Consigned luggage measurement and identification method and system, electronic equipment and storage medium

Abstract

The invention discloses a consigned luggage measurement and identification method and system, electronic equipment and a storage medium, and relates to the technical field of intelligent logistics. The method comprises the steps that multi-dimensional data of current luggage on a luggage conveying belt are collected, the multi-dimensional data are preprocessed and fused, luggage parameters of the current luggage are obtained, and the luggage parameters comprise size information, weight information and luggage structure characteristics; determining the type of the current luggage based on the luggage parameters; determining the processing priority of the current luggage based on the flight information corresponding to the current luggage and the luggage parameters; and determining the processing flow of the current luggage based on the processing priority and the real-time load of the luggage processing system. By implementing the technical scheme provided by the invention, the efficiency and safety of the luggage processing flow can be improved.

Description

Technical Field

[0001] This application relates to the field of intelligent logistics technology, and particularly to a method, system, electronic device and storage medium for measuring and identifying checked luggage. Background Art

[0002] With the rapid development of the aviation industry, the number of global air passengers has been increasing annually, and airport baggage handling systems are facing huge processing pressures. Baggage handling is an important part of airport operations and has a crucial impact on the travel experience of passengers and aviation safety. In large international airports, the number of checked luggage handled daily can reach more than 100,000 pieces. How to efficiently and accurately handle these pieces of luggage has become a key challenge for airport management.

[0003] Existing baggage handling technologies mainly rely on barcodes or radio frequency identification (RFID) tags to track and identify luggage. When passengers check in their luggage, airline staff attach tags to the luggage, and then the luggage is transported to the sorting area, security check area and loading area through an automated conveyor system. Currently, most airports use a fixed-path baggage conveyor system, and the luggage passes through each processing link in a preset process sequence. Due to the complexity and diversity of luggage, traditional methods cannot achieve highly personalized baggage handling, resulting in relatively low efficiency and safety in the overall baggage handling process. Summary of the Invention

[0004] This application provides a method, system, electronic device and storage medium for measuring and identifying checked luggage, which can improve the efficiency and safety of the baggage handling process.

[0005] In a first aspect, this application provides a method for measuring and identifying checked luggage, the method comprising: Collecting multi-dimensional data of the current luggage on the baggage conveyor belt, and preprocessing and fusing the multi-dimensional data to obtain luggage parameters of the current luggage, the luggage parameters including size information, weight information and luggage structure characteristics; Determining the category of the current luggage based on the luggage parameters; Determining the processing priority of the current luggage based on the flight information corresponding to the current luggage and the luggage parameters; Determining the processing process of the current luggage based on the processing priority and the real-time load of the baggage handling system.

[0006] By adopting the above technical solution, by collecting multi-dimensional data of the current luggage on the baggage conveyor belt, preprocessing and fusing these data, comprehensive baggage parameters including size information, weight information and structural features are obtained, realizing the accurate perception of the physical characteristics of the luggage. Then, based on these baggage parameters, the specific category of the current luggage is intelligently determined, enabling the system to identify different types of luggage and perform targeted processing. Next, the processing priority is determined by combining the flight information corresponding to the current luggage and the baggage parameters, which can distinguish between the luggage that needs to be processed urgently and ordinary luggage, effectively avoiding the unified and fixed processing method in the traditional system. Finally, according to the determined processing priority and the real-time load condition of the baggage handling system, an optimal processing flow for the current luggage is customized, including the appropriate transfer area, transfer time and security inspection level, realizing the dynamic optimization of baggage handling. This method of comprehensive perception, intelligent classification and dynamic processing significantly improves the accuracy, efficiency and security of baggage handling.

[0007] In the second aspect of the present application, a checked baggage measurement and identification system is provided. The system includes: A baggage parameter acquisition module, configured to collect multi-dimensional data of the current luggage on the baggage conveyor belt, preprocess and fuse the multi-dimensional data to obtain the baggage parameters of the current luggage, where the baggage parameters include size information, weight information and baggage structural features; A baggage category determination module, configured to determine the category of the current luggage based on the baggage parameters; A priority determination module, configured to determine the processing priority of the current luggage based on the flight information corresponding to the current luggage and the baggage parameters; A processing flow determination module, configured to determine the processing flow of the current luggage based on the processing priority and the real-time load of the baggage handling system, where the processing flow includes a transfer area, a transfer time and a security inspection level.

[0008] In the third aspect of the present application, a computer storage medium is provided. The computer storage medium stores multiple instructions, and the instructions are suitable for being loaded and executed by a processor to perform the above method steps.

[0009] In the fourth aspect of the present application, an electronic device is provided, including: a processor and a memory; wherein, the memory stores a computer program, and the computer program is suitable for being loaded and executed by the processor to perform the above method steps.

[0010] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: This application collects multi-dimensional data of the current luggage on the baggage conveyor belt, preprocesses and fuses this data to obtain comprehensive luggage parameters including size information, weight information, and structural features, achieving accurate perception of the physical characteristics of the luggage. Then, based on these luggage parameters, it intelligently determines the specific category of the current luggage, enabling the system to identify different types of luggage and perform targeted processing. Next, it determines the processing priority by combining the flight information corresponding to the current luggage and the luggage parameters, being able to distinguish between luggage that urgently needs to be processed and ordinary luggage, effectively avoiding the unified and fixed processing method in the traditional system. Finally, according to the determined processing priority and the real-time load status of the baggage handling system, it customizes the optimal processing flow for the current luggage, including the appropriate transfer area, transfer time, and security inspection level, realizing the dynamic optimization of baggage handling. This method of comprehensive perception, intelligent classification, and dynamic processing significantly improves the accuracy, efficiency, and security of baggage handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is a schematic flowchart of a method for measuring and identifying checked luggage provided by an embodiment of the present application; Figure 2 is a schematic block diagram of a system for measuring and identifying checked luggage provided by an embodiment of the present application; Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0012] Description of the reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] In order to enable those skilled in the art to better understand the technical solutions in this specification, the following will clearly and completely describe the technical solutions in the embodiments of this specification in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0014] In the description of the embodiments of the present application, words such as "for example" or "for illustration" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, using words such as "for example" or "for illustration" aims to present relevant concepts in a specific manner.

[0015] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly indicating the technical features indicated. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0016] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0017] Please refer to Figure 1 , and a flowchart of a method for measuring and identifying checked luggage is specifically proposed. This method can be implemented depending on a computer program, can be implemented depending on a single-chip microcomputer, or can run on a checked luggage measurement and identification system. This computer program can be integrated in a computer device or can run as an independent tool-type application. Specifically, this method includes steps 10 to 40, and the above steps are as follows: Step 10: Collect multi-dimensional data of the current luggage on the luggage conveyor belt, and preprocess and fuse the multi-dimensional data to obtain the luggage parameters of the current luggage. The luggage parameters include size information, weight information, and luggage structure characteristics.

[0018] In the embodiments of the present application, the current luggage refers to a specific luggage item being processed and identified on the luggage conveyor belt, which is the checked luggage that the system currently needs to measure, classify, and determine the processing flow.

[0019] In the embodiments of the present application, the multi-dimensional data refers to the comprehensive information of the luggage collected by various different types of sensing devices, including but not limited to size information, weight information, and luggage structure characteristics.

[0020] Specifically, multi-view two-dimensional images of the luggage are obtained through multiple cameras located at different positions. A structured light scanner projects a coded light pattern and captures the reflected image to generate three-dimensional depth data. At the same time, the pressure distribution and weight data of the luggage are obtained through a pressure sensor array and a weight sensor under the conveyor belt, and an infrared thermal imager is used to collect the thermal radiation distribution image of the luggage. The system preprocesses these multi-dimensional data, including image background separation and edge extraction to obtain contour information, constructs a three-dimensional model of the luggage based on the contour information and depth data, calculates the weight characteristics of the luggage in combination with the pressure and weight data, and analyzes the material and internal structure of the luggage through the thermal radiation image. Finally, the system fuses all the processing results to form complete luggage parameters including size information, weight information, and structural features, providing a comprehensive and accurate data basis for subsequent luggage classification and optimization of the processing process, and overcoming the problem of insufficient recognition of luggage characteristics caused by traditional single-dimensional data acquisition.

[0021] Based on the above embodiments, as an alternative embodiment, the step of collecting multi-dimensional data of the current luggage on the luggage conveyor belt may further include the following steps: Step 1011: Obtain multi-view two-dimensional image data of the current luggage collected by multiple cameras set at different heights and angles in a preset area of the luggage conveyor belt.

[0022] Specifically, multiple high-definition cameras are set in a preset area after the entrance of the luggage conveyor belt. These cameras are arranged at different heights and angles: the top camera is installed about 2 meters above the conveyor belt and points vertically downward, the left and right cameras are installed about 1 meter above the two sides of the conveyor belt and horizontally face the center of the conveyor belt, and the front and rear cameras are installed about 1.2 meters above the front and rear ends of the conveyor belt and face the preset area at an angle of 45°. When the current luggage passes through the preset area, these cameras are triggered synchronously, and the image acquisition control module synchronously acquires two-dimensional images of multiple angles such as the top view, left and right side views, and front and rear views of the luggage. The system transmits these images to the data processing unit through the image transmission module to form multi-view two-dimensional image data of the current luggage. This multi-angle two-dimensional image data contains all-round information of the luggage appearance, avoiding the problem of information loss that may be caused by a single view, and providing a complete two-dimensional image basis for subsequent luggage contour extraction and surface feature analysis.

[0023] Step 1012: Obtain the reflected image of the current luggage and generate three-dimensional depth data. The reflected image is obtained by projecting a preset coded light pattern onto the current luggage by a structured light scanner installed above the luggage conveyor belt.

[0024] Specifically, the system installs a structured light scanner about 1.5 meters above the conveyor belt. The scanner includes a light pattern projector and a high-speed camera. After the current piece of luggage enters the preset area, the light pattern projector projects a preset coded light pattern onto the surface of the luggage, including a gray code stripe and a phase-shifted sine stripe sequence. After these light patterns are projected onto the surface of the luggage, due to the undulations of the luggage surface, the light patterns will be correspondingly deformed. The high-speed camera installed in the structured light scanner synchronously captures these deformed light patterns to form a reflected image of the current piece of luggage. The system calculates the spatial coordinates of each point on the luggage surface based on the captured reflected image through the principle of triangulation and the phase analysis algorithm, generating point cloud data representing the three-dimensional shape of the luggage, that is, the three-dimensional depth data of the current piece of luggage. This three-dimensional depth data accurately describes the three-dimensional shape and surface undulations of the luggage, providing high-precision three-dimensional spatial information for subsequent dimension measurement and shape analysis.

[0025] Step 1013: Obtain the contact pressure distribution data and weight data of the current piece of luggage with the luggage conveyor belt, as well as the thermal radiation distribution image of the current piece of luggage.

[0026] Specifically, a pressure sensor array is installed below the preset area section of the conveyor belt. These sensors are evenly distributed in a grid pattern to detect the pressure distribution of the current piece of luggage on the conveyor belt in real time. At the same time, the system integrates a high-precision weighing module into the conveyor belt support structure. After the current piece of luggage completely enters the preset area, the weighing module measures and records the total weight of the luggage to form the weight data of the current piece of luggage. In addition, the system installs an infrared thermal imager about 1.2 meters above the conveyor belt. When the current piece of luggage passes by, the thermal imager captures the thermal radiation emitted from the surface of the luggage to form a thermal image representing the temperature distribution, that is, the thermal radiation distribution image of the current piece of luggage. The contact pressure distribution data reflects the spatial distribution of the weight of the current piece of luggage, the weight data provides an accurate measurement of the luggage mass, and the thermal radiation distribution image shows the thermal characteristic differences of the luggage surface material and internal structure. These three types of data together complement the physical and thermal characteristic information that cannot be provided by the two-dimensional image and three-dimensional depth data.

[0027] Step 1014: Aggregate the multi-view two-dimensional image data, three-dimensional depth data, pressure distribution data, weight data, and thermal radiation distribution image into the multi-dimensional data of the current piece of luggage.

[0028] Specifically, the central data processing unit receives the data streams from various sensors and performs time synchronization processing to ensure that all data corresponds to the same current piece of luggage. The system maps the data collected by different sensors into a unified spatial coordinate system according to the pre-calibrated spatial correspondence relationship to achieve spatial alignment of the data. Then, the system integrates these data into the same data structure according to a predetermined format to form a comprehensive data set containing two-dimensional image information, three-dimensional spatial information, pressure information, weight information, and thermal distribution information, that is, the multi-dimensional data of the current piece of luggage. This multi-dimensional data aggregation method realizes the comprehensive perception and description of various physical characteristics of the current piece of luggage, providing a rich and diverse data basis for subsequent luggage parameter extraction and feature analysis.

[0029] Based on the above embodiments, as an alternative embodiment, the step of preprocessing and fusing the multi-dimensional data to obtain the luggage parameters of the current piece of luggage may further include the following steps: Step 1021: Perform background separation and edge extraction on the multi-view two-dimensional image data to obtain the contour information of the current piece of luggage.

[0030] Specifically, apply image preprocessing algorithms to the obtained multi-view two-dimensional image data, including image denoising, illumination equalization, and contrast enhancement, etc., to improve the image quality. Then, the system uses a background separation algorithm to segment the foreground and background of the processed image, separating the luggage (foreground) from the conveyor belt and the surrounding environment (background). This separation process is based on a Gaussian mixture model and color feature analysis and can adapt to the image segmentation requirements under different illumination conditions. Then, apply the Canny edge detection algorithm to the foreground segmentation result to extract the edges of the luggage and form a preliminary edge contour. To obtain a complete and closed contour, the system further applies morphological processing algorithms, including dilation, erosion, and edge connection, etc., to repair the possible breaks and noise points in the edges, and finally obtains the accurate contour information of the current piece of luggage from each perspective. This multi-view contour information combines the observation results from different angles, avoiding the occlusion and information loss problems that may be caused by a single perspective, and providing an accurate two-dimensional contour representation for subsequent luggage shape analysis.

[0031] Step 1022: Construct a three-dimensional model of the luggage based on the contour information and three-dimensional depth data, and calculate the size information of the current piece of luggage.

[0032] Specifically, the multi-view contour information is spatially registered with the 3D depth data to ensure that the 2D contour corresponds to the 3D point cloud in terms of spatial position. Then, the system adopts a point cloud reconstruction algorithm based on contour constraints, uses the contour information to screen and complement the 3D point cloud, removes noise points and fills in the missing areas of the point cloud caused by occlusion. Next, the system applies a triangular mesh reconstruction algorithm to the processed point cloud to generate a 3D mesh model representing the surface shape of the current luggage, that is, the solid model of the luggage. Based on this solid model, the system determines the main axis direction of the luggage through the principal component analysis method, and calculates the maximum length, width and height of the luggage in the main axis direction to obtain the basic dimensions of the luggage. At the same time, the system also calculates parameters such as the surface area, volume and shape complexity of the luggage to form the complete current luggage size information. This method of constructing a solid model based on multi-source data fusion overcomes the limitations of relying solely on 2D images or 3D point clouds, can more accurately represent the 3D shape of the luggage, and provides a reliable geometric basis for size measurement.

[0033] Step 1023: Calculate the weight information of the current luggage according to the pressure distribution data, weight data and solid model.

[0034] Specifically, the pressure distribution data is spatially corresponded with the solid model to determine the contact area and contact pressure distribution between the luggage and the conveyor belt. Then, combined with the total weight data, a mathematical model of luggage weight distribution is established. Based on the principles of physical mechanics, considering the shape, contact area and pressure distribution of the luggage, the mass distribution of each area inside the luggage is calculated. Through integral calculation, the system obtains the center of gravity position and weight distribution density map of the luggage, and further analyzes the uniformity and concentration of the weight distribution to judge whether there is a heavy object concentration area inside the luggage. At the same time, the system combines the volume information calculated by the solid model to calculate the average density and density change gradient of the luggage to form the complete weight information of the current luggage. This method of weight analysis by fusing multi-data sources not only provides the absolute weight value of the luggage, but also reveals the distribution characteristics of the items inside the luggage, providing an important reference basis for subsequent luggage handling and classification.

[0035] Step 1024: Based on the thermal radiation distribution image, contour information and solid model, identify the material distribution and internal structure of the luggage, and extract structural features.

[0036] Specifically, the thermal radiation distribution image is spatially registered with the contour information and the three-dimensional model, and the thermal radiation data is mapped onto the surface of the luggage. Then, the system applies a thermal image analysis algorithm to identify the temperature difference regions and the characteristics of temperature gradient changes in the thermal radiation distribution, which are usually related to material interfaces and internal structures. Based on a pre-established material-thermal property database, the system analyzes the matching degree between the thermal radiation pattern and various common luggage materials (such as cloth, metal, plastic, leather, etc.) to determine the material distribution on the surface of the luggage. At the same time, the system combines the deep penetration characteristics of thermal radiation to analyze the heat accumulation regions and isolation regions in the thermal image, and infers the internal structure of the luggage, such as the frame position, the layout of compartments, the distribution of fillers, etc. In addition, the system also analyzes the geometric characteristics of the three-dimensional model, including surface curvature, rigid regions, and flexible regions, to further verify and improve the material distribution and structure inference. Finally, the system integrates the above analysis results to extract the structural characteristics of the current luggage, including but not limited to the degree of hard shell, frame type, surface material composition, and internal separation conditions, etc.

[0037] Step 1025: Integrate the contour information, size information, weight information, and structural characteristics into luggage parameters.

[0038] Specifically, the system establishes a unified data structure for luggage parameters, which includes three categories: geometric characteristics, physical characteristics, and structural characteristics. The system's contour information is used as a component of the geometric characteristics, and size information (length, width, height, volume, etc.) is also included in the geometric characteristics category. At the same time, weight information (total weight, center of gravity position, weight distribution, etc.) is classified into the physical characteristics category. In addition, the extracted structural characteristics (material distribution, internal structure, etc.) are set as a separate structural characteristics category by the system. During the data integration process, the system performs feature normalization to ensure that the dimensions and representation forms of different types of features are consistent, facilitating the application of subsequent processing algorithms. Finally, the system generates a parameter package for the current luggage, which stores and represents the comprehensive characteristics of the current luggage in a unified format, providing a complete and accurate parameter basis for subsequent luggage classification recognition, priority determination, and processing flow optimization.

[0039] Step 20: Determine the category of the current luggage based on the luggage parameters.

[0040] Specifically, a knowledge base for luggage categories is constructed. This knowledge base contains predefined common luggage types (such as hard-shell suitcases, soft-sided luggage, irregularly shaped luggage, etc.) and their typical parameter feature patterns. The luggage parameters of the current luggage are obtained, including contour information, size information, weight information, and structural features, and a classification method based on multi-feature fusion is used for category recognition. During the recognition process, the system first calculates the matching degree of the parameters of each dimension of the current luggage with the feature patterns of different categories in the knowledge base: for the contour information, the system uses a shape matching algorithm to compare the similarity between the contour of the current luggage and the typical contour of the category; for the size information, the system compares the length, width, and height of the current luggage with the standard size ranges of different categories; for the weight information, the system analyzes the total weight and weight distribution of the current luggage with the weight feature patterns of different categories; for the structural features, the system compares the degree of hard shell, material composition, etc. of the current luggage with the matching degree of the structural characteristics of different categories. After completing the feature matching of each dimension, the system uses a weighted fusion mechanism to comprehensively evaluate the matching results. The system assigns weights to different features, calculates the comprehensive score, and selects the category with the highest score as the category of the current luggage.

[0041] Based on the above embodiments, as another alternative embodiment, the step of determining the category of the current luggage based on the luggage parameters may further include the following steps: Step 201: Input the luggage parameters into a pre-trained multi-layer neural network model. The multi-layer neural network model performs feature extraction and dimensionality reduction processing on the input luggage parameters to obtain a feature vector.

[0042] Specifically, since the luggage parameters have a high number of dimensions and diverse feature types, the system first performs standardization preprocessing on the parameters to unify parameters with different dimensions and ranges into a standard interval, ensuring that the weights of various parameters in the neural network will not be imbalanced due to numerical range differences. The preprocessed luggage parameters are input into a pre-trained multi-layer neural network model. This model uses a deep learning architecture, including an input layer, multiple hidden layers, and an output layer. The number of neurons in the input layer matches the dimension of the luggage parameters and receives the complete luggage parameter data; the hidden layer consists of multiple fully connected layers, each layer containing a different number of neurons, and uses the ReLU activation function to enhance the non-linear expression ability of the model; the model also includes a batch normalization layer to accelerate the training process and improve the stability of the model. The first few hidden layers of the model are mainly responsible for feature extraction, automatically learning the key patterns in the luggage parameters through the connection weights between neurons; the last few hidden layers perform dimensionality reduction operations, mapping high-dimensional features to a low-dimensional space, retaining key information while reducing redundancy. After multiple layers of processing, the system extracts a fixed-length feature vector from the middle layer of the neural network. This feature vector is a highly abstract and compressed representation of the original luggage parameters and contains the key information required for luggage classification.

[0043] Step 202: Calculate the probabilities of the current piece of luggage belonging to each preset category based on the extracted feature vectors, and select the category with the highest probability as the preliminary category of the current piece of luggage.

[0044] Specifically, input the feature vectors into the subsequent layers of the neural network model, which are specifically designed for classification tasks. The last few layers of the model are fully connected layers, gradually mapping the feature vectors to output units equal in number to the preset luggage category quantities. The final output layer uses the Softmax activation function to convert the raw output of the neural network into a probability distribution, making the sum of the probabilities of all categories equal to 1, and each probability value representing the likelihood of the current piece of luggage belonging to the corresponding category. The preset luggage categories include common types such as hard-shell suitcases, soft-sided luggage, sports equipment bags, instrument cases, baby strollers, wheelchairs, irregularly shaped items, etc., as well as special categories defined according to airline requirements. The system compares the probability values of all categories and selects the category with the highest probability as the preliminary category of the current piece of luggage, while recording this probability value as an indicator of classification confidence.

[0045] Step 203: Perform anomaly detection on the preliminary category and the historical parameters of the same type of luggage to obtain an anomaly value.

[0046] Specifically, extract the historical luggage parameter records of the same type as the preliminary category from the database, which contain the typical feature distributions of the luggage of this category. The system uses the Isolation Forest algorithm to perform anomaly detection on the current piece of luggage. This algorithm is based on the principle of decision trees and evaluates the degree of anomaly by randomly constructing multiple isolation trees and calculating the average path length of the samples. The system calculates the degree of deviation of the current luggage parameters from the historical luggage of the same type in the feature space to obtain an anomaly value representing the degree of anomaly. The calculation of the anomaly value takes into account multiple factors: one is the Mahalanobis distance between the current luggage features and the average features of the historical luggage of the same type, reflecting the overall degree of deviation; the second is the deviation of the current luggage in each main feature dimension. For example, anomalies in some key features (such as weight, material, etc.) may indicate classification errors; the third is the rarity of the combination of the current luggage features, reflecting the anomaly of the relationship between the features. Through these multi-dimensional anomaly analyses, the system can comprehensively evaluate the reliability of the current classification result and calculate a comprehensive anomaly value. This anomaly detection mechanism can effectively identify situations where, although the classifier assigns a high probability, the actual features are significantly inconsistent with the typical features of the category, providing the system with the ability of self-verification.

[0047] Step 204: When the anomaly value is greater than the anomaly threshold, trigger the manual review process.

[0048] Specifically, the outlier is compared with a preset outlier threshold. The outlier threshold is preset according to system operation experience and classification accuracy requirements, and can be dynamically adjusted according to system performance and operation needs. When the outlier exceeds the threshold, it indicates that although the current piece of luggage is classified into a certain category, its characteristics are significantly different from the typical characteristics of this category, and the classification result may be incorrect. At this time, the system automatically triggers the manual review process: First, the system generates an outlier alarm and marks the current piece of luggage as "to be manually confirmed"; then, the system sends the multi-dimensional data of the luggage, the preliminary classification result, the outlier, and the specific manifestation of the outlier (such as which characteristics are significantly abnormal) to the manual review workstation; finally, the manual operator confirms or corrects the luggage category based on the information provided by the system and on-site observation.

[0049] Step 205: When the outlier is not greater than the outlier threshold, confirm that the preliminary category is the category of the current piece of luggage.

[0050] Specifically, when the outlier is not greater than the threshold, it indicates that the characteristics of the current piece of luggage have sufficient consistency with the typical characteristic distribution of the preliminary category, and the preliminary classification result has a high credibility. At this time, the system automatically confirms that the preliminary category is the final category of the current piece of luggage without manual intervention. The system stores the final category information together with the luggage parameters in the database and transmits the classification result to subsequent processing links, such as luggage routing, special handling marking, or loading planning.

[0051] Step 30: Determine the processing priority of the current piece of luggage based on the flight information and luggage parameters corresponding to the current piece of luggage.

[0052] Specifically, obtain the flight information associated with the current piece of luggage from the airport database, including key data such as flight number, departure time, and boarding gate location. The system uses a multi-factor weighted scoring mechanism to calculate the processing priority: For the flight time factor, the system calculates the difference between the current time and the flight departure time and sets the basic priority score according to a preset time gradient table. Luggage with a departure time approaching gets a higher time factor score; for the luggage category factor, different weights are assigned according to the luggage category and its characteristics. Special luggage (such as medical equipment, fragile items) gets a higher category factor score; for the luggage parameter factor, the system analyzes parameters such as size and weight and assigns different parameter factor scores to oversized luggage (requiring special handling equipment) and light and small luggage (high processing efficiency) respectively. The system sums up the scores of each factor weighted according to the preset weights to obtain the comprehensive priority score of the current piece of luggage, and divides the luggage into four levels: urgent, high priority, normal, and low priority according to the score range. The division result serves as the processing priority of the current piece of luggage to guide the subsequent sorting routing and loading order of the luggage.

[0053] Based on the above embodiments, as another alternative embodiment, the step of determining the processing priority of the current piece of luggage based on the flight information and luggage parameters corresponding to the current piece of luggage may further include the following steps: Step 301: Obtain the flight information corresponding to the current piece of luggage. The flight information includes the departure time, boarding time, origin, destination, and transfer information.

[0054] Specifically, read the unique identification code of the luggage through the barcode or RFID tag on the luggage tag, and then query the airport flight management system database to obtain the detailed flight information associated with the luggage. The obtained flight information includes: the scheduled departure time of the flight, that is, the time point when the aircraft is scheduled to depart; the passenger boarding time, that is, the time point when the airline requires passengers to start boarding; the origin of the flight, that is, the departure airport of the current flight; the destination of the flight, that is, the arrival airport of the current flight; and the transfer information, including whether it is a transfer luggage, the transfer airport, the transfer connection time, etc. For connecting flights or multi-segment voyages, the system will obtain the complete itinerary information and identify the key connection points. The system also checks the flight status data, including whether there is a delay, the estimated delay duration, the boarding gate change, and other latest dynamics, to ensure that subsequent processing decisions are based on the latest flight situation. This comprehensive acquisition of flight information provides an accurate data basis for the subsequent calculation of time urgency, enabling the system to accurately evaluate the time sensitivity of each piece of luggage.

[0055] Step 302: Calculate the time urgency of the current piece of luggage based on the flight information.

[0056] Specifically, first calculate the difference between the current time and the flight departure time as the basic time margin. Then, the system estimates the shortest time required for the luggage to be transported from the current location to the target loading area based on the origin, destination, and terminal layout data, including the conveyor belt running time, sorting node processing time, and loading preparation time. For transfer luggage, the system specifically considers the transfer connection time and calculates the transfer time margin. The system compares the time margin with a preset time threshold to set the basic urgency level. In addition, the system also considers factors such as flight scale and luggage volume, and appropriately increases the urgency assessment for the luggage of large flights or peak-hour flights; considers the historical flight delay rate and current weather conditions, and adjusts the urgency of the luggage of flights with high delay risks. The system integrates and calculates these factors to finally obtain a standardized time urgency value between 0 and 100, where the higher the value, the more urgent the time. This multi-dimensional time urgency calculation method enables the system to accurately evaluate the time sensitivity of each piece of luggage and provides a key basis for priority allocation.

[0057] Step 303: Analyze the size information and structural characteristics in the luggage parameters to determine the special processing requirement coefficient.

[0058] Specifically, two key parameters, size information and structural features, are analyzed. For size information, the system compares the length, width, height and volume of the current baggage with the compatible range of standard baggage handling equipment, identifies oversized baggage, and evaluates the difficulty of special handling required based on the degree of excess. For structural features, the system analyzes factors such as the material distribution, hard shell degree, shape complexity and weight distribution of the baggage, and identifies baggage characteristics that may require special handling, such as fragile items, irregularly shaped items or baggage with a significant center of gravity shift. The system assigns handling difficulty scores to different special characteristics based on the preset special handling evaluation matrix, and calculates the comprehensive handling complexity by considering the combined effects of the characteristics. At the same time, combined with the baggage category, special categories of baggage that require special equipment or manual handling, such as medical equipment, musical instruments or sports equipment, are identified. These analysis results are integrated into a standardized special handling demand coefficient, which reflects the special resources and operational complexity required to handle the current baggage.

[0059] Step 304: Calculate the processing priority index according to the time urgency and the special processing requirement coefficient.

[0060] Specifically, the system calculates the weighted sum according to the preset weights: Processing priority index = α × time urgency + β × special processing demand coefficient, where α and β are weight coefficients preset according to the airport operation strategy. Usually α is greater than β, reflecting the priority of time factors. In order to handle complex priority strategies, the system introduces a conditional weight adjustment mechanism: when the time urgency exceeds the high-risk threshold, the system increases the α value to ensure that extremely time-critical luggage receives the highest priority; when the special processing demand coefficient exceeds the complex threshold, the system increases the β value to ensure that extremely complex luggage receives sufficient processing time. In addition, the system also considers the airline's VIP service strategy and applies a priority enhancement coefficient to the luggage of VIP passengers; considering operational efficiency optimization, the priority index is appropriately adjusted for ordinary luggage that can be efficiently processed in batches with other luggage. Finally, the system calculates a comprehensive processing priority index, which reflects both the time urgency of the luggage and the complexity of processing, providing a scientific basis for subsequent priority division.

[0061] Step 305: The processing priority of the current baggage is divided according to the processing priority index.

[0062] Specifically, compare the processing priority index with a preset grading threshold to classify the current piece of luggage into the corresponding processing priority level. The system sets four standard priority levels: emergency level (priority index ≥ 90), which requires immediate processing and is assigned the highest resource priority; high priority level (70 ≤ priority index < 90), which requires priority processing but is secondary to emergency-level luggage; medium priority level (40 ≤ priority index < 70), which is processed according to the regular process; low priority level (priority index < 40), which can be processed when resources are idle. The system determines the priority level to which the current piece of luggage belongs based on the specific value of the processing priority index of the current piece of luggage and adds the corresponding priority mark to the luggage information.

[0063] Step 40: Determine the processing flow of the current piece of luggage based on the processing priority and the real-time load of the luggage handling system.

[0064] Specifically, the load status of each area and device of the luggage handling system is monitored in real time, including the conveyor belt occupancy rate, the congestion degree of sorting nodes, the operation status of security inspection equipment, and the workload of the manual processing area. The system determines the optimal processing flow by using an adaptive path planning algorithm based on the processing priority and the system load. For high-priority luggage, the system preferentially allocates high-speed conveyor areas with low loads, tries to avoid congested nodes, and ensures the shortest conveyor time; for medium-priority luggage, the system balances the path efficiency and system balance, and avoids local congestion caused by concentrated resource use; for low-priority luggage, the system arranges a longer but lower-load path, or temporarily buffers it in a low-occupancy area and waits to be processed after the system load decreases. At the same time, the system dynamically determines the security inspection level according to the luggage category, destination security requirements, and historical security inspection data, such as standard security inspection, secondary inspection, or special item special inspection. The system forms a complete set of processing instructions, including the detailed conveyor area path, the estimated conveyor time at each node, and the specified security inspection level, and transmits it to the execution control module of the luggage handling system.

[0065] On the basis of the above embodiments, as another alternative embodiment, the step of determining the processing flow of the current piece of luggage based on the processing priority and the real-time load of the luggage handling system may further include the following steps: Step 401: Obtain the real-time load data of each processing area of the luggage handling system. The real-time load data includes the number of pieces of luggage, the processing rate, and the queue length in each area.

[0066] Specifically, operation data is collected in real time through a sensor network distributed at key nodes of the baggage handling system. These sensors include optoelectronic sensors installed along the conveyor belts to detect the baggage flow and density; weight sensors and imaging sensors installed at sorting nodes to monitor the working status of sorting equipment; operation status monitors installed at security inspection equipment to record the processing speed and queue situation of the equipment; and operation monitoring systems in the manual processing areas to count the workload and efficiency of manual operations. The system centrally processes and standardizes these real-time collected data, and calculates three key indicators for each processing area: the number of baggages, that is, the number of baggages being processed or waiting to be processed in the current area; the processing rate, that is, the number of baggages that can be processed in this area per unit time, considering the equipment specifications and the current operating efficiency; the queue length, that is, the number of baggages waiting to enter this area for processing and the estimated waiting time. The system also calculates the time change trends of these indicators to predict the load changes in each area in the short term in the future.

[0067] Step 402: Establish a processing area path map, which includes the connection relationships and transfer times between processing areas.

[0068] Specifically, a topology structure diagram is constructed based on the physical layout of the airport baggage handling system. Each processing area is regarded as a node in the diagram, and the conveyor belts and sorting equipment connecting the areas are regarded as connecting edges. The processing areas include a baggage receiving area, a standard security inspection area, a premium security inspection area, a special item inspection area, an automatic sorting area, a manual sorting area, and multiple baggage transfer areas, etc. The system assigns two key attributes to each connecting edge: one is the basic transfer time, that is, the time required for a baggage to be transferred from one area to another without congestion, which is calculated based on the conveyor belt length and the standard operating speed; the other is the current transfer capacity, which reflects the available status of the connecting equipment, including whether it is operating normally, whether there are some channels closed, etc. The system also considers special path restrictions, such as certain baggages with special sizes or weights may not be able to pass through specific channels, or require special equipment for processing. The system integrates this information into a complete path map data structure, which supports efficient path query and calculation. By maintaining such a dynamically updated processing area path map, the system can always master the overall layout and connection status of the baggage handling system, providing a topological basis for subsequent path planning.

[0069] Step 403: Determine the target processing time requirements according to the processing priorities, and calculate multiple feasible processing paths that meet the target processing time requirements in combination with the real-time load data.

[0070] Specifically, set the target processing time requirements according to the determined processing priorities: for urgent-level luggage, the system sets the shortest possible processing time, usually requiring a reduction of more than 50% compared to the standard processing time; for high-priority luggage, the system sets a processing time reduced by 20% - 30% compared to the standard time; for medium-priority luggage, the system sets requirements that meet the standard processing time; for low-priority luggage, the system allows an appropriate extension of the processing time, but not exceeding 1.5 times the standard time. After determining the target processing time requirements, the system applies an improved Dijkstra algorithm to perform path search on the processing area path map. Different from traditional algorithms, the path calculation of the system simultaneously considers static transfer time and dynamic load conditions: convert real-time load data into dynamic weights of each connection edge, and the higher the load in a region, the greater the weight, indicating that the longer the possible delay through this region; the system calculates multiple possible paths from the current location to the destination, and the total time-consuming of each path is the superposition of static transfer time and dynamic load time of each segment; the system sets a maximum path number limit and selects several paths with the shortest expected total time-consuming as candidates. To improve the calculation efficiency, the system adopts a heuristic search strategy, preferentially exploring paths towards the target direction, and quickly screening out a set of feasible paths that meet the target processing time requirements. This path planning method that combines priorities and real-time loads enables the system to allocate appropriate resources for luggage of different priorities, avoiding system congestion while ensuring processing efficiency.

[0071] Step 404: Determine the corresponding security inspection level based on the structural characteristics and processing priorities of the current luggage, and screen out the paths that meet the security inspection level requirements from multiple feasible processing paths.

[0072] Specifically, analyze the structural characteristics of the current piece of luggage, and combine the luggage category and luggage parameters to evaluate the safety risk coefficient. The system considers multiple factors: the material composition and density distribution of the luggage, which may affect the X-ray penetration effect; the shape complexity and internal structure of the luggage, which may require multi-angle scanning; the special contents of the luggage (such as electronic devices, liquids), which may require special inspection. At the same time, the system combines the current safety level requirements and processing priorities to determine the security inspection requirements in three aspects: the type of security inspection equipment, such as standard X-ray machines, CT scanners or special item detection equipment; the security inspection accuracy requirements, such as fast scanning or detailed scanning; whether secondary inspection or manual verification is required. The system integrates these requirements into the security inspection level of the current piece of luggage, and checks each feasible processing path calculated, and filters out a subset of paths that can meet the determined security inspection level requirements. The filtering process considers the type of security inspection equipment available on the path, the processing capacity of the current security inspection area, and the feasibility of special inspections. For some high-risk luggage or special items, the system may enforce a specific security inspection process, even if this may result in an extended processing time. This security inspection level determination and path filtering mechanism based on luggage characteristics and safety requirements ensures that each piece of luggage can receive an appropriate level of security inspection, meeting safety standards while avoiding resource waste caused by over-inspection.

[0073] Step 405: Select the path with the shortest completion time from the filtered paths as the processing flow for the current piece of luggage.

[0074] Specifically, the system first calculates the estimated completion time of each path, that is, the total time required to reach the destination from the current location through the planned path, including the transfer time, waiting time, and processing time in each area. Then, the system considers the stability and risk factors of the path, such as the reliability of the equipment on the path, historical congestion conditions, and the probability of unexpected delays. After comprehensively evaluating the completion time and risk of each path, the system selects the path with the shortest estimated completion time and controllable risk as the final processing flow for the current piece of luggage. The system converts the selected processing flow into specific execution instructions, including the detailed order of transfer areas, the estimated transfer time for each area, the type of security inspection equipment to be passed through, and the security inspection level requirements. The system also generates a visual representation of the processing flow for the operator to monitor and reference. Finally, the system sends the complete processing flow instructions to the control module of the luggage handling system and the relevant processing areas, and each area adjusts the equipment parameters and operation processes according to the instructions to ensure that the current piece of luggage is smoothly transferred and processed according to the planned path. This optimal path selection mechanism based on multi-factor evaluation enables the system to allocate the most efficient processing flow for each piece of luggage, minimizing the processing time and improving the overall processing efficiency.

[0075] Based on the above embodiments, as another alternative embodiment, a method for measuring and identifying checked luggage may further include the following process: Specifically, electronic tag information is generated based on the processing flow. This electronic tag information includes key data such as the unique identification code of the luggage, the processing priority, the complete path node sequence, the estimated arrival time of each node, the security inspection requirements, and the special processing instructions. The system encodes, compresses, and encrypts this information, and then writes the electronic tag information into the physical identification tag of the current luggage through near-field communication technology. The physical identification tag is an intelligent electronic tag that integrates RFID and low-power Bluetooth technologies, and is built with a microprocessor, a storage chip, a wireless communication module, and a button battery. It can store the complete information of the luggage and support dynamic updates. During the luggage processing, the physical identification tag exchanges data with the reading and writing devices in each processing area through its wireless communication module: when the luggage passes through a processing node, the area reader automatically identifies the tag and updates the real-time position information and processing status of the luggage; at the same time, the tag transmits the updated information back to the central system, enabling the system to keep track of the exact position and processing progress of each piece of luggage in real time. The system conducts consistency checks by comparing the actual position and processing status of the luggage with the predetermined processing flow. When it detects that the luggage deviates from the predetermined path, the processing time is abnormally delayed, or the processing status is abnormal, the system automatically triggers a hierarchical alarm and starts the corresponding corrective program: for minor deviations, the system automatically calculates alternative paths for path correction; for severe deviations, in addition to issuing a high-level alarm, the system also notifies the nearby operator for manual intervention and updates the processing priority of the luggage to prevent the delay from expanding. This intelligent tracking and exception handling mechanism based on electronic tags realizes the whole-process visual management of luggage processing, greatly improves the accuracy and reliability of luggage processing, effectively prevents luggage misdelivery, loss, or delay, and at the same time provides detailed processing records for service quality evaluation and system optimization.

[0076] Please refer to Figure 2 , which is a schematic diagram of the modules of a checked luggage measurement and identification system provided by an embodiment of this application. Among them, the system includes: A luggage parameter acquisition module, which is used to collect multi-dimensional data of the current luggage on the luggage conveyor belt, and preprocess and fuse the multi-dimensional data to obtain the luggage parameters of the current luggage. The luggage parameters include size information, weight information, and luggage structure characteristics; A luggage category determination module, which is used to determine the category of the current luggage based on the luggage parameters; A priority determination module, which is used to determine the processing priority of the current luggage based on the flight information corresponding to the current luggage and the luggage parameters; A processing flow determination module, which is used to determine the processing flow of the current luggage based on the processing priority and the real-time load of the luggage processing system.

[0077] Optionally, the luggage parameter acquisition module is further configured to acquire multi-view two-dimensional image data of the current luggage collected by a plurality of cameras with different heights and angles set in a preset area of the luggage conveyor belt; Acquire a reflection image of the current luggage and generate three-dimensional depth data, where the reflection image is acquired after a preset coded light pattern is projected onto the current luggage by a structured light scanner installed above the luggage conveyor belt; Acquire the contact pressure distribution data and weight data of the current luggage with the luggage conveyor belt, and the thermal radiation distribution image of the current luggage; Pool the multi-view two-dimensional image data, the three-dimensional depth data, the pressure distribution data, the weight data, and the thermal radiation distribution image into multi-dimensional data of the current luggage.

[0078] Optionally, the luggage parameter acquisition module is further configured to perform background separation and edge extraction on the multi-view two-dimensional image data to obtain the contour information of the current luggage; Construct a three-dimensional model of the luggage based on the contour information and the three-dimensional depth data, and calculate the size information of the current luggage; Calculate the weight information of the current luggage according to the pressure distribution data, the weight data, and the three-dimensional model; Based on the thermal radiation distribution image, the contour information, and the three-dimensional model, identify the material distribution and internal structure of the luggage, and extract structural features; Integrate the contour information, the size information, the weight information, and the structural features into luggage parameters.

[0079] Optionally, the luggage category determination module is further configured to input the luggage parameters into a pre-trained multi-layer neural network model, and the multi-layer neural network model performs feature extraction and dimensionality reduction processing on the input luggage parameters to obtain a feature vector; Calculate the probability that the current luggage belongs to each preset category based on the extracted feature vector, and select the category with the highest probability as the preliminary category of the current luggage; Perform anomaly detection on the preliminary category and historical luggage parameters of the same category to obtain an anomaly value; When the anomaly value is greater than the anomaly threshold, trigger an artificial review process; When the anomaly value is not greater than the anomaly threshold, confirm the preliminary category as the category of the current luggage.

[0080] Optionally, the priority determination module is further configured to acquire the flight information corresponding to the current luggage, where the flight information includes the departure time, boarding time, origin, destination, and transfer information; Calculate the time urgency of the current luggage based on the flight information; Analyze the size information and structural features in the luggage parameters to determine the special handling requirement coefficient; Calculate the processing priority index according to the time urgency and the special handling requirement coefficient; Classify the current luggage into the processing priority levels of the current luggage according to the processing priority index.

[0081] Optionally, the processing flow determination module is further configured to obtain the real-time load data of each processing area of the luggage handling system, where the real-time load data includes the number of luggages, the processing rate, and the queue length in each area; Establish a processing area path map, where the processing area path map includes the connection relationships and transfer times between the processing areas; Determine the target processing time requirement according to the processing priority, and calculate multiple feasible processing paths that meet the target processing time requirement in combination with the real-time load data; Determine the corresponding security inspection level based on the structural features and the processing priority of the current luggage, and screen out the paths that meet the security inspection level requirements from the multiple feasible processing paths; Select the path with the shortest completion time from the screened paths as the processing flow of the current luggage, where the processing flow includes the transfer area, the transfer time, and the security inspection level.

[0082] Optionally, the processing flow determination module is further configured to generate electronic tag information according to the processing flow of the current luggage; Bind the electronic tag information to the physical identification tag of the current luggage, and update the location information and processing status of the current luggage in real time during the current luggage handling process through the wireless communication module of the physical identification tag; When it is detected that the current luggage deviates from the corresponding processing flow, automatically trigger an alarm and start a rectification program.

[0083] It should be noted that: when the system provided in the above embodiment realizes its functions, only the above-mentioned division of each functional module is used for illustration. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process can be seen in the method embodiment, which will not be elaborated here.

[0084] The embodiment of the present application also provides a computer storage medium, which can store multiple instructions, and the instructions are suitable for being loaded and executed by a processor to perform a method for measuring and identifying checked luggage in the above embodiment. The specific execution process can refer to the specific description of the above embodiment, which will not be elaborated here.

[0085] Please refer to Figure 3 This application also discloses an electronic device. Figure 3 It is a schematic structural diagram of an electronic device disclosed in an embodiment of this application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0086] Among them, the communication bus 302 is used to implement connection communication between these components.

[0087] Among them, the user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may further include a standard wired interface and a wireless interface.

[0088] Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0089] Among them, the processor 301 may include one or more processing cores. The processor 301 connects various parts within the entire server using various interfaces and lines. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling data stored in the memory 305, it executes various functions of the server and processes data. Optionally, the processor 301 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 301 may integrate one or a combination of several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 301 and may be implemented separately by a single chip.

[0090] Among them, the memory 305 may include a Random Access Memory (RAM), or may also include a Read-Only Memory. Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above method embodiments, etc.; the data storage area may store data involved in the above method embodiments. Optionally, the memory 305 may also be at least one storage device located far from the aforementioned processor 301. Refer to Figure 3 , in the memory 305 as a computer storage medium, an operating system, a network communication module, a user interface module, and an application program of a checked baggage measurement and recognition method may be included.

[0091] In Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain data input by the user; while the processor 301 can be used to call an application program for a checked baggage measurement and recognition method stored in the memory 305. When executed by one or more processors 301, the electronic device 300 is caused to execute the method of one or more of the above embodiments. It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be in other sequences or performed simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0092] In the above embodiments, the descriptions of the respective embodiments have their own focuses. For parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0093] In several implementation manners provided by this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0094] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0095] In addition, the functional units in each embodiment of this application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0096] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of this application. And the aforementioned memory includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0097] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, all equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will easily think of other implementation schemes of the present disclosure after considering the specification and the disclosure of the practical truth.

[0098] This application aims to cover any variations, uses, or adaptive changes of the present disclosure. These variations, uses, or adaptive changes follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for measuring and identifying checked luggage, characterized in that, The method includes: Collecting multi-dimensional data of the current luggage on the luggage conveyor belt, preprocessing and fusing the multi-dimensional data to obtain luggage parameters of the current luggage, where the luggage parameters include size information, weight information, and luggage structure characteristics; Determining the category of the current luggage based on the luggage parameters; Determining the processing priority of the current luggage based on the flight information corresponding to the current luggage and the luggage parameters; Determining the processing flow of the current luggage based on the processing priority and the real-time load of the luggage handling system.

2. The checked baggage measurement and identification method according to claim 1, characterized in that The collecting multi-dimensional data of the current luggage on the luggage conveyor belt includes: Obtaining multi-view two-dimensional image data of the current luggage collected by a plurality of cameras set at different heights and angles in a preset area of the luggage conveyor belt; Obtaining a reflection image of the current luggage and generating three-dimensional depth data, where the reflection image is collected after a preset coded light pattern is projected onto the current luggage by a structured light scanner installed above the luggage conveyor belt; Obtaining the contact pressure distribution data and weight data between the current luggage and the luggage conveyor belt, and the thermal radiation distribution image of the current luggage; Collecting the multi-view two-dimensional image data, the three-dimensional depth data, the pressure distribution data, the weight data, and the thermal radiation distribution image as the multi-dimensional data of the current luggage.

3. The checked baggage measurement and identification method according to claim 2, characterized in that, The preprocessing and fusing the multi-dimensional data to obtain the luggage parameters of the current luggage includes: Performing background separation and edge extraction on the multi-view two-dimensional image data to obtain the contour information of the current luggage; Constructing a three-dimensional model of the luggage based on the contour information and the three-dimensional depth data, and calculating the size information of the current luggage; Calculating the weight information of the current luggage according to the pressure distribution data, the weight data, and the three-dimensional model; Identifying the material distribution and internal structure of the current luggage based on the thermal radiation distribution image, the contour information, and the three-dimensional model, and extracting structural characteristics; Integrating the contour information, the size information, the weight information, and the structural characteristics into luggage parameters.

4. The checked baggage measurement and identification method according to claim 1, characterized in that The determining the category of the current luggage based on the luggage parameters includes: Inputting the luggage parameters into a pre-trained multi-layer neural network model, where the multi-layer neural network model performs feature extraction and dimensionality reduction processing on the input luggage parameters to obtain a feature vector; Calculating the probability that the current luggage belongs to each preset category based on the feature vector, and selecting the category with the highest probability as the preliminary category of the current luggage; Performing anomaly detection on the preliminary category and the historical luggage parameters of the same category to obtain an anomaly value; When the anomaly value is greater than the anomaly threshold, triggering an artificial review process; When the anomaly value is not greater than the anomaly threshold, confirming the preliminary category as the category of the current luggage.

5. The checked baggage measurement and identification method according to claim 1, characterized in that, The determining the processing priority of the current luggage based on the flight information corresponding to the current luggage and the luggage parameters includes: Obtaining the flight information corresponding to the current luggage, where the flight information includes departure time, boarding time, origin, destination, and transfer information; Calculating the time urgency of the current luggage based on the flight information; Analyze the size information and structural characteristics in the luggage parameters to determine the special handling requirement coefficient; Calculate the processing priority index according to the time urgency and the special handling requirement coefficient; Divide the processing priority of the current luggage according to the processing priority index; 6. The checked baggage measurement and identification method according to claim 1, characterized in that, Determine the processing flow of the current luggage based on the processing priority and the real-time load of the luggage handling system, including: Obtain the real-time load data of each processing area of the luggage handling system, and the real-time load data includes the number of luggages, processing rate and queue length in the processing area; Establish a processing area path map, which includes the connection relationship and transfer time between each processing area; Determine the target processing time requirement according to the processing priority, and calculate multiple feasible processing paths that meet the target processing time requirement in combination with the real-time load data; Determine the corresponding security inspection level based on the structural characteristics and the processing priority of the current luggage, and screen out the paths that meet the security inspection level requirements from the multiple feasible processing paths; Select the path with the shortest completion time from the screened paths as the processing flow of the current luggage, and the processing flow includes the transfer area, transfer time and security inspection level; 7. The method for measuring and identifying checked luggage according to claim 1, characterized in that, The method further includes: Generate electronic tag information according to the processing flow of the current luggage; Bind the electronic tag information to the physical identification tag of the current luggage, and update the position information and processing status of the current luggage in real time through the wireless communication module of the physical identification tag during the current luggage processing; When it is detected that the current luggage deviates from the corresponding processing flow, an alarm is automatically triggered and a rectification program is started; 8. A checked baggage measurement and identification system, characterized in that, The system includes: A luggage parameter acquisition module, which is used to collect multi-dimensional data of the current luggage on the luggage conveyor belt, and preprocess and fuse the multi-dimensional data to obtain the luggage parameters of the current luggage, and the luggage parameters include size information, weight information and luggage structural characteristics; A luggage category determination module, which is used to determine the category of the current luggage based on the luggage parameters; A priority determination module, which is used to determine the processing priority of the current luggage based on the flight information corresponding to the current luggage and the luggage parameters; A processing flow determination module, which is used to determine the processing flow of the current luggage based on the processing priority and the real-time load of the luggage handling system; 9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores multiple instructions, and the instructions are suitable for being loaded and executed by a processor to execute the method according to any one of claims 1-7; 10. An electronic device, characterized in that, It includes a processor, a memory, a user interface and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method according to any one of claims 1-7.

Images