Box type recommendation method, computer equipment, readable storage medium and program product

Abstract

The invention relates to a box type recommendation method, computer equipment, a readable storage medium and a program product, relates to the technical field of intelligent logistics and supply chain optimization, and can adapt to complex and changeable logistics business scenes. The method comprises the following steps: acquiring multi-dimensional feature information in a logistics business development process; the multi-dimensional feature information comprises cargo feature information representing physical attributes of first cargoes to be boxed, box type feature information representing physical attributes and bearing performance of a plurality of available box types, and business scene feature information representing logistics business requirements; determining a plurality of first three-dimensional models and a first box type matching degree between each first three-dimensional model and a plurality of candidate box types according to the multi-dimensional feature information; the first three-dimensional model represents a possible placement combination of the first goods, and the first box type matching degree represents feasibility of placing the first three-dimensional model in a box body corresponding to the candidate box type; and according to each first box type matching degree, determining a recommended box type of the first cargo in each candidate box type.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent logistics and supply chain optimization, and in particular to a box type recommendation method and device, a computer device, a computer readable storage medium and a computer program product. BACKGROUND

[0002] In the process of developing logistics business in the field of intelligent logistics and supply chain optimization, recommending a suitable box type (i.e., accurately matching a packaging box for goods) for goods is a key link connecting the attributes of goods, packaging requirements and supply chain execution. At present, the way to recommend a box type for goods mainly relies on manual experience and / or an algorithm model based on static rules.

[0003] However, this traditional box type recommendation method is limited by manual intervention, is low in efficiency and prone to errors, and most of them only recommend a box type according to the basic size of the goods (e.g., a static rule of determining a recommended box type based on a preset size interval corresponding to a fixed box type), ignoring key factors such as the physical properties of the goods and logistics business requirements, resulting in a recommended box type that is difficult to adapt to diversified logistics business scenarios. SUMMARY

[0004] Therefore, it is necessary to provide a box type recommendation method, device, computer device, computer readable storage medium and computer program product to solve the above technical problems.

[0005] In a first aspect, the present application provides a box type recommendation method, comprising:

[0006] obtaining multi-dimensional feature information in the process of developing logistics business; the multi-dimensional feature information includes goods feature information representing the physical properties of a first goods to be packed, box type feature information representing the physical properties and carrying performance of a plurality of available box types, and business scenario feature information representing logistics business requirements;

[0007] determining a plurality of first three-dimensional models corresponding to the first goods and a first box type matching degree between each of the first three-dimensional models and a plurality of candidate box types according to the multi-dimensional feature information; the first three-dimensional model represents a possible arrangement combination of the first goods, and the first box type matching degree represents the feasibility of arranging the first three-dimensional model in a box corresponding to the candidate box type;

[0008] determining a recommended box type for the first goods from the candidate box types according to the first box type matching degree.

[0009] In a second aspect, the present application further provides a box type recommendation device, comprising:

[0010] The acquisition module is configured to acquire multi-dimensional feature information in a logistics business development process; the multi-dimensional feature information comprises goods feature information representing physical attributes of a first goods to be packed, box type feature information representing physical attributes and load capacity of a plurality of available box types, and business scenario feature information representing logistics business requirements;

[0011] The first determination module is configured to determine, according to the multi-dimensional feature information, a plurality of first three-dimensional models corresponding to the first goods and a first box type matching degree between each of the first three-dimensional models and a plurality of candidate box types; the first three-dimensional model represents a possible arrangement combination of the first goods, and the first box type matching degree represents a feasibility of arranging the first three-dimensional model in a box corresponding to the candidate box type;

[0012] The second determination module is configured to determine, according to each of the first box type matching degrees, a recommended box type of the first goods from the candidate box types.

[0013] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, the memory stores a computer program, and the processor realizes the following steps when executing the computer program:

[0014] Acquiring multi-dimensional feature information in a logistics business development process; the multi-dimensional feature information comprises goods feature information representing physical attributes of a first goods to be packed, box type feature information representing physical attributes and load capacity of a plurality of available box types, and business scenario feature information representing logistics business requirements;

[0015] Determining, according to the multi-dimensional feature information, a plurality of first three-dimensional models corresponding to the first goods and a first box type matching degree between each of the first three-dimensional models and a plurality of candidate box types; the first three-dimensional model represents a possible arrangement combination of the first goods, and the first box type matching degree represents a feasibility of arranging the first three-dimensional model in a box corresponding to the candidate box type;

[0016] Determining, according to each of the first box type matching degrees, a recommended box type of the first goods from the candidate box types.

[0017] In a fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program; the computer program is executed by a processor to realize the following steps:

[0018] Acquiring multi-dimensional feature information in a logistics business development process; the multi-dimensional feature information comprises goods feature information representing physical attributes of a first goods to be packed, box type feature information representing physical attributes and load capacity of a plurality of available box types, and business scenario feature information representing logistics business requirements;

[0019] According to the multi-dimensional feature information, a plurality of first three-dimensional models corresponding to the first cargo and a first box type matching degree between each of the first three-dimensional models and a plurality of candidate box types are determined; the first three-dimensional model represents a possible placement combination of the first cargo, and the first box type matching degree represents a feasibility of placing the first three-dimensional model in a box corresponding to the candidate box type.

[0020] According to each of the first box type matching degrees, a recommended box type of the first cargo is determined from each of the candidate box types.

[0021] In a fifth aspect, the present application further provides a computer program product comprising a computer program which, when executed by a processor, implements the following steps:

[0022] Obtaining multi-dimensional feature information in a logistics business process; the multi-dimensional feature information includes cargo feature information representing physical attributes of a first cargo to be boxed, box type feature information representing physical attributes and carrying performance of a plurality of available box types, and business scenario feature information representing logistics business requirements;

[0023] According to the multi-dimensional feature information, a plurality of first three-dimensional models corresponding to the first cargo and a first box type matching degree between each of the first three-dimensional models and a plurality of candidate box types are determined; the first three-dimensional model represents a possible placement combination of the first cargo, and the first box type matching degree represents a feasibility of placing the first three-dimensional model in a box corresponding to the candidate box type;

[0024] According to each of the first box type matching degrees, a recommended box type of the first cargo is determined from each of the candidate box types.

[0025] The box type recommendation method, device, computer equipment, computer readable storage medium and computer program product obtain multi-dimensional feature information in a logistics business development process, the multi-dimensional feature information includes goods feature information representing physical attributes of a first goods to be packed, box type feature information representing physical attributes and carrying performance of a plurality of available box types, and business scenario feature information representing logistics business requirements, according to the multi-dimensional feature information, a plurality of first three-dimensional models corresponding to the first goods and a first box type matching degree between each first three-dimensional model and a plurality of candidate box types are determined, the first three-dimensional model represents a possible placement combination of the first goods, and the first box type matching degree represents the feasibility of the first three-dimensional model placed in the box corresponding to the candidate box type, and according to each first box type matching degree, a recommended box type of the first goods is determined in each candidate box type. Compared with the traditional way, by comprehensively considering the physical attributes of the first goods to be packed, the physical attributes and carrying performance of the plurality of available box types, and the logistics business requirements, the limitation of only relying on the basic size of the goods is broken, the recommended box type can be more in line with the actual business requirements, and the business scenario feature information representing the logistics business requirements is introduced, the recommended box type that is suitable for different logistics business scenarios can be dynamically determined, the flexibility and scene adaptability of the box type recommendation are improved, and efficient and accurate box type recommendation is realized. The present application also fully considers the actual placement posture and space utilization rate of the goods in the box, by generating a plurality of first three-dimensional models (i.e. different possible placement combinations of the first goods), and calculating the first box type matching degree thereof and the candidate box type, the adaptation under different placement modes can be evaluated, thereby helping to select the box type with the highest space utilization rate, the most stable packaging, and the best protection for the goods, and effectively reducing the goods damage and space waste caused by improper packaging. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other related drawings can be obtained by those skilled in the art without creating any inventive labor.

[0027] Figure 1 An application environment diagram of a box type recommendation method in an embodiment;

[0028] Figure 2 A flowchart of a box type recommendation method in an embodiment;

[0029] Figure 3 A flowchart of a goods splitting processing step in an embodiment;

[0030] Figure 4 A flowchart of a candidate box type determination step in an embodiment;

[0031] Figure 5 Flowchart of the box type recommendation method in another embodiment;

[0032] Figure 6 Block diagram of the box type recommendation device in an embodiment;

[0033] Figure 7 Internal structure diagram of the computer device in an embodiment. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0035] It should be noted that the terms "first", "second", etc. used in the present application can be used to describe various objects, but these elements are not limited by these terms. These terms are only used to distinguish the first object from the second object. The term "including" and any variation thereof used in the present application is intended to cover non-exclusive inclusion. The term "multiple" used in the present application means two and more than two. The term "and / or" used in the present application means one of the options or any combination of multiple options.

[0036] In the related art, in the process of developing logistics business in the field of intelligent logistics and supply chain optimization, the box type recommendation technology spans multiple cross-disciplines and technical fields, mainly involving logistics engineering, artificial intelligence and machine learning, and industrial engineering. Among them, logistics engineering focuses on the adaptability of packaging and transportation, involving core issues such as cargo unitization, packaging standardization, and transportation efficiency optimization; artificial intelligence and machine learning rely on algorithm models to realize intelligent recommendation, which belongs to the specific application of "intelligent decision system" in the logistics scene; industrial engineering focuses on cost optimization and resource utilization rate improvement (such as material saving and space utilization rate maximization) of packaging process. At present, the traditional way to recommend a box for goods mainly relies on artificial experience and / or algorithm models based on static rules.

[0037] However, for special-shaped goods (such as irregularly shaped mechanical parts), combined goods (such as a collection of multiple small items), or special attribute goods (such as fresh food that needs to be kept warm or electronic components that need to be protected from magnetism), artificial box selection often "packs small items in large boxes", which not only increases the amount of paperboard used, increases costs, and does not meet environmental protection concepts, but also increases the risk of irregular fragile goods (such as glass bottles) being easily damaged due to large gaps in the box during transportation. In addition, the employees responsible for packaging goods need to repeatedly measure the goods and the box, and the single decision-making process takes too long, especially in large-volume order scenarios such as shopping festivals, where the number of packages increases dramatically in a single day, and artificial box selection cannot cope.

[0038] While the algorithm model based on static rules mostly matches the box type according to the basic dimensions (length, width, height) of the goods (for example, a preset size interval is fixed to correspond to a box type), it is difficult to adapt to diversified business scenarios, and it ignores key factors such as the weight, material (such as fragile, liquid, fresh), stacking restrictions (such as not invertible) of the goods, resulting in the recommended box type may not meet the actual transportation requirements. The algorithm model based on static rules has slow operation speed, and it is difficult for such algorithm model to achieve fast box type recommendation when facing large quantities of goods (such as tens of thousands of e-commerce orders per day). Moreover, when the goods information or scene parameters are updated, the model cannot quickly recalculate, resulting in the lag of the box type recommendation result.

[0039] To this end, the box type recommendation method provided by the embodiments of the present application obtains multi-dimensional feature information in the process of carrying out logistics business, the multi-dimensional feature information includes goods feature information representing the physical properties of the first goods to be packed, box type feature information representing the physical properties and carrying performance of a plurality of available box types, and business scene feature information representing the logistics business requirements, determines a plurality of first three-dimensional models corresponding to the first goods and a first box type matching degree between each first three-dimensional model and a plurality of candidate box types according to the multi-dimensional feature information, the first three-dimensional model represents a possible placement combination of the first goods, and the first box type matching degree represents the feasibility of placing the first three-dimensional model in the box corresponding to the candidate box type, and determines the recommended box type of the first goods in each candidate box type according to each first box type matching degree. Compared with the traditional way, the embodiments break the limitation of relying only on the basic dimensions of the goods by comprehensively considering the physical properties of the first goods to be packed, the physical properties and carrying performance of a plurality of available box types, and the logistics business requirements, which can make the recommended box type more in line with the actual business requirements. Moreover, by introducing the business scene feature information representing the logistics business requirements, the adapted recommended box type can be dynamically determined for different logistics business scenes, which improves the flexibility and scene adaptability of box type recommendation, and realizes efficient and accurate box type recommendation. The embodiments also fully consider the actual placement posture and space utilization rate of the goods in the box, by generating a plurality of first three-dimensional models (i.e., different possible placement combinations of the first goods) and calculating the first box type matching degree thereof and the candidate box type, the adaptation under different placement modes can be evaluated, thereby helping to select the box type with the highest space utilization rate, the most stable packaging, and the best protection for the goods, effectively reducing the damage and space waste caused by improper packaging.

[0040] In one exemplary embodiment, a box type recommendation method is provided. The method can be applied to, for example, Figure 1The application environment shown. Among them, the terminal communicates with the server through the network. The data storage system can store the data required by the server to process. The data storage system can be integrated on the server, or placed on the cloud or other network servers. Among them, the terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, unmanned aerial vehicles, low-altitude aircraft, Internet of Things devices, and portable wearable devices. The Internet of Things device can be a smart television, a smart vehicle device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server can be a standalone physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The present embodiment illustrates that the method is applied to the terminal. It can be understood that the method can also be applied to the server, and can also be applied to a system including the terminal and the server, and is realized through the interaction of the terminal and the server.

[0041] In the present embodiment, as shown in the method can include the following steps: Figure 2

[0042] Step S201, acquiring multi-dimensional feature information in the process of developing logistics business; The multi-dimensional feature information includes the goods feature information representing the physical properties of the first goods to be packed, the box type feature information representing the physical properties and carrying performance of a plurality of available box types, and the business scenario feature information representing the logistics business demand.

[0043] Among them, the multi-dimensional feature information refers to the feature information covering multiple dimensions (such as goods, box types and business scenarios). The first goods to be packed can include only one item, or can include multiple items. The physical properties of the first goods can include the size (such as length, width, and height) of the first goods, weight, material (such as glass), and whether it can be stacked / stacked, etc. The available box type refers to the box type corresponding to the box that can be used to pack / place goods in the current logistics business development process. The physical properties and carrying performance of the box type can include the size of the box type, the size of the inner and outer surfaces of the box material, and the box type carrying information (such as the upper limit of the box type carrying capacity), etc. The logistics business demand can include the logistics transportation mode (such as road transportation) and the transportation environment (such as extreme environment such as humidity) of the first goods, the storage space (such as the size of the warehouse shelf) and the storage period (such as short cycle turnover) of the storage box during transportation, the order type (such as retail order, wholesale order, which can be used to determine the single box loading capacity and box size), customer special requirements (such as specified box material), delivery time (such as urgent time), etc.

[0044] ​Exemplarily, from the dual angles of "physical attributes + special attributes", the goods characteristic information capable of representing the physical attributes of the first goods to be packed is collected; the goods characteristic information includes size characteristics (such as length, width, and height), weight characteristics (such as single-piece weight and total weight), volume characteristics (such as actual volume and effective volume), and shape characteristics (such as regular pieces, irregular pieces, and flexible pieces) of the first goods to be packed. The box type characteristic information and the goods characteristic information form an "adaptation corresponding relationship", according to which the box type characteristic information capable of representing the physical attributes and carrying performance of the plurality of available box types is collected; the box type characteristic information includes size parameters (such as internal dimensions), carrying performance parameters (such as maximum load capacity), and volume parameters (such as actual volume and effective volume) of the plurality of available box types. The business scenario characteristic information can determine the "priority orientation" of the box type recommendation, in order to avoid the "theoretical optimum" of the box type recommendation deviating from the actual business, the business scenario characteristic information should include order characteristics (such as considering whole-box adaptation for bulk orders and considering mixed packing for scattered orders).

[0045] Among them, the goods characteristic information directly determines the basic adaptability of the box type. The maximum load capacity of the box includes dynamic load capacity (such as instantaneous load capacity during transportation bumps) and static load capacity (that is, the maximum weight that the box can bear in a static state). The actual volume of the box type can be calculated according to its internal dimensions.

[0046] In this embodiment, the multi-dimensional characteristic information, as a key factor affecting the accuracy of box type recommendation, covers three core subjects of goods, box types, and business scenarios, can ensure the comprehensiveness of characteristics and the adaptability of scenarios, and avoid the box type recommendation deviation problem caused by missing characteristics.

[0047] In step S202, according to the multi-dimensional characteristic information, a plurality of first three-dimensional models corresponding to the first goods and a first box type matching degree between each first three-dimensional model and a plurality of candidate box types are determined; the first three-dimensional model represents a possible placement combination of the first goods, and the first box type matching degree represents the feasibility of placing the first three-dimensional model in the box corresponding to the candidate box type.

[0048] Exemplarily, according to the multi-dimensional feature information, the basic geometric features (such as the size of the goods, the volume of the goods), the physical property correlation information (such as the material of the goods, the bearing parameter) and the placement adaptation features (such as the possible placement posture of the goods, whether the goods can be stacked) of each item included in the first goods are determined; according to the basic geometric features, the physical property correlation information and the placement adaptation features, the placement mode (such as the stacking relationship between the goods in the first goods, the placement angle) of the first goods is adjusted to obtain a possible placement combination of the first goods; the spatial form and the key attributes of the goods in the possible placement combination are restored in a digital manner to obtain a first three-dimensional model corresponding to the first goods; the first three-dimensional model is simulated at a plurality of stable placement angles (such as flat, side, vertical) in each candidate box type to obtain a plurality of candidate placement models; and the first box type matching degree between the candidate placement model and the first three-dimensional model corresponding to the candidate placement model is determined according to the space utilization rate of the candidate placement model.

[0049] In a specific implementation, before step S202, the multi-dimensional feature information can also be pre-processed including outlier processing, missing value processing and data consistency correction.

[0050] In the embodiment, the way of outlier processing is specifically: through the "3σ principle" or the box plot, the data (such as the weight of the goods is 0 kg, the size of the box type is negative) that exceeds the reasonable range is screened out, that is, the outlier; for the physical outliers (such as the size of the small parts is 1000 cm), directly eliminate and feedback the data collection end to correct; for accidental outliers (such as single weighing deviation), the mean or median of the same batch of goods is used to replace (such as the weight of a batch of parts is mostly 2 kg, only 1 is 5 kg, replace 5 kg with 2 kg).

[0051] In the embodiment, the way of missing value processing is specifically: for the missing of key features (such as the size and weight of the goods, the bearing of the box type, the internal size of the consumables), trigger the data supplement process, if it cannot be supplemented, mark it as "to be confirmed" and do not participate in this recommendation; for the missing of non-key features (such as whether the goods can be stacked and stored, the external size of the box type and the consumables), fill in according to the "default rule" (such as no special marking, default 3 layers of stacking).

[0052] In the embodiment, the way of data consistency correction includes unit unification and format unification. For unit unification, non-standard units such as inches and pounds are converted to cm and kg (such as 1 inch = 2.54 cm, 1 pound ≈ 0.453 kg); for format unification, the size data is unified to "length x width x height" format, and the weight data is kept to one decimal place to avoid calculation errors caused by format confusion.

[0053] In step S203, according to the first box type matching degree, the recommended box type of the first goods is determined in each candidate box type.

[0054] Exemplarily, in each candidate box type, a candidate box type whose first box type matching degree meets a target condition is selected as the recommended box type of the first cargo.

[0055] In one specific implementation, the first box type matching degree can include a box type filling rate when the first three-dimensional model is placed inside the candidate box type and a box body consumable cost corresponding to the candidate box type, and the target condition can be that the box type filling rate is the highest and the box body consumable cost meets a consumable cost constraint condition.

[0056] In one exemplary embodiment, in step S202, determining the plurality of first three-dimensional models corresponding to the first cargo and the first box type matching degree between each first three-dimensional model and the plurality of candidate box types according to the multi-dimensional feature information can include:

[0057] According to the cargo feature information, a plurality of first three-dimensional models corresponding to the first cargo are established, and according to the box type feature information, a plurality of digital models corresponding to each candidate box type are established; the plurality of digital models corresponding to the candidate box type are obtained by rotating the box body corresponding to the candidate box type; for each candidate box type, each first three-dimensional model is placed inside the digital model corresponding to the candidate box type to obtain a first packing simulation result, and the first box type matching degree between each first three-dimensional model and the candidate box type is determined according to the first packing simulation result.

[0058] Exemplarily, according to the cargo feature information, the placement mode of each article included in the first cargo is adjusted to obtain a plurality of possible placement combinations of the first cargo; according to the possible placement combinations, a first three-dimensional model corresponding to the first cargo is established; the box body corresponding to the candidate box type is rotated in different directions multiple times to obtain a plurality of digital models corresponding to the candidate box type (for example, in the xyz coordinate axis of the box body, the box body is rotated by 90° around the x-axis, 180° around the x-axis, 90° around the y-axis, 180° around the y-axis, and 90° around the z-axis to obtain five digital models of placement postures, combined with the digital model of the box body in the original posture, the candidate box type corresponds to six digital models); for each candidate box type, each first three-dimensional model is placed inside the digital model corresponding to the candidate box type to obtain a first packing simulation result, and the first box type matching degree between each first three-dimensional model and the candidate box type is determined according to the first packing simulation result.

[0059] In one exemplary embodiment, before step S202, a cargo splitting processing step can also be included. As shown in Figure 3 the cargo splitting processing step can include the following steps:

[0060] Step S301, determining the volume of the first cargo according to the cargo feature information.

[0061] The first cargo can include a plurality of items, and a total volume of the items included in the first cargo (i.e., a volume of the first cargo) can be greater than a maximum volume of the box type.

[0062] In a case where the volume of the first cargo is greater than the volume target value, the first cargo is split to obtain a plurality of second cargos.

[0063] The volume target value can be the maximum volume that can be accommodated by the box type.

[0064] For example, in a case where the volume of the first cargo is greater than the volume target value, the first cargo is split to obtain a plurality of second cargos according to the maximum volume that can be accommodated by the box type; the volume of each second cargo is less than or equal to the maximum volume that can be accommodated by the box type. In the process of splitting the first cargo, the integrity of the items in each second cargo obtained can be guaranteed by avoiding splitting a single independent item (e.g., a large component that cannot be split).

[0065] In step S303, the recommended box type of each second cargo is determined from the plurality of candidate box types according to the multi-dimensional feature information.

[0066] For example, a bin packing problem (BPP) heuristic algorithm is used, and a first-fit decreasing (FFD) algorithm is used as the calculation logic. The second cargos are first sorted in descending order of volume, and then each second cargo is placed into the first box type that can accommodate it, and the space of the box type in which the cargo has been placed is preferentially utilized, so as to determine the recommended box type of each second cargo (i.e., the first box type that can accommodate the second cargo). Each box type can correspond to a plurality of box bodies, and the box type can be reused.

[0067] In this embodiment, the number of items included in the first cargo is determined according to the cargo feature information; the number of items included in the first cargo is less than or equal to a number target value, indicating that the largest box type can accommodate the first cargo; and the number of items included in the first cargo is greater than the number target value, indicating that the largest box type cannot accommodate the first cargo. In a case where the number of items included in the first cargo is less than or equal to the number target value, a plurality of first three-dimensional models corresponding to the first cargo and a first box type matching degree between each first three-dimensional model and a plurality of candidate box types can be determined according to the multi-dimensional feature information, and the recommended box type of the first cargo is determined from the plurality of candidate box types according to the first box type matching degree; in a case where the number of items included in the first cargo is greater than the number target value, the first cargo is split to obtain a plurality of second cargos, and the recommended box type of each second cargo is determined from the plurality of candidate box types according to the multi-dimensional feature information.

[0068] In an example embodiment, in step S303, determining the recommended box type of each second cargo from the candidate box types according to the multi-dimensional feature information can include:

[0069] processing the second cargos in sequence; the processing sequence of each second cargo is determined according to the volume of the second cargo; the volume of each second cargo is determined according to the cargo feature information; in the process of processing each second cargo, a plurality of second three-dimensional models corresponding to the second cargo and a second box type matching degree between each second three-dimensional model and each candidate box type are determined according to the multi-dimensional feature information; the second three-dimensional model represents a possible placement combination of the second cargo, and the second box type matching degree represents the feasibility of placing the second three-dimensional model in the box corresponding to the candidate box type; and the recommended box type of the second cargo is determined from the candidate box types according to the second box type matching degree.

[0070] In an example embodiment, the second cargo can include only one item or a plurality of items.

[0071] In an example embodiment, the volume of each second cargo is determined according to the cargo feature information; each second cargo is sorted in descending order of volume to obtain a sorting result; each second cargo is processed in sequence according to the sorting result; in the process of processing each second cargo: a plurality of second three-dimensional models corresponding to the second cargo are established according to the cargo feature information, and a plurality of digital models corresponding to each candidate box type are established according to the box type feature information; the plurality of digital models corresponding to the candidate box type are obtained by rotating the box corresponding to the candidate box type; for each candidate box type, each second three-dimensional model is placed in the interior of the digital model corresponding to the candidate box type to obtain a second packing simulation result, and a second box type matching degree between each second three-dimensional model and the candidate box type is determined according to the second packing simulation result; the second box type matching degree includes a box type filling rate when the second three-dimensional model is placed in the interior of the candidate box type and a box material cost corresponding to the candidate box type; the box material cost corresponding to the candidate box type is determined according to the box type feature information; a material cost constraint condition is established according to the business scenario feature information; the recommended box type of the second cargo is determined from each candidate box type whose box material cost satisfies the material cost constraint condition; and the box type filling rate of the recommended box type of the second cargo satisfies a target range.

[0072] In an example embodiment, before step S202, a candidate box type determination step can also be included. As shown in Figure 4 the candidate box type determination step can include the following steps:

[0073] In step S401, box size constraint conditions and box weight constraint conditions are established according to the cargo feature information and the business scenario feature information.

[0074] The box type size constraint condition refers to a condition that needs to be met by the size of the recommended box type of the first cargo; and the box type load-bearing constraint condition refers to a condition that needs to be met by the load-bearing (including dynamic load-bearing and static load-bearing) of the recommended box type of the first cargo.

[0075] Exemplarily, according to the cargo characteristic information and the business scenario characteristic information, a size requirement of a box type for loading the first cargo is determined; according to the size requirement, a box type size constraint condition is established in the bottom rule engine; according to the cargo characteristic information and the business scenario characteristic information, a load-bearing requirement of a box type for loading the first cargo is determined; and according to the load-bearing requirement, a box type load-bearing constraint condition is established in the bottom rule engine.

[0076] In step S402, according to the box type characteristic information, the box type size constraint condition and the box type load-bearing constraint condition, a plurality of candidate box types of the first cargo are determined from a plurality of available box types; the box type size information of the candidate box type meets the box type size constraint condition; and the box type load-bearing information of the candidate box type meets the box type load-bearing constraint condition.

[0077] Exemplarily, the bottom rule engine selects, from the plurality of available box types, a box type whose box type size information meets the box type size constraint condition and whose box type load-bearing information meets the box type load-bearing constraint condition as a candidate box type according to the box type characteristic information, the box type size constraint condition and the box type load-bearing constraint condition, thereby forming a candidate box type list. Preferably, the number of candidate box types in the candidate box type list is usually kept at 5-10, so as to avoid excessive influence on the subsequent calculation efficiency.

[0078] In this embodiment, the bottom rule engine is responsible for “preliminary filtering”, which quickly eliminates the box types that do not meet the constraint at all, thereby reducing the calculation amount of the subsequent model.

[0079] In one exemplary embodiment, in step S401, establishing the box type size constraint condition and the box type load-bearing constraint condition according to the cargo characteristic information and the business scenario characteristic information can include:

[0080] According to the cargo characteristic information, cargo size information and cargo type of the first cargo are determined; in the case of the cargo type being a basic category or a common category, the box type size constraint condition is determined to be that the inner size of the candidate box type is greater than or equal to the maximum size of the first cargo; in the case of the cargo type being a flexible cargo, according to the size information of the reserved folding space or the reserved compression space corresponding to the flexible cargo and the cargo size information, the box type size constraint condition is established; in the case of the cargo type being an irregular cargo, according to the size information of the reserved placing adjustment space corresponding to the irregular cargo and the cargo size information, the box type size constraint condition is established; in the case of the cargo type being a fragile cargo, according to the size information of the buffer layer corresponding to the fragile cargo and the cargo size information, the box type size constraint condition is established; according to the cargo characteristic information, cargo weight information of the first cargo is determined, and according to the business scenario characteristic information, a logistics transportation safety coefficient is determined; according to the cargo weight information and the logistics transportation safety coefficient, a box type bearing constraint condition is established.

[0081] In the formula, the cargo size information of the first cargo includes the maximum size of the first cargo; the flexible cargo refers to a cargo (such as a down product) without a fixed shape, easy to deform, foldable or extrudable; the irregular cargo refers to a cargo (such as a special metal part) without a standard geometric shape and difficult to regularize; the fragile cargo refers to a cargo (such as a ceramic) easy to break under impact, vibration or extrusion; the cargo weight information of the first cargo includes the total weight of the first cargo.

[0082] Exemplarily, for establishment of the box type size constraint condition, specifically: according to the cargo characteristic information, the maximum size of the first cargo and the cargo type are determined; in the case that the cargo type is a basic category or a common category, the box type size constraint condition is determined as the inner size of the candidate box type ≥ the maximum size of the first cargo (for example, considering the rotation of the goods, the first cargo can be rotated as "width × length × height", and the inner length of the box type needs to satisfy the condition that the inner length of the box type ≥ max (the length of the first cargo, the width of the first cargo, the height of the first cargo)); in the case that the cargo type is a flexible cargo, according to the size information of the reserved folding space or the reserved compression space corresponding to the flexible cargo and the cargo size information, the unfolding reserved size corresponding to the flexible cargo is determined, and according to the unfolding reserved size corresponding to the flexible cargo, the box type size constraint condition is established (for example, the box type size constraint condition is that the inner size of the candidate box type is greater than or equal to the unfolding reserved size corresponding to the flexible cargo); in the case that the cargo type is an irregular cargo, according to the size information of the reserved placing adjustment space corresponding to the irregular cargo and the cargo size information, the placing reserved size corresponding to the irregular cargo is determined, and according to the placing reserved size corresponding to the irregular cargo, the box type size constraint condition is established (for example, the box type size constraint condition is that the inner size of the candidate box type is greater than or equal to the placing reserved size corresponding to the irregular cargo); in the case that the cargo type is a fragile cargo, according to the size information of the buffer layer corresponding to the fragile cargo and the cargo size information, the buffer reserved size corresponding to the fragile cargo is determined, and according to the buffer reserved size corresponding to the fragile cargo, the box type size constraint condition is established (for example, the box type size constraint condition is that the inner size of the candidate box type is greater than or equal to the buffer reserved size corresponding to the fragile cargo).

[0083] Exemplarily, the establishment of the box type bearing constraint condition specifically includes: according to the cargo characteristic information, the total weight of the first cargo is determined, and according to the business scenario characteristic information, the logistics transportation safety coefficient is determined (for example, 1.2 for land transportation and 1.5 for air transportation, to avoid overloading caused by high-altitude jolting); according to the total weight of the first cargo and the logistics transportation safety coefficient, the box type bearing constraint condition is determined as the maximum bearing of the box type ≥ the total weight of the first cargo × (1+the logistics transportation safety coefficient).

[0084] In an example embodiment, in the case that the cargo type is a flexible cargo, according to the size information of the reserved folding space or the reserved compression space corresponding to the flexible cargo and the cargo size information, the box type size constraint condition can be established.

[0085] In the case that the cargo type is a flexible cargo, according to the size information of the reserved folding space or the reserved compression space corresponding to the flexible cargo and the cargo size information, the box type size constraint condition is determined as the inner size of the candidate box type ≥ the unfolding reserved size corresponding to the flexible cargo; wherein the ratio of the unfolding reserved size corresponding to the flexible cargo to the size of the flexible cargo in the natural unfolding state is within a first target range.

[0086] Exemplarily, in the case that the type of the first cargo is flexible cargo, the box type size constraint condition is determined as the inner size of the candidate box type ≥ 1.1 times the size of the first cargo in the natural relaxed state according to the size information of the reserved folding space or the reserved compression space corresponding to the flexible cargo (such as 0.1 times the size of the first cargo in the natural relaxed state) and the cargo size information.

[0087] In the present embodiment, the first target range can be 1.05-1.2. In the case that the type of the first cargo is flexible cargo, by considering the size information of the reserved folding space or the reserved compression space corresponding to the flexible cargo when establishing the box type size constraint condition, the ratio of the relaxed reserved size corresponding to the flexible cargo to the size of the flexible cargo in the natural relaxed state is determined to be within the first target range, and the box type size constraint condition is limited to that the inner size of the candidate box type is greater than or equal to the relaxed reserved size corresponding to the flexible cargo, which can not only avoid excessive increase of the packing materials, but also ensure sufficient cargo packing space, prevent the flexible cargo from being wrinkled, damaged or its performance changed (such as the internal structure and electrical performance of the flexible electronic component may be affected by excessive compression or folding) and other situations after being excessively squeezed or folded, thereby ensuring the quality stability of the flexible cargo during transportation and storage.

[0088] In an exemplary embodiment, in the case that the type of the first cargo is irregular cargo, the box type size constraint condition is established according to the size information of the reserved placement adjustment space corresponding to the irregular cargo and the cargo size information, which can include:

[0089] In the case that the type of the first cargo is irregular cargo, the box type size constraint condition is determined as the inner size of the candidate box type > 1.2 times the size of the minimum bounding box of the irregular cargo according to the size information of the reserved placement adjustment space corresponding to the irregular cargo and the cargo size information; wherein the ratio of the placement reserved size corresponding to the irregular cargo to the size of the minimum bounding box of the irregular cargo is within a second target range.

[0090] Exemplarily, in the case that the type of the first cargo is irregular cargo, the box type size constraint condition is determined as the inner size of the candidate box type ≥ 1.2 times the size of the minimum bounding box of the first cargo according to the size information of the reserved placement adjustment space corresponding to the irregular cargo (such as 0.2 times the size of the minimum bounding box of the first cargo) and the cargo size information.

[0091] In the embodiment, the second target range can be 1.1-1.3. In the case that the cargo type is irregular cargo, by considering the size information of the reserved placement adjustment space corresponding to the irregular cargo when establishing the box type size constraint condition, it is determined that the ratio of the placement reserved size corresponding to the irregular cargo to the size of the minimum bounding box of the irregular cargo is within the second target range, and the box type size constraint condition is limited to that the inner size of the candidate box type is greater than or equal to the placement reserved size corresponding to the irregular cargo, which can not only avoid excessive increase of the packing material, but also ensure sufficient cargo packing space. Moreover, by setting the reserved placement adjustment space, not only can the protruding part of the irregular cargo be prevented from being damaged due to frequent collision with the box wall during transportation, but also sufficient space can be provided for the operator, so that the operator can flexibly adjust and try different placement angles when placing the irregular cargo to determine the suitable packing scheme.

[0092] In an exemplary embodiment, in the case that the cargo type is fragile cargo, establishing the box type size constraint condition according to the size information of the buffer layer corresponding to the fragile cargo and the cargo size information can include:

[0093] In the case that the cargo type is fragile cargo, the box type size constraint condition is determined to be that the inner size of the candidate box type is greater than or equal to the buffer reserved size corresponding to the fragile cargo; wherein the buffer reserved size corresponding to the fragile cargo is determined according to the size information of the buffer layer corresponding to the fragile cargo and the cargo size information.

[0094] Exemplarily, in the case that the cargo type is fragile cargo, according to the size information of the buffer layer corresponding to the fragile cargo and the cargo size information, the box type size constraint condition is determined to be that the inner size of the box type is greater than or equal to (the maximum size of the first cargo + the thickness of the buffer layer).

[0095] In the embodiment, in the case that the cargo type is fragile cargo, by considering the size information of the buffer layer corresponding to the fragile cargo when establishing the box type size constraint condition, it can be ensured that a buffer layer (such as foam or sponge) with sufficient thickness can be added around the fragile cargo during subsequent packing of the fragile cargo, so as to avoid damage of the fragile cargo due to external impact force or frequent collision with the box wall during movement.

[0096] In an exemplary embodiment, the first box type matching degree includes a box type filling rate when the first three-dimensional model is placed in the interior of the candidate box type and a box body material cost corresponding to the candidate box type; and in step S203, determining the recommended box type of the first cargo in each candidate box type according to each first box type matching degree can include:

[0097] According to the box type feature information, the box body consumable cost corresponding to the candidate box type is determined; according to the business scene feature information, a consumable cost constraint condition is established; in each candidate box type in which the box body consumable cost meets the consumable cost constraint condition, the recommended box type of the first cargo is determined; and the box type filling rate of the recommended box type is within the third target range.

[0098] The box type filling rate of the first three-dimensional model when placed in the interior of the candidate box type can represent the space utilization rate of the candidate box type when the first three-dimensional model is placed in the interior of the candidate box type.

[0099] Exemplarily, according to the box type feature information, the box body material and the box body size information of the candidate box type are determined; according to the box body material and the box body size information of the candidate box type, the box body consumable cost corresponding to the candidate box type is determined; according to the business scene feature information, a consumable cost constraint condition meeting the logistics business demand is determined; and by using a best fit algorithm, in each candidate box type in which the box body consumable cost meets the consumable cost constraint condition, the candidate box type with the highest box type filling rate and within the third target range (such as 80%~90%) of the box type filling rate is selected as the recommended box type of the first cargo.

[0100] In a specific implementation, if the box type filling rate of the candidate box type is greater than 90%, it is necessary to check whether the goods in the candidate box type will be overfilled to cause packaging difficulty, and to adaptively select a box type with a box type filling rate within the range of 80%~90%.

[0101] In an exemplary embodiment, in step S203, according to the matching degrees of the first box types, the recommended box type of the first cargo is determined in each candidate box type, which can further include:

[0102] In the case that the box type filling rates of each candidate box type are all less than the target filling rate, the multiple candidate box types of the first cargo are determined in multiple available box types for multiple times until the box type filling rate of at least one candidate box type in the current multiple candidate box types is greater than or equal to the target filling rate, and then the recommended box type of the first cargo is determined in the current candidate box types; and the box type filling rate of the recommended box type is greater than or equal to the box type filling rates of the current candidate box types.

[0103] Exemplarily, the target filling rate is 60%. If the box type filling rates of each candidate box type are all less than 60%, it is necessary to re-screen to avoid that the bottom rule engine misses some box types when screening the candidate box types; if the box type filling rates of the multiple candidate box types obtained by re-screening are all less than 60%, it is still necessary to re-screen until the box type filling rate of at least one candidate box type in the multiple candidate box types obtained by re-screening is greater than or equal to 60%, and then the candidate box type with the highest box type filling rate is selected as the recommended box type of the first cargo in the current candidate box types.

[0104] In an example embodiment, in step S203, determining the recommended box type of the first cargo from the candidate box types according to the respective first box type matching degree can further include:

[0105] In the case that the box type filling rate of each candidate box type is less than the target filling rate, the plurality of candidate box types of the first cargo are determined in the plurality of available box types for multiple times until the total number of times of determining the plurality of candidate box types of the first cargo is equal to the number target value, and then the recommended box type of the first cargo is determined from the current candidate box types; wherein the box type filling rate of the recommended box type is greater than or equal to the box type filling rate of the current candidate box types.

[0106] For example, the target filling rate is 60%. If the box type filling rate of each candidate box type is less than 60%, it is necessary to re-screen. If the candidate box type with a box type filling rate greater than 60% is still not matched after the number of re-screening is equal to the number target value, the bottom logic is used, and the candidate box type corresponding to the highest box type filling rate is selected from the current candidate box types as the recommended box type of the first cargo.

[0107] In order to enable those skilled in the art to better understand the above steps, the embodiments of the present application are exemplarily illustrated by an example below. It should be understood that the embodiments of the present application are not limited thereto.

[0108] As shown in FIG. 5, the example can include the following steps: Figure 5

[0109] In step S501, multi-dimensional feature information in the process of carrying out the logistics business is obtained.

[0110] The multi-dimensional feature information includes cargo feature information representing the physical attributes of the first cargo to be packed, box type feature information representing the physical attributes and carrying performance of the plurality of available box types, and business scenario feature information representing the logistics business demand.

[0111] In step S502, the volume of the first cargo and the number of items contained in the first cargo are determined according to the cargo feature information.

[0112] In step S503, in the case that the number of items contained in the first cargo is less than or equal to the number target value, the plurality of candidate box types of the first cargo are determined in the plurality of available box types according to the multi-dimensional feature information.

[0113] ​In a specific implementation, according to the cargo characteristic information, cargo size information and cargo type of the first cargo are determined; in the case that the cargo type is a basic category or a common category, the box type size constraint condition is that the inner size of the candidate box type is greater than or equal to the maximum size of the first cargo; in the case that the cargo type is a flexible cargo, according to the size information of the reserved folding space or the reserved compression space corresponding to the flexible cargo and the cargo size information, the box type size constraint condition is that the inner size of the candidate box type is greater than or equal to 1.1 times of the size of the first cargo in a natural relaxed state; in the case that the cargo type is an irregular cargo, according to the size information of the reserved placement adjustment space corresponding to the irregular cargo and the cargo size information, the box type size constraint condition is that the inner size of the candidate box type is greater than or equal to 1.2 times of the size of the minimum bounding box of the first cargo; in the case that the cargo type is a fragile cargo, according to the size information of the buffer layer corresponding to the fragile cargo and the cargo size information, the box type size constraint condition is that the inner size is greater than or equal to (the maximum size of the first cargo + the thickness of the buffer layer); according to the cargo characteristic information, the total weight of the first cargo is determined, and according to the business scenario characteristic information, a logistics transportation safety coefficient is determined; according to the total weight of the first cargo and the logistics transportation safety coefficient, the box type bearing constraint condition is that the maximum bearing of the box type is greater than or equal to the total weight of the first cargo × (1 + the logistics transportation safety coefficient); according to the box type characteristic information, the box type size constraint condition and the box type bearing constraint condition, a plurality of candidate box types of the first cargo are determined from a plurality of available box types; the box type size information of the candidate box type satisfies the box type size constraint condition; the box type bearing information of the candidate box type satisfies the box type bearing constraint condition.

[0114] In step S504, according to the multi-dimensional characteristic information, a plurality of first three-dimensional models corresponding to the first cargo and a first box type matching degree between each first three-dimensional model and the plurality of candidate box types are determined.

[0115] Among them, the first three-dimensional model represents a possible placement combination of the first cargo, and the first box type matching degree represents the feasibility of placing the first three-dimensional model in the box corresponding to the candidate box type.

[0116] In a specific implementation, according to the cargo characteristic information, a plurality of first three-dimensional models corresponding to the first cargo are established, and according to the box type characteristic information, a plurality of digital models corresponding to each candidate box type are established; the plurality of digital models corresponding to the candidate box type are obtained by rotating the box corresponding to the candidate box type; for each candidate box type, each first three-dimensional model is placed in the interior of the digital model corresponding to the candidate box type to obtain a first packing simulation result, and according to the first packing simulation result, a first box type matching degree between each first three-dimensional model and the candidate box type is determined.

[0117] In step S505, according to each first box type matching degree, a recommended box type of the first cargo is determined from each candidate box type.

[0118] In a specific implementation, the first box type matching degree includes a box type filling rate when the first three-dimensional model is placed inside a candidate box type and a box body consumable cost corresponding to the candidate box type. The box body consumable cost corresponding to the candidate box type is determined according to the box type feature information. The consumable cost constraint condition is established according to the business scenario feature information. The recommended box type of the first cargo is determined from the candidate box types whose box body consumable costs satisfy the consumable cost constraint condition. The box type filling rate of the recommended box type is within the third target range.

[0119] In another specific implementation, in a case where the box type filling rates of the candidate box types are all less than the target filling rate, the multiple candidate box types of the first cargo are determined multiple times from the multiple available box types until the box type filling rate of at least one candidate box type in the current multiple candidate box types is greater than or equal to the target filling rate, the recommended box type of the first cargo is determined from the current candidate box types, or until the total number of times of determining the multiple candidate box types of the first cargo is equal to the number target value, the recommended box type of the first cargo is determined from the current candidate box types. The box type filling rate of the recommended box type is greater than or equal to the box type filling rates of the current candidate box types.

[0120] Step S506, in a case where the number of the items contained in the first cargo is greater than the number target value or the volume of the first cargo is greater than the volume target value, the first cargo is split to obtain multiple second cargos.

[0121] Step S507, according to the multi-dimensional feature information, the recommended box type of each second cargo is determined from the candidate box types.

[0122] In a specific implementation, the second cargos are processed in sequence. The processing order of the second cargos is determined according to the volumes of the second cargos. The volumes of the second cargos are determined according to the cargo feature information. In the process of processing each second cargo, the multiple second three-dimensional models corresponding to the second cargo and the second box type matching degrees between the second three-dimensional models and the candidate box types are determined according to the multi-dimensional feature information. The second three-dimensional models represent possible placement combinations of the second cargo, and the second box type matching degrees represent the feasibility of placing the second three-dimensional models in the box bodies corresponding to the candidate box types. The recommended box type of the second cargo is determined from the candidate box types according to the second box type matching degrees.

[0123] In a specific implementation, after determining the recommended box type, evaluation indexes are designed from the three dimensions of "technology-business-user", and the effect of the box type recommendation is comprehensively measured according to the evaluation indexes. The accuracy of the box type recommendation of a single day can reach more than 90%, the calculation cost and response speed are optimized, online reasoning is accelerated, the average calculation time of a single day is in the order of milliseconds, and it has been verified that the box type recommendation method provided in the embodiment can cover the logistics business of goods in 3C, beverages, cosmetics, shoes and clothes and other industries. Among them, the evaluation indexes include the average filling rate, the adaptation success rate, the packaging efficiency, the complaint rate and the satisfaction degree; the average filling rate refers to the average filling rate of all recommended box types; the adaptation success rate refers to the proportion of recommended box types that can be actually used normally; the packaging efficiency refers to the average packaging time of each order; the complaint rate refers to the proportion of customer complaints caused by box type problems (such as damage, size mismatch); and the satisfaction degree refers to the satisfaction score of warehouse operators on the recommended box type.

[0124] In the embodiment, by including the physical attributes (such as size, weight, material) of the first goods to be packed, the physical attributes (such as size, material cost) and load-bearing performance (such as dynamic load-bearing and static load-bearing) of the available box types, and the business scenario feature information representing the logistics business demand into a unified analysis framework, the comprehensiveness and accuracy of the box type recommendation can be improved, and the recommended box type of the first goods can be adjusted according to different logistics business scenarios, thereby improving the scene adaptability. Moreover, according to the above multi-dimensional feature information, the embodiment preliminarily screens a plurality of candidate box types that meet the box size constraint condition and the box load constraint condition for different types of goods such as flexible goods, irregular goods and fragile goods, which can adapt to the logistics transportation business demand of special types of goods, and obtains a first three-dimensional model by simulating a plurality of possible placement combinations of the first goods. According to the multi-dimensional feature information, the plurality of first three-dimensional models corresponding to the first goods and the first box type matching degree between each first three-dimensional model and the plurality of candidate box types are determined, which can realize the box type recommendation for the combined goods, thereby realizing the upgrade of the box type recommendation from "single size matching" to "full-scene, full-link optimization", and improving the efficiency, economy and reliability of logistics packaging.

[0125] It should be understood that although each step in the flowchart involved in the above-described embodiments is shown in sequence according to the direction of the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least some of the steps in the flowchart involved in the above-described embodiments can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or steps or stages in other steps. It can be understood that the steps in different embodiments can be freely combined as needed, and various non-contradictory schemes formed by the combination are within the scope of protection of the present application.

[0126] Based on the same inventive concept, the embodiments of the present application also provide a box type recommendation device for implementing the above-mentioned box type recommendation method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more box type recommendation device embodiments provided below can refer to the limitations of the box type recommendation method in the above text, which will not be repeated here.

[0127] In one exemplary embodiment, as shown in Figure 6 a box type recommendation device is provided, comprising:

[0128] The acquisition module 601 is configured to acquire multi-dimensional feature information in the process of carrying out the logistics business. The multi-dimensional feature information includes cargo feature information representing the physical attributes of the first cargo to be packed, box type feature information representing the physical attributes and carrying performance of the plurality of available box types, and business scenario feature information representing the logistics business demand.

[0129] The first determination module 602 is configured to determine, according to the multi-dimensional feature information, a plurality of first three-dimensional models corresponding to the first cargo and a first box type matching degree between each first three-dimensional model and the plurality of candidate box types. The first three-dimensional model represents a possible placement combination of the first cargo, and the first box type matching degree represents the feasibility of placing the first three-dimensional model in the box corresponding to the candidate box type.

[0130] The second determination module 603 is configured to determine, according to the first box type matching degree, a recommended box type of the first cargo from the candidate box types.

[0131] In an example embodiment, the first determining module 602 is further configured to establish a plurality of first three-dimensional models corresponding to the first cargo according to the cargo feature information, and establish a plurality of digital models corresponding to each candidate box type according to the box type feature information; the plurality of digital models corresponding to the candidate box type are obtained by rotating a box body corresponding to the candidate box type; for each candidate box type, the first three-dimensional models are placed inside the digital model corresponding to the candidate box type to obtain a first packing simulation result, and a first box type matching degree between the first three-dimensional models and the candidate box type is determined according to the first packing simulation result.

[0132] In an example embodiment, the box type recommendation apparatus can further include a splitting processing module. The splitting processing module is configured to determine a volume of the first cargo and a number of items contained in the first cargo according to the cargo feature information; split the first cargo to obtain a plurality of second cargos when the volume of the first cargo is greater than a volume target value; and determine a recommended box type of each second cargo from the plurality of second cargos in each candidate box type according to the multi-dimensional feature information.

[0133] In an example embodiment, the splitting processing module is further configured to process each second cargo in sequence; a processing order of each second cargo is determined according to a volume of each second cargo; the volume of each second cargo is determined according to the cargo feature information; during processing of each second cargo, a plurality of second three-dimensional models corresponding to the second cargo and a second box type matching degree between each second three-dimensional model and each candidate box type are determined according to the multi-dimensional feature information; the second three-dimensional models represent possible placement combinations of the second cargo, and the second box type matching degree represents a feasibility of placing the second three-dimensional model in a box body corresponding to the candidate box type; and a recommended box type of the second cargo is determined from each candidate box type according to the second box type matching degree.

[0134] In an example embodiment, the box type recommendation apparatus can further include a third determining module. The third determining module is configured to establish a box type size constraint condition and a box type weight constraint condition according to the cargo feature information and the business scenario feature information; determine a plurality of candidate box types of the first cargo from a plurality of available box types according to the box type feature information, the box type size constraint condition and the box type weight constraint condition; box type size information of the candidate box type satisfies the box type size constraint condition; and box type weight information of the candidate box type satisfies the box type weight constraint condition.

[0135] In an example embodiment, the third determining module is further configured to determine, according to the cargo characteristic information, cargo size information and a cargo type of the first cargo; in a case where the cargo type is a basic type or a common type, determine that the box size constraint condition is that an inner size of a box type of the candidate box type is greater than or equal to a maximum size of the first cargo; in a case where the cargo type is a flexible cargo, establish the box size constraint condition according to size information of a reserved folding space or a reserved compression space corresponding to the flexible cargo and the cargo size information; in a case where the cargo type is an irregular cargo, establish the box size constraint condition according to size information of a reserved placement adjustment space corresponding to the irregular cargo and the cargo size information; in a case where the cargo type is a fragile cargo, establish the box size constraint condition according to size information of a buffer layer corresponding to the fragile cargo and the cargo size information; determine, according to the cargo characteristic information, cargo weight information of the first cargo, and determine, according to the business scenario characteristic information, a logistics transportation safety coefficient; and establish a box bearing constraint condition according to the cargo weight information and the logistics transportation safety coefficient.

[0136] In an example embodiment, the third determining module is further configured to, in a case where the cargo type is a flexible cargo, determine, according to size information of a reserved folding space or a reserved compression space corresponding to the flexible cargo and the cargo size information, that the box size constraint condition is that an inner size of a box type of the candidate box type is greater than or equal to an unfolding reserved size corresponding to the flexible cargo; wherein a ratio of the unfolding reserved size corresponding to the flexible cargo to a size of the flexible cargo in a natural unfolding state is within a first target range.

[0137] In an example embodiment, the third determining module is further configured to, in a case where the cargo type is an irregular cargo, determine, according to size information of a reserved placement adjustment space corresponding to the irregular cargo and the cargo size information, that the box size constraint condition is that an inner size of a box type of the candidate box type is greater than or equal to a placement reserved size corresponding to the irregular cargo; wherein a ratio of the placement reserved size corresponding to the irregular cargo to a size of a minimum bounding box of the irregular cargo is within a second target range.

[0138] In an example embodiment, the third determining module is further configured to, in a case where the cargo type is a fragile cargo, determine that the box size constraint condition is that an inner size of a box type of the candidate box type is greater than or equal to a buffer reserved size corresponding to the fragile cargo; wherein the buffer reserved size corresponding to the fragile cargo is determined according to size information of a buffer layer corresponding to the fragile cargo and the cargo size information.

[0139] In an example embodiment, the box type matching degree includes a box type filling rate when the three-dimensional model is placed inside the candidate box type and a box body consumable cost corresponding to the candidate box type; the second determination module 603 is further configured to determine the box body consumable cost corresponding to the candidate box type according to the box type feature information, establish a consumable cost constraint condition according to the business scenario feature information, and determine the recommended box type of the first goods from the candidate box types whose box body consumable costs satisfy the consumable cost constraint condition; and the box type filling rate of the recommended box type is within the third target range.

[0140] In an example embodiment, the second determination module 603 is further configured to, in a case where the box type filling rates of the candidate box types are all less than the target filling rate, determine multiple candidate box types of the first goods from the multiple available box types multiple times until the box type filling rate of at least one candidate box type in the current multiple candidate box types is greater than or equal to the target filling rate, and then determine the recommended box type of the first goods from the current candidate box types; and the box type filling rate of the recommended box type is greater than or equal to the box type filling rates of the current candidate box types.

[0141] In an example embodiment, the second determination module 603 is further configured to, in a case where the box type filling rates of the candidate box types are all less than the target filling rate, determine multiple candidate box types of the first goods from the multiple available box types multiple times until the total number of times of determining the multiple candidate box types of the first goods is equal to the number target value, and then determine the recommended box type of the first goods from the current candidate box types; and the box type filling rate of the recommended box type is greater than or equal to the box type filling rates of the current candidate box types.

[0142] Each module in the above box type recommendation apparatus can be realized by software, hardware, and a combination thereof in whole or in part. Each module can be embedded in or independent of a processor in a computer device in a hardware form, or stored in a memory in a computer device in a software form, so as to be called and executed by a processor to perform operations corresponding to each module.

[0143] In an example embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in FIG. 8. Figure 7As shown in the figure. The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store multi-dimensional feature information and other data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to realize a box type recommendation method.

[0144] Those skilled in the art can understand that, Figure 7 The person skilled in the art can understand that,

[0145] In one exemplary embodiment, a computer device is provided, including a memory and a processor, the memory stores a computer program, and the processor executes the computer program to realize the steps in the above method embodiments.

[0146] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by the processor to realize the steps in the above method embodiments.

[0147] In one embodiment, a computer program product is provided, including a computer program, and the computer program is executed by the processor to realize the steps in the above method embodiments.

[0148] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0149] The technical features of the above embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist, they should be considered as the scope of the present application.

[0150] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A box type recommendation method, characterized in that, The method includes: Acquire multi-dimensional feature information during the logistics operation process; the multi-dimensional feature information includes cargo feature information that characterizes the physical attributes of the first cargo to be packed, box type feature information that characterizes the physical attributes and load-bearing capacity of multiple available box types, and business scenario feature information that characterizes the logistics business requirements. Based on the multi-dimensional feature information, multiple first three-dimensional models corresponding to the first cargo and a first box type matching degree between each first three-dimensional model and multiple candidate box types are determined; the first three-dimensional model represents the possible placement combination of the first cargo, and the first box type matching degree represents the feasibility of placing the first three-dimensional model in the box corresponding to the candidate box type. Based on the matching degree of each of the first container types, the recommended container type for the first cargo is determined from among the candidate container types.

2. The method according to claim 1, characterized in that, The step of determining multiple first three-dimensional models corresponding to the first cargo and the first container type matching degree between each first three-dimensional model and multiple candidate container types based on the multi-dimensional feature information includes: Based on the cargo feature information, multiple first three-dimensional models corresponding to the first cargo are established, and based on the box type feature information, multiple digital models corresponding to each candidate box type are established; the multiple digital models corresponding to the candidate box types are obtained by rotating the box body corresponding to the candidate box type. For each candidate box type, the first three-dimensional model is placed inside the digital model corresponding to the candidate box type to obtain a first box packing simulation result. Based on the first box packing simulation result, a first box type matching degree between each first three-dimensional model and the candidate box type is determined.

3. The method according to claim 1, characterized in that, Before determining the multiple first three-dimensional models corresponding to the first cargo and the first container type matching degree between each first three-dimensional model and multiple candidate container types based on the multi-dimensional feature information, the method further includes: Based on the cargo characteristic information, determine the volume of the first cargo; If the volume of the first cargo is greater than the target volume value, the first cargo is split into multiple second cargoes; Based on the multi-dimensional feature information, a recommended container type for each of the second goods is determined from among the candidate container types.

4. The method according to claim 3, characterized in that, The step of determining the recommended container type for each of the second goods from among the candidate container types based on the multi-dimensional feature information includes: Each of the second goods is processed sequentially; the processing order of each of the second goods is determined based on the volume of each of the second goods; the volume of each of the second goods is determined based on the goods characteristic information. In the process of processing each of the second goods, based on the multi-dimensional feature information, multiple second three-dimensional models corresponding to the second goods and the second box type matching degree between each second three-dimensional model and each of the candidate box types are determined; the second three-dimensional model represents the possible placement combination of the second goods, and the second box type matching degree represents the feasibility of placing the second three-dimensional model in the box corresponding to the candidate box type; Based on the second container type matching degree, the recommended container type for the second cargo is determined from among the candidate container types.

5. The method according to claim 1, characterized in that, Before determining the multiple first three-dimensional models corresponding to the first cargo and the first container type matching degree between each first three-dimensional model and multiple candidate container types based on the multi-dimensional feature information, the method further includes: Based on the cargo characteristic information and the business scenario characteristic information, establish container size constraints and container load-bearing constraints; Based on the container type feature information, the container type size constraints, and the container type load-bearing constraints, multiple candidate container types for the first cargo are determined from the multiple available container types; the container type size information of the candidate container types satisfies the container type size constraints; and the container type load-bearing information of the candidate container types satisfies the container type load-bearing constraints.

6. The method according to claim 5, characterized in that, The step of establishing container size constraints and container load-bearing constraints based on the cargo characteristic information and the business scenario characteristic information includes: Based on the cargo characteristic information, determine the cargo size information and cargo type of the first cargo; When the cargo type is either a basic category or a general category, the box size constraint is determined to be that the internal size of the candidate box type is greater than or equal to the maximum size of the first cargo. When the cargo type is flexible cargo, box size constraints are established based on the size information of the reserved folding space or reserved compression space corresponding to the flexible cargo and the cargo size information; When the cargo type is irregular cargo, box size constraints are established based on the size information of the reserved placement adjustment space corresponding to the irregular cargo and the cargo size information. When the cargo type is fragile cargo, box size constraints are established based on the size information of the buffer layer corresponding to the fragile cargo and the cargo size information. Based on the cargo characteristic information, determine the cargo weight information of the first cargo, and based on the business scenario characteristic information, determine the logistics transportation safety factor; Based on the cargo weight information and the logistics transportation safety factor, load-bearing constraints for the container type are established.

7. The method according to claim 6, characterized in that, When the cargo type is flexible cargo, based on the size information of the reserved folding space or reserved compression space corresponding to the flexible cargo and the cargo size information, box size constraints are established, including: When the cargo type is flexible cargo, the box size constraint is determined based on the size information of the reserved folding space or reserved compression space corresponding to the flexible cargo and the cargo size information, that is, the internal size of the candidate box type is greater than or equal to the unfolded reserved size corresponding to the flexible cargo. The ratio of the pre-extension allowance dimension corresponding to the flexible cargo to the dimension of the flexible cargo in its naturally extended state is within the first target range.

8. The method according to claim 6, characterized in that, When the goods are irregularly shaped, based on the size information of the reserved placement adjustment space corresponding to the irregular goods and the size information of the goods, box size constraints are established, including: When the cargo type is irregular cargo, based on the size information of the reserved placement adjustment space corresponding to the irregular cargo and the cargo size information, the box size constraint condition is determined to be that the internal size of the candidate box type is greater than or equal to the reserved placement size corresponding to the irregular cargo. The ratio of the reserved placement size for the irregular goods to the size of the smallest enclosing box of the irregular goods is within the second target range.

9. The method according to claim 6, characterized in that, When the cargo type is fragile, based on the size information of the buffer layer corresponding to the fragile cargo and the cargo size information, box size constraints are established, including: When the cargo type is fragile cargo, the box size constraint is determined to be that the internal size of the candidate box type is greater than or equal to the buffer reserve size corresponding to the fragile cargo. The buffer reserve size corresponding to the fragile goods is determined based on the size information of the buffer layer corresponding to the fragile goods and the size information of the goods.

10. The method according to any one of claims 1 to 9, characterized in that, The first box type matching degree includes the box type filling rate when the first three-dimensional model is placed inside the candidate box type and the box material cost corresponding to the candidate box type; The step of determining the recommended container type for the first cargo from among the candidate container types based on the first container type matching degree includes: Based on the box type feature information, determine the box body consumable cost corresponding to the candidate box type; Based on the business scenario characteristics, establish consumable cost constraints; Among the candidate container types whose container material costs meet the material cost constraints, a recommended container type for the first cargo is determined; the container type fill rate of the recommended container type is within the third target range.

11. The method according to claim 10, characterized in that, The step of determining the recommended container type for the first cargo from among the candidate container types based on the first container type matching degree further includes: If the container filling rate of each of the candidate container types is less than the target filling rate, multiple candidate container types for the first cargo are determined from the multiple available container types multiple times until the container filling rate of at least one of the current multiple candidate container types is greater than or equal to the target filling rate. Then, the recommended container type for the first cargo is determined from the current candidate container types. Wherein, the box filling rate of the recommended box type is greater than or equal to the box filling rate of each of the current candidate box types.

12. The method according to claim 10, characterized in that, The step of determining the recommended container type for the first cargo from among the candidate container types based on the first container type matching degree further includes: If the container filling rate of each of the candidate container types is less than the target filling rate, the candidate container types of the first cargo are determined multiple times from the multiple available container types until the total number of times the candidate container types of the first cargo are determined equal to the target number. Then, the recommended container type of the first cargo is determined from the current candidate container types. Wherein, the box filling rate of the recommended box type is greater than or equal to the box filling rate of each of the current candidate box types.

13. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 12.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 12.

15. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 12.

Images