Baggage handling method and device for an airport based on baggage sorting, and electronic device

Abstract

This invention discloses an airport baggage handling method, apparatus, and electronic equipment based on baggage sorting, relating to the field of airport baggage scheduling technology. The method includes: inputting current baggage data into a preset learning model to obtain an initial weight set; determining the sorting score of each piece of baggage currently on the conveyor using a preset sorting scoring function based on the initial weight set, generating a queue of baggage to be handled; handling each piece of baggage in the queue; collecting current stacking data of the baggage handling equipment after handling; adjusting the weights based on the current stacking data and target stacking data; determining the sorting score of each piece of baggage currently on the conveyor based on the adjusted weights; and handling the baggage based on the sorting score until all baggage to be handled at the target airport has been handled. This invention solves the technical problem in related technologies where dynamic sorting of baggage is not possible, leading to low stacking completion rates.

Description

Technical Field

[0001] This invention relates to the field of airport baggage handling technology, and more specifically, to an airport baggage handling method, apparatus, and electronic equipment based on baggage sorting. Background Technology

[0002] With the rapid development of the aviation industry, airports have increasingly higher requirements for passenger baggage management. Currently, airport baggage transfer mainly relies on manual handling, which suffers from problems such as low efficiency, rough handling, and the inability of management personnel to obtain real-time baggage transfer location information, failing to meet the needs of efficient airport operation and management.

[0003] During airport baggage sorting and handling, baggage needs to be stacked according to the target flight, cargo hold space constraints, and safety and stability requirements. Current baggage scheduling generally uses a "first-come, first-served" or fixed rules to sort baggage. However, due to the large differences in baggage size and weight, baggage handling based on the current baggage scheduling method results in unstable stacking structures. Furthermore, in a multi-flight parallel environment, it is impossible to effectively and dynamically identify "critical baggage" (such as heavy, special-sized baggage that needs priority loading), and the current baggage scheduling method lacks real-time adjustment capabilities, leading to a decrease in stacking completion and handling speed.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides an airport baggage handling method, apparatus, and electronic device based on baggage sorting, to at least solve the technical problem in related technologies that the inability to dynamically sort baggage leads to low stacking completion.

[0006] According to one aspect of the present invention, an airport baggage handling method based on baggage sorting is provided, comprising: acquiring current baggage data of a target airport and inputting the current baggage data into a preset learning model to obtain an initial weight set; determining the sorting score of each piece of baggage currently located on a transport vehicle based on the initial weight set using a preset sorting scoring function, and generating a baggage queue based on the sorting score, wherein the transport vehicle is used to transport baggage; handling each piece of baggage in the baggage queue based on the queue order, and collecting current stacking data of the baggage handling equipment after handling is completed, wherein the current stacking data is used to characterize the stacking state of all the baggage that has been handled on the baggage handling equipment; adjusting each weight in the initial weight set based on the current stacking data and the target stacking data; determining the sorting score of each piece of baggage currently located on the transport vehicle based on the adjusted weights, and handling the baggage based on the sorting score, until all the baggage to be handled at the target airport has been handled.

[0007] Furthermore, before inputting the current baggage data into the preset learning model to obtain the initial weight set, the process includes: collecting historical baggage data and historical palletizing data corresponding to each historical baggage data. The historical baggage data includes at least: transportation type, flight type, and baggage attribute data. The historical palletizing data is used to represent the expected palletizing, which is obtained through ranking scoring indicators and the weights corresponding to each ranking scoring indicator. The preset learning model is trained using the historical baggage data and historical palletizing data to obtain the trained preset learning model. The trained preset learning model is used to output a set of weights, which are used to represent the importance of the ranking scoring indicators.

[0008] Furthermore, the step of determining the ranking score of each piece of luggage currently located on the transport vehicle based on the initial weight set and using a preset ranking scoring function includes: acquiring luggage attribute data for each piece of luggage to be transported, wherein the luggage attribute data includes at least: luggage size, luggage weight, and luggage shape; adjusting the weights in the initial ranking scoring function based on the initial weight set to obtain the preset ranking scoring function, wherein the preset ranking scoring function consists of multiple ranking scoring indicators, each ranking scoring indicator having a corresponding weight, and the ranking scoring indicators include at least one of the following: size indicator, weight indicator, spatial matching indicator, and palletizing strategy indicator; and determining the ranking score of each piece of luggage to be transported based on the luggage attribute data of the luggage to be transported using the preset ranking scoring function.

[0009] Furthermore, the step of determining the ranking score of the baggage to be handled based on the baggage attribute data and using a preset ranking scoring function includes: determining a size index value based on the baggage size included in the baggage attribute data; determining a weight index value based on the baggage weight included in the baggage attribute data; determining a space matching index value based on the baggage shape and remaining space on the baggage equipment included in the baggage attribute data; determining a palletizing strategy index value based on the type of the transport vehicle and the flight type included in the current baggage data; and determining the ranking score of the baggage to be handled based on the size index value, weight index value, space matching index value, and palletizing strategy index value using a preset ranking scoring function.

[0010] Furthermore, before adjusting each weight in the initial weight set based on the current palletizing data and the target palletizing data, the process includes: if a previous palletizing state exists, constructing a target palletizing model based on the previous palletizing state and a preset palletizing strategy, where the previous palletizing state refers to the stacking state of the luggage equipment before each piece of luggage to be moved in the handling queue; if no previous palletizing state exists, acquiring a 3D image of the luggage equipment; determining the current palletizing state based on the 3D image, and constructing a target palletizing model based on the current palletizing state and the preset palletizing strategy; and determining the target palletizing data based on the target palletizing model.

[0011] Furthermore, the step of adjusting each weight in the initial weight set based on the current palletizing data and the target palletizing data includes: determining the index value corresponding to each palletizing scoring indicator based on the current palletizing data and the target palletizing data, wherein the palletizing scoring indicators include at least one of the following: space utilization, stacking stability, weight distribution uniformity, baggage compliance, and operational efficiency; scoring the current palletizing status using a preset palletizing scoring function based on the index values ​​corresponding to all palletizing scoring indicators to obtain a palletizing score; and adjusting each weight in the initial weight set if the palletizing score is less than a preset palletizing score threshold.

[0012] Furthermore, the step of adjusting each weight in the initial weight set when the palletizing score is less than the preset palletizing score threshold includes: normalizing the index value corresponding to each palletizing score indicator to obtain the target index value; determining the ranking score indicator corresponding to each palletizing score indicator; determining the ranking score indicator corresponding to the target palletizing score indicator as the target ranking score indicator when the target index value corresponding to the target palletizing score indicator is the smallest; and adjusting the weight corresponding to the target ranking score indicator.

[0013] According to another aspect of the present invention, an airport baggage handling device based on baggage sorting is also provided, comprising: an acquisition unit, configured to acquire current baggage data of a target airport and input the current baggage data into a preset learning model to obtain an initial weight set; a first determination unit, configured to determine the sorting score of each piece of baggage currently located on a conveyor based on the initial weight set and using a preset sorting scoring function, and generate a baggage queue to be handled based on the sorting score, wherein the conveyor is used to transport baggage; a handling unit, configured to handle each piece of baggage in the baggage queue to be handled based on the queue order of the baggage queue to be handled, and, upon completion of handling, collect current stacking data of the baggage handling equipment, wherein the current stacking data is used to characterize the stacking state of all the baggage that has been handled on the baggage handling equipment; an adjustment unit, configured to adjust each weight in the initial weight set based on the current stacking data and the target stacking data; and a second determination unit, configured to determine the sorting score of each piece of baggage currently located on a conveyor based on the adjusted weights, and handle the baggage to be handled based on the sorting score until all the baggage to be handled at the target airport has been handled.

[0014] Furthermore, the airport baggage handling device also includes: a first acquisition module, used to acquire historical baggage data and historical palletizing data corresponding to each historical baggage data, before inputting the current baggage data into the preset learning model to obtain the initial weight set; wherein the historical baggage data includes at least: transport tool type, flight type, and baggage attribute data, and the historical palletizing data is used to represent the expected palletizing, which is obtained by ranking scoring indicators and the weights corresponding to each ranking scoring indicator; and a first training module, used to train the preset learning model using the historical baggage data and the historical palletizing data to obtain the trained preset learning model, wherein the trained preset learning model is used to output a set of weights, which are used to represent the importance of the ranking scoring indicators.

[0015] Further, the first determining unit includes: a first acquiring module, used to acquire luggage attribute data for each piece of luggage to be moved, wherein the luggage attribute data includes at least: luggage size, luggage weight, and luggage shape; a first adjusting module, used to adjust the weights in the initial ranking scoring function based on the initial weight set to obtain a preset ranking scoring function, wherein the preset ranking scoring function consists of multiple ranking scoring indicators, each ranking scoring indicator having a corresponding weight, and the ranking scoring indicators include at least one of the following: size indicator, weight indicator, spatial matching indicator, and palletizing strategy indicator; and a first determining module, used to determine the ranking score of each piece of luggage to be moved based on the luggage attribute data of the luggage to be moved using the preset ranking scoring function.

[0016] Furthermore, the first determining module includes: a first determining submodule, used to determine a size index value based on the baggage size contained in the baggage attribute data; a second determining submodule, used to determine a weight index value based on the baggage weight contained in the baggage attribute data; a third determining submodule, used to determine a space matching index value based on the baggage shape and remaining space on the baggage equipment contained in the baggage attribute data; a fourth determining submodule, used to determine a palletizing strategy index value based on the type of the transport tool and the flight type contained in the current baggage data; and a fifth determining submodule, used to determine the sorting score of the baggage to be handled using a preset sorting and scoring function based on the size index value, weight index value, space matching index value, and palletizing strategy index value.

[0017] Furthermore, the airport baggage handling device also includes: a first construction module, used to construct a target palletizing model based on the previous palletizing state and a preset palletizing strategy, before adjusting each weight in the initial weight set based on the current palletizing data and the target palletizing data, where the previous palletizing state refers to the stacking state of the baggage handling equipment before each piece of baggage to be handled in the handling queue; a second acquisition module, used to acquire three-dimensional images of the baggage handling equipment when the previous palletizing state does not exist; a second determination module, used to determine the current palletizing state based on the three-dimensional images, and construct the target palletizing model based on the current palletizing state and the preset palletizing strategy; and a third determination module, used to determine the target palletizing data based on the target palletizing model.

[0018] Furthermore, the adjustment unit includes: a fourth determining module, used to determine the index value corresponding to each palletizing scoring indicator based on the current palletizing data and the target palletizing data, wherein the palletizing scoring indicators include at least one of the following: space utilization, stacking stability, weight distribution uniformity, baggage compliance, and operational efficiency; a first scoring module, used to score the current palletizing state based on the index values ​​corresponding to all palletizing scoring indicators and using a preset palletizing scoring function to obtain a palletizing score; and a second adjustment module, used to adjust each weight in the initial weight set when the palletizing score is less than a preset palletizing score threshold.

[0019] Furthermore, the second adjustment module includes: normalizing the index value corresponding to each palletizing score indicator to obtain the target index value; determining the ranking score indicator corresponding to each palletizing score indicator; determining the ranking score indicator corresponding to the target palletizing score indicator as the target ranking score indicator when the target index value corresponding to the target palletizing score indicator is minimized; and adjusting the weight corresponding to the target ranking score indicator.

[0020] According to another aspect of the present invention, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the airport baggage handling method based on baggage sorting described above.

[0021] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement any of the above-described airport baggage handling methods based on baggage sorting.

[0022] In this invention, current baggage data of the target airport is acquired and input into a preset learning model to obtain an initial weight set. Based on the initial weight set, a preset ranking and scoring function is used to determine the ranking score of each piece of baggage currently on the transport vehicle. Based on the ranking score, a transport queue is generated. Based on the queue order, each piece of baggage in the transport queue is transported. After the transport is completed, the current stacking data of the baggage handling equipment is collected. Based on the current stacking data and the target stacking data, each weight in the initial weight set is adjusted. Based on the adjusted weights, the ranking score of each piece of baggage currently on the transport vehicle is determined. The baggage is then transported based on the ranking score until all baggage at the target airport has been transported. This solves the technical problem in related technologies where baggage cannot be dynamically sorted, resulting in low stacking completion.

[0023] This invention employs an intelligent learning model to automatically identify baggage handling sequences by collecting and dynamically analyzing baggage data from target airports in real time. This achieves efficient resource allocation and optimized workflows, solving the technical problems of low efficiency, rough handling, and the inability of management personnel to monitor baggage location in traditional airport baggage handling. Particularly in multi-flight parallel operation environments, it ensures timely processing of critical baggage (such as overweight or extra-large items), while improving palletizing stability and space utilization. It reduces handling delays and safety hazards caused by improper stacking, enhancing the intelligence level and overall operational efficiency of airport baggage handling and palletizing. Through continuous dynamic adjustment and feedback optimization, the system learns and adapts to specific airport operational needs, ultimately achieving adaptive improvement of the baggage handling process and providing strong technical support for airport management. Attached Figure Description

[0024] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:

[0025] Figure 1 This is a flowchart of an optional airport baggage handling method based on baggage sorting according to an embodiment of the present invention;

[0026] Figure 2 This is a schematic diagram of an optional airport baggage handling device based on baggage sorting according to an embodiment of the present invention;

[0027] Figure 3 This is a hardware structure block diagram of an electronic device (or mobile device) for an airport baggage handling method based on baggage sorting, according to an embodiment of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., used in this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] It should be noted that all related information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, and displayed data) collected and involved in this invention are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of this data comply with the relevant laws, regulations, and standards of the relevant regions, necessary confidentiality measures have been taken, and it does not violate public order and good morals. Corresponding operation entry points are provided for users to choose to authorize or refuse. For example, this system has an interface with relevant users or organizations. Before obtaining relevant information, a request to obtain the information needs to be sent to the aforementioned user or organization through the interface, and the relevant information is obtained only after receiving consent from the aforementioned user or organization.

[0031] This invention proposes an intelligent task priority ranking method for airport baggage handling and palletizing. By combining baggage multi-dimensional attributes, dynamic operation status, and palletizing targets, an adaptive priority scoring and scheduling mechanism is constructed to achieve optimal resource allocation and stable pallet formation.

[0032] This invention improves the utilization rate of robotic arms and conveying equipment through intelligent priority allocation, reducing waiting time and ineffective handling. It also ensures that overweight, bulky, or priority-loaded baggage is processed quickly. Furthermore, real-time priority adjustment makes the stacking process more aligned with the target stack shape, reducing the risk of collapse. With the introduction of a machine learning model, the sorting strategy can be continuously optimized based on operational experience, achieving self-learning and evolution. Therefore, it is not only applicable to airport baggage palletizing but can also be extended to warehousing logistics, container loading, and other scenarios.

[0033] The present invention will now be described in detail with reference to various embodiments.

[0034] Example 1

[0035] According to an embodiment of the present invention, an embodiment of an airport baggage handling method based on baggage sorting is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0036] Figure 1 This is a flowchart of an optional airport baggage handling method based on baggage sorting according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0037] Step S101: Obtain the current baggage data of the target airport and input the current baggage data into the preset learning model to obtain the initial weight set.

[0038] In this embodiment of the invention, sensors (such as 3D cameras, RFID (Radio Frequency Identification) readers, and weight sensors) installed at key nodes such as airport conveyor belts and sorting areas can acquire in real time the size, weight, target flight information, and special tags (fragile, expedited, oversized) of each piece of luggage. They can also acquire the type of conveyor used for luggage transport at the target airport (such as carousels, chutes, etc.) and the main flight types at the target airport (such as business and tourist flights). This data constitutes the current luggage data.

[0039] Then, by inputting this data into the preset learning model, the initial weights of each variable in the sorting and scoring function used to sort and score luggage can be obtained, thus obtaining the initial weight set.

[0040] In this embodiment of the invention, the learning model can operate based on a weighted strategy, that is, by setting the importance of each attribute through expert knowledge or preliminary experiments, an initial weight set is formed. For example, initially, the weights of factors such as size matching, weight distribution rationality, and palletizing adaptability are assumed to be 0.3, 0.4, and 0.2, respectively. This reflects the initial preferences and evaluation criteria for baggage handling, and then the weights are optimized through continuous iteration.

[0041] Step S102: Based on the initial weight set, a preset sorting score function is used to determine the sorting score of each piece of luggage currently on the transport vehicle, and a transport queue is generated based on the sorting score, wherein the transport vehicle is used to transport luggage.

[0042] In this embodiment of the invention, a comprehensive scoring function (i.e., a preset ranking scoring function) is constructed using an initial set of weights. The function considers multiple dimensions of the luggage, such as size, weight, and compatibility with the current stacking status, and obtains a ranking score for each piece of luggage through weighted summation. Then, based on the ranking scores, a priority-sorted list of luggage, i.e., a queue to be handled, is generated. Luggage at the top of the queue is handled and stacked first, ensuring efficient resource allocation and timely processing of critical luggage.

[0043] Here, "baggage to be moved" refers to baggage currently located on a conveyor, which can be a turntable, chute, or similar device.

[0044] Step S103: Based on the queue order of the luggage to be transported, each piece of luggage to be transported in the luggage to be transported is transported, and when the transport is completed, the current stacking data of the luggage rack is collected, wherein the current stacking data is used to characterize the stacking status of all the luggage that has been transported on the luggage rack.

[0045] In this embodiment of the invention, a robotic arm or other automated equipment can be used to process baggage one by one according to the order of the queue to be handled, and move it onto baggage racks, such as baggage carts, so that the baggage can be transported to a designated location (such as an aircraft check-in cabin). After a batch of baggage is handled, sensors (such as pressure sensors, cameras, etc.) on the baggage racks collect data on the stacking status of the stacked baggage, including layer distribution, void ratio, load distribution, etc. This current palletizing data is used to evaluate the effectiveness of the palletizing.

[0046] Step S104: Adjust each weight in the initial weight set based on the current palletizing data and the target palletizing data.

[0047] In this embodiment of the invention, the target palletizing data represents an ideal palletizing standard, typically encompassing high stability and high space utilization. Comparing it with the current palletizing data identifies deviations, guiding weight adjustments. Quantitative evaluation of the palletizing results identifies factors (such as weight distribution and size matching) that significantly impact palletizing stability or efficiency. Based on this, the weights of corresponding factors are dynamically adjusted to optimize the ranking and scoring function. For example, if palletizing instability is found to be primarily due to unreasonable weight distribution, the weight factor's weight may be increased to give it greater importance in future processing.

[0048] Step S105: Based on the adjusted weights, determine the sorting score of each piece of luggage currently on the transport vehicle, and move the luggage based on the sorting score until all luggage at the destination airport has been moved.

[0049] In this embodiment of the invention, the ranking and scoring function is updated based on the optimized weight set derived from the palletizing results. The adjusted weights are then reapplied to recalculate the ranking score for each piece of luggage currently on the transport vehicle, ensuring that each handling decision is based on the latest and most optimized information. This iterative process continues until all luggage has been properly handled, achieving the target palletizing effect.

[0050] In this embodiment of the invention, through continuous optimization and iteration, the baggage handling process can be continuously improved, ultimately achieving predetermined palletizing goals, including but not limited to efficient space utilization, ensuring palletizing stability, and prioritizing critical baggage. This not only enhances the intelligence level of airport operations but also improves customer satisfaction and the overall efficiency of airport operations.

[0051] In summary, by employing an intelligent learning model and dynamically analyzing real-time baggage data from the target airport, the system automatically identifies baggage handling sequences, achieving efficient resource allocation and optimized workflows. This solves the technical problems of inefficiency, rough handling, and the inability of management personnel to monitor baggage location in traditional airport baggage processing. Particularly in multi-flight parallel environments, it ensures timely processing of critical baggage (such as overweight or extra-large items), while improving palletizing stability and space utilization. It also reduces handling delays and safety hazards caused by improper stacking, enhancing the intelligence level and overall operational efficiency of airport baggage handling and palletizing. Through continuous dynamic adjustment and feedback optimization, the system learns and adapts to specific airport operational needs, ultimately achieving adaptive improvement in baggage handling processes and providing strong technical support for airport management.

[0052] To improve the accuracy of the preset learning model, in the airport baggage handling method based on baggage sorting provided in Embodiment 1 of this application, before inputting the current baggage data into the preset learning model to obtain the initial weight set, historical baggage data and historical palletizing data corresponding to each historical baggage data are collected. The historical baggage data includes at least: transport tool type, flight type, and baggage attribute data. The historical palletizing data is used to represent the expected palletizing, which is obtained by sorting score indicators and the weights corresponding to each sorting score indicator. The preset learning model is trained using the historical baggage data and the historical palletizing data to obtain the trained preset learning model. The trained preset learning model is used to output a set of weights, which are used to represent the importance of the sorting score indicators.

[0053] In this embodiment of the invention, historical baggage data processed by the airport over a past period can be collected first. This data covers at least the type of transport tool (such as carousels, chutes, etc.), flight type (international flights, domestic flights, business flights, etc.), and baggage attribute data (including but not limited to size, weight, destination flight information, and special baggage markings). Furthermore, based on the results of each palletizing operation, including but not limited to indicators such as space utilization, stacking stability, weight distribution rationality, and special baggage compliance, the optimal palletizing method can be determined as the expected palletizing method. Here, the expected palletizing method is the ideal palletizing state based on the palletizing strategy and target setting, reflecting the manager's expectations for palletizing quality and efficiency. It can be represented by ranking scoring indicators and the weights corresponding to each ranking scoring indicator. Ranking scoring indicators are standards used to quantitatively evaluate the effectiveness of baggage handling and palletizing, including baggage size matching, weight distribution rationality, urgency, and special constraints. Each indicator has a specific weight to reflect its importance in the overall score.

[0054] In this embodiment of the invention, the preset learning model is a model using the Reinforcement Learning (RL) algorithm (DQN (Deep Q-Network)). Collected historical baggage data and historical palletizing data are used as the training set to train the preset learning model. The training process employs machine learning methods, especially reinforcement learning or ranking learning techniques. By learning from past successful and failed cases, the model gradually learns how to assign reasonable weights to different ranking and scoring metrics to adapt to the ever-changing logistics environment of airports. Before the training phase, the model may have been initially configured based on expert experience or preliminary data, but through this training, the model can more accurately understand and reflect the needs of actual working scenarios.

[0055] In this embodiment of the invention, after training is completed, the preset learning model can output a set of optimized weights. These weights accurately represent the importance of each sorting and scoring indicator, and can guide subsequent intelligent baggage sorting and palletizing decisions, thereby achieving optimal resource allocation and work process optimization.

[0056] In this embodiment, by learning from historical data, the priority of baggage tasks can be adaptively adjusted, and palletizing strategies can be optimized. This results in higher operational efficiency, better palletizing stability, and better space utilization in the complex and ever-changing airport baggage handling and palletizing process. Through continuous feedback and model iteration, it can quickly adapt to new challenges, such as the addition of special baggage types or changes in flight scheduling, ensuring smooth and efficient airport baggage handling. This process not only reduces the error rate in baggage handling but also improves the safe transportation experience for passengers and cargo.

[0057] To improve the accuracy of determining the sorting score for each piece of baggage to be handled, the airport baggage handling method based on baggage sorting provided in Embodiment 1 of this application obtains baggage attribute data for each piece of baggage to be handled. The baggage attribute data includes at least: baggage size, baggage weight, and baggage shape. Based on an initial weight set, the weights in the initial sorting scoring function are adjusted to obtain a preset sorting scoring function. The preset sorting scoring function consists of multiple sorting scoring indicators, each with a corresponding weight. The sorting scoring indicators include at least one of the following: size indicator, weight indicator, spatial matching indicator, and palletizing strategy indicator. For each piece of baggage to be handled, the sorting score is determined using the preset sorting scoring function based on the baggage attribute data.

[0058] In this embodiment of the invention, baggage scheduling can be regarded as a sequential decision problem, including: State S: current stacking status and baggage attributes to be processed; Action A: select which baggage to process first; Reward R: after completing this stacking, issues such as stack stability, utilization rate, and completion rate of key baggage.

[0059] In this embodiment of the invention, each piece of luggage to be transported on the conveyor is identified to obtain information such as luggage dimensions (length, width, height), luggage weight (accurate to two decimal places), and luggage shape (regular or irregular). This information is acquired through RFID tags, barcode readers, 3D vision sensors, and other means to ensure the comprehensiveness and accuracy of the data.

[0060] In this embodiment of the invention, the initial weight set output by the learning model includes preliminary weight allocations for multiple dimensions such as size, weight, spatial matching, and palletizing strategy. These weights reflect the relative importance of different attributes in prioritizing baggage tasks. The weights in the initial ranking scoring function are adjusted to optimize the ranking scoring function, resulting in a preset ranking scoring function.

[0061] Here, the preset sorting and scoring function consists of multiple sorting and scoring indicators, each with a specific weight reflecting its relative importance in determining baggage priority. The combination of indicators and weights constitutes a scoring rule used to automatically assess the priority of each piece of baggage.

[0062] For example, the ranking scoring function is as follows:

[0063] ;

[0064] in, (i=1, 2, 3, 4) are dynamic weights. Represents the normalization function. Indicates size specifications, Indicates weight. Indicates spatial matching index, This indicates the palletizing strategy.

[0065] In this embodiment of the invention, for each piece of luggage to be moved, a ranking score is calculated based on its luggage attribute data using the aforementioned pre-constructed ranking and scoring function. This score comprehensively considers the luggage's size, weight, shape, and its matching degree with the current palletizing situation and strategy requirements, ensuring the intelligence and flexibility of luggage handling.

[0066] Here, the calculation of sorting scores is the core of intelligent baggage sorting, which directly determines the order in which baggage is handled and palletized, helping to improve the efficiency and stability of palletizing, while meeting the diverse needs of airport operations.

[0067] In this embodiment, efficient and intelligent sorting of baggage handling and palletizing tasks is achieved by dynamically adjusting weights and using a preset sorting and scoring function. This not only distinguishes the priority of different baggage items but also flexibly adjusts strategies based on real-time palletizing status and changes in airport logistics needs, ensuring optimal resource allocation and smooth workflow. By comprehensively considering multiple key indicators (such as size, weight, space matching, and palletizing strategy), it effectively avoids problems such as space waste, unstable stacking, and delays in handling critical baggage that may occur in the "first-come, first-served" method, significantly improving the intelligence, operational efficiency, and security of airport baggage handling.

[0068] To further accurately determine the sorting score of baggage to be handled, in the airport baggage handling method based on baggage sorting provided in Embodiment 1 of this application, a size index value is determined based on the baggage size included in the baggage attribute data; a weight index value is determined based on the baggage weight included in the baggage attribute data; a space matching index value is determined based on the baggage shape and the remaining space on the baggage handling equipment included in the baggage attribute data; a palletizing strategy index value is determined based on the type of the conveyor and the flight type included in the current baggage data; and a preset sorting score function is used to determine the sorting score of the baggage to be handled based on the size index value, weight index value, space matching index value, and palletizing strategy index value.

[0069] In this embodiment of the invention, the dimensions of each piece of baggage to be handled are measured, typically by reading pre-stored dimensional data using a 3D vision sensor or RFID tag. Then, a dimensional index value is calculated based on this dimensional information, reflecting the impact of baggage on space occupancy during palletizing. The weight of each piece of baggage is obtained through a built-in weighing device or RFID tag, and its weight index value is calculated. This index is used to assess the load impact of baggage on the robotic arm and baggage handling equipment during handling, as well as the potential risks to palletizing stability. Based on the baggage shape (regular or irregular) and the distribution of remaining space on the conveyor, the degree of matching between each piece of baggage and the current palletizing environment is assessed, resulting in a space matching index value. This ensures that baggage is placed rationally, without wasting space or reducing stability. Furthermore, by combining the type of conveyor (e.g., carousel) and flight type (e.g., business flight), the priority of specific baggage in a specific flight and palletizing environment can be assessed, resulting in a palletizing strategy index value. This ensures that baggage handling and palletizing strategies adapt to the specific requirements of different flights and the dynamic operational status of the airport.

[0070] In this embodiment of the invention, based on size index values, weight index values, spatial matching index values, and palletizing strategy index values, these values ​​are input into a preset sorting and scoring function to calculate a sorting score for each piece of luggage. This score comprehensively considers the attributes of the luggage and the strategic requirements of the current palletizing operation, providing a basis for subsequent handling priority ranking.

[0071] In this embodiment, baggage can be processed not only based on static rules, but also adaptively adjusted according to the baggage's real-time attributes (size, weight, shape) and dynamic operating conditions (remaining space, type of transport vehicle, flight type). The quantitative evaluation and ranking scoring of this series of indicators enables more accurate identification and processing of "critical baggage," while ensuring the stability of palletizing and space utilization.

[0072] To improve the accuracy of determining target palletizing data, in the airport baggage handling method based on baggage sorting provided in Embodiment 1 of this application, before adjusting each weight in the initial weight set based on the current palletizing data and the target palletizing data, if a previous palletizing state exists, a target palletizing model is constructed based on the previous palletizing state and a preset palletizing strategy. The previous palletizing state refers to the stacking state of the baggage handling equipment before each piece of baggage in the handling queue. If no previous palletizing state exists, a three-dimensional image of the baggage handling equipment is acquired. Based on the three-dimensional image, the current palletizing state is determined, and based on the current palletizing state and the preset palletizing strategy, a target palletizing model is constructed. Based on the target palletizing model, the target palletizing data is determined.

[0073] In this embodiment of the invention, existing palletizing conditions, including current level, remaining space, load distribution, stability coefficient, etc., can be collected or input in real time by a 3D camera. Then, combined with a preset palletizing strategy (such as heavy items on the bottom and light items on top, large items first, and regular shapes first), a target pallet model is established.

[0074] Specifically, when processing multiple batches of luggage consecutively, the next target palletizing model can be constructed based on the previous palletizing state and a preset palletizing strategy. Here, the previous palletizing state refers to the state of luggage already stacked on the luggage racks before starting to handle any luggage in the current queue, including hierarchical structure, load-bearing distribution, and stability coefficient. When starting for the first time or when the current handling task is an independent batch and there is no previous palletizing state as a reference, a 3D camera or scanning device can be used to acquire 3D images of the luggage racks to obtain an initial palletizing environment. Based on the acquired 3D images, image analysis techniques (such as deep learning and computer vision) are used to determine the current palletizing state, including the number, location, and stacking height of luggage already stacked, as well as the layout and available load-bearing capacity of the remaining space.

[0075] Whether based on the previous palletizing status or the current palletizing status, a target palletizing model can be constructed by combining preset palletizing strategies (such as the principle of heavy baggage at the bottom and light baggage at the top, the principle of prioritizing special baggage, and the principle of maximizing space utilization). This model provides an ideal reference framework for subsequent palletizing operations, guiding the robotic arm on how to select and place baggage to achieve the desired stacking effect, such as stability, compactness, and safety compliance. Then, based on the constructed target palletizing model, a set of target palletizing data is generated, including specific instructions such as the expected palletizing levels, baggage placement locations, and stacking order. This data will directly guide the handling robotic arm and auxiliary tools to complete the handling and palletizing of baggage.

[0076] In this embodiment, by constructing a target palletizing model, the system can quickly adapt to the current palletizing environment and generate optimized palletizing strategies, whether in a dynamic scenario of continuous baggage handling or a static scenario of initial startup. This enables precise scheduling and efficient execution of baggage handling tasks. This dynamic planning capability not only improves the stability and space utilization of palletizing but also reduces waiting time and ineffective operations during handling, effectively addressing the challenges of airport baggage management and ensuring smooth baggage handling processes and passenger satisfaction.

[0077] To improve the accuracy of adjusting each weight in the initial weight set, in the airport baggage handling method based on baggage sorting provided in Embodiment 1 of this application, the index value corresponding to each palletizing scoring indicator is determined based on the current palletizing data and the target palletizing data. The palletizing scoring indicators include at least one of the following: space utilization, stacking stability, weight distribution uniformity, baggage compliance, and operational efficiency. Based on the index values ​​corresponding to all palletizing scoring indicators, a preset palletizing scoring function is used to score the current palletizing state to obtain a palletizing score. If the palletizing score is less than a preset palletizing score threshold, each weight in the initial weight set is adjusted.

[0078] In this embodiment of the invention, after the actual stacking is completed, the generated stack type is modeled using sensors or digital twin technology. The actual stack type is compared with the target stack type, the difference value is calculated, and the difference is fed back to the priority scoring function for adaptive optimization. During implementation, the stack type score can be decomposed into multiple quantifiable sub-items to achieve linkage between the score and the priority model (feedback mechanism), including weight learning, RL reward design, and handling logic for hard and soft constraints (triggering alarms / rework). If the on-site conditions are met, the sensor combination and data flow (point cloud → voxel → center / quality → score) can be referenced. The final calculation proves the effect (e.g., StackScore > 80 is considered acceptable). The stacking score index includes 7 core dimensions:

[0079] (1) Stability (S_stab): resistance to overturning / slippage;

[0080] (2) Compactness / Space Utilization (S_comp): porosity and volume utilization;

[0081] (3) Load distribution uniformity (LoadBalance, S_load): the rationality of inter-story load distribution;

[0082] (4) Alignment and geometric regularity (S_align): inter-layer offset, angle, and perpendicularity;

[0083] (5) Accessibility / loading order compliance (S_acc): Whether the key baggage is in a pick-up location;

[0084] (6) Safety and regulatory compliance (Safety, S_safety): Overweight, non-compliance with fragile item labeling, etc.;

[0085] (7) Completeness / Target Matching Degree (TargetMatch, S_target): The degree of matching with the target stack type in terms of shape and pattern;

[0086] Here, the target stack modeling is a pre-defined "ideal stack type," such as: heavy at the bottom, light at the top, and with a void ratio of less than 5%. Actual stack modeling: the actual stacking structure is obtained through sensor or digital twin modeling.

[0087] Then, based on the differences, adjust the weights in the ranking scoring function. For example, if the heap is frequently unstable, increase the weight; if there are too many gaps, increase the weight. The weights are adjusted accordingly. This achieves adaptive optimization, meaning the ranking and scoring function is not fixed.

[0088] Specifically, space utilization is calculated by comparing the actual space occupied in the current palletizing data with the total capacity of baggage equipment. High space utilization means more compact palletizing and efficient use of space. Using physical models and sensor data, the center of gravity distribution and structural stability of the palletizing are evaluated to determine the stacking stability index. Improved stability directly affects the safety of palletizing and the convenience of subsequent processing. The weight distribution of each layer or area in the current palletizing data is analyzed to calculate the weight distribution uniformity index. Uniform weight distribution helps improve the overall load-bearing capacity and stability of the palletizing. Based on preset baggage stacking rules (such as specific location requirements for overweight or fragile items), the baggage stacking is evaluated to determine compliance, thus determining the baggage compliance index. Compliance ensures the safety and rationality of baggage handling. Operational efficiency is quantified by comparing actual operation time with the theoretical minimum time, or the number of pauses in the operation process. High efficiency means faster processing speed and reduced passenger waiting time.

[0089] Then, the index values ​​corresponding to all the palletizing scoring indicators calculated above are input into a preset palletizing scoring function to obtain a comprehensive palletizing score. The scoring function is usually a weighted summation formula, where each index value is multiplied by a preset weight and then summed. For example, the palletizing scoring function is as follows:

[0090] ;

[0091] Where α, β, γ, δ, and ε are weighting coefficients; space utilization S is the actual total volume of stacked luggage / available stacking volume; stacking stability T is calculated based on the centroid offset rate and bottom load balance; weight distribution rationality W is the proportion of heavy items placed on the lower layer; special luggage compliance P refers to the correct placement of fragile / urgent / oversized luggage; and operational efficiency E is the ratio of the time taken to complete the stack to the theoretical optimal time.

[0092] When the calculated palletizing score is lower than the preset palletizing score threshold, it indicates that the current palletizing status has failed to achieve the expected optimization goal, and the strategy needs to be adjusted. The threshold is set based on historical data analysis and expert experience, representing the minimum acceptable palletizing quality standard. In cases where the score is not met, each weight in the initial weight set is fine-tuned. Adjustment strategies may include: increasing the weight of indicators with low scores (such as stability or efficiency), or decreasing the weight of indicators with high scores.

[0093] For example, in the automated baggage sorting and loading process at an airport, each batch of baggage is palletized. After palletizing is completed, the actual stack pattern needs to be evaluated to determine whether the stacking meets the preset target stacking standards and to provide feedback for subsequent task priority adjustments.

[0094] The following parameters can be selected for palletizing scoring:

[0095] Space utilization rate S: Actual total volume of stacked luggage / available stacking volume;

[0096] Stack stability T: calculated based on centroid offset rate and bottom load balance;

[0097] Weight distribution rationality W: the proportion of heavy objects placed on the lower layer;

[0098] Special baggage compliance (P): such as the proper placement of fragile / express / oversized baggage;

[0099] Operational efficiency E: The ratio of the time taken to complete the stack to the theoretically optimal time.

[0100] The scoring function is as follows:

[0101] ;

[0102] Where α, β, γ, δ, and ε are weighting coefficients.

[0103] The specific steps are as follows:

[0104] Step 1: After palletizing is completed, the 3D sensor and digital twin model are used to obtain the actual pallet type data;

[0105] Step 2: Calculate the values ​​of the five parameters above and normalize them to the [0,1] interval;

[0106] Step 3: Substitute into the scoring function to obtain the overall score value of the stack type;

[0107] Step 4: Compare the score with the target threshold. If it is lower than the threshold, trigger optimization feedback and adjust the weight parameters in the priority function of subsequent tasks.

[0108] When applied in airport testing, the scoring function can significantly distinguish between "efficient and stable stacking" and "stacks with serious space waste or unstable stacking". In 100 batches of test data, space utilization was improved by about 12%, and the risk of stacking collapse was reduced by about 18%, achieving adaptive optimization of the system.

[0109] In this embodiment, an adaptive and optimized palletizing supervision mechanism is achieved by quantifying and evaluating palletizing scoring indicators, comprehensively calculating palletizing scores, and adjusting the weights in the governance strategy when the scores are not up to standard. This mechanism can ensure that palletizing operations remain efficient, safe, and compliant even in changing operating environments.

[0110] To further adjust each weight in the initial weight set, in the airport baggage handling method based on baggage sorting provided in Embodiment 1 of this application, the index value corresponding to each palletizing score index is normalized to obtain a target index value; the sorting score index corresponding to each palletizing score index is determined; when the target index value corresponding to the target palletizing score index is minimized, the sorting score index corresponding to the target palletizing score index is determined as the target sorting score index; and the weights corresponding to the target sorting score index are adjusted.

[0111] In this embodiment of the invention, the index values ​​corresponding to each palletizing scoring indicator are normalized to ensure that all scoring indicators are compared on the same scale, eliminating the influence of dimensions. The normalized values ​​are target index values, which will be between 0 and 1, intuitively reflecting the relative importance and current state of each indicator. Then, the ranking scoring indicator corresponding to each palletizing scoring indicator is determined. For example, the space utilization rate in the palletizing scoring indicator corresponds to the space matching indicator in the ranking scoring indicator, so that when the index value of the palletizing scoring indicator is unreasonable, the weight of the corresponding ranking scoring indicator can be adjusted. When the target index value corresponding to the target palletizing scoring indicator reaches its minimum (i.e., the indicator performance is the worst), the ranking scoring indicator corresponding to that indicator is determined as the target ranking scoring indicator. This indicates that the current palletizing status has obvious defects in this indicator and needs to be given priority. For the target ranking scoring indicator, its corresponding weight is adjusted to improve the influence of this indicator in the comprehensive scoring calculation. Weight adjustment can be performed through machine learning models (such as reinforcement learning) or manually fine-tuned according to expert rules.

[0112] In this embodiment, adaptive optimization of the palletizing strategy can be achieved through dynamic index value normalization, determination of ranking and scoring indicators, and targeted weight adjustment. Specifically, when the performance of a certain palletizing scoring indicator is abnormal, it can be automatically identified and used as a focus for optimization. By adjusting the weight, it can be ensured that the indicator is significantly improved in subsequent baggage handling and palletizing processes. This mechanism not only improves palletizing quality but also ensures that the palletizing strategy can flexibly adapt to the real-time needs and special challenges of airport logistics, such as handling large baggage, optimizing loading order, or improving palletizing efficiency.

[0113] The following describes in detail another optional implementation method.

[0114] In this embodiment of the invention, a digital twin-based intelligent task priority ranking simulation control system for airport baggage handling is proposed, comprising:

[0115] Data acquisition layer: conveyor belt, palletizing robotic arm, sensor / vision system, to record luggage attributes and stacking results in real time;

[0116] Feature processing layer: Normalizes the data and extracts features (such as volume / weight ratio, whether it fits the remaining space);

[0117] Model training layer: Train supervised learning models or RL models offline using historical data;

[0118] Decision execution layer: At runtime, it calls the model results to generate a baggage priority queue and schedules the execution.

[0119] Feedback optimization layer: Feedback is provided on the difference between the actual stacking effect and the model prediction to continuously iterate and optimize the model.

[0120] The intelligent task prioritization process for airport baggage handling is as follows:

[0121] (1) Baggage task feature collection: The basic attributes of each piece of baggage are obtained through sensors, weighing devices and baggage barcode system, including size, weight, target flight information and special labels.

[0122] (2) Initial calculation of task priority: Construct a priority comprehensive scoring function, using luggage size matching degree, weight distribution rationality, urgency, special constraints, etc. as input features, and use weighted calculation or machine learning model to obtain the initial priority score.

[0123] (3) Baggage scheduling and palletizing: The system allocates and schedules baggage according to priority, drives the robotic arm to complete the stacking, and models the real-time stacking pattern during the process.

[0124] (4) Stack type scoring after stacking: After stacking is completed, the system calls the stack type scoring module to quantitatively evaluate the overall stacking result. The evaluation indicators include, but are not limited to: space utilization, stacking stability (center of gravity shift, load balance), weight distribution rationality, compliance of special luggage, and operation efficiency. The above indicators are normalized and input into the comprehensive scoring function to obtain the final stack type score value.

[0125] (5) Feedback optimization: The system dynamically adjusts the weight parameters in the priority scoring function based on the difference between the stacking type score and the preset threshold. For example, when the stacking stability score is too low, the weight factor weight is increased; when the space utilization is insufficient, the size matching factor weight is increased, thereby gradually optimizing in subsequent tasks.

[0126] In this embodiment of the invention, an intelligent learning model is employed to automatically identify baggage handling order by collecting and dynamically analyzing baggage data from the target airport in real time. This achieves efficient resource allocation and optimized workflow, thereby solving the technical problems of low efficiency, rough handling, and the inability of management personnel to monitor baggage location in traditional airport baggage handling. Especially in multi-flight parallel operation environments, it ensures timely processing of critical baggage (such as overweight or special-sized items), while improving palletizing stability and space utilization, reducing handling delays and safety hazards caused by improper stacking, and enhancing the intelligence level and overall operational efficiency of airport baggage handling and palletizing. Through continuous dynamic adjustment and feedback optimization, the system learns and adapts to the specific operational needs of the airport, ultimately achieving adaptive improvement of the baggage handling process and providing strong technical support for airport management.

[0127] The following is a detailed description with reference to another embodiment.

[0128] Example 2

[0129] The airport baggage handling device based on baggage sorting provided in this embodiment includes multiple implementation units, each of which corresponds to a specific implementation step in Embodiment 1 above.

[0130] Figure 2 This is a schematic diagram of an optional airport baggage handling device based on baggage sorting according to an embodiment of the present invention, such as... Figure 2 As shown, the airport baggage handling device may include: an acquisition unit 20, a first determination unit 21, a handling unit 22, an adjustment unit 23, and a second determination unit 24.

[0131] Among them, the acquisition unit 20 is used to acquire the current baggage data of the target airport and input the current baggage data into the preset learning model to obtain the initial weight set;

[0132] The first determining unit 21 is used to determine the sorting score of each piece of luggage currently located on the conveyor based on the initial weight set and a preset sorting score function, and to generate a queue of luggage to be transported based on the sorting score, wherein the conveyor is used to transport luggage.

[0133] The handling unit 22 is used to handle each piece of luggage to be handled in the queue based on the queue order of the queue to be handled, and to collect the current stacking data of the luggage equipment when the handling is completed. The current stacking data is used to characterize the stacking status of all the luggage that has been handled on the luggage equipment.

[0134] Adjustment unit 23 is used to adjust each weight in the initial weight set based on the current palletizing data and the target palletizing data;

[0135] The second determining unit 24 is used to determine the sorting score of each piece of baggage currently located on the transport vehicle based on the adjusted weights, and to move the baggage based on the sorting score until all baggage to be moved at the target airport has been moved.

[0136] The aforementioned airport baggage handling system employs an intelligent learning model to automatically identify baggage handling sequences by collecting and dynamically analyzing real-time baggage data from the target airport. This enables efficient resource allocation and optimized workflows, resolving the technical problems of inefficiency, rough handling, and the inability of management personnel to monitor baggage location in traditional airport baggage handling. Particularly in multi-flight parallel environments, it ensures timely processing of critical baggage (such as overweight or extra-large items), while improving palletizing stability and space utilization. It reduces handling delays and safety hazards caused by improper stacking, enhancing the intelligence level and overall operational efficiency of airport baggage handling and palletizing. Through continuous dynamic adjustment and feedback optimization, the system learns and adapts to specific airport operational needs, ultimately achieving adaptive improvement of the baggage handling process and providing strong technical support for airport management.

[0137] Optionally, the airport baggage handling device further includes: a first acquisition module, used to acquire historical baggage data and historical palletizing data corresponding to each historical baggage data, before inputting the current baggage data into the preset learning model to obtain an initial weight set; wherein the historical baggage data includes at least: transport tool type, flight type, and baggage attribute data, and the historical palletizing data is used to represent the expected palletizing, which is obtained by ranking scoring indicators and weights corresponding to each ranking scoring indicator; and a first training module, used to train the preset learning model using the historical baggage data and historical palletizing data to obtain the trained preset learning model, wherein the trained preset learning model is used to output a set of weights, which are used to represent the importance of the ranking scoring indicators.

[0138] Optionally, the first determining unit includes: a first acquiring module, used to acquire luggage attribute data for each piece of luggage to be moved, wherein the luggage attribute data includes at least: luggage size, luggage weight, and luggage shape; a first adjusting module, used to adjust the weights in the initial ranking scoring function based on the initial weight set to obtain a preset ranking scoring function, wherein the preset ranking scoring function consists of multiple ranking scoring indicators, each ranking scoring indicator having a corresponding weight, and the ranking scoring indicators include at least one of the following: size indicator, weight indicator, spatial matching indicator, and palletizing strategy indicator; and a first determining module, used to determine the ranking score of each piece of luggage to be moved based on the luggage attribute data of the luggage to be moved using the preset ranking scoring function.

[0139] Optionally, the first determining module includes: a first determining submodule, used to determine a size index value based on the baggage size contained in the baggage attribute data; a second determining submodule, used to determine a weight index value based on the baggage weight contained in the baggage attribute data; a third determining submodule, used to determine a space matching index value based on the baggage shape and the remaining space on the baggage equipment contained in the baggage attribute data; a fourth determining submodule, used to determine a palletizing strategy index value based on the type of the conveying tool and the flight type contained in the current baggage data; and a fifth determining submodule, used to determine the sorting score of the baggage to be handled using a preset sorting and scoring function based on the size index value, weight index value, space matching index value, and palletizing strategy index value.

[0140] Optionally, the airport baggage handling device further includes: a first construction module, used to construct a target palletizing model based on the previous palletizing state and a preset palletizing strategy, before adjusting each weight in the initial weight set based on the current palletizing data and the target palletizing data, provided that a previous palletizing state exists. The previous palletizing state refers to the stacking state of the baggage handling equipment before each piece of baggage in the handling queue. A second acquisition module is used to acquire a three-dimensional image of the baggage handling equipment when a previous palletizing state does not exist. A second determination module is used to determine the current palletizing state based on the three-dimensional image and to construct the target palletizing model based on the current palletizing state and the preset palletizing strategy. A third determination module is used to determine the target palletizing data based on the target palletizing model.

[0141] Optionally, the adjustment unit includes: a fourth determining module, used to determine the index value corresponding to each palletizing scoring indicator based on the current palletizing data and the target palletizing data, wherein the palletizing scoring indicators include at least one of the following: space utilization, stacking stability, weight distribution uniformity, baggage compliance, and operational efficiency; a first scoring module, used to score the current palletizing state based on the index values ​​corresponding to all palletizing scoring indicators and using a preset palletizing scoring function to obtain a palletizing score; and a second adjustment module, used to adjust each weight in the initial weight set when the palletizing score is less than a preset palletizing score threshold.

[0142] Optionally, the second adjustment module includes: normalizing the index value corresponding to each palletizing score index to obtain a target index value; determining the ranking score index corresponding to each palletizing score index; determining the ranking score index corresponding to the target palletizing score index as the target ranking score index when the target index value corresponding to the target palletizing score index is the smallest; and adjusting the weight corresponding to the target ranking score index.

[0143] The aforementioned airport baggage handling device may also include a processor and a memory. The aforementioned acquisition unit 20, first determination unit 21, handling unit 22, adjustment unit 23, second determination unit 24, etc., are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0144] The aforementioned processor contains a kernel that retrieves the corresponding program units from memory. One or more kernels can be configured. By adjusting kernel parameters, a ranking score is determined for each piece of baggage currently on the transport vehicle based on the adjusted weights. Baggage is then moved based on its ranking score until all baggage at the destination airport has been moved.

[0145] The aforementioned memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0146] This invention also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program with the following steps: acquiring current baggage data of the target airport, inputting the current baggage data into a preset learning model to obtain an initial weight set, determining the ranking score of each piece of baggage currently on the transport vehicle based on the initial weight set using a preset ranking and scoring function, generating a transport queue based on the ranking score, transporting each piece of baggage in the transport queue based on the queue order, and collecting the current palletizing data of the baggage handling equipment after transport is completed, adjusting each weight in the initial weight set based on the current palletizing data and the target palletizing data, determining the ranking score of each piece of baggage currently on the transport vehicle based on the adjusted weights, and transporting the baggage based on the ranking score until all baggage at the target airport has been transported.

[0147] According to another aspect of the present invention, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the airport baggage handling method based on baggage sorting described above.

[0148] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the above-described airport baggage handling method based on baggage sorting.

[0149] Figure 3 This is a hardware structure block diagram of an electronic device (or mobile device) for an airport baggage handling method based on baggage sorting, according to an embodiment of the present invention. Figure 3 As shown, an electronic device may include one or more processors (e.g., Figure 3 The processors 302a, 302b, ..., 302n, etc., may include, but are not limited to, processing devices such as microprocessors (MCUs) or programmable logic devices (FPGAs), and a memory 304 for storing data. In addition, it may include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports in the I / O interface), a network interface, a keyboard, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 3 The structure shown is for illustrative purposes only and does not limit the structure of the electronic device described above. For example, the electronic device may also include... Figure 3 The more or fewer components shown, or having the same Figure 3 The different configurations shown.

[0150] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0151] The embodiments or examples disclosed herein are not exhaustive, but merely illustrative of some embodiments or examples, and are not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment or example can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment or example can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment or example can be arbitrarily interchanged. Furthermore, optional methods or examples in a particular embodiment or example can be arbitrarily combined; moreover, embodiments or examples can be arbitrarily combined. For example, some or all steps of different embodiments or examples can be arbitrarily combined, and a particular embodiment or example can be arbitrarily combined with optional methods or examples of other embodiments or examples.

[0152] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0153] In the several embodiments provided by this invention, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection can be through some interfaces; the indirect coupling or communication connection of units or modules can be electrical or other forms.

[0154] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0155] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0156] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0157] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. An airport baggage handling method based on baggage sorting, characterized in that, include: Obtain the current baggage data of the target airport and input the current baggage data into a preset learning model to obtain an initial weight set; Based on the initial weight set, a preset sorting and scoring function is used to determine the sorting score of each piece of luggage currently on the transport vehicle, and a transport queue is generated based on the sorting score, wherein the transport vehicle is used to transport luggage; Based on the queue order of the waiting queue, each piece of luggage in the waiting queue is moved, and when the moving is completed, the current stacking data of the luggage equipment is collected, wherein the current stacking data is used to characterize the stacking status of all the luggage that has been moved on the luggage equipment; Based on the current palletizing data and the target palletizing data, each weight in the initial weight set is adjusted. Specifically, based on the current palletizing data and the target palletizing data, a value corresponding to each palletizing scoring indicator is determined. The palletizing scoring indicators include at least one of the following: space utilization, stacking stability, weight distribution uniformity, baggage compliance, and operational efficiency. Based on the value of each of the palletizing scoring indicators, a preset palletizing scoring function is used to score the current palletizing status, resulting in a palletizing score. If the palletizing score is less than a preset palletizing score threshold, each weight in the initial weight set is adjusted. Based on the adjusted weights, a sorting score is determined for each piece of baggage currently on the transport vehicle, and the baggage is moved based on the sorting score until all baggage at the destination airport has been moved. Before adjusting each weight in the initial weight set based on the current palletizing data and the target palletizing data, the method further includes: if a previous palletizing state exists, constructing a target palletizing model based on the previous palletizing state and a preset palletizing strategy, wherein the previous palletizing state refers to the stacking state of the luggage equipment before handling each piece of luggage in the queue to be handled; if the previous palletizing state does not exist, acquiring a three-dimensional image of the luggage equipment; determining the current palletizing state based on the three-dimensional image, and constructing the target palletizing model based on the current palletizing state and the preset palletizing strategy; determining the target palletizing data based on the target palletizing model; wherein the target palletizing data includes the expected palletizing level, luggage placement position, and stacking order, used to guide the handling robotic arm and auxiliary tools to complete the handling and palletizing of luggage.

2. The airport baggage handling method according to claim 1, characterized in that, Before inputting the current luggage data into the preset learning model to obtain the initial weight set, the process also includes: Collect historical baggage data and historical palletizing data corresponding to each piece of historical baggage data, wherein the historical baggage data includes at least: transportation tool type, flight type, and baggage attribute data, and the historical palletizing data is used to characterize the expected palletizing, which is obtained by ranking scoring indicators and weights corresponding to each ranking scoring indicator; The preset learning model is trained using the historical baggage data and the historical palletizing data to obtain the trained preset learning model. The trained preset learning model is used to output a set of weights, which are used to characterize the importance of the ranking and scoring indicators.

3. The airport baggage handling method according to claim 1, characterized in that, Based on the initial weight set, the step of determining the ranking score of each piece of luggage currently on the transport vehicle using a preset ranking and scoring function includes: Obtain luggage attribute data for each of the luggage items to be moved, wherein the luggage attribute data includes at least: luggage size, luggage weight, and luggage shape; Based on the initial weight set, the weights in the initial sorting and scoring function are adjusted to obtain the preset sorting and scoring function. The preset sorting and scoring function consists of multiple sorting and scoring indicators, each of which corresponds to a weight. The sorting and scoring indicators include at least one of the following: size indicator, weight indicator, space matching indicator, and palletizing strategy indicator. For each piece of luggage to be moved, the sorting score of the luggage is determined using the preset sorting and scoring function based on the luggage attribute data of the luggage to be moved.

4. The airport baggage handling method according to claim 3, characterized in that, The step of determining the ranking score of the luggage to be moved based on the luggage attribute data and using the preset ranking scoring function includes: Based on the luggage dimensions included in the luggage attribute data, determine the size index value; Based on the luggage weight included in the luggage attribute data, a weight index value is determined; Based on the luggage attribute data, including the luggage shape and the remaining space on the luggage equipment, a space matching index value is determined; Based on the type of the delivery tool and the flight type included in the current baggage data, determine the palletizing strategy index value; Based on the size index value, the weight index value, the space matching index value, and the palletizing strategy index value, the sorting score of the luggage to be moved is determined using the preset sorting scoring function.

5. The airport baggage handling method according to claim 1, characterized in that, When the palletizing score is less than a preset palletizing score threshold, the step of adjusting each weight in the initial weight set includes: The index values ​​corresponding to each of the palletizing scoring indicators are normalized to obtain the target index value; Determine the ranking score index corresponding to each of the palletizing score indices; When the target index value corresponding to the target palletizing score index is minimized, the ranking score index corresponding to the target palletizing score index is determined as the target ranking score index. The weights corresponding to the target ranking and scoring indicators are adjusted.

6. An airport baggage handling device based on baggage sorting, characterized in that, include: The acquisition unit is used to acquire the current baggage data of the target airport and input the current baggage data into a preset learning model to obtain an initial weight set; The first determining unit is used to determine the sorting score of each piece of luggage currently located on the transport vehicle based on the initial weight set and using a preset sorting score function, and to generate a queue of luggage to be transported based on the sorting score, wherein the transport vehicle is used to transport luggage; The handling unit is used to handle each piece of luggage in the queue to be handled based on the queue order of the queue to be handled, and to collect the current stacking data of the luggage equipment when the handling is completed, wherein the current stacking data is used to characterize the stacking status of all the luggage that has been handled on the luggage equipment; An adjustment unit is configured to adjust each weight in the initial weight set based on the current palletizing data and the target palletizing data. Specifically, based on the current palletizing data and the target palletizing data, an index value corresponding to each palletizing scoring indicator is determined. The palletizing scoring indicators include at least one of the following: space utilization, stacking stability, weight distribution uniformity, baggage compliance, and operational efficiency. Based on the index values ​​corresponding to all the palletizing scoring indicators, a preset palletizing scoring function is used to score the current palletizing state, resulting in a palletizing score. If the palletizing score is less than a preset palletizing score threshold, each weight in the initial weight set is adjusted. The second determining unit is configured to determine the sorting score of each piece of baggage currently located on the transport vehicle based on the adjusted weights, and to move the baggage based on the sorting score until all the baggage to be moved at the target airport has been moved; The airport baggage handling device further includes: a first construction module, used to construct a target palletizing model based on the previous palletizing state and a preset palletizing strategy, before adjusting each weight in the initial weight set based on the current palletizing data and the target palletizing data, where the previous palletizing state refers to the stacking state of the baggage handling equipment before each piece of baggage to be handled in the handling queue; a second acquisition module, used to acquire three-dimensional images of the baggage handling equipment when the previous palletizing state does not exist; a second determination module, used to determine the current palletizing state based on the three-dimensional images, and construct the target palletizing model based on the current palletizing state and the preset palletizing strategy; and a third determination module, used to determine the target palletizing data based on the target palletizing model; wherein the target palletizing data includes the expected palletizing level, baggage placement position, and stacking order, used to guide the handling robotic arm and auxiliary tools to complete the handling and palletizing of baggage.

7. A computer program product, characterized in that, The method includes a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the airport baggage handling method based on baggage sorting as described in any one of claims 1 to 5.

8. An electronic device, characterized in that, It includes one or more processors and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the airport baggage handling method based on baggage sorting as described in any one of claims 1 to 5.

Images