Method for determining cargo loading plan, electronic device and storage medium

Abstract

The application provides a method for determining a cargo loading scheme, an electronic device and a storage medium, and relates to the technical field of logistics management. The method comprises the following steps: acquiring loading space parameters and attribute information corresponding to each to-be-loaded cargo; sorting the to-be-loaded cargos according to the attribute information corresponding to each to-be-loaded cargo, to obtain a cargo sequence; using a beam search algorithm and a maximum empty space algorithm to obtain an initial loading scheme according to the cargo sequence, the loading space parameters and the attribute information corresponding to each to-be-loaded cargo; and using an adaptive large domain search algorithm to destroy and repair the initial loading scheme according to the initial loading scheme, the loading space parameters and the attribute information corresponding to each to-be-loaded cargo, to obtain a final loading scheme, which is used to indicate the final loading position of each to-be-loaded cargo in the loading space. Thus, the loading rate of the loading scheme is improved.

Description

Technical Field

[0001] This application relates to the field of logistics management technology, and in particular to a method for determining a cargo loading scheme, electronic equipment, and storage medium. Background Technology

[0002] In the logistics and transportation industry, cargo loading is a crucial step, directly impacting transportation safety, efficiency, cost, and customer satisfaction. Load factor, often referred to as space utilization rate, is a key indicator for measuring the efficiency of space utilization in cargo loading.

[0003] Currently, loading goods into the loading space mainly relies on the personal experience of the staff, who design loading plans based on the volume and weight of the goods, the dimensions of the loading space, and transportation requirements.

[0004] However, the volume and weight of goods vary, and transportation needs are also different. This requires staff to have strong planning capabilities. In long-distance dedicated line scenarios, the loading space is large and the number of goods is large, which makes the calculation complex for staff more complicated, resulting in a lower loading rate of the loading plan. Summary of the Invention

[0005] This application provides a method for determining a cargo loading plan, an electronic device, and a storage medium to address the problem that cargo volume and weight vary, transportation needs differ, requiring strong planning capabilities from staff, and in long-distance dedicated line scenarios with large loading spaces and numerous cargoes, the computational complexity for staff is high, resulting in a low loading rate of the obtained loading plan. This application aims to improve the loading rate of the loading plan.

[0006] In a first aspect, this application provides a method for determining a cargo loading scheme, comprising:

[0007] Obtain loading space parameters and attribute information corresponding to each cargo to be loaded. The attribute information is used to indicate the parameters that affect the loading position of the cargo in the loading space.

[0008] Based on the attribute information corresponding to each cargo to be loaded, the cargo to be loaded is sorted to obtain a cargo sequence;

[0009] Based on the cargo sequence, loading space parameters, and attribute information corresponding to each cargo to be loaded, the initial loading scheme is obtained by using the bundle search algorithm and the maximum free space algorithm. The bundle search algorithm is used to evaluate the loading position of the cargo to be loaded in the loading space, the maximum free space algorithm is used to construct the maximum free space in the loading space, and the initial loading scheme is used to indicate the initial loading position of each cargo to be loaded in the loading space.

[0010] According to the initial loading scheme, the loading space parameters, and the attribute information corresponding to each to-be-loaded cargo, an adaptive large-domain search algorithm is used to damage and repair the initial loading scheme to obtain a final loading scheme, which is used to indicate the final loading position of each to-be-loaded cargo in the loading space.

[0011] In a possible design, the attribute information includes size information, weight information, loading priority, and loading constraint.

[0012] In a possible design, according to the cargo sequence, the loading space parameters, and the attribute information corresponding to each to-be-loaded cargo, a beam search algorithm and a maximum empty space algorithm are used to obtain an initial loading scheme, including:

[0013] For the nth to-be-loaded cargo in the cargo sequence, a second candidate point available for the nth to-be-loaded cargo is determined from a plurality of first candidate points according to the attribute information corresponding to the nth to-be-loaded cargo, a first score corresponding to each second candidate point is calculated for the nth to-be-loaded cargo, the first candidate point is a position point corresponding to a maximum empty space in an EMS list of the loading space, and the maximum empty space is determined according to the attribute information corresponding to the to-be-loaded cargo loaded into the loading space and the loading space parameters; initially, n is 1.

[0014] According to the first score of the first K third candidate points in the second candidate points, the current K loading states of the loading space are updated, the loading state is used to indicate the loading position of the first to-be-loaded cargo to the nth to-be-loaded cargo in the loading space, and K is a positive integer.

[0015] According to the K loading states, the attribute information corresponding to the first to-be-loaded cargo to the nth to-be-loaded cargo, and the loading space parameters, the maximum empty space corresponding to the loading space in each loading state is calculated by using the maximum empty space algorithm, and the EMS list is updated.

[0016] n is updated to n+1 until the loading state includes the loading position of all to-be-loaded cargos in the loading space.

[0017] From the K loading states, a loading state is selected as the initial loading scheme.

[0018] In a possible design, the first score corresponding to each second candidate point for the nth to-be-loaded cargo is calculated, including:

[0019] For each second candidate point, according to attribute information and loading space parameters corresponding to the first to the n th to-be-loaded cargo respectively, a space utilization rate and a gravity center stability after the n th to-be-loaded cargo is loaded to the current loading space according to the position point indicated by the second candidate point are calculated; and a first score corresponding to the second candidate point is calculated according to the space utilization rate corresponding to the second candidate point and the gravity center stability corresponding to the second candidate point.

[0020] In a possible design, according to the initial loading scheme, the loading space parameters and the attribute information corresponding to each to-be-loaded cargo respectively, an adaptive large domain search algorithm is used to destroy and repair the initial loading scheme to obtain a final loading scheme, including:

[0021] According to the weight of the destruction operator, a target destruction operator is selected from the destruction operator list, and a destruction operation is performed on the to-be-loaded cargo in the initial loading scheme according to the target destruction operator to obtain a to-be-repaired loading scheme, the destruction operation being used to remove part of the to-be-loaded cargo from the initial loading scheme, and the to-be-repaired loading scheme being used to indicate the initial loading position of the remaining to-be-loaded cargo in the loading space and the empty position in the loading space;

[0022] According to the weight of the repair operator, a target repair operator is selected from the repair operator list, and a repair operation is performed on the empty position in the to-be-repaired loading scheme according to the target repair operator to obtain a to-be-determined loading scheme, the repair operation being used to reinsert the removed part of the to-be-loaded cargo into the empty position in the loading space;

[0023] According to the loading space parameters and the attribute information corresponding to each to-be-loaded cargo respectively, a second score corresponding to the to-be-determined loading scheme is calculated;

[0024] When the second score is greater than the best score, the best loading scheme is updated to the to-be-determined loading scheme; and the weight of the destruction operator is updated and the weight of the repair operator is updated every time the first preset number of times of the destruction operation and the repair operation are performed; wherein the initial best loading scheme is the initial loading scheme, and the best score is the second score corresponding to the best loading scheme;

[0025] The destruction operation, the repair operation and the calculation of the second score are continued to be performed until the second preset number of times of the destruction operation and the repair operation are performed.

[0026] The best loading scheme is determined as the final loading scheme.

[0027] In a possible design, the destruction operator list includes a random removal operator, a correlation removal operator and a worst removal operator, and the repair operator list includes a greedy insertion operator, a random insertion operator and an optimal insertion operator.

[0028] In a possible design, the second score corresponding to the to-be-determined loading scheme is calculated according to the loading space parameter and attribute information corresponding to each to-be-loaded cargo, and the second score corresponding to the to-be-determined loading scheme is calculated according to the space utilization rate, the center-of-gravity stability, and the support degree score of the to-be-determined loading scheme.

[0029] The space utilization rate, the center-of-gravity stability, and the support degree score of the to-be-determined loading scheme are calculated according to the loading space parameter and attribute information corresponding to each to-be-loaded cargo.

[0030] The second score corresponding to the to-be-determined loading scheme is calculated according to the space utilization rate, the center-of-gravity stability, and the support degree score.

[0031] In a possible design, the to-be-loaded cargos are sorted according to attribute information corresponding to each to-be-loaded cargo, to obtain a cargo sequence, including:

[0032] For each to-be-loaded cargo, a sorting weight corresponding to the to-be-loaded cargo is calculated according to size information, weight information, a loading priority, a first weight, a second weight, and a third weight of the to-be-loaded cargo.

[0033] The to-be-loaded cargos are sorted according to the sorting weight corresponding to each to-be-loaded cargo, to obtain the cargo sequence.

[0034] According to the cargo sequence, the loading space parameter, and the attribute information corresponding to each to-be-loaded cargo, the beam search algorithm and the maximum empty space algorithm are used to obtain an initial loading scheme, so that an initial loading scheme that meets the constraints of the loading space parameter and the attribute information corresponding to the to-be-loaded cargos and has a space utilization rate meeting the requirements is generated in a reasonable time based on the beam search algorithm. In the process of the beam search algorithm, the maximum empty space in the loading space is constructed based on the maximum empty space algorithm, the positions of all possible to-be-loaded cargos in the loading space are efficiently described, and it is ensured that the beam search algorithm can comprehensively and accurately enumerate all possible loading positions, thereby improving the quality of the generated initial loading scheme and helping to improve the loading rate. According to the initial loading scheme, the loading space parameter, and the attribute information corresponding to each to-be-loaded cargo, the adaptive large-domain search algorithm is used to destroy and repair the initial loading scheme, to obtain a final loading scheme, so that the initial loading scheme jumps out of the local optimum, and a final loading scheme with a higher space utilization rate is generated, thereby significantly improving the loading rate.

[0035] In a second aspect, the present application provides a determination apparatus, comprising: a module for executing the determination method of the cargo loading scheme in the first aspect and any possible design of the first aspect.

[0036] In a third aspect, the present application provides an electronic device, comprising a first processor, wherein the first processor implements the determination method of the cargo loading scheme in the first aspect and any possible design of the first aspect when executing a computer executable program or instruction in a memory.

[0037] In a fourth aspect, the present application provides an electronic device, comprising at least one memory and at least one second processor, wherein the memory stores a computer executable program or instruction, and the second processor implements the determination method of the cargo loading scheme in the first aspect and any possible design of the first aspect when executing the computer executable program or instruction.

[0038] In a fifth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer executable program or instruction, and the computer executable program or instruction is executed by a processor to implement the determination method of the cargo loading scheme in the first aspect and any possible design of the first aspect.

[0039] In a sixth aspect, the present application provides a computer program product, comprising: an execution instruction, wherein the execution instruction is stored in a readable storage medium, at least one processor of an electronic device can read the execution instruction from the readable storage medium, and the at least one processor executes the execution instruction to enable the electronic device to implement the determination method of the cargo loading scheme in the first aspect and any possible design of the first aspect.

[0040] The above description is only a summary of the technical solutions of the embodiments of the present application, in order to enable the technical means of the embodiments of the present application to be more clearly understood, and can be implemented according to the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the embodiments of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 A flowchart of a cargo loading scheme determination method provided by an embodiment of the present application.

[0042] Figure 2 A flowchart of a method for obtaining an initial loading scheme provided by an embodiment of the present application.

[0043] Figure 3 A schematic diagram of a maximum empty space provided by an embodiment of the present application.

[0044] Figure 4 A schematic diagram of a loading state provided by an embodiment of the present application Figure 1 .

[0045] Figure 5 A schematic of a loading state provided for an embodiment of the present application Figure 2 .

[0046] Figure 6 A schematic of a loading state provided for an embodiment of the present application Figure 3 .

[0047] Figure 7 A schematic of a loading state provided for an embodiment of the present application Figure 4 .

[0048] Figure 8 A schematic of a loading state provided for an embodiment of the present application Figure 5 .

[0049] Figure 9 A flowchart of a method for calculating a first score provided for an embodiment of the present application.

[0050] Figure 10 A flowchart of a method for obtaining a final loading plan provided for an embodiment of the present application.

[0051] Figure 11 A flowchart of a method for calculating a second score provided for an embodiment of the present application.

[0052] Figure 12 A flowchart of a method for obtaining a sequence of goods provided for an embodiment of the present application.

[0053] Figure 13 A structural schematic of a determining device provided for an embodiment of the present application.

[0054] Figure 14 A structural schematic of an electronic device provided for an embodiment of the present application Figure 1 .

[0055] Figure 15 A structural schematic of an electronic device provided for an embodiment of the present application Figure 2 . DETAILED DESCRIPTION

[0056] In this application, "at least one" means one or more, "multiple" means two or more. The "and / or" describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after it. "At least one of the following" or similar expressions means any combination of these items, including single item or any combination of multiple items. For example, at least one of a, b or c alone can represent: a alone, b alone, c alone, combination of a and b, combination of a and c, combination of b and c, or combination of a, b and c, where a, b and c can be single or multiple. In addition, the terms "first", "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0057] The terms "center", "longitudinal", "transverse", "upper", "lower", "left", "right", "front", "back", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, which is only for the convenience of describing the application and simplifying the description, and cannot be understood as indicating or implying that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the application.

[0058] The terms "connected" and "connected" should be broadly understood, for example, the "connected" or "connected" of the circuit structure can mean not only physical connection, but also electrical connection or signal connection, for example, it can be directly connected, that is, physically connected, or indirectly connected through at least one element in the middle, as long as the circuit is connected, it can also be the internal connection of two elements; In addition to signal connection through circuit, signal connection through media medium, such as radio waves, can also be referred to. For those skilled in the art, the specific meaning of the above terms in this application can be understood according to the specific circumstances.

[0059] In related technologies, the following methods 1 and 2 can generally be used to generate loading schemes.

[0060] Method 1: Three-dimensional packing method based on genetic algorithm (GA). This method models the loading problem as a three-dimensional packing problem (3D Bin Packing Problem) and solves it using a genetic algorithm. Specifically, first, encode the goods, convert the size, weight, loading position, etc. Information of each cargo into a chromosome representation; Through genetic operations such as selection, crossover, mutation, search for the optimal loading scheme in the solution space.

[0061] Method 2: Online loading algorithm based on heuristic rules. This algorithm presets a series of loading rules such as "heavy goods at the bottom and light goods at the top", "large first and small later", "corner priority" and the like, and guides the loading process of goods through a rule engine. According to the time sequence of the arrival of goods, the algorithm sequentially finds the best loading position for each goods.

[0062] However, in the above-mentioned method 1, the genetic algorithm is prone to fall into a local optimal solution, especially in the special line logistics scene with a large number of goods types and complex constraint conditions, it is difficult to guarantee the global optimality; secondly, the genetic algorithm converges slowly, and for the logistics loading scene that needs to respond quickly, the time cost is too high; finally, this method mainly focuses on single vehicle loading optimization, lacks intelligent processing of goods combination selection, and cannot effectively solve the optimal combination selection problem of multi-ticket goods in special line logistics.

[0063] In the above-mentioned method 2, this method excessively depends on the quality and integrity of the loading rules, and is difficult to adapt to the changing actual logistics scene. First, the heuristic rules are often based on local information to make decisions, lack a global optimization perspective, and are prone to cause subsequent goods to be unable to be effectively loaded; second, the design and tuning of rules require a large amount of expert experience, and when facing new goods types or loading requirements, rules need to be redefined; third, this method uses a greedy strategy and cannot back up once a loading decision is made, lacking the ability to adjust and optimize the existing loading scheme; fourth, in terms of goods combination selection, this method usually adopts a first-come-first-serve strategy and cannot realize intelligent optimization selection of goods combination.

[0064] Based on this, the present application provides a method for determining a goods loading scheme, an electronic device and a storage medium. According to the loading space parameters and the attribute information of the goods to be loaded, a beam search (BS) algorithm is used to maintain a plurality of candidate loading schemes, and an optimal loading scheme is selected from the plurality of candidate loading schemes as an initial loading scheme. In the process of generating the initial loading scheme, an empty max space (EMS) algorithm is also used for space management to improve the loading rate. After determining the initial loading scheme, an adaptive large neighborhood search (ALNS) algorithm is used to further optimize the initial loading scheme to obtain a final loading scheme with a higher loading rate, thereby significantly improving the loading rate.

[0065] Among them, the method for determining a goods loading scheme provided by the present application is executed by an electronic device, or by a determination device in the electronic device.

[0066] The electronic device can be a server, a desktop computer, a mobile phone, a tablet computer, a notebook computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, or the like. The determining apparatus can be implemented by a combination of software and / or hardware. For example, the determining apparatus can be a central processing unit (CPU). Alternatively, the determining apparatus can be an application (APP), a webpage, or a public account, or the like.

[0067] For simplicity of description, embodiments of the present application are described by taking the determining apparatus as an example.

[0068] In the following, embodiments of the present application will be described in combination with Figures 1 to 12 The method for determining a cargo loading scheme provided by an embodiment of the present application will be described in detail.

[0069] Please refer to Figure 1 , Figure 1 A flowchart of a method for determining a cargo loading scheme provided by an embodiment of the present application is shown in FIG. 1. As shown in FIG. 1, the method comprises the following steps. Figure 1

[0070] In S101, the determining apparatus acquires loading space parameters and attribute information corresponding to each cargo to be loaded.

[0071] The loading space refers to a fixed space boundary in which the cargo to be loaded is placed, for example, a vehicle cabin, a container, a ship cabin, an aircraft cabin, or the like. The loading space parameters are used to indicate the size of the loading space, and can include the length, width, and height of the loading space. The determining apparatus can acquire the loading space parameters through a size measuring device.

[0072] The attribute information is used to indicate parameters affecting the loading position of the cargo to be loaded in the loading space. The attribute information can include size information, weight information, loading priority, and loading constraints.

[0073] The size information is used to indicate the size of the cargo to be loaded, and can include the length, width, and height. The determining apparatus can acquire the size information through a size measuring device.

[0074] The weight information is used to indicate the weight of the cargo to be loaded. The determining apparatus can acquire the weight information based on an electronic scale.

[0075] ​The loading priority is used to indicate the priority of loading the to-be-loaded cargo into the loading space. The determining device can use a score or a grade to measure the loading priority. For example, if the loading priority of a to-be-loaded cargo is 100 points, it means that the to-be-loaded cargo is the most priority to be loaded. If the loading priority of a to-be-loaded cargo group is 0 points, it means that the to-be-loaded cargo is not priority to be loaded.

[0076] The loading constraint is used to indicate the constraint condition when the to-be-loaded cargo is loaded into the loading space. The loading constraint can be “non-reversible”, “non-load-bearing”, “reversible and load-bearing”, or “non-reversible and load-bearing”, etc. The determining device can use an identifier to mark the loading constraint. For example, the identifier “0” can be defined as “non-reversible”, the identifier “1” can be defined as “non-load-bearing”, the identifier “2” can be defined as “reversible and load-bearing”, and the identifier “3” can be defined as “non-reversible and load-bearing”, so as to distinguish different loading constraints.

[0077] The determining device can enter the identifier of each to-be-loaded cargo through a radio frequency identification (RFID) reader, and associate the attribute information of the to-be-loaded cargo through the identifier of each to-be-loaded cargo.

[0078] On the basis of the above example, the attribute information includes size information, weight information, loading priority, and loading constraint. The to-be-loaded cargo includes cargo A, cargo B, cargo C, and cargo D. The attribute information corresponding to each to-be-loaded cargo can be shown in Table 1 as follows:

[0079] Table 1

[0080]

[0081] Therefore, the determining device obtains the loading space parameters and the attribute information corresponding to each to-be-loaded cargo, so as to generate a loading scheme that adapts to the loading space, the to-be-loaded cargo, and the loading demand.

[0082] In S102, the determining device sorts the to-be-loaded cargo according to the attribute information corresponding to each to-be-loaded cargo, to obtain a cargo sequence.

[0083] In order to ensure that the cargo can be loaded in the loading space according to the demand, the determining device can sort the to-be-loaded cargo, so as to guide the cargo loading sequence when generating the loading scheme subsequently. The cargo loading sequence can directly affect the loading rate and the feasibility of the loading scheme. The determining device can sort the to-be-loaded cargo based on the loading demand.

[0084] For example, if the demand is to place the large-volume goods first and then the small-volume goods, the determining apparatus can calculate the volume of the to-be-loaded goods according to the size information, and sort the to-be-loaded goods in descending order of volume to obtain the goods sequence.

[0085] For another example, if the demand is to follow the principle of “heavy goods at the bottom and light goods at the top”, the determining apparatus can sort the to-be-loaded goods in descending order of weight according to the weight information to obtain the goods sequence.

[0086] For another example, if the demand is to comprehensively consider the volume, weight and loading priority of the goods, the determining apparatus can score the to-be-loaded goods according to the size information, weight information, loading priority and respective weights, and sort the to-be-loaded goods in descending order of score to obtain the goods sequence.

[0087] Based on this, the determining apparatus can obtain the goods sequence, thereby providing a reasonable goods loading order for subsequent generation of the loading scheme, ensuring the feasibility of the generated loading scheme and improving the quality of the generated loading scheme, thereby helping to improve the loading rate.

[0088] S103, the determining apparatus obtains an initial loading scheme by using a beam search algorithm and a maximum empty space algorithm according to the goods sequence, the loading space parameters and the attribute information corresponding to each to-be-loaded good.

[0089] The beam search algorithm is used to evaluate the loading position of the to-be-loaded goods in the loading space, and the maximum empty space algorithm is used to construct the maximum empty space in the loading space.

[0090] The initial loading scheme is used to indicate the initial loading position of each to-be-loaded good in the loading space.

[0091] The beam search algorithm is a heuristic search algorithm that can optimize in a large search space. Specifically, the determining apparatus can sequentially take the to-be-loaded goods from the goods sequence as the current goods, and then enumerate all possible loading positions for the current goods based on the maximum empty space in the loading space constructed by the maximum empty space algorithm. The space utilization rate, center of gravity stability and other parameters after loading the current goods are calculated by using the loading space parameters and the attribute information corresponding to each to-be-loaded good. Each loading scheme is scored by using these parameters. The determining apparatus can set the beam width of the beam search to K, that is, only the top K loading schemes with the highest score are retained, and then the next to-be-loaded good is placed based on the K loading schemes, until the initial loading position of all to-be-loaded goods in the goods sequence in the loading space is determined.

[0092] Since the beam search algorithm only retains K candidate schemes each time, the amount of calculation can be greatly reduced, and the shortcoming of the greedy algorithm of easily falling into local optimization can be avoided. Therefore, based on the beam search algorithm, the determination apparatus can generate an initial loading scheme that meets the constraints of the loading space parameters and the attribute information corresponding to the to-be-loaded goods and the space utilization rate meets the requirements within a reasonable time. In the process of the beam search algorithm, the determination apparatus uses the maximum empty space algorithm to construct the maximum empty space in the loading space, thereby efficiently describing the positions of all possible to-be-loaded goods in the loading space, ensuring that the beam search algorithm can comprehensively and accurately enumerate all possible loading positions, ensuring the space utilization rate, and thereby improving the quality of the generated initial loading scheme.

[0093] In S104, the determination apparatus uses the adaptive large-domain search algorithm to destroy and repair the initial loading scheme according to the initial loading scheme, the loading space parameters, and the attribute information corresponding to each to-be-loaded good, to obtain a final loading scheme.

[0094] The final loading scheme is used to indicate the final loading position of each to-be-loaded good in the loading space.

[0095] Considering that the initial loading scheme is not a globally optimal scheme, based on this, the determination apparatus can use the adaptive large-domain search algorithm to iteratively destroy and repair the initial loading scheme, dynamically adjust the initial loading scheme, make the initial loading scheme jump out of the local optimum, and thereby generate a globally better scheme.

[0096] The determination apparatus can adaptively select a destruction operator to destroy the initial loading scheme, and then adaptively select a repair operator to repair the destroyed initial loading scheme, and score the repaired initial loading scheme based on the space utilization rate and the like. After multiple iterations, a loading scheme with the highest score is finally obtained, thereby obtaining a globally better scheme with a higher space utilization rate, and improving the loading rate of the final loading scheme.

[0097] In the embodiment of the present application, the determining device obtains the loading space parameters and the attribute information corresponding to each to-be-loaded cargo, so as to generate a loading scheme that adapts to the loading space, the to-be-loaded cargo and the loading demand. The determining device sorts the to-be-loaded cargo according to the attribute information corresponding to each to-be-loaded cargo, to obtain a cargo sequence, thereby providing a reasonable cargo loading order for subsequent generation of the loading scheme, ensuring the feasibility of the generated loading scheme and improving the quality of the generated loading scheme, thereby helping to improve the loading rate. The determining device obtains an initial loading scheme by using the beam search algorithm and the maximum empty space algorithm according to the cargo sequence, the loading space parameters and the attribute information corresponding to each to-be-loaded cargo, thereby generating an initial loading scheme that meets the constraints of the loading space parameters and the attribute information corresponding to the to-be-loaded cargo and has a space utilization rate meeting the requirements, based on the beam search algorithm, within a reasonable time. In the process of the beam search algorithm, the maximum empty space algorithm is used to construct the maximum empty space in the loading space, efficiently describe the positions of all possible to-be-loaded cargos in the loading space, and ensure that the beam search algorithm can comprehensively and accurately enumerate all possible loading positions, thereby improving the quality of the generated initial loading scheme and helping to improve the loading rate. The determining device obtains a final loading scheme by using the adaptive large domain search algorithm to destroy and repair the initial loading scheme according to the initial loading scheme, the loading space parameters and the attribute information corresponding to each to-be-loaded cargo, thereby enabling the initial loading scheme to jump out of the local optimum, generating a final loading scheme with a higher space utilization rate, and thereby significantly improving the loading rate.

[0098] Based on the above exemplary description, the following introduces a method for obtaining an initial loading scheme. Figure 2

[0099] Please refer to Figure 2 , Figure 2 for a flowchart of a method for obtaining an initial loading scheme provided by an embodiment of the present application. As shown in Figure 2 , the method comprises the following steps.

[0100] S201, the determining device determines, for the nth to-be-loaded cargo in the cargo sequence, a usable second candidate point from a plurality of first candidate points according to the attribute information corresponding to the nth to-be-loaded cargo, and calculates a first score corresponding to each second candidate point.

[0101] wherein, initially, n is 1.

[0102] wherein, the first candidate point is a position point corresponding to a maximum empty space in an empty max space (EMS) list corresponding to the loading space.

[0103] ​The maximum empty space is determined according to attribute information of the to-be-loaded cargo loaded in the loading space and loading space parameters. Initially, no cargo is loaded in the loading space, and therefore the EMS list only includes one maximum empty space, that is, the loading space. A position point corresponding to the maximum empty space is a position point in the maximum empty space. The determining apparatus can map the loading space to a space rectangular coordinate system and determine any corner point of the loading space as a coordinate origin, so that the first candidate point can be the coordinate origin initially. After the to-be-loaded cargo is loaded in the loading space, the determining apparatus can determine the maximum empty space and the first candidate point based on attribute information of the loaded cargo and loading space parameters.

[0104] The EMS list can record the starting coordinates and size of the maximum empty space, and the starting coordinates are the coordinates of the first candidate point, so that the determining apparatus locates the maximum empty space and determines a position that can be used to place the to-be-loaded cargo based on the maximum empty space.

[0105] Since the to-be-loaded cargo has loading constraints, the determining apparatus first determines an available second candidate point from the first candidate point according to attribute information of the nth to-be-loaded cargo. For example, the nth to-be-loaded cargo is cargo A, and the loading constraint of cargo A is “not to be turned over”. When determining the second candidate point, the determining apparatus should ensure that cargo A can be placed at the position point indicated by the candidate point without turning over cargo A.

[0106] For different second candidate points, the nth to-be-loaded cargo has different loading effects when loaded in the second candidate points, for example, placed in different positions, which will affect parameters such as space utilization and center of gravity stability. Based on this, the determining apparatus can calculate a first score corresponding to each second candidate point for the nth to-be-loaded cargo, so as to determine a second candidate point that is more matched with the nth to-be-loaded cargo.

[0107] S202, the determining apparatus updates K loading states of the loading space according to the first K third candidate points with the maximum first score in the second candidate points.

[0108] The loading state is used to indicate loading positions of the 1st to-be-loaded cargo to the nth to-be-loaded cargo in the loading space.

[0109] K is a positive integer; K is the beam width of the beam search algorithm, which can define the width of the beam search algorithm. K can be 2, for example.

[0110] The determining device screens out K third candidate points with the first high scores from the available second candidate points, and generates a loading state based on the third candidate points, thereby enumerating all available and high-scored loading modes, so that K loading states can be maintained at the same time, thereby improving the comprehensiveness of determining the loading scheme, avoiding missing the optimal scheme, and further helping to improve the loading rate.

[0111] In S203, the determining device respectively calculates the maximum empty space corresponding to the loading space in each loading state according to the K loading states, the attribute information corresponding to the first to nth to-be-loaded cargos, and the loading space parameters, and updates the EMS list. The value of n is updated to n+1 until the loading state includes the loading positions of all to-be-loaded cargos in the loading space.

[0112] After the K loading states are determined, the maximum empty space changes because the loading space has placed the first to nth to-be-loaded cargos. For each loading state, the determining device needs to delete the space occupied by the first to nth to-be-loaded cargos in the loading space, and re-determine the corresponding maximum empty space based on the remaining loading space according to the attribute information corresponding to the first to nth to-be-loaded cargos and the loading space parameters, and update the EMS list, so as to perform the next iteration.

[0113] Therefore, by using the maximum empty space algorithm, the determining device can efficiently and accurately determine all positions available for placing the to-be-loaded cargos in the process of determining the initial loading scheme, thereby improving the efficiency of determining the loading scheme and helping to improve the loading rate.

[0114] The determining device updates the value of n to n+1 and starts to determine the loading position of the next cargo in the cargo sequence.

[0115] The above process will be described below in combination with Figures 3 to 8 .

[0116] It should be noted that the loading space, the maximum empty space, and the cargos in the present application are all objects or spaces in a three-dimensional space. The loading space, the maximum empty space, and the cargos are represented as two-dimensional rectangles in the present application, which is for the convenience of description and does not mean that the loading space, the maximum empty space, and the cargos are two-dimensional graphics. Figures 3 to 8

[0117] The cargo sequence is [cargo A, cargo C, cargo B], and K is 2. As shown in FIG. 4, the first to third to-be-loaded cargos are placed in the loading space according to the first to third candidate points, and the maximum empty space corresponding to the first to third candidate points is calculated. Figure 3 ​As shown, initially, the dashed rectangle represents the maximum free space, the initial maximum free space is the loading space, and point P0 is the initial first candidate point. The determination device starts processing the goods A, and determines that the goods A can be placed at point P0 according to the attribute information corresponding to the goods A and the loading space parameters. Since there is only one first candidate point, the determination device directly determines point P0 as the second candidate point, and calculates the first score of the goods A corresponding to point P0. Since the first score is also only one, initially, the loading state obtained by the determination device is as shown in Figure 4 , that is, the goods A is placed at point P0.

[0118] Based on the loading state as shown in Figure 4 , the determination device calculates the maximum free space corresponding to the loading space in the loading state according to the attribute information corresponding to the goods A and the loading space parameters through the maximum free space algorithm. Figure 4 As shown, the maximum free space corresponding to the loading space in the loading state is a dashed rectangle ① and a dashed rectangle ②, wherein point P1 is the first candidate point corresponding to the dashed rectangle ①, and point P2 is the first candidate point corresponding to the dashed rectangle ②.

[0119] The determination device starts processing the goods C, and determines that the goods A can be placed at point P1 and point P2 according to the attribute information corresponding to the goods A and the loading space parameters. The determination device determines point P1 and point P2 as the second candidate point, and calculates the first score of the goods C corresponding to point P1 and the first score corresponding to point P2. The determination device determines that the first two scores are the first score of the goods C corresponding to point P1 and the first score of the goods C corresponding to point P2, thereby obtaining two loading states as shown in Figure 5 and Figure 6 , that is, Figure 5 represents that the goods C is placed at point P1, Figure 6 represents that the goods C is placed at point P2.

[0120] Based on the loading state as shown in Figure 5 , the determination device calculates the maximum free space corresponding to the loading space in the loading state according to the attribute information corresponding to the goods C and the loading space parameters through the maximum free space algorithm. Figure 5 As shown, the maximum free space corresponding to the loading space in the loading state is a dashed rectangle ③, a dashed rectangle ④ and a dashed rectangle ⑤, wherein point P3 is the first candidate point corresponding to the dashed rectangle ③, point P4 is the first candidate point corresponding to the dashed rectangle ④, and point P5 is the first candidate point corresponding to the dashed rectangle ⑤.

[0121] Based on the loading state as shown in Figure 6 , the determination device calculates the maximum free space corresponding to the loading space in the loading state according to the attribute information corresponding to the goods C and the loading space parameters through the maximum free space algorithm. Figure 6The maximum empty space corresponding to the loading space in the shown loading state is respectively a dashed rectangle 6, a dashed rectangle 7 and a dashed rectangle 8, wherein a point P6 is a first candidate point corresponding to the dashed rectangle 6, a point P7 is a first candidate point corresponding to the dashed rectangle 7, and a point P8 is a first candidate point corresponding to the dashed rectangle 8.

[0122] The determining device starts processing the goods B, and determines that the goods B can be placed at the point P3, the point P5, the point P7 and the point P8 according to the attribute information corresponding to the goods B and the loading space parameters. The determining device determines the point P3, the point P5, the point P7 and the point P8 as second candidate points, and calculates the first scores corresponding to the goods B and the point P3, the point P5, the point P7 and the point P8 respectively. Figure 7 and Figure 8 as shown, Figure 7 indicates that the goods B are placed at the point P5, Figure 8 indicates that the goods B are placed at the point P8.

[0123] Based on this, Figure 7 and Figure 8 the loading state shown in the figure includes the loading positions of all the to-be-loaded goods in the loading space, and the determining device obtains two loading states.

[0124] S204, the determining device selects one of the K loading states as an initial loading scheme.

[0125] The determining device can score the K loading states based on the barycentric stability and the space utilization, and determine the loading state with the highest score as the initial loading scheme. Alternatively, the determining device can also randomly select one of the K loading states as the initial loading scheme.

[0126] Based on the above exemplary description, the following introduces a method for calculating the first score for each second candidate point. Figure 9

[0127] Please refer to Figure 9 , Figure 9 a flowchart of a method for calculating the first score provided by an embodiment of the present application. As shown in the figure, for each second candidate point, the method includes: Figure 9

[0128] S301, the determining device calculates the space utilization and the barycentric stability after the nth to-be-loaded goods are loaded into the current loading space according to the positions indicated by the second candidate points according to the attribute information corresponding to the 1st to-be-loaded goods to the nth to-be-loaded goods and the loading space parameters.

[0129] ​​The determining apparatus can calculate the volume of the goods loaded into the loading space according to the size information corresponding to the first to the nth goods to be loaded, calculate the volume of the loading space according to the loading space parameters, and determine the space utilization ratio as the ratio of the volume of the goods loaded into the loading space to the volume of the loading space.

[0130] The determining apparatus can calculate the coordinates of the center of gravity of the goods loaded into the loading space according to the size information corresponding to the first to the nth goods to be loaded, and calculate the stability of the center of gravity according to the length and the width of the loading space in the loading space parameters.

[0131] The determining apparatus calculates a first score corresponding to the second candidate point according to the space utilization ratio corresponding to the second candidate point and the stability of the center of gravity corresponding to the second candidate point.

[0132] For each second candidate point, the determining apparatus can calculate the first score according to Formula I as follows:

[0133] Formula I;

[0134] wherein, the first score is, the fourth weight is, the space utilization ratio is, the fifth weight is, the stability of the center of gravity is.

[0135] Therefore, the determining apparatus can score the second candidate points by comprehensively considering the space utilization ratio and the stability of the center of gravity after the goods are loaded into the loading space, thereby improving the feasibility of the determined loading scheme.

[0136] Based on the above exemplary description, the following introduces a method for obtaining a final loading scheme. Figure 10

[0137] Please refer to Figure 10 , Figure 10 FIG. 1 is a flowchart of a method for obtaining a final loading scheme according to an embodiment of the present application. As shown in FIG. 1, the method comprises the following steps. Figure 10

[0138] S401, the determining apparatus selects a target destruction operator from a destruction operator list according to the weight of the destruction operator.

[0139] The destruction operator list includes a plurality of destruction operators, for example, the destruction operator list includes a random removal operator, a correlation removal operator and a worst removal operator. Each destruction operator has a weight, which is used to indicate the probability of the determining apparatus selecting the destruction operator. Initially, the weight of each destruction operator is consistent. ​​

[0140] wherein the random removal operator is configured to randomly select r goods removals, r being a positive integer. The correlation removal operator is configured to remove a combination of goods that are adjacent in spatial position. The worst removal operator is configured to remove a good that contributes the least to an objective function of an adaptive large domain search algorithm.

[0141] S402, the determination device determines to perform a destruction operation on the to-be-loaded goods in the initial loading scheme according to a target destruction operator, to obtain a to-be-repaired loading scheme.

[0142] wherein the destruction operation is configured to remove part of the to-be-loaded goods from the initial loading scheme, and the to-be-repaired loading scheme is configured to indicate initial loading positions of the remaining to-be-loaded goods in the loading space and empty positions in the loading space.

[0143] For example, the target destruction operator is a random removal operator, and the determination device randomly removes r goods from the initial loading scheme to obtain the to-be-repaired loading scheme.

[0144] S403, the determination device selects a target repair operator from a repair operator list according to a weight of the repair operator.

[0145] wherein the repair operator list includes a plurality of repair operators, for example, the repair operator list includes a greedy insertion operator, a random insertion operator and an optimal insertion operator. Each repair operator has a weight, and the weight is used to indicate the probability of the determination device selecting the repair operator. Initially, the weight of each repair operator is consistent.

[0146] wherein the greedy insertion operator is configured to insert goods according to a maximum benefit principle, and the maximum benefit principle can be measured by space utilization and barycenter stability. The random insertion operator is configured to randomly insert goods. The optimal insertion operator is configured to find the best insertion position and insert goods, and the best insertion position can be measured by space utilization and barycenter stability.

[0147] S404, the determination device performs a repair operation on the empty positions in the to-be-repaired loading scheme according to the target repair operator, to obtain a to-be-determined loading scheme.

[0148] wherein the repair operation is configured to re-insert the removed part of the to-be-loaded goods into the empty positions in the loading space.

[0149] In the destruction operation, the determination device removes part of the to-be-loaded goods, and in the repair operation, the determination device re-inserts the removed part of the to-be-loaded goods into the empty positions in the loading space based on the target repair operator, in order to obtain a better loading scheme than before the destruction, to obtain the to-be-determined loading scheme.

[0150] S405, the determination device calculates a second score corresponding to the to-be-determined loading scheme according to the loading space parameters and the attribute information corresponding to each to-be-loaded good.

[0151] To evaluate whether the to-be-determined loading scheme is a better loading scheme, the determining apparatus can score the to-be-determined loading scheme by using the loading space parameters and the attribute information respectively corresponding to each to-be-loaded cargo. For example, the determining apparatus can respectively calculate the space utilization, the center-of-gravity stability, and the support degree score of the to-be-determined loading scheme, so as to evaluate the to-be-determined loading scheme.

[0152] S406, the determining apparatus determines whether the second score is greater than the best score.

[0153] When the second score is greater than the best score, S407 is performed; when the second score is less than or equal to the best score, S408 is performed.

[0154] The initial best loading scheme is the initial loading scheme, and the best score is the second score corresponding to the best loading scheme.

[0155] Based on this, the determining apparatus can determine whether the to-be-determined loading scheme is a better loading scheme through the second score. If the second score is greater than the best score, the determining apparatus updates the best loading scheme to the to-be-determined loading scheme, so as to ensure that a better loading scheme can be obtained in each iteration process.

[0156] S407, the determining apparatus updates the best loading scheme to the to-be-determined loading scheme.

[0157] S408, the determining apparatus determines whether the first preset number of times of the destruction operation and the repair operation have been performed after the last update of the weight.

[0158] When the first preset number of times of the destruction operation and the repair operation have been performed after the last update of the weight, S409 is performed; when the first preset number of times of the destruction operation and the repair operation have not been performed after the last update of the weight, S4010 is performed.

[0159] The determining apparatus can update the weight of the destruction operator and the weight of the repair operator each time the first preset number of times of the destruction operation and the repair operation are performed, so as to preferentially select the destruction operator and the repair operator that can obtain the best loading scheme in the subsequent iteration process.

[0160] The first preset number of times can be set according to requirements. For example, the first preset number of times is 100 times, that is, the determining apparatus updates the weight of the destruction operator and the weight of the repair operator each time 100 times of the destruction operation and the repair operation are performed.

[0161] S409, the determining apparatus updates the weight of the destruction operator and the weight of the repair operator.

[0162] In some examples, the determining apparatus can update the weight of the damage operator or update the weight of the repair operator by Formula Two.

[0163] Formula Two;

[0164] wherein, is the weight of the target operator after being updated, is the weight of the target operator before being updated, is a weight update coefficient, ∈(0, 1), is the sum of the second scores obtained when the target operator is used to damage or repair in the first preset number of times of damage operation and repair operation after the last weight update, is the number of times the target operator is used in the first preset number of times of damage operation and repair operation after the last weight update.

[0165] wherein, the target operator is one of the damage operators in the damage operator list or one of the repair operators in the repair operator list.

[0166] Based on this, the determining apparatus can dynamically update the weights of the damage operators and the repair operators according to the performance of each operator in the first preset number of times of damage or repair, thereby increasing the weight of the operator with a higher second score and decreasing the weight of the operator with a lower second score. By updating the weight of the damage operator and updating the weight of the repair operator, the determining apparatus can use the operator that can generate a better loading scheme more in the iteration process, thereby helping to improve the search effect of the adaptive large-domain search algorithm to find a better loading scheme, and further helping to improve the loading rate of the finally obtained loading scheme.

[0167] S4010, the determining apparatus judges whether the second preset number of times of damage operation and repair operation has been performed.

[0168] If the second preset number of times of damage operation and repair operation has been performed, the determining apparatus performs S4011; if the second preset number of times of damage operation and repair operation has not been performed, the determining apparatus continues to perform S401. That is, the damage operation is continued to be performed, the repair operation is continued to be performed, and the second score is continued to be calculated until the second preset number of times of damage operation and repair operation is performed.

[0169] wherein, the second preset number is the termination condition of the adaptive large-domain search algorithm, and the second preset number is, for example, 500 times.

[0170] If the second preset number of times of damage operation and repair operation has been performed, the iteration is completed, and the determining apparatus outputs the best loading scheme. Otherwise, the determining apparatus continues the next iteration.

[0171] S4011、The determining apparatus determines the optimal loading scheme as the final loading scheme.

[0172] Based on this, the determining apparatus removes part of the goods by the destruction operation, thereby searching for a new loading scheme in a large neighborhood space, greatly increasing the possibility of finding a globally better solution. The determining apparatus adjusts the weights so that the adaptive large-domain search algorithm can learn by itself and focus on the most effective search strategy, avoiding blind search and greatly improving the efficiency of the algorithm in optimizing the loading scheme.

[0173] Based on the above exemplary description, below, in combination with Figure 11 , a method for calculating the second score is introduced.

[0174] Please refer to Figure 11 , Figure 11 A flowchart of a method for calculating the second score provided by an embodiment of the present application. As Figure 11 shown, the method comprises:

[0175] S501, The determining apparatus calculates the space utilization, barycenter stability and support degree score of the to-be-determined loading scheme according to the loading space parameters and the attribute information corresponding to each to-be-loaded goods.

[0176] Among them, the support degree score is used to evaluate the stability of the to-be-loaded goods in the loading space. The determining apparatus can calculate the bottom surface support ratio of the to-be-loaded goods based on the attribute information corresponding to each to-be-loaded goods, thereby obtaining the support degree score.

[0177] S502, The determining apparatus calculates the second score corresponding to the to-be-determined loading scheme according to the space utilization, barycenter stability and support degree score.

[0178] In some examples, the determining apparatus can calculate the second score by the following formula three.

[0179] Formula three;

[0180] Among them, is the second score, is the sixth weight, is the seventh weight, is the eighth weight, is the space utilization, is the barycenter stability, is the support degree score.

[0181] Based on the above exemplary description, below, in combination with Figure 12 , a method for obtaining the goods sequence is introduced.

[0182] Please refer to Figure 12 ,Figure 12 A method for obtaining a cargo sequence is provided for an embodiment of the present application. As shown in Figure 12 the method comprises:

[0183] S601, the determining device determines, for each to-be-loaded cargo, a sorting weight corresponding to the to-be-loaded cargo according to size information, weight information, loading priority, a first weight, a second weight, and a third weight of the to-be-loaded cargo.

[0184] For each to-be-loaded cargo, the determining device can calculate the sorting weight corresponding to the to-be-loaded cargo by the following Formula Four:

[0185] Formula Four;

[0186] wherein, is the sorting weight corresponding to the to-be-loaded cargo, is the weight of the to-be-loaded cargo, is the first weight, is the volume of the to-be-loaded cargo, is the second weight, is the loading priority of the to-be-loaded cargo, is the third weight.

[0187] The determining device can determine the weight of the to-be-loaded cargo based on the weight information of the to-be-loaded cargo, and calculate the volume of the to-be-loaded cargo based on the size information of the to-be-loaded cargo.

[0188] Therefore, the determining device adopts a multi-key sorting strategy to sort the to-be-loaded cargos, so as to take into account the size, weight, and loading priority of the to-be-loaded cargos, provide a more demand-conforming loading order for subsequent generation of a loading scheme, and further help improve the rationality of the loading scheme.

[0189] S602, the determining device sorts the to-be-loaded cargos according to the sorting weight corresponding to each to-be-loaded cargo.

[0190] The determining device can sort the to-be-loaded cargos in descending order of the sorting weight, thereby obtaining a cargo sequence.

[0191] Figure 13 A structural diagram of a determining device is provided for an embodiment of the present application. As shown in Figure 13 the device comprises an acquisition module 101, a sorting module 102, a generation module 103, and an optimization module 104.

[0192] The acquisition module 101 is configured to acquire loading space parameters and attribute information corresponding to each to-be-loaded cargo, the attribute information being used to indicate parameters affecting the loading position of the to-be-loaded cargo in the loading space.

[0193] The sorting module 102 is configured to sort the to-be-loaded cargos according to attribute information corresponding to each of the to-be-loaded cargos, to obtain a cargo sequence.

[0194] The generating module 103 is configured to generate an initial loading scheme according to the cargo sequence, the loading space parameters, and the attribute information corresponding to each of the to-be-loaded cargos, by using a beam search algorithm and a maximum empty space algorithm, the beam search algorithm being used to evaluate a loading position of the to-be-loaded cargos in the loading space, and the maximum empty space algorithm being used to construct a maximum empty space in the loading space, the initial loading scheme being used to indicate an initial loading position of each of the to-be-loaded cargos in the loading space.

[0195] The optimization module 104 is configured to optimize the initial loading scheme according to the initial loading scheme, the loading space parameters, and the attribute information corresponding to each of the to-be-loaded cargos, by using an adaptive large neighborhood search algorithm to destroy and repair the initial loading scheme, to obtain a final loading scheme, the final loading scheme being used to indicate a final loading position of each of the to-be-loaded cargos in the loading space.

[0196] It should be noted that the determination apparatus of the embodiments of the present application can be used to execute the technical solutions of the method embodiments, and the implementation principles and technical effects are similar, which will not be described here again.

[0197] In some examples, the attribute information includes size information, weight information, loading priority, and loading constraint.

[0198] In some examples, the generating module 103 is specifically configured to:

[0199] For the nth to-be-loaded cargo in the cargo sequence, the generating module 103 is configured to determine available second candidate points from a plurality of first candidate points according to attribute information corresponding to the nth to-be-loaded cargo, to calculate a first score corresponding to each of the second candidate points and the nth to-be-loaded cargo, the first candidate point being a position point corresponding to a maximum empty space in an EMS list of the loading space, the maximum empty space being determined according to attribute information corresponding to to-be-loaded cargos loaded into the loading space and the loading space parameters; initially, n is 1.

[0200] The generating module 103 is configured to update K loading states of the loading space according to the first K third candidate points with the largest first scores in the second candidate points, the loading state being used to indicate loading positions of the first to nth to-be-loaded cargos in the loading space; K is a positive integer.

[0201] The generating module 103 is configured to calculate a maximum empty space corresponding to the loading space in each of the K loading states by using the maximum empty space algorithm according to the K loading states, the attribute information corresponding to the first to nth to-be-loaded cargos, and the loading space parameters, and to update the EMS list.

[0202] updating n as n+1 until all loading positions of all to-be-loaded cargos in the loading state are included in the loading space;

[0203] selecting one loading state from the K loading states as an initial loading scheme.

[0204] In some examples, the generating module 103 is specifically configured to:

[0205] For each second candidate point, according to the attribute information and the loading space parameters corresponding to the first to-be-loaded cargo to the n-th to-be-loaded cargo, calculating the space utilization and the center of gravity stability after loading the n-th to-be-loaded cargo to the current loading space according to the position point indicated by the second candidate point; and according to the space utilization corresponding to the second candidate point and the center of gravity stability corresponding to the second candidate point, calculating a first score corresponding to the second candidate point.

[0206] In some examples, the optimization module 104 is specifically configured to:

[0207] According to the weight of the destruction operator, selecting a target destruction operator from the destruction operator list, and performing a destruction operation on the to-be-loaded cargo in the initial loading scheme according to the target destruction operator, to obtain a to-be-repaired loading scheme, the destruction operation being used to remove part of the to-be-loaded cargo from the initial loading scheme, and the to-be-repaired loading scheme being used to indicate the initial loading position of the remaining to-be-loaded cargo in the loading space and the empty position in the loading space;

[0208] According to the weight of the repair operator, selecting a target repair operator from the repair operator list, and performing a repair operation on the empty position in the to-be-repaired loading scheme according to the target repair operator, to obtain a to-be-determined loading scheme, the repair operation being used to re-insert the removed part of the to-be-loaded cargo into the empty position in the loading space;

[0209] According to the loading space parameters and the attribute information corresponding to each to-be-loaded cargo, calculating a second score corresponding to the to-be-determined loading scheme;

[0210] When the second score is greater than the best score, updating the best loading scheme as the to-be-determined loading scheme; and updating the weight of the destruction operator and the weight of the repair operator every time the first preset number of times of the destruction operation and the repair operation are performed; wherein the initial best loading scheme is the initial loading scheme, and the best score is the second score corresponding to the best loading scheme;

[0211] Continuing to perform the destruction operation, the repair operation, and the calculation of the second score until the second preset number of times of the destruction operation and the repair operation are performed.

[0212] Determining the best loading scheme as a final loading scheme.

[0213] In some examples, the list of destruction operators includes random removal, correlation removal, and worst removal operators, while the list of repair operators includes greedy insertion, random insertion, and optimal insertion operators.

[0214] In some examples, optimization module 104 is specifically used for:

[0215] Based on the loading space parameters and the attribute information corresponding to each cargo to be loaded, the space utilization rate, center of gravity stability and support score of the proposed loading scheme are calculated.

[0216] Based on the space utilization rate, center of gravity stability, and support score, calculate the second score corresponding to the pending loading scheme.

[0217] In some examples, sorting module 102 is specifically used for:

[0218] For each cargo to be loaded, calculate the sorting weight corresponding to the cargo based on its size information, weight information, loading priority, first weight, second weight, and third weight.

[0219] The goods to be loaded are sorted according to their respective sorting weights to obtain a goods sequence.

[0220] Figure 14 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 1 .like Figure 14 As shown, the electronic device may include a first processor 201, which, when executing a computer-executable program or instruction stored in a memory, implements the embodiments of this application. Figures 1 to 12 The method for determining the cargo loading scheme shown.

[0221] The electronic device can be used to perform the various steps and / or processes corresponding to the electronic devices in the above method embodiments.

[0222] Figure 15 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 2 .like Figures 1 to 12 As shown, the electronic device may include a second processor 301 and a memory 302. The memory 302 stores a computer program. When the second processor 301 executes the computer program, it implements the embodiments of this application. Figures 1 to 12 The method for determining the cargo loading scheme shown.

[0223] The electronic device can be used to perform the various steps and / or processes corresponding to the electronic devices in the above method embodiments.

[0224] The electronic device provided in the present application can be used to execute the technical solutions of the foregoing method embodiments, and has similar implementation principles and technical effects. The operations performed by each module can be further understood with reference to the related descriptions of the method embodiments, which will not be repeated here. The modules herein can also be replaced by components or circuits.

[0225] The present application can divide the functional modules of the electronic device according to the foregoing method examples. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The foregoing integrated module can be implemented in the form of hardware or in the form of a software functional module. It should be noted that the division of the modules in each embodiment of the present application is illustrative, and is merely a logical functional division. Actual implementation can have another division manner.

[0226] Another embodiment of the present application further provides a computer readable storage medium, and the computer readable storage medium stores a computer program. When the computer program is executed by a processor, the method for determining a cargo loading scheme shown in the foregoing embodiments of the present application can be implemented. Figures 1 to 12 The method for determining a cargo loading scheme shown in the foregoing embodiments of the present application can be implemented.

[0227] The present application further provides a program product, which includes execution instructions stored in a computer readable storage medium. At least one processor of an electronic device can read the execution instructions from the computer readable storage medium, and the at least one processor executes the execution instructions to enable the electronic device to implement the method for determining a cargo loading scheme shown in the foregoing embodiments of the present application. Figures 1 to 12 The method for determining a cargo loading scheme shown in the foregoing embodiments of the present application can be implemented.

[0228] The present application further provides a chip. The chip is connected with a memory, or the chip integrates the memory. When a software program stored in the memory is executed, the method for determining a cargo loading scheme shown in the foregoing embodiments of the present application can be implemented. ​ The method for determining a cargo loading scheme shown in the foregoing embodiments of the present application can be implemented.

[0229] In the several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. There can be another division manner for actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, units or modules can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

[0230] Those skilled in the art will appreciate that the features of the various embodiments can be combined with each other, as means within the scope of the present application and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0231] The above-described embodiments are only used to illustrate the technical solutions of the present application, but not limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of determining a cargo loading plan, characterized by, The method comprises: obtaining loading space parameters and attribute information corresponding to each to-be-loaded cargo, the attribute information being used to indicate parameters affecting loading positions of the to-be-loaded cargos in the loading space; sorting the to-be-loaded cargos according to the attribute information corresponding to each to-be-loaded cargo to obtain a cargo sequence; obtaining an initial loading scheme by using a beam search algorithm and a maximum empty space algorithm according to the cargo sequence, the loading space parameters and the attribute information corresponding to each to-be-loaded cargo, the beam search algorithm being used to evaluate the loading positions of the to-be-loaded cargos in the loading space, and the maximum empty space algorithm being used to construct a maximum empty space in the loading space, the initial loading scheme being used to indicate initial loading positions of each to-be-loaded cargo in the loading space; obtaining a final loading scheme by using an adaptive large neighborhood search algorithm to destroy and repair the initial loading scheme according to the initial loading scheme, the loading space parameters and the attribute information corresponding to each to-be-loaded cargo, the final loading scheme being used to indicate final loading positions of each to-be-loaded cargo in the loading space; wherein the obtaining of the final loading scheme by using the adaptive large neighborhood search algorithm to destroy and repair the initial loading scheme according to the initial loading scheme, the loading space parameters and the attribute information corresponding to each to-be-loaded cargo comprises: selecting a target destruction operator from a destruction operator list according to a weight of a destruction operator, performing a destruction operation on the to-be-loaded cargos in the initial loading scheme according to the target destruction operator to obtain a to-be-repaired loading scheme, the destruction operation being used to remove part of the to-be-loaded cargos from the initial loading scheme, and the to-be-repaired loading scheme being used to indicate initial loading positions of the remaining to-be-loaded cargos in the loading space and empty positions in the loading space; selecting a target repair operator from a repair operator list according to a weight of a repair operator, performing a repair operation on the empty positions in the to-be-repaired loading scheme according to the target repair operator to obtain a to-be-determined loading scheme, the repair operation being used to reinsert the removed part of the to-be-loaded cargos into the empty positions in the loading space; calculating a second score corresponding to the to-be-determined loading scheme according to the loading space parameters and the attribute information corresponding to each to-be-loaded cargo; when the second score is greater than an optimal score, updating an optimal loading scheme to the to-be-determined loading scheme, updating the weight of the destruction operator and the weight of the repair operator every time the destruction operation and the repair operation are performed for a first preset number of times, wherein an initial optimal loading scheme is the initial loading scheme, and the optimal score is a second score corresponding to the optimal loading scheme; continuing to perform the destruction operation, the repair operation and the calculation of the second score until the destruction operation and the repair operation are performed for a second preset number of times; determining the optimal loading scheme as the final loading scheme; wherein the updating of the weight of the destruction operator and the weight of the repair operator comprises: updating the weight of the damage operator and updating the weight of the repair operator according to all second scores obtained after performing the first preset number of times of damage operation and repair operation after the last time of updating the weight; The second score corresponding to the to-be-determined loading scheme is calculated according to the loading space parameter and attribute information corresponding to each to-be-loaded cargo. The space utilization, the center of gravity stability and the support degree score of the to-be-determined loading scheme are calculated according to the loading space parameter and attribute information corresponding to each to-be-loaded cargo. The second score corresponding to the to-be-determined loading scheme is calculated according to the space utilization, the center of gravity stability and the support degree score.

2. The method of claim 1, wherein, The attribute information includes size information, weight information, loading priority and loading constraint.

3. The method of claim 1, wherein, The initial loading scheme is obtained by using the beam search algorithm and the maximum empty space algorithm according to the cargo sequence, the loading space parameter and the attribute information corresponding to each to-be-loaded cargo. For the nth to-be-loaded cargo in the cargo sequence, the available second candidate point is determined from a plurality of first candidate points according to the attribute information corresponding to the nth to-be-loaded cargo, the first score corresponding to the nth to-be-loaded cargo and each second candidate point is calculated, the first candidate point is a position point corresponding to a maximum empty space in an EMS list of the loading space, and the maximum empty space is determined according to the attribute information of the to-be-loaded cargo loaded into the loading space and the loading space parameter; initially, n is 1. The current K loading states of the loading space are updated according to the first K third candidate points with the maximum first score in the second candidate points, and the loading state is used to indicate the loading position of the first to-be-loaded cargo to the nth to-be-loaded cargo in the loading space; K is a positive integer. The maximum empty space corresponding to the loading space in each loading state is calculated by the maximum empty space algorithm according to the K loading states, the attribute information corresponding to the first to-be-loaded cargo to the nth to-be-loaded cargo and the loading space parameter, and the EMS list is updated. n is updated to n+1 until the loading state includes the loading position of all to-be-loaded cargos in the loading space. One loading state is selected from the K loading states as the initial loading scheme.

4. The method of claim 3, wherein, The first score corresponding to each second candidate point is calculated by calculating the space utilization and the center of gravity stability after loading the nth to-be-loaded cargo into the current loading space according to the attribute information corresponding to the first to-be-loaded cargo to the nth to-be-loaded cargo and the loading space parameter, and calculating the first score corresponding to the second candidate point according to the space utilization corresponding to the second candidate point and the center of gravity stability corresponding to the second candidate point. ​ 5. The method of claim 1, wherein, The list of the damage operators includes a random removal operator, a correlation removal operator and a worst removal operator, and the list of the repair operators includes a greedy insertion operator, a random insertion operator and an optimal insertion operator.

6. The method according to any one of claims 1 to 4, characterized in that, The sorting of the to-be-loaded cargos according to the attribute information corresponding to each of the to-be-loaded cargos to obtain a cargo sequence comprises: For each of the to-be-loaded cargos, a sorting weight corresponding to the to-be-loaded cargo is calculated according to size information, weight information, a loading priority, a first weight, a second weight and a third weight of the to-be-loaded cargo. The to-be-loaded cargos are sorted according to the sorting weight corresponding to each of the to-be-loaded cargos to obtain the cargo sequence.

7. An electronic device, comprising: Comprise: A first processor; The first processor is configured to execute a computer executable program or instruction in a memory, so that the electronic device executes the method for determining the cargo loading scheme according to any one of claims 1-6.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer executable program or instruction, which is configured to execute the method for determining the cargo loading scheme according to any one of claims 1-6.

Images