Check-in counter resource allocation method based on Monte Carlo simulation algorithm

Abstract

According to the check-in counter resource allocation method based on the Monte Carlo simulation algorithm, accurate prediction of check-in counter resources is achieved based on existing information of an airport, dependence on artificial experience is reduced, and prediction accuracy is improved; meanwhile, an airport passenger arrival probability density function is taken as an input condition of simulation calculation, the predicted passenger arrival density better fits the actual situation, and the solving result is more accurate; the Monte Carlo simulation algorithm is adopted for repeated sampling, the defect that single case scene satisfaction but not global satisfaction exists in single calculation simulation is avoided, the solving result is accurate, and the credibility is high; and an optimization algorithm model is established based on a time window thought, the global process can be reproduced and derived, and the reliability of a solving result is high.

Description

Technical Field

[0001] The present invention relates to the technical field of check-in counter resource configuration, and in particular to a check-in counter resource configuration method based on a Monte Carlo simulation algorithm. Background Art

[0002] 2 Domestic airports have carried out a wealth of innovative explorations in the construction of smart airports. The fully open check-in mode can effectively improve the utilization rate of check-in counters and facilitate passengers to choose the appropriate counter to check in their luggage. It has become one of the important contents of the smart construction of various airports. Under the traditional non-open check-in counter mode, airport airlines generally configure a certain proportion of check-in counters based on the size of the flight type and combined with manual experience, which leads to the problem of low utilization rate of check-in counters.

[0003] In order to improve the reasonable allocation of check-in counter resources, relevant research has been carried out at home and abroad. Currently, there are two main resource allocation methods: analytical method and simulation method;

[0004] The analytical method is mainly based on the knowledge of queuing theory in operations research. It regards the check-in counter as a service resource and the passengers as service objects. It uses the mathematical model of queuing theory to solve the problem. This method generally regards the arrival of passengers as an equal-probability random event that obeys a negative exponential distribution. As we all know, the probability density function of passenger arrival is a partial function. The assumptions of the analytical method of queuing theory are obviously greatly deviated from the actual distribution of passenger arrival at the airport, and the solution results have a large deviation.

[0005] The simulation method mainly relies on intelligent algorithms for simulation. It generally uses big data as input conditions and performs prediction and solution based on intelligent algorithms such as genetic algorithms, gradient decision algorithms, and machine learning. This method has less specific analysis of counter resources, passenger arrivals, etc. The results given do not have a rigorous derivation process and have a low confidence level. For risk considerations, airports and airlines generally only use it as a reference.

[0006] In summary, the traditional check-in counter resource configuration method relies heavily on manual experience. For safety reasons, the configuration redundancy is high and there is a high waste of resources. In recent years, the emerging counter resource configuration methods proposed cannot meet the airport requirements in terms of accuracy and confidence. Summary of the invention

[0007] In view of the deficiencies in the prior art, the present invention provides a check-in counter resource configuration method based on a Monte Carlo simulation algorithm, which solves the problems in the prior art.

[0008] According to an embodiment of the present invention, a check-in counter resource configuration method based on a Monte Carlo simulation algorithm comprises the following steps:

[0009] S1: Obtain flight data, passenger arrival data and counter service time data within a preset time period, and couple them to obtain a passenger arrival probability density function and a counter service time probability density function;

[0010] S2: The total number of luggage within a preset time period is obtained based on flight data and passenger arrival data. Based on the Monte Carlo algorithm, the passenger arrival probability density function and the counter service time probability density function are simulated and sampled to obtain the luggage arrival time set and the counter service time set within the preset time period.

[0011] S3: randomly obtain a check-in counter number, construct an optimization objective function based on the baggage arrival time set, the counter service time set and the check-in counter number, and calculate and solve the optimization objective function to obtain the service queue waiting time set of each baggage within the preset time period;

[0012] S4: repeat steps S1 to S3 N times to obtain N service queue waiting time sets, and calculate the queue time based on the N service queue waiting time sets;

[0013] S5: repeat steps S2 to S4 for a preset number of times to obtain a queuing time set, and obtain a satisfied queuing time set based on the queuing time set;

[0014] S6: Select the number of check-in counters that minimizes the number of centralized check-in counters required for the queuing time as the optimal configuration solution.

[0015] As an embodiment of the present invention, step S1 includes:

[0016] Obtain flight data, passenger arrival data, and counter service time data within a preset time period; flight data includes: number of flight seats, passenger load factor, and flight take-off and landing times; passenger arrival data includes: passenger arrival time and baggage coefficient; counter service time data includes: single service start time and single service end time;

[0017] The passenger arrival probability density function f(x) is obtained by coupling the three-parameter Weibull function. The formula of the passenger arrival distribution probability function f(x) is as follows:

[0018]

[0019] Among them, β>0 is the shape parameter, α>0 is the scale parameter, and μ>0 is the location parameter;

[0020] The normal distribution function is coupled to obtain the counter service time probability density function. The formula of the counter service time probability density function g(c) is as follows:

[0021]

[0022] Among them, μ is the population mean and σ is the population standard deviation.

[0023] As an embodiment of the present invention, the total number of luggage within a preset time period is obtained according to flight data and passenger arrival data, including:

[0024] The total number of baggage within a preset time period is calculated based on flight data and baggage factor. The calculation formula for the total number of baggage is as follows:

[0025] m=∑P j ·ε·η

[0026] Among them, m is the total number of luggage, P j is the number of seats on the flight, ε is the passenger load factor, and η is the baggage coefficient.

[0027] As an embodiment of the present invention, a passenger arrival probability density function and a counter service time probability density function are simulated and sampled based on a Monte Carlo algorithm to obtain a baggage arrival time set and a counter service time set within a preset time period, including:

[0028] Select a proposed distribution q(x) so that the proposed distribution q(x) covers the target distribution f(x); obtain a constant k1 so that k1·q(x)≥f(x) holds for all x;

[0029] Extract a sample AT1 from the proposed distribution q(x) and calculate the acceptance probability α1 of the sample AT1. The calculation formula is as follows:

[0030]

[0031] Randomly generate a uniformly distributed number U1, and determine whether the acceptance probability α1 of sample AT1 is not less than U1; if not, accept sample AT1 as the baggage arrival time; if less, reject sample AT1;

[0032] Repeat the above steps until m baggage arrival times are obtained, and obtain the baggage arrival time set {AT1, AT2, ..., AT i ,…,AT m};

[0033] As an embodiment of the present invention, based on the Monte Carlo algorithm, the passenger arrival probability density function and the counter service time probability density function are simulated and sampled to obtain a baggage arrival time set and a counter service time set within a preset time period, and further includes:

[0034] Select a proposed distribution p(c) so that the proposed distribution p(c) covers the target distribution g(c); obtain a constant k2 such that k2·p(c)≥g(c) holds for all c;

[0035] Extract a sample ST1 from the proposed distribution p(c) and calculate the acceptance probability α2 of sample ST1. The calculation formula is as follows:

[0036]

[0037] Randomly generate a uniformly distributed number U2, and determine whether the acceptance probability α2 of sample ST1 is not less than U2; if not, accept sample ST1 as the counter service time; if less, reject sample ST1;

[0038] Repeat the above steps until m counter service hours are obtained, and obtain the counter service time set {ST1, ST2, ..., ST i ,…,ST n}.

[0039] As an embodiment of the present invention, step S3 includes:

[0040] The optimization objective function is constructed based on the baggage arrival time set, counter service time set and the number of check-in counters. The optimization objective function and its constraints are as follows:

[0041]

[0042]

[0043] Where X is the set of baggage that needs to be checked in, i represents the i-th baggage, X = {1, ..., j, i, ..., m}; T is the set of service time periods, t represents the t-th time unit, T = {0, ..., t, ..., p}; m is the total number of baggage that needs to be checked in within the scheduled time period, in pieces; p is the total length of the scheduled time period, in seconds; Q is the total number of check-in counters open for baggage check-in, in units; M

[0044] is a very large number; AT i is the estimated arrival time of the i-th piece of luggage, in seconds; ST i The estimated service time for the i-th piece of luggage, in seconds; RT i DT is the service start time of the i-th piece of luggage, in seconds; i is the end time of the i-th piece of luggage service, in seconds; R i,t is a 0-1 variable. When baggage i is being checked in at the check-in counter in the tth time period, it is 1, otherwise it is 0; y i,j is a 0-1 variable, which is 1 when the service completion time of bag i is earlier than the service start time of bag j, otherwise it is 0;

[0045] The improved NSGA-Ⅱ algorithm is used to solve and calculate the optimization objective function, and the baggage service situation within the preset time period is obtained; the baggage service situation includes: the baggage service start time set, the baggage service end time set and the counter receiving the service;

[0046] The service queue waiting time set of each baggage is calculated based on the baggage service start time set and the baggage service end time set. The calculation formula of the service queue waiting time set of each baggage is as follows:

[0047]

[0048] Where, ΔT i is an element in the service queue waiting time set, and the service queue waiting time set is represented by {ΔT1, ΔT2, …, ΔT i ,…,ΔT m}.

[0049] As an embodiment of the present invention, the queuing time includes: the average queuing time of passengers and the maximum queuing time ΔT max ;

[0050] Calculate the queue time based on N service queue waiting time sets, including:

[0051] Calculate the maximum passenger queue time ΔT based on N service queue waiting time sets max , the average queuing time of passengers ΔT max The calculation formula is as follows:

[0052] ΔT max =max{ΔT 1,1 ,...,ΔT i,j ,...ΔT m,N}

[0053] Calculate the average passenger queuing time based on N service queue waiting time sets Average waiting time for passengers The calculation formula is as follows:

[0054]

[0055] Where, ΔT i,b is the i-th value in the b-th service queue waiting time set, b∈(0,N).

[0056] As an embodiment of the present invention, obtaining a satisfied queuing time set based on the queuing time set includes:

[0057] Select a queue time to focus on and determine whether it meets the average queue time of passengers. Not greater than the preset average queuing time Tak , and the maximum queuing time of passengers ΔT max Not greater than the preset maximum queue time T ml ; If satisfied, get a queue time; if not satisfied, give up the queue time;

[0058] Repeat the above steps until all elements in the queuing time set are traversed and a satisfying queuing time set is obtained.

[0059] Compared with the prior art, the present invention has the following beneficial effects: by realizing accurate prediction of check-in counter resources based on existing airport information, dependence on manual experience is reduced and prediction accuracy is improved; at the same time, referring to the airport passenger arrival probability density function as the input condition for simulation calculation, the predicted passenger arrival density is more in line with the actual situation and the solution result is more accurate; the Monte Carlo simulation algorithm is used for repeated sampling to avoid the drawback of a single calculation simulation that satisfies a single case scenario rather than the whole world, and the solution result is accurate and credible; an optimization algorithm model is established based on the time window concept, the global process can be reproduced and derived, and the solution result is credible. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A schematic diagram of a flow chart of an embodiment of the present invention;

[0061] Figure 2 A distribution diagram of outbound flight time periods based on discrete statistics according to another embodiment of the present invention;

[0062] Figure 3 This is a regular curve of passengers arriving at the airport during different flight periods according to another embodiment of the present invention;

[0063] Figure 4 This is a schematic diagram of the layout of a check-in counter at an airport according to another embodiment of the present invention;

[0064] Figure 5 This is a spatiotemporal network diagram of the check-in counter occupancy situation obtained by solving another embodiment of the present invention. DETAILED DESCRIPTION

[0065] The technical solution of the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0066] like Figures 1 to 5 As shown, the embodiment of the present invention proposes a check-in counter resource configuration method based on a Monte Carlo simulation algorithm, comprising the following steps:

[0067] S1: Obtain flight data, passenger arrival data and counter service time data within a preset time period, and couple to obtain a passenger arrival probability density function and a counter service time probability density function;

[0068] S2: The total number of luggage within a preset time period is obtained based on flight data and passenger arrival data. Based on the Monte Carlo algorithm, the passenger arrival probability density function and the counter service time probability density function are simulated and sampled to obtain the luggage arrival time set and the counter service time set within the preset time period.

[0069] S3: randomly obtain a check-in counter number, construct an optimization objective function based on the baggage arrival time set, the counter service time set and the check-in counter number, and calculate and solve the optimization objective function to obtain the service queue waiting time set of each baggage within the preset time period;

[0070] S4: repeat steps S1 to S3 N times to obtain N service queue waiting time sets, and calculate the queue time based on the N service queue waiting time sets;

[0071] S5: repeat steps S2 to S4 for a preset number of times to obtain a queuing time set, and obtain a satisfied queuing time set based on the queuing time set;

[0072] S6: Select the number of check-in counters that minimizes the number of centralized check-in counters to meet the queuing time as the optimal configuration solution;

[0073] The working principle of the above technical solution is as follows: in actual use, the flight data, passenger arrival data and counter service time data within a preset time period are coupled to obtain the passenger arrival probability density function and the counter service time probability density function; then the total number of luggage within the preset time period is obtained based on the flight data and the passenger arrival data, and the passenger arrival probability density function and the counter service time probability density function are simulated and sampled based on the Monte Carlo algorithm to obtain the luggage arrival time set and the counter service time set within the preset time period; then a check-in counter number is randomly obtained, and an optimization objective function is constructed based on the luggage arrival time set, the counter service time set and the number of check-in counters, and the service queue waiting time set of each luggage within the preset time period is calculated based on the optimization objective function; the above steps are repeated N times to obtain N service queue waiting time sets, and then the queue time is calculated; after repeating the above steps multiple times, a queue time set is obtained, and a queue time set that satisfies the queue time set is obtained based on the queue time set; finally, the minimum element of the number of check-in counters that satisfies the queue time set is selected, and the number of check-in counters with the minimum element is used as the optimal configuration scheme; wherein the flight data and the counter service time data are statistical data of the airline, and the passenger arrival data is obtained by survey or statistical historical data;

[0074] The beneficial effects of the above technical solution are as follows: through the above technical solution, accurate prediction of check-in counter resources is achieved based on the existing information of the airport, which reduces the reliance on manual experience and improves the accuracy of the prediction; at the same time, referring to the airport passenger arrival probability density function as the input condition of the simulation calculation, the predicted passenger arrival density is more in line with the actual situation and the solution is more accurate; the Monte Carlo simulation algorithm is used for repeated sampling to avoid the drawbacks of a single calculation simulation that satisfies a single case scenario rather than the whole world, and the solution is accurate and reliable; an optimization algorithm model is established based on the time window idea, the global process can be reproduced and derived, and the solution is reliable.

[0075] In one embodiment, step S1 includes:

[0076] Obtain flight data, passenger arrival data, and counter service time data within a preset time period; flight data includes: number of flight seats, passenger load factor, and flight take-off and landing times; passenger arrival data includes: passenger arrival time and baggage coefficient; counter service time data includes: single service start time and single service end time;

[0077] The passenger arrival probability density function f(x) is obtained by coupling the three-parameter Weibull function. The formula of the passenger arrival distribution probability function f(x) is as follows:

[0078]

[0079] Among them, β>0 is the shape parameter, α>0 is the scale parameter, and μ>0 is the location parameter;

[0080] The normal distribution function is coupled to obtain the counter service time probability density function. The formula of the counter service time probability density function g(c) is as follows:

[0081]

[0082] Among them, μ is the population mean and σ is the population standard deviation.

[0083] In one embodiment, the total number of luggage within a preset period is obtained based on flight data and passenger arrival data, including:

[0084] The total number of baggage within a preset time period is calculated based on flight data and baggage factor. The calculation formula for the total number of baggage is as follows:

[0085] m=∑P j ·ε·η

[0086] Among them, m is the total number of luggage, P j is the number of seats on the flight, ε is the passenger load factor, and η is the baggage coefficient.

[0087] In one embodiment, a passenger arrival probability density function and a counter service time probability density function are simulated and sampled based on a Monte Carlo algorithm to obtain a baggage arrival time set and a counter service time set within a preset time period, including:

[0088] S221: Select a proposed distribution q(x) so that the proposed distribution q(x) covers the target distribution f(x); obtain a constant k1 so that k1·q(x)≥f(x) holds for all x;

[0089] S222: Extract a sample AT1 from the proposed distribution q(x) and calculate the acceptance probability α1 of the sample AT1. The calculation formula is as follows:

[0090]

[0091] S223: randomly generate a uniformly distributed number U1, and determine whether the acceptance probability α1 of sample AT1 is not less than U1; if not, accept sample AT1 as the baggage arrival time; if less, reject sample AT1;

[0092] Repeat the above steps S221 to S223 until m baggage arrival times are obtained, and obtain the baggage arrival time set {AT1, AT2, ..., AT i ,…,AT m};

[0093] In one embodiment, the passenger arrival probability density function and the counter service time probability density function are simulated and sampled based on the Monte Carlo algorithm to obtain a baggage arrival time set and a counter service time set within a preset time period, and further includes:

[0094] S231: Select a proposed distribution p(c) so that the proposed distribution p(c) covers the target distribution g(c); obtain a constant k2 so that k2·p(c)≥g(c) holds for all c;

[0095] S232: Extract a sample ST1 from the proposed distribution p(c) and calculate the acceptance probability α2 of the sample ST1. The calculation formula is as follows:

[0096]

[0097] S233: randomly generate a uniformly distributed number U2, and determine whether the acceptance probability α2 of the sample ST1 is not less than U2; if not, accept the sample ST1 as the counter service time; if less, reject the sample ST1;

[0098] Repeat the above steps S231 to S233 until m counter service durations are obtained, and obtain a counter service duration set {ST1, ST2, ..., STi ,…,ST m}.

[0099] In one embodiment, step S3 includes:

[0100] The optimization objective function is constructed based on the baggage arrival time set, counter service time set and the number of check-in counters. The optimization objective function and its constraints are as follows:

[0101]

[0102]

[0103] Where X is the set of baggage that needs to be checked in, i represents the i-th baggage, X = {1, ..., j, i, ..., m}; T is the set of service time periods, t represents the t-th time unit, T = {0, ..., t, ..., p}; m is the total number of baggage that needs to be checked in within the scheduled time period, in pieces; p is the total length of the scheduled time period, in seconds; Q is the total number of check-in counters open for baggage check-in, in units; M

[0104] is a very large number; AT i is the estimated arrival time of the i-th piece of luggage, in seconds; ST i The estimated service time for the i-th piece of luggage, in seconds; RT i DT is the service start time of the i-th piece of luggage, in seconds; i is the end time of the i-th piece of luggage service, in seconds; R i,t is a 0-1 variable. When baggage i is being checked in at the check-in counter in the tth time period, it is 1, otherwise it is 0; y i,j is a 0-1 variable, which is 1 when the service completion time of bag i is earlier than the service start time of bag j, otherwise it is 0;

[0105] The improved NSGA (Non-Dominated Sorting Genetic Algorithm)-Ⅱ algorithm is used to solve and calculate the optimization objective function, and the baggage service situation within the preset time period is obtained; wherein the baggage service situation includes: the baggage service start time set, the baggage service end time set and the counter receiving the service;

[0106] The service queue waiting time set of each baggage is calculated based on the baggage service start time set and the baggage service end time set. The calculation formula of the service queue waiting time set of each baggage is as follows:

[0107]

[0108] Where, ΔT iis an element in the service queue waiting time set, and the service queue waiting time set is represented by {ΔT1, ΔT2, …, ΔT i ,…,ΔT m};

[0109] The value range of a randomly obtained check-in counter number is between the preset minimum configured check-in counter number and the total check-in counter data.

[0110] In one embodiment, the queuing time includes: the average queuing time of passengers and the maximum queuing time ΔT max ;

[0111] Calculate the queue time based on N service queue waiting time sets, including:

[0112] Calculate the maximum passenger queue time ΔT based on N service queue waiting time sets max , the average queuing time of passengers ΔT max The calculation formula is as follows:

[0113] ΔT max =max{ΔT 1,1 ,...,ΔT i,j ,...ΔT m,N}

[0114] Calculate the average passenger queuing time based on N service queue waiting time sets Average waiting time for passengers The calculation formula is as follows:

[0115]

[0116] Where, ΔT i,b The i-th value of the waiting time of the b-th service queue, b∈(0,N); the N-th value should be selected according to the actual needs and the Monte Carlo method to make the simulation results converge;

[0117] The queue time set is obtained based on the queue time set, including:

[0118] S61: Select a queue time in the queue time set to determine whether it meets the average queue time of passengers Not greater than the preset average queuing time T al , and the maximum queuing time of passengers ΔT max Not greater than the preset maximum queue time T ml ; If satisfied, get a queue time; if not satisfied, give up the queue time;

[0119] Repeat the above step S61 until all elements in the queuing time set are traversed to obtain a queuing time set that satisfies the queuing time set;

[0120] Among them, the preset maximum queuing time T ml and the preset average queuing time T al It is set based on the average and maximum queue times promised by IATA or airport services.

[0121] The minimum number of check-in counters to meet the queuing time can be expressed as:

[0122]

[0123] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. A check-in counter resource configuration method based on Monte Carlo simulation algorithm, characterized in that: The following steps are involved: S1: Obtain flight data, passenger arrival data and counter service time data within a preset time period, and couple them to obtain a passenger arrival probability density function and a counter service time probability density function; S2: The total number of luggage within a preset time period is obtained based on flight data and passenger arrival data. Based on the Monte Carlo algorithm, the passenger arrival probability density function and the counter service time probability density function are simulated and sampled to obtain the luggage arrival time set and the counter service time set within the preset time period. S3: randomly obtain a check-in counter number, construct an optimization objective function based on the baggage arrival time set, the counter service time set and the check-in counter number, and calculate and solve the optimization objective function to obtain the service queue waiting time set of each baggage within the preset time period; S4: repeat steps S1 to S3 N times to obtain N service queue waiting time sets, and calculate the queue time based on the N service queue waiting time sets; S5: repeat steps S2 to S4 for a preset number of times to obtain a queuing time set, and obtain a satisfied queuing time set based on the queuing time set; S6: Select the number of check-in counters that minimizes the number of concentrated check-in counters to meet the queuing time as the optimal configuration solution.

2. A check-in counter resource configuration method based on Monte Carlo simulation algorithm as claimed in claim 1, characterized in that: Step S1 includes: Obtain flight data, passenger arrival data, and counter service time data within a preset time period; flight data includes: number of flight seats, passenger load factor, and flight take-off and landing times; passenger arrival data includes: passenger arrival time and baggage coefficient; counter service time data includes: single service start time and single service end time; The passenger arrival probability density function f(x) is obtained by coupling the three-parameter Weibull function. The formula of the passenger arrival distribution probability function f(x) is as follows: Among them, β>0 is the shape parameter, α>0 is the scale parameter, and μ>0 is the location parameter; The normal distribution function is coupled to obtain the counter service time probability density function. The formula of the counter service time probability density function g(c) is as follows: Among them, μ is the population mean and σ is the population standard deviation.

3. A check-in counter resource configuration method based on Monte Carlo simulation algorithm as claimed in claim 2, characterized in that: Get the total number of bags within a preset period based on flight data and passenger arrival data, including: The total number of baggage within a preset time period is calculated based on flight data and baggage factor. The calculation formula for the total number of baggage is as follows: m=∑P j ·e·h Among them, m is the total number of luggage, P j is the number of seats on the flight, ε is the passenger load factor, and η is the baggage coefficient.

4. A check-in counter resource configuration method based on Monte Carlo simulation algorithm as claimed in claim 3, characterized in that: Based on the Monte Carlo algorithm, the passenger arrival probability density function and the counter service time probability density function are simulated and sampled to obtain the baggage arrival time set and the counter service time set within the preset time period, including: Select a proposed distribution q(x) so that the proposed distribution q(x) covers the target distribution f(x); obtain a constant k1 so that k1·q(x)≥f(x) holds for all x; Extract a sample AT1 from the proposed distribution q(x) and calculate the acceptance probability α1 of the sample AT1. The calculation formula is as follows: Randomly generate a uniformly distributed number U1, and determine whether the acceptance probability α1 of sample AT1 is not less than U1; if not, accept sample AT1 as the baggage arrival time; if less, reject sample AT1; Repeat the above steps until m baggage arrival times are obtained, and obtain the baggage arrival time set {AT1, AT2, ..., AT i ,…,AT m }; 5. The check-in counter resource configuration method based on Monte Carlo simulation algorithm as claimed in claim 3, characterized in that: Based on the Monte Carlo algorithm, the passenger arrival probability density function and the counter service time probability density function are simulated and sampled to obtain the baggage arrival time set and the counter service time set within the preset time period, which also includes: Select a proposed distribution p(c) so that the proposed distribution p(c) covers the target distribution g(c); obtain a constant k2 such that k2·p(c)≥g(c) holds for all c; Extract a sample ST1 from the proposed distribution p(c) and calculate the acceptance probability α2 of sample ST1. The calculation formula is as follows: Randomly generate a uniformly distributed number U2, and determine whether the acceptance probability α2 of sample ST1 is not less than U2; if not, accept sample ST1 as the counter service time; if less, reject sample ST1; Repeat the above steps until m counter service hours are obtained, and obtain the counter service time set {ST1, ST2, ..., ST i ,…,ST n }.

6. A check-in counter resource configuration method based on Monte Carlo simulation algorithm as claimed in claim 2, characterized in that: Step S3 includes: The optimization objective function is constructed based on the baggage arrival time set, counter service time set and the number of check-in counters. The optimization objective function and its constraints are as follows: Wherein, X is the set of baggage that needs to be checked in, i represents the i-th baggage, X = {1, ..., j, i, ..., m}; T is the set of service time periods, t represents the t-th time unit, T = {0, ..., t, ..., p}; m is the total number of baggage that needs to be checked in within the scheduled time period, in pieces; p is the total duration of the scheduled time period, in seconds; Q is the total number of check-in counters open for baggage check-in, in pieces; M is a very large number; ATi is the estimated arrival time of the i-th baggage, in seconds; STi is the estimated service time of the i-th baggage, in seconds; RTi is the service start time of the i-th baggage, in seconds; DTi is the service end time of the i-th baggage, in seconds; R i，t is a 0-1 variable. When baggage i is being checked in at the check-in counter in the tth time period, it is 1, otherwise it is 0; y i，j is a 0-1 variable, which is 1 when the service completion time of bag i is earlier than the service start time of bag j, otherwise it is 0; The improved NSGA-II algorithm is used to solve and calculate the optimization objective function to obtain the baggage service situation within the preset time period; wherein the baggage service situation includes: the baggage service start time set, the baggage service end time set and the counter receiving the service; The service queue waiting time set of each baggage is calculated based on the baggage service start time set and the baggage service end time set. The calculation formula of the service queue waiting time set of each baggage is as follows: Among them, ΔTi is an element in the service queue waiting time set, and the service queue waiting time set is expressed as {ΔT1, ΔT2, …, ΔT i ,…,ΔT m }.

7. A check-in counter resource configuration method based on Monte Carlo simulation algorithm as claimed in claim 2, characterized in that: Queuing time includes: Average queuing time for passengers and the maximum queuing time ΔT max ; Calculate the queue time based on N service queue waiting time sets, including: Calculate the maximum passenger queue time ΔT based on N service queue waiting time sets max , the average queuing time of passengers ΔT max The calculation formula is as follows: ΔT max =max{ΔT 1，1 ,…,ΔT i，j ,…ΔT m，N } Calculate the average passenger queuing time based on N service queue waiting time sets Average waiting time for passengers The calculation formula is as follows: Where, ΔT i，b is the i-th value in the b-th service queue waiting time set, b∈(0,N).

8. A check-in counter resource configuration method based on Monte Carlo simulation algorithm as claimed in claim 7, characterized in that: The queue time set is obtained based on the queue time set, including: Select a queue time to focus on and determine whether it meets the average queue time of passengers. Not greater than the preset average queuing time T al , and the maximum queuing time of passengers ΔT max Not greater than the preset maximum queue time T ml ; If satisfied, get a queue time; if not satisfied, give up the queue time; Repeat the above steps until all elements in the queuing time set are traversed and a satisfying queuing time set is obtained.

Images