Freight loading method and device

Abstract

The invention relates to the technical field of freight loading, and discloses a freight loading method and device. The freight loading method comprises the following steps: configuring a plurality of specification combination results of stacking blocks for stacking cargoes of the same type; selecting a target stacking specification of the stacking block from a combination result of multiple specifications; and based on the optimized cargo placement model, the cargos of the same type stacked into the stacking blocks according to the target stacking specification are loaded into the target truck through the intelligent forklift equipment. Therefore, after the stacking specifications of the stacking blocks of the intelligent forklift equipment are considered, the cargos are loaded based on the optimized cargo placement model, the loading space of the intelligent forklift equipment can be fully utilized, and then the carrying frequency of the intelligent forklift equipment is reduced to meet the loading requirement of a large amount of cargos.

Description

Technical Field

[0001] The present invention relates to the technical field of freight loading, and in particular to a freight loading method and device. Background Art

[0002] Freight loading is a critical link in the logistics chain that involves the safe and efficient loading of goods from their point of origin onto a transport vehicle (such as a truck, train, ship or aircraft) for shipment to their destination.

[0003] In the related art, if the goods are loaded hastily without considering the loading space of the intelligent forklift equipment, the loading space of the intelligent forklift equipment cannot be fully utilized, thereby increasing the number of transportation times of the intelligent forklift equipment, making it difficult to meet the loading needs of large quantities of goods. Summary of the invention

[0004] In view of this, the present invention provides a freight loading method and device to solve the problem that the loading space of the intelligent forklift equipment cannot be fully utilized, thereby increasing the number of transportation times of the intelligent forklift equipment and it is difficult to meet the loading needs of a large amount of goods.

[0005] In a first aspect, the present invention provides a freight loading method, the method comprising:

[0006] Based on the loading conditions of the target truck and the loading conditions of the intelligent forklift equipment carrying the stacking blocks, multiple combination results of specifications of the stacking blocks used to stack the same type of goods are configured;

[0007] Select the target stacking specification of the palletizing block from the combination results of multiple specifications;

[0008] Set the cargo stacking variable. The cargo stacking quantity indicates the cargo stacking quantity that is required to stack the cargo in different directions to meet the target stacking specifications.

[0009] Generate a cargo placement model based on the total weight constraint function of the cargo loaded on the truck, the total weight constraint function of the stacking block, the total volume constraint function of the stacking block, the constraint function of the intelligent forklift equipment, and the cargo stacking quantity of the target stacking specification;

[0010] Use the preset optimization algorithm to optimize the cargo stacking variables so that the cargo placement model meets the preset conditions;

[0011] Based on the optimized cargo placement model, the same type of cargo stacked into stacking blocks according to the target stacking specifications is loaded into the target truck through the intelligent forklift equipment.

[0012] In an optional embodiment, based on the loading conditions of the target truck and the loading conditions of the intelligent forklift device carrying the stacking blocks, multiple specification combination results of stacking blocks for stacking the same type of goods are configured, including:

[0013] Obtaining a first stacking quantity, a second stacking quantity, and a third stacking quantity of the target truck, wherein the first stacking quantity is the maximum stacking quantity along the length direction of the target truck, the second stacking quantity is the maximum stacking quantity along the width direction of the target truck, and the third stacking quantity is the maximum stacking quantity along the height direction of the target truck;

[0014] Get the maximum carrying quantity of the intelligent forklift equipment;

[0015] Based on the first stacking quantity, the second stacking quantity, the third stacking quantity, the maximum carrying quantity of the intelligent forklift, and the cargo stacking requirements in the length direction, the width direction, and the height direction of the target truck, multiple different preset numerical values ​​are selected from positive integers to configure multiple specification combination results of the stacking stacking blocks.

[0016] In an optional implementation, the total weight constraint function based on the cargo loaded on the truck is created by the following formula:

[0017]

[0018] Among them, s i is the number of palletizing blocks of the i-th type required for preparation, a is the number of combinations of various specifications of palletizing blocks, max is to ensure that the total weight of the goods loaded on the truck is maximized, and q ij is the basic quantity of goods stacked in the j-direction in the stacking block of the i-th target stacking specification, q ik is the basic quantity of goods stacked in the k direction in the stacking block of the i-th target stacking specification, q il is the basic quantity of goods stacked along the l direction in the stacking block of the i-th target stacking specification, and w0 is the basic weight of the goods.

[0019] In an optional embodiment, the constraint function of the total weight of the stacking block is created by the following formula:

[0020]

[0021] Among them, a is the number of combinations of various specifications of stacking blocks, q ij is the basic quantity of goods stacked along the long side j in the i-th stacking block, q ik is the basic quantity of goods stacked in the k direction in the stacking block of the i-th target stacking specification, q il is the basic quantity of goods stacked in the stacking block of the i-th target stacking specification along the l-direction, s i is the number of palletizing blocks of the ith type required for preparation, and w is the upper limit of the truck load.

[0022] In an optional embodiment, the constraint function of the total volume of the stacking block is created by the following formula:

[0023]

[0024]

[0025] Among them, M i is the length of the palletized block, N i is the width of the palletized block, P i is the height of the stacking block, q ij is the basic quantity of goods stacked along the long side j in the i-th stacking block, q ik is the basic quantity of goods stacked along the width direction k in the i-th stacking block, q il is the basic quantity of goods stacked along the high side direction l in the i-th stacking block, m0 is the length of the goods, n0 is the width of the goods, p0 is the height of the goods, m is the length of the truck, n is the width of the truck, p is the height of the truck, Z1 is the width of the truck door, and Z2 is the height of the truck door.

[0026] In an optional implementation, the constraint function of the intelligent forklift device is created by the following formula:

[0027] (M i ,N i ,P i )∈Veh

[0028] Among them, Veh is the load-bearing volume requirement of the intelligent forklift equipment for loading goods, M i is the length of the palletized block, N i is the width of the palletized block, P i is the height of the stacking blocks.

[0029] In an optional implementation, the stacking variables are optimized using a preset optimization algorithm so that the cargo placement model meets preset conditions, including:

[0030] Using cargo stacking variables as the initial solution for the preset optimization algorithm;

[0031] The cargo stacking variables corresponding to the initial solution are adjusted according to the neighborhood search method to redetermine the cargo stacking quantity of the target stacking specification;

[0032] Generate an optimized cargo placement model based on the total weight constraint function of the cargo loaded on the truck, the total weight constraint function of the stacking blocks, the total volume constraint function of the stacking blocks, the constraint function of the intelligent forklift equipment, and the cargo stacking quantity of the re-determined target stacking specifications;

[0033] Evaluate whether the optimized cargo placement model meets the preset conditions. If not, return to the step of stacking cargo variables until the preset conditions are met.

[0034] In a second aspect, the present invention provides a freight loading device, the device comprising:

[0035] A configuration module, used for configuring multiple specification combination results of palletizing blocks for stacking the same type of goods based on the loading conditions of the target truck and the loading conditions of the intelligent forklift equipment carrying the palletizing blocks;

[0036] A selection module is used to select a target stacking specification of a stacking block from a combination of multiple specifications;

[0037] A setting module is used to set cargo stacking variables, where the cargo stacking quantity indicates the cargo stacking quantity that is required to stack the cargo in different directions to meet the target stacking specifications;

[0038] A generation module, for generating a cargo placement model based on a total weight constraint function of cargo loaded on a truck, a total weight constraint function of a stacking block, a total volume constraint function of a stacking block, a constraint function of an intelligent forklift device, and a cargo stacking quantity of a target stacking specification;

[0039] An optimization module is used to optimize the number of goods stacked using a preset optimization algorithm so that the goods placement model meets preset conditions;

[0040] The loading module is used to load the same type of goods stacked into stacking blocks according to target stacking specifications into a target truck through an intelligent forklift device based on the optimized goods placement model.

[0041] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the freight loading method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0042] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the freight loading method of the first aspect or any corresponding embodiment thereof.

[0043] In a fifth aspect, the present invention provides a computer program product, including computer instructions, the computer instructions are used to enable a computer to execute the freight loading method of the first aspect or any corresponding embodiment thereof. The technical solution of the present invention has the following advantages:

[0044] The present invention relates to the technical field of freight loading, and discloses a freight loading method and device. The present invention configures multiple specification combination results of stacking blocks for stacking the same type of goods based on the loading conditions of a target truck and the loading conditions of an intelligent forklift device carrying stacking blocks; selects the target stacking specifications of the stacking blocks from the multiple specification combination results; sets a cargo stacking variable, and the cargo stacking quantity represents the cargo stacking quantity of the cargo stacked in different directions into the target stacking specifications; generates a cargo placement model based on the total weight constraint function of the truck loaded with goods, the constraint function of the total weight of the stacking blocks, the constraint function of the total volume of the stacking blocks, the constraint function of the intelligent forklift device, and the cargo stacking quantity of the target stacking specifications; optimizes the cargo stacking variables using a preset optimization algorithm so that the cargo placement model meets the preset conditions; and based on the optimized cargo placement model, loads the same type of cargo stacked into stacking blocks according to the target stacking specifications into the target truck through the intelligent forklift device. Therefore, after considering the stacking specifications of the stacking blocks of the intelligent forklift device, and loading the cargo based on the optimized cargo placement model, the present invention can make full use of the loading space of the intelligent forklift device, thereby reducing the number of transportation times of the intelligent forklift device, so as to meet a large number of cargo loading requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 is a flow chart of a freight loading method according to an embodiment of the present invention;

[0047] Figure 2 is a schematic diagram of software and hardware of an intelligent forklift device according to an embodiment of the present invention;

[0048] Figure 3 is a schematic flow chart of another freight loading method according to an embodiment of the present invention;

[0049] Figure 4 is a schematic diagram of multimodal data fusion performed by an intelligent forklift device according to an embodiment of the present invention;

[0050] Figure 5 is a structural block diagram of a freight loading device according to an embodiment of the present invention;

[0051] Figure 6 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0053] According to an embodiment of the present invention, an embodiment of a freight loading method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0054] According to an embodiment of the present invention, a freight loading method embodiment is provided, which can be used for intelligent forklift equipment, computer equipment, such as mobile phones, tablet computers, desktop computers, portable notebooks, servers, etc. In the embodiment of the present disclosure, Figure 1 is a flow chart of a freight loading method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0055] Step S101, based on the loading conditions of the target truck and the loading conditions of the intelligent forklift equipment carrying the stacking blocks, multiple specification combination results of stacking blocks for stacking the same type of goods are configured.

[0056] In a specific example, the freight loading method in the embodiment of the present disclosure is used to load freight in railway freight. Therefore, the target truck can be a train. When the freight loading method is used in a highway, the target truck can be a train.

[0057] Specifically, in the disclosed embodiment, the target truck is preferably a train. The loading condition of the target truck may be the maximum number of goods allowed to be placed in the travel direction of the train according to the full placement requirement, the maximum number of goods allowed to be placed in the lateral direction of the train parallel to the travel direction according to the full placement requirement, and the number of goods allowed to be placed in the height direction of the train according to the requirement, and the loading condition of the intelligent forklift device may be the total number of goods allowed to be loaded by the intelligent forklift device at one time.

[0058] Furthermore, the same type of goods refers to goods that are substantially the same in shape and weight, for example, the same type of cement or rice. Based on the loading conditions of the target truck and the loading conditions of the intelligent forklift device carrying the stacking blocks, the configuration results of multiple combinations of specifications of stacking blocks for stacking the same type of goods are as follows:

[0059] For example, the loading conditions of the train carriage are: the maximum number of goods allowed to be placed in the direction of the train according to the full placement requirement is 9 bags of goods, the maximum number of goods allowed to be placed in the horizontal direction parallel to the direction of the train according to the full placement requirement is 13 bags of goods, and the maximum number of goods allowed to be placed in the height direction of the train according to the requirement is 14 bags. At the same time, the total number of goods allowed to be loaded at one time by the intelligent forklift equipment is 36 bags. Combined with the goods placement standards in the length direction, width direction, and height direction of the intelligent forklift equipment, the goods are placed. For example, the goods are placed in the length direction according to the preset value 3, the width direction is also placed according to the preset value 3, and the height direction is placed according to the preset value 4. The stacking specification of the stacking block is 3×3×4, and the intelligent forklift equipment can just transport all 36 bags of goods. Similarly, for example, the goods can also be placed in the length direction according to the preset value 3, the width direction is also placed according to the preset value 3, and the height direction is placed according to the preset value 3. The stacking specification of the stacking block is 3×3×3, and it takes two times to transport all 36 bags of goods. Therefore, the various combinations of specifications of the palletizing blocks configured in this manner for stacking the same type of goods are 3×3×3 and 3×3×4.

[0060] Step S102, selecting a target stacking specification of the stacking blocks from the multiple specification combination results.

[0061] Specifically, based on the target stacking specification of the stacking blocks selected from the multiple specification combination results 3×3×3 and 3×3×4 exemplified above, 3×3×4 can be selected as the target stacking specification of the stacking blocks.

[0062] Step S103, setting a cargo stacking variable, where the cargo stacking quantity represents the cargo stacking quantity of the cargo stacked in different directions to achieve a target stacking specification.

[0063] Specifically, the cargo stacking variable is a variable involved in the calculation, which represents the number of cargo stacked into a stacking block along a certain direction of the stacking block. For example, the cargo stacking number can be expressed as q ij It represents the number of goods stacked in the stacking block of the i-th target stacking specification along the j direction, and the j direction corresponds to the length direction of the stacking block.

[0064] Step S104, generating a cargo placement model based on the total weight constraint function of the cargo loaded on the truck, the total weight constraint function of the stacking blocks, the total volume constraint function of the stacking blocks, the constraint function of the intelligent forklift equipment and the cargo stacking quantity of the target stacking specification.

[0065] Specifically, the total weight constraint function of the goods loaded on the truck is to ensure that the total weight of the goods loaded on the truck is maximized, the total weight constraint function of the stacking blocks is to further constrain the total weight of the stacking blocks, the total volume constraint function of the stacking blocks is to further constrain the total volume of the stacking blocks, the constraint function of the intelligent forklift equipment is to further constrain the size of the goods that can be provided by the intelligent forklift equipment, the cargo placement model is a model that constrains the way the goods are placed, and the target stacking specification cargo stacking quantity is the cargo stacking quantity formed according to the target stacking specification 3×3×3, or 3×3×4.

[0066] Step S105, optimizing the cargo stacking variables using a preset optimization algorithm so that the cargo placement model meets preset conditions.

[0067] Specifically, the preset optimization algorithm may be a commonly used genetic algorithm or a simulated annealing algorithm or a particle swarm optimization algorithm, through which the cargo placement model is further solved to optimize the results, so as to ensure the feasibility and accuracy of the target loading strategy.

[0068] Step S106: Based on the optimized cargo placement model, the same type of cargo stacked into stacking blocks according to the target stacking specifications is loaded into the target truck by the intelligent forklift equipment.

[0069] Specifically, the freight loading method in the embodiment of the present disclosure can be applied to computer equipment, or directly applied to intelligent forklift equipment. If the freight loading method in the embodiment of the present disclosure is directly applied to the intelligent forklift equipment, the intelligent forklift equipment will load the same type of goods stacked into stacking blocks according to the target stacking specifications into the target truck based on the cargo placement model. Intelligent forklift equipment is designed for automatic cargo and loading. The equipment is equipped with high-precision sensors and machine vision, which can identify the type and location of cargo in real time and automatically plan the optimal loading path. The intelligent forklift equipment receives and executes operation instructions through integration with the central controller to ensure accurate stacking of cargo. In addition, the intelligent forklift equipment also has automatic obstacle avoidance and fault self-diagnosis functions to enhance operation safety and continuity. Intelligent unmanned forklifts not only improve loading and unloading efficiency, but also significantly reduce labor costs and operating error rates. Figure 2 The schematic diagram of the software, hardware and mechanical system design of the intelligent forklift equipment is shown. In order to meet the existing railway loading standards and optimize the loading layout of goods, efficient stacking of goods and maximum utilization of space are achieved. By executing the above steps S101 to S106, the intelligent forklift equipment can automatically calculate the best way to place the goods, thereby reducing loading and unloading time and improving the utilization rate of the compartment space.

[0070] In this embodiment, a freight loading method is provided, which can be used for intelligent forklift equipment, computer equipment, such as mobile phones, tablet computers, desktop computers, portable notebooks, servers, etc. Figure 3 is a flow chart of a freight loading method according to an embodiment of the present invention. Figure 3 As shown, step S101, based on the loading conditions of the target truck and the loading conditions of the intelligent forklift equipment carrying the stacking blocks, multiple specification combination results of the stacking blocks for stacking the same type of goods are configured. The process includes the following steps:

[0071] Step S1011, obtaining the first stacking number, the second stacking number, and the third stacking number of the target truck, the first stacking number is the maximum stacking number along the length direction of the target truck, the second stacking number is the maximum stacking number along the width direction of the target truck, and the third stacking number is the maximum stacking number along the height direction of the target truck.

[0072] Specifically, the first stacking quantity is the maximum stacking quantity along the length direction (driving direction) of the target truck, for example, the maximum stacking quantity in this direction is 9 bags of cargo; the second stacking quantity is the maximum stacking quantity along the width direction (lateral direction) of the target truck; for example, the maximum stacking quantity in this direction is 13 bags of cargo; the third stacking quantity is the maximum stacking quantity along the height direction of the target truck, for example, the maximum stacking quantity in this direction is 14 bags.

[0073] Step S1012, obtaining the maximum carrying capacity of the intelligent forklift equipment.

[0074] Specifically, the maximum carrying quantity of the intelligent forklift equipment, for example, the maximum carrying quantity of the intelligent forklift equipment may be 36 bags.

[0075] Step S1013, based on the first stacking quantity, the second stacking quantity, the third stacking quantity, the maximum carrying quantity of the intelligent forklift, and the cargo stacking requirements in the length direction, width direction, and height direction of the target truck, select multiple different preset values ​​from positive integers to configure multiple specification combination results of the stacking stacking blocks.

[0076] Specifically, the preset value selected from the positive integers may be 3 or 4, and the cargo stacking requirements in the length direction, width direction, and height direction of the target truck are to allow full stacking requirements in the length direction, to allow full stacking requirements in the width direction, and not to allow full stacking requirements in the height direction. Multiple combinations of multiple different preset values ​​selected from positive integers to configure stacking blocks may result in a cargo stacking quantity formed by 3×3×3, or 3×3×4. Steps S102 to S106 are described in detail in the above embodiment and will not be repeated here.

[0077] Therefore, the freight loading method in the embodiment of the present invention configures a variety of specification combinations of stacking blocks for stacking the same type of goods based on the loading conditions of the target truck and the loading conditions of the intelligent forklift equipment carrying the stacking blocks, which is conducive to the intelligent forklift equipment stacking the same type of goods into goods of different target stacking specifications.

[0078] In an optional embodiment, the total weight constraint function based on the cargo loaded on the truck is created by the following formula (1):

[0079]

[0080] Among them, s i is the number of palletizing blocks of the i-th type required for preparation, a is the number of combinations of various specifications of palletizing blocks, max is to ensure that the total weight of the goods loaded on the truck is maximized, and q jj is the basic quantity of goods stacked in the j-direction in the stacking block of the i-th target stacking specification, q ik is the basic quantity of goods stacked in the k direction in the stacking block of the i-th target stacking specification, q il is the basic quantity of goods stacked along the l direction in the stacking block of the i-th target stacking specification, and w0 is the basic weight of the goods.

[0081] In the above formula (1), the numerator in formula (1) represents the total weight of the goods loaded on the truck, and the denominator in the formula represents the number of combinations of various specifications and the number of stacking blocks required for preparation. During the calculation process, the total weight of the goods loaded on the truck is ensured to be maximized.

[0082] The total weight constraint function of the cargo loaded on the truck is to prevent the total weight of the cargo from being too large and causing overloading.

[0083] In an optional embodiment, the constraint function of the total weight of the stacking block is created by the following formula:

[0084]

[0085] Among them, a is the number of combinations of various specifications of stacking blocks, q ij is the basic quantity of goods stacked in the j-direction in the stacking block of the i-th target stacking specification, q ik is the basic quantity of goods stacked in the k direction in the stacking block of the i-th target stacking specification, q il is the basic quantity of goods stacked in the stacking block of the i-th target stacking specification along the l-direction, s i is the number of palletizing blocks of the ith type required for preparation, and w is the upper limit of the truck load.

[0086] The constraint function of the total weight of the stacking blocks is to prevent the total weight of the stacking blocks loaded in the intelligent forklift equipment from being too large and causing overloading.

[0087] In an optional embodiment, the constraint function of the total volume of the stacking block is created by the following formula (2):

[0088]

[0089]

[0090] Among them, M i is the length of the palletized block, N i is the width of the palletized block, P i is the height of the stacking block, q ij is the basic quantity of goods stacked along the long side j in the i-th stacking block, q ik is the basic quantity of goods stacked along the width direction k in the i-th stacking block, q il is the basic quantity of goods stacked along the high side direction l in the i-th stacking block, m0 is the length of the goods, n0 is the width of the goods, p0 is the height of the goods, m is the length of the truck, n is the width of the truck, p is the height of the truck, Z1 is the width of the truck door, and Z2 is the height of the truck door.

[0091] The length, width and height of the stacking block are constrained by the above formula (3), thereby achieving the purpose of constraining the total volume of the stacking block.

[0092] The constraint function of the total volume of the stacking block is to prevent the total volume of the goods from exceeding the loading volume of the intelligent forklift equipment, which will affect the loading of the stacking block.

[0093] In an optional implementation, the constraint function of the intelligent forklift device is created by the following formula (4):

[0094] (m i ,N i ,P i )∈Veh (4)

[0095] Among them, Veh is the load-bearing volume requirement of the intelligent forklift equipment for loading goods, M i is the length of the palletized block, N i is the width of the palletized block, P i is the height of the stacking blocks.

[0096] By changing M in the above formula (4) i ,N i ,P i At the same time, constraints are applied to prevent the stacking blocks from rolling over. When the length, width and height of the stacking blocks are within the carrying volume of the intelligent forklift equipment, the preset conditions of the intelligent forklift equipment are met.

[0097] The constraint function of the intelligent forklift equipment is to prevent the cargo loading requirements of the intelligent forklift equipment from being violated when loading cargo.

[0098] If the freight loading method in the embodiment of the present disclosure is directly applied to the intelligent forklift equipment, the scene modeling and positioning of the intelligent forklift equipment is the key to ensure the efficient operation of the intelligent forklift equipment. Figure 4 As shown in the figure, by adopting SLAM (simultaneous localization and mapping) technology, the intelligent forklift equipment can self-position in unknown environments and create accurate maps of the surrounding environment in real time. Combined with lidar, camera and IMU (inertial measurement unit), the intelligent forklift equipment can perform high-precision environmental perception and obstacle detection, and achieve accurate navigation and operation in complex scenarios. In addition, the intelligent forklift equipment integrates multiple sensor data through advanced data fusion algorithms to improve positioning accuracy and operational reliability, ensuring stability and efficiency in a dynamically changing working environment.

[0099] The intelligent forklift equipment adopts Yolov8's target detection algorithm for the recognition of cargo palletizing in actual scenarios. In order to fully meet the use requirements of intelligent forklift equipment in open scenarios, it is necessary to fully collect various sample data in actual use scenarios, while taking into account the problem of high difficulty in sample collection in some special scenarios, such as inconsistent data distribution in cloudy and foggy environments. In order to solve the problems of diversity and imbalance in data distribution, the embodiments of the present disclosure adopt a variety of data enhancement methods to enhance and generate existing data and expand the sample size, including but not limited to traditional data transformations such as Crop and Rotation, image processing methods such as Frog and Contrastion, and similar sample generation based on diffusion model.

[0100] In addition, for the existing data, the disclosed embodiment performs data set distillation on the sample set and performs additional data enhancement and similar sample mining based on the distilled data. This task belongs to single-class multi-target detection. In order to enhance the generalization of the model, negative sample generation is required. Specifically, the disclosed embodiment generates negative samples and partial samples in a ratio of 1:1:3 by randomly moving the position of the detection frame, where the partial samples are data with an IOU between 0.4-0.6 with the positive samples, and the negative samples are data with an IOU less than 0.3.

[0101] Considering that the detection algorithm needs to be deployed in edge devices, it is necessary to consider both accuracy and device computing resource overhead and efficiency. Therefore, YoloV8 is used as the basic model. In addition, in order to improve the efficiency and performance of model training, a two-stage training method is used for model training. Stage 1: Based on positive and negative samples, the model backbone other than the detection head is trained by contrastive learning. Stage 2: Introduce some samples and use end-to-end training to train YoLov8 for single-class multi-target detection tasks.

[0102] In the actual reasoning stage after the model is deployed, the embodiment of the present disclosure counts the number of palletizing based on the number of detected target bounding boxes. In order to improve the accuracy of target positioning, the embodiment of the present disclosure uses a multi-camera multi-view fusion method to detect the type of palletizer in the current scene. Specifically, for the palletizing example in the current scene, the robot first goes around to collect information about the surrounding environment, and then calculates the palletizing overview in the current scene after building a rough three-dimensional description of the entire environment based on the NERF algorithm. After further detecting the palletizing at the current camera position, the hole position is located until the hole position that can move the target palletizing is obtained.

[0103] Based on the canny operator and combined with visual image information, a high-precision and fast rectangular hole positioning method is developed. The specific process can be composed of the following steps:

[0104] a) Gaussian filtering: There is a certain amount of noise in the image, which directly affects the rectangle detection effect. Therefore, Gaussian filtering is first performed on the target image to remove part of the noise information and achieve the effect of image smoothing.

[0105] b) Edge detection: For the smoothed image, an edge information detection algorithm is designed based on the canny operator. Specifically, by setting two thresholds: maxVal and minVal, the pixels are judged: those greater than maxVal are detected as edges, and those less than minVal are detected as non-edges. For the middle pixel, if it is adjacent to the pixel determined to be an edge, it is judged as an edge; otherwise, it is a non-edge.

[0106] c) Line fitting: This scheme uses the Hough operator for line detection and fitting. First, the image that has been binarized after canny detection is first mapped one by one into the parameter space of the polar coordinate system. Then, the points where the curves intersect more are found in the parameter space. These points are the straight lines detected in the original scattered point set.

[0107] d) Rectangular hole location: Rectangle detection is performed on the detected straight line image, and a certain threshold is set to filter the detected rectangles to finally obtain the target hole location.

[0108] Multi-information fusion: Combine the camera depth information to process the depth image data and improve the positioning accuracy of the rectangular hole.

[0109] In this embodiment, a freight loading device is also provided, which is used to implement the above-mentioned embodiments and preferred implementations, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0110] This embodiment provides a freight loading device, such as Figure 5 As shown, including:

[0111] A configuration module 51, configured to configure a plurality of combination results of specifications of stacking blocks for stacking the same type of goods based on the loading conditions of the target truck and the loading conditions of the intelligent forklift device carrying the stacking blocks;

[0112] A selection module 52 is used to select a target stacking specification of a stacking block from a plurality of specification combination results;

[0113] A setting module 53 is used to set a cargo stacking variable, where the cargo stacking quantity represents the cargo stacking quantity of the cargo stacked in different directions to a target stacking specification;

[0114] A generation module 54 is used to generate a cargo placement model based on a total weight constraint function of cargo loaded on a truck, a total weight constraint function of a stacking block, a total volume constraint function of a stacking block, a constraint function of an intelligent forklift device, and a cargo stacking quantity of a target stacking specification;

[0115] An optimization module 55 is used to optimize the stacking quantity of goods using a preset optimization algorithm so that the goods placement model meets preset conditions;

[0116] The loading module 56 is used to load the same type of goods stacked into stacking blocks according to the target stacking specifications into the target truck through the intelligent forklift equipment based on the optimized goods placement model.

[0117] In some optional embodiments, a constraint function based on the total weight of the cargo loaded on the truck is created using the above formula (1).

[0118] In some optional embodiments, the constraint function of the total weight of the stacking block is created by the above formula (2).

[0119] In some optional embodiments, the constraint function of the total volume of the stacking block is established by the above formula (3).

[0120] In some optional implementations, the constraint function of the intelligent forklift device is created by the above formula (4).

[0121] In some optional implementations, the optimization module includes:

[0122] An initial solution determination submodule, for using cargo stacking variables as an initial solution for a preset optimization algorithm;

[0123] The stacking quantity determination submodule is used to adjust the cargo stacking variables corresponding to the initial solution according to the neighborhood search method to re-determine the cargo stacking quantity of the target stacking specification;

[0124] A placement model generation submodule is used to generate an optimized cargo placement model based on a constraint function of the total weight of cargo loaded on a truck, a constraint function of the total weight of a stacking block, a constraint function of the total volume of a stacking block, a constraint function of an intelligent forklift device, and a re-determined target stacking specification cargo stacking quantity;

[0125] The placement model evaluation submodule is used to evaluate whether the optimized cargo placement model meets the preset conditions. If it does not meet the preset conditions, it returns to the step of stacking cargo variables until the preset conditions are met.

[0126] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0127] The freight loading device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0128] The embodiment of the present invention also provides a computer device having the above Figure 6 Freight loading device shown.

[0129] See also Figure 6 , Figure 6 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 6As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 10 is taken as an example.

[0130] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0131] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0132] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0133] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0134] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0135] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0136] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0137] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for loading freight, characterized in that: The method comprises: Based on the loading conditions of the target truck and the loading conditions of the intelligent forklift equipment carrying the stacking blocks, multiple combination results of specifications of the stacking blocks used to stack the same type of goods are configured; Selecting a target stacking specification of the stacking block from the plurality of specification combination results; Setting a cargo stacking variable, wherein the cargo stacking quantity represents the cargo stacking quantity of the cargo stacked in different directions to achieve the target stacking specification; Generate a cargo placement model based on a total weight constraint function of cargo loaded on a truck, a total weight constraint function of a stacking block, a total volume constraint function of a stacking block, a constraint function of an intelligent forklift device, and a cargo stacking quantity of the target stacking specification; Optimizing the cargo stacking variables using a preset optimization algorithm so that the cargo placement model meets preset conditions; Based on the optimized cargo placement model, the same type of cargo stacked into stacking blocks according to the target stacking specifications is loaded into the target truck by an intelligent forklift device.

2. The method according to claim 1, characterized in that: Based on the loading conditions of the target truck and the loading conditions of the intelligent forklift equipment carrying the palletizing blocks, multiple specification combination results of the palletizing blocks used to stack the same type of goods are configured, including; Obtaining a first stacking quantity, a second stacking quantity, and a third stacking quantity of the target truck, wherein the first stacking quantity is the maximum stacking quantity along the length direction of the target truck, the second stacking quantity is the maximum stacking quantity along the width direction of the target truck, and the third stacking quantity is the maximum stacking quantity along the height direction of the target truck; Get the maximum carrying quantity of the intelligent forklift equipment; Based on the first stacking quantity, the second stacking quantity, the third stacking quantity, the maximum carrying quantity of the intelligent forklift, and the cargo stacking requirements in the length direction, width direction, and height direction of the target truck, multiple different preset numerical values ​​are selected from positive integers to configure multiple specification combination results of the stacking stacking blocks.

3. The method according to claim 1, characterized in that The constraint function based on the total weight of the goods loaded on the truck is created by the following formula: Among them, s i is the number of palletizing blocks of the i-th type required for preparation, a is the number of combinations of various specifications of palletizing blocks, max is to ensure that the total weight of the goods loaded on the truck is maximized, and q ij is the basic quantity of goods stacked in the j-direction in the stacking block of the i-th target stacking specification, q ik is the basic quantity of goods stacked in the k direction in the stacking block of the i-th target stacking specification, q il is the basic quantity of goods stacked along the l direction in the stacking block of the i-th target stacking specification, and w0 is the basic weight of the goods.

4. The method according to claim 1, characterized in that: The constraint function of the total weight of the stacking block is created by the following formula: Among them, a is the number of combinations of various specifications of stacking blocks, q ij is the basic quantity of goods stacked in the j-direction in the stacking block of the i-th target stacking specification, q ik is the basic quantity of goods stacked in the k direction in the stacking block of the i-th target stacking specification, q il is the basic quantity of goods stacked in the stacking block of the i-th target stacking specification along the l-direction, s i is the number of palletizing blocks of the ith type required for preparation, and w is the upper limit of the truck load.

5. The method according to claim 1, characterized in that The constraint function of the total volume of the palletizing block is created by the following formula: M i =q ij ×m0,N i =q ik ×n0,P i =q il ×p0 M i ≤m,N i ≤n,P i ≤p,M i <Z1,N i <Z1,P i <Z2 Among them, M i is the length of the palletized block, N i is the width of the palletized block, P i is the height of the stacking block, q ij is the basic quantity of goods stacked along the long side j in the i-th stacking block, q ik is the basic quantity of goods stacked along the width direction k in the i-th stacking block, q il is the basic quantity of goods stacked along the high side direction l in the i-th stacking block, m0 is the length of the goods, n0 is the width of the goods, p0 is the height of the goods, m is the length of the truck, n is the width of the truck, p is the height of the truck, Z1 is the width of the truck door, and Z2 is the height of the truck door.

6. The method according to claim 1, characterized in that The constraint function of the intelligent forklift device is created by the following formula: (M i ,N i ,P i )∈Veh Among them, Veh is the load-bearing volume requirement of the intelligent forklift equipment for loading goods, M i is the length of the palletized block, N i is the width of the palletized block, P i is the height of the stacking blocks.

7. The method according to claim 1, characterized in that Optimizing the stacking variables using a preset optimization algorithm so that the cargo placement model meets preset conditions includes: Using the cargo stacking variable as an initial solution of the preset optimization algorithm; Adjusting the cargo stacking variables corresponding to the initial solution according to the neighborhood search method to re-determine the cargo stacking quantity of the target stacking specification; Generate an optimized cargo placement model based on the total weight constraint function of the cargo loaded on the truck, the total weight constraint function of the stacking blocks, the total volume constraint function of the stacking blocks, the constraint function of the intelligent forklift equipment, and the re-determined cargo stacking quantity of the target stacking specification; Evaluate whether the optimized cargo placement model meets the preset conditions. If not, return to the step of stacking cargo variables until the preset conditions are met.

8. A freight loading device, characterized in that: The device comprises: A configuration module, used for configuring multiple specification combination results of palletizing blocks for stacking the same type of goods based on the loading conditions of the target truck and the loading conditions of the intelligent forklift equipment carrying the palletizing blocks; A selection module, used for selecting a target stacking specification of a stacking block from the plurality of specification combination results; A setting module, used to set a cargo stacking variable, wherein the cargo stacking quantity represents the cargo stacking quantity of the cargo stacked in different directions to achieve the target stacking specification; A generation module, for generating a cargo placement model based on a total weight constraint function of cargo loaded on a truck, a total weight constraint function of a stacking block, a total volume constraint function of a stacking block, a constraint function of an intelligent forklift device, and a cargo stacking quantity of the target stacking specification; An optimization module, used to optimize the stacking quantity of the goods using a preset optimization algorithm so that the goods placement model meets preset conditions; The loading module is used to load the same type of goods stacked into stacking blocks according to the target stacking specifications into the target truck through an intelligent forklift device based on the optimized goods placement model.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the freight loading method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the freight loading method according to any one of claims 1 to 7.

11. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the freight loading method according to any one of claims 1 to 7.

Images