Method and device for providing operation instruction in air freight logistics

Abstract

The invention provides a method and a device for providing operation instructions in air freight logistics. The method may include: identifying, by a camera device of a terminal device, a package and extracting information about the package; generating or predicting a unit decomposition model of the parcel based on the extracted information; identifying environment information and user information of the terminal device and determining a loading operation point; a unit decomposition model and a loading algorithm are applied to calculate an expected loading shape of a container (ULD) and the expected loading shape is output by augmented reality (AR).

Description

[0001] Cross-references to related applications

[0002] This application claims priority and benefit to Korean Patent Application No. 10-2024-0143187 filed with the Korean Intellectual Property Office on October 18, 2024, and Korean Patent Application No. 10-2025-0135444 filed with the Korean Intellectual Property Office on September 19, 2025, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This invention relates to a method and apparatus for providing operational instructions in air cargo logistics. Background Technology

[0004] In the air freight industry, the process of loading cargo into Unit Load Devices (ULDs) relies heavily on the experience and intuition of the workers. However, because cargo received on pallets or individually numbered units cannot directly provide the accurate dimensions and shape of each package, it is difficult to calculate the expected load rate in advance during the actual loading process. Furthermore, the difficulty for workers to accurately determine the loading location and shape leads to reduced loading efficiency and frequent rework. Additionally, the inability to determine whether cargo has a regular or irregular pattern, or whether it exists in blind spots, during operations can cause confusion during loading. Summary of the Invention

[0005] The aim of this solution is to provide methods and apparatus for providing operational instructions in air cargo logistics, which can visually confirm the loading shape and expected load rate when loading cargo into a container (ULD) in the air cargo sector, thereby improving work efficiency.

[0006] According to one embodiment, a method for providing operational instructions in air cargo logistics is performed in a terminal device equipped with a camera, and the method may include: identifying packages and extracting information about the packages through the camera of the terminal device; generating or predicting a cell decomposition model of the packages based on the extracted information; identifying environmental and user information of the terminal device and determining the loading operation point; applying the cell decomposition model and loading algorithm to calculate the expected loading shape of the container (ULD), and outputting the expected loading shape via augmented reality (AR).

[0007] Identifying packages and extracting information about them using a camera device on a terminal device can include: using the Air Waybill (AWB) as a unique ID for the package during the booking stage; managing the number of package piece (PCS) units as a key value; and quantifying the separation number information by utilizing a post-inbound inspection and volume measurement system (VMS).

[0008] Generating or predicting a unit decomposition model of a package may include: generating modeling data based on the segmentation numbering information measured by VMS; and mapping the modeling data to an auxiliary database to construct the digital shape of the package.

[0009] Generating or predicting a cell decomposition model of a package may include: extracting the external surfaces of the modeling data and assigning an ID to each PCS cell; and predicting the size of the PCS cells.

[0010] Generating or predicting a cell decomposition model for a package may include: analyzing and dividing the boundary surfaces of the modeling data through gradients; and correcting the decomposition model of the PCS cell by inferring insufficient or excessive components by utilizing the correlation between the boxes.

[0011] The cell decomposition model for generating or predicting packages may include estimating individual boxes as clusters of regular cargo when the world dimensions (WLD) of individual boxes analyzed during the decomposition of packages exhibit the same pattern within the error range.

[0012] The method may further include: when a single container is estimated to be a cluster of regular goods, decomposing the entire package based on a combination of the number of WLD and PCS units; when the conditions for a regular goods cluster are not met, switching to an irregular goods cluster mode for analysis.

[0013] The unit decomposition model for generating or predicting packages may include: assigning dimensions to each individual ID of a package when it is confirmed in the analysis of irregular cargo cluster patterns that all captured cargo is box-shaped.

[0014] The method may further include: estimating goods in blind spots that were not directly identified during the analysis of irregular cargo cluster patterns, and reflecting the estimated goods in the decomposition model of the PCS cell.

[0015] The method may further include: when the ULD is identified by a camera device, displaying the shape of the ULD as a boundary area, and outputting the cargo to be loaded as a semi-transparent object through AR.

[0016] According to one embodiment, an apparatus for providing operational instructions in air cargo logistics includes: one or more non-volatile computer-readable media including instructions; and one or more processors configured to perform operations by executing the instructions, the operations including: identifying packages and extracting information about the packages via a camera device of a terminal device; generating or predicting a cell decomposition model of the packages based on the extracted information; identifying environmental information and user information of the terminal device and determining a loading operation point; applying the cell decomposition model and loading algorithms to calculate the expected loading shape of the container (ULD), and outputting the expected loading shape via augmented reality (AR).

[0017] Identifying packages and extracting information about them using a camera device on a terminal device can include: using the Air Waybill (AWB) as a unique ID for the package during the booking stage; managing the number of package piece (PCS) units as a key value; and quantifying the separation number information by utilizing a post-inbound inspection and volume measurement system (VMS).

[0018] Generating or predicting a unit decomposition model of a package may include: generating modeling data based on the segmentation numbering information measured by VMS; and mapping the modeling data to an auxiliary database to construct the digital shape of the package.

[0019] Generating or predicting a cell decomposition model of a package may include: extracting the external surfaces of the modeling data and assigning an ID to each PCS cell; and predicting the size of the PCS cells.

[0020] Generating or predicting a cell decomposition model for a package may include: analyzing and dividing the boundary surfaces of the modeling data through gradients; and correcting the decomposition model of the PCS cell by inferring insufficient or excessive components by utilizing the correlation between the boxes.

[0021] The cell decomposition model for generating or predicting packages may include estimating individual boxes as clusters of regular cargo when the world dimensions (WLD) of individual boxes analyzed during the decomposition of packages exhibit the same pattern within the error range.

[0022] The operation may further include: when a single box is estimated to be a cluster of regular goods, decomposing the entire package based on the combination of the number of WLD and PCS units; when the conditions for a regular goods cluster are not met, switching to an irregular goods cluster mode for analysis.

[0023] The unit decomposition model for generating or predicting packages may include: assigning dimensions to each individual ID of a package when it is confirmed in the analysis of irregular cargo cluster patterns that all captured cargo is box-shaped.

[0024] The operation may further include: estimating goods in blind spots that were not directly identified during the analysis of irregular cargo cluster patterns, and reflecting the estimated goods in the decomposition model of the PCS unit.

[0025] According to one embodiment, a computer-readable medium may include one or more non-volatile computer-readable media comprising instructions executable by a computing device, wherein, when executed by one or more processors of the computing device, the instructions cause the computing device to perform operations including: identifying a package and extracting information about the package via a camera device of a terminal device; generating or predicting a cell decomposition model of the package based on the extracted information; identifying environmental and user information of the terminal device and determining a loading operation point; applying the cell decomposition model and a loading algorithm to calculate the expected loading shape of the container (ULD); and outputting the expected loading shape via augmented reality (AR). Attached Figure Description

[0026] Figure 1 This is a schematic diagram illustrating a device for providing operational instructions in air cargo logistics according to one implementation scheme.

[0027] Figure 2 This is a schematic diagram illustrating a method for providing operational instructions in air cargo logistics according to one implementation plan.

[0028] Figures 3 to 5 This is a schematic diagram illustrating an example of the implementation of apparatus and methods for providing operational instructions in air cargo logistics.

[0029] Figure 6 It is a schematic diagram illustrating a computing device according to one embodiment. Detailed Implementation

[0030] In the following, embodiments of the invention will be described in detail with reference to the accompanying drawings to enable those skilled in the art to readily implement the invention. However, the invention can be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, parts unrelated to the description have been omitted for clarity, and the same reference numerals are assigned to the same parts throughout the specification.

[0031] Throughout the specification and claims, when a component is referred to as "comprising" an element, this means that the component does not exclude other components but may further include other components, unless otherwise specifically stated. Terms including ordinal numbers such as first, second, etc., may be used to describe various components, but the components are not limited by these terms. These terms are used only to distinguish one component from another.

[0032] The terms “…unit” and “…module” described in the specification may refer to a unit capable of performing at least one of the functions or operations described in the specification, and may be implemented in hardware or circuitry, software, or a combination of hardware or circuitry and software. Furthermore, at least some configurations or functions of the method and apparatus for providing operational instructions in air cargo logistics according to the embodiments described below may be implemented as programs or software, and such programs or software may be stored in a computer-readable recording medium or storage medium.

[0033] Figure 1 This is a schematic diagram illustrating a device for providing operational instructions in air cargo logistics according to one implementation scheme.

[0034] Reference Figure 1 According to one embodiment, the device 10 for providing operational instructions in air cargo logistics can be implemented as a computing device including a processor and memory. For example, the device 10 for providing operational instructions in air cargo logistics can be implemented as a device that later combines... Figure 6 The computing device 50 described herein. In this case, the processor may correspond to processor 510 of computing device 50, and the memory may correspond to memory 520 of computing device 50. Alternatively, in some embodiments, the means 10 for providing operational instructions in air cargo logistics may include one or more non-volatile computer-readable media containing instructions and one or more processors configured to perform operations by executing the instructions. Here, the operations may include the configuration, functions, and steps described herein with respect to the methods and means for providing operational instructions in air cargo logistics according to embodiments. In this specification, the term "module" is used to logically distinguish these operations performed by the methods and means for providing operational instructions in air cargo logistics according to embodiments.

[0035] The device 10 for providing operational instructions in air cargo logistics may include a package identification module 11, a modeling and decomposition prediction module 12, an operation point determination module 13, and an object simulation and visualization module 14.

[0036] The package identification module 11 can identify packages and extract information about them using the camera device of the terminal device. Here, the terminal device may correspond to the device 10 that provides operational instructions in air freight logistics. The camera device may be an imaging device that can be used to acquire images of packages.

[0037] A parcel can refer to a single unit of cargo loaded into a container (ULD) or pallet during air transport. Parcels can be distinguished by an Air Waybill (AWB), grouped into warehouses according to separation numbers, and further subdivided into multiple individual parcel units, i.e., pieces (PCS) units, within each separation number. In other words, compared to pallet-level cargo as a higher unit, a parcel can correspond to an individual unit of cargo, can have inconsistent sizes and shapes, and can take various forms, including regular (e.g., box-shaped) or irregular shapes.

[0038] Information about a package may include identifying information such as an air waybill number or segment number, physical specifications such as the package's width, length, height, volume, or weight, and appearance information such as the package's shape, surface pattern, or material properties. Additionally, detailed unit information such as the number of packages (PCS) included in the package and the ID assigned to each PCS may also be included in the package information.

[0039] In some implementations, the package identification module 11 may include: using the AWB as a unique ID for the package during the ordering stage, managing the number of PCS units as a key value, and quantifying the separation number information by utilizing a post-inbound inspection and volume measurement system (VMS).

[0040] The modeling and decomposition prediction module 12 can generate or predict a unit decomposition model of the package based on the information extracted by the package identification module 11. Here, the unit decomposition model can refer to a digital model including the size, shape, position, and volume of each PCS unit obtained by decomposing the package into PCS units. The unit decomposition model can correspond to the result of converting the total volume of the package into decomposable units based on identification information such as AWB, separator number, and PCS information. Furthermore, the unit decomposition model of the package can be a digital simulation result that predictively presents the shape and arrangement of the individual PCS units that constitute the actual package, and can be used as input data for loading algorithms to calculate the ULD loading shape and expected loading rate.

[0041] In some implementations, the modeling and decomposition prediction module 12 can generate modeling data based on the segmentation number information measured by the VMS, and can construct the digital shape of the package by mapping the modeling data to an auxiliary database. Here, the modeling data can be three-dimensional shape data generated based on the size, volume, and appearance shape information of the segmentation number units obtained from the VMS. The modeling data can represent the outline or boundary surface of the package as polygons, or it can be simplified and represented as cuboid data in the form of a box, and in some cases, it can further include pattern information extracted through image analysis. In addition, the expected size and ID of each PCS unit can be assigned to the modeling data, and the overall structure of the package can be represented as subdivided units. Meanwhile, the auxiliary database can include reference information needed to correct or interpret the modeling data. For example, the auxiliary database can store the package's booking and warehousing history, AWB tracking number, PCS quantity, logistics terminal environment information, and past measurement data.

[0042] By mapping modeling data to an auxiliary database, the overall digital shape of a package can be constructed, which is difficult to ascertain solely through measured dimensions. This constructed digital shape can subsequently improve the prediction accuracy of the unit decomposition model and can be used as input data for the ULD loading algorithm.

[0043] In some implementations, the modeling and decomposition prediction module 12 can extract the external surfaces of the modeling data, assign an ID to each PCS unit, and predict the size of the PCS unit. Here, extracting the external surfaces can mean analyzing the boundary lines of the 3D modeling data measured by VMS to identify the surfaces that form the shape of the package. External surfaces can be defined such that the boundaries between adjacent surfaces are separated by using edge detection algorithms or image analysis techniques, allowing the PCS units to be distinguishable within the overall package modeling. Once each PCS unit is distinguished, a unique ID can be assigned to the distinguished PCS unit.

[0044] Meanwhile, the dimensions of each PCS cell can be calculated based on the boundary length and height of the outer surface. With the width, length, and height dimensions predicted, the volume and shape of the PCS cell can be defined, and these can be used as input data for the ULD loading algorithm to calculate the loading rate.

[0045] In some implementations, the modeling and decomposition prediction module 12 can analyze and partition the boundary surfaces of the modeling data through gradient analysis, and can correct the decomposition model of the PCS element by inferring insufficient or excessive components by utilizing the correlation between boxes. Here, analyzing the boundary surfaces through gradient analysis can mean detecting height differences, depth differences, or geometric discontinuities between adjacent surfaces in the 3D modeling data measured by VMS, and distinguishing individual blocks that constitute the package. Through such analysis, provisional boundaries of the PCS element can be established.

[0046] At this point, the correlation between containers can be derived by utilizing the dimensions, patterns, and arrangement rules of other PCS units included in the same partition number. For example, in the case of repetitive regular goods with the same dimensions, even if the dimensions on some surfaces are not fully extracted, the missing parts can be inferred based on the correlation with other containers, and over-extracted components can be corrected based on the average value or regularity within the cluster. Therefore, a cell decomposition model that is more similar to the actual state can be constructed.

[0047] In some implementations, when the world dimensions (WLDs) of individual boxes analyzed during package decomposition exhibit the same pattern within an error range, the modeling and decomposition prediction module 12 can estimate the individual boxes as clusters of regular goods. Here, WLDs exhibiting the same pattern within an error range can mean that the width, length, and height values ​​of each box match within a predetermined tolerance range. For example, when multiple boxes are determined to all have the same standard cuboid shape, these boxes can be considered regular goods. In the case where boxes are estimated as clusters of regular goods, the modeling and decomposition prediction module 12 can simplify the cell decomposition model by repeatedly arranging multiple boxes with the same dimensions. By processing in this way, the decomposition speed of goods with repeating patterns can be improved, and computational resources can be saved.

[0048] In some implementations, when a package is estimated to be a cluster of regular goods, the modeling and decomposition prediction module 12 can decompose the entire package based on a combination of WLD and PCS unit numbers. Furthermore, when the conditions for a regular goods cluster are not met, it can switch to an irregular goods cluster analysis mode. Therefore, efficiency can be improved when packages have a regular pattern, and accuracy can be ensured when packages have an irregular pattern, thus providing a stable unit decomposition model for various types of goods.

[0049] In some implementations, when it is confirmed in the irregular cargo cluster pattern analysis that all the captured cargo is box-shaped, the modeling and decomposition prediction module 12 can assign a size to each individual ID cargo and estimate the cargo in the blind spots that are not directly identified in the irregular cargo cluster pattern analysis and reflect the estimated cargo in the decomposition model of the PCS unit.

[0050] Here, confirming whether a shipment is box-shaped can be done by applying contour detection or surface recognition algorithms to the captured images. Each shipment can be identified as box-shaped if it meets the basic geometric features of a cuboid. At this point, each shipment can be matched with the ID assigned by the package identification module 11, and its width, length, and height dimensions can be recorded in the corresponding ID. These dimensional values ​​can be corrected using VMS measurement data.

[0051] Simultaneously, cargo in blind spots can be estimated to compensate for limitations in camera shooting angles, the presence of shadows, or areas obscured by other cargo. This estimation can be achieved by utilizing the size and positional relationships of adjacent containers, as well as repetitive pattern information within the same cluster. The estimated cargo in blind spots can be inserted into the model as new PCS units or added to missing areas in the existing decomposition model.

[0052] The work point determination module 13 can determine the loading work point by identifying environmental information and user information of the terminal device. Here, environmental information can be information collected through the terminal device's camera, position sensor, or wireless communication module, and can include the coordinates of a specific area within the logistics terminal where the terminal device is located, image patterns of the surrounding structure, or wireless network signal strength. Environmental information can be compared and matched with pre-registered reference data in the logistics terminal and can be used to identify which area the terminal device is located in. User information can include the ID of the staff logged into the terminal device, shift information, or a work schedule assigned by the logistics management server. In other words, the work point determination module 13 can automatically assign a loading work point by comprehensively considering environmental and user information and matching the terminal environment where the terminal device is currently located with the work area assigned to the staff. Once the work point is determined, visualization of the parcel's unit breakdown model and output of the ULD loading shape can be achieved to correspond to the actual area assigned to the staff.

[0053] The object simulation and visualization module 14 can apply a unit decomposition model and loading algorithm to calculate the expected loading shape of the ULD, and can output the expected loading shape via augmented reality (AR). In some embodiments, when the ULD is identified by a camera device, the object simulation and visualization module 14 can display the shape of the ULD as a boundary area, and can output the expected loaded cargo as a semi-transparent object via AR.

[0054] Here, the expected loading shape can be the result of applying the dimensions, volume, and arrangement orientation of the individual PCS units included in the unit decomposition model to the loading algorithm, and together the occupancy rate and expected loading rate of the entire ULD can be calculated. The calculated expected loading shape can be displayed as an AR object superimposed on an image from a camera device at the terminal device. For example, unloaded packages can be output as semi-transparent boxes superimposed inside the ULD, and the remaining loading space can be visually displayed compared to loaded packages. Workers can intuitively view the expected loading rate, loading orientation, and remaining space through the terminal device screen, thus enabling efficient loading operations without relying on experience.

[0055] According to this implementation plan, when parcels are loaded into a ULD (Unified Loading Distributor) in the air cargo sector, the size and shape of individual parcel units can be predicted, and accurate loading rates can be calculated. Furthermore, by distinguishing between regular and irregular cargo and estimating cargo in blind spots, a unit decomposition model similar to the actual situation can be provided. Additionally, based on environmental and user information, loading operation points can be automatically designated, and by visualizing the expected loading shape and loading rate using AR (Augmented Reality), operational instructions can be provided in a highly immersive manner while reducing worker confusion.

[0056] Figure 2 This is a schematic diagram illustrating a method for providing operational instructions in air cargo logistics according to one implementation plan.

[0057] Reference Figure 2 According to one embodiment, a method for providing operational instructions in air cargo logistics may include: identifying packages and extracting information about the packages using a camera device of a terminal device (S201); generating or predicting a cell decomposition model of the packages based on the extracted information (S202); identifying environmental and user information of the terminal device and determining the loading operation point (S203); and applying the cell decomposition model and loading algorithm to calculate the expected loading shape of the container (ULD), and outputting the expected loading shape via augmented reality (S204).

[0058] A more detailed description of the method can be found in the descriptions of other embodiments included in this specification, and therefore repeated descriptions will be omitted.

[0059] Figures 3 to 5 This is a schematic diagram illustrating an example of the implementation of apparatus and methods for providing operational instructions in air cargo logistics.

[0060] Reference Figure 3The left side shows the results of shaping modeling data based on information measured by VMS and mapping the modeling data to an auxiliary database, while the right side shows the results of extracting external surfaces from the modeling data, assigning PCSIDs to the cargo, and predicting dimensions.

[0061] As can be seen from the left, in the initial stage, packages are measured while they are stacked, resulting in a complex overall shape and unclear boundaries for the goods. Therefore, the measurement data obtained from the VMS can be mapped to an auxiliary database to be associated with each package's booking information, AWB, PCS quantity, etc., and can be used as reference data for possible breakdowns in subsequent stages.

[0062] On the right, as the outer surfaces are extracted, the boundaries of individual container units are derived, and a unique ID is assigned to each PCS and visualized on each PCS. Furthermore, since the boundaries of the container units are represented by different colors, it is intuitively understood that what appears to be a single collection of goods is actually composed of multiple PCS units. This size-predicted PCS unit model can be input into the loading algorithm and used as base data to calculate the optimal loading shape and expected loading rate in the ULD.

[0063] Reference Figure 4 The results of extracting and reconstructing the modeling data into PCS sub-boxes are shown.

[0064] Here, each sub-box represents a separate PCS unit that makes up the package, and they are distinguished and displayed with different colors. This allows for a visual understanding of how multiple PCS units are arranged within the overall cargo structure, and each PCS unit can be defined with a unique ID and dimensions. The reconstructed modeling data is based on the mapping results of VMS measurement information and an auxiliary database, subsequently derived through external surface extraction and boundary analysis and correction processes. Therefore, Figure 4 The results shown visually demonstrate the state of goods in the original aggregate form being subdivided into PCS units and converted into a digital model.

[0065] Reference Figure 5 An example of a terminal device screen viewed by staff is shown, in which the expected cargo when the ULD is captured can be represented as a semi-transparent object, and the expected load rate can also be displayed.

[0066] Here, the terminal device's camera identifies the actually loaded goods, and the object simulation and visualization module 14 can output the expected loading shape, calculated through the application unit decomposition model and loading algorithm, as a semi-transparent box superimposed on the screen. In this way, workers can visually see the location and orientation of the unloaded goods within the ULD. Furthermore, the expected loading rate, considering the current loading volume and remaining space, can be displayed digitally on the screen. Because the actual environment image and AR object are displayed in this combined manner, workers can immediately determine the optimal loading shape and efficiency without relying solely on experience. Therefore, the terminal device's screen can serve as a mixed reality-based work instruction interface that simultaneously displays the actual goods and the expected loaded goods.

[0067] Figure 6 It is a schematic diagram illustrating a computing device according to one embodiment.

[0068] Reference Figure 6 The method and apparatus for providing operational instructions in air cargo logistics according to the implementation scheme can be implemented using a computing device 50. Such a computing device 50 can be implemented as various forms of electronic devices, servers or similar devices, and its functions can be implemented through a combination of software and hardware.

[0069] The computing device 50 may include at least one of a processor 510, a memory 530, a user interface input device 540, a user interface output device 550, and a storage device 560 that communicate with each other via a bus 520. The computing device 50 may further include a network interface 570 electrically connected to a network 40. The network interface 570 can send or receive signals with other entities via the network 40.

[0070] Processor 510 can be implemented as various types of processing devices, such as a microcontroller unit (MCU), application processor (AP), central processing unit (CPU), graphics processing unit (GPU), neural processing unit (NPU), or quantum processing unit (QPU). Processor 510 can be a semiconductor device that executes instructions stored in memory 530 or storage device 560 and can perform the core tasks of the system. The program code and data stored in memory 530 or storage device 560 instruct processor 510 to perform specific tasks, thereby enabling the operation of the entire system. Processor 510 can thus be configured to implement the above-described... Figures 1 to 5 The various functions and methods described.

[0071] Memory 530 and storage device 560 may include various types of volatile or non-volatile storage media for storing and accessing system data. For example, memory 530 may include read-only memory (ROM) 531 and random access memory (RAM) 532. In some embodiments, memory 530 may be embedded within processor 510, in which case data transfer speeds between memory 530 and processor 510 can be very high. In other embodiments, memory 530 may be located external to processor 510, in which case memory 530 may be connected to processor 510 via various data buses or interfaces. Such connections may be made through various known means, such as peripheral component interconnect high-speed (PCIe) interfaces for high-speed data transfer or memory controllers.

[0072] In some embodiments, at least a portion of the configuration or function of the method and apparatus for providing operational instructions in air cargo logistics according to the embodiments can be implemented as a program or software executed by computing device 50, and said program or software can be stored in a computer-readable recording medium or storage medium. Specifically, the computer-readable recording medium or storage medium according to one embodiment can record a program for performing the steps included in the implementation of the method and apparatus for providing operational instructions in air cargo logistics according to the embodiments on a computer including processor 510 (which executes programs or commands stored in memory 530 or storage device 560).

[0073] In some implementations, at least part of the configuration or function of the method and apparatus for providing operational instructions in air cargo logistics according to the implementation can be implemented using the hardware or circuitry of the computing device 50, or can be implemented as separate hardware or circuitry that can be electrically connected to the computing device 50.

[0074] In some embodiments, one or more non-volatile computer-readable media may be provided containing instructions executable by computing device 50, and when executed by one or more processors of computing device 50, the instructions may cause computing device 50 to perform operations. Here, the operations may include the configuration, functions, and steps of the methods and apparatus described herein with respect to providing operational instructions in air cargo logistics according to embodiments.

[0075] According to the implementation plan, when parcels are loaded into a ULD (Unified Loading Distributor) in the air cargo sector, the size and shape of individual parcels can be predicted, and accurate loading rates can be calculated. Furthermore, by distinguishing between regular and irregular cargo and estimating cargo in blind spots, a cell decomposition model similar to the actual situation can be provided. Additionally, based on environmental and user information, loading operation points can be automatically designated, and by visualizing the expected loading shape and loading rate using AR (Augmented Reality), operational instructions can be provided in a highly immersive manner while reducing worker confusion.

[0076] Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements made by those skilled in the art using the basic concepts of the present invention as defined in the appended claims also fall within the scope of the present invention.

Claims

1. A method for providing operational instructions in air cargo logistics, the method being performed in a terminal device equipped with a camera, the method comprising: The terminal device's camera identifies the package and extracts information about it. A unit decomposition model for generating or predicting packages is generated based on the extracted information; Identify environmental and user information of the terminal device and determine the loading operation point; The application of a cell decomposition model and loading algorithm is used to calculate the expected loading shape of the container, and the expected loading shape is output via augmented reality.

2. The method according to claim 1, wherein, Identifying packages and extracting information about them using the camera device on the terminal device includes: Use the air waybill as the unique ID for the package during the booking stage; The number of package units is managed as a key value; The separation numbering information is quantified by using a post-warehousing inspection and volume measurement system.

3. The method according to claim 2, wherein, Unit decomposition models for generating or predicting packages include: Modeling data is generated based on the partition numbering information measured by the volume measurement system; The modeling data is mapped to an auxiliary database to construct the digital shape of the package.

4. The method according to claim 3, wherein, Unit decomposition models for generating or predicting packages include: Extract the external surfaces from the modeling data and assign an ID to each part unit; Predict the dimensions of the component unit.

5. The method according to claim 4, wherein, Unit decomposition models for generating or predicting packages include: The boundary surfaces of the modeling data are analyzed and divided using differentials; The decomposition model of the component unit is corrected by inferring insufficient or excessive components by utilizing the correlation between the boxes.

6. The method according to claim 1, wherein, Unit decomposition models for generating or predicting packages include: When the world dimensions of individual boxes analyzed during the parcel decomposition process exhibit the same pattern within the error range, the individual boxes are estimated as clusters of regular goods.

7. The method of claim 6, further comprising: When individual boxes are estimated as clusters of regular goods, the entire package is broken down based on a combination of world size and the number of piece units; When the conditions for regular cargo clusters are not met, switch to irregular cargo cluster mode for analysis.

8. The method according to claim 7, wherein, Unit decomposition models for generating or predicting packages include: When it is confirmed in the analysis of irregular cargo cluster patterns that all the captured cargo is box-shaped, a size is assigned to each individual cargo ID.

9. The method of claim 8, further comprising: The estimated cargo is located in blind spots that were not directly identified during the analysis of irregular cargo cluster patterns, and the estimated cargo is reflected in the decomposition model of the unit.

10. The method of claim 1, further comprising: When the container is identified by the camera device, the shape of the container is displayed as a boundary area and the cargo to be loaded is output as a semi-transparent object through augmented reality.

11. An apparatus for providing operational instructions in air cargo logistics, the apparatus comprising: One or more non-volatile computer-readable media including instructions; as well as One or more processors configured to perform operations by executing the instructions, the operations including: The terminal device's camera identifies the package and extracts information about it. A unit decomposition model for generating or predicting packages is generated based on the extracted information; Identify environmental and user information of the terminal device and determine the loading operation point; The application of a cell decomposition model and loading algorithm is used to calculate the expected loading shape of the container, and the expected loading shape is output via augmented reality.

12. The apparatus for providing operational instructions in air cargo logistics according to claim 11, wherein, Identifying packages and extracting information about them using the camera device on the terminal device includes: Use the air waybill as the unique ID for the package during the booking stage; The number of package units is managed as a key value; The separation numbering information is quantified by using a post-warehousing inspection and volume measurement system.

13. The apparatus for providing operational instructions in air cargo logistics according to claim 12, wherein, Unit decomposition models for generating or predicting packages include: Modeling data is generated based on the partition numbering information measured by the volume measurement system; The modeling data is mapped to an auxiliary database to construct the digital shape of the package.

14. The apparatus for providing operational instructions in air cargo logistics according to claim 13, wherein, Unit decomposition models for generating or predicting packages include: Extract the external surfaces from the modeling data and assign an ID to each part unit; Predict the dimensions of the component unit.

15. The apparatus for providing operational instructions in air cargo logistics according to claim 14, wherein, Unit decomposition models for generating or predicting packages include: The boundary surfaces of the modeling data are analyzed and divided using differentials; The decomposition model of the component unit is corrected by inferring insufficient or excessive components by utilizing the correlation between the boxes.

16. The apparatus for providing operational instructions in air cargo logistics according to claim 11, wherein, Unit decomposition models for generating or predicting packages include: When the world dimensions of individual containers analyzed during the parcel decomposition process exhibit the same pattern within the error range, the individual containers are estimated as clusters of regular goods.

17. The apparatus for providing operational instructions in air cargo logistics according to claim 16, wherein, The operation further includes: When individual boxes are estimated as clusters of regular goods, the entire package is broken down based on a combination of world size and the number of piece units; When the conditions for regular cargo clusters are not met, switch to irregular cargo cluster mode for analysis.

18. The apparatus for providing operational instructions in air cargo logistics according to claim 17, wherein, Unit decomposition models for generating or predicting packages include: When it is confirmed in the analysis of irregular cargo cluster patterns that all the captured cargo is box-shaped, a size is assigned to each individual cargo ID.

19. The apparatus for providing operational instructions in air cargo logistics according to claim 18, wherein, The operation further includes: The estimated cargo is located in blind spots that were not directly identified during the analysis of irregular cargo cluster patterns, and the estimated cargo is reflected in the decomposition model of the unit.

20. One or more non-volatile computer-readable media comprising instructions executable by a computing device, wherein, When executed by one or more processors of a computing device, the instructions cause the computing device to perform operations, the operations including: The terminal device's camera identifies the package and extracts information about it. A unit decomposition model for generating or predicting packages is generated based on the extracted information; Identify environmental and user information of the terminal device and determine the loading operation point; The application of a cell decomposition model and loading algorithm is used to calculate the expected loading shape of the container, and the expected loading shape is output via augmented reality.

Images