Intelligent joint control method and system for airport luggage check-in based on multi-person identification

Abstract

The application provides an airport luggage check-in intelligent joint control method and system based on multi-person identification, relates to the technical field of airport intelligent service, and comprises the following steps: acquiring monitoring images of operation areas of multiple self-service devices; identifying and tracking multiple users in the operation areas according to the monitoring images, generating user identifiers of the users, and establishing an association relationship between the user identifiers and the luggage of the users; in combination with the positional relationship of the users with respect to the self-service devices and the state information of the self-service devices, distributing corresponding target self-service devices to the users, and establishing a binding relationship between the user identifiers and the corresponding target self-service devices; and generating control strategies of the target self-service devices according to the binding relationship. The application has the technical effect of reducing security risk problems such as user operation of incorrect devices and non-matching of luggage and user identity.

Description

Technical Field

[0001] This application relates to the field of intelligent airport service technology, specifically to an intelligent joint control method, system, equipment and medium for airport baggage check-in based on multi-person identification. Background Technology

[0002] With the rapid development of the air transport industry and the continuous growth of passenger travel demand, airports, as important transportation hubs, are facing increasingly severe service pressures and management challenges. Traditional manual baggage check-in services often suffer from long waiting times, low service efficiency, and insufficient staffing during peak hours. They also face technical challenges such as baggage mismatch, difficulties in identity verification, and inaccurate security risk control. Especially in complex scenarios where multiple users simultaneously utilize self-service check-in devices, accurately identifying user identities, rationally allocating equipment resources, ensuring the correct correspondence between baggage and users, and preventing security issues such as misoperation and identity theft have become key technical bottlenecks restricting the development of intelligent airport services.

[0003] Currently, the main solutions to these problems are deploying self-service baggage check-in devices and using a single authentication method, such as scanning boarding passes or ID cards to verify user identity and guiding users through the baggage check-in process via touchscreen interfaces. These solutions alleviate the pressure on manual services to some extent and improve the automation level of baggage check-in services. However, when dealing with scenarios involving multiple concurrent users, these methods lack the intelligent perception and coordinated management capabilities for multiple target objects in complex scenarios, which can easily lead to security risks such as user error on devices and mismatches between baggage and user identities. Summary of the Invention

[0004] This application provides a method, system, device, and medium for intelligent joint control of airport baggage check-in based on multi-person identification, which can reduce security risks such as user operation errors, mismatch between baggage and user identity, etc.

[0005] In a first aspect, this application provides a method for intelligent joint control of airport baggage check-in based on multi-user identification. The method includes: acquiring monitoring images of the operating areas of multiple self-service devices; identifying and tracking multiple users within the operating areas based on the monitoring images, generating user identifiers for each user, and establishing a correlation between the user identifiers and the baggage of each user; acquiring status information of each self-service device; combining the positional relationship of each user relative to each self-service device and the status information of each self-service device, assigning a corresponding target self-service device to each user, and establishing a binding relationship between the user identifiers and the corresponding target self-service devices; and generating a system based on the binding relationship. The control strategy for each target self-service device includes: each target self-service device only responds to operations from users with whom it has a binding relationship, and rejects operations from users without a binding relationship; during user operations, the monitoring image is used to verify whether there is a binding relationship between the current user's user ID and the target self-service device, and to verify whether there is an association between the luggage on the target self-service device and the current user's user ID; if there is no binding relationship between the current user's user ID and the target self-service device, and / or no association between the luggage on the target self-service device and the current user's user ID, then the target self-service device is paused and an error message is generated.

[0006] By adopting the above technical solution, the system can intelligently identify and continuously track multiple users within the operating area based on monitoring images, establish a precise association between user identifiers and luggage, and achieve intelligent device allocation by combining the status information of self-service devices and user location relationships, thereby constructing a dynamic binding relationship between user identifiers and target self-service devices. The control strategy generated based on this binding relationship ensures that each target self-service device only responds to user operations with which it has a binding relationship, effectively preventing device contention and misoperation issues in multi-user environments. During user operations, the system uses a real-time dual verification mechanism to verify both the binding relationship between the current user's identifier and the target self-service device, and the association relationship between the luggage on the target self-service device and the current user's identifier. If either verification fails, the device is immediately paused and an error message is generated, thus achieving end-to-end security control. This solution significantly improves the security, accuracy, and operational efficiency of airport baggage check-in services in multi-user concurrent scenarios, effectively reducing security risks such as user error with devices and mismatches between luggage and user identities.

[0007] Secondly, this application provides an intelligent joint control system for airport baggage check-in based on multi-person identification. The system includes: a first acquisition module, a second acquisition module, a generation module, a verification module, and a judgment module; wherein... The first acquisition module is used to acquire monitoring images of the operating areas of multiple self-service devices; based on the monitoring images, identify and track multiple users within the operating areas, generate user identifiers for each user, and establish a correlation between the user identifiers and the luggage of each user; the second acquisition module is used to acquire the status information of each self-service device; combining the positional relationship of each user relative to each self-service device and the status information of each self-service device, assign a corresponding target self-service device to each user, and establish a binding relationship between the user identifiers and the corresponding target self-service devices; the generation module is used to generate control policies for each target self-service device based on the binding relationship. The control strategy includes: each target self-service device only responds to operations from users with which it is bound, and rejects operations from users without which it is not bound; the verification module is used to verify, during user operation, whether there is a binding relationship between the current user's user ID and the target self-service device, and whether there is an association between the luggage on the target self-service device and the current user's user ID, through the monitoring image; the judgment module is used to pause the target self-service device and generate an error message if there is no binding relationship between the current user's user ID and the target self-service device, and / or no association between the luggage on the target self-service device and the current user's user ID.

[0008] Thirdly, this application provides an electronic device that adopts the following technical solution: 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 a computer program of any of the above-mentioned intelligent joint control methods for airport baggage check-in based on multi-person identification.

[0009] Fourthly, this application provides a computer-readable storage medium that employs the following technical solution: storing a computer program capable of being loaded by a processor and executing any of the above-mentioned intelligent joint control methods for airport baggage check-in based on multi-person identification.

[0010] In summary, this application includes at least one of the following beneficial technical effects: The system can intelligently identify and continuously track multiple users within the operating area based on surveillance images, establishing a precise association between user identifiers and luggage. It then combines the status information of self-service devices and user location relationships to achieve intelligent device allocation, thereby constructing a dynamic binding relationship between user identifiers and target self-service devices. The control strategy generated based on this binding relationship ensures that each target self-service device only responds to user operations with which it has a binding relationship, effectively preventing device contention and misoperation issues in multi-user environments. During user operations, the system uses a real-time dual verification mechanism to verify both the binding relationship between the current user's identifier and the target self-service device, and the association relationship between the luggage on the target self-service device and the current user's identifier. If either verification fails, the device is immediately paused and an error message is generated, thus achieving end-to-end security control. This solution significantly improves the security, accuracy, and operational efficiency of airport baggage check-in services in multi-user concurrent scenarios, effectively reducing security risks such as user-operated devices errors and mismatches between luggage and user identities. Attached Figure Description

[0011] Figure 1 This is a flowchart illustrating an intelligent joint control method for airport baggage check-in based on multi-person identification, provided in an embodiment of this application. Figure 2 This is a logic block diagram provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an intelligent joint control system for airport baggage check-in based on multi-person identification provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0012] Explanation of reference numerals in the attached figures: 1000, electronic device; 1001, processor; 1002, communication bus; 1003, user interface; 1004, network interface; 1005, memory. Detailed Implementation

[0013] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0014] In the description of the embodiments in this application, words such as "illustrative," "for example," or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "illustrative," "for example," or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Rather, the use of words such as "illustrative," "for example," or "for example" is intended to present the relevant concepts in a specific manner.

[0015] Figure 1 This is a flowchart illustrating an intelligent joint control method for airport baggage check-in based on multi-person identification, provided in an embodiment of this application. Figure 1 As shown, the method includes S101-S105: S101: Acquire monitoring images of the operating areas of multiple self-service devices; based on the monitoring images, identify and track multiple users within the operating area, generate user identifiers for each user, and establish the association between each user's user identifier and each user's luggage.

[0016] The system first acquires real-time monitoring images through high-definition cameras deployed in the operating areas of each self-service baggage check-in machine. These images cover the area where users are active in front of the machines. The purpose of acquiring these images is to provide a visual data foundation for subsequent multi-person identification and baggage association, ensuring that the system can accurately identify and track all users and their luggage within the operating area, thereby avoiding identity confusion and baggage mismatch when multiple people use the self-service baggage check-in service simultaneously.

[0017] After receiving the monitored image, the system first processes it using a deep learning-based multi-object detection algorithm. This algorithm can simultaneously identify multiple human targets in the image. The multi-object detection algorithm extracts image features through a convolutional neural network and uses an object detection framework to locate the position coordinates and bounding box information of each user in the image. After detecting multiple users, the system extracts primary appearance feature information for each user. This primary appearance feature information includes biometric information and appearance attributes such as the user's height, body shape, clothing color, and facial features. Based on the extracted primary appearance feature information, the system uses a feature encoding algorithm to generate a unique user identifier for each user. The user identifier is a digital identity identifier calculated from feature vectors and is used to uniquely identify the user throughout the entire transport process.

[0018] To achieve continuous user tracking, the system employs a multi-target tracking algorithm combined with a motion prediction model. By analyzing changes in user position and motion trajectory between consecutive frames, it establishes consistency in user identity over time. The multi-target tracking algorithm predicts the user's position in the next frame based on a Kalman filter and uses a Hungarian algorithm for data association, ensuring that the system maintains the continuity and accuracy of user identification even if the user experiences brief occlusion or partially leaves the monitoring area.

[0019] While identifying and tracking users, the system detects and identifies luggage targets in the surveillance images. The system uses a specially trained luggage detection model to identify various types of luggage, including suitcases, backpacks, and handbags, and extracts secondary appearance feature information for each detected piece of luggage. This secondary appearance feature information covers visual attributes such as luggage size, color, shape, and surface texture; these features constitute a unique identifier feature vector for each piece of luggage.

[0020] The process of establishing the association between user identifiers and luggage is achieved by analyzing spatial and temporal relationships. The system continuously monitors the spatial relationship between each user and their surrounding luggage, specifically by calculating the Euclidean distance and relative positional changes between the user and the luggage to determine whether a particular piece of luggage consistently follows a specific user. A continuous association relationship refers to a relatively stable spatial distance and positional relationship between the luggage and the user within a certain time window, typically set at a distance threshold of within 2 meters and a duration exceeding 10 seconds. When the system detects a user carrying, dragging, or pushing luggage, it records this interaction and, combined with secondary appearance feature information, establishes an association data structure. This data structure stores the mapping relationship between the user identifier and the feature vector of their associated luggage in key-value pairs.

[0021] Based on the above embodiments, as an optional implementation, in S101, identifying and tracking multiple users within the operating area based on the monitoring image, generating user identifiers for each user, and establishing the association between each user's user identifier and their luggage specifically includes S11-S14: S11 performs multi-target detection on the monitoring image to identify multiple users within the operating area.

[0022] The system first performs a multi-object detection algorithm on the acquired surveillance images to identify multiple users within the operating area. Multi-object detection employs the YOLO algorithm framework based on deep learning, which can simultaneously detect multiple human targets in the image and generate bounding boxes and confidence scores for each detected user. The system filters false detections by setting an appropriate confidence threshold to ensure that the detected targets are indeed valid user objects. The advantage of multi-object detection lies in its ability to handle complex scenes where users occlude, overlap, and are densely distributed, providing accurate target localization for subsequent individual identification and tracking.

[0023] S12, extract the first appearance feature information of each user, generate the user identifier of each user based on the first appearance feature information, and track the movement trajectory of each user in the operating area.

[0024] The first set of appearance features includes visual features that can be used for identity differentiation, such as facial features, height and body shape, clothing color, and hairstyle outline. The system employs a feature extraction network to perform deep feature encoding on each detected user, generating a high-dimensional feature vector as the user's unique identifier, i.e., the user ID. The user ID not only includes static appearance features but also incorporates the user's behavioral patterns and movement characteristics. Through temporal analysis of multiple frames of images, a continuous movement trajectory of the user within the operating area is established. Movement trajectory tracking uses a Kalman filter algorithm to predict the user's next position and maintain tracking continuity, ensuring stable user tracking even under brief occlusion or image quality degradation.

[0025] S13, detect the luggage carried by each user and extract the second appearance feature information of each piece of luggage.

[0026] Baggage detection utilizes a specially trained baggage recognition model capable of identifying various types of baggage, including suitcases, handbags, and backpacks, while eliminating interference from other irrelevant objects. The system extracts secondary appearance feature information for each detected piece of baggage, including visual recognition elements such as size specifications, surface color distribution, shape outline, material texture, and visible brand logos. This secondary appearance feature information is enhanced with multi-angle sampling and illumination normalization to improve its robustness, ensuring accurate identification of the same piece of baggage under different viewing angles and lighting conditions.

[0027] S14. Combining the continuous spatial relationship between each user and their luggage, and the second appearance feature information, establish the association between each user's user identifier and their luggage.

[0028] A sustained spatial companionship relationship refers to a relatively fixed spatial distance and positional relationship between a user and specific luggage over time. This relationship is determined through continuous analysis of multiple frames of images. The system calculates the Euclidean distance and relative position angle between each user and all surrounding luggage, and identifies luggage objects that maintain a stable companionship relationship with the user through statistical analysis. The determination of a sustained companionship relationship considers the user's movement patterns and the luggage's following behavior. The system analyzes the luggage's response behavior when the user stops, turns, and moves to confirm that the luggage is indeed actively carried by the user rather than accidentally approaching.

[0029] S102, obtain the status information of each self-service device; combine the positional relationship of each user relative to each self-service device and the status information of each self-service device, assign the corresponding target self-service device to each user, and establish the binding relationship between the user identifier of each user and the corresponding target self-service device.

[0030] The system needs to implement an intelligent device allocation mechanism to optimize the efficiency of baggage handling services in multi-user environments and avoid problems such as user queuing and device usage conflicts. The core purpose of this step is to establish a one-to-one binding relationship between users and devices by acquiring real-time device status and user location information, ensuring that each user can obtain dedicated service devices, thereby improving overall service efficiency and eliminating operational chaos.

[0031] The system first establishes a communication connection with the internal control units of each self-service check-in device to obtain real-time status information. This status information includes key parameters such as the device's operating status, current service status, hardware health status, and availability status. The operating status reflects whether the device is working properly, including power status, network connection status, and the operation of core functional modules. The current service status indicates whether the device is providing service to users, specifically categorized into four types: idle, occupied, maintenance, and fault. Idle status indicates the device is not in use and can be immediately assigned to a new user; occupied status indicates the device is providing check-in service to a user; maintenance status indicates the device is undergoing system maintenance or cleaning; and fault status indicates the device has a hardware or software malfunction and cannot provide service normally. Hardware health status covers the working status of key components such as the weighing module, printing module, scanning module, and conveyor belt, while availability status comprehensively assesses whether the device has the capability to provide complete check-in service to users.

[0032] While acquiring device status information, the system analyzes the user tracking data established in step S101 to calculate the positional relationship of each user relative to each self-service device. This positional relationship is achieved through a visual positioning algorithm from the surveillance cameras. This algorithm converts pixel coordinates in the surveillance image into actual coordinates in physical space, thereby accurately calculating the straight-line distance between the user and each self-service device. The system uses the Euclidean distance formula to calculate spatial distance and considers the user's movement direction and speed to predict the user's movement intention and target device preference. Movement intention analysis is based on user behavior pattern recognition. By analyzing the user's movement trajectory, dwell time, and facing direction, it determines whether the user has a tendency to use a specific self-service device.

[0033] Based on a comprehensive analysis of status information and location relationships, the system executes an intelligent allocation algorithm to determine the corresponding target self-service device for each user. The allocation algorithm first filters out candidate self-service devices that are in an idle or allocable state from all available devices. An allocable state means that although the device may be performing some background tasks, it still has the ability to accept service requests from new users. During the filtering process, the system excludes devices that are in a faulty, maintenance, or hardware malfunction state, ensuring that all candidate devices can provide complete baggage handling services.

[0034] After candidate devices are identified, the system employs a distance-first allocation strategy, assigning each user the nearest candidate self-service device as their target device. The nearest-distance principle considers not only physical distance but also the walking path and expected time required for the user to reach the device, avoiding delays caused by obstacles or crowds. When multiple users are detected approaching the same candidate self-service device simultaneously, the system activates a conflict resolution mechanism, determining the primary service user based on preset priority rules. These preset priority rules comprehensively consider factors such as user arrival time, waiting time, membership level, and special needs, using a weighted scoring algorithm to calculate each user's priority score. Users arriving earlier receive higher time priority, users with longer waiting times receive compensatory priority, and users with premium memberships or special needs receive service priority.

[0035] The system will determine the user with the highest priority score as the primary service user and assign the corresponding candidate self-service device to that user as the target self-service device. For other users with lower priority, the system will automatically guide them to other available candidate self-service devices. The guidance process will be implemented through various methods such as on-screen prompts, voice announcements, and mobile application push notifications. The guidance information includes the location of the recommended device, the estimated waiting time, and the arrival route to help users quickly find the appropriate service device.

[0036] After device allocation is completed, the system establishes a binding relationship between each user's identifier and the corresponding target self-service device. This binding relationship is a temporary logical association, stored in a database as a record containing information such as user identifier, device identifier, binding time, and expected service duration. Once the binding relationship is established, the corresponding target self-service device enters a dedicated service mode, responding only to operation requests from users with whom it has a binding relationship. Simultaneously, the device displays partial user identification information on its screen for user confirmation. The system also activates a real-time monitoring mechanism for the binding relationships, continuously analyzing monitoring images to verify whether the bound user has arrived as expected and started using the device. If a bound user is detected as not arriving for an extended period or abandoning the device, the system automatically terminates the binding relationship and reopens the device for other users.

[0037] Based on the above embodiments, as an optional implementation, in S102, combining the positional relationship of each user relative to each self-service device and the status information of each self-service device, a corresponding target self-service device is assigned to each user, and the binding relationship between each user's user identifier and the corresponding target self-service device is established, specifically including S21-S24: S21, based on the status information of each self-service device, select candidate self-service devices that are in an idle or available state from multiple self-service devices.

[0038] The system first performs preliminary screening based on real-time status information of each self-service device, identifying candidate self-service devices available for allocation from a pool of options. An "idle" status means the device is not currently being used by any user and all functional modules are functioning normally, ready to provide service to new users immediately. An "allocable" status means the device, while possibly performing maintenance tasks or background processing, still has the ability to accept new user allocations and is expected to transition to service status within a short time. The system excludes devices in a faulty, maintenance-locked, or hardware-malfunctioning state, ensuring that all candidate self-service devices have full service capabilities. This status screening mechanism avoids assigning users to devices that are not functioning properly, thereby improving service success rates and user satisfaction.

[0039] S22, based on location relationships, assign the nearest candidate self-service device to each user as the target self-service device.

[0040] The system calculates the spatial distance between each user and all candidate self-service devices, and comprehensively considers the user's current location, direction of movement, and expected path to determine the optimal device allocation scheme. The closest proximity principle considers not only straight-line distance but also analyzes the user's actual walking path to the device, avoiding path obstructions caused by obstacles or crowd congestion. The system assigns each user the candidate self-service device with the closest distance and optimal path as the target self-service device. This allocation method minimizes user movement costs and waiting time.

[0041] S23, when multiple users are detected to be approaching the same candidate self-service device at the same time, the primary service user is determined according to the preset priority rules, the candidate self-service device is assigned to the primary service user as the target self-service device, and other users are guided to other candidate self-service devices.

[0042] The preset priority rules establish a comprehensive scoring mechanism based on multiple evaluation dimensions, including factors such as user arrival time, waiting time, membership level, and special needs. Users arriving earlier receive bonus points for time priority, users with longer waiting times receive bonus points for fairness compensation, premium members receive bonus points for service level, and users with special luggage or special needs receive bonus points for service priority. The system determines the primary service user—the user with the highest priority score—through weighted calculation and assigns the disputed candidate self-service device to this user. For other users who are not assigned a device, the system automatically guides them to the next closest candidate self-service device. The guidance process is achieved through display prompts and voice announcements, ensuring that users can quickly find an alternative device and obtain service.

[0043] S24, Establish the binding relationship between each user's user ID and the corresponding target self-service device.

[0044] The binding relationship is stored as a database record, containing key information such as user identifier, device identifier, binding establishment time, expected service duration, and binding status. Establishing a binding relationship triggers the corresponding device to enter dedicated service mode, displaying the user's identity verification information on the device interface and activating personalized service configuration. Simultaneously, the system initiates continuous monitoring of the binding relationship, verifying its validity by analyzing the user's actual behavior. If the user does not reach the designated device for an extended period or chooses to abandon the service, the system automatically terminates the binding relationship and reopens the device for other users.

[0045] S103, Based on the binding relationship, generate control policies for each target self-service device. The control policies include: each target self-service device only responds to the operations of users with which it has a binding relationship, and rejects the operations of users with which it does not have a binding relationship.

[0046] The system first generates a dedicated control policy for each target self-service device based on the binding relationship data. This control policy is a comprehensive control scheme encompassing user authentication rules, operation permission definitions, and exception handling mechanisms. Its core principle is to achieve a one-to-one dedicated service model between the device and the user. Each control policy includes parameters such as user identification information bound to a specific target self-service device, the user's physical feature vector, allowed operation types, and time windows. The system then distributes these control policies to the local control unit of the corresponding target self-service device via a secure communication protocol, enabling each device to possess independent identity recognition and access control capabilities.

[0047] The core mechanism of the control strategy is to establish a device-level user authentication system. This system ensures that each target self-service device only responds to operations from users with whom it has a binding relationship. In practice, each target self-service device deploys an identity recognition module in its user interface and sensor system. This module continuously monitors the identity of users approaching the device. When a user attempts to interact with the device, the device first captures a real-time image of the user through an integrated camera and extracts the user's appearance features, including facial features, height, body type, and clothing characteristics—biometric data. The device then compares the extracted feature information with the preset authorized user feature vectors in the control strategy in real time, using a feature similarity calculation algorithm to assess the matching degree between the current user and the bound user.

[0048] The authentication process employs a multi-layered feature matching mechanism to enhance accuracy and security. The system first performs coarse-grained overall appearance matching, initially filtering by comparing easily identifiable features such as height, body shape, and primary clothing colors. If the coarse-grained matching passes a preset similarity threshold, the system further performs fine-grained facial feature matching, using deep learning algorithms to analyze the user's facial geometry, key point locations, and texture features to calculate facial similarity to the authorized user. Only when both coarse-grained and fine-grained matching reach their respective confidence thresholds does the system recognize the current user and the bound user as the same person, allowing the user to proceed with subsequent operations.

[0049] For authorized users who pass verification, the target self-service device will activate all service functions, including the complete baggage check-in process such as baggage weighing, label printing, information entry, and baggage confirmation. The device interface will display personalized welcome messages and operation guidance, and provide customized service options based on the user's historical baggage check-in records and preferences. Simultaneously, the device will continuously monitor the user's actions to ensure the continuity and consistency of the process. If a change in user identity or multiple people operating simultaneously is detected during the operation, the device will immediately initiate an identity re-verification process.

[0050] Conversely, when a user unrelated to the target self-service device attempts to operate it, the control policy triggers a rejection mechanism. This mechanism first displays a user-friendly message on the device interface, informing the user that the device has been reserved by another user or is currently serving another user, while also providing location information and guidance for nearby available devices. If the unauthorized user continues to attempt forced operation, the device locks all critical functional modules, including touchscreen response, hardware button input, and sensor data acquisition, ensuring that device resources are not illegally occupied. The device will also explain the correct usage process to the user through voice prompts and on-screen displays, suggesting that the user request device allocation through normal channels or wait for the current user to complete their operation.

[0051] To prevent persistent interference from malicious users, the control strategy also includes a progressive security response mechanism. When the system detects multiple attempts by the same unauthorized user to access the device, it records the user's characteristics and escalates the security alert level. At the high security alert level, the device not only rejects unauthorized operations but also proactively sends an anomaly alarm to the central monitoring system, notifying security personnel to monitor the security situation in that area. Simultaneously, the system analyzes the unauthorized user's behavioral patterns to determine if there is a risk of malicious damage or fraud, and can initiate temporary area control measures if necessary.

[0052] The control strategy also considers flexible handling mechanisms for special circumstances. For example, when an authorized user needs to assist others in an emergency, or when multiple family members are handling baggage check-in procedures together, the system provides a temporary authorization function. Authorized users can apply for temporary authorization through the device interface after identity verification. The system will require the applicant to provide the authorized person's basic information and perform facial recognition, generating a temporary binding relationship with a limited time and scope of permissions. This flexible mechanism maintains security while fully considering the actual needs of users and the diversity of usage scenarios.

[0053] S104. During user operation, the system verifies whether there is a binding relationship between the current user's user ID and the target self-service device through monitoring images, and verifies whether there is an association between the luggage on the target self-service device and the current user's user ID.

[0054] Once a user begins operating the target self-service device, the system immediately initiates a continuous authentication and monitoring mechanism. This mechanism acquires real-time monitoring images through high-resolution cameras deployed in the operating area of ​​the target self-service device. These images cover the user's operating space in front of the device and the luggage placement area on the device surface. Unlike the initial identification in step S101, the monitoring image acquisition in step S104 is more precise and focused. The cameras employ a higher frame rate and clearer image quality to ensure that every subtle movement and facial expression change during the user's operation is captured, providing sufficient visual data support for accurate authentication.

[0055] When a user operates in front of the target self-service device, the system performs real-time user identification processing on the acquired monitoring images. The user identification process uses the same deep learning algorithm framework as step S101, but has been specifically optimized for the operational scenario. The system first locates the user's position in the image using a human detection algorithm and extracts the current user's appearance feature information. This appearance feature information includes multi-dimensional biometric and appearance attribute data such as the user's facial geometry, detailed features of the eyes and mouth, hairstyle outline, clothing style and color matching, etc. To improve the accuracy and robustness of identification, the system extracts user features from multiple angles and under different lighting conditions to establish a comprehensive feature vector for the current user.

[0056] Based on the extracted appearance features, the system executes a user identification algorithm to recognize the current user. This algorithm compares the current user's feature vector with the feature templates of all user identifiers stored in the system, using multiple metrics such as cosine similarity and Euclidean distance to calculate the degree of feature matching. The system sets a dynamic similarity threshold to adapt to different lighting conditions and changes in user posture, ensuring accurate identification even when the user's appearance changes slightly. When the similarity calculation result exceeds the preset threshold, the system determines the current user's identifier and records the confidence level and timestamp information.

[0057] After determining the current user's identifier, the system immediately executes the binding relationship verification process to check whether a valid binding relationship exists between the user identifier and the current target self-service device. Binding relationship verification is achieved by querying the binding relationship database established in step S102. The system retrieves binding records indexed by the current user identifier and verifies parameters such as the validity of the binding relationship, the time range, and the permission range. A valid binding relationship requires not only that the user identifier matches the device identifier, but also that the binding time is within the validity period, and that the user has the corresponding operation permissions. If the binding relationship verification fails, the system immediately triggers an exception handling process, suspending device operation and generating a security warning.

[0058] Parallel to user authentication is the process of verifying baggage association. The system identifies baggage currently being checked in by analyzing the surface and surrounding area of ​​the target self-service device in surveillance images. Baggage recognition employs a specially trained baggage detection model capable of accurately identifying various types, sizes, and colors of luggage and extracting detailed appearance features. These features include visual identification elements such as baggage dimensions, surface color distribution, texture patterns, brand logos, wear marks, and unique markings. The system combines these features to form a unique identifier feature vector for each piece of luggage.

[0059] The system matches and verifies the extracted baggage feature vectors against the user-baggage association database established in step S101 to confirm whether the baggage on the current device has a pre-established association with the user's identifier. The association verification uses a feature similarity matching algorithm, comparing multiple key feature dimensions of the baggage to determine the consistency of its identity. Since baggage may change angles or undergo slight deformation during handling, the system employs multi-view feature matching and a deformation tolerance mechanism to allow reasonable changes in the baggage's appearance within a certain range. Simultaneously, the system also verifies the spatial relationship between the baggage and the user to ensure that the baggage was indeed placed or operated by the current user.

[0060] To improve the accuracy and reliability of verification, the system implements a continuous verification mechanism, which involves continuously verifying the association between the user's identity and baggage throughout the entire process. Continuous verification is not a single, static check, but a dynamic, real-time process. The system periodically samples monitoring images and repeatedly executes the verification algorithm to ensure the consistency of the user's identity and baggage association throughout the entire check-in process. If any inconsistency in identity or abnormal baggage association is detected at any time, the system will immediately record the anomaly and initiate the corresponding processing procedure.

[0061] When the system detects a valid binding relationship between the user's identifier and the target self-service device, and a correct association between the baggage and the user's identifier, the verification process is successful, and the system allows the user to continue the baggage check-in process. Upon successful verification, the system will display a success message on the device interface and record the verification time and confidence level, providing reliable data support for subsequent operation traceability and liability determination. Simultaneously, the system will maintain high-frequency monitoring, continuously watching for any anomalies that may occur during the operation.

[0062] Based on the above embodiments, as an optional implementation, in S104, during user operation, verifying whether there is a binding relationship between the current user's user ID and the target self-service device, and verifying whether there is an association between the luggage on the target self-service device and the current user's user ID, specifically includes S41-S43: S41, acquire the monitoring image of the operating area of ​​the target self-service equipment, perform user identification on the monitoring image, and extract the appearance feature information of the current user.

[0063] The system acquires high-quality real-time monitoring images through dedicated surveillance cameras deployed in the operating area of ​​the target self-service equipment. The monitoring images of the operating area have higher resolution and more precise shooting angles, specifically optimized for user posture and facial features. The system executes user recognition algorithms on the acquired monitoring images, using a combination of human detection and facial recognition to locate the current user's position and posture. The user recognition process filters out background interference and irrelevant personnel, focusing on extracting information about the user directly interacting with the device. The system extracts the current user's appearance features, including facial geometry, height, body type, clothing features, and behavioral posture, among other multi-dimensional recognition elements. These features are processed by a feature extraction network to form a high-dimensional feature vector for identity verification.

[0064] S42, determine the current user's identifier based on the appearance feature information; verify whether there is a binding relationship between the current user's identifier and the target self-service device.

[0065] The system performs similarity matching between the current user's feature vector and all user identifiers stored in the database. A deep learning algorithm is used to calculate feature similarity and determine the current user's identity. The user identifier determination process considers factors such as lighting variations, angle deviations, and slight appearance changes, and dynamically adjusts for different recognition conditions by setting a similarity threshold. After determining the user identifier, the system immediately queries the binding relationship database to verify whether a valid binding relationship exists between the user identifier and the current target self-service device. Binding relationship verification not only checks the existence of the relationship but also verifies the validity of the binding time and the matching of the permission scope, ensuring that the current user is indeed authorized to use the device.

[0066] S43, extract the appearance feature information of the luggage on the target self-service device; based on the appearance feature information of the luggage, verify whether there is a correlation between the luggage and the user identifier of the current user.

[0067] The system identifies and locates currently processed baggage by analyzing objects on the surface and surrounding area of ​​the target self-service equipment in the surveillance images. Baggage recognition employs a specialized object detection algorithm that accurately distinguishes baggage from other items and extracts detailed appearance features. These features include visual recognition elements such as size specifications, color distribution, surface texture, shape contour, and visible markings. These features are comprehensively processed through multi-angle sampling and feature fusion techniques to form a unique identifier for the baggage. The system then matches and verifies the extracted baggage features against the user-baggage association database established in step S101, using feature similarity calculations to determine whether the baggage has a pre-established association with the current user's identifier.

[0068] The verification process employs parallel processing and cross-validation to improve accuracy and reliability. User authentication and baggage association verification occur simultaneously, and the system combines the results of both verifications to make a final security judgment. If user authentication succeeds but baggage association verification fails, or vice versa, the system will determine this as an abnormal state and initiate the corresponding processing procedure. Only when both verifications succeed, does the system deem the current operation safe and compliant, allowing the user to continue with the baggage check-in process.

[0069] S105, if there is no binding relationship between the current user's user ID and the target self-service device, and / or there is no association between the luggage on the target self-service device and the current user's user ID, then suspend the target self-service device and generate an error message.

[0070] Initiate the anomaly detection process immediately. Missing binding relationships can stem from various reasons, including user identification errors, expired binding relationships, malicious user impersonation, and system data synchronization anomalies. Regardless of the specific cause, the system must handle the anomaly according to unified security standards, prioritizing system security over user convenience. The system will first perform secondary verification of the binding relationship by querying backup databases and cached records to confirm its true status, ruling out false positives caused by network latency or data transmission errors.

[0071] In parallel, the same anomaly handling mechanism is triggered when the system detects that there is no expected association between the baggage on the target self-service device and the current user's identifier. Abnormal baggage associations typically indicate security incidents such as baggage mismatch, baggage substitution, or malicious operation. The lack of baggage associations is more serious than abnormal user identities because it directly involves the security of physical assets and the protection of passenger property. The system performs deep feature analysis on the detected baggage, comprehensively comparing it with all known baggage records in the database to attempt to identify the true ownership of the baggage, while also analyzing the rationality of the baggage's current location and the continuity of its time sequence.

[0072] Based on the anomaly detection results, the system immediately executes an emergency suspension operation on the target self-service device. Device suspension is a multi-layered security measure. First, the user interface is locked, with all touchscreen input, physical button response, and voice interaction immediately ceasing. Next, the system suspends the device's core functional modules, including critical hardware components such as the weighing system, label printer, barcode scanner, and conveyor belt, ensuring that any operation that might affect the baggage handling process cannot continue. The device suspension operation employs a tiered locking mechanism, determining the scope and depth of the lock based on the severity of the anomaly. Minor authentication anomalies may only lock the user interface, while severe security threats require a complete disabling of all device functions.

[0073] While suspending equipment operation, the system generates detailed anomaly alerts to all relevant parties. This anomaly alert is a multi-channel, multi-level information delivery system. First, it displays user-friendly, understandable information on the target self-service device's screen, informing the user that an operational anomaly has been detected and manual assistance is required, while also providing contact information for staff and temporary solutions. The device also issues anomaly alerts via a voice broadcast system, ensuring that visually impaired users or those not paying attention to the screen display receive timely information. The content of the anomaly alerts is carefully designed to clearly explain the nature of the problem while avoiding causing excessive panic or unnecessary confusion for the user.

[0074] In addition to user-facing alerts, the system also sends real-time anomaly alarms to the central monitoring center. These alarms include detailed event descriptions, anomaly type classifications, involved user information, device status snapshots, and handling suggestions, helping monitoring personnel quickly understand the situation and take appropriate countermeasures. Alarm information uses a standardized format and coding system for automated event analysis and statistics. The system also sets different alarm levels based on the severity of the anomaly; for high-level anomalies that may involve security threats, the system directly sends emergency notifications to security departments and management personnel.

[0075] To facilitate problem diagnosis and resolution, the system automatically saves complete on-site data at the moment the anomaly occurred. This data includes surveillance video recordings before and after the anomaly, user operation logs, equipment status records, and relevant database query results. This data is organized and stored using timestamps as an index, forming a complete event archive. The system also performs preliminary automated analysis of the anomaly, identifying possible causes and generating a diagnostic report, providing valuable reference information for subsequent manual processing.

[0076] During anomaly handling, the system also activates a preventative monitoring mechanism for adjacent devices. When a target self-service device malfunctions, the system automatically upgrades the security monitoring level of surrounding devices, strengthening the monitoring of user behavior and device status in adjacent areas to prevent the spread or chain reaction of the anomaly. Preventative monitoring includes measures such as increasing image acquisition frequency, lowering the fault tolerance threshold for authentication, and enabling additional security sensors to ensure that the security of the entire check-in area is not affected by a single point of failure.

[0077] The system also considers user experience optimization during anomaly handling, using an intelligent guidance mechanism to help affected users obtain alternative services. When a user is unable to continue using their current device due to an anomaly, the system automatically recommends the nearest available device and provides detailed route guidance and appointment services. For legitimate users who have been misjudged by the system, a manual verification channel is provided, allowing staff intervention to quickly resolve the issue and restore normal service.

[0078] The method also includes: when it is detected that the target user is authenticated by boarding pass or QR code, the user identifier of the target user is bound and updated with the real identity information of the target user.

[0079] Throughout the operation of the intelligent baggage check-in system, a mechanism for binding and updating user identifiers with real identity information is also required. This is a crucial step in associating anonymized visual recognition results with specific passenger identity information. The core purpose of this mechanism is to convert user identifiers generated based on physical characteristics into legally valid and traceable real identity records, ensuring that the baggage check-in service not only achieves user differentiation and equipment allocation at the technical level, but also meets the actual needs of civil aviation safety management and passenger services at the business level.

[0080] When a target user performs a formal identity verification operation at a self-service check-in device, the system detects this crucial action and initiates the identity binding process. Identity verification is typically achieved by scanning the barcode or QR code on the boarding pass, or possibly by identifying the user through an electronic boarding pass they actively present. The boarding pass contains the passenger's complete and authentic identity information, including officially certified personal data such as name, ID number, flight information, seat number, and special service requests. This information constitutes the passenger's unique identifier and service basis within the civil aviation system. QR code verification retrieves the same identity data by parsing the encoded information, ensuring the accuracy and completeness of the information.

[0081] The system reads identity information from boarding passes or QR codes using an integrated scanning module, and then formats and verifies the validity of the data. Validity verification includes checking the authenticity of flight information, verifying the correct format of the ID number, and confirming the validity and usage status of the boarding pass, among other data checks. The system communicates in real-time with the airport's central database to verify that the read identity information matches the records in the flight management system, ensuring that forged or expired identity information is not accepted by the system.

[0082] After verifying the authenticity and validity of the identity information, the system performs a binding update operation between the user identifier and the real identity information. This process involves associating and mapping the anonymous user identifier generated based on appearance features in step S101 with the specific personal identity information obtained from the boarding pass. The system creates or updates an identity binding record in the database, which contains key fields such as the user identifier's feature vector, the corresponding real name, ID card number, flight information, and binding timestamp. The binding update is not a simple data replacement, but rather, while maintaining the original user identifier's technical characteristics, it adds an associated reference to the real identity information, forming a dual identification system of technical recognition and business identity.

[0083] The binding update process also triggers a retrospective identity verification of the user's historical operation records. The system retrieves all operation records, device allocation history, and baggage association information of the user identifier in the current session, associating these originally anonymized technical records with specific passenger identities to form a complete personal service profile. This retrospective verification ensures that all actions taken by the user from the moment they enter the operating area can be traced back to a specific personal identity, providing complete data support for subsequent liability determination and service quality assessment.

[0084] Once identity verification is complete, the system updates relevant security policies and service configurations. Based on the passenger's real identity information, the system can obtain personalized information such as membership level, special service needs, baggage allowance, and security level, thereby providing more accurate and personalized baggage handling services. For example, for premium members, the system may offer more lenient baggage weight tolerance or priority handling services, while for passengers with special security markings, the system may initiate additional security verification procedures. This personalized service configuration, based on the reliability of the real identity information, ensures the fairness and accuracy of service differentiation.

[0085] The binding and update mechanism also considers data security and privacy protection requirements. The system employs separate storage and encrypted transmission to protect passengers' sensitive personal information, ensuring physical isolation between physical appearance data and identity information data to prevent privacy risks caused by data leaks. Simultaneously, the system records all operations involving access to and modification of real identity information, establishing a complete data access audit trail to meet compliance requirements of data protection regulations.

[0086] By implementing this identity binding and update mechanism, the system successfully combines technical identification capabilities with business identity management needs, achieving a seamless transition from anonymized user tracking to real-name service provision. This mechanism not only enhances the personalization and security management capabilities of baggage handling services but also provides more accurate and reliable data support for airport operations management. The implementation of identity binding transforms the entire intelligent baggage handling system from a purely technical tool into an intelligent service platform with a complete business loop, simultaneously meeting the dual needs of technological innovation and business operations.

[0087] Based on the above embodiments, as an optional implementation method, the method further includes S61-S64: S61, Statistics on the usage frequency, average check-in time, and number of abnormal events for each self-service device.

[0088] The system establishes a comprehensive statistical system for equipment operation data, continuously collecting key performance indicators for each self-service device. Usage frequency refers to the ratio of the number of times a device is used by users within a specific time period to its total available time, reflecting the device's utilization rate. Average check-in time is the average time required for all users to complete the entire check-in process on this device, reflecting the device's service efficiency and the smoothness of user operation. The number of abnormal events tracks the frequency of events affecting normal service, such as equipment malfunctions, user errors, system errors, and equipment maintenance. Through real-time data collection and regular statistical analysis, the system establishes detailed performance profiles for each device, providing a reliable quantitative basis for subsequent efficiency assessments and optimization decisions.

[0089] S62 uses the usage frequency as the first parameter, the reciprocal of the average check-in time as the second parameter, and the reciprocal of the number of abnormal events as the third parameter. The first, second, and third parameters are weighted and summed to generate the operating efficiency value of each self-service device.

[0090] Usage frequency is the first parameter, reflecting the device's activity level; higher frequency indicates greater user preference and system trust. The reciprocal of average shipping time is the second parameter, converting time cost into an efficiency indicator; shorter shipping times correspond to higher efficiency values. The reciprocal of the number of abnormal events is the third parameter, reflecting the device's stability and reliability; fewer abnormal events correspond to higher stability scores. The system performs a weighted summation of these three parameters, with weighting coefficients adjusted based on business needs and historical experience. Typically, efficiency has the highest weight, followed by stability, and usage frequency has a relatively lower weight. The operational efficiency value is a comprehensive scoring indicator that fully reflects the device's service capabilities, operational stability, and user acceptance across multiple dimensions.

[0091] S63, when the operating efficiency value of an abnormal self-service device is lower than a preset threshold, adjust the allocation weight of the abnormal self-service device to reduce the probability of assigning users to the abnormal self-service device.

[0092] When the operating efficiency value of an abnormal self-service device is detected to be lower than a preset threshold, the system determines that the device has performance or stability issues and needs to have its priority reduced in the allocation decision. Allocation weight adjustment is achieved by modifying the weight parameters in the device selection algorithm, lowering the weight coefficient of the abnormal device, thereby reducing the probability of a user being assigned to that device. This adjustment is not a simple device disabling, but a gradual deweighting based on efficiency assessment, allowing the device to continue providing services under low load conditions, while providing a buffer for device maintenance and performance recovery. The weight adjustment mechanism enables the system to gradually optimize resource allocation and improve overall service quality while ensuring service continuity.

[0093] S64, based on the distribution density of users in the operating area and the operating efficiency of each self-service device, predicts the load status of each self-service device within a preset time period after the current moment, and generates scheduling suggestions for each self-service device based on the load status.

[0094] The system analyzes the distribution density of users within the operating area, including the current number of users present, the arrival frequency of new users, and the expected user growth trend. Combining the operational efficiency values ​​of each self-service device, the system employs time-series forecasting algorithms and machine learning models to predict the load status of each device within a preset time period. Load status prediction considers multiple variables such as user behavior patterns, flight schedules, historical traffic data, and external factors, providing relatively accurate short-term load prediction results. Based on the predicted load status, the system generates targeted scheduling suggestions, including recommendations to activate backup devices, redirect some users to low-load devices, and schedule device maintenance windows. These scheduling suggestions are provided to system administrators and the automatic scheduling module in the form of decision support information, supporting both manual decision-making and automatic execution modes.

[0095] Based on the above embodiments, as an optional implementation, in S64, the load status of each self-service device within a preset time period after the current moment is predicted according to the distribution density of users in the operating area and the operating efficiency of each self-service device, and the scheduling suggestions for each self-service device are generated according to the load status, specifically including S641-S644: S641, Calculate the user distribution density in each area of ​​the operation area and determine the number of users waiting to be served in the corresponding area of ​​each self-service device.

[0096] The system establishes a user distribution density statistical mechanism based on spatial partitioning. The operating area is divided into multiple corresponding service sub-areas, with each self-service device responsible for serving users within its corresponding area. The system analyzes real-time monitoring images and user location data to statistically determine the current number and distribution of users in each area. The number of users awaiting service includes not only those already in the queue but also those moving towards the area and potential users expected to arrive within a short time. The system employs a dynamic statistical method, comprehensively considering factors such as user movement trajectories, dwell time, and behavioral intentions to accurately identify the number of valid users who truly require shipping services. This regionalized statistical approach provides an accurate data foundation for subsequent load calculations, ensuring that the prediction results reflect the actual distribution of service demand.

[0097] S642, based on the operating efficiency value of each self-service device and the number of users waiting to be served, calculate the number of users expected to complete the shipping service for each self-service device within a preset time period.

[0098] The system combines the operational efficiency values ​​and current status of each self-service device to calculate the maximum number of users each device can serve within a preset time period. Operational efficiency directly impacts service processing speed per unit time; devices with higher efficiency values ​​can serve more users in the same amount of time. The calculation process also considers factors such as the device's current load status, expected maintenance time, and potential abnormal interruptions, employing a conservative estimation method to ensure the reliability of the prediction results. The estimated number of users completing the shipping service is a dynamically adjusted forecast, continuously updated based on real-time changes in device performance and environmental factors, providing an accurate reference for service capacity assessment based on load status.

[0099] S643, based on the difference between the number of users waiting to be served and the number of users expected to complete the shipping service, predicts the load status of each self-service device within a preset time period after the current moment.

[0100] The difference between the number of users awaiting service and the expected number of users completing shipment services reflects the supply-demand balance. A positive difference indicates that demand exceeds supply, and the equipment may face overload pressure. A negative difference indicates sufficient supply, and the equipment is operating at a relatively relaxed level. Based on this difference calculation and a preset load threshold range, the system classifies the load status of each device into three levels: light load, normal, and overload. Load status prediction is not a static classification result, but a dynamic prediction that includes a time dimension. It can display the trend of load status changes and key time nodes within a preset time period, providing time window guidance information for scheduling decisions.

[0101] S644, when the target self-service device is in an overloaded state, generate a scheduling suggestion to guide the users waiting to be served in the area corresponding to the target self-service device to the self-service device in a lightly loaded state.

[0102] An overload status means that the number of users waiting to be served in the area corresponding to the device exceeds the device's service capacity. Without intervention, this will lead to longer user wait times and decreased service quality. The system will automatically search for other self-service devices currently under light load, which have sufficient service capacity and shorter wait times. The scheduling suggestion includes detailed information such as the number of users to be transferred, the identifier of the target device, the expected improvement in wait time, and the suggested redirection path. The system will prioritize underloaded devices that are reasonably located and have high operating efficiency as redirection targets, ensuring that users receive a better service experience after the transfer, rather than simply resolving the overload issue.

[0103] The guidance suggestions are implemented in several ways, including displaying guidance information in the overloaded device area, reminding users to select other devices via voice prompts, and pushing alternative device suggestions in the mobile application. The system will also dynamically adjust the allocation strategy for new users, temporarily reducing the allocation priority of overloaded devices and prioritizing the allocation of new users to lightly loaded devices, thereby alleviating overload pressure at its source.

[0104] Figure 2 This is a logic block diagram provided in an embodiment of this application, such as... Figure 2As shown, firstly, the system acquires surveillance images through a visual recognition module, generating a unique user identifier while identifying and tracking the user, and establishing initial association data between the user and their luggage. Next, the system comprehensively considers the real-time status information of each self-service device and the user's spatial position relative to the device, intelligently assigning a target device to the user, thus establishing a unique binding relationship between "user identifier and target device." Based on this binding relationship, the system further generates an exclusive control strategy, limiting the target device to responding only to the operation commands of specific users with whom it has a binding relationship. In subsequent user operations, the system continuously uses surveillance images for real-time dual verification (as shown by the dotted line on the left, calling the initial association data as a comparison reference), verifying both whether the current operator is a bound user and whether the luggage on the conveyor belt is the luggage associated with that user. Once the system detects that there is no binding relationship between the current user and the device, or no association between the luggage on the device and the current user identifier, the process immediately enters the anomaly handling stage, triggering the suspension of device operation and generating an anomaly prompt, thereby ensuring the safety and accuracy of the self-service baggage check-in process.

[0105] Based on the above method, this application also discloses an intelligent joint control system for airport baggage check-in based on multi-person identification, such as... Figure 3 As shown, Figure 3 This is a schematic diagram of the structure of an intelligent joint control system for airport baggage check-in based on multi-person identification, provided in an embodiment of this application. The system includes: a first acquisition module, a second acquisition module, a generation module, a verification module, and a judgment module; wherein, The first acquisition module is used to acquire monitoring images of the operating areas of multiple self-service devices; based on the monitoring images, it identifies and tracks multiple users within the operating area, generates user identifiers for each user, and establishes a correlation between each user's user identifier and their luggage; the second acquisition module is used to acquire the status information of each self-service device; combining the positional relationship of each user relative to each self-service device and the status information of each self-service device, it assigns a corresponding target self-service device to each user and establishes a binding relationship between each user's user identifier and the corresponding target self-service device; the generation module is used to generate control policies for each target self-service device based on the binding relationship, the control policies including: each target self-service device only responds to the operations of users with which it has a binding relationship, and rejects the operations of users with which it does not have a binding relationship; the verification module is used to verify, during user operation, whether there is a binding relationship between the current user's user identifier and the target self-service device, and whether there is a correlation between the luggage on the target self-service device and the current user's user identifier; the judgment module is used to pause the target self-service device and generate an error message if there is no binding relationship between the current user's user identifier and the target self-service device, and / or no correlation between the luggage on the target self-service device and the current user's user identifier.

[0106] It should be noted that the system provided in the above embodiments is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be 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 embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0107] Please see Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.

[0108] The communication bus 1002 is used to realize the connection and communication between these components.

[0109] The user interface 1003 may include a display screen and a camera. Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0110] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0111] The processor 1001 may include one or more processing cores. The processor 1001 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and by calling data stored in the memory 1005. Optionally, the processor 1001 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 1001 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content to be displayed on the screen; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 1001 and may be implemented as a separate chip.

[0112] The memory 1005 may include random access memory (RAM) or read-only memory. Optionally, the memory 1005 may include a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 1005 may also be at least one storage device located remotely from the aforementioned processor 1001. Figure 4 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for an intelligent joint control method for airport baggage check-in based on multi-person identification.

[0113] exist Figure 4In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and to obtain the user input data; while the processor 1001 can be used to call an application program stored in the memory 1005 that is a smart joint control method for airport baggage check-in based on multi-person recognition. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.

[0114] An electronic device readable storage medium stores instructions that, when executed by one or more processors, cause the electronic device to perform one or more of the methods described in the above embodiments.

[0115] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0116] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0117] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only 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 couplings, direct couplings, or communication connections may be through some service interfaces; indirect couplings or communication connections between devices or units may be electrical or other forms.

[0118] 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 network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0119] Furthermore, the functional units in the various embodiments of this application 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.

[0120] 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 device (CMD). Based on this understanding, the technical solution of this application, 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 memory 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 this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0121] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Other embodiments of this disclosure will be readily apparent to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described herein. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A method for intelligent joint control of airport baggage check-in based on multi-person recognition, characterized in that, The method includes: Acquire monitoring images of the operating areas of multiple self-service devices; based on the monitoring images, identify and track multiple users within the operating areas, generate user identifiers for each user, and establish a correlation between the user identifiers of each user and the luggage of each user; Obtain the status information of each self-service device; combine the positional relationship of each user relative to each self-service device and the status information of each self-service device, assign a corresponding target self-service device to each user, and establish a binding relationship between the user identifier of each user and the corresponding target self-service device; Based on the binding relationship, a control policy is generated for each of the target self-service devices. The control policy includes: each target self-service device only responds to the operations of users with which it has a binding relationship, and rejects the operations of users without which it has no binding relationship. During user operation, the monitoring images are used to verify whether there is a binding relationship between the current user's user ID and the target self-service device, and to verify whether there is an association between the luggage on the target self-service device and the current user's user ID. If there is no binding relationship between the current user's user ID and the target self-service device, and / or there is no association between the luggage on the target self-service device and the current user's user ID, then the target self-service device will be paused and an error message will be generated.

2. The intelligent joint control method for airport baggage check-in based on multi-person identification as described in claim 1, characterized in that, The step of identifying and tracking multiple users within the operating area based on the surveillance images, generating user identifiers for each user, and establishing a correlation between each user's user identifier and their luggage includes: Multi-target detection is performed on the monitoring image to identify multiple users within the operating area; Extract the first appearance feature information of each user, generate the user identifier of each user based on the first appearance feature information, and track the movement trajectory of each user in the operation area; Detect the luggage carried by each user and extract the second appearance feature information of each piece of luggage; By combining the continuous spatial association between each user and their luggage, and the second appearance feature information, an association between each user's user identifier and their luggage is established.

3. The intelligent joint control method for airport baggage check-in based on multi-person identification as described in claim 1, characterized in that, The method further includes: When a target user is detected to have authenticated their identity via boarding pass or QR code, the user identifier of the target user is bound and updated with the target user's real identity information.

4. The intelligent joint control method for airport baggage check-in based on multi-person identification according to claim 1, characterized in that, The step of combining the location relationship of each user relative to each self-service device and the status information of each self-service device to assign a corresponding target self-service device to each user and establish a binding relationship between the user identifier of each user and the corresponding target self-service device includes: Based on the status information of each self-service device, candidate self-service devices that are in an idle or available state are selected from the multiple self-service devices. Based on the location relationship, the nearest candidate self-service device is assigned to each user as the target self-service device; When multiple users are detected approaching the same candidate self-service device at the same time, the primary service user is determined according to the preset priority rules, the candidate self-service device is assigned to the primary service user as the target self-service device, and other users are guided to other candidate self-service devices. Establish a binding relationship between the user identifier of each user and the corresponding target self-service device.

5. The intelligent joint control method for airport baggage check-in based on multi-person identification according to claim 1, characterized in that, During user operation, the process of verifying, through the monitoring image, whether there is a binding relationship between the current user's user ID and the target self-service device, and whether there is an association between the luggage on the target self-service device and the current user's user ID, includes: Acquire monitoring images of the operating area of ​​the target self-service device, perform user identification on the monitoring images, and extract the appearance feature information of the current user; Based on the appearance feature information, determine the user identifier of the current user; verify whether there is a binding relationship between the user identifier of the current user and the target self-service device; Extract the appearance feature information of the luggage on the target self-service device; based on the appearance feature information of the luggage, verify whether there is a correlation between the luggage and the user identifier of the current user.

6. The intelligent joint control method for airport baggage check-in based on multi-person identification according to claim 1, characterized in that, The method further includes: Statistics were compiled on the usage frequency, average check-in time, and number of abnormal events for each of the aforementioned self-service devices. Using the usage frequency as the first parameter, the reciprocal of the average baggage handling time as the second parameter, and the reciprocal of the number of abnormal events as the third parameter, a weighted sum is performed on the first parameter, the second parameter, and the third parameter to generate the operating efficiency value of each self-service device. When the operating efficiency value of an abnormal self-service device is lower than a preset threshold, the allocation weight of the abnormal self-service device is adjusted to reduce the probability of assigning users to the abnormal self-service device. Based on the distribution density of users within the operating area and the operating efficiency of each self-service device, the load status of each self-service device within a preset time period after the current moment is predicted, and scheduling suggestions for each self-service device are generated based on the load status.

7. The intelligent joint control method for airport baggage check-in based on multi-person identification according to claim 6, characterized in that, The step of predicting the load status of each self-service device within a preset time period after the current moment based on the user distribution density and operating efficiency of each self-service device within the operating area, and generating scheduling suggestions for each self-service device based on the load status, includes: Statistically analyze the user distribution density of each area within the operation area to determine the number of users waiting to be served in the area corresponding to each self-service device; Based on the operating efficiency value of each self-service device and the number of users waiting to be served, calculate the number of users expected to complete the shipping service for each self-service device within a preset time period. Based on the difference between the number of users waiting to be served and the number of users expected to complete the shipping service, the load status of each self-service device in a preset time period after the current moment is predicted; When a target self-service device is overloaded, a scheduling suggestion is generated to redirect users waiting to be served in the area corresponding to the target self-service device to a self-service device with a light load.

8. A multi-person recognition-based intelligent joint control system for airport baggage check-in, characterized in that, The system includes: a first acquisition module, a second acquisition module, a generation module, a verification module, and a judgment module; wherein... The first acquisition module is used to acquire monitoring images of the operating areas of multiple self-service devices; based on the monitoring images, identify and track multiple users in the operating area, generate user identifiers for each user, and establish an association between the user identifiers of each user and the luggage of each user; The second acquisition module is used to acquire the status information of each self-service device; combine the positional relationship of each user relative to each self-service device and the status information of each self-service device, assign a corresponding target self-service device to each user, and establish a binding relationship between the user identifier of each user and the corresponding target self-service device; The generation module is used to generate control policies for each of the target self-service devices based on the binding relationship. The control policies include: each target self-service device only responds to the operations of users with which it has a binding relationship, and rejects the operations of users without which it has a binding relationship. The verification module is used to verify, during user operation, whether there is a binding relationship between the current user's user identifier and the target self-service device through the monitoring image, and whether there is an association between the luggage on the target self-service device and the current user's user identifier. The judgment module is used to pause the target self-service device and generate an error message if there is no binding relationship between the current user's user ID and the target self-service device, and / or there is no association between the luggage on the target self-service device and the current user's user ID.

9. An electronic device, characterized in that, The device 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 to cause the electronic device to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer program is stored that can be loaded by a processor and executed as described in any one of claims 1-7.

Images