Data processing method, device and equipment in airport security guidance, medium and product

Abstract

The application provides an airport security check guidance data processing method, device, equipment, medium and product, and relates to the technical field of data processing. The method comprises the following steps: acquiring multi-source real-time data of each security check channel, determining a queuing state by using a preset analysis algorithm, predicting an estimated security check time length in a future preset time period, and then matching and determining a target security check channel and pushing corresponding security check recommendation information to a passenger mobile terminal. The method avoids the situation of relying on manual observation and experience judgment, single data collection means, lag and inability to accurately perceive the channel operation state in real time, solves the problem of excessive congestion of part of the channel and idling of part of the channel resources caused by passengers blindly following the crowd or selecting the security check channel according to experience, reduces the queuing waiting time of the passengers, improves the overall utilization rate of the civil aviation airport security check channel resources and the airport operation management efficiency, and optimizes the passenger airport travel service experience.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to data processing methods, devices, equipment, media and products for airport security check guidance. Background Technology

[0002] Currently, in the existing civil aviation airport security check system, excessively long passenger waiting times and uneven utilization of channel resources have become significant issues affecting airport operational efficiency and passenger experience.

[0003] Current security checkpoint management relies primarily on manual observation and experience, lacking real-time and accurate monitoring of checkpoint operations. Passengers often blindly follow crowds or rely on experience when choosing a checkpoint, lacking personalized intelligent guidance. This leads to overcrowding in some checkpoints while other checkpoints remain unused, increasing overall passenger wait times and reducing the efficiency of security resource utilization. Consequently, this impacts airport operational efficiency and passenger service experience. Summary of the Invention

[0004] This application provides a data processing method, apparatus, equipment, medium, and product for airport security check guidance, in order to solve the problems existing in the prior art.

[0005] Firstly, this application provides a data processing method for airport security check guidance, including:

[0006] Acquire multi-source real-time data from each security checkpoint;

[0007] Based on the multi-source real-time data, the queuing status of each security checkpoint is determined using a preset analysis algorithm;

[0008] Based on the queuing status, the estimated security check time for each security checkpoint is predicted within a preset time period in the future;

[0009] Based on the estimated security check times, the target security check lanes are determined;

[0010] Send security check recommendation information to the passenger's mobile terminal; wherein the security check recommendation information includes the target security check lane.

[0011] In one possible design, the multi-source real-time data includes video surveillance data and facial recognition data, and the queuing status includes the number of people in the queue and the passage time.

[0012] The step of determining the queuing status of each security checkpoint based on the multi-source real-time data and using a preset identification and analysis algorithm includes:

[0013] Image analysis is performed on the video surveillance data to identify passenger gathering areas at the entrance of the security checkpoint;

[0014] Within the passenger gathering area, the number of passengers is determined by a face detection algorithm, and this number is used as the queue size.

[0015] Based on the facial recognition data, the time points when passengers enter and leave the security checkpoint are recorded;

[0016] The time interval between adjacent passengers passing through the security checkpoint is determined based on the time point, and the time interval is used as the passage time.

[0017] In one possible design, the queuing status includes the number of people in the queue and the passage time;

[0018] The prediction of the estimated security check time for each security checkpoint within a preset time period based on the queuing status includes:

[0019] The number of people in the queue, the passage time, historical passenger flow data, flight schedule information and weather factors are used as input parameters and input into the preset prediction model to output the expected queue length for each security checkpoint.

[0020] Based on the estimated queue length and the passage time, the estimated waiting time for each security checkpoint is determined.

[0021] The estimated security check time for each security checkpoint is determined based on the passenger's current location information, flight departure time, estimated queue length, and estimated waiting time.

[0022] In one possible design, determining the estimated security check time for each security checkpoint based on the passenger's current location information, flight departure time, estimated queue length, and estimated waiting time includes:

[0023] Based on the passenger's current location information, calculate the estimated travel time for the passenger to reach each security checkpoint;

[0024] The estimated security check time for each security checkpoint is obtained based on the estimated travel time, the estimated waiting time, and the security check processing time.

[0025] In one possible design, determining the target security check lane based on each of the estimated security check times includes:

[0026] Security check channels whose estimated security check time is less than a preset time threshold are selected as candidate security check channels;

[0027] Calculate the risk value of missing the flight for each of the candidate security checkpoints based on the passenger's flight departure time;

[0028] The candidate security checkpoint corresponding to the lowest value among the various missed flight risk values ​​is determined as the target security checkpoint.

[0029] One possible design also includes:

[0030] Monitor the real-time queue length at each security checkpoint;

[0031] If the number of people queuing in any security checkpoint exceeds a preset threshold, a channel scheduling instruction is generated.

[0032] The channel scheduling command is sent to the staff terminal.

[0033] Secondly, this application provides a data processing device for airport security check guidance, comprising:

[0034] The acquisition module is used to acquire multi-source real-time data from each security checkpoint.

[0035] The queuing status analysis module is used to determine the queuing status of each security checkpoint based on the multi-source real-time data and using a preset analysis algorithm.

[0036] The queue prediction module is used to predict the estimated security check time of each security check channel within a preset time period based on the queue status.

[0037] The security check lane determination module is used to determine the target security check lane based on the estimated security check time.

[0038] The information sending module is used to send security check recommendation information to passengers' mobile terminals; wherein, the security check recommendation information includes the target security check channel.

[0039] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0040] The memory stores computer-executed instructions;

[0041] The processor executes computer execution instructions stored in the memory to implement the method as described in any of the first aspects.

[0042] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any of the first aspects.

[0043] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the first aspects.

[0044] The data processing method, device, equipment, medium, and product for airport security check guidance provided in this application acquire multi-source real-time data from each security checkpoint, use a preset analysis algorithm to determine the queuing status and predict the expected security check time within a preset time period, and then match and determine the target security checkpoint and push the corresponding security check recommendation information to the passenger's mobile terminal. This avoids the situation of relying on manual observation and experience judgment, and the single and lagging data collection methods that cannot accurately perceive the channel operation status in real time. It solves the problem of some channels being overcrowded and some channels being idle due to passengers blindly following the crowd or choosing security checkpoints based on experience. It balances the resource load and scheduling allocation of each security checkpoint, reduces the passenger's security check waiting time, improves the overall utilization rate of civil aviation airport security checkpoint resources and airport operation and management efficiency, and optimizes the passenger's airport travel service experience. Attached Figure Description

[0045] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0046] Figure 1 An application scenario diagram corresponding to a data processing method in airport security check guidance provided in an embodiment of this application;

[0047] Figure 2 A flowchart illustrating a data processing method for airport security check guidance, provided as an embodiment of this application;

[0048] Figure 3 A flowchart illustrating a data processing method for airport security check guidance, provided as another embodiment of this application;

[0049] Figure 4 A schematic diagram of the structure of a data processing device in airport security check guidance provided in one embodiment of this application;

[0050] Figure 5 This is a structural example diagram of an electronic device provided in an embodiment of this application.

[0051] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0052] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0053] To clearly understand the technical solution of this application, the solutions of the prior art will be described in detail first.

[0054] In existing civil aviation airport security systems, excessively long passenger waiting times and uneven utilization of security lane resources have become significant issues affecting airport operational efficiency and passenger experience. Current security lane management primarily relies on manual observation and experience-based judgment, lacking the ability to accurately and in real-time perceive the operational status of security lanes. Specifically, the methods for collecting operational data on security lanes are limited and outdated, typically relying on manual statistics or simple video surveillance to obtain queue numbers. Furthermore, passengers often blindly follow the flow of people or rely on experience when choosing security lanes, lacking personalized intelligent guidance. This leads to some lanes becoming overcrowded while others remain idle, not only prolonging overall passenger waiting times but also reducing the utilization efficiency of security resources. Consequently, this impacts airport operational efficiency and passenger service experience.

[0055] Figure 1 An application scenario diagram corresponding to a data processing method in airport security check guidance provided in an embodiment of this application is shown, such as... Figure 1 As shown, the application scenario provided in this embodiment includes: a data acquisition terminal 10, a data processing platform 11, and a passenger mobile terminal 12. The data acquisition terminal 10 and the data processing platform 11 transmit data in real time through the airport intranet, and the data processing platform 11 and the passenger mobile terminal 12 establish a push link through the airport communication network. Optionally, the data acquisition terminal 10 may include, but is not limited to, security checkpoint cameras, infrared passenger flow sensors, gate access counters, and security equipment status collectors. The passenger mobile terminal 12 may be a mobile phone, an airport official APP, or a travel mini-program.

[0056] Optionally, the data processing method for airport security check guidance provided in this application is applicable to passenger security check guidance scenarios at civil aviation airports, and is particularly suitable for high-density traffic scenarios such as morning peak hours, concentrated flight take-off and landing, and large passenger flows during holidays at large hub airports.

[0057] Specifically, the data processing flow during airport security checks is as follows: Data acquisition terminal 10 collects multi-source real-time data from airport security checkpoints and sends the data to data processing platform 11. Data processing platform 11 analyzes the multi-source real-time data based on a preset analysis algorithm to determine the congestion level, queue length, and other queuing status of each security checkpoint; based on the queuing status of each checkpoint, it predicts the estimated security check time within a preset time period; then, based on the estimated security check time of each checkpoint, it selects the target security checkpoint with the shortest waiting time and the most abundant resources; finally, data processing platform 11 sends security check recommendation information containing the target security checkpoint number and estimated waiting time to passenger mobile terminal 12. Passengers can then proceed to the target security checkpoint based on the security check recommendation information received by passenger mobile terminal 12, thereby achieving precise and intelligent passenger flow diversion, balancing the utilization rate of security checkpoint resources, and effectively shortening the overall queuing time.

[0058] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0059] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0060] Figure 2 A flowchart illustrating a data processing method in airport security check guidance, as provided in one embodiment of this application, is shown below. Figure 2 As shown, the execution subject of this embodiment is a data processing device for airport security check guidance. This device can be implemented through a computer program, or through a medium storing the relevant computer program, such as a USB flash drive and / or optical disc; alternatively, it can be implemented through a physical device that integrates or installs the relevant computer program, such as a chip or electronic device. The electronic device may be a computer or a server, etc. The data processing method for airport security check guidance provided in this embodiment includes the following steps:

[0061] S201. Obtain multi-source real-time data from each security checkpoint.

[0062] The purpose of this step is to comprehensively and in real-time capture the operational status data of each security checkpoint, providing data support for subsequent status analysis and duration prediction.

[0063] Multi-source real-time data refers to various dynamic data originating from different data collection terminals and covering the entire operation process of the security checkpoint. Optionally, multi-source real-time data may include, but is not limited to, passenger flow-related data, security equipment operation data, passenger individual characteristic data, and environmental auxiliary data.

[0064] Optionally, passenger flow data can be collected in real time using high-definition cameras, infrared sensors, millimeter-wave radar, and other equipment deployed at the entrances of security checkpoints and queuing areas. This data includes the number of people queuing, queue length, passenger entry rate, and passenger exit rate. The number of people queuing can be identified and counted using target detection algorithms based on the images captured by the cameras. The queue length can be calculated by combining the passenger spacing detected by sensors with the number of people queuing, ensuring the real-time nature and accuracy of data collection and avoiding errors and delays in manual statistics.

[0065] Optionally, the operational data of security inspection equipment can be collected in real time through the data interface of security inspection equipment (such as baggage scanners, body scanners, identity verification devices, etc.) to collect data such as the operating status (normal, fault, standby), security inspection processing rate (number of passengers completed security inspection per unit time), and equipment idle time, so as to determine the actual processing capacity of the channel.

[0066] Optionally, passenger individual characteristic data can be obtained through channels such as passenger mobile terminal authorization and airport security check appointment system to obtain relevant characteristic information of passengers (such as whether they are easy to check, whether they are carrying large luggage, whether they are passengers with mobility impairments, etc.). This type of data is used for subsequent personalized guidance to improve the rationality and pertinence of the guidance.

[0067] Optionally, the environmental auxiliary data may include data such as ambient temperature, humidity, and lighting brightness in the security check area, as well as airport flight dynamic data (such as flight take-off / landing times and flight delays).

[0068] Optionally, after the data acquisition terminal acquires data in real time, it transmits the data to the data processing terminal. At the same time, the acquired data is initially cleaned (e.g., noise, redundant information and incomplete data are removed) and the format is standardized to ensure the validity and consistency of the data.

[0069] It should be noted that the user facial data and other data collected in this application were all collected after the user confirmed and authorized the collection.

[0070] S202. Based on multi-source real-time data, the queuing status of each security checkpoint is determined using a preset analysis algorithm.

[0071] The preset analysis algorithm can be a pre-set comprehensive algorithm based on machine learning, statistical analysis, or queuing theory.

[0072] Optionally, the multi-source real-time data collected and preprocessed in S201 can be fused and processed to correlate and match passenger flow data, equipment operation data, passenger individual characteristic data, and environmental auxiliary data, constructing a unified channel operation data matrix. This enables collaborative analysis of multi-dimensional data and avoids judgment bias caused by a single data source. For example, the number of people queuing in a certain channel can be correlated with the processing rate of the security check equipment in that channel, combined with passenger individual characteristics (such as the proportion of passengers carrying large luggage), to comprehensively judge the actual congestion situation of that channel.

[0073] Optionally, a preset analysis algorithm can be used to calculate and analyze the fused data to extract queuing status characteristic indicators, including but not limited to: current number of people in the queue, queue length, average waiting time, channel congestion (the ratio of the number of people in the queue to the channel's rated capacity), and security equipment utilization rate. The average waiting time can be calculated by combining historical security check time data with the current number of people in the queue and the equipment processing rate; channel congestion can be classified into different congestion levels by setting thresholds according to airport security standards.

[0074] Optionally, the queuing status of each security checkpoint can be divided into three preset categories: congested (e.g., more than 30 people in line, average waiting time exceeding 30 minutes), normal (e.g., no more than 15 people in line, average waiting time less than 15 minutes), and idle (e.g., fewer than 5 people in line). This step enables real-time and accurate perception of the operational status of each security checkpoint, replacing manual observation and experience-based judgment, and improving the accuracy and efficiency of judging the security checkpoint queuing status.

[0075] Optionally, the preset analysis algorithm can adopt LSTM (Long Short-Term Memory) deep learning algorithm or multi-stage queuing model. Among them, the LSTM algorithm can effectively capture the time series characteristics of the data, is suitable for scenarios with large fluctuations in passenger flow, and can accurately identify the changing trend of the number of people in the queue. The multi-stage queuing model can describe the dynamic transmission process between service nodes through continuous time Markov chains, and improve the accuracy of queuing status judgment by combining the closure approximation method.

[0076] S203. Based on the queuing status, predict the estimated security check time for each security checkpoint within a preset time period.

[0077] This step, based on the current queuing status, combined with historical data and dynamic influencing factors, uses a predictive algorithm to accurately predict the security check time for each channel in the future, providing passengers with a reference waiting time.

[0078] The preset time period can be set according to the actual application scenario, such as 5 to 15 minutes, which can meet the decision-making needs of passengers and ensure the accuracy of the prediction.

[0079] Optionally, when making predictions, historical security check data (including the number of people queuing, security check time, and equipment operating status in the same period of history) is first retrieved to construct a training dataset for the prediction model. The training dataset is then used to train the prediction model using machine learning algorithms to optimize its parameters. Secondly, the current queuing status data for each channel determined in S202 (such as the number of people queuing, equipment processing speed, and passenger characteristic proportions) is input into the trained prediction model, and adjustments are made based on environmental auxiliary data and flight dynamic data. For example, if there is a surge in flights and passenger traffic during a certain period, the estimated security check time is appropriately increased; if a security check device in a certain channel experiences a minor malfunction or a decrease in processing speed, the estimated security check time for that channel is extended accordingly. Finally, the prediction model outputs the estimated security check time for each security check channel within a preset future time period, i.e., the total time required for passengers to complete the security check from entering the queue, including queuing time and security check operation time.

[0080] The prediction model in this step can adopt a hybrid prediction model that integrates historical data and real-time data, combining queuing theory and deep learning techniques to balance prediction accuracy and real-time performance.

[0081] S204. Based on the estimated security check duration, determine the target security check lane.

[0082] This step selects the optimal security check lane based on the estimated security check time for each lane and the individual needs of passengers, thereby achieving balanced utilization of security resources and minimizing passenger waiting time.

[0083] Optionally, several security checkpoints (1 to 3) with the shortest expected security check times can be selected as candidate lanes to ensure passengers can minimize their waiting time. Then, based on the individual passenger characteristic data obtained in S201, the candidate lanes are adjusted to provide personalized guidance. For example, for passengers with easy security checks, dedicated easy security check lanes are prioritized; for passengers with large luggage, lanes equipped with large luggage screening equipment and higher processing efficiency are prioritized; for passengers with mobility impairments, lanes that are close, have short queues, and have good accessibility facilities are prioritized to ensure targeted and humanized guidance.

[0084] Optionally, the resource balance of the adjusted candidate target channels can be checked. If the congestion of a candidate channel is close to the congestion threshold, and there are other channels with similar expected security check times but lower congestion, the target channel can be fine-tuned to avoid congestion in a certain channel due to over-recommendation, and to ensure the balance of resource utilization of each security check channel.

[0085] S205. Send security check recommendation information to passengers' mobile terminals; the security check recommendation information includes the target security check lane.

[0086] This step accurately pushes the information of the identified target security checkpoint to passengers, guiding them to the target checkpoint in an orderly manner, realizing intelligent guidance and solving the problem of passengers blindly choosing checkpoints.

[0087] Optionally, the data processing terminal organizes the identified target security checkpoint information (including checkpoint number, checkpoint location, estimated security check time, and route guidance) to generate standardized security check recommendation information. Secondly, this recommendation information is pushed to passengers via relevant applications on their mobile devices (such as the airport's official app, third-party mini-programs, and SMS). For passengers with authorized location permissions, real-time location information can be used to provide precise route guidance, helping them quickly find the target checkpoint.

[0088] Optionally, the system can receive real-time feedback from passengers (such as whether they accept the recommendation or have already proceeded to the target channel), and dynamically adjust the recommendation information based on passenger feedback and the real-time queuing status of each channel to ensure the effectiveness of the guidance.

[0089] Optionally, the security check recommendations can also include security precautions (such as prohibited items, quick security check tips, etc.) to further enhance the passenger security check experience and shorten security check processing time. Passengers can view the recommendations via mobile devices and choose whether to proceed to their target lane based on their needs, achieving independent and orderly security check flow.

[0090] The data processing method for airport security check guidance provided in this application acquires multi-source real-time data from each security checkpoint, uses a preset analysis algorithm to determine the queuing status and predict the expected security check time within a preset time period, and then matches and determines the target security checkpoint and pushes the corresponding security check recommendation information to the passenger's mobile terminal. This avoids the problems of relying on manual observation and experience judgment, single and lagging data collection methods, and the inability to accurately perceive the channel operation status in real time. It solves the problems of some channels being overcrowded and others being idle due to passengers blindly following the crowd or choosing security checkpoints based on experience. It balances the resource load and scheduling allocation of each security checkpoint, reduces passenger waiting time for security checks, improves the overall utilization rate of civil aviation airport security checkpoint resources and airport operation and management efficiency, and optimizes the passenger airport travel service experience.

[0091] As an optional implementation, based on any of the above embodiments, the multi-source real-time data includes video surveillance data and facial recognition data, and the queuing status includes the number of people in the queue and the passage time.

[0092] In this embodiment, the multi-source real-time data specifically includes video surveillance data and facial recognition data. The video surveillance data can be collected in real-time by high-definition video capture equipment deployed in the security checkpoints and passageways of civil aviation airport terminals, covering the entire area from security checkpoint entrances, queuing areas, and exits, with a capture frequency of no less than 25 frames per second to ensure clear capture of passenger movement trajectories and crowding patterns. Facial recognition data can be collected by non-contact facial recognition monitoring equipment linked to the video capture equipment. This non-cooperative collection mode requires no passenger stop, scanning, or registration, capturing passenger facial feature information in real-time without affecting passenger flow efficiency, thus achieving unique identification and trajectory tracking of passengers.

[0093] Specifically, the queuing status includes the number of people in the queue and the passage time. The number of people in the queue is used to intuitively reflect the current congestion level of each security checkpoint and is an indicator for judging the congestion status of the checkpoint. The passage time is used to reflect the actual processing efficiency of each security checkpoint and provides accurate real-time data support for the prediction of the subsequent security check duration. The combination of the two can comprehensively and accurately characterize the operation status of the security checkpoint.

[0094] Specifically, based on multi-source real-time data, the queuing status of each security checkpoint is determined using a preset identification and analysis algorithm, including the following steps:

[0095] First, image analysis is performed on the video surveillance data to identify areas where passengers gather at the entrance of the security checkpoint.

[0096] The purpose of this step is to accurately define the queuing area of ​​the security checkpoint, eliminate interference from irrelevant personnel (such as passersby and on-site staff), and ensure the accuracy of subsequent queue counting. Optionally, the video surveillance data is preprocessed, including image denoising, grayscale conversion, and contrast enhancement, to remove noise interference caused by factors such as changes in ambient light, image blur, and obstruction by debris, thereby improving image clarity. Subsequently, semantic segmentation algorithms and object detection algorithms (such as the YOLOv8 algorithm, which balances recognition speed and accuracy) are used to analyze the preprocessed video images. Combined with the physical boundaries of the security checkpoint entrance (such as fences and marking lines), the queuing area formed by passenger gathering is automatically identified and designated as the Region of Interest (ROI) for queue counting.

[0097] Optionally, the target detection algorithm dynamically adjusts the range of the region of interest in real time. When the queue extends or shifts, it automatically adapts to the queue changes, avoiding omissions or misjudgments in the headcount due to queue movement. Compared with existing video surveillance that simply captures images and cannot distinguish between queuing areas and irrelevant areas, this step, through precise area identification, can exclude irrelevant personnel from the count, improving the accuracy of subsequent headcount statistics.

[0098] Specifically, in areas where passengers congregate, the number of passengers is determined using a face detection algorithm, and this number is used as the queue size.

[0099] This step utilizes face detection algorithms to accurately count the number of passengers, avoiding issues such as misidentifying luggage or miscellaneous items as passengers, or the same passenger appearing multiple times in the frame and being counted repeatedly, thus ensuring the accuracy of the queue count.

[0100] Optionally, within the identified passenger gathering area, a pre-defined recognition and analysis algorithm calls a face detection model, such as MTCNN (Multi-task Cascaded Convolutional Networks) or SSD (Single Shot MultiBox Detector), to perform face detection on each frame of video images within the area, extracting feature points (such as the corners of the eyes, mouth, and bridge of the nose) for each face. A face feature deduplication algorithm is then used to match the facial features of the same passenger across different frames, avoiding duplicate counting. For example, if the same passenger is identified in five consecutive frames, the algorithm only counts them once, preventing duplicate counting. The face detection algorithm supports accurate recognition of faces in different poses (front, side, head down) and with varying degrees of occlusion (wearing masks, wearing hats), adapting to the diverse states of passengers in airport security scenarios. The statistical cycle can be set to 1 second per instance, updating the queue number data in real time to ensure data real-time performance. Furthermore, this process uses a non-intrusive data collection method, requiring no passenger cooperation and not affecting passenger queuing order or passage efficiency.

[0101] Specifically, based on facial recognition data, the system records the time points when passengers enter and leave the security checkpoint. The time interval between adjacent passengers passing through the security checkpoint is then determined and used as the passage time.

[0102] The purpose of this step is to capture the passenger's entire passage trajectory in the security checkpoint, obtain the complete time node from the passenger entering the security checkpoint to completing the security checkpoint, and provide basic data for the calculation of subsequent passage time. Its principle is based on the unique identification characteristics of facial recognition.

[0103] Optionally, facial recognition monitoring devices are deployed at the entrance and exit of the security checkpoint. When a passenger enters the security checkpoint, the facial recognition device at the entrance captures their facial features and matches them with the facial features of the queued passengers. After confirming their identity, the device automatically records the passenger's entry time. When a passenger completes the security check and leaves the security checkpoint exit, the facial recognition device at the exit captures their facial features again and matches them with the facial features recorded at the entrance. After confirming that it is the same passenger, the device records their departure time.

[0104] It should be noted that, in order to ensure the accuracy of the time point recording, the facial recognition equipment is linked with security inspection equipment (such as body scanners and baggage scanners). When the passenger completes the last security check, the facial recognition equipment at the exit is triggered to collect the data, so as to avoid misjudgment of the departure time point caused by the passenger lingering or loitering at the exit.

[0105] Specifically, the real-time processing efficiency of the security checkpoint is intuitively reflected by the time interval between adjacent passengers. The shorter the time interval, the higher the processing efficiency of the checkpoint, and vice versa. Optionally, the entry and exit times of all passengers in the same security checkpoint are sorted, and the departure time interval between two adjacent passengers (i.e., the departure time of the later passenger minus the departure time of the earlier passenger) is calculated according to the order in which passengers leave the security checkpoint. This time interval is determined as the real-time processing time of the security checkpoint.

[0106] For example, if passenger A leaves the security checkpoint at 10:00:05 and passenger B leaves the security checkpoint at 10:01:12, the time interval between them is 1 minute and 7 seconds, which is the current passage time of the security checkpoint. If no adjacent passengers leave within a certain time period, the historical average passage time of the channel is used as the temporary passage time to ensure the continuity of passage time data.

[0107] The data processing method for airport security check guidance provided in this application determines the queuing status of security checkpoints by collecting real-time data from multiple sources, including video surveillance data and facial recognition data. First, it analyzes and identifies passenger gathering areas from the video surveillance images. Then, it uses a facial detection algorithm to accurately determine the number of people in the queue. Based on facial recognition data, it records the time points of passengers entering and exiting the security checkpoints to calculate the processing time. Therefore, compared to relying on single, delayed data collection and manual judgment, it can obtain key queuing status information such as the number of people in the queue and the processing time more accurately and in real-time.

[0108] As an optional implementation, based on any of the above embodiments, the queuing status includes the number of people in the queue and the passage time.

[0109] Figure 3 A flowchart illustrating a data processing method for airport security check guidance, as provided in another embodiment of this application; Figure 3As shown, specifically, based on the queuing status, the estimated security check time for each security checkpoint within a preset time period is predicted, including the following steps:

[0110] S301. Input parameters such as the number of people queuing, passage time, historical passenger flow data, flight schedule information and weather factors into the preset prediction model to output the expected queue length for each security checkpoint.

[0111] The purpose of this step is to combine multiple influencing factors to accurately predict the trend of queue length changes for each security checkpoint within a preset time period.

[0112] The number of people queuing and the passage time are derived from the real-time queuing status data of each security checkpoint. The number of people queuing is a precise statistical value of the current passenger gathering area, and the passage time is the average time interval between adjacent passengers passing through the security checkpoint. Both are real-time dynamically updated data to ensure the real-time nature of the prediction.

[0113] Historical passenger flow data can be obtained by retrieving passenger flow data from the target airport over the past 3 to 12 months, including historical data such as the number of people queuing, passage time, and security check time at each security checkpoint at different times and on different dates (weekdays / weekends / holidays). After data cleaning and normalization, this data can be used as the training and reference basis for the preset prediction model to capture the periodic patterns of passenger flow changes.

[0114] Among them, flight schedule information can be obtained by accessing the airport's flight scheduling system to obtain the daily flight schedule, including flight departure / landing times, flight numbers, expected passenger throughput, and connecting flight information. Flight data related to security check times (such as flight numbers 1-2 hours before departure) can be extracted, because peak flight times can lead to a surge in passenger flow, which directly affects the length of security check queues.

[0115] Among them, weather factors can be obtained by accessing the meteorological service interface to obtain real-time weather data for the current day and for the next preset time period, including weather types such as sunny, rainy, snowy, and foggy, as well as visibility conditions. Because severe weather may cause flight delays, passenger gatherings, or affect the travel rhythm of passengers, it can indirectly affect the length of security check queues.

[0116] Optionally, by fusing the above-mentioned multi-source input parameters, and through data standardization and feature extraction, data of different dimensions and formats are converted into a unified feature vector to construct the input dataset for the prediction model. Optionally, the fusion logic of the input parameters of the preset prediction model can be as follows: historical passenger flow data is normalized and then weighted and fused with real-time queuing data; flight schedule information is matched with real-time passenger arrival rates through time windows; and weather factors are input into the preset prediction model through classification coding (e.g., sunny = 0, rainy = 1).

[0117] Optionally, the preset prediction model can employ a hybrid model that integrates time-series prediction and machine learning, such as a hybrid model of LSTM and XGBoost (eXtreme Gradient Boosting). The LSTM model captures the time-series variation characteristics of each input parameter, such as the trend of passenger flow with flight schedules, while the XGBoost model uncovers the nonlinear relationships between parameters, such as the correlation between weather factors and passenger flow changes, and the correlation between flight density and queue length. Finally, the fused input parameters are input into the trained preset prediction model. Based on the matching degree between real-time parameters and historical patterns, the preset prediction model outputs the predicted queue length for each security checkpoint within a preset time period (e.g., 5 to 60 minutes, adjustable according to the actual scenario). This predicted queue length is a dynamically changing value that will be adjusted synchronously with the updates of real-time input parameters to ensure the timeliness of the prediction results.

[0118] S302. Determine the estimated waiting time for each security checkpoint based on the estimated queue length and passage time.

[0119] This step calculates the estimated waiting time for passengers after they enter the queue, based on queue length and real-time traffic efficiency, and intuitively reflects the congestion level of each channel.

[0120] Optionally, the formula for calculating the expected waiting time is: Expected waiting time = Expected queue length × Passage time, where the expected queue length is the number of people queuing in each channel within the future preset time period output by S301, and the passage time is the real-time passage time of each channel.

[0121] Optionally, a waiting time threshold can be set (which can be set according to airport security standards, such as 60 minutes). If the estimated waiting time for a security checkpoint exceeds the threshold, it will be automatically marked as a "high-congestion lane," triggering a subsequent early warning mechanism to provide a basis for airport scheduling and passenger guidance. If the estimated queue length for a lane is 0, the estimated waiting time will be set to 1 to 2 times the transit time to ensure the rationality and continuity of the data. Through this step, the abstract queue length is transformed into an intuitive waiting time, allowing passengers to accurately know the estimated waiting time for security checks.

[0122] S303. Based on the passenger's current location information, flight departure time, estimated queue length, and estimated waiting time, determine the estimated security check time for each security checkpoint.

[0123] The purpose of this step is to combine individual travel needs of passengers to achieve personalized calculation of the estimated security check time, so that the prediction results are more in line with the actual situation of passengers.

[0124] Optionally, personalized passenger data can be obtained, including: the passenger's current location information (obtained through authorized location access on the passenger's mobile terminal, accurate to the terminal floor and area), and flight departure time (obtained through flight information linked to the passenger's APP or by querying the airport system); secondly, the parameters are analyzed collaboratively, and the estimated security check time is calculated step by step.

[0125] Optionally, firstly, calculate the travel time for passengers to reach each security checkpoint, and then integrate and calculate the estimated security check time. Optionally, based on the physical distance between the passenger's current location and each security checkpoint, combined with the passenger flow rate in the terminal (which can be set with reference to historical data), calculate the travel time for the passenger to reach the entrance of each security checkpoint from the current location. For example, if the passenger is currently in Area A of the terminal, 50 meters away from security checkpoint 1 and 80 meters away from security checkpoint 2, then the travel time to security checkpoint 1 is approximately 42-62 seconds, and the travel time to security checkpoint 2 is approximately 67-100 seconds. Optionally, the estimated security check time = travel time + estimated waiting time + basic security check time for a single passenger (i.e., passage time, ensuring that it covers the time for the passenger's own security check operation). Further risk adjustments are made based on the flight departure time. If the estimated security check time for a passenger to a certain channel plus the subsequent boarding time (referring to the distance to the airport boarding gate and the advance boarding time) is close to or exceeds the flight departure time, the estimated security check time for that channel will be appropriately increased (for example, by adding a buffer time of 10%-20%) to remind passengers to avoid the risk of missing their flight.

[0126] Finally, the system outputs the personalized estimated security check time for each passenger at each security checkpoint, ensuring that the prediction results obtained by each passenger are in line with their own travel schedule. This avoids misjudgments caused by overlooking travel time and also takes into account the risk of missing flights, thereby improving the practicality and humanization of the prediction.

[0127] The data processing method for airport security check guidance provided in this application comprehensively considers multiple dimensions of data, such as the number of people queuing, passage time, historical passenger flow data, flight schedule information, and weather factors, when predicting the estimated security check time for each security check channel within a preset time period. These factors are input into a preset prediction model to obtain the estimated queue length. Then, the estimated waiting time is calculated by combining the passage time with the estimated waiting time. Finally, the estimated security check time is determined based on the passenger's current location, flight departure time, etc. This method overcomes the limitation of traditional prediction methods that consider only one factor, and can more accurately reflect the actual situation. It provides passengers with more scientific and reasonable security check guidance, effectively balances passenger flow in each channel, reduces passenger waiting time, improves the utilization rate of airport security check resources and overall operational efficiency, and enhances the passenger travel experience.

[0128] As an optional implementation, based on any of the above embodiments, the estimated security check time for each security checkpoint is determined according to the passenger's current location information, flight departure time, estimated queue length, and estimated waiting time, including the following steps:

[0129] First, based on the passenger's current location information, calculate the estimated travel time for the passenger to reach each security checkpoint.

[0130] The purpose of this step is to accurately calculate the travel time for passengers from their current location to each security checkpoint, avoid overlooking the deviation in estimated security check time caused by travel time, and ensure that the prediction results match the actual travel pace of passengers.

[0131] Optionally, the system acquires the passenger's current location information and the precise location information of each security checkpoint to construct a spatial coordinate system for the terminal building. The passenger's current location is obtained through mobile terminal GPS (Global Positioning System), Beidou positioning, or indoor Bluetooth positioning, with an accuracy of within 1 meter, adapting to the complex indoor environment of the terminal building. The location information of each security checkpoint is pre-stored on the backend server, including the specific coordinates of the checkpoint entrance, the floor it is located on, and surrounding signage information, ensuring the accuracy of distance calculation. Next, the straight-line distance between the passenger's current location and the entrance of each security checkpoint is calculated and corrected based on the actual passage scenario in the terminal building. For example, factors affecting passage are considered, such as the width of the corridors, the distribution of escalators / elevators, and densely populated areas (such as check-in areas and the area around shops). The straight-line distance is corrected by a coefficient (the correction coefficient ranges from 1.1 to 1.5, with higher values ​​for densely populated areas and lower values ​​for open areas), to obtain the actual passage distance.

[0132] Optionally, the estimated travel time can be calculated by combining the average passenger flow rate within the terminal, using the formula: Estimated travel time = Actual travel distance ÷ Average passenger flow rate. The average passenger flow rate can be set to 0.8-1.2 meters per second based on historical passenger flow data, and can be dynamically adjusted according to individual passenger characteristics: for passengers with mobility impairments or carrying large luggage, the flow rate can be reduced to 0.5-0.7 meters per second; for passengers who easily pass through security or have no luggage, the flow rate can be increased to 1.3-1.5 meters per second, ensuring the personalization and accuracy of the travel time calculation.

[0133] In addition, if a passenger is currently near a security checkpoint queue (the actual travel distance is less than 5 meters), the estimated travel time will be set to 0. If there are special circumstances such as temporary traffic control or route construction in the terminal, the backend server will obtain relevant information in real time and make additional corrections to the estimated travel time (adding a buffer time of 5-10 minutes) to avoid prediction deviations caused by route abnormalities.

[0134] Next, based on the estimated travel time, estimated waiting time, and security check processing time, the estimated security check time for each security checkpoint is obtained.

[0135] The estimated waiting time is the anticipated time for passengers to queue for security checks after arriving at the security checkpoint. The security check processing time is the basic time required for a single passenger to complete the security check process.

[0136] Secondly, the formula for estimating security check time is: Estimated security check time = Estimated travel time + Estimated waiting time + Security check processing time. This formula covers the entire process from the passenger's current location to completing the security check, avoiding the problem of inconsistencies between predicted and actual results caused by only calculating waiting time and ignoring travel time and security check operation time.

[0137] Optionally, risk corrections can be made based on flight departure times to further improve the practicality and security of the prediction results. The backend server calculates the estimated security check time and boarding time based on the passenger's flight departure time. Boarding time includes the travel time from the security exit to the boarding gate and the boarding queue time. Based on historical data, it can be set to 15-30 minutes. If the total time is close to or exceeds the flight departure time (the difference is less than 10 minutes), the estimated security check time for that security check channel is automatically increased by 10%-20% to add a buffer time, and it is marked as a "high-risk channel for missing flights," reminding passengers to choose other channels first. If the total time is much lower than the flight departure time (the difference is greater than 30 minutes), the buffer time can be appropriately reduced to ensure the rationality of the prediction results and avoid overly conservative predictions that cause passengers to wait too early.

[0138] Optionally, the backend server synchronizes the real-time queuing status of each security checkpoint in real time. If the estimated queue length or estimated waiting time of a certain checkpoint changes, the estimated security check time will be updated synchronously, and the updated information will be pushed to the passenger APP in real time to ensure the timeliness of the prediction results.

[0139] As an optional implementation, based on any of the above embodiments, the target security check lane is determined according to the estimated security check time, including the following steps:

[0140] First, security check lanes with an expected security check time of less than a preset time threshold are selected as candidate security check lanes.

[0141] The purpose of this step is to quickly eliminate security checkpoints that are overly congested or have excessively long estimated check times by filtering through preset time thresholds, thus narrowing down the candidate checkpoints, improving the efficiency of subsequent target checkpoint determination, and ensuring that the candidate checkpoints can meet passengers' basic needs for "convenience".

[0142] Optionally, firstly, the basis for setting the preset time threshold and the rules for dynamic adjustment should be clearly defined to ensure the reasonableness and adaptability of the threshold. Specifically, the preset time threshold should be dynamically adjusted based on airport security service standards (such as an average waiting time of 15 minutes), passenger acceptable waiting time survey data (which, combined with airport passenger travel questionnaires, can be set at 20-30 minutes), and real-time passenger flow scenarios. For example, during peak passenger flow periods (such as holidays and periods with high flight volume), the preset time threshold can be increased to 30-40 minutes to avoid insufficient candidate channels leading to a lack of selection; during periods of stable passenger flow, the preset time threshold can be decreased to 20-25 minutes to ensure that the selected candidate channels are more convenient.

[0143] Optionally, the estimated security check time for each security checkpoint is compared one by one, and channels with estimated security check times less than a preset time threshold are selected as candidate security checkpoints. If the estimated security check time for all security checkpoints is greater than or equal to the preset time threshold, then 1-2 channels with the shortest estimated security check times are selected as candidate security checkpoints, and a congestion warning is triggered and pushed to the airport operations terminal to remind management personnel to allocate resources in a timely manner (such as opening backup channels or increasing the number of staff on duty) to avoid passengers missing their flights due to excessive channel congestion.

[0144] Optionally, the equipment operation status of candidate security check channels can be checked during the screening process. If a candidate channel has problems such as equipment failure or abnormal processing speed, it can be removed from the candidate list to ensure the normal operation capability of the candidate channels, avoid deviations in the expected security check time due to equipment problems, and further improve the reliability of the candidate channels.

[0145] Next, based on the passenger's flight departure time, the risk value of missing the flight corresponding to each candidate security checkpoint is calculated.

[0146] Optionally, the formula for calculating the risk value of missing a flight can be: Risk value of missing a flight = negative vectorized value of (flight departure time - current time - estimated security check time - boarding preparation time).

[0147] The flight departure time and current time are both accurate to the minute to ensure the accuracy of time difference calculations. The current time is synchronized in real time through the backend server to avoid errors in risk value calculation due to time deviations. The estimated security check time is a personalized prediction for each candidate security checkpoint, covering passenger travel time, queuing time, and security check processing time to ensure it matches the actual travel pace of passengers. The boarding preparation time can be set with reference to historical airport data and boarding procedures, including the travel time from the security exit to the boarding gate and the queuing time at the boarding gate. For example, it can be set to 15-30 minutes and can be dynamically adjusted according to the distance to the boarding gate and individual passenger characteristics (such as passengers with mobility impairments). The farther the distance and the slower the passenger's movement, the more appropriate the boarding preparation time should be.

[0148] The negative vectorization value is calculated by negatively processing the difference between "flight departure time - current time - estimated security check time - boarding preparation time". The smaller the difference, the higher the risk of missing the flight. If the difference is negative, it means that the passenger is very likely to miss the flight if they choose this channel, and the risk value is set to the maximum value (e.g., 100). If the difference is greater than or equal to 30 minutes, it means that the risk of missing the flight is extremely low, and the risk value is set to the minimum value (e.g., 0) to ensure the quantification of the risk value is reasonable. For example, if a passenger chooses a channel and the estimated security check time is 20 minutes, the boarding preparation time is 15 minutes, and the flight departure time is only 30 minutes away from the current time, then the risk value of missing the flight is (30-20-15) = -5, which is marked as "high risk" after normalization.

[0149] Optionally, the calculated flight delay risk value can be revised and optimized, taking into account weather factors, flight dynamics (such as flight delay warnings), and on-site conditions in the terminal (such as route control). If there is severe weather or flight delay warning on the day, the flight delay risk value of each candidate channel can be appropriately increased. If there is route control around a candidate channel in the terminal, which increases the travel time for passengers, the flight delay risk value of that channel can be increased accordingly to ensure that the risk value can truly reflect the actual possibility of missing the flight.

[0150] Optionally, the missed flight risk value of each candidate security checkpoint is standardized (normalized to between 0 and 100) to facilitate subsequent sorting and comparison, where 0 represents no risk of missing the flight, and 100 represents a very high probability of missing the flight. The higher the risk value, the greater the likelihood that the passenger will miss the flight if they choose that checkpoint. Optionally, linear mapping or piecewise functions can be used to normalize the missed flight risk value.

[0151] Finally, the candidate security checkpoint with the lowest value among the various flight miss risk values ​​is determined as the target security checkpoint.

[0152] Optionally, the missed flight risk values ​​of each candidate security checkpoint are sorted and arranged in ascending order of missed flight risk value. The candidate security checkpoint with the lowest missed flight risk value is selected and determined as the target security checkpoint. If multiple candidate security checkpoints have the same missed flight risk value and are all the lowest (e.g., multiple channels have a risk value of 0), the expected security check time of each channel is further compared, and the channel with the shortest expected security check time is selected as the target security checkpoint, taking into account both safety and convenience.

[0153] Optionally, if the risk of missing a flight is high for all candidate security checkpoints (e.g., a risk of missing a flight greater than 80), then when the target security checkpoint is determined, a flight miss risk warning message is pushed to the passenger's mobile terminal to remind the passenger to speed up their journey and further reduce the risk of missing a flight.

[0154] The data processing method for airport security check guidance provided in this application first filters out candidate security check lanes whose estimated check time is less than a preset time threshold when determining the target security check lane. This avoids passengers missing their trips due to excessively long security check wait times. Then, it calculates the missed flight risk value for each candidate lane based on the passenger's flight departure time and selects the lane with the lowest missed flight risk value as the target lane. Therefore, compared to simply selecting a lane based on the number of people in the queue or the lane's availability, it can more accurately meet the actual needs of passengers and effectively reduce the probability of passengers missing their flights.

[0155] As an optional implementation, based on any of the above embodiments, the following steps are also included:

[0156] First, monitor the real-time queue length at each security checkpoint.

[0157] Optionally, multi-source data acquisition devices (high-definition cameras, infrared sensors, millimeter-wave radar, etc.) can be deployed to monitor the queuing areas of each security checkpoint 24 hours a day, focusing on capturing changes in the number of passengers in the queue, ensuring that the dynamic fluctuations in the number of people in the queue can be captured in real time, and avoiding untimely scheduling due to data acquisition delays.

[0158] Secondly, the collected real-time queue data is processed in real time, including data cleaning, outlier filtering and verification, to remove abnormal data caused by temporary passenger stops, obstructions, or equipment misjudgments (such as sudden increases or decreases in the number of people), ensuring the accuracy of queue statistics.

[0159] Optionally, the processed real-time queue number data can be pushed to the back-end data processing terminal, the central control room display terminal, and the staff terminal, so that managers can monitor the queuing dynamics of each channel in real time.

[0160] Secondly, if the number of people queuing at any security checkpoint exceeds a preset threshold, a channel scheduling instruction is generated.

[0161] This step determines the level of congestion in the channel by setting a preset threshold for the number of people, and generates targeted scheduling instructions to replace manual experience-based scheduling, thereby improving the timeliness and accuracy of scheduling.

[0162] Optionally, firstly, the basis for setting the preset number of people threshold and the rules for dynamic adjustment should be clearly defined to ensure the rationality and adaptability of the threshold. Specifically, the preset number of people threshold is dynamically adjusted based on the rated capacity of the security checkpoint (such as the maximum number of passengers that can queue at the same time in a single checkpoint, combined with the checkpoint width and the number of security equipment), airport security service standards, and real-time passenger flow scenarios. For example, if the rated capacity of a regular security checkpoint is 20 people, the preset number of people threshold is set to 15 people (i.e., when the number of people queuing reaches 15, an early warning dispatch is triggered); during peak passenger flow periods (such as holidays and periods with high flight volume), the preset number is increased to 18 people to avoid frequent dispatch triggers; during periods of stable passenger flow, the preset number is decreased to 12 people to ensure timely management of potential congestion.

[0163] Optionally, the real-time queuing number of people at each security checkpoint is compared with the preset number threshold. If the real-time queuing number of people at any checkpoint exceeds the preset number threshold, the checkpoint is determined to be in a "congestion warning state". The dispatch instruction generation module is automatically activated to generate targeted checkpoint dispatch instructions based on the degree of congestion and on-site resource conditions.

[0164] Optionally, channel scheduling instructions may include personnel scheduling instructions, channel start / stop instructions, equipment scheduling instructions, and diversion guidance instructions.

[0165] Among them, the personnel dispatch instruction can be "Please have the personnel on duty in a certain area immediately go to a certain channel to provide support and speed up the security check processing speed," which is suitable for scenarios where the number of people queuing at a certain channel slightly exceeds the threshold and the equipment is operating normally but the processing efficiency is insufficient; the channel start / stop instruction can be "Please immediately open a certain backup security check channel to divert passengers from a certain channel," which is suitable for scenarios where the number of people queuing at a certain channel far exceeds the threshold and the existing channel cannot quickly clear the queue; the equipment dispatch instruction can be "Please check the operating status of the security check equipment in a certain channel to ensure that the equipment is operating at full capacity, and report any faults immediately," which is suitable for scenarios where the number of people queuing surges due to abnormal equipment operation; the diversion and guidance instruction can be "Please have the on-site guidance personnel guide passengers queuing at a certain channel to divert them to a certain or an empty channel," which is suitable for scenarios where a single channel is congested and there are idle resources in surrounding channels.

[0166] Finally, the channel scheduling instruction is sent to the staff's terminal.

[0167] Optionally, dispatch instructions can be pushed to the corresponding staff terminals based on their type. Specifically, personnel dispatch instructions are pushed to the handheld terminals and mobile apps of relevant on-duty personnel; channel start / stop instructions and equipment dispatch instructions are pushed to the terminals of central control room management personnel and equipment maintenance personnel; and diversion guidance instructions are pushed to the terminals of on-site guidance personnel, ensuring that instructions are accurately delivered and avoiding interference from irrelevant personnel.

[0168] Optionally, a multi-channel synchronous push approach can be adopted to ensure the reliability of instruction transmission. For example, dispatch instructions (including text instructions, voice reminders, and pop-up alerts) can be simultaneously pushed to staff terminals via the airport's dedicated internal communication network. Voice reminders and pop-up alerts have priority, ensuring staff can discover and view the instructions immediately. After receiving the instructions, staff provide feedback on the execution status through their terminals, such as "departed for support," "backup channel activated," or "equipment operating normally." The backend server receives feedback information in real time and updates the execution progress of the dispatch instructions. If the execution of a dispatch instruction times out (e.g., no execution status feedback within 10 minutes), a secondary alert is triggered, reminding management personnel to follow up and supervise, ensuring that the dispatch instructions are implemented effectively, thus forming a closed-loop management system.

[0169] The data processing method for airport security check guidance provided in this application monitors the number of people queuing at each security checkpoint in real time. When the number of people queuing at any checkpoint exceeds a preset threshold, a checkpoint scheduling instruction is generated and sent to the staff's terminal. This allows for faster and more accurate perception of checkpoint congestion, enabling staff to respond quickly and allocate checkpoint resources. This effectively avoids situations where some checkpoints are overcrowded while others are idle, thus optimizing the passenger travel experience.

[0170] Figure 4 A schematic diagram of the structure of a data processing device in airport security check guidance provided in one embodiment of this application is shown below. Figure 4 As shown, the data processing device for airport security check guidance provided in this embodiment is located in an electronic device. The data processing device 40 for airport security check guidance provided in this embodiment includes: an acquisition module 41, a queue status analysis module 42, a queue prediction module 43, a security check lane determination module 44, and an information sending module 45.

[0171] Specifically, the acquisition module 41 is used to acquire multi-source real-time data of each security checkpoint; the queue status analysis module 42 is used to determine the queue status of each security checkpoint based on the multi-source real-time data and using a preset analysis algorithm; the queue prediction module 43 is used to predict the expected security check duration of each security checkpoint within a preset time period based on the queue status; the security checkpoint determination module 44 is used to determine the target security checkpoint based on the expected security check duration; and the information sending module 45 is used to send security check recommendation information to the passenger's mobile terminal, wherein the security check recommendation information includes the target security checkpoint.

[0172] Optionally, the multi-source real-time data includes video surveillance data and facial recognition data, and the queuing status includes the number of people in the queue and the passage time. Optionally, the queuing status analysis module 42, when determining the queuing status of each security checkpoint based on multi-source real-time data and using a preset recognition and analysis algorithm, is specifically used for: performing image analysis on the video surveillance data to identify the passenger gathering area at the entrance of the security checkpoint; determining the number of passengers within the passenger gathering area using a facial detection algorithm, and using the number of passengers as the number of people in the queue; recording the time points when passengers enter and leave the security checkpoint based on facial recognition data; and determining the time interval between adjacent passengers passing through the security checkpoint based on the time points, and using the time interval as the passage time.

[0173] Optionally, the queuing status includes the number of people in the queue and the passage time. Optionally, the queuing prediction module 43, when predicting the estimated security check time for each security checkpoint within a preset time period based on the queuing status, is specifically used for: taking the number of people in the queue, the passage time, historical passenger flow data, flight schedule information, and weather factors as input parameters, inputting them into a preset prediction model to output the estimated queue length corresponding to each security checkpoint; determining the estimated waiting time corresponding to each security checkpoint based on the estimated queue length and the passage time; and determining the estimated security check time for each security checkpoint based on the passenger's current location information, flight departure time, estimated queue length, and estimated waiting time.

[0174] Optionally, the queue prediction module 43, when determining the estimated security check time for each security checkpoint based on the passenger's current location information, flight departure time, estimated queue length, and estimated waiting time, is specifically used to: calculate the estimated travel time for the passenger to reach each security checkpoint based on the passenger's current location information; and obtain the estimated security check time for each security checkpoint based on the estimated travel time, estimated waiting time, and security check processing time.

[0175] Optionally, the security checkpoint determination module 44, when determining the target security checkpoint based on each estimated security check duration, is specifically used to: designate security checkpoints with estimated security check durations less than a preset duration threshold as candidate security checkpoints; calculate the missed flight risk value corresponding to each candidate security checkpoint based on the passenger's flight departure time; and determine the candidate security checkpoint corresponding to the one with the lowest missed flight risk value as the target security checkpoint.

[0176] Optionally, the data processing device for airport security check guidance provided in this application further includes a monitoring module. Optionally, the monitoring module is used to: monitor the real-time queuing number of people at each security checkpoint; generate a channel scheduling instruction when the real-time queuing number of people at any security checkpoint exceeds a preset threshold; and send the channel scheduling instruction to the staff terminal.

[0177] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, as shown below. Figure 5 As shown, the electronic device 50 provided in this embodiment includes: a processor 51 and a memory 52 communicatively connected to the processor 51.

[0178] The memory 52 stores computer-executable instructions; the processor 51 executes the computer-executable instructions stored in the memory 52 to implement the method provided in any of the above embodiments.

[0179] The program may include program code, which includes computer-executable instructions. Memory 52 may include high-speed RAM, and may also include non-volatile memory, such as at least one disk storage device.

[0180] In this embodiment, the memory 52 and the processor 51 are connected via a bus. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The bus is represented by a single straight line, but this does not mean that there is only one bus or one type of bus.

[0181] This application also provides a computer-readable storage medium, including computer-executable instructions stored in the computer-readable storage medium, which, when executed by a processor, are used to implement the method provided in any of the above embodiments.

[0182] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the method provided in any of the above embodiments.

[0183] The modules described as separate components may or may not be physically separate. The components shown as modules 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 modules can be selected to implement the solution of this embodiment according to actual needs.

[0184] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The unit composed of the above modules can be implemented in hardware or in the form of hardware plus software functional units.

[0185] The integrated modules described above, implemented as software functional modules, can be stored in a computer-readable storage medium. These software functional modules, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods of the various embodiments of this application.

[0186] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0187] The memory may include high-speed RAM, and may also include non-volatile storage (NVM), such as at least one disk storage device, and may also be a USB flash drive, external hard drive, read-only memory, disk or optical disc, etc.

[0188] The aforementioned storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0189] An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Alternatively, the storage medium can be an integral part of the processor. The processor and storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and storage medium can exist as discrete components in an electronic control unit or main control device.

[0190] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0191] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A data processing method for airport security check guidance, characterized in that, include: Acquire multi-source real-time data from each security checkpoint; Based on the multi-source real-time data, the queuing status of each security checkpoint is determined using a preset analysis algorithm; Based on the queuing status, the estimated security check time for each security checkpoint is predicted within a preset time period in the future; Based on the estimated security check times, the target security check lanes are determined; Send security check recommendation information to the passenger's mobile terminal; wherein the security check recommendation information includes the target security check lane.

2. The method according to claim 1, characterized in that, The multi-source real-time data includes video surveillance data and facial recognition data, and the queuing status includes the number of people in the queue and the passage time. The step of determining the queuing status of each security checkpoint based on the multi-source real-time data and using a preset identification and analysis algorithm includes: Image analysis is performed on the video surveillance data to identify passenger gathering areas at the entrance of the security checkpoint; Within the passenger gathering area, the number of passengers is determined by a face detection algorithm, and this number is used as the queue size. Based on the facial recognition data, the time points when passengers enter and leave the security checkpoint are recorded; The time interval between adjacent passengers passing through the security checkpoint is determined based on the time point, and the time interval is used as the passage time.

3. The method according to claim 1, characterized in that, The queuing status includes the number of people in the queue and the passage time; The prediction of the estimated security check time for each security checkpoint within a preset time period based on the queuing status includes: The number of people in the queue, the passage time, historical passenger flow data, flight schedule information and weather factors are used as input parameters and input into the preset prediction model to output the expected queue length for each security checkpoint. Based on the estimated queue length and the passage time, the estimated waiting time for each security checkpoint is determined. The estimated security check time for each security checkpoint is determined based on the passenger's current location information, flight departure time, estimated queue length, and estimated waiting time.

4. The method according to claim 3, characterized in that, The process of determining the estimated security check time for each security checkpoint based on the passenger's current location information, flight departure time, estimated queue length, and estimated waiting time includes: Based on the passenger's current location information, calculate the estimated travel time for the passenger to reach each security checkpoint; The estimated security check time for each security checkpoint is obtained based on the estimated travel time, the estimated waiting time, and the security check processing time.

5. The method according to claim 1, characterized in that, The determination of the target security check lane based on each of the estimated security check times includes: Security check channels whose estimated security check time is less than a preset time threshold are selected as candidate security check channels; Calculate the risk value of missing the flight for each of the candidate security checkpoints based on the passenger's flight departure time; The candidate security checkpoint corresponding to the lowest value among the various missed flight risk values ​​is determined as the target security checkpoint.

6. The method according to any one of claims 1-5, characterized in that, Also includes: Monitor the real-time queue length at each security checkpoint; If the number of people queuing in any security checkpoint exceeds a preset threshold, a channel scheduling instruction is generated. The channel scheduling command is sent to the staff terminal.

7. A data processing device for airport security check guidance, characterized in that, include: The acquisition module is used to acquire multi-source real-time data from each security checkpoint. The queuing status analysis module is used to determine the queuing status of each security checkpoint based on the multi-source real-time data and using a preset analysis algorithm. The queue prediction module is used to predict the estimated security check time of each security check channel within a preset time period based on the queue status. The security check lane determination module is used to determine the target security check lane based on the estimated security check time. The information sending module is used to send security check recommendation information to passengers' mobile terminals; wherein, the security check recommendation information includes the target security check channel.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-6.

Images