport.

[0048] Optionally, model parameters of the genetic model may include, but are not limited to, population size, crossover probability, mutation probability, and number of iterations.

[0049] Optionally, a random number tool may be used to randomly select a target transportation tool from the obtained at least one candidate transportation tool.

[0050] S108. When the degree of adaptability is greater than a threshold value of the degree of adaptability, the target transport vehicle is controlled to transport the goods corresponding to the target waybill.

[0051] Optionally, if the degree of fitness is greater than a fitness threshold, it indicates that the degree of match between the target waybill and the target transport vehicle is very high, and it is most appropriate to use the target transport vehicle to transport the goods corresponding to the target waybill.

[0052] In the above cargo transportation method, the cargo weight and cargo volume corresponding to the target waybill are obtained from the waybill data set, and the corresponding upper limit value of the load and upper limit value of the volume of each transport tool among multiple transport tools are obtained; for each transport tool, when the upper limit value of the load is not less than the cargo weight, and the upper limit value of the volume is not less than the cargo volume, the transport tool is determined as a candidate transport tool; a target transport tool is randomly selected from at least one candidate transport tool obtained, and the cargo weight, cargo volume, upper limit value of the load and upper limit value of the volume of the target transport tool are input into the trained genetic model, and the fitness between the target waybill and the target transport tool is output; when the fitness is greater than the fitness threshold, the target transport tool is controlled to transport the cargo corresponding to the target waybill. The method provided by the present application determines that the target transport tool is the transport tool that best matches the target waybill, which can effectively improve the efficiency of transporting goods.

[0053] In some embodiments, Figure 2 As shown, the waybill data set includes the corresponding cargo weights and cargo volumes of multiple initial waybills; the process of determining the target waybill includes:

[0054] S202: For each transportation start time of the initial waybill, obtain the latest allowed time corresponding to the transportation start time.

[0055] S204. Sort the multiple initial waybills in order from the latest allowed time.

[0056] S206: Determine the first initial waybill in the sorting result as the target waybill.

[0057] Optionally, the latest allowed time represents the urgency of the corresponding initial waybill. The earlier the latest allowed time is, the more urgent the corresponding initial waybill is, and the goods corresponding to the initial waybill need to be transported first.

[0058] In this embodiment, multiple initial waybills are sorted in order from the latest allowed time, and the first initial waybill in the sorting result is determined as the target waybill. In this way, the goods corresponding to the initial waybill can be transported according to the emergency situation of the initial waybill, which can effectively ensure the timeliness of the goods transportation.

[0059] In some embodiments, when the degree of fitness is greater than the degree of fitness threshold, after controlling the target transport vehicle to transport the goods corresponding to the target waybill, it also includes: determining the first initial waybill located after the target waybill in the sorting result as the new target waybill; returning to the step of obtaining the goods weight and cargo volume corresponding to the target waybill from the waybill data set, and continuing to execute until the goods corresponding to all initial waybills are transported.

[0060] Optionally, after transporting the goods corresponding to the target waybill, the first initial waybill after the target waybill is the most urgent initial waybill, and the goods corresponding to this initial waybill need to be transported first.

[0061] In this embodiment, after transporting the goods corresponding to the target waybill, the goods corresponding to the first initial waybill located after the target waybill are transported first, which can effectively ensure the timeliness of the goods transportation.

[0062] In some embodiments, the method also includes: when the degree of fitness is not greater than the degree of fitness threshold, for at least one candidate means of transport, except the target means of transport, randomly selecting a means of transport from the remaining means of transport as a new target means of transport; returning to the step of inputting the cargo weight, cargo volume, upper limit value of the load and upper limit value of the volume of the target means of transport into the trained genetic model, and continuing to execute until the degree of fitness is greater than the degree of fitness threshold.

[0063] Optionally, when the degree of compatibility between all candidate transport vehicles and the target waybill is not greater than a compatibility threshold, the candidate transport vehicle with the greatest degree of compatibility is determined as the transport vehicle for finally transporting the goods corresponding to the target waybill.

[0064] In this embodiment, the final transportation plan is determined by comparing the fitness degree with the fitness degree threshold for multiple times, so that the determined transportation plan is more reasonable.

[0065] In some embodiments, the fitness is output by the trained genetic model based on the difference between the upper limit value of the target transportation vehicle and the weight of the cargo, and the difference between the upper limit value of the capacity of the target transportation vehicle and the volume of the cargo.

[0066] Optionally, the calculation formula of the fitness is as follows:

[0067]

[0068] In the formula, For the degree of fit, is the cargo weight, is the upper load limit, is the cargo volume, The upper limit of volume.

[0069] In this embodiment, the degree of adaptation is determined based on the difference between the upper limit of the load of the target transport and the weight of the cargo, and the difference between the upper limit of the volume of the target transport and the volume of the cargo, so that the determined degree of adaptation is more accurate.

[0070] In some embodiments, the training process of the genetic model includes: obtaining the sample cargo weight and sample cargo volume corresponding to the sample waybill, and the sample load upper limit value and sample volume upper limit value corresponding to the sample transport vehicle, and obtaining the sample fitness between the sample waybill and the sample transport vehicle; inputting the sample cargo weight, sample cargo volume, sample load upper limit value, sample volume upper limit value and sample fitness into the pre-trained genetic model, and outputting the loss value; for each training round, when the corresponding training number of the training round reaches the preset number of times, or the loss value is within the preset loss value range, the genetic model obtained in the training round is determined as the trained genetic model.

[0071] Optionally, before training the genetic model, the values ​​of the model parameters need to be set. For example, in order to balance the diversity of the initial solution and the computational efficiency, the population size is set to 80, in order to ensure the high frequency exchange of the parent's excellent genes, the crossover probability is set to 0.8, in order to prevent the model from converging prematurely, the mutation probability is set to 0.03, and in order to promote the stable convergence of the algorithm, the number of iterations is set to 200.

[0072] Optionally, the training process of the genetic model is as follows: after the sample cargo weight, sample cargo volume, sample load upper limit value, sample volume upper limit value and sample fitness are input into the genetic model before training, the model will calculate multiple initial fitness degrees; then the selection operation is performed, using the tournament strategy, setting 5 individuals in each group, randomly grouping from the initial solution set, and selecting the best fitness solution for each group to enter the next generation population until the population size is reached; then the crossover and mutation operations are implemented, and the parents are selected from the contemporary excellent individuals during the crossover, and each pair randomly determines the crossover point. After exchanging the crossover point, the gene sequence is obtained to obtain the offspring to integrate the advantages. During the mutation, the offspring generates a random decimal, which is triggered when it is less than 0.03, and the transportation tool is re-selected from a variety of sample transportation tools to replace the original recommendation to prevent local optimality; finally, the population is updated and convergence detected, the offspring replaces part of the parents to update the population and start a new iteration, and the fitness changes between the contemporary and previous generations are checked in each round, and convergence is determined when 200 iterations are reached or the loss value change is less than the threshold.

[0073] In this embodiment, by training the genetic model, the degree of fit between the target waybill and the target means of transport determined based on the genetic model is made more accurate.

[0074] In one embodiment, Figure 3 As shown, another method for transporting goods is provided, which includes the following:

[0075] (1) Capture the weight and volume data of the waybill and summarize the vehicle model capacity and load parameters. Organize the collected scattered data according to unified standards and build a structured data set.

[0076] (2) Set the algorithm parameters. Set the population size to 80 to balance the diversity of the initial solution and computational efficiency. Set the crossover probability to 0.8 to ensure high-frequency exchange of excellent genes from the parent generation. Set the mutation probability to 0.03 to moderately introduce new features to prevent premature convergence. Set the number of iterations to 200 to promote stable convergence of the algorithm.

[0077] (3) For each combination of waybill and candidate vehicle model, calculate the absolute value of the difference between the waybill weight and the vehicle model load, as well as the absolute value of the difference between the waybill volume and the vehicle model capacity. Assume that the waybill weight is , vehicle load is , the volume of the waybill is , the vehicle volume is , then the basic fitness The calculation formula is: From the pre-processed waybill data set and vehicle model database, extract the weight and volume of each waybill, as well as the load and capacity data of each candidate vehicle model in order, substitute the corresponding values ​​into the formula, and calculate the basic compatibility value of each waybill-vehicle combination. The smaller this value is, the higher the compatibility between the waybill and the vehicle model at the physical space level.

[0078] (4) Set the load constraint condition, create a judgment function, set two input parameters, which are used to receive the waybill weight value and the vehicle model load limit value respectively. A simple comparison is performed inside the function: if the vehicle model load limit is greater than or equal to the waybill weight, it returns "True", which means that the corresponding waybill-vehicle combination meets the load constraint; otherwise, it returns "False". For the volume constraint condition, a similar processing method is used as the load constraint. A judgment function is created, and the input parameters are set as the waybill volume value and the vehicle model volume limit value. Inside the function, when the vehicle model volume limit is not less than the waybill volume, it returns "True", and if it is not satisfied, it returns "False". Then, all waybill-vehicle combinations are traversed one by one through a loop, and the waybill volume and vehicle model volume data in each set of data are input into this volume judgment function, and those combinations that return "False" are filtered out.

[0079] (5) Take the first waybill from the waybill dataset, prepare an empty list for storing the preliminary plan, and start the process. For each waybill, traverse the vehicle model database, compare the load and volume, select the suitable vehicle model to form a candidate list, use the random number tool to randomly select a vehicle model in its index, complete the current waybill matching, return to the waybill dataset to take the next waybill, and loop through all waybill processing to obtain a complete set of initial plans.

[0080] (6) Take the first solution from the initial vehicle model recommendation solution set and prepare a temporary storage area. Split the solution to obtain the waybill and vehicle model information, and substitute them into the load and volume constraint judgment functions respectively. If both return "True", it is qualified and proceed to the next one; if there is "False", it is unqualified. For unqualified solutions, return to the corresponding waybill, eliminate the recommended models that do not meet the requirements based on the previous candidate models, and return to the initial random solution generation process. If there is no option, re-traverse the database to screen and extract. Process each solution in sequence until all solutions pass the verification to ensure that the initial solution set is feasible.

[0081] (7) The fitness of each waybill-vehicle pairing in the initial solution set is evaluated, and it is substituted into the basic fitness formula in turn to calculate the corresponding fitness value. The higher the fitness, the lower the value. Then, the selection operation is performed, using the tournament strategy, setting 5 individuals in each group, and randomly grouping them from the initial solution set. The best fitness solution in each group is selected to enter the next generation population until the population size is reached. Then, crossover and mutation operations are performed. During crossover, the parent generation is selected from the contemporary excellent individuals. Each pair randomly determines the crossover point. After exchanging the crossover point, the gene sequence is obtained to obtain the offspring to integrate the advantages. During mutation, the offspring generates a random decimal. If it is less than 0.03, it is triggered to reselect the vehicle model from the vehicle model library to replace the original recommendation to prevent local optimality. Finally, the population is updated and convergence detection is performed. The offspring replaces part of the parents to update the population and start a new iteration. Each round checks the fitness change between the contemporary and previous generations. Convergence is determined when 200 iterations are reached or the change is less than the threshold.

[0082] (8) Finally, the optimal solution is derived. After the algorithm converges, the solution with the lowest fitness is found in the final population, the recommended vehicle model is displayed, and the vehicle model trial calculation is completed.

[0083] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0084] Based on the same inventive concept, the embodiment of the present application also provides a cargo transportation device for implementing the cargo transportation method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more cargo transportation device embodiments provided below can refer to the limitations on the cargo transportation method above, and will not be repeated here.

[0085] In an exemplary embodiment, Figure 4 As shown, a cargo transportation device 400 is provided, comprising: an acquisition module 401, a determination module 402, a selection module 403 and a control module 404, wherein:

[0086] The acquisition module 401 is used to acquire the cargo weight and cargo volume corresponding to the target waybill from the waybill data set, and acquire the corresponding upper load limit value and upper volume limit value of each of the multiple means of transport.

[0087] The determination module 402 is used to determine, for each transport means, a transport means as a candidate transport means when the upper limit value of the load is not less than the weight of the goods and the upper limit value of the volume is not less than the volume of the goods.

[0088] The selection module 403 is used to randomly select a target transport tool from at least one candidate transport tool obtained, input the cargo weight, cargo volume, upper limit value of the load and upper limit value of the volume of the target transport tool into the trained genetic model, and output the fitness between the target waybill and the target transport tool.

[0089] The control module 404 is used to control the target transportation tool to transport the goods corresponding to the target waybill when the fitness is greater than the fitness threshold.

[0090] In some embodiments, the waybill data set includes the cargo weights and cargo volumes corresponding to multiple initial waybills; the cargo transportation device 400 is specifically used to obtain the latest allowed time corresponding to the transportation start time of each initial waybill; sort the multiple initial waybills in order from the latest allowed time from front to back; and determine the first initial waybill in the sorting result as the target waybill.

[0091] In some embodiments, the cargo transportation device 400 is also used to determine the first initial waybill located after the target waybill in the sorting result as a new target waybill; return to the step of obtaining the cargo weight and cargo volume corresponding to the target waybill from the waybill data set, and continue to execute until the cargo corresponding to all initial waybills has been transported.

[0092] In some embodiments, the cargo transport device 400 is also used to randomly select a transport tool from the remaining transport tools other than the target transport tool among at least one candidate transport tool as a new target transport tool when the fitness is not greater than the fitness threshold; return to the step of inputting the cargo weight, cargo volume, upper limit value of the load and upper limit value of the volume of the target transport tool into the trained genetic model, and continue to execute until the fitness is greater than the fitness threshold.

[0093] In some embodiments, the cargo transport device 400 is also used for the fitness output by the trained genetic model based on the difference between the load upper limit value of the target transport vehicle and the cargo weight, and the difference between the volume upper limit value of the target transport vehicle and the cargo volume.

[0094] In some embodiments, the cargo transport device 400 is also used to obtain the sample cargo weight and sample cargo volume corresponding to the sample waybill, and the sample load upper limit value and sample volume upper limit value corresponding to the sample transport vehicle, and obtain the sample fitness between the sample waybill and the sample transport vehicle; the sample cargo weight, sample cargo volume, sample load upper limit value, sample volume upper limit value and sample fitness are input into the pre-trained genetic model, and the loss value is output; for each training round, when the corresponding training number of the training round reaches the preset number of times, or the loss value is within the preset loss value range, the genetic model obtained in the training round is determined as the trained genetic model.

[0095] Each module in the above cargo transport device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0096] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 5As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a method for transporting goods is implemented.

[0097] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0098] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: obtaining the cargo weight and cargo volume corresponding to a target waybill from a waybill data set, and obtaining the corresponding upper limit value of the load and upper limit value of the volume for each of a plurality of means of transport; for each means of transport, when the upper limit value of the load is not less than the cargo weight, and the upper limit value of the volume is not less than the cargo volume, determining the means of transport as a candidate means of transport; randomly selecting a target means of transport from at least one obtained candidate means of transport, inputting the cargo weight, cargo volume, upper limit value of the load and upper limit value of the volume of the target means of transport into a trained genetic model, and outputting the degree of fitness between the target waybill and the target means of transport; when the degree of fitness is greater than a fitness threshold, controlling the target means of transport to transport the cargo corresponding to the target waybill.

[0099] In one embodiment, the waybill data set implemented when the processor executes the computer program includes the cargo weights and cargo volumes corresponding to multiple initial waybills; the process of determining the target waybill includes: for the transportation start time of each initial waybill, obtaining the latest allowed time corresponding to the transportation start time; sorting the multiple initial waybills in order from the latest allowed time from front to back; and determining the first initial waybill in the sorting result as the target waybill.

[0100] In one embodiment, the processor executes a computer program to control the target transport vehicle to transport the goods corresponding to the target waybill when the degree of fitness is greater than a fitness threshold, and further includes: determining the first initial waybill after the target waybill in the sorting result as a new target waybill; returning to the step of obtaining the weight and volume of the goods corresponding to the target waybill from the waybill data set, and continuing to execute until the goods corresponding to all initial waybills are transported.

[0101] In one embodiment, the method implemented when the processor executes the computer program also includes: when the fitness is not greater than the fitness threshold, for at least one candidate means of transport, excluding the target means of transport, randomly selecting a means of transport from the remaining means of transport as a new target means of transport; returning to the step of inputting the cargo weight, cargo volume, upper limit value of the load and upper limit value of the volume of the target means of transport into the trained genetic model, and continuing to execute until the fitness is greater than the fitness threshold.

[0102] In one embodiment, the fitness achieved by the processor when executing the computer program is output by the trained genetic model based on the difference between the upper limit value of the load of the target transportation vehicle and the weight of the cargo, and the difference between the upper limit value of the volume of the target transportation vehicle and the volume of the cargo.

[0103] In one embodiment, the training process of the genetic model implemented when the processor executes the computer program includes: obtaining the sample cargo weight and sample cargo volume corresponding to the sample waybill, and the sample load upper limit value and sample volume upper limit value corresponding to the sample transport vehicle, and obtaining the sample fitness between the sample waybill and the sample transport vehicle; inputting the sample cargo weight, sample cargo volume, sample load upper limit value, sample volume upper limit value and sample fitness into the pre-trained genetic model, and outputting the loss value; for each training round, when the number of training times corresponding to the training round reaches a preset number of times, or the loss value is within a preset loss value range, the genetic model obtained in the training round is determined as the trained genetic model.

[0104] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: obtaining the cargo weight and cargo volume corresponding to the target waybill from the waybill data set, and obtaining the corresponding upper limit value of the load and upper limit value of the volume for each of a plurality of means of transport; for each means of transport, when the upper limit value of the load is not less than the cargo weight, and the upper limit value of the volume is not less than the cargo volume, the means of transport is determined as a candidate means of transport; a target means of transport is randomly selected from at least one obtained candidate means of transport, the cargo weight, cargo volume, upper limit value of the load and upper limit value of the volume of the target means of transport are input into the trained genetic model, and the degree of fitness between the target waybill and the target means of transport is output; when the degree of fitness is greater than a fitness threshold, the target means of transport is controlled to transport the cargo corresponding to the target waybill.

[0105] In one embodiment, the waybill data set implemented when the computer program is executed by the processor includes the cargo weights and cargo volumes corresponding to multiple initial waybills; the process of determining the target waybill includes: for the transportation start time of each initial waybill, obtaining the latest allowed time corresponding to the transportation start time; sorting the multiple initial waybills in order from the latest allowed time from front to back; and determining the first initial waybill in the sorting result as the target waybill.

[0106] In one embodiment, the computer program implemented when executed by the processor controls the target transport vehicle to transport the goods corresponding to the target waybill when the degree of fitness is greater than the degree of fitness threshold, and also includes: determining the first initial waybill located after the target waybill in the sorting result as the new target waybill; returning to the step of obtaining the goods weight and cargo volume corresponding to the target waybill from the waybill data set, and continuing to execute until the goods corresponding to all initial waybills are transported.

[0107] In one embodiment, the method implemented when the computer program is executed by the processor also includes: when the fitness is not greater than the fitness threshold, for at least one candidate means of transport, excluding the target means of transport, randomly selecting a means of transport from the remaining means of transport as a new target means of transport; returning to the step of inputting the cargo weight, cargo volume, upper limit value of the load and upper limit value of the volume of the target means of transport into the trained genetic model, and continuing to execute until the fitness is greater than the fitness threshold.

[0108] In one embodiment, the fitness achieved when the computer program is executed by the processor is output by the trained genetic model based on the difference between the upper limit of the target transport vehicle's load and the cargo weight, and the difference between the upper limit of the target transport vehicle's capacity and the cargo volume.

[0109] In one embodiment, the training process of the genetic model implemented when the computer program is executed by the processor includes: obtaining the sample cargo weight and sample cargo volume corresponding to the sample waybill, and the sample load upper limit value and sample volume upper limit value corresponding to the sample transport vehicle, and obtaining the sample fitness between the sample waybill and the sample transport vehicle; inputting the sample cargo weight, sample cargo volume, sample load upper limit value, sample volume upper limit value and sample fitness into the pre-trained genetic model, and outputting the loss value; for each training round, when the corresponding number of training times of the training round reaches the preset number of times, or the loss value is within the preset loss value range, the genetic model obtained in the training round is determined as the trained genetic model.

[0110] In one embodiment, a computer program product is provided, comprising a computer program, which implements the following steps when executed by a processor: obtaining the cargo weight and cargo volume corresponding to a target waybill from a waybill data set, and obtaining the corresponding upper limit value of the load and upper limit value of the volume for each of a plurality of means of transport; for each means of transport, when the upper limit value of the load is not less than the cargo weight, and the upper limit value of the volume is not less than the cargo volume, determining the means of transport as a candidate means of transport; randomly selecting a target means of transport from at least one obtained candidate means of transport, inputting the cargo weight, cargo volume, upper limit value of the load and upper limit value of the volume of the target means of transport into a trained genetic model, and outputting the degree of fitness between the target waybill and the target means of transport; when the degree of fitness is greater than a fitness threshold, controlling the target means of transport to transport the cargo corresponding to the target waybill.

[0111] In one embodiment, the waybill data set implemented when the computer program is executed by the processor includes the cargo weights and cargo volumes corresponding to multiple initial waybills; the process of determining the target waybill includes: for the transportation start time of each initial waybill, obtaining the latest allowed time corresponding to the transportation start time; sorting the multiple initial waybills in order from the latest allowed time from front to back; and determining the first initial waybill in the sorting result as the target waybill.

[0112] In one embodiment, the computer program implemented when executed by the processor controls the target transport vehicle to transport the goods corresponding to the target waybill when the degree of fitness is greater than the degree of fitness threshold, and also includes: determining the first initial waybill located after the target waybill in the sorting result as the new target waybill; returning to the step of obtaining the goods weight and cargo volume corresponding to the target waybill from the waybill data set, and continuing to execute until the goods corresponding to all initial waybills are transported.

[0113] In one embodiment, the method implemented when the computer program is executed by the processor also includes: when the fitness is not greater than the fitness threshold, for at least one candidate means of transport, excluding the target means of transport, randomly selecting a means of transport from the remaining means of transport as a new target means of transport; returning to the step of inputting the cargo weight, cargo volume, upper limit value of the load and upper limit value of the volume of the target means of transport into the trained genetic model, and continuing to execute until the fitness is greater than the fitness threshold.

[0114] In one embodiment, the fitness achieved when the computer program is executed by the processor is output by the trained genetic model based on the difference between the upper limit of the target transport vehicle's load and the cargo weight, and the difference between the upper limit of the target transport vehicle's capacity and the cargo volume.

[0115] In one embodiment, the training process of the genetic model implemented when the computer program is executed by the processor includes: obtaining the sample cargo weight and sample cargo volume corresponding to the sample waybill, and the sample load upper limit value and sample volume upper limit value corresponding to the sample transport vehicle, and obtaining the sample fitness between the sample waybill and the sample transport vehicle; inputting the sample cargo weight, sample cargo volume, sample load upper limit value, sample volume upper limit value and sample fitness into the pre-trained genetic model, and outputting the loss value; for each training round, when the corresponding number of training times of the training round reaches the preset number of times, or the loss value is within the preset loss value range, the genetic model obtained in the training round is determined as the trained genetic model.

[0116] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0117] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0118] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0119] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A cargo transportation method, characterized in that: The method comprises: Obtain the cargo weight and cargo volume corresponding to the target waybill from the waybill data set, and obtain the corresponding upper load limit and upper volume limit of each of the multiple means of transport; For each transport means, if the upper limit value of the load is not less than the weight of the cargo, and the upper limit value of the volume is not less than the volume of the cargo, the transport means is determined as a candidate transport means; Randomly select a target transport tool from the obtained at least one candidate transport tool, input the cargo weight, cargo volume, upper limit value of the load and upper limit value of the volume of the target transport tool into the trained genetic model, and output the degree of fit between the target waybill and the target transport tool; When the degree of fitness is greater than a threshold value of the degree of fitness, the target transportation vehicle is controlled to transport the goods corresponding to the target waybill.

2. The method according to claim 1, characterized in that The waybill data set includes the cargo weight and cargo volume corresponding to a plurality of initial waybills; the process of determining the target waybill includes: For each initial waybill's transportation start time, obtain the latest allowed time corresponding to the transportation start time; Sorting the multiple initial waybills in order from the latest allowed time; The first initial waybill in the sorting result is determined as the target waybill.

3. The method according to claim 2, characterized in that After controlling the target transport vehicle to transport the goods corresponding to the target waybill when the degree of fitness is greater than the degree of fitness threshold, the method further includes: Determine the first initial waybill after the target waybill in the sorting result as a new target waybill; Return to the step of obtaining the cargo weight and cargo volume corresponding to the target waybill from the waybill data set, and continue to execute until all the cargo corresponding to the initial waybill has been transported.

4. The method according to claim 1, characterized in that: The method further comprises: When the fitness degree is not greater than the fitness degree threshold, for the remaining transportation means in the at least one candidate transportation means except the target transportation means, randomly select a transportation means from the remaining transportation means as a new target transportation means; Return to the step of inputting the cargo weight, the cargo volume, the upper limit value of the load and the upper limit value of the volume of the target transportation vehicle into the trained genetic model, and continue to execute until the fitness is greater than the fitness threshold.

5. The method according to claim 1, characterized in that: The fitness degree is output by the trained genetic model based on the difference between the upper limit value of the load of the target transportation vehicle and the weight of the cargo, and the difference between the upper limit value of the volume of the target transportation vehicle and the volume of the cargo.

6. The method according to claim 1, characterized in that The training process of the genetic model includes: Obtain the sample cargo weight and sample cargo volume corresponding to the sample waybill, as well as the sample load upper limit value and sample volume upper limit value corresponding to the sample transport vehicle, and obtain the sample compatibility between the sample waybill and the sample transport vehicle; Input the sample cargo weight, the sample cargo volume, the sample load upper limit value, the sample volume upper limit value and the sample fitness into the pre-trained genetic model, and output the loss value; For each training round, when the number of training times corresponding to the training round reaches a preset number of times, or the loss value is within a preset loss value range, the genetic model obtained in the training round is determined as the trained genetic model.

7. A cargo transport device, characterized in that: The device comprises: An acquisition module is used to obtain the cargo weight and cargo volume corresponding to the target waybill from the waybill data set, and obtain the corresponding upper load limit value and upper volume limit value of each of the multiple means of transport; a determination module, configured to determine, for each transport means, the transport means as a candidate transport means when the upper limit value of the load is not less than the weight of the goods and the upper limit value of the volume is not less than the volume of the goods; A selection module is used to randomly select a target transport tool from the obtained at least one candidate transport tool, input the cargo weight, the cargo volume, the upper limit value of the load and the upper limit value of the volume of the target transport tool into the trained genetic model, and output the fitness between the target waybill and the target transport tool; The control module is used to control the target transportation tool to transport the goods corresponding to the target waybill when the fitness is greater than the fitness threshold.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images