Logistics transportation cost management intelligent optimization system and method

Abstract

The invention discloses an intelligent optimization system and method for logistics transportation cost management, and relates to the technical field of intelligent logistics management, and the system comprises a data collection and analysis module which is responsible for collecting basic data of goods and analyzing the data; the constraint condition and transportation characteristic analysis module analyzes the characteristics of various constraint conditions and actual transportation environments in the cargo transportation process; the initial loading scheme generation module is responsible for generating an initial loading scheme according to characteristics and constraint conditions of goods; when an initial loading scheme is generated, three heuristic methods of first adaptation, optimal adaptation and worst adaptation are adopted, historical data are combined to guide generation of the scheme, and meanwhile, a genetic algorithm and a simulated annealing algorithm are introduced to further optimize the scheme, so that an approximate optimal solution is efficiently searched in a solution space.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent logistics management, and in particular to an intelligent optimization system and method for logistics transportation cost management. Background Art

[0002] Logistics and transportation cost management is an important part of logistics enterprises to improve economic benefits and enhance market competitiveness. With the development of information technology and artificial intelligence technology, intelligent optimization methods play an increasingly important role in logistics and transportation cost management. By using a logistics and transportation cost management system, it can not only help enterprises reduce logistics costs and improve service levels, but also enhance the market competitiveness of enterprises and promote the healthy and sustainable development of the logistics industry.

[0003] At present, a single heuristic method is often used to generate the initial loading plan, which will result in the generated initial plan often not being diverse enough and lacking adaptability to different scenarios and needs, which in turn leads to insufficient quality of the final solution, making the loading plan not optimal in practical applications. Therefore, we propose an intelligent optimization system and method for logistics transportation cost management to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide a logistics transportation cost management intelligent optimization system and method to solve the current market problems raised by the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An intelligent optimization system for logistics and transportation cost management, comprising:

[0007] The data collection and analysis module is responsible for collecting basic data of goods and analyzing the data;

[0008] The constraint condition and transportation characteristic analysis module analyzes various constraint conditions in the cargo transportation process and the characteristics of the actual transportation environment;

[0009] The initial loading plan generation module is responsible for generating a preliminary loading plan based on the characteristics and constraints of the cargo;

[0010] The evaluation function design module is used to quantify the quality of the loading scheme;

[0011] The genetic algorithm optimization module is used to optimize the loading scheme;

[0012] The simulated annealing algorithm optimization module is used to perform further local search based on the genetic algorithm optimization;

[0013] The termination condition and result output module is used to set the termination conditions of the optimization process and stop the iteration when these conditions are met.

[0014] A method for intelligent optimization of logistics transportation cost management, comprising the following steps:

[0015] S1: Design the system architecture for data collection, use sensors and scanning equipment to collect the size, weight, shape and type of goods, and analyze the fragility, moisture resistance requirements, stacking restrictions, temperature requirements, dangerousness, expiration date, and value of the goods;

[0016] S2: Constrain the shape and size of goods, cargo weight, stacking rules, loading and unloading efficiency, space utilization, safety, and compatibility to maximize the loading rate and minimize the loading time to solve the problem, and determine the transportation characteristics of actual transportation in road conditions, bridges and tunnels, and traffic conditions;

[0017] S3: Generate the initial solution through first adaptation, best adaptation, and worst adaptation. Each method places the goods according to the order of the goods and the remaining space in the carriage, thereby generating different loading schemes. Before using the heuristic method, the cargo list is first randomly sorted to increase the diversity of the initial population. When historical loading data is available, the historical loading data is used to guide the generation of the initial loading scheme. After the initial solution is generated using the heuristic method, the loading scheme is randomly perturbed, that is, the positions of two goods are randomly exchanged or the direction of a certain cargo is randomly adjusted. For the loading of multiple carriages, different carriage allocation strategies are first considered when generating the initial population. The initial loading scheme is generated using the metaheuristic method, and rules are designed to guide the generation of the initial loading scheme.

[0018] S4: Design an evaluation function to satisfy the loading rate, loading time and satisfaction of all constraints in step S3. The higher the loading rate, the higher the evaluation score; the shorter the loading time, the higher the evaluation score. If the constraints are violated, a corresponding penalty score is given;

[0019] S5: Select excellent individuals to enter the next generation according to the evaluation function, randomly select two individuals, generate new loading plans through crossover strategy, ensure that the crossover plan still meets all constraints, perform targeted mutations on some parts of the individuals considering the characteristics and constraints of the goods, and verify the constraints of the newly generated loading plan;

[0020] S6: Set a suitable initial temperature. Under the current temperature, randomly perturb the loading scheme generated by the genetic algorithm by randomly exchanging the positions of goods, randomly adjusting the placement direction of goods, and randomly increasing or decreasing the number of goods. The degree of perturbation does not destroy the structure of the solution. Use the Metropolis criterion to decide whether to accept the new loading scheme. When the new scheme is better than the current one, accept the new scheme. When the new scheme is worse, decide whether to accept the new scheme based on the temperature and a randomly generated acceptance probability. The acceptance probability is inversely proportional to the temperature, that is, the greater the probability of accepting a worse solution, the greater the probability of accepting a worse solution. As the iteration proceeds, the temperature is gradually lowered. The termination condition is that the preset minimum temperature is reached, there is no obvious improvement after multiple consecutive iterations, or the preset number of iterations is reached.

[0021] S7: The termination condition is that the loading time exceeds the preset time limit. The selection, crossover, mutation operations of the genetic algorithm and the local search of the simulated annealing algorithm are repeatedly executed until the set termination condition is met. When the termination condition is met, the iteration is stopped, and the final recorded optimal loading plan and the corresponding loading rate and loading time are output.

[0022] As a further optimization scheme of the present invention, in step S1, the scanning device includes a 3D scanner, a weighing sensor, and a barcode scanner. The sensors are integrated into the logistics system. When the goods enter the logistics process, the sensors automatically collect relevant size and weight information, and use a barcode scanner or radio frequency identification to collect the type and identity information of the goods. The collected data is transmitted to the central data processing system in real time through a wireless network, and the data is encrypted using encryption and fault-tolerant technology.

[0023] As a further optimization scheme of the present invention, in step S3, all the goods to be loaded are first randomly sorted. After the initial solution is generated, the positions of two goods are randomly exchanged or the direction of a certain goods is randomly adjusted. For loading problems involving multiple carriages, different carriage allocation strategies are considered when generating the initial population. First, the goods are evenly distributed to each carriage, and then optimized and adjusted according to the characteristics of the goods and the remaining space in the carriage.

[0024] As a further optimization scheme of the present invention, in step S4, the evaluation function uses the loading rate, loading time, and satisfaction of the constraints as evaluation indicators to give an overall score for the loading scheme. A nonlinear function is used to quantify the impact of the loading rate and loading time on the evaluation score. The shorter the loading time, the more linearly the evaluation score increases. The satisfaction of the constraints is processed by a penalty function. When the loading scheme violates the constraints, a penalty score is given.

[0025] As a further optimization scheme of the present invention, in step S5, two excellent individuals are randomly selected as parent individuals, and a new loading scheme is generated through a crossover strategy. The intersection point is selected based on the characteristics and constraints of the goods, and it is ensured that the scheme after the crossover still satisfies all loading constraints. The constraint satisfaction of the newly generated loading scheme is verified, and it is ensured that the new scheme does not violate any loading constraints. After the iteration is completed, all generated loading schemes are finally evaluated, and the optimal loading scheme is selected as the output.

[0026] As a further optimization scheme of the present invention, in step S6, when the new solution is poor, it is decided whether to accept the new solution based on the temperature and a randomly generated acceptance probability. The acceptance probability is defined as exp(-ΔE / T), where ΔE is the difference of the evaluation function and T is the current temperature. When the temperature is higher, the poorer solution can be accepted.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] When generating the initial loading plan, the present invention adopts three heuristic methods, namely first adaptation, best adaptation and worst adaptation, and combines historical data to guide the generation of the plan. At the same time, it also introduces genetic algorithm and simulated annealing algorithm to further optimize the plan, so as to efficiently search for the approximate optimal solution in the solution space.

[0029] The present invention combines the genetic algorithm and the simulated annealing algorithm, giving full play to the advantages of both in global search and local search, helping to avoid falling into the local optimum and improving the quality and stability of the solution.

[0030] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is a module block diagram of the intelligent optimization system for logistics and transportation cost management of the present invention;

[0032] Figure 2 It is a flowchart of S4 in the intelligent optimization method for logistics transportation cost management of the present invention;

[0033] Figure 3 It is a flowchart of S5 in the intelligent optimization method for logistics transportation cost management of the present invention;

[0034] Figure 4 It is a flowchart of S6 in the intelligent optimization method for logistics transportation cost management of the present invention;

[0035] Figure 5 It is a flowchart of S7 in the intelligent optimization method for logistics transportation cost management of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] Embodiment 1

[0038] See also Figure 1-Figure 5 , a logistics transportation cost management intelligent optimization system, comprising:

[0039] The data collection and analysis module is responsible for collecting basic data of goods and analyzing the data;

[0040] The constraint condition and transportation characteristic analysis module analyzes various constraint conditions in the cargo transportation process and the characteristics of the actual transportation environment;

[0041] The initial loading plan generation module is responsible for generating a preliminary loading plan based on the characteristics and constraints of the cargo;

[0042] The evaluation function design module is used to quantify the quality of the loading scheme;

[0043] The genetic algorithm optimization module is used to optimize the loading scheme;

[0044] The simulated annealing algorithm optimization module is used to perform further local search based on the genetic algorithm optimization;

[0045] The termination condition and result output module is used to set the termination conditions of the optimization process and stop the iteration when these conditions are met.

[0046] A method for intelligent optimization of logistics transportation cost management, comprising the following steps:

[0047] S1: Design the system architecture for data collection, use sensors and scanning equipment to collect the size, weight, shape and type of goods, and analyze the fragility, moisture resistance requirements, stacking restrictions, temperature requirements, dangerousness, expiration date, and value of the goods;

[0048] S2: Constrain the shape and size of goods, cargo weight, stacking rules, loading and unloading efficiency, space utilization, safety, and compatibility to maximize the loading rate and minimize the loading time to solve the problem, and determine the transportation characteristics of actual transportation in road conditions, bridges and tunnels, and traffic conditions;

[0049] S3: Generate the initial solution through first adaptation, best adaptation, and worst adaptation. Each method places the goods according to the order of the goods and the remaining space in the carriage, thereby generating different loading schemes. Before using the heuristic method, the cargo list is first randomly sorted to increase the diversity of the initial population. When historical loading data is available, the historical loading data is used to guide the generation of the initial loading scheme. After the initial solution is generated using the heuristic method, the loading scheme is randomly perturbed, that is, the positions of two goods are randomly exchanged or the direction of a certain cargo is randomly adjusted. For the loading of multiple carriages, different carriage allocation strategies are first considered when generating the initial population. The initial loading scheme is generated using the metaheuristic method, and rules are designed to guide the generation of the initial loading scheme.

[0050] S4: Design an evaluation function to satisfy the loading rate, loading time and satisfaction of all constraints in step S3. The higher the loading rate, the higher the evaluation score; the shorter the loading time, the higher the evaluation score. If the constraints are violated, a corresponding penalty score is given;

[0051] S5: Select excellent individuals to enter the next generation according to the evaluation function, randomly select two individuals, generate new loading plans through crossover strategy, ensure that the crossover plan still meets all constraints, perform targeted mutations on some parts of the individuals considering the characteristics and constraints of the goods, and verify the constraints of the newly generated loading plan;

[0052] S6: Set a suitable initial temperature. Under the current temperature, randomly perturb the loading scheme generated by the genetic algorithm by randomly exchanging the positions of goods, randomly adjusting the placement direction of goods, and randomly increasing or decreasing the number of goods. The degree of perturbation does not destroy the structure of the solution. Use the Metropolis criterion to decide whether to accept the new loading scheme. When the new scheme is better than the current one, accept the new scheme. When the new scheme is worse, decide whether to accept the new scheme based on the temperature and a randomly generated acceptance probability. The acceptance probability is inversely proportional to the temperature, that is, the greater the probability of accepting a worse solution, the greater the probability of accepting a worse solution. As the iteration proceeds, the temperature is gradually lowered. The termination condition is that the preset minimum temperature is reached, there is no obvious improvement after multiple consecutive iterations, or the preset number of iterations is reached.

[0053] S7: The termination condition is that the loading time exceeds the preset time limit. The selection, crossover, mutation operations of the genetic algorithm and the local search of the simulated annealing algorithm are repeatedly executed until the set termination condition is met. When the termination condition is met, the iteration is stopped, and the final recorded optimal loading plan and the corresponding loading rate and loading time are output.

[0054] In step S1, the scanning equipment includes a 3D scanner, a weighing sensor, and a barcode scanner. The sensors are integrated into the logistics system. When the goods enter the logistics process, the sensors automatically collect relevant size and weight information. The type and identity information of the goods are collected using a barcode scanner or radio frequency identification. The collected data is transmitted to the central data processing system in real time through a wireless network, and the data is encrypted using encryption and fault-tolerant technology.

[0055] Specifically, determine the fragility of the goods based on the type of goods and packaging method, and give special protection during loading. For goods that need to be moisture-proof, analyze the moisture-proof performance of their packaging materials, as well as the necessary storage conditions. Determine the height and method of stacking the goods based on their shape, size, and weight to prevent damage to the goods during transportation. For goods such as food and medicine that require temperature control, clarify their temperature range during transportation and storage. For dangerous or flammable goods, assess their dangers and develop corresponding safety measures. For time-sensitive goods such as food and chemicals, check their production date and expiration date to ensure that they will not expire during transportation. Assess the value of the goods based on information such as the type, brand, and market price of the goods, so that more protection can be given to high-value goods during loading.

[0056] In step S2, the goods are classified according to the shape and size data of the goods collected in step S1, and corresponding stacking rules are formulated for goods of different shapes. The space layout in the carriage is planned according to the size of the goods to maximize the space utilization. The stacking order and position of the goods are arranged according to the weight information of the goods, and stacking rules are formulated so that there is enough support and spacing between the goods, considering the loading and unloading speed of the goods, optimizing the loading and unloading process, and reducing unnecessary waiting time. For dangerous goods or flammable goods, additional safety measures are taken to isolate and fix them, consider the compatibility between the goods, avoid chemical reactions or mutual contamination, and reasonably divide different types of goods to ensure the safety of various types of goods during transportation.

[0057] In step S3, all the goods to be loaded are first randomly sorted. After the initial solution is generated, the positions of two goods are randomly exchanged or the direction of a certain goods is randomly adjusted. For loading problems involving multiple carriages, different carriage allocation strategies are considered when generating the initial population. First, the goods are evenly distributed to each carriage, and then optimized and adjusted according to the characteristics of the goods and the remaining space in the carriage.

[0058] Specifically, for the first adaptation, each cargo is placed in the first compartment that can accommodate it in the order of the cargo. For the best adaptation, for each cargo, all compartments are searched to find the compartment with the smallest remaining space that can accommodate the cargo for loading. For the worst adaptation, contrary to the best adaptation, the compartment with the largest remaining space is selected first to load the cargo, avoiding filling up a compartment too early, thus providing more loading options for subsequent cargo.

[0059] In step S4, the evaluation function uses the loading rate, loading time, and satisfaction of constraints as evaluation indicators to give an overall score for the loading plan. A nonlinear function is used to quantify the impact of the loading rate and loading time on the evaluation score. The shorter the loading time, the more linearly the evaluation score increases. The satisfaction of the constraints is processed through a penalty function. When the loading plan violates the constraints, a penalty score is given.

[0060] Specifically, the loading rate refers to the ratio of the volume or weight of the goods actually loaded to the total capacity or load of the carriage. The higher the loading rate, the higher the space utilization rate, which is an indicator for evaluating the quality of the loading plan. The loading time refers to the total time required to complete the loading of all goods. The shorter the loading time, the higher the loading efficiency, which is conducive to improving the overall logistics efficiency. As for the satisfaction of the constraint conditions, the satisfaction of all the constraint conditions defined in step S3 is also an important indicator for evaluating the loading plan.

[0061] Different weights are assigned to the loading rate, loading time and the satisfaction of the constraint conditions. When the loading rate is important, the loading rate is given a higher weight; when the loading time is more important, the loading time is given a higher weight. The weight distribution is determined by the hierarchical analysis method.

[0062] For each loading scheme, calculate its loading rate and loading time. Check whether the loading scheme meets all constraints and record the violations. Use the evaluation function to calculate the evaluation score of each loading scheme. Sort all loading schemes according to the evaluation score and select the best loading scheme as the starting point for subsequent optimization.

[0063] In step S4, the evaluation function is:

[0064] Evaluation score = (loading rate score) + (loading time score) - (constraint penalty score)

[0065] Among them: loading rate score = w1*loading rate, w1 is the weight coefficient of the loading rate, the higher the loading rate, the higher the score.

[0066] Loading time score = w2*(1-actual loading time / expected loading time), where w2 is the weight coefficient of loading time. The shorter the loading time, the higher the score.

[0067] Constraint penalty score = Σ(wi*violation degree of constraint i), wi is the weight coefficient of each constraint. If the plan violates a constraint, a corresponding penalty score will be given according to the degree of violation.

[0068] By adjusting the weight coefficients w1, w2 and wi, a trade-off is made between the loading rate, loading time and constraint satisfaction to reflect the actual needs in different scenarios.

[0069] In step S5, two excellent individuals are randomly selected as parent individuals, and a new loading plan is generated through a crossover strategy. The intersection point is selected based on the characteristics and constraints of the goods, and it is ensured that the plan after the crossover still meets all loading constraints. The constraint satisfaction of the newly generated loading plan is verified, and it is ensured that the new plan does not violate any loading constraints. After the iteration, all generated loading plans are finally evaluated and the optimal loading plan is selected as the output.

[0070] Specifically, fitness proportional selection: the probability of selection of an individual is proportional to its fitness.

[0071] Selection probability formula:

[0072] Where P i is the probability of the i-th individual being selected, f(x i ) is the fitness function value of the ith individual, and N is the population size.

[0073] In step S6, when the new solution is poor, whether to accept the new solution is determined based on the temperature and a randomly generated acceptance probability. The acceptance probability is defined as exp(-ΔE / T), where ΔE is the difference in the evaluation function and T is the current temperature. The higher the temperature, the more acceptable the poorer solution.

[0074] In step S6, the Metropolis criterion:

[0075] Acceptance probability formula:

[0076] Among them, P is the probability of accepting a new solution, ΔE is the energy difference between the new solution and the current solution or the difference in the objective function value, and T is the current temperature. The formula is used to decide whether to accept a worse new solution.

[0077] During the annealing process, the temperature will gradually decrease, and the temperature update formula is:

[0078] T new =α·T old

[0079] Where α is the annealing coefficient, which is used to control the temperature drop rate.

[0080] Energy difference or objective function difference: ΔE = E new -E current

[0081] Where E new is the objective function value of the new solution, E current is the objective function value of the current solution, and the difference is used to calculate the acceptance probability.

[0082] In the local search of the simulated annealing algorithm, when the new solution is worse than the current solution, a probability is used to decide whether to accept the new solution. The probability formula is: P = e -ΔE / T

[0083] Where P is the probability of accepting a new solution, ΔE is the energy difference between the new solution and the current solution, T is the current temperature.

[0084] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0085] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0086] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0087] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0088] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. An intelligent optimization system for logistics and transportation cost management, characterized in that: include: The data collection and analysis module is responsible for collecting basic data of goods and analyzing the data; The constraint condition and transportation characteristic analysis module analyzes various constraint conditions in the cargo transportation process and the characteristics of the actual transportation environment; The initial loading plan generation module is responsible for generating a preliminary loading plan based on the characteristics and constraints of the cargo; The evaluation function design module is used to quantify the quality of the loading scheme; The genetic algorithm optimization module is used to optimize the loading scheme; The simulated annealing algorithm optimization module is used to perform further local search based on the genetic algorithm optimization; The termination condition and result output module is used to set the termination conditions of the optimization process and stop the iteration when these conditions are met.

2. An intelligent optimization method for logistics transportation cost management, characterized in that: The following steps are involved: S1: Design the system architecture for data collection, use sensors and scanning equipment to collect the size, weight, shape and type of goods, and analyze the fragility, moisture resistance requirements, stacking restrictions, temperature requirements, dangerousness, expiration date, and value of the goods; S2: Constrain the shape and size of goods, cargo weight, stacking rules, loading and unloading efficiency, space utilization, safety, and compatibility to maximize the loading rate and minimize the loading time to solve the problem, and determine the transportation characteristics of actual transportation in road conditions, bridges and tunnels, and traffic conditions; S3: Generate the initial solution through first adaptation, best adaptation, and worst adaptation. Each method places the goods according to the order of the goods and the remaining space in the carriage, thereby generating different loading schemes. Before using the heuristic method, the cargo list is first randomly sorted to increase the diversity of the initial population. When historical loading data is available, the historical loading data is used to guide the generation of the initial loading scheme. After the initial solution is generated using the heuristic method, the loading scheme is randomly perturbed, that is, the positions of two goods are randomly exchanged or the direction of a certain cargo is randomly adjusted. For the loading of multiple carriages, different carriage allocation strategies are first considered when generating the initial population. The initial loading scheme is generated using the metaheuristic method, and rules are designed to guide the generation of the initial loading scheme. S4: Design an evaluation function to satisfy the loading rate, loading time and satisfaction of all constraints in step S3. The higher the loading rate, the higher the evaluation score; the shorter the loading time, the higher the evaluation score. If the constraints are violated, a corresponding penalty score is given; S5: Select excellent individuals to enter the next generation according to the evaluation function, randomly select two individuals, generate new loading plans through crossover strategy, ensure that the crossover plan still meets all constraints, perform targeted mutations on some parts of the individuals considering the characteristics and constraints of the goods, and verify the constraints of the newly generated loading plan; S6: Set a suitable initial temperature. Under the current temperature, randomly perturb the loading scheme generated by the genetic algorithm by randomly exchanging the positions of goods, randomly adjusting the placement direction of goods, and randomly increasing or decreasing the number of goods. The degree of perturbation does not destroy the structure of the solution. Use the Metropolis criterion to decide whether to accept the new loading scheme. When the new scheme is better than the current one, accept the new scheme. When the new scheme is worse, decide whether to accept the new scheme based on the temperature and a randomly generated acceptance probability. The acceptance probability is inversely proportional to the temperature, that is, the greater the probability of accepting a worse solution, the greater the probability of accepting a worse solution. As the iteration proceeds, the temperature is gradually lowered. The termination condition is that the preset minimum temperature is reached, there is no obvious improvement after multiple consecutive iterations, or the preset number of iterations is reached. S7: The termination condition is that the loading time exceeds the preset time limit. The selection, crossover, mutation operations of the genetic algorithm and the local search of the simulated annealing algorithm are repeatedly executed until the set termination condition is met. When the termination condition is met, the iteration is stopped, and the final recorded optimal loading plan and the corresponding loading rate and loading time are output.

3. The method for intelligent optimization of logistics transportation cost management according to claim 2 is characterized by: In step S1, the scanning equipment includes a 3D scanner, a weighing sensor, and a barcode scanner. The sensors are integrated into the logistics system. When the goods enter the logistics process, the sensors automatically collect relevant size and weight information. The type and identity information of the goods are collected using a barcode scanner or radio frequency identification. The collected data is transmitted to the central data processing system in real time through a wireless network, and the data is encrypted using encryption and fault-tolerant technology.

4. The method for intelligent optimization of logistics transportation cost management according to claim 2 is characterized by: In step S3, all the goods to be loaded are first randomly sorted. After the initial solution is generated, the positions of two goods are randomly exchanged or the direction of a certain goods is randomly adjusted. For loading problems involving multiple carriages, different carriage allocation strategies are considered when generating the initial population. First, the goods are evenly distributed to each carriage, and then optimized and adjusted according to the characteristics of the goods and the remaining space in the carriage.

5. The method for intelligent optimization of logistics transportation cost management according to claim 2 is characterized by: In step S4, the evaluation function uses the loading rate, loading time, and satisfaction of constraints as evaluation indicators to give an overall score for the loading plan. A nonlinear function is used to quantify the impact of the loading rate and loading time on the evaluation score. The shorter the loading time, the more linearly the evaluation score increases. The satisfaction of the constraints is processed through a penalty function. When the loading plan violates the constraints, a penalty score is given.

6. The method for intelligent optimization of logistics transportation cost management according to claim 2 is characterized by: In step S5, two excellent individuals are randomly selected as parent individuals, and a new loading plan is generated through a crossover strategy. The intersection point is selected based on the characteristics and constraints of the goods, and it is ensured that the plan after the crossover still meets all loading constraints. The constraint satisfaction of the newly generated loading plan is verified, and it is ensured that the new plan does not violate any loading constraints. After the iteration, all generated loading plans are finally evaluated and the optimal loading plan is selected as the output.

7. The method for intelligent optimization of logistics transportation cost management according to claim 2 is characterized by: In step S6, when the new solution is poor, whether to accept the new solution is determined based on the temperature and a randomly generated acceptance probability. The acceptance probability is defined as exp(-ΔE / T), where ΔE is the difference in the evaluation function and T is the current temperature. The higher the temperature, the more acceptable the poorer solution.

Images