Airport check-in counter configuration planning method and device

Abstract

The application relates to the field of airport management and aviation services, and discloses an airport check-in and consignment counter configuration planning method and device, which comprises the following steps: S1, collecting real-time or historical data to obtain a passenger arrival rate, a counter service rate and system limitation condition parameters; S2, constructing a queuing theory model based on the collected data, and preliminarily evaluating the check-in counter configuration through an M / M / c queuing model; and S3, using optimal control theory to establish a target function, optimizing the configuration scheme, and minimizing the comprehensive target among the queuing time, the passenger waiting time and the resource configuration cost. The dynamic counter configuration scheme based on the real-time data acquisition and feedback mechanism achieves the technical effect of dynamically adjusting the counter quantity during the peak period, thereby effectively avoiding the problem of long passenger queues during the peak period and reducing the resource waste during the trough period.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of airport management and aviation services, in particular to an airport check-in and consignment counter configuration planning method and device. BACKGROUND

[0002] At present, an experience formula estimation method is generally used in the check-in and consignment counter configuration planning process of an airport, and the method is used for rough calculation of the number of counters according to the average ticketing efficiency obtained through historical data analysis and the peak hour passenger number predicted. Although the method is simple and fast, in actual application, the method often leads to unreasonable allocation of resources in the check-in area, and long waiting time of passengers may be caused due to underestimation of demand, and investment waste and high idle rate of equipment may be caused due to overestimation of demand.

[0003] The industry gradually starts to use a software simulation tool to perform more detailed resource configuration analysis, and through simulation of passenger flow, operation efficiency and service quality under different configurations are evaluated. However, although the simulation verification after the event improves the accuracy of planning, due to long time consumption of modeling simulation and slow iteration speed, the planning stage is limited in cost control and efficiency optimization, and cannot adapt to the fast design change cycle.

[0004] The traditional experience formula method and the later software simulation method have their own limitations, the former lacks consideration of dynamic passenger flow and passenger experience, and the latter is limited by design iteration efficiency, and cannot respond to design changes in time, leading to high initial investment of airport facilities and insufficient flexibility. SUMMARY

[0005] In view of the deficiencies of the prior art, the application provides an airport check-in and consignment counter configuration planning method and device, and solves the problems of long time consumption of modeling simulation, slow iteration speed, inability to respond to design changes in time and lack of consideration of dynamic passenger flow and passenger experience in the prior art.

[0006] To achieve the above purpose, the application is implemented through the following technical scheme: an airport check-in and consignment counter configuration planning method, comprising the following steps:

[0007] S1, collect real-time or historical data to obtain passenger arrival rate, counter service rate and system limitation condition parameters; after the data is collected, the data needs to be cleaned and standardized. The flow data of different airports is uniformly converted into a standard format, abnormal data is removed, missing values are filled, and the comparability and accuracy of the data are ensured. After the standardization processing, the data can be better used for subsequent model construction and optimization calculation.

[0008] S2, based on the collected data, construct a queuing theory model, and preliminarily evaluate the check-in counter configuration through the M / M / c queuing model; the role of the model is to simulate the situation of passenger arrival and service under the given number of counters. By calculating the queuing time W q (t), the service efficiency and passenger waiting time under different time periods and counter configurations can be evaluated. By adjusting the number of counters c(t), the waiting time and queue length of passengers under different configurations can be predicted, thereby providing a reference for subsequent optimization.

[0009] S3, use optimal control theory to establish an objective function to optimize the configuration scheme, and minimize the comprehensive objective between queuing time, passenger waiting time and resource configuration cost; by solving the optimal control problem, the number of counters c(t) can be dynamically adjusted to minimize the cost function. The optimization goal is to adjust the counter configuration according to the changes of real-time data, thereby reducing the waiting time of passengers and avoiding waste of resources.

[0010] S4, combined with dynamic game theory, simulate the game between the airport management and the airlines, and solve the optimal counter configuration and flight arrangement through Nash equilibrium; the introduction of game theory considers the interest game between the airport management and the airlines. The airport management wants to maximize the utilization of resources and reduce operating costs; the airlines want to improve customer satisfaction by reducing passenger waiting time. In the game model, the decision of the airport management is to adjust the number of counters c(t), while the airlines adjust the flight arrangement to affect the passenger flow. The game solves the Nash equilibrium, balances the goals of both parties, and produces the optimal counter configuration and flight scheduling strategy.

[0011] S5, real-time collection of operation data and feedback to the optimization system, through real-time adjustment of the number of counters, the system operation remains in the optimal state; it can respond to passenger flow fluctuations in real time. During operation, the system will continuously collect operation data. Whenever the system state changes, real-time data will be input into the optimization system, and the number of counters c(t) will be automatically adjusted through the feedback mechanism. When the passenger arrival volume increases, the system will automatically increase the number of counters c(t) to reduce the queuing pressure of passengers; during the low period, the number of counters c(t) will automatically adjust to reduce unnecessary waste of resources. The real-time feedback mechanism ensures that the counter configuration can match the actual operation demand, improving the self-adaptability and flexibility of the system.

[0012] S6, integrate the optimization algorithm into the airport management system, continuously optimize and ensure that the configuration and operation of the airport check-in and delivery counter are always in the optimal state; through the automatic control system, the optimization algorithm can be seamlessly executed, and the counter configuration can be adjusted in real time. The system continuously monitors passenger flow and operating efficiency, automatically adjusts the strategy, and ensures that the resource configuration is always in the optimal state in actual operation. During system operation, airport management personnel check and fine-tune the optimization results according to real-time reports, further improving the efficiency of the system. The system can also update the model regularly based on long-term data to ensure the continuous effectiveness of the method.

[0013] Preferably, the queuing theory model is constructed by M / M / c queuing model, and the queuing time W q (t) is calculated by the following formula:

[0014]

[0015] Where λ(t) is the passenger arrival rate, μ is the service rate of each counter, and c(t) is the number of counters configured at time t. The model assumes that the passenger arrival process follows a Poisson distribution, and the service process of the counter is an exponential distribution. On this basis, by analyzing the relationship between the passenger arrival rate λ(t) and the service rate μ of the counter, the model calculates the average waiting time W q (t) of passengers at each time t.

[0016] By modeling the passenger flow in different time periods, the queuing theory model can provide predictions for different counter configurations c(t). The model also allows automatic adjustment of counter configuration based on changes in passenger arrival rate λ(t) and service rate μ to ensure optimal service level and resource utilization.

[0017] Preferably, the objective function aims to minimize the queuing time, passenger waiting time, and resource configuration cost at the same time, and the optimal control theory optimization process is carried out by the following objective function:

[0018] J = ∫0 T [Q(x(t)) + R(u(t))]dt

[0019] Where Q(x(t)) is a cost function related to passenger waiting time and queue length, representing the cost of passenger waiting; R(u(t)) is the resource cost brought by counter configuration, representing the cost of equipment construction and operation.

[0020] The optimal control theory is applied to dynamically adjust the counter configuration to maximize resource utilization and reduce passenger waiting time. The objective function J balances the resource cost and social cost in the system, minimizing the overall cost. Specifically, Q(x(t)) is the cost function related to the queue length and waiting time, which reflects the waiting cost of passengers, especially important during peak hours. R(u(t)) represents the cost of resource configuration, including equipment construction, personnel cost, and operating expenses.

[0021] Through the solution of optimal control, the number of counters c(t) can be adjusted in real time to achieve the best resource allocation in the shortest time. The model takes into account various external changes and dynamically adjusts the system to minimize the operating cost of the airport, the waiting time of passengers, and the optimization of resource utilization.

[0022] Preferably, the optimal control method dynamically adjusts the number of counters c(t) according to the system state x(t) by solving the minimum objective function J to achieve the optimal solution in the optimization process, thereby realizing the optimal configuration scheme. The objective function J is the optimal solution considering the passenger waiting time and resource configuration cost, and the control variable is the number of counters c(t), and the system state x(t) includes the queue length and service efficiency index. Each time the objective function J is calculated and combined with real-time data to adjust the counter configuration, ensuring that the system always remains in the optimal state.

[0023] The solution process combines optimization algorithms to dynamically monitor the system state and calculate the optimal solution for adjusting the number of counters in real time, thereby minimizing the operating cost of the system and the waiting time of passengers.

[0024] Preferably, the dynamic game theory simulates the game between the airport management and the airlines, and the game model optimizes the decisions of the airport management and the airlines in counter configuration and flight scheduling by solving the Nash equilibrium, so that the objectives of the two parties are simultaneously optimized.

[0025] In airport management, the airport management and the airlines are two main stakeholders. The goal of the airport management is to maximize resource utilization and reduce idle resources, while the airlines aim to improve passenger satisfaction and reduce queue time. Through the dynamic game model, the decision-making process of both parties can be simulated to ensure that their objectives are balanced in the overall system.

[0026] Using Nash equilibrium solution, the airport management and the airlines will adjust their strategies according to the other party's strategy. Ultimately, the model finds a best balance point by optimizing counter configuration and flight scheduling, which meets the airlines' demand for service quality and ensures the optimization of resource configuration for the airport management.

[0027] Preferably, the real-time data collection monitors and records passenger arrival rate, queue length, and counter usage data through sensors, camera devices, and other monitoring equipment. This data is further input into the optimization system for real-time analysis and adjustment.

[0028] Data collection is a critical step in this method. Through sensors, cameras, and other monitoring equipment installed at key locations in the airport, real-time collection of passenger arrival rate, queue length, and counter usage data is achieved. This data continuously flows into the optimization system for real-time analysis by the system.

[0029] The optimization system will calculate in real-time whether the current counter configuration meets passenger demand and make adjustments based on current traffic. During peak periods, the system will automatically increase the number of counters based on real-time collected queue length and passenger arrival data to alleviate congestion. The real-time nature of data collection and feedback ensures that counter configuration can respond to operational needs at any time.

[0030] Preferably, the optimization system adjusts the counter configuration based on real-time passenger demand through a real-time feedback mechanism, ensuring that the system always operates in an optimal state.

[0031] The purpose of the real-time feedback mechanism is to automatically adjust the counter configuration based on changing passenger demand. Whenever the system state changes (queue length or arrival rate changes), the optimization system will feed back the adjustment of the number of counters c(t) to the control execution module.

[0032] The real-time nature of this mechanism ensures that counter configuration can quickly respond to changes. If the system detects an abnormal increase in passenger arrival rate during a certain period, the system will immediately increase the number of counters based on model calculations to avoid long queues. At the same time, the system will also monitor the idle rate of the counters to prevent excessive configuration and waste of resources.

[0033] Preferably, the optimization system uses machine learning or data mining algorithms to model historical operational data through a real-time data analysis module, and predicts future passenger flow and passenger behavior patterns based on the modeling results. Based on this, the counter configuration plan is adjusted to achieve optimal resource allocation and reduce excessive configuration or resource waste in dynamic adjustment.

[0034] To cope with future passenger flow fluctuations, the optimization system uses machine learning or data mining algorithms to model historical operational data through a real-time data analysis module. The system analyzes passenger flow trends over the past few months or even years to predict future passenger arrival patterns and behavior.

[0035] Through these prediction data, the optimization system can make early prediction of future peak or low period, dynamically adjust the counter configuration scheme, and avoid excessive configuration or resource waste. If it is predicted that the peak period of a holiday will come, the system can configure more counters in advance according to the past similar situation, to ensure that passengers can be processed quickly during the peak period.

[0036] Preferably, the method further comprises simulation evaluation of different counter configuration schemes, by establishing a variety of scene simulation models, evaluating the performance of each configuration under different passenger flow environment, and comparing and selecting the optimal configuration scheme for implementation in combination with operation cost and passenger satisfaction index.

[0037] In order to ensure the feasibility and effectiveness of the optimal configuration scheme, the system simulates and evaluates different counter configuration schemes by establishing a variety of scene simulation models. The system simulates a variety of passenger flow environments, including holiday peak period, regular daily peak period, and low period.

[0038] Through simulation of different configuration schemes, the system can evaluate the performance of each configuration under a specific environment, and select the most suitable configuration scheme for the current operation environment in combination with operation cost and passenger satisfaction factors. This simulation evaluation provides data support for the configuration of airport check-in and delivery counters, and ensures the scientificity and accuracy of the decision.

[0039] An airport check-in and delivery counter configuration planning device based on the above method, the device is used to execute the above method, the device comprises:

[0040] A data collection module for collecting and transmitting passenger arrival rate, counter service rate, queuing time, system limitation condition data; a queuing theory model module for calculating passenger queuing time based on M / M / c queuing model and performing preliminary counter configuration evaluation; an optimal control module for optimizing objective function and dynamically adjusting the number of counters according to optimal control theory;

[0041] A dynamic game module for simulating the game between the airport management and the airlines, and obtaining the optimal configuration scheme by solving the game model;

[0042] A real-time feedback module for collecting and feeding back running state data in real time, and adjusting the number of counters according to real-time data to maintain the optimal configuration of the system;

[0043] A control execution module for outputting the optimal counter number configuration instruction to the airport management system to control the counter configuration in real time; through the coordinated work of different modules, the automatic airport check-in and delivery counter configuration planning is realized. The data collection module, the queuing theory model module, the optimal control module, the dynamic game module, and the real-time feedback module each perform its specific task, and through data flow, a complete optimization control chain is formed.

[0044] The control execution module of the system receives the optimization result and adjusts through the automatic control system without manual intervention. The cooperative work of all modules enables the airport to flexibly adjust the counter configuration under different time periods and passenger flow conditions, thereby improving efficiency and optimizing resource allocation.

[0045] The application provides an airport check-in and consignment counter configuration planning method and device. The application has the following beneficial effects:

[0046] 1. The application adopts a dynamic counter configuration scheme based on real-time data acquisition and feedback mechanism, achieving the technical effect of dynamically adjusting the number of counters during peak periods. Compared with the scheme in the prior art that simply relies on static models or empirical rules, the application can respond to changes in passenger flow in real time and accurately adjust the counter configuration, thereby effectively avoiding long queues of passengers during peak periods and reducing resource waste during low periods.

[0047] 2. The application dynamically optimizes the configuration of airport check-in and consignment counters by introducing optimal control theory and game models, achieving the technical effect of balancing passenger waiting time and resource use. Compared with the scheme that relies on experience to set the number of counters, the application can accurately adjust the number of counters according to real-time passenger flow, thereby significantly improving passenger satisfaction and avoiding negative experiences caused by long queues in the past.

[0048] 3. The application can quickly adjust and optimize the scheme according to real-time changes in the environment by integrating a real-time feedback mechanism, achieving the technical effect of responding to sudden passenger flow fluctuations. Unlike the system in the prior art that relies more on fixed models or manual intervention, the application automatically adjusts resource allocation under complex actual operating conditions, enabling the system to flexibly respond to changes in different scenarios such as holidays and special events, and maintaining stable operation.

[0049] 4. The application optimizes resource allocation between airport management and airlines through a dynamic game model, achieving the cost control effect of achieving a win-win situation. Compared with the one-sided optimization model in the prior art, the application not only improves resource utilization and reduces idle resource waste, but also reduces unnecessary investment while meeting passenger demand, effectively reducing the operating cost of the airport. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 is a method flowchart of the application;

[0051] Figure 2 is a device system architecture diagram of the application. DETAILED DESCRIPTION

[0052] With reference to the drawings of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the protection scope of the present application.

[0053] Please refer to the drawings of the present application Figure 1 -attached Figure 2 The embodiments of the present application provide an airport check-in consignment counter configuration planning method, comprising:

[0054] S1: data collection and preprocessing:

[0055] Data collection and acquisition:

[0056] In the present embodiment, data collection is carried out through various devices and sensors. Various devices in the airport, including passenger flow sensors, counter use monitors, queue length monitoring devices, are included in the data collection system. The data collection module can automatically collect the following data in each key area of the airport:

[0057] Passenger arrival rate λ(t): represents the number of passengers arriving per unit time. These data are collected through sensors at access control systems, security checkpoints, and boarding gate locations;

[0058] Counter service rate μ: the number of passengers that each counter can handle per minute, usually obtained by monitoring the service time and passenger processing time of each counter through the background system;

[0059] Queue length L q (t): represents the number of passengers waiting for service at a certain time, usually counted in real time by sensors or monitoring devices in the queue area.

[0060] Data cleaning and standardization:

[0061] After data collection, the system needs to clean and standardize the original data. Generally, data may have missing values, outliers, or inconsistent formats, which will directly affect the accuracy of the model and the optimization results if not processed. In order to ensure the quality of the data, the cleaning process includes the following steps:

[0062] Remove invalid data: such as duplicate records, error records (impossible negative values).

[0063] Fill in missing data: use interpolation method, mean filling method or other statistical methods to fill in missing data to ensure the integrity of the input data of the model.

[0064] Outlier removal: When some data values are obviously out of reasonable range (sensor failure or human error), these data are marked as outliers and removed from the dataset.

[0065] In the process of standardization, all data units will be uniformly converted. All time units are unified as minutes, and the dimensions of different sensor data are unified to the same unit to ensure the consistency of subsequent model calculations.

[0066] Specifically, the counter service rate μ is adjusted according to the performance of the equipment, and the passenger arrival rate λ(t) fluctuates according to the peak period and holiday factors, so it is necessary to standardize each data according to the different data sources. Time stamp is used to normalize all data in time series to ensure the consistency of data in time dimension.

[0067] Estimation and prediction of passenger arrival rate:

[0068] In some embodiments, the passenger arrival rate λ(t) is a key input parameter, which is affected by time, season, holiday and other factors. Therefore, the present application uses a combination of historical data and real-time data to estimate the arrival rate in the future when preprocessing data.

[0069] First, the system will establish a passenger flow prediction model according to historical data, and fit a sinusoidal function through historical data to represent the periodic fluctuation of passenger arrival rate in a day:

[0070]

[0071] Where:

[0072] λ0 is the basic passenger arrival rate (daily average value);

[0073] λ(t) is the fluctuation amplitude of the arrival rate;

[0074] T is the period (24 hours represent the passenger flow fluctuation in a day);

[0075] t is the current time.

[0076] This estimation method is based on historical data to estimate the passenger flow fluctuation in the future. Specifically, if it is during the holiday or large-scale activity, the system will adjust the estimated amplitude Δλ or period T of the arrival rate according to the historical data, so that the model is more close to the actual situation.

[0077] Data storage and transmission:

[0078] All the cleaned and standardized data will be transmitted to a database or cloud platform for storage. These data are transmitted through the data transmission module, using efficient data transmission protocols (MQTT, HTTPs) to ensure the real-time and security of the data. The data storage module provides stable support for subsequent model calculations and ensures that data can be read and written smoothly under high concurrency conditions.

[0079] In some embodiments, the system uses distributed storage technology to improve the fault tolerance and access efficiency of data. Through distributed databases, data can be allocated to multiple storage nodes on demand, avoiding single point failures and quickly recovering data in the event of failure. The redundant storage mechanism of data also enables the system to ensure the integrity and security of data.

[0080] Data analysis and prediction preparation:

[0081] Once the data is stored, the system will further analyze the data to prepare for subsequent model optimization. The data analysis module will use statistical analysis and machine learning techniques to uncover the patterns behind the data. The system will identify certain periods of time when passenger arrival rates have special fluctuations, or certain areas where queue times are too long. Based on these analysis results, the system can provide improvement suggestions and optimization solutions for subsequent steps.

[0082] For example, during certain holidays, certain flights or airlines may bring larger passenger flow fluctuations. The system identifies these patterns through modeling and learning from historical data, and adjusts the number of counters in advance based on the prediction results to cope with future changes.

[0083] S2: Establishment and adjustment of queuing theory model:

[0084] In this embodiment, based on the construction of the M / M / c queuing model, the arrival process of passengers and the service process of counters are first considered. In this model, the passenger arrival rate λ(t) is considered as a function of time, representing the number of passengers arriving per unit time, while the counter service rate μ is the number of passengers processed per minute per counter. For multi-counter configuration, use c(t) to represent the number of counters configured at time t. At this time, the queue time W q (t) can be calculated by the following formula:

[0085]

[0086] Where W q (t): represents the average waiting time of passengers at time t (unit: minutes), which reflects the time passengers need to wait in the queue.

[0087] λ(t): represents the passenger arrival rate (unit: person / minute), i.e., the number of passengers arriving per unit time. This value is usually predicted by historical data and varies according to different time periods or special events.

[0088] μ: represents the service rate of each counter (unit: person / minute), i.e., the number of passengers each counter can handle per minute.

[0089] c(t): represents the number of counters configured at time t, which is a control variable in the model and needs to be dynamically adjusted according to the actual passenger flow.

[0090] The core goal of this queuing model is to calculate W q (t) to determine whether the number of counters c(t) needs to be adjusted. If the calculated W q (t) value is high, it indicates that the waiting time for passengers in the queue is too long, and the number of counters needs to be increased; conversely, if W q (t) value is low, it means that the number of counters is too large, resulting in resource waste, and the system can reduce the number of counters.

[0091] Dynamic adjustment of the number of counters:

[0092] In order to adapt to different passenger flow demands, the number of counters c(t) in the queuing model must be dynamically adjusted. By collecting the passenger arrival rate λ(t) and the counter service rate μ in real time, combined with the calculated queuing time W q (t), the system can determine whether to increase or decrease the number of counters.

[0093] During peak periods or special events, the passenger arrival rate λ(t) increases sharply, and the system needs to increase the number of counters to cope with the instantaneous passenger flow pressure. Correspondingly, when the passenger flow decreases (during off-peak periods or non-peak periods), the system can reduce the number of counters to avoid resource waste. For example, during the peak period of holidays, the system will increase the number of counters c(t) to handle more passengers, while during normal or late-night periods, it will reduce unnecessary counter configuration.

[0094] In order to achieve this dynamic adjustment, an optimal control algorithm is used in this embodiment to automatically calculate the optimal number of counters. Through optimal control theory, the system can dynamically adjust c(t) according to the changes in λ(t) and W q (t) to ensure maximum utilization of resources while minimizing passenger waiting time.

[0095] Special processing during peak and off-peak periods:

[0096] The system's special handling strategy for peak and off-peak periods, through the analysis of historical data and the combination of real-time data, can predict and adjust the passenger flow in different time periods. In peak periods, the arrival rate λ(t) of passengers increases, leading to a significant increase in queuing time. At this time, the system increases the number of counters c(t) through the queuing theory model to shorten the waiting time and improve service quality. Specifically, the system will adjust the number of counters in advance according to historical holiday data or event predictions.

[0097] In the off-peak period, the passenger flow is relatively low, and the number of counters c(t) can be reduced accordingly. At this time, by reducing the number of counters, the airport can save operating costs and avoid over-investment. In actual operation, the system will predict the passenger flow in each time period according to the regularity of daily, weekly, and holiday, and flexibly adjust the number of counters.

[0098] For example, assuming that from 9 am to 11 am during a holiday, the passenger arrival rate λ(t) is at a peak, the system can increase the number of counters c(t) and reduce the number of counters during the normal period (2 pm to 5 pm), thereby effectively improving operational efficiency.

[0099] Dynamic adjustment of queuing model parameters

[0100] In order to more accurately reflect the actual situation, this embodiment also dynamically adjusts the parameters in the queuing model. In addition to the basic passenger arrival rate λ(t) and counter service rate μ, the model also considers other factors that affect service efficiency, such as equipment failure and the state of staff.

[0101] For example, assuming that a counter's service rate μ decreases due to equipment failure during a certain period, the system will automatically adjust the service rate μ of that counter, thereby more accurately simulating the actual service situation. To achieve this goal, the system will update the value of μ after each period according to the actual service situation, ensuring that the queuing theory model's calculation results are closer to actual operations.

[0102] S3: Application of optimal control theory:

[0103] Construction of optimal control objective function:

[0104] The optimal control theory requires us to first define an objective function JJJ that considers the impact of queuing time, resource allocation cost, and passenger experience. The form of the objective function is:

[0105] J = ∫0 T [Q(x(t)) + R(u(t))]dt

[0106] Where J is the overall objective function, representing the total cost within the time interval [0, T]. By minimizing J, this embodiment can achieve optimal counter allocation.

[0107] Q(x(t)) is the cost function related to the waiting time and queue length of passengers. Generally speaking, the longer the waiting time of passengers, the higher the social and economic cost, so it is necessary to minimize this part of the cost.

[0108] R(u(t)) is the resource cost required for adjusting the number of counters, representing the cost of equipment construction, operation and maintenance. Each additional counter will generate additional operating costs, so the cost function of this part also needs to be minimized.

[0109] Q(x(t)): the cost function related to the queuing behavior of passengers. This part of the cost mainly considers the factors of queue length and queue length.

[0110] R(u(t)): Resource cost related to the number of counter configuration. Specifically, increasing the number of counters will result in increased facility and personnel costs, so this part of the cost needs to be optimized.

[0111] x(t): system state variable, including passenger arrival rate λ(t), counter service rate μ, queue length L q (t). State variables represent the current state of the system, affecting the decision-making process.

[0112] u(t): control variable, i.e. the number of counters c(t) configured at time t, which is dynamically adjusted to achieve optimal configuration.

[0113] Specifically, within the time interval [0, T], the optimal control system will calculate the current passenger flow and queue situation in real time, and dynamically adjust the number of counters based on these data. Each adjustment will result in a change in the value of the objective function J, and the optimization algorithm will continue to adjust until the value of the objective function reaches the minimum, thereby achieving the optimal counter configuration.

[0114] Dynamic adjustment in the optimization process:

[0115] To achieve the optimal control goal, numerical optimization algorithm is used in the embodiment of the invention. Specifically, gradient descent method is used to solve the optimal value of the objective function J. The system can determine the best counter configuration scheme under given passenger arrival rate, queue situation and resource constraints, and the specific steps are as follows:

[0116] 1. Gradient descent method calculates the gradient (i.e. derivative) of the objective function with respect to the control variable, then updates the control variable along the negative gradient direction, so as to gradually approach the optimal value of the objective function. In this embodiment, the control variable is the number of counters c(t), which is updated by gradient descent method to minimize the total cost J;

[0117] 2、In the gradient descent method, first need to calculate the objective function J on the control variable c(t) partial derivative. Let Δc(t) represents the adjustment amount of the number of counters in each iteration, the update formula is as follows:

[0118]

[0119] Wherein:

[0120] c(t+1): the number of counters updated at the next time,

[0121] c(t): the number of counters at the current time,

[0122] η: learning rate, control gradient descent step size. Usually, a small learning rate is selected to ensure the stability of the algorithm convergence,

[0123] The partial derivative of the objective function J on the number of counters c(t) (gradient) indicates the sensitivity of the objective function to the change of the control variable.

[0124] 3、Gradient calculation:

[0125] The objective function J is the integral of time, so the embodiment first needs to calculate the partial derivative of the objective function J on c(t). According to the chain rule, the partial derivative of the objective function can be decomposed into the following two parts:

[0126]

[0127] Wherein:

[0128] Indicates the sensitivity of the queuing related cost to the change of the number of counters c(t), reflecting the change of the passenger waiting time when the number of counters changes, the influence on the system cost;

[0129] Indicates the sensitivity of the resource allocation cost to the change of the number of counters c(t), reflecting the influence of resource consumption on the system cost when the number of counters changes.

[0130] Specifically, the calculation of the gradient involves modeling Q(x(t)) and R(u(t)) through the queuing theory model and the optimal control model. The following is the expression form:

[0131] Gradient of passenger waiting cost:

[0132]

[0133] Wherein, λ(t) is the passenger arrival rate, W q (t) is the average waiting time of passengers. Calculate the change of waiting time when the number of counters changes, so as to get the sensitivity of the queuing time.

[0134] Gradient of resource cost:

[0135]

[0136] where α and β are resource cost coefficients related to the configuration of the counter, typically reflecting the cost of equipment construction and maintenance. By taking the derivative of the resource cost function, this embodiment can calculate the impact of changes in the number of counters on resource costs.

[0137] Once the gradient is calculated, the system can adjust the number of counters through an update formula. This process is repeated in each iteration until the objective function J converges to a minimum value. The specific iteration process is as follows:

[0138] Initialization: Set the initial number of counters c(0) and choose an appropriate learning rate η.

[0139] Iterative update: Calculate the gradient of the current objective function J with respect to c(t) and update the number of counters c(t):

[0140]

[0141] Convergence judgment: If the change in the objective function J is less than the set threshold or the maximum number of iterations is reached, stop updating and consider the gradient descent method to have converged, obtaining the optimal counter configuration.

[0142] Dynamic adaptability in peak and trough periods:

[0143] In this embodiment, the optimal control theory has high dynamic adaptability. Specifically, the system can flexibly adjust the number of counters c(t) according to changes in passenger flow. For example, during peak periods, the arrival rate λ(t) of passengers will increase significantly, leading to an increase in queue time and queue length. At this time, the optimal control theory will automatically calculate the best time and number of increased counters to ensure that the waiting time of passengers is not too long.

[0144] Specifically, assume that during a certain period, the arrival rate λ(t) of passengers suddenly increases. The system analyzes the changes in arrival rate through prediction and adjusts the parameters in the objective function J, so that the number of counters c(t) can be quickly increased to cope with the sudden surge in passenger flow.

[0145] In the low period, when the passenger flow decreases, the system saves resources by reducing the number of counters c(t). At this time, the optimal control system accurately calculates the most resource-saving counter configuration scheme under the premise of maintaining service quality by analyzing historical data and real-time information.

[0146] Integration of real-time data and feedback mechanism:

[0147] Another advantage of the present invention is the integration of real-time data feedback mechanism. The system acquires passenger arrival rate, counter service rate, and queue length data in real-time and passes these information to the optimal control module. The optimal control system dynamically calculates and adjusts the counter number c(t) based on these data.

[0148] For example, when the system detects a sudden surge in passenger arrival rate during a certain period, the optimal control theory re-evaluates the objective function based on the new data and dynamically adjusts the counter number. This process is adaptive and does not require human intervention, greatly improving the response speed and decision-making efficiency of the system.

[0149] S4: Application of dynamic game theory:

[0150] Construction of game model:

[0151] The construction of the game model is based on the Nash equilibrium theory. In the game between the airport and the airline, both parties choose the optimal strategy to achieve the optimal counter configuration and flight arrangement. Specifically, the airport management wants to reduce the queuing time of passengers by reasonably configuring the counter number c(t), while ensuring the optimal use of resources; the airline wants to optimize passenger flow, reduce flight delays, and improve passenger satisfaction.

[0152] Objective function of airport management:

[0153] The objective function of the airport management is to maximize the efficiency of resource use and minimize operating costs. In this embodiment, the objective function of the airport management can be represented as:

[0154] J airport =∫0 T [R utilization (c(t))+C cost (c(t))]dt

[0155] Where:

[0156] R utilization (c(t)) represents the efficiency of resource use, which is usually related to factors such as counter utilization and passenger flow. This term of the cost function aims to maximize the efficiency of resource use by optimizing the counter configuration c(t).

[0157] C cost (c(t)) represents the resource cost related to the configuration of the counter number c(t). Generally, increasing the number of counters means more investment in facilities and operating costs, so this term of the cost function aims to minimize the resource configuration cost while ensuring service quality.

[0158] Objective function of airline:

[0159] Airline companies focus on improving passenger satisfaction and flight punctuality, especially during peak hours, as passenger queuing time and waiting time directly affect flight punctuality and customer experience. Therefore, the objective function of an airline company can be represented as:

[0160] J airline =∫0 T [S satisfaction (L q (t))+P punctuality (λ(t))]dt

[0161] Where:

[0162] S satisfaction (L q (t)) represents passenger satisfaction, which is usually related to queuing time L q (t), counter configuration, and service quality. The longer the waiting time, the lower the satisfaction, and the airline company hopes to improve passenger satisfaction by reducing queuing time.

[0163] P punctuality (λ(t)) represents the punctuality of the flight, which is usually related to the passenger arrival rate λ(t) and the counter service rate μ. The airline company hopes to improve the punctuality of the flight by optimizing the counter configuration c(t) to reduce flight delays.

[0164] Strategy selection and optimal solution in game model:

[0165] The core of the game model is strategy selection. In the embodiments of the present application, the airport management and the airline company each have a set of strategies to choose from. The strategy of the airport management is to choose the appropriate number of counters c(t), while the strategy of the airline company is to choose the appropriate flight scheduling scheme.

[0166] 1. Selection of control variables:

[0167] The control variable of the airport management is the number of counters c(t), and the goal is to optimize resource allocation;

[0168] The control variable of the airline company is the flight scheduling scheme, which affects the arrival rate λ(t) and the punctuality of the flight.

[0169] 2. The airport management and the airline company update their control variables c(t) and flight scheduling scheme respectively through gradient descent method, and the update formula can be represented as:

[0170]

[0171] Where:

[0172] c(t+1) and λ(t+1) are the updated number of counters and flight scheduling scheme respectively;

[0173] η airport and η airline is the learning rate, controlling the update step size;

[0174] is the partial derivative of the airport manager's objective function with respect to the number of counters c(t);

[0175] is the partial derivative of the airline's objective function with respect to the passenger arrival rate λ(t).

[0176] 3. Gradient calculation:

[0177] To optimize these objective functions using gradient descent, the embodiment first calculates the gradient of the objective functions with respect to the policy variables:

[0178] Gradient for the airport manager:

[0179]

[0180] This gradient represents the relationship between resource utilization and cost for the airport manager under different counter configurations. If C cost (c(t)) = αc(t) 2 , then its derivative is:

[0181]

[0182] Gradient for the airline:

[0183]

[0184] If S satisfaction (L q (t)) = βL q (t) and L q (t) has a linear relationship with λ(t), then we can get:

[0185]

[0186] 4. Iterative process and convergence:

[0187] Gradient descent iteratively adjusts the policy variables based on the calculated gradient until the objective function converges to a minimum. The system updates the number of counters c(t) and the flight scheduling scheme λ(t) at each iteration until the stopping criteria are met (the gradient is less than a pre-set threshold or the maximum number of iterations is reached).

[0188] Dynamic adjustment in the game:

[0189] The game model in this embodiment is not only based on static analysis, but also combines real-time data and dynamic adjustment mechanism. At each time, the system will make real-time calculation and optimization decision based on the latest passenger arrival rate λ(t), queuing time L q (t), counter configuration data c(t).

[0190] When the airline requires to increase flights, the system will increase the number of counters according to the new passenger flow prediction to ensure that passengers can check-in and board on time. When the airport management adjusts the counter configuration, the airline will adjust the flight schedule according to the new configuration, so as to achieve the best resource utilization and passenger satisfaction.

[0191] In some embodiments, the system uses distributed computing to speed up the game process, quickly solves the optimal solution under different strategies through parallel computing, and realizes real-time decision adjustment.

[0192] S5: Real-time data acquisition and feedback mechanism:

[0193] Real-time data acquisition:

[0194] Data acquisition is the basis for the system to respond to changes in the external environment. Through sensors, cameras and other monitoring devices deployed in different locations of the airport, the real-time data acquisition module can obtain information about passenger flow, counter service rate, and passenger queuing. Specifically, the key data collected includes but is not limited to:

[0195] Passenger arrival rate λ(t): This is the data monitored by the system in real time, indicating the number of passengers arriving per unit time. Through sensors at security checkpoints and boarding gates, the passenger arrival situation at each time can be obtained.

[0196] Counter service rate μ: The number of passengers that each counter can handle per unit time. Through real-time monitoring of passenger processing time by the back-end system for each counter, this value is calculated.

[0197] Queuing time L q (t): Indicates the number of passengers waiting for service at a certain time. The queue length and time are calculated by the monitoring devices (infrared sensors) or video analysis system in the queuing area.

[0198] Counter usage: The working status of each counter is monitored in real time through counter status sensors to determine whether it is idle or busy. If a counter fails, the system can also feedback in time and respond.

[0199] Generally, the data collection process involves multiple sensors working in coordination, using wireless communication technology to upload the collected data to a central processing system. In this way, the system can understand the changes in key indicators in real time, thus providing real-time support for subsequent optimization decisions.

[0200] Data processing and real-time feedback:

[0201] After data collection is complete, the system enters the data processing phase. First, all collected data will be processed through a data cleaning and filtering module. This process will delete invalid data or outliers, ensuring that the data input into the system is accurate and effective. For example, when a sensor fails, the system can automatically mark and skip the abnormal data collected by that device.

[0202] After data processing, the system will standardize the key data of passenger arrival rate λ(t), queue length L q (t) and counter usage to ensure consistency of information from different data sources. All processed data will be sent to the real-time optimization module for further analysis.

[0203] Through the real-time feedback mechanism, the system can automatically adjust the counter configuration c(t) according to the collected real-time data. When the passenger arrival rate λ(t) and queue length L q (t) increase, the system will automatically increase the number of counters according to the optimal control algorithm; when the passenger flow decreases, the number of counters will decrease, avoiding resource waste.

[0204] Adaptive and intelligent adjustment mechanism:

[0205] Another important feature of this embodiment is the adaptive optimization mechanism. The system not only can automatically adjust the counter configuration according to real-time data, but also can intelligently adjust the optimization strategy under different operating conditions. Specifically, when the system identifies atypical passenger flow patterns (during holidays or special events), it will automatically adjust the relevant parameters in the objective function, thus optimizing the counter configuration strategy.

[0206] System response speed and real-time decision-making:

[0207] To ensure the efficiency of the real-time feedback mechanism, this embodiment uses a high-efficiency data processing and computing platform, combining multi-core processors and distributed computing technology to ensure that the system can complete data processing and counter configuration adjustment within seconds. In this way, the system can quickly respond to passenger flow fluctuations, optimize counter configuration in real time, maximize airport resource utilization efficiency, and avoid long waiting times for passengers.

[0208] Data security and fault-tolerant mechanism:

[0209] Considering the high reliability requirement of airport operations, the present embodiment also includes data security and fault-tolerant mechanisms. All real-time data transmission and storage use encryption methods to ensure data security during transmission. At the same time, the system has built-in redundant backup mechanisms, which can restore data from backup nodes when a device fails or data is lost, ensuring uninterrupted optimization decisions.

[0210] S6: Optimization execution and integration:

[0211] Execution optimization results and system integration:

[0212] In this embodiment, the optimization execution module is combined with the aforementioned optimization algorithm to ensure that the counter configuration c(t) after each optimization can be quickly implemented in the airport management system. The system will convert the optimization calculation results into specific operation instructions through the automatic control module, notify the relevant departments in real time, and execute the adjustment plan. This process ensures that the number of counters, personnel scheduling, and equipment usage can respond to changes immediately and effectively.

[0213] For example, when the system calculates that the number of counters c(t) needs to be increased through optimal control theory, the optimization execution module will not only generate adjustment instructions, but also through the interface with the personnel scheduling system and the equipment management system, ensure that additional staff are dispatched in place and equipment is properly activated or adjusted.

[0214] Real-time generation and feedback of execution instructions:

[0215] In some embodiments, the optimization execution module is closely integrated with optimization calculation through real-time feedback mechanisms to ensure that each adjustment is timely and accurate. When the system calculates the optimal number of counters c(t) based on real-time data, the execution module will immediately generate instructions and pass them to the automatic control system, including but not limited to counter number adjustment, personnel scheduling, and equipment usage.

[0216] For example, suppose the system calculates that 4 counters c(t) need to be added during peak hours to handle the surge in passenger flow. The execution module will pass the instructions to the control system within a few seconds, automatically activate the corresponding counters, and ensure that the corresponding staff are on duty. This automated execution method ensures that the adjustment plan can take effect immediately, avoiding the delay of manual operation and improving response efficiency.

[0217] Dynamic monitoring and adjustment of the execution module:

[0218] The optimization execution module not only executes instructions, but also monitors the effects of the adjusted counter configuration in real time. Specifically, the execution module continuously monitors the following key indicators: queue length L q(t), the passenger arrival rate λ(t), the counter usage, and the service rate μ. When the monitoring system detects that the queuing time is too long or the resource allocation is improper, the system automatically fine-tunes to ensure that the number of counters is always within the optimal configuration range.

[0219] Collaboration with other systems:

[0220] In this embodiment, the optimization execution module not only focuses on the adjustment of the number of counters, but also needs to coordinate the use of other operating resources to ensure the collaboration of all systems. In addition to counter adjustment, the execution module also exchanges data and collaborates with personnel scheduling, security process, and equipment management systems to ensure that while optimizing the counter configuration, the resources in other links can also be adjusted synchronously.

[0221] For example, assuming that the system decides to increase the number of counters c(t) during peak hours, the execution module will automatically arrange more staff to the corresponding counter positions through collaboration with the personnel scheduling system; at the same time, through the interface with the security system, the system will require adjustment of the number of security channels to ensure smooth operation of the entire airport. In this case, the execution module not only optimizes the counter configuration, but also ensures the smooth operation of other operating links, avoiding the occurrence of bottleneck problems.

[0222] The airport check-in and consignment counter configuration planning device described below can be correspondingly referred to the airport check-in and consignment counter configuration planning method described above.

[0223] The device comprises:

[0224] A data acquisition module for collecting and transmitting passenger arrival rate, counter service rate, queuing time, system limit condition data; a queuing theory model module for calculating passenger queuing time based on the M / M / c queuing model and performing preliminary counter configuration evaluation; an optimal control module for optimizing the objective function according to the optimal control theory and dynamically adjusting the number of counters;

[0225] A dynamic game module for simulating the game between the airport management and the airlines, and obtaining the optimal configuration scheme by solving the game model;

[0226] A real-time feedback module for collecting and feeding back the running state data in real time, and adjusting the number of counters according to the real-time data to maintain the optimal configuration of the system;

[0227] A control execution module for outputting the optimal counter number configuration instruction to the airport management system to control the counter configuration in real time.

[0228] The device in this embodiment can be used to execute the above-mentioned method embodiments, and the principles and technical effects are similar, which will not be repeated here.

[0229] While embodiments of the application have been shown and described, it is to be understood that the embodiments described are merely exemplary of the principles and application of the present application. Numerous modifications and adaptions can be effected without departing from the spirit and scope of the present application, which is not limited to the exact construction and arrangement described. It is intended, therefore, to cover all modifications and adaptions that fall within the scope of the claims and their equivalents.

Claims

1. A method for planning the configuration of airport check-in and baggage drop-off counters, characterized in that: Includes the following steps: S1. Collect real-time or historical data to obtain passenger arrival rate, counter service rate, and system limitation parameters; S2. Based on the collected data, construct a queuing theory model and conduct a preliminary assessment of the check-in counter configuration using the M / M / c queuing model; S3. Using optimal control theory, establish an objective function to optimize the configuration scheme and minimize the comprehensive objective between queuing time, passenger waiting time and resource allocation cost; S4. Combining dynamic game theory, simulate the game between airport management and airlines, and solve for the optimal counter configuration and flight schedule through Nash equilibrium; S5. Collect operational data in real time and feed it back to the optimization system. Adjust the number of counters in real time to keep the system running at its best. S6. Integrate the optimization algorithm into the airport management system, continuously optimize it, and ensure that the configuration and operation of airport check-in and baggage drop-off counters are always in the optimal state. The optimal control method solves by minimizing the objective function J and dynamically adjusts the number of counters c(t) according to the system state x(t) so that the objective function in the optimization process reaches the optimum, thereby achieving the optimal configuration scheme; The objective function aims to simultaneously minimize queuing time, passenger waiting time, and resource allocation cost. The optimal control theory optimization process is carried out through the following objective function: Where Q(x(t)) is a cost function related to passenger waiting time and queue length, representing the cost of passenger waiting; R(u(t)) represents the resource cost associated with counter configuration, indicating the equipment construction and operation costs; The dynamic game theory simulates the game between airport management and airlines. The game model optimizes the decisions of airport management and airlines in terms of counter allocation and flight scheduling by solving the Nash equilibrium, so that the goals of both parties are simultaneously optimal.

2. The airport check-in and baggage drop-off counter configuration planning method according to claim 1, characterized in that, The queuing theory model is constructed using the M / M / c queuing model, and the queuing time W q The formula for calculating (t) is: Where λ(t) is the passenger arrival rate, μ is the service rate of each counter, and c(t) is the number of counters configured at time t.

3. The airport check-in and baggage drop-off counter configuration planning method according to claim 1, characterized in that, The real-time data acquisition uses sensors and camera devices to monitor and record passenger arrival rates, queuing times, and counter usage data. This data is then further input into the optimization system for real-time analysis and adjustment.

4. The airport check-in and baggage drop-off counter configuration planning method according to claim 1, characterized in that, The optimization system uses a real-time feedback mechanism to feed back the adjustment results of the number of counters to the system, and adjusts the counter configuration according to the real-time needs of passengers to ensure that the system always operates in an optimal state.

5. The airport check-in and baggage drop-off counter configuration planning method according to claim 1, characterized in that, The optimization system uses a real-time data analysis module to model historical operational data using machine learning or data mining algorithms. Based on the modeling results, it predicts future passenger flow and passenger behavior patterns, and adjusts the counter configuration scheme accordingly. This dynamic adjustment achieves optimal resource allocation and reduces over-configuration or resource waste.

6. The airport check-in and baggage drop-off counter configuration planning method according to claim 1, characterized in that, The method further includes simulation evaluation of different counter configuration schemes. By establishing multiple scenario simulation models, the performance of each configuration under different passenger flow environments is evaluated, and the optimal configuration scheme is selected for implementation by combining operating costs and passenger satisfaction indicators.

7. An airport check-in and baggage drop-off counter configuration planning device based on the method of claim 1, characterized in that, The apparatus is used to perform the method, and the apparatus includes: The data acquisition module is used to collect and transmit data on passenger arrival rate, counter service rate, queue time, and system constraints. The queuing theory model module is used to calculate passenger queuing time and perform preliminary counter configuration evaluation based on the M / M / c queuing model. The optimal control module is used to optimize the objective function and dynamically adjust the number of counters based on optimal control theory. The dynamic game module is used to simulate the game between airport management and airlines, and obtain the optimal configuration scheme by solving the game model; The real-time feedback module is used to collect and report operational status data in real time, and adjust the number of counters based on the real-time data to maintain the optimal configuration of the system. The control execution module is used to output the optimal number of counters configuration instructions to the airport management system and control the counter configuration in real time.

Images