Logistics and transportation intelligent auxiliary commodity protection methods and related equipment

Abstract

The present invention discloses a method and related equipment for intelligently assisting commodity protection in logistics transportation, and relates to the field of logistics. The method includes: obtaining the packaging type information of e-commerce logistics commodities before loading, transshipment or delivery, wherein the packaging type information is obtained based on the recognition of packaging image information, and the packaging type information includes the material, size and shape of the packaging; predicting the load-bearing boundary information of each commodity packaging to be loaded based on the packaging type information; calculating the optimal commodity stacking strategy through a three-dimensional loading algorithm according to the dead weight information, load-bearing boundary information, packaging type information and three-dimensional modeling information of the vehicle storage space of different commodities, so as to generate commodity stacking prompt information based on the stacking strategy. The method can solve the problem that in e-commerce express logistics transportation, especially in the loading stage of transshipment and delivery, when commodities are stacked, the packaging of the stacked commodities and even the commodities themselves are easily squeezed and damaged.

Description

Technical Field

[0001] The present invention relates to the field of logistics, and in particular to a smart-assisted commodity protection method and related equipment for logistics transportation. Background Art

[0002] In e-commerce express logistics transportation, especially in the loading stage of transshipment and delivery, goods may be stacked. Due to the different types of goods and different types of packaging, logistics staff usually only consider the weight of the goods and stack the heavier goods at the bottom. The packaging of the stacked goods and even the goods themselves are easily squeezed and damaged. Summary of the Invention

[0003] In view of the above problems, the present invention provides a smart assisted commodity protection method and related equipment for logistics transportation. The main purpose is to solve the problem that in e-commerce express logistics transportation, especially in the loading stage of transshipment and delivery, commodities may be stacked and the packaging of the stacked commodities and even the commodities themselves may be easily squeezed and damaged.

[0004] To solve at least one of the above technical problems, in a first aspect, the present invention provides a method for intelligently assisting commodity protection in logistics transportation, the method comprising:

[0005] Obtaining packaging type information of e-commerce logistics products before loading, transshipment or delivery. The packaging type information is obtained based on packaging image information recognition, and the packaging type information includes the material, size and shape of the packaging;

[0006] Predicting the load-bearing boundary information of each commodity package to be loaded based on the package type information;

[0007] The optimal product stacking strategy is calculated using a three-dimensional loading algorithm based on the weight information, load-bearing boundary information, packaging type information, and three-dimensional modeling information of the vehicle storage space of different products, so as to generate product stacking prompt information based on the stacking strategy.

[0008] Optionally, the product stacking prompt information includes a product stacking order, and the method further includes:

[0009] Based on the stacking order of the commodities, the corresponding commodities are sequentially transferred to the vehicle storage space so as to execute the commodity stacking strategy manually or automatically.

[0010] Optionally, the material of the packaging includes the structure and thickness of the packaging layer, and the method further includes:

[0011] Extracting material features from the packaging image information, wherein the material features particularly include the cross-sectional features of the packaging layer edge seal and the material features of the packaging surface;

[0012] Identifying the structure and thickness of the packaging layer based on the cross-sectional features of the packaging edge seal;

[0013] The load-bearing boundary information of the commodity packaging is predicted based on the packaging type information in combination with the structure and thickness of the packaging layer and the material characteristics of the packaging surface.

[0014] Optionally, also include:

[0015] Obtain product type and / or merchant type based on backend order information;

[0016] predicting the internal support type of the package according to the product type and / or merchant type;

[0017] The load-bearing boundary information of the commodity packaging is predicted based on the packaging type information in combination with the internal support type.

[0018] Optionally, also include:

[0019] If it is impossible to extract effective packaging layer edge sealing cross-sectional features based on packaging image information, obtain the product net weight through backend order information;

[0020] Obtain the packaged weight by weighing to calculate the net weight of the package;

[0021] Predicting the structure and thickness of the packaging layer based on the net weight of the packaging and the packaging type information including the material, size and shape of the packaging;

[0022] The load-bearing boundary information of the commodity packaging is predicted based on the packaging type information in combination with the structure and thickness of the packaging layer and the material characteristics of the packaging surface.

[0023] Optionally, also include:

[0024] In the loading and delivery scenario, the delivery route is planned based on the product stacking strategy so that when arriving at each delivery address, there are no other stacked products on the surface of the product associated with the delivery address.

[0025] Optionally, also include:

[0026] Obtaining the actual time and location of the cold chain goods in the automatic receiving cabinet;

[0027] According to the distribution information, a cell is allocated for the goods to be delivered in the optimal automatic receiving cabinet. The allocated cell is located in the cell of the concentrated area of ​​the stored cold chain goods and is the cell to be picked up that is idle the shortest distance from the current moment.

[0028] In a second aspect, an embodiment of the present invention further provides a smart auxiliary commodity protection device for logistics transportation, the device comprising:

[0029] An acquisition unit is used to obtain packaging type information of e-commerce logistics products before loading, transshipment or delivery. The packaging type information is obtained based on packaging image information recognition, and the packaging type information includes the material, size and shape of the packaging;

[0030] A prediction unit, configured to predict the load-bearing boundary information of each commodity package to be loaded on the vehicle based on the package type information;

[0031] The calculation unit is used to calculate the optimal product stacking strategy through a three-dimensional loading algorithm based on the weight information, load-bearing boundary information, packaging type information and three-dimensional modeling information of the vehicle storage space of different products, so as to generate product stacking prompt information based on the stacking strategy.

[0032] In order to achieve the above-mentioned purpose, according to the third aspect of the present invention, a computer-readable storage medium is provided, and the above-mentioned computer-readable storage medium includes a stored program, wherein when the above-mentioned program is executed by the processor, the above-mentioned logistics transportation intelligent assisted commodity protection method is implemented.

[0033] In order to achieve the above-mentioned purpose, according to the fourth aspect of the present invention, there is provided an electronic device, comprising at least one processor and at least one memory connected to the above-mentioned processor; wherein the above-mentioned processor is used to call the program instructions in the above-mentioned memory to execute the above-mentioned intelligent assisted commodity protection method for logistics transportation.

[0034] Through the above-mentioned technical solution, the present invention provides a method and related equipment for intelligently assisting product protection in logistics and transportation. This method obtains packaging information for e-commerce logistics products before loading, transshipment, or delivery. This packaging information, obtained through packaging image recognition and including the packaging material, size, and shape, is then used to predict the load-bearing capacity of each product package to be loaded. A three-dimensional loading algorithm is then used to calculate the optimal product stacking strategy based on the product's weight, load-bearing capacity, packaging type, and three-dimensional modeling of the vehicle's storage space. This strategy is then used to generate product stacking prompts. Automatically identifying packaging information improves data collection efficiency and accuracy and reduces manual errors. Based on packaging material and shape information, customized stacking strategies can be provided for different product types. For example, for fragile items, the system can recommend placing them in a higher position or isolating them separately. By predicting the load-bearing capacity, the load-bearing capacity of each product can be accurately determined, thus avoiding overloading. By avoiding stacking overweight items below fragile items, packaging damage or product damage caused by excessive pressure can be effectively reduced. By optimizing stacking positions, transport efficiency is improved while ensuring the safety of each product. The system automatically provides stacking recommendations based on data, reducing errors caused by manual intervention and improving the accuracy of the entire logistics process. The system eliminates the need for operators to identify or verify the specific products within the package; it relies solely on external packaging information (such as material, size, and weight) to calculate and predict load-bearing boundaries.

[0035] Correspondingly, the intelligent auxiliary commodity protection device, electronic device and computer-readable storage medium for logistics transportation provided by the embodiments of the present invention also have the above-mentioned technical effects.

[0036] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0038] Figure 1 A schematic diagram showing a flow chart of a method for intelligently assisting commodity protection in logistics transportation provided by an embodiment of the present invention is shown;

[0039] Figure 2A schematic block diagram showing the composition of a smart auxiliary commodity protection device for logistics transportation provided by an embodiment of the present invention is shown;

[0040] Figure 3 A schematic block diagram of the composition of an intelligent auxiliary commodity protection electronic device for logistics transportation provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0041] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0042] In order to solve the problem that the packaging of stacked goods and even the goods themselves are easily squeezed and damaged when goods are stacked in e-commerce express logistics transportation, especially in the loading stage of transshipment and delivery, the embodiment of the present invention provides a logistics transportation intelligent auxiliary goods protection method, such as Figure 1 As shown, the method includes:

[0043] S101. Obtain packaging type information of e-commerce logistics products before loading, transshipment or delivery. The packaging type information is obtained based on packaging image information recognition, and the packaging type information includes the material, size and shape of the packaging.

[0044] S102: Predicting the load-bearing boundary information of each commodity package to be loaded based on the package type information.

[0045] S103: Calculate an optimal product stacking strategy using a three-dimensional loading algorithm based on the weight information, load-bearing boundary information, packaging type information, and three-dimensional modeling information of the vehicle storage space of different products, and generate product stacking prompt information based on the stacking strategy.

[0046] It is understandable that by combining product packaging type information, product weight information, load-bearing boundary information and vehicle storage space information, a more intelligent and scientific product stacking solution can be provided for e-commerce logistics and transportation, thereby reducing the risk of damage to products during transportation.

[0047] For example, packaging type information refers to features such as the material, size, and shape of the product packaging. This information is crucial for determining how the product withstands external pressure when stacked. By recognizing images of product packaging, detailed packaging characteristics can be extracted. Before loading, use a high-definition camera or mobile device to capture images of the packaging appearance of each product. The image should be as clear as possible to capture the main features of the product packaging. The packaging image is analyzed using a deep learning algorithm (such as a convolutional neural network, CNN) to automatically identify the material (such as carton, foam, plastic, etc.), size (length, width, height), and shape (regular or irregular) of the packaging. This step can be done with the help of existing computer vision technology and image processing technology. Based on the recognition results, the product packaging is classified into different types (such as fragile items, soft items, large items, heavy items, etc.).

[0048] For example, the load-bearing boundary information refers to the maximum load that the product packaging can withstand when it is under pressure. Products with different packaging materials and shapes have different boundaries when subjected to external pressure. By predicting the load-bearing capacity of the product packaging, it is possible to avoid excessive pressure on the products during stacking, thereby avoiding damage to the packaging or the products. According to the material type of the product packaging, a load-bearing model for each material is established. For example, the pressure that a cardboard box can withstand is much lower than that of a metal or plastic container. Use finite element analysis (FEA) or other mechanical simulation techniques to simulate the compressive force that the product is subjected to during the stacking process and predict its bearing capacity. For packages of different shapes and sizes, the system will simulate the load-bearing distribution based on actual conditions. When predicting the load-bearing capacity, it is also necessary to introduce a safety factor to ensure that the product packaging can maintain a certain degree of integrity even under extreme conditions.

[0049] For example, based on the commodity's deadweight information, load-bearing boundary information, packaging type information and vehicle storage space information, the system can comprehensively consider how to optimally stack the commodities in the transport compartment to ensure that the commodities are not subjected to excessive pressure or displacement during transportation, thereby improving the safety and efficiency of transportation. The deadweight of each commodity can be automatically obtained by scanning a label or barcode. For irregularly shaped commodities, the system estimates its center of gravity position and overall weight by predicting the packaging shape. Detailed information on the interior space of the vehicle is obtained using three-dimensional modeling technology to determine the optimal stacking position for each commodity. Cargo loading algorithms (such as virtual stacking or heuristic algorithms) can be used to calculate the optimal stacking solution. Based on the deadweight, load-bearing boundary, packaging type and space information of each commodity, the system automatically generates stacking prompt information. This information includes the optimal stacking position and stacking order for each commodity, such as stacking heavy objects first, then light objects, and placing fragile items on top.

[0050] Through the above-mentioned technical solution, the present invention provides an intelligently assisted product protection method for logistics transportation. This method obtains packaging information for e-commerce logistics products before loading, transshipment, or delivery. This packaging information, obtained through packaging image recognition and including the packaging material, size, and shape, is then used to predict the load-bearing boundary of each product package to be loaded. A three-dimensional loading algorithm is then used to calculate the optimal product stacking strategy based on the product's weight, load-bearing boundary, packaging type, and three-dimensional modeling of the vehicle's storage space. This strategy is then used to generate product stacking prompts. Automatically identifying packaging information improves data collection efficiency and accuracy and reduces manual errors. Based on packaging material and shape information, customized stacking strategies can be provided for different product types. For example, for fragile items, the system can recommend placing them in a higher position or isolating them separately. By predicting the load-bearing boundary, the load-bearing range of each product can be accurately determined, thus avoiding overloading. By avoiding stacking overweight items below fragile items, damage to packaging or products caused by excessive pressure can be effectively reduced. By optimizing stacking positions, transportation efficiency is improved while ensuring the safety of each product. The system automatically provides stacking recommendations based on data, reducing errors caused by manual intervention and improving the accuracy of the entire logistics process. The system does not require operators to understand or confirm the specific products inside the package, relying solely on external packaging information (such as material, size, and weight) to calculate and predict load-bearing boundaries.

[0051] In one embodiment, the product stacking prompt information includes a product stacking order, and the method further includes:

[0052] Based on the stacking order of the commodities, the corresponding commodities are sequentially transferred to the vehicle storage space so as to execute the commodity stacking strategy manually or automatically.

[0053] It can be understood that by introducing the product stacking order prompt function, not only the stacking strategy is optimized, but also the product delivery and stacking order are closely integrated, thereby further improving the loading efficiency and accuracy.

[0054] For example, after the stacking strategy is calculated, a loading order list of items is generated based on the three-dimensional model of the vehicle cargo hold and the stacking strategy. For example, the item list can be arranged from bottom to top as [A, B, C, D], where A represents the bottom item and D represents the top item. The items can be transferred sequentially to the vehicle storage space. An electronic screen or handheld device can be used to display the number and location of the items currently being loaded to logistics personnel. Automated conveying equipment (such as conveyor belts or automated guided vehicles (AGVs)) can also be used to deliver items to the vehicle cargo hold in the stacking order. After each transfer, the current task status is updated in real time, for example, "Stacking completed item: A, next item: B." Product stacking information is displayed through a visual interface and may include images or names of the items currently being loaded, their orientation and location, and any load-bearing margins that require attention. During manual loading, the operator confirms the item's location and marks it complete. During automated loading, the system monitors and provides real-time feedback.

[0055] For example, based on the optimization results of a three-dimensional loading algorithm, the order can be generated according to the following rules: Weight priority, with heavier items being loaded first to ensure they are positioned at the bottom; load-bearing priority, prioritizing items with lower load-bearing capacity to prevent them from being stacked in inappropriate locations; and space optimization, dynamically adjusting the stacking order based on the vehicle's cargo hold shape and available space. Automated conveying equipment, combined with barcode or RFID tag scanning systems, identifies the items and matches them to the stacking order indicated in the prompts. By controlling the conveying equipment's operating sequence and path, each item is ensured to arrive at the target location in the specified order. Cameras or sensors within the cargo hold monitor the stacking status of the items and automatically determine whether the stacking is accurate. If errors occur (such as item shifting), the system prompts the operator to make adjustments or triggers an automatic correction mechanism. This automatically delivers items to the stacking location, reducing manual search and handling time and improving work efficiency. By combining stacking prompts with the conveying order, items are ensured to be accurately placed in the intended location, reducing the risk of damage caused by improper stacking. The combination of automated conveying and stacking order makes the entire loading process more intelligent, reduces manual intervention, and improves loading quality.

[0056] According to some embodiments, the material of the packaging includes the structure and thickness of the packaging layer, and the method further includes:

[0057] Extracting material features from the packaging image information, wherein the material features particularly include the cross-sectional features of the packaging layer edge seal and the material features of the packaging surface;

[0058] Identifying the structure and thickness of the packaging layer based on the cross-sectional features of the packaging edge seal;

[0059] The load-bearing boundary information of the commodity packaging is predicted based on the packaging type information in combination with the structure and thickness of the packaging layer and the material characteristics of the packaging surface.

[0060] It is understandable that through detailed feature analysis of the packaging material (including edge sealing cross-sectional features and surface material features), the structure and thickness of the packaging layer can be more accurately identified, and the load-bearing boundary of the packaging can be predicted based on this information.

[0061] For example, the cross-sectional features of the package edge seal refer to the layered structure, thickness, and material arrangement observed from the side of the package. By extracting these features through image processing technology, the number of packaging layers, the materials between the layers, and the thickness of each layer can be identified. The surface material features of the package include surface texture, color, and reflectivity. These features can reflect the material type of the package (such as paper, plastic, metal, etc.). Based on the cross-sectional features of the edge seal, a pattern recognition algorithm (such as a convolutional neural network, CNN) is used to analyze the layered structure of the package, and the thickness is calculated by measuring the cross-sectional width. For example, the cross-sectional features of the edge seal of a corrugated box show a three-layer structure, including an outer cardboard layer, a corrugated core layer, and an inner cardboard layer. The thickness of each layer can be accurately extracted using an edge detection algorithm. Combined with the structure and thickness of the packaging layers, the compressive strength and load-bearing boundary of the package are calculated based on a mechanical model. For example, the compressive strength of a corrugated box C = F·P·Z, where C is the compressive strength, F is the edge pressure strength, P is the perimeter, and Z is the box coefficient.

[0062] For example, an industrial camera or high-resolution scanner can be used to capture images of the edge seal cross-section and surface material of a product package. Image processing techniques (such as edge detection and segmentation algorithms) are used to extract the multilayer structure of the cross-section. The material and thickness of each layer are identified based on geometric features (such as gap width and interlayer uniformity). Texture analysis algorithms (such as Gabor filters) are used to extract surface texture features. The material type of the packaging surface is classified based on optical properties (such as reflectivity and color). The extracted edge seal cross-sectional features are analyzed to identify the packaging's structural layers and thickness. Based on the extracted material information and thickness, the load-bearing boundary is calculated using a packaging mechanics model. If the packaging is cardboard, the compressive strength is calculated to predict the maximum load-bearing capacity. If the packaging is plastic or metal, finite element analysis is used to simulate the deformation and rupture risk of the packaging under stacking pressure. Therefore, compared to relying solely on a rough classification of packaging material, this solution, based on a comprehensive analysis of edge seal cross-section and surface features, can more accurately predict the load-bearing boundary, particularly for multi-layer composite packaging. This solution can handle complex packaging structures (such as multi-layer corrugated paper, composite plastic, and metal packaging), improving its adaptability to different packaging types. Providing more reliable load-bearing boundary information helps optimize product stacking strategies and avoid packaging damage due to insufficient load-bearing capacity.

[0063] According to some embodiments, further comprising:

[0064] Obtain product type and / or merchant type based on backend order information;

[0065] predicting the internal support type of the package according to the product type and / or merchant type;

[0066] The load-bearing boundary information of the commodity packaging is predicted based on the packaging type information in combination with the internal support type.

[0067] It's understandable that by combining the product type and merchant type in backend order information, we can further predict the type of internal packaging support, thereby improving the accuracy of predicting the product packaging's load-bearing boundaries. This approach is suitable for handling complex packaging structures, such as those with internal supports (such as fillers, trays, or partitions), and helps optimize packaging stacking strategies.

[0068] For example, the possible packaging structure and internal support type that may be used are inferred based on the characteristics of the goods (such as electronic products, food, and fragile items). For example, foam support or plastic fixed frames are often used for electronic products, and bubble film or corrugated partitions are often used for fragile items. The standard packaging methods of different merchants may vary greatly. For example: high-end brands tend to use multi-layer protection and high-quality support, while ordinary merchants may use economical packaging. A correspondence model between internal support type and product / merchant type is established based on historical data. For example: for electronic products, the internal support is predicted to be a foam mold; for merchant type: food supplier, the internal support is predicted to be a cardboard partition. The load-bearing boundary is predicted in combination with the internal support type, and the packaging load-bearing boundary calculation model is updated based on the predicted internal support type (such as support material, size, and distribution). For example, foam support enhances compressive performance and improves the load-bearing capacity of the package. Loose fillers (such as shredded paper) have limited contribution to compressive performance.

[0069] Exemplarily, the system extracts product types (such as categories and brands) and merchant types (such as supplier names and logistics service levels) from the order database. For example, order information: Product type = glassware; Merchant type = high-end tableware brand. Using a machine learning model or rule engine, the internal support type of the packaging is predicted based on the product and merchant type. If the product type is fragile and the merchant type is a high-end brand, the predicted support type is foam support + cardboard partition. If the product type is an ordinary consumer product and the merchant type is a small or medium-sized merchant, the predicted support type is loose filler. The internal support type is used as an input variable and combined with the packaging type information to predict the load-bearing boundary. An example of a mechanical model update: for unsupported packaging, the load-bearing boundary is determined by the material and thickness of the outer packaging. For supported packaging, the load-bearing boundary is determined by both the outer packaging and the internal support. The model is Pmax = C outer packaging + C support, where C outer packaging is the load-bearing capacity of the outer packaging and C support is the load-bearing capacity of the internal support. The stacking order and position are updated based on the new load-bearing boundary information. Visual prompts are provided to guide manual or automated equipment in loading. By factoring in internal support types, predictions are more accurate than ever, particularly for complex packaging, ensuring a more precise assessment of load-bearing capacity. This reduces the risk of packaging deformation or product damage caused by insufficient or unevenly distributed internal support. Packaging solutions are optimized based on merchant characteristics and product features, improving logistics service quality.

[0070] According to some embodiments, further comprising:

[0071] If it is impossible to extract effective packaging layer edge sealing cross-sectional features based on packaging image information, obtain the product net weight through backend order information;

[0072] Obtain the packaged weight by weighing to calculate the net weight of the package;

[0073] Predicting the structure and thickness of the packaging layer based on the net weight of the packaging and the packaging type information including the material, size and shape of the packaging;

[0074] The load-bearing boundary information of the commodity packaging is predicted based on the packaging type information in combination with the structure and thickness of the packaging layer and the material characteristics of the packaging surface.

[0075] It's understandable that by incorporating product and packaged weight data, when edge cross-sectional features can't be extracted from package images, the package's structure and thickness can be predicted based on the net weight and other known information (such as material, size, and shape), ultimately predicting the package's load-bearing boundary. This approach provides a complementary solution for scenarios where information is missing, improving its applicability and reliability.

[0076] Exemplarily, the net weight of the package is the result of subtracting the net weight of the product from the weight of the packaging: Wpackaging = Wtotal - Wproduct, where Wpackaging is the net weight of the package, Wtotal is the weight of the packaging, and Wproduct is the net weight of the product. Based on the net weight of the package and the packaging type information (material, size, shape), the structure and thickness of the packaging layer can be inferred: the net weight of the package can reflect the density and distribution of the packaging material. Combined with the size and shape, the thickness of the packaging layer is estimated based on the density standard of the packaging material (such as corrugated paper, plastic film, etc.). Combined with the structure and thickness of the packaging layer and the surface material characteristics, the load-bearing capacity of the package is predicted based on the mechanical model. Therefore, when the packaging image information is unavailable, the weighing and order data are used to supplement the prediction process to ensure the continuity of the load-bearing boundary prediction. The structure and thickness are inferred based on the net weight of the package, and combined with the known material properties, the accuracy of the calculation of the compressive strength of the package is improved. It is suitable for complex or diverse packaging structures, especially when the edge sealing cross-section information cannot be directly obtained.

[0077] According to some embodiments, further comprising:

[0078] In the loading and delivery scenario, the delivery route is planned based on the product stacking strategy so that when arriving at each delivery address, there are no other stacked products on the surface of the product associated with the delivery address.

[0079] As you can see, by combining product stacking strategies with delivery route planning in the loading and delivery scenario, it is possible to unload goods at each delivery address without moving other products. This approach can significantly improve delivery efficiency, avoid the risk of product damage caused by multiple handling, and enhance logistics service quality.

[0080] For example, the product stacking strategy is usually calculated based on the weight, load-bearing limit and packaging type of the product to ensure the safety of stacking. On this basis, combined with the delivery path information, the products associated with each delivery address are arranged in a position that is easy to remove (such as the top or outside) to ensure that other products do not need to be moved during unloading. The goal is to match the stacking order with the delivery path, reduce the time cost and labor of repeated handling, and avoid the squeezing and collision of products caused by handling. Avoid moving other products every time unloading to save operating time. Reduce the risk of squeezing, collision or damage to products during handling. Fast unloading and efficient delivery improve customer satisfaction.

[0081] According to some embodiments, further comprising:

[0082] confirming the internal support type of the package through the fluoroscopic image data;

[0083] The load-bearing boundary information of the commodity packaging is predicted based on the packaging type information in combination with the internal support type.

[0084] As can be understood, by analyzing fluoroscopic image data (e.g., internal image data obtained through X-ray or other imaging techniques) to determine the internal support type of the product packaging, and combining this support type information with the packaging type information, the product packaging's load-bearing boundary information can be accurately predicted. This method further improves the accuracy of load-bearing boundary prediction and provides more reliable input for product stacking strategies.

[0085] Exemplarily, perspective imaging technology is used to obtain the internal structure data of the package. The characteristics of the internal support are extracted from the image, including the support material, support shape, distribution position and its geometric parameters. The internal support structure of the package has an important influence on the load-bearing performance. For example: evenly distributed honeycomb structure support helps to improve the overall load-bearing capacity, and asymmetric support may cause local uneven load-bearing. Based on the type and distribution of the support structure, the calculation model of the load-bearing boundary is adjusted. Combining the packaging type information (material, number of layers, thickness, size, etc.) and the internal support type information, a load-bearing boundary prediction model is established. The model outputs the load-bearing limit of the product in different pressure directions.

[0086] For example, N is the total number of goods, M is the total number of delivery addresses, and w i The weight of the i-th item, p i The delivery address index of the i-th item, p i ∈{1,2,…,M}, V is the three-dimensional geometric constraint of the vehicle cargo space (such as length, width, and height). R is the delivery path, R=[r1,r2,…,r M ], indicating the order of addresses to be reached in sequence. Decision variable x i,j ∈{0,1}, indicating whether product i is stacked on top of product j, if yes, then it is 1, otherwise it is 0. Stacking physical constraint, Among them C j Is the load-bearing boundary of commodity j. Spatial geometric constraints, the stacking position of commodities must be within the vehicle space V. For each commodity i, its position coordinate (x i ,y i ,z i ) and size (l i ,w i ,h i ) satisfies: 0≤x i ≤V x -l i ,0≤y i ≤V y -w i ,0≤z i ≤V z -h i , delivery order constraint, arrival address r k When all commodities i satisfy p i =r kThere are no other products stacked on the product surface, that is: In the process of target optimization, including stacking safety, maximizing load-bearing utilization, and reducing the risk of exceeding the load-bearing boundary during stacking: Minimize:∑ i,j x i,j ·(w i +w j -C j ) 2 Delivery efficiency, minimize the number of stacking and moving times, and ensure that there are no other products stacked at the address each time: Minimize:∑ i ∑ j x j,i ·δ(p i ≠p j ) where δ() is an indicator function; space utilization, maximizing vehicle space utilization and reducing vacant space: Maximize is the ratio of the actual product volume to the vehicle's total space volume. Therefore, the comprehensive optimization objective is a weighted sum: Objective: min(α1·Stacking Safety + α2·Delivery Efficiency - α3·Space Utilization). This mathematical method allows for efficient calculation of joint optimization strategies to meet the requirements of efficient, safe, and reliable logistics systems.

[0087] Furthermore, as a response to the above Figure 1 In addition to the implementation of the method shown in the figure, the embodiment of the present invention also provides a logistics transportation intelligent auxiliary commodity protection device for the above Figure 1 This device embodiment corresponds to the aforementioned method embodiment. For ease of reading, this device embodiment will not describe the details of the aforementioned method embodiment one by one, but it should be clear that the device in this embodiment can implement all the contents of the aforementioned method embodiment. Figure 2 As shown, the device includes:

[0088] An acquisition unit 21 is configured to acquire packaging type information of e-commerce logistics products before loading for transshipment or delivery. The packaging type information is obtained based on packaging image information recognition and includes the material, size, and shape of the packaging;

[0089] A prediction unit 22, configured to predict the load-bearing boundary information of each commodity package to be loaded on the vehicle based on the package type information;

[0090] The calculation unit 23 is used to calculate the optimal product stacking strategy based on the weight information, load-bearing boundary information, packaging type information and three-dimensional modeling information of the vehicle storage space of different products through a three-dimensional loading algorithm, so as to generate product stacking prompt information based on the stacking strategy.

[0091] Through the above-mentioned technical solution, the intelligent logistics and transportation auxiliary product protection device provided by the present invention obtains the packaging type information of e-commerce logistics products before loading, transshipment, or delivery. This packaging type information is obtained based on packaging image information recognition and includes the packaging material, size, and shape. Based on this packaging type information, the device predicts the load-bearing boundary information of each product package to be loaded. A 3D loading algorithm is used to calculate the optimal product stacking strategy based on the product's weight, load-bearing boundary information, packaging type information, and 3D modeling of the vehicle storage space. Product stacking prompts are generated based on this stacking strategy. Automatically identifying packaging information improves data collection efficiency and accuracy and reduces manual operation errors. Based on packaging material and shape information, customized stacking strategies can be provided for different product types. For example, for fragile items, the system can recommend placing them in a higher position or isolating them separately. By predicting the load-bearing boundary, the load-bearing range of each product can be accurately determined, thus avoiding overloading. By avoiding stacking overweight items below fragile items, damage to packaging or products caused by excessive pressure can be effectively reduced. By optimizing stacking positions, transportation efficiency is improved while ensuring the safety of each product. The system automatically gives stacking suggestions based on the data, reducing errors caused by manual intervention and improving the accuracy of the entire logistics process.

[0092] The processor includes a core, which retrieves the corresponding program unit from the memory. One or more cores can be configured, and by adjusting the core parameters, a smart logistics and transportation assisted product protection method can be implemented.

[0093] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program. When the program is executed by a processor, it implements the above-mentioned logistics transportation intelligent assisted commodity protection method.

[0094] An embodiment of the present invention provides a processor configured to run a program, wherein when the program is run, the method for intelligently assisting commodity protection in logistics and transportation is executed:

[0095] Obtaining packaging type information of e-commerce logistics products before loading, transshipment or delivery. The packaging type information is obtained based on packaging image information recognition, and the packaging type information includes the material, size and shape of the packaging;

[0096] Predicting the load-bearing boundary information of each commodity package to be loaded based on the package type information;

[0097] The optimal product stacking strategy is calculated using a three-dimensional loading algorithm based on the weight information, load-bearing boundary information, packaging type information, and three-dimensional modeling information of the vehicle storage space of different products, so as to generate product stacking prompt information based on the stacking strategy.

[0098] An embodiment of the present invention provides an electronic device comprising at least one processor and at least one memory connected to the processor; wherein the processor is configured to call program instructions in the memory to execute the above-described intelligently assisted commodity protection method for logistics transportation:

[0099] Obtaining packaging type information of e-commerce logistics products before loading, transshipment or delivery. The packaging type information is obtained based on packaging image information recognition, and the packaging type information includes the material, size and shape of the packaging;

[0100] Predicting the load-bearing boundary information of each commodity package to be loaded based on the package type information;

[0101] The optimal product stacking strategy is calculated using a three-dimensional loading algorithm based on the weight information, load-bearing boundary information, packaging type information, and three-dimensional modeling information of the vehicle storage space of different products, so as to generate product stacking prompt information based on the stacking strategy.

[0102] An embodiment of the present invention provides an electronic device 30, such as Figure 3 As shown, the electronic device includes at least one processor 301, and at least one memory 302 and a bus 303 connected to the processor; wherein the processor 301 and the memory 302 communicate with each other through the bus 303; the processor 301 is used to call the program instructions in the memory to execute the above-mentioned logistics transportation intelligent assisted commodity protection method.

[0103] The intelligent electronic devices in this article can be PCs, PADs, mobile phones, etc.

[0104] The present application also provides a computer program product, which, when executed on a process management electronic device, is adapted to execute a program for initializing the following method steps:

[0105] Obtaining packaging type information of e-commerce logistics products before loading, transshipment or delivery. The packaging type information is obtained based on packaging image information recognition, and the packaging type information includes the material, size and shape of the packaging;

[0106] Predicting the load-bearing boundary information of each commodity package to be loaded based on the package type information;

[0107] The optimal product stacking strategy is calculated using a three-dimensional loading algorithm based on the weight information, load-bearing boundary information, packaging type information, and three-dimensional modeling information of the vehicle storage space of different products, so as to generate product stacking prompt information based on the stacking strategy.

[0108] The present application is described with reference to the flowcharts and / or block diagrams of the methods, electronic devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable process management electronic device to produce a machine, so that the instructions executed by the processor of the computer or other programmable process management electronic device generate instructions for implementing the process in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0109] In a typical configuration, an electronic device includes one or more processors (CPUs), a memory, and a bus. The electronic device may also include an input / output interface, a network interface, and the like.

[0110] Memory may include non-permanent memory in a computer-readable medium, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory includes at least one memory chip. Memory is an example of a computer-readable medium.

[0111] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer-readable storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage electronic devices or any other non-transmission media that can be used to store information that can be accessed by computing electronic devices. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0112] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or electronic device that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, commodity, or electronic device. In the absence of further limitations, an element defined by the phrase "comprises a..." does not preclude the presence of additional identical elements in the process, method, commodity, or electronic device that includes the element.

[0113] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable computer-readable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0114] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for intelligently assisting commodity protection in logistics transportation, characterized in that: include: Obtaining packaging type information of e-commerce logistics products before loading, transshipment or delivery. The packaging type information is obtained based on packaging image information recognition, and the packaging type information includes the material, size and shape of the packaging; Obtain product type and / or merchant type based on backend order information; predicting the internal support type of the package according to the product type and / or merchant type; Predicting the load-bearing boundary information of each product package to be loaded based on the material, size, and shape of the package in combination with the internal support type, where the load-bearing boundary information refers to the maximum load that the product package can withstand when subjected to pressure; The optimal product stacking strategy is calculated through a three-dimensional loading algorithm based on the dead weight information, load-bearing boundary information, packaging type information and three-dimensional modeling information of the vehicle storage space of different products, so as to generate product stacking prompt information based on the stacking strategy, wherein the algorithm constraint conditions include that the product stacking cannot exceed the load-bearing boundary indicated by the load-bearing boundary information of the product packaging.

2. The method according to claim 1, characterized in that The product stacking prompt information includes the product stacking order, and the method further includes: Based on the stacking order of the commodities, the corresponding commodities are sequentially transferred to the vehicle storage space so as to execute the commodity stacking strategy manually or automatically.

3. The method according to claim 2, characterized in that The material of the packaging includes the structure and thickness of the packaging layer, and the method further includes: Extracting material features from the packaging image information, wherein the material features include the cross-sectional features of the packaging layer edge seal and the material features of the packaging surface; Identifying the structure and thickness of the packaging layer based on the edge sealing cross-sectional features of the packaging layer; The load-bearing boundary information of the commodity packaging is predicted based on the packaging type information in combination with the structure and thickness of the packaging layer and the material characteristics of the packaging surface.

4. The method according to claim 3, characterized in that Also includes: If it is impossible to extract effective packaging layer edge sealing cross-sectional features based on packaging image information, obtain the product net weight through backend order information; Obtain the packaged weight by weighing to calculate the net weight of the package; Predicting the structure and thickness of the packaging layer based on the net weight of the packaging and the packaging type information including the material, size and shape of the packaging; The load-bearing boundary information of the commodity packaging is predicted based on the packaging type information in combination with the structure and thickness of the packaging layer and the material characteristics of the packaging surface.

5. The method according to claim 1, wherein Also includes: confirming the internal support type of the package through the fluoroscopic image data; The load-bearing boundary information of the commodity packaging is predicted based on the packaging type information in combination with the internal support type.

6. The method according to claim 1, characterized in that Also includes: In the loading and delivery scenario, the delivery route is planned based on the product stacking strategy so that when arriving at each delivery address, there are no other stacked products on the surface of the product associated with the delivery address.

7. A smart auxiliary commodity protection device for logistics transportation, characterized in that: For implementing the method according to any one of claims 1 to 6, the device comprises: An acquisition unit is used to obtain packaging type information of e-commerce logistics products before loading, transshipment or delivery. The packaging type information is obtained based on packaging image information recognition, and the packaging type information includes the material, size and shape of the packaging; A prediction unit, configured to predict the load-bearing boundary information of each commodity package to be loaded on the vehicle based on the material, size, and shape of the package; A calculation unit is used to calculate the optimal product stacking strategy through a three-dimensional loading algorithm based on the dead weight information, load-bearing boundary information, packaging type information and three-dimensional modeling information of the vehicle storage space of different products, so as to generate product stacking prompt information based on the stacking strategy, wherein the algorithm constraint conditions include that the product stacking cannot exceed the load-bearing boundary indicated by the load-bearing boundary information of the product packaging.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed by a processor, the logistics and transportation intelligent assisted commodity protection method as described in any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: The electronic device includes at least one processor and at least one memory connected to the processor; wherein the processor is used to call program instructions in the memory to execute the intelligent assisted commodity protection method for logistics transportation as described in any one of claims 1 to 6.

Images