Truck packing scheme recommendation system based on dual-stage maximum loading rate

Abstract

The invention discloses a truck boxing scheme recommendation system based on a dual-stage maximum loading rate, which belongs to the technical field of intelligent logistics and freight fleet recommendation systems and comprises a truck information processing module, a cargo management module, a pre-packaging processing module, a loading optimization module and a loading scheme export module. According to the method, the performance is obviously improved in the aspect of lorry loading optimization; the two-stage optimization strategy and the modular design are combined with the innovative genetic algorithm application, so that the system is excellent in performance when processing complex goods and diversified requirements; the method has the advantages of high-efficiency data processing and real-time response capability, user friendliness and transportation cost reduction, so that the method has remarkable advantages in practical application, and multiple problems in the prior art are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of smart logistics and freight fleet recommendation systems, and specifically is a freight fleet solution recommendation system based on maximum loading rate. Background Art

[0002] In modern logistics and transportation industries, cargo loading rate is one of the important factors in transportation cost and efficiency. In order to load as much cargo as possible in a limited space, various loading optimization technologies are widely used. However, traditional loading methods rely on the experience of "experienced people" and simple stacking calculations, which makes it difficult to achieve the maximum space utilization of truck cargo boxes. In addition, the diversity and complexity of cargo further increase the difficulty of loading optimization. Therefore, it is of great significance to develop a system that can automatically and accurately optimize the loading rate of trucks.

[0003] 1. Publicly known technology

[0004] Cargo information processing technology: Users upload truck attributes through a graphical user interface (GUI) or application programming interface (API), including truck dimensions, load factor, price, etc., and store them in a structured manner in a database (MySQL). It is widely used in logistics and transportation management systems.

[0005] Cargo management technology: Cargo management involves the management and storage of cargo information of various types and specifications. The warehouse management system (WMS) uses RFID, barcode scanning and other technologies to automatically identify, record and upload cargo to the system. The database stores detailed cargo information, including cargo size, cargo weight, cargo quantity, etc., and encodes and structures the information.

[0006] Genetic algorithm optimization technology: Genetic algorithm is an optimization algorithm based on natural selection and genetic extremism, which is widely used in complex optimization problems. Its basic operations include population initialization, fitness calculation, selection, crossover and mutation. In the packing optimization of the present invention, the genetic algorithm iteratively optimizes the packing pile combination scheme by simulating the natural selection process to maximize the loading rate. This technology is widely used in the fields of path planning, resource allocation, scheduling and loading optimization.

[0007] 2. Existing Technology

[0008] Patent No. CN202410087427.3

[0009] Technical name: Method, device, electronic device and storage medium for determining the packing scheme of goods Main content: This patent proposes a method and device for determining the packing scheme of goods, which determines the packing scheme of each combination of goods in the packaging box based on the size of the goods, the minimum size of the goods and the size of the packaging box. The method includes: determining at least one Nth packing scheme for each Nth combination of goods in the packaging box; determining the optimal packing scheme based on the number and unit price of the packing schemes. By considering the combination of goods of different sizes, the accuracy of the packing scheme is improved, the calculation process is simplified, and the calculation efficiency is improved.

[0010] Problems and defects: Although this method takes into account the diversity of cargo sizes, it may still not be efficient enough to determine the packing solution when faced with large-scale, multi-type cargo. The preset calculation method may have limitations when dealing with complex constraints, making it difficult to fully optimize the packing rate.

[0011] Patent No. CN201910680870.0

[0012] Technical name: A method and system for generating a packing plan for items in a logistics warehouse Main content: The present invention proposes a method and system for generating a packing plan in a logistics warehouse. The system obtains the three-dimensional size data of all types of boxes and items in an order, and uses a heuristic search algorithm and a genetic algorithm to search for the optimal packing plan. The method includes: according to the three-dimensional size data of the box and the item and the set parameters, for a specific box selection plan, searching for the minimum height and the packing plan that meets the height; and then searching for the optimal packing plan according to preset conditions.

[0013] Existing problems and defects: This method uses heuristic and genetic algorithms. Although it has good flexibility and adaptability, it has high computational complexity and may be inefficient when processing large-scale data. The algorithm has limited ability to process real-time data and is difficult to respond quickly to dynamic changes in the warehouse.

[0014] Patent No. CN202010350085.1

[0015] Technical name: Cargo packing plan output method, device, computer equipment and storage medium Main content: This application proposes a method for outputting cargo packing plans through computer equipment, obtaining the packing order of packing boxes and the order of goods to be packed, and obtaining and adjusting the cargo packing plan through mixed placement point search. The method includes: searching for mixed placement points according to the packing order and preset detection constraint information; adjusting the packing order according to the goods corresponding to the current leaf node packing box to obtain the target packing plan.

[0016] Existing problems and defects: The method mainly focuses on the search for packaging order and placement points. It may be difficult to achieve the optimal packing solution when dealing with complex space constraints and multi-type goods. The computational complexity of mixed placement point search is high, and the system may have deficiencies in real-time performance and response speed.

[0017] Patent No. CN201510602432.4

[0018] Technical name: Three-dimensional packing scheme generation method based on three-step dynamic programming Main content: This patent provides a three-dimensional packing scheme generation method based on three-step dynamic programming, which decomposes the three-dimensional packing problem into three 01 knapsack problems and generates a packing scheme by step-by-step solution. The method includes: decomposing the three-dimensional packing problem into three 01 knapsack problems executed in sequence, optimizing the packing rate and generation speed, improving the utilization rate of container space, and reducing freight costs.

[0019] Problems and defects: Although the dynamic programming algorithm improves the packing rate and speed, its computational complexity is still high, especially when dealing with large-scale goods, the efficiency may be limited. The method of decomposing it into a 01 knapsack problem may not perform well when dealing with special-shaped goods and multiple constraints, affecting the packing effect.

[0020] Explain the cause of the defect in combination with the structure

[0021] Algorithm limitations: The algorithms used in existing technologies, such as dynamic programming, heuristic search and genetic algorithms, can effectively optimize under certain conditions. However, when faced with large-scale, multi-type goods and complex constraints, they have high computational complexity, low efficiency and difficulty in responding quickly to dynamic changes.

[0022] System design defects: The existing system design does not adequately consider real-time data processing and dynamic response, making it difficult to adapt to the rapid changes and diverse needs in actual applications, affecting the practicality and effectiveness of the packing solution. Summary of the invention

[0023] The technical problem to be solved by the present invention is to provide the present invention in view of the deficiencies of the background technology.

[0024] The present invention adopts the following technical solutions to solve the above technical problems:

[0025] A truck packing solution recommendation system based on two-stage maximization of loading rate, including:

[0026] Truck information processing module: used to receive and store single truck attributes uploaded by users, wherein the trucks are all rectangular parallelepipeds, and the truck attributes specifically include truck length, truck width, truck height, truck load, and truck unit price;

[0027] Goods management module: used to manage and store the properties of goods of various types and specifications uploaded by users, where the types include wooden boxes, cartons, and pallets, and the specifications include the length, width, and height of goods, and each of the goods has a unique number;

[0028] Pre-packaging processing module: pre-pack all goods into a list of goods piles according to the stacking restriction conditions. Each goods pile contains a group of goods that can be stacked together.

[0029] Loading optimization module: According to the genetic algorithm, with the maximization of loading rate as the optimization goal, select sub-lists from the cargo pile list output by the T3 module and load them into the truck, and output the packing plan list;

[0030] Loading plan export module: parses the cargo position in the loaded truck described in the loading optimization module, including cargo number, cargo placement position, cargo placement posture, and displays it in a detailed plan table and multi-view pictures, wherein the multi-view pictures include left view, right view, top view, and side view;

[0031] Among them, the truck information processing module and the cargo management module are input by the user and the outputs are connected together to the pre-packaging processing module, the outputs of the pre-packaging processing module and the truck information processing module are connected together to the loading optimization module, and the output of the loading optimization module is connected to the loading plan export module.

[0032] As a further preferred solution of the truck packing solution recommendation system based on the dual-stage maximum loading rate of the present invention, the stacking restriction conditions of the pre-packaging processing module specifically include the following rules:

[0033] P1: Directional constraints: During loading, the placement of different types of goods is subject to restrictions and rules, including vertical placement, horizontal placement, and misplaced placement;

[0034] P2: Weight constraint: For trucks, the total amount of cargo loaded must not exceed the weight; for different types of cargo, pre-packed stacking requires different stacking conditions, including large cargo not pressing small cargo, pyramid structure, and customized stacking layers;

[0035] P3: Stability constraint: The stacking of goods must not be suspended in the air. When pre-packing, the bottom surface must be in full contact and the force-bearing surface must be uniform.

[0036] P4: Height Limitation: During pre-packaging, the height of any stack of goods must not exceed the height of the truck as stated in Module T1.

[0037] As a further preferred solution of the truck packing solution recommendation system based on the dual-stage maximum loading rate of the present invention, the pre-packing processing module completes the pre-packing of goods through the following steps:

[0038] Step T3-1: Sort the cargo from large to small according to the attributes of the cargo as index values. The specific index values ​​are cargo weight, cargo length, cargo width, and cargo height. Assume that the sorted cargo list is T = [t1, t2, .., t n ], where t i Represents a commodity;

[0039] Step T3-2: Initialize the cargo pile S and start pre-packaging;

[0040] Step T3-3: Traverse and take out item t from the item list i , calculate the cargo packing constraint result, assuming the height of the truck is h max , the cargo pile is S = [s1,s2,..,s r ], the calculation formula for the stacking restriction condition is:

[0041]

[0042] Among them, w represents the width of the goods, l represents the length of the goods, h represents the height of the goods, and z represents the weight of the goods;

[0043] Step T3-4: Assuming that the cargo packing restriction condition is True, pack the cargo t i Move from the cargo list T to the cargo pile S;

[0044] Step T3-5: Assuming that the result of the cargo packing restriction condition is False, execute step T3-3;

[0045] Step T3-6: Repeat steps T3-3 to T3-5 until the cargo list is traversed and cargo pile S is added to the cargo pile list;

[0046] Step T3-7: Repeat steps T3-3 to T3-6 until the cargo list is empty, at which time the cargo pile list is output as the output result of the pre-packaging processing module.

[0047] As a further preferred solution of the truck packing solution recommendation system based on the dual-stage maximum loading rate of the present invention, the loading optimization module uses a genetic algorithm to complete the cargo stacking and packing. The specific packing process is as follows:

[0048] Step T4-1: Initialize the alternative solution group: input the cargo pile list described in module T3, and randomly generate the packing initial solution list Q according to the packing restriction conditions. The initial packing solution has the same dimension as the cargo pile list, specifically composed of 0 and 1, where 1 means using the pile and 0 means not using the pile;

[0049] Step T4-2: Feasibility verification of the solution: Initially solve Q for each packing i , use the heuristic layout algorithm to pack, if the packing is successful, then add the initial solution to the packing verification solution list

[0050] Step T4-3: Fitness calculation: For each packing verification solution list, the fitness calculation function f(x) is used to sort them from large to small, where the fitness calculation function is:

[0051]

[0052] Among them, xi represents the i-th packing verification solution, and si represents the i-th cargo pile in the cargo pile list;

[0053] Step T4-4: Select the solution to be enhanced: Use the roulette wheel selection method to select two heap container verification solutions Q1 and Q2 according to the calculated fitness value. The two heap container verification solutions constitute the solution to be enhanced. The roulette wheel selection method randomly selects according to the ratio of the calculated fitness values ​​of the heap container verification solutions. The higher the fitness, the greater the probability of being selected.

[0054] Step T4-5: ​​Enhancement of the scheme to be enhanced: Perform crossover and mutation operations on the selected scheme to be enhanced, and output the enhanced scheme;

[0055] Step T4-6: Enhanced solution verification: Use step T4-2 to verify the solution for each stacking container in the enhanced solution;

[0056] Step T4-7: loop solution: repeat steps T4-2 to T4-6 until the number of iterations reaches the maximum, and the specific number of iterations is set to 100;

[0057] Step T4-8: Final result output: List the boxing verification solution The output is a list of packing solutions.

[0058] As a further preferred solution of the truck packing solution recommendation system based on dual-stage maximum loading rate of the present invention, in step T4-2, the heuristic layout algorithm includes one-block heuristic layout, two-block heuristic layout and hollow-block heuristic layout, and the specific features include:

[0059] One-block heuristic layout: The goods can be placed horizontally or vertically on the cargo box according to the ratio between the size of the cargo box and the size of the goods;

[0060] Two-block heuristic layout: There are two ways to place goods in the cargo box, some goods are placed horizontally or some goods are placed vertically;

[0061] Hollow-block heuristic layout: Taking the center point of the cargo box as the reference point, by identifying the central free area, with maximizing the loading space utilization as the optimization goal, the goods are selected and placed in an alternating manner at the four corners of the cargo box.

[0062] As a further preferred solution of the truck packing solution recommendation system based on the dual-stage maximum loading rate of the present invention, in step T4-5, the crossover operation and mutation operation specifically include the following steps:

[0063] Step T4-5-1: Select the intersection point, randomly select a position from the packing verification solution as the intersection point, the length of the packing verification solution is r, then the position of the intersection point is k, where 1<=k<=r-1;

[0064] Step T4-5-2: Confirm the intersection position of the solution to be enhanced, and split the two stacking container verification solutions Q1 and Q2 at the intersection. The specific calculation formula is:

[0065]

[0066] Step T4-4-3: Crossover operation, crossover is performed at the crossover point k to generate a crossover enhancement scheme. The specific calculation formula is:

[0067]

[0068] Step T4-5-4: mutation operation, randomly select a position from the cross enhancement scheme as the mutation point, the position of the mutation point is j, where 1<=j<=r-1, generate a mutation enhancement scheme, the specific calculation formula is:

[0069]

[0070] Among them, ~ represents the negation operation, and the specific operation is: If it is 0, then negate it to 1; If it is 1, negate it to 0.

[0071] Compared with the prior art, the present invention adopts the above technical solution and has the following technical effects:

[0072] 1. Two-stage optimization strategy: The present invention adopts a two-stage strategy of pre-packaging processing and loading optimization; the pre-packaging processing module first packs the goods into piles according to preset rules, and then the loading optimization module uses genetic algorithms to optimize the selection of these pre-packed goods piles; this strategy effectively reduces the computational complexity, improves the overall loading efficiency, and ensures full utilization of the truck space;

[0073] 2. Modular design: The system is designed as multiple functional modules, including truck information processing module, cargo management module, pre-packaging processing module, loading optimization module and loading plan export module. Each module has clear functions and works together to improve the flexibility and maintainability of the system; this modular design allows the system to be flexibly adjusted and expanded according to actual needs to adapt to the loading needs of different types and specifications of cargo;

[0074] 3. Innovative application of genetic algorithm: The present invention adopts a specific genetic algorithm in loading optimization. By designing a specific fitness function and comprehensively considering factors such as truck load, space utilization and loading sequence, the algorithm can quickly converge under complex constraints and find the optimal loading solution. The innovative application of selection, crossover and mutation operations enables the system to perform well in handling complex constraints and diversified goods, significantly improving the loading rate and optimization effect.

[0075] 4. Efficient data processing and real-time response capabilities: The present invention designs an efficient information processing module and a loading plan export module, which can quickly process real-time data and generate loading plans that adapt to dynamic changes; the system can respond to changes in actual operations in real time, ensure the real-time and effectiveness of the loading plan, and significantly improve the actual application effect of the system;

[0076] 5. User-friendly and easy to operate: The present invention simplifies the operation process, reduces manual intervention, and improves the convenience of operation and user experience through the automated loading plan generation and export process. Users only need to upload truck attributes and cargo information, and the system can automatically generate the optimal loading plan, which greatly facilitates operators and improves work efficiency.

[0077] 6. Reduce transportation costs: By improving loading rate and optimizing efficiency, the present invention can reduce the number of transportation times and reduce transportation costs; the system fully utilizes the space and load capacity of the truck to ensure that the quantity of goods transported each time is maximized, thereby reducing the overall transportation cost and improving economic benefits;

[0078] 7. Improve the accuracy and practicality of loading schemes: The loading optimization module of the present invention is designed with a specific fitness function and takes into account a variety of loading constraints, so that the generated loading scheme is not only optimal in theory, but also highly practical in actual operation; the scheme generated by the system not only optimizes the loading rate, but also facilitates the actual loading operation, thereby improving the accuracy and operability of the loading scheme;

[0079] Through the above technical advantages, the present invention achieves significant performance improvement in truck loading optimization; the two-stage optimization strategy and modular design combined with the innovative application of genetic algorithms enable the system to perform well in handling complex cargo and diversified demands; efficient data processing and real-time response capabilities, user-friendliness and the effect of reducing transportation costs make the present invention have significant advantages in practical applications and solve many problems in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0081] Figure 1 It is a system architecture diagram of a truck packing solution based on a dual-stage maximum loading rate of the present invention;

[0082] Figure 2 It is the packing restriction condition of the present invention;

[0083] Figure 3 It is the pre-packaging flow chart of the present invention;

[0084] Figure 4 It is a packing flow chart of the present invention;

[0085] Figure 5 It is the one-block heuristic layout of the present invention;

[0086] Figure 6 It is the Two-block heuristic layout of the present invention;

[0087] Figure 7 It is the Hollow-block heuristic layout of the present invention;

[0088] Figure 8 It is a multi-view picture of the packaging result of the present invention;

[0089] Fig. 9 It is a schematic diagram of the pre-packaging effect of the present invention;

[0090] Fig.10 It is a 3D display diagram of the freight solution of the present invention. DETAILED DESCRIPTION

[0091] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings:

[0092] 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 in 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. The present invention is described in detail below based on the drawings and preferred embodiments, and the purpose and effect of the present invention will become clearer. It should be understood that the specific embodiments described here are only used to explain the present invention and are not used to limit the present invention.

[0093] Example 1: Figure 1 As shown, the truck packing solution recommendation system based on dual-stage maximization of loading rate described in the present invention is specifically composed of the following modules:

[0094] T1: Truck information processing module: used to receive and store the attributes of a single truck uploaded by the user, wherein the trucks are all rectangular parallelepipeds, and the truck attributes specifically include truck length, truck width, truck height, truck load, and truck unit price;

[0095] T2: Cargo management module: used to manage and store the properties of various types and specifications of cargo uploaded by users, where the types include wooden boxes, cartons, and pallets, and the specifications include cargo length, cargo width, and cargo height. Each cargo has a unique number;

[0096] T3: Pre-packaging processing module: connected with the truck information processing module and the cargo management module, pre-packs all cargo into a cargo pile list according to the stacking restriction conditions. Each cargo pile contains a group of cargo that can be stacked together.

[0097] like Figure 2 As shown, the stacking restriction conditions specifically include the following rules:

[0098] P1: Directional constraints: During loading, the placement of different types of goods is subject to restrictions and rules. The placement positions include vertical placement, horizontal placement, and misplaced placement ( Figure 2 -A);

[0099] P2: Weight constraint: For trucks, the total amount of cargo loaded must not exceed the weight; for different types of cargo, pre-packed stacking requires different stacking conditions, including large cargo should not be pressed on small cargo, pyramid structure ( Figure 2-B), customized stacking layer;

[0100] P3: Stability constraint: The stacking of goods must not be suspended in the air. When pre-packing, the bottom surface must be in full contact and the force-bearing surface must be uniform.

[0101] P4: Height Limitation: During pre-packaging, the height of any stack of goods must not exceed the height of the truck as stated in Module T1.

[0102] like Figure 3 As shown in the figure, pre-packaging specifically includes the following processes:

[0103] Step T3-1: Sort the cargo from large to small according to the attributes of the cargo as index values. The specific index values ​​are cargo weight, cargo length, cargo width, and cargo height. Assume that the sorted cargo list is T = [t1, t2, .., t n ], where t i Represents a commodity;

[0104] Step T3-2: Initialize the cargo pile S and start pre-packaging;

[0105] Step T3-3: Traverse and take out item t from the item list i , calculate the cargo packing constraint result, assuming the height of the truck is h max , the cargo pile is S = [s1,s2,..,s r ], the calculation formula for the stacking restriction condition is:

[0106]

[0107] Among them, w represents the width of the goods, l represents the length of the goods, h represents the height of the goods, and z represents the weight of the goods;

[0108] Step T3-4: Assuming that the cargo packing restriction condition is True, pack the cargo t i Move from the cargo list T to the cargo pile S;

[0109] Step T3-5: Assuming that the result of the cargo packing restriction condition is False, execute step T3-3;

[0110] Step T3-6: Repeat steps T3-3 to T3-5 until the cargo list is traversed and cargo pile S is added to the cargo pile list;

[0111] Step T3-7: Repeat steps T3-3 to T3-6 until the cargo list is empty, at which time the cargo pile list is output as the output result of the pre-packaging processing module.

[0112] T4: Loading optimization module: connected with the truck information processing module and the pre-packaging processing module, according to the genetic algorithm, with the maximization of the loading rate as the optimization goal, selects a sub-list from the cargo pile list output by the pre-packaging processing module and loads it into the truck, and outputs a packing plan list, such as Figure 4 As shown, the specific packing process is as follows:

[0113] Step T4-1: Initialize the alternative solution group: input the cargo pile list described in module T3, and randomly generate the packing initial solution list Q according to the packing restriction conditions. The initial packing solution has the same dimension as the cargo pile list, specifically composed of 0 and 1, where 1 means using the pile and 0 means not using the pile;

[0114] Step T4-2: Feasibility verification of the solution: Initially solve Q for each packing i , use the heuristic layout algorithm to pack, if the packing is successful, then add the initial solution to the packing verification solution list

[0115] Step T4-3: Fitness calculation: For each packing verification solution list, the fitness calculation function f(x) is used to sort them from large to small, where the fitness calculation function is:

[0116]

[0117] Among them, x i represents the ith packing verification solution, s i Represents the i-th cargo pile in the cargo pile list;

[0118] Step T4-4: Select the solution to be enhanced: Use the roulette wheel selection method to select two heap container verification solutions Q1 and Q2 according to the calculated fitness value. The two heap container verification solutions constitute the solution to be enhanced. The roulette wheel selection method randomly selects according to the ratio of the calculated fitness values ​​of the heap container verification solutions. The higher the fitness, the greater the probability of being selected.

[0119] Step T4-5: ​​Enhancement of the scheme to be enhanced: Perform crossover and mutation operations on the selected scheme to be enhanced, and output the enhanced scheme;

[0120] Step T4-6: Enhanced solution verification: Use step T4-2 to verify the solution for each stacking container in the enhanced solution;

[0121] Step T4-7: loop solution: repeat steps T4-2 to T4-6 until the number of iterations reaches the maximum, and the specific number of iterations is set to 100;

[0122] Step T4-8: Final result output: List the boxing verification solution The output is a list of packing solutions.

[0123] Among them, Figure 5 As shown in the one-block heuristic layout, the goods can be placed horizontally or vertically on the pallet according to the ratio between the size of the pallet and the size of the goods. If the length of the goods is parallel to the length of the pallet, the horizontal layout mode of the goods in this layer is called the H-box mode. Figure 5 As shown in A; if the length of the box is parallel to the width of the pallet, the vertical layout mode of the goods is called the V-box mode, such as Figure 5 As shown in B.

[0124] Among them, Figure 6 As shown in the figure, the two-block heuristic layout is equivalent to two ways of placing goods in one layer, that is, the H-box mode and the V-box mode. The two-block heuristic layout can be divided into two types. The H-box and V-box are placed on the left and right sides of the pallet respectively. This is a two-block heuristic layout with a left-right structure, such as Figure 6 Left: H-box and V-box are placed on the upper and lower sides of the tray respectively. This is a two-block heuristic layout of the upper and lower structures. Figure 6 Right picture.

[0125] Among them, Figure 7 The figure below shows a hollow-block heuristic layout, which also has horizontally placed H-boxes and vertically placed V-boxes. Two identical H-boxes and two identical V-boxes are placed alternately at the four corners of the tray. After placement, there will be a hole in the middle, so it is called a hollow-block heuristic layout. This layout is similar to a windmill, and can also be called a windmill product heuristic layout.

[0126] T5: Loading plan export module: connected to T4, analyzes the location of the goods in the loaded truck described in T4, including the number of the goods, the placement of the goods, and the placement of the goods, and displays them in a detailed plan table and multi-view pictures, such as Figure 8 As shown, the multi-view image includes a left view, a right view, a top view, and a side view.

[0127] Example 2: The following uses simulation data to describe in detail how the system of the present invention loads goods into a truck. The input cargo details are shown in Table 1. The input cargo types include wooden boxes, cartons, pallets, and pallets. The input cargo details are shown in Table 2. The input vehicle information includes truck length, truck width, truck height, truck load, and truck unit price. In the pre-packaging of cargo stacking, a higher "cargo pile" can be packed as much as possible while meeting the vehicle height limit and cargo stacking limit conditions. Fig. 9As shown, the pre-packaging described in the present invention is specifically divided into bulk packaging, same type packaging and mixed packaging.

[0128] Table 1

[0129] Type of cargo long Width high weight quantity Wooden box 122 511 880 321 3 tray 1160 840 1620 221 2 tray 1160 840 1620 221 3 Wooden box 2130 675 880 458 3 Wooden box 610 321 340 18 1 Take the lead 1550 1550 750 796 2 Take the lead 1550 1550 750 796 1

[0130] Table 2

[0131] line unit price Load-bearing Carriage length Carriage width Carriage height Qingdao City Shanghai City 6700 20000 14500 3250 4100

[0132] The above stacking pre-packaging has obtained the best cargo pile list, and the packing algorithm places the cargo pile list into the fleet. In the process of packing the fleet, it is necessary to take out as many goods as possible and load them into the carriages in the fleet in turn. Specifically, a heuristic algorithm is used for packing, given a list of cargo piles to be loaded and several truck cargo boxes of different specifications and sizes. The experimental results are shown in Table 3. The experiment compares the TOP1 solution cost of the packing algorithm schemes under various formula combinations. The experimental results show that in terms of the cost saving effect of the optical wiring packing task: original packing + original packing < the cost of the packing of the present invention + original packing < the cost of the original packing + the packing of the present invention < the cost of the packing of the present invention + the packing of the present invention.

[0133] Table 3

[0134]

[0135] Through the loading plan export module, this embodiment outputs the packing plan and packing guidance diagram, and also displays 3D packing modeling. Among them, the packing plan mainly displays the packing method, reinforcement method and multiple packing views (front view, top view, side view), which can be selected by the dispatch center station or assemblers. The packing guidance diagram displays the spatial position of the goods in the container from multiple perspectives to guide on-site packing operations, realizing packing without experience. Fig.10 As shown, this embodiment demonstrates 3D packing modeling: the spatial position of the goods is dynamically displayed in the form of a 3D model, so as to accurately and quickly locate and control the position of the goods.

[0136] Through the above embodiments, the truck packing solution recommendation system based on dual-stage maximum loading rate described in the present invention can handle goods of various specifications and sizes, ensuring that the goods are loaded and transported in a cost-effective manner. It is committed to solving the following business pain points of enterprises:

[0137] Intelligent algorithms solve the problem of low loading rate: Packing needs to consider the matching of various restrictions of goods and containers, and use intelligent algorithms to balance key data such as the volume, weight, and pressure of each piece of cargo in the truck to improve the loading rate and load factor, so as to achieve "less use of the truck, but better loading of the truck".

[0138] View guidance solves repeated trial installation: Traditional packing often requires a lot of time for packing experiments, and repeated attempts to reach the packing limit. There are very few "old masters" with rich experience. Through the guidance of multi-view packing renderings, companies can get rid of the single mode of relying entirely on personal ability and packing experience, and achieve "anyone can pack, and everyone knows how to pack."

[0139] Plan generation solves the difficulty of audit and traceability: Manually issued packing plans not only consume manpower costs, but are also not intuitive enough, which leads to unclear audit details and difficult to trace packing problems. Through the packing plan generated by the system, the location of the goods is clear, the plan structure is simplified, and the guidance of goods placement is refined to "which row, which column, which layer".

[0140] The present invention adopts a two-stage strategy of pre-packaging and loading optimization. The pre-packaging module first packs the goods into piles according to preset rules, and then the loading optimization module uses genetic algorithms to optimize the selection of these pre-packed goods piles. This strategy effectively reduces the computational complexity, improves the overall loading efficiency, and ensures full utilization of the truck space.

[0141] The system is designed as multiple functional modules, including truck information processing module, cargo management module, pre-packaging processing module, loading optimization module and loading plan export module. Each module has clear functions and works together to improve the flexibility and maintainability of the system. This modular design allows the system to be flexibly adjusted and expanded according to actual needs to adapt to the loading needs of different types and specifications of cargo.

[0142] The present invention adopts a specific genetic algorithm in loading optimization. By designing a specific fitness function and comprehensively considering factors such as truck load, space utilization and loading sequence, the algorithm can converge quickly under complex constraints and find the optimal loading solution. The innovative application of selection, crossover and mutation operations enables the system to perform well in dealing with complex constraints and diversified goods, significantly improving the loading rate and optimization effect.

[0143] The present invention designs an efficient information processing module and a loading plan export module, which can quickly process real-time data and generate loading plans that adapt to dynamic changes. The system can respond to changes in actual operations in real time, ensure the real-time and effectiveness of the loading plan, and significantly improve the actual application effect of the system.

[0144] The present invention simplifies the operation process, reduces manual intervention, and improves the convenience of operation and user experience through the automated loading plan generation and export process. Users only need to upload truck attributes and cargo information, and the system can automatically generate the optimal loading plan, which greatly facilitates operators and improves work efficiency.

[0145] By improving the loading rate and optimizing the efficiency, the present invention can reduce the number of transportations and reduce the transportation cost. The system makes full use of the space and load capacity of the truck to ensure the maximum amount of goods transported each time, thereby reducing the overall transportation cost and improving the economic benefits.

[0146] The loading optimization module of the present invention utilizes a specific fitness function design and takes into account a variety of loading constraints, so that the generated loading scheme is not only optimal in theory, but also highly practical in actual operation. The scheme generated by the system not only optimizes the loading rate, but also facilitates actual loading operations, improving the accuracy and operability of the loading scheme.

[0147] The present invention achieves significant performance improvement in truck loading optimization. The two-stage optimization strategy and modular design combined with the innovative application of genetic algorithms enable the system to perform well in handling complex cargo and diverse demands. The efficient data processing and real-time response capabilities, user-friendliness, and the effect of reducing transportation costs make the present invention have significant advantages in practical applications and solve many problems in the prior art.

[0148] Those skilled in the art can understand that the above are only preferred examples of the invention and are not intended to limit the invention. Although the invention is described in detail with reference to the above embodiments, those skilled in the art can still modify the technical solutions recorded in the above embodiments or replace some of the technical features with equivalents. Any modification, equivalent replacement, etc. made within the spirit and principle of the invention should be included in the protection scope of the invention. All technical features in this embodiment can be freely combined according to actual needs.

[0149] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A truck packing solution recommendation system based on dual-stage maximum loading rate, characterized in that: Include: Truck information processing module: used to receive and store single truck attributes uploaded by users, wherein the trucks are all rectangular parallelepipeds, and the truck attributes specifically include truck length, truck width, truck height, truck load, and truck unit price; Goods management module: used to manage and store the properties of goods of various types and specifications uploaded by users, where the types include wooden boxes, cartons, and pallets, and the specifications include the length, width, and height of goods, and each of the goods has a unique number; Pre-packaging processing module: pre-pack all goods into a list of goods piles according to the stacking restriction conditions. Each goods pile contains a group of goods that can be stacked together. Loading optimization module: According to the genetic algorithm, with the maximization of loading rate as the optimization goal, select sub-lists from the cargo pile list output by the T3 module and load them into the truck, and output the packing plan list; Loading plan export module: parses the cargo position in the loaded truck described in the loading optimization module, including cargo number, cargo placement position, cargo placement posture, and displays it in a detailed plan table and multi-view pictures, wherein the multi-view pictures include left view, right view, top view, and side view; Among them, the truck information processing module and the cargo management module are input by the user and the outputs are connected together to the pre-packaging processing module, the outputs of the pre-packaging processing module and the truck information processing module are connected together to the loading optimization module, and the output of the loading optimization module is connected to the loading plan export module.

2. A truck packing solution recommendation system based on dual-stage maximum loading rate according to claim 1, characterized in that: The stacking restriction conditions of the pre-packaging processing module specifically include the following rules: P1: Directional constraints: During loading, the placement of different types of goods is subject to restrictions and rules, including vertical placement, horizontal placement, and misplaced placement; P2: Weight constraint: For trucks, the total amount of cargo loaded must not exceed the weight; for different types of cargo, pre-packed stacking requires different stacking conditions, including large cargo not pressing small cargo, pyramid structure, and customized stacking layers; P3: Stability constraint: The stacking of goods must not be suspended in the air. When pre-packing, the bottom surface must be in full contact and the force-bearing surface must be uniform. P4: Height Limitation: During pre-packaging, the height of any stack of goods must not exceed the height of the truck as stated in Module T1.

3. The truck packing solution recommendation system based on dual-stage maximum loading rate according to claim 1 is characterized in that: The pre-packaging processing module completes the pre-packaging of goods through the following steps: Step T3-1: Sort the cargo from large to small using the cargo attributes as index values. The specific index values ​​are cargo weight, cargo length, cargo width, and cargo height. Assume that the sorted cargo list is T = [t1, t2, .., t n ], where t i Represents a commodity; Step T3-2: Initialize the cargo pile S and start pre-packaging; Step T3-3: Traverse and take out item t from the item list i , calculate the cargo packing constraint result, assuming the height of the truck is h max , the cargo pile is S = [s1,s2,..,s r ], the calculation formula for the stacking restriction condition is: Among them, w represents the width of the goods, l represents the length of the goods, h represents the height of the goods, and z represents the weight of the goods; Step T3-4: Assuming that the cargo packing restriction condition is True, pack the cargo t i Move from the cargo list T to the cargo pile S; Step T3-5: Assuming that the result of the cargo packing restriction condition is False, execute step T3-3; Step T3-6: Repeat steps T3-3 to T3-5 until the cargo list is traversed and cargo pile S is added to the cargo pile list; Step T3-7: Repeat steps T3-3 to T3-6 until the cargo list is empty, at which time the cargo pile list is output as the output result of the pre-packaging processing module.

4. The truck packing solution recommendation system based on dual-stage maximum loading rate according to claim 1 is characterized in that: The loading optimization module uses genetic algorithms to complete cargo stacking and packing. The specific packing process is as follows: Step T4-1: Initialize the alternative solution group: input the cargo pile list described in module T3, and randomly generate the packing initial solution list Q according to the packing restriction conditions. The initial packing solution has the same dimension as the cargo pile list, specifically composed of 0 and 1, where 1 means using the pile and 0 means not using the pile; Step T4-2: Feasibility verification of the solution: Initially solve Q for each packing i , use the heuristic layout algorithm to pack, if the packing is successful, then add the initial solution to the packing verification solution list Step T4-3: Fitness calculation: For each packing verification solution list, the fitness calculation function f(x) is used to sort them from large to small, where the fitness calculation function is: Among them, xi represents the i-th packing verification solution, and si represents the i-th cargo pile in the cargo pile list; Step T4-4: Select the solution to be enhanced: Use the roulette wheel selection method to select two heap container verification solutions Q1 and Q2 according to the calculated fitness value. The two heap container verification solutions constitute the solution to be enhanced. The roulette wheel selection method randomly selects according to the ratio of the calculated fitness values ​​of the heap container verification solutions. The higher the fitness, the greater the probability of being selected. Step T4-5: ​​Enhancement of the scheme to be enhanced: Perform crossover and mutation operations on the selected scheme to be enhanced, and output the enhanced scheme; Step T4-6: Enhanced solution verification: Use step T4-2 to verify the solution for each stacking container in the enhanced solution; Step T4-7: loop solution: repeat steps T4-2 to T4-6 until the number of iterations reaches the maximum, and the specific number of iterations is set to 100; Step T4-8: Final result output: List the boxing verification solution The output is a list of packing solutions.

5. The truck packing solution recommendation system based on dual-stage maximum loading rate according to claim 4 is characterized in that: In step T4-2, the heuristic layout algorithm includes one-block heuristic layout, two-block heuristic layout and hollow-block heuristic layout, and the specific features include: One-block heuristic layout: The goods can be placed horizontally or vertically on the cargo box according to the ratio between the size of the cargo box and the size of the goods; Two-block heuristic layout: There are two ways to place goods in the cargo box, some goods are placed horizontally or some goods are placed vertically; Hollow-block heuristic layout: Taking the center point of the cargo box as the reference point, by identifying the central free area, with maximizing the loading space utilization as the optimization goal, the goods are selected and placed in an alternating manner at the four corners of the cargo box.

6. The truck packing solution recommendation system based on dual-stage maximum loading rate according to claim 4 is characterized in that: In step T4-5, the crossover operation and mutation operation specifically include the following steps: Step T4-5-1: Select the intersection point, randomly select a position from the packing verification solution as the intersection point, the length of the packing verification solution is r, then the position of the intersection point is k, where 1<=k<=r-1; Step T4-5-2: Confirm the intersection position of the solution to be enhanced, and split the two stacking container verification solutions Q1 and Q2 at the intersection. The specific calculation formula is: Step T4-4-3: Crossover operation, crossover is performed at the crossover point k to generate a crossover enhancement scheme. The specific calculation formula is: Step T4-5-4: mutation operation, randomly select a position from the cross enhancement scheme as the mutation point, the position of the mutation point is j, where 1<=j<=r-1, generate a mutation enhancement scheme, the specific calculation formula is: Among them, ~ represents the negation operation, and the specific operation is: If it is 0, then negate it to 1; If it is 1, negate it to 0.

Images