Airport luggage turntable scheduling method and related device
Through the time prediction model and the optimization allocation of idle time of luggage carousels, the problems of balanced allocation and resource utilization in airport luggage carousels are solved, and service quality and economic benefits are improved.
Patent Information
- Application Number
- CN202411279376.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-12
- Publication Date
- 2024-12-03
AI Technical Summary
The existing airport luggage carousel scheduling method lacks balanced allocation and overall planning, resulting in peak congestion and waste of resources during low peak periods, affecting service quality and economic benefits.
The time prediction model is used to predict the time when a flight arrives at the luggage carousel through feature encoding, and optimize the allocation of the idle time of the luggage carousel to achieve reasonable luggage carousel scheduling.
It improves the rationality and orderliness of luggage carousel scheduling, improves the quality of airport services, saves resources, and ensures rapid extraction during peak periods and effective utilization of resources during low peak periods.
Smart Images

Figure CN119067400A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of software technology, and in particular to an airport baggage carousel scheduling method and related devices. Background Art
[0002] After passengers disembark from their flights, they need to collect their checked baggage from the baggage carousel, which is an important part of the arriving passenger process.
[0003] At present, the scheduling of baggage carousels is generally assigned manually or on a first-come-first-served basis, lacking balanced allocation and overall planning. Reasonable scheduling of baggage carousels at airports can, on the one hand, enable passengers to quickly retrieve their luggage during peak hours, avoid congestion, and effectively improve the quality of airport services; on the other hand, it can save airport resources and improve economic benefits when passenger flow is low.
[0004] Therefore, how to optimize the scheduling of baggage carousels has become an urgent problem to be solved at this stage. Summary of the invention
[0005] In view of the above problems, the present application provides an airport baggage carousel scheduling method and related devices to achieve the purpose of optimizing the scheduling of baggage carousels. The specific scheme is as follows:
[0006] A first aspect of the present application provides an airport baggage carousel scheduling method, the airport baggage carousel scheduling method comprising:
[0007] Obtaining a first flight description of a target flight, and performing feature encoding on the first flight description;
[0008] Retrieving a pre-trained time prediction model, and inputting the feature encoding result of the first flight description into the time prediction model to obtain a predicted time for the target flight to arrive at the baggage carousel;
[0009] Obtaining the duration of occupancy of the baggage carousel by the target flight, and obtaining the idle time of the baggage carousel;
[0010] By comparing the predicted time and the idle time, a target baggage carousel is allocated to the target flight from the baggage carousels, and the target idle time corresponding to the target baggage carousel is updated according to the predicted time and the occupied time.
[0011] In a possible implementation, the training process of the time prediction model includes:
[0012] Using grid search to adjust the hyperparameters of the Xgboost model, so that the Xgboost models under different hyperparameters are respectively used as base models;
[0013] Obtaining a second flight description of the scheduled flight, and performing feature encoding on the second flight description;
[0014] Dividing the feature encoding result of the second description text into a training set, a validation set and a test set;
[0015] Determining training samples for this training from the training set, and inputting the training samples into the basic model for training to adjust the weight parameters of the basic model;
[0016] Using the validation set to validate the basic model after this training to obtain a first accuracy rate of the basic model after this training;
[0017] When the first accuracy rate is less than the corresponding first threshold, the weight parameters of the basic model are adjusted in reverse, and the step of determining the training samples for the current training from the training set is returned to be executed;
[0018] When the first accuracy rate is greater than or equal to the corresponding first threshold, the training is terminated, and the basic model after the training is used as a candidate time prediction model;
[0019] For multiple candidate time prediction models corresponding to different hyperparameters, each candidate time prediction model is tested using a test set to obtain a second accuracy rate of each candidate time prediction model;
[0020] The candidate time prediction model with the second highest accuracy among the multiple candidate time prediction models is used as the time prediction model.
[0021] In a possible implementation, obtaining the occupancy time of the baggage carousel by the target flight includes:
[0022] The flights among the target flights whose predicted times are within the specified time period are taken as flights to be scheduled;
[0023] Obtain the occupancy time of the baggage carousel by the flight to be scheduled.
[0024] In a possible implementation, obtaining the occupancy time of the baggage carousel by the target flight includes:
[0025] Obtaining the total weight and total number of pieces of baggage of the target flight, and obtaining the maximum load weight and maximum load number of pieces of baggage carousel;
[0026] Sorting the target flights according to the order of the predicted time from early to late;
[0027] Flights are merged based on the sorting results of the target flights, and the two adjacent flights to be merged meet the following conditions: the time difference of the predicted time is less than the corresponding second threshold, the sum of the total baggage weight is less than the maximum carrying weight, and the sum of the total number of baggage pieces is less than the maximum carrying number of pieces.
[0028] In a possible implementation, allocating a target baggage carousel for the target flight from the baggage carousels by comparing the predicted time with the idle time includes:
[0029] Acquire the working state of the luggage carousel, where the working state is an open state or a closed state;
[0030] determining a first luggage carousel in the open state and a second luggage carousel in the closed state among the luggage carousels;
[0031] Determining whether the first baggage carousel is empty;
[0032] If the first luggage carousel is empty, selecting one of the second luggage carousels as a target luggage carousel, and controlling the target luggage carousel to switch from a closed state to an open state;
[0033] If the first baggage carousel is not empty, determining whether there is a third baggage carousel among the first baggage carousels whose idle time is earlier than the predicted time;
[0034] If the third baggage carousel exists, selecting the one of the third baggage carousels with the latest idle time as the target baggage carousel;
[0035] If the third baggage carousel does not exist, determining whether there is a fourth baggage carousel among the first baggage carousels whose time difference between the idle time and the predicted time is less than a corresponding third threshold;
[0036] If the fourth baggage carousel exists, selecting the one of the fourth baggage carousels with the earliest idle time as the target baggage carousel;
[0037] If the fourth baggage carousel does not exist, determining whether the second baggage carousel is empty;
[0038] If the second baggage carousel is empty, selecting the first baggage carousel with the earliest idle time as the target baggage carousel;
[0039] If the second luggage carousels are not empty, one of the second luggage carousels is selected as a target luggage carousel, and the target luggage carousel is controlled to switch from a closed state to an open state.
[0040] In a possible implementation, the airport baggage carousel scheduling method further includes:
[0041] The idle time of the first luggage carousel is counted, and when the idle time is greater than a corresponding fourth threshold, the first luggage carousel is controlled to switch from an open state to a closed state.
[0042] A second aspect of the present application provides an airport baggage carousel scheduling device, the airport baggage carousel scheduling device comprising:
[0043] Model training module, used to pre-train the time prediction model;
[0044] A time prediction module is used to obtain a first flight description of a target flight and perform feature coding on the first flight description; retrieve the time prediction model and input the feature coding result of the first flight description into the time prediction model to obtain a predicted time for the target flight to arrive at the baggage carousel;
[0045] The carousel scheduling module is used to obtain the occupancy time of the baggage carousel by the target flight and the idle time of the baggage carousel; by comparing the predicted time with the idle time, a target baggage carousel is allocated to the target flight from the baggage carousels, and the target idle time corresponding to the target baggage carousel is updated according to the predicted time and the occupancy time.
[0046] A third aspect of the present application provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the airport baggage carousel scheduling method of the first aspect or any implementation of the first aspect.
[0047] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:
[0048] The memory is used to store computer programs;
[0049] The processor is used to execute the computer program so that the electronic device can implement the airport baggage carousel scheduling method of the above-mentioned first aspect or any implementation manner of the first aspect.
[0050] In a fifth aspect, the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the airport baggage carousel scheduling method of the above-mentioned first aspect or any implementation method of the first aspect.
[0051] By means of the above technical solution, the present application provides an airport baggage carousel scheduling method and related devices, which obtain the first flight description of the target flight and perform feature encoding on the first flight description; retrieve the pre-trained time prediction model, and input the feature encoding result of the first flight description into the time prediction model to obtain the predicted time of the target flight arriving at the baggage carousel; obtain the occupancy time of the baggage carousel by the target flight, and obtain the idle time of the baggage carousel; by comparing the predicted time and the idle time, allocate a target baggage carousel to the target flight from the baggage carousels, and update the target idle time corresponding to the target baggage carousel according to the predicted time and the occupancy time. The present application predicts the time when the flight arrives at the baggage carousel, and compares the time and the idle time of the baggage carousel to allocate a baggage carousel to the flight, thereby realizing the optimized scheduling of the baggage carousel, ensuring the rationality and orderliness of the scheduling, improving the airport service quality, and saving airport resources. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.
[0053] Figure 1 A schematic diagram of a flow chart of an airport baggage carousel scheduling method provided in an embodiment of the present application;
[0054] Figure 2 A partial flow chart of a method for dispatching baggage carousels at an airport provided in an embodiment of the present application;
[0055] Figure 3 A schematic diagram of another part of the flow chart of a method for dispatching baggage carousels at an airport provided in an embodiment of the present application;
[0056] Figure 4 A schematic diagram of another part of the flow chart of a method for dispatching baggage carousels at an airport provided in an embodiment of the present application;
[0057] Figure 5 A schematic diagram of another part of the flow chart of a method for dispatching baggage carousels at an airport provided in an embodiment of the present application;
[0058] Figure 6 A schematic diagram of the structure of an airport baggage carousel scheduling device provided in an embodiment of the present application;
[0059] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0060] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.
[0061] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
[0062] The terms "first", "second" etc. in the specification of the application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable in appropriate circumstances, and this is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.
[0063] See also Figure 1 , Figure 1 The following is a flow chart of a method for scheduling airport baggage carousels provided in an embodiment of the present application. Figure 1 As shown, an airport baggage carousel scheduling method provided by an embodiment of the present application may include steps S101 to S104, and these steps are described in detail below.
[0064] S101, obtaining a first flight description of a target flight, and performing feature coding on the first flight description.
[0065] In the embodiment of the present application, the target flight is the flight to be arrived at the airport on the same day, and the corresponding flight description is obtained, that is, the first flight description. The first flight description includes flight scheduling information, flight basic information, passenger information, and time information. For example, the scheduling information includes the estimated arrival time, arrival parking space, expected delay, number of flights arriving in the same period (the first half hour and the second half hour belong to the same period), departure time, etc. The basic flight information includes the aircraft model, total baggage weight, total number of baggage pieces, airline company, domestic / international flight, flight mileage, number of flight knots, etc. The passenger information includes the number of passengers, the number of passengers with checked baggage, etc. The time information includes whether the arrival time is a weekend, whether the arrival time is a holiday, and the arrival month.
[0066] Further, feature engineering is established to perform feature coding on the first flight description. For example, for the estimated arrival time, it can be divided into time periods of 4 hours (for example, 00:00:00-03:59:59, 04:00:00-07:59:59), and converted into time period values 1, 2, 3, 4, 5, 6. In addition, the take-off time can also be processed in the same way; for the arrival parking space, it can be numerically coded from near to far according to its distance from the baggage carousel (1, 2, 3, ...); for the aircraft type, it can be numerically coded from small to large according to the maximum passenger capacity (1, 2, 3, ...); for the airline, it can be numerically coded from small to large according to the number of all aircraft of the airline (1, 2, 3, ...); for whether it is expected to be delayed, delay is 1, and no delay is 0; for domestic / international flights, domestic flights are 1, and international flights are 0; for whether the arrival time is a weekend, it is 1 if it is a weekend, otherwise it is 0; for whether the arrival time is a holiday, it is 1 if it is a holiday, otherwise it is 0.
[0067] When the first flight description is fully encoded as feature values, normalization is continued. The min-max normalization method can be used to scale the value range to (0,1). The conversion function is x = (x - min) / (max -min), where max is the maximum value of the feature value and min is the minimum value of the feature value.
[0068] S102, calling a pre-trained time prediction model, inputting the feature encoding result of the first flight description into the time prediction model to obtain the predicted time for the target flight to arrive at the baggage carousel.
[0069] In the embodiment of the present application, the Xgboost model is used as a basic model in advance to train a time prediction model, and the time prediction model is used to predict the time when the flight arrives at the baggage carousel.
[0070] The feature encoding result of the first flight description is input into the time prediction model, and the time when the target flight arrives at the baggage carousel predicted by the time prediction model can be obtained, that is, the predicted time when the target flight arrives at the baggage carousel.
[0071] See also Figure 2 , Figure 2 This is a partial flow chart of a method for scheduling airport baggage carousels provided in an embodiment of the present application. Figure 2 As shown, an airport baggage carousel scheduling method provided by an embodiment of the present application, wherein the training process of the time prediction model can adopt steps S201 to S208, and these steps are described in detail below.
[0072] S201, using grid search to adjust the hyperparameters of the Xgboost model, so that the Xgboost models under different hyperparameters are used as base models respectively.
[0073] In the embodiment of the present application, the hyperparameters of the Xgboost model are adjusted by grid search, and different hyperparameters are obtained by enumeration. Then, the Xgboost models under different hyperparameters are respectively used as the basic models for training in subsequent steps S202 to S207, so as to obtain the candidate time prediction models corresponding to the different hyperparameters.
[0074] S202, obtaining a second flight description of the scheduled flight, and performing feature coding on the second flight description.
[0075] In the embodiment of the present application, the scheduled flight is a historical flight that has arrived, and the corresponding flight description, i.e., the second flight description, is obtained. The second flight description includes flight scheduling information, flight basic information, passenger information, and time information. For example, the scheduling information includes the actual arrival time, arrival parking space, actual delay, number of flights arriving in the same period (the first half hour and the second half hour belong to the same period), departure time, etc. The basic flight information includes the aircraft model, total baggage weight, total number of baggage pieces, airline company, domestic / international flight, flight mileage, number of flight knots, etc. The passenger information includes the number of passengers, the number of passengers with checked baggage, etc. The time information includes whether the arrival time is a weekend, whether the arrival time is a holiday, the arrival month, etc.
[0076] Furthermore, feature engineering is established to perform feature coding on the second flight description. Specifically, the coding method of the actual arrival time is the same as the estimated arrival time, and the coding method of whether the actual delay is the same as the estimated delay. Other information can refer to the feature coding method of the first flight description, which will not be repeated here.
[0077] S203, dividing the feature encoding result of the second description text into a training set, a verification set and a test set.
[0078] In an embodiment of the present application, after obtaining the feature encoding result of the second description text, it can be used as sample data and divided in a ratio of 7:1:2 to obtain a training set, a validation set, and a test set.
[0079] S204, determining training samples for this training from the training set, and inputting the training samples into the basic model for training to adjust the weight parameters of the basic model.
[0080] In an embodiment of the present application, during each training process, after randomly obtaining a training sample for this training from a training set, the training sample can be input into the basic model to adjust the weight parameters of the basic model.
[0081] S205, using the validation set to validate the basic model after this training to obtain a first accuracy rate of the basic model after this training.
[0082] In the embodiment of the present application, the validation set is used to validate the basic model after this training, so as to obtain the prediction result of the basic model after this training for the validation set (i.e., the predicted arrival time of the historical flights in the validation set at the baggage carousel), and combined with the annotation result of the validation set (i.e., the actual arrival time of the historical flights in the validation set at the baggage carousel), the accuracy of the basic model after this training for the validation set, i.e., the first accuracy, can be calculated.
[0083] S206, when the first accuracy rate is less than the corresponding first threshold, the weight parameters of the basic model are adjusted in reverse, and the process returns to step S204.
[0084] In an embodiment of the present application, if the first accuracy rate is less than the corresponding first threshold value, indicating that the prediction deviation of the Xgboost model after this training is large, the weight parameters of the basic model are adjusted in the opposite direction, and the execution returns to step S204 to enter the next training of the basic model.
[0085] S207, when the first accuracy rate is greater than or equal to the corresponding first threshold, end the training and use the basic model after this training as a candidate time prediction model.
[0086] In the embodiment of the present application, if the first accuracy is greater than or equal to the corresponding first threshold, it means that the prediction deviation of the basic model after this training is small, the training is terminated, and the basic model after this training is used as a candidate time prediction model and saved. The Xgboost model corresponding to the next set of hyperparameters continues to be used as the basic model for training steps S202 to S207 until all Xgboost models corresponding to all hyperparameters are trained and multiple candidate time prediction models are obtained.
[0087] S208, for multiple candidate time prediction models corresponding to different hyperparameters, use the test set to test each candidate time prediction model to obtain a second accuracy rate of each candidate time prediction model.
[0088] In an embodiment of the present application, for multiple candidate time prediction models corresponding to different hyperparameters, each candidate time prediction model is tested using a test set to obtain the prediction results of each candidate time prediction model for the test set (i.e., the predicted time for historical flights in the test set to arrive at the baggage carousel). Combined with the annotation results of the test set (i.e., the actual time for historical flights in the test set to arrive at the baggage carousel), the accuracy of each candidate time prediction model for the test set, i.e., the second accuracy, can be calculated.
[0089] S209: Using the candidate time prediction model with the second highest accuracy among the multiple candidate time prediction models as the time prediction model.
[0090] In the embodiment of the present application, the second accuracy rates of the candidate time prediction models are compared, and the candidate time prediction model with the highest second accuracy rate is used as the time prediction model.
[0091] S103, obtaining the occupancy time of the baggage carousel by the target flight, and obtaining the idle time of the baggage carousel.
[0092] In the embodiment of the present application, the occupancy time of the baggage carousel (i.e., the time from the arrival of the baggage at the carousel to the passengers picking up the baggage) of the target flight can be determined according to the total number of baggage pieces of the target flight. For example, when the total number of baggage pieces is less than 150, the occupancy time of the baggage carousel of the target flight is 10 minutes; when the total number of baggage pieces is greater than or equal to 150 and less than 250, the occupancy time of the baggage carousel of the target flight is 15 minutes; when the total number of baggage pieces is greater than 250, the occupancy time of the baggage carousel of the target flight is 20 minutes.
[0093] In addition, in an embodiment of the present application, the idle time of the baggage carousel is further obtained, and the idle time can be the predicted idle time (determined according to the predicted time and occupancy time of the assigned flight) or the actual idle time (the known idle time when no flight is assigned).
[0094] In a possible implementation, to ensure the timeliness of scheduling, flights arriving within a certain period of time in the future can be prioritized. Figure 3 , Figure 3 This is another partial flow chart of a method for scheduling airport baggage carousels provided in an embodiment of the present application. Figure 3 As shown, an airport baggage carousel scheduling method is provided in an embodiment of the present application, wherein in step S103, "obtaining the occupancy time of the baggage carousel by the target flight" can adopt steps S1031 to S1032, and these steps are described in detail below.
[0095] S1031: select the target flights whose predicted time is within the specified time period as the flights to be scheduled.
[0096] S1032, obtaining the occupancy time of the baggage carousel by the flight to be scheduled.
[0097] Specifically, in the embodiment of the present application, at least one flight among the target flights whose predicted time is within a specified time period in the future (e.g., H hours in the future) can be used as a flight to be scheduled. At this time, the occupancy time of the baggage carousel by the flight to be scheduled can be obtained, and then by comparing the predicted time and the idle time, a target baggage carousel can be allocated to the flight to be scheduled from the baggage carousels.
[0098] In a possible implementation, in order to effectively utilize the baggage carousel, two or more flights may be combined during scheduling, and the combined flights share one baggage carousel. Figure 4 , Figure 4 This is another partial flow chart of a method for scheduling airport baggage carousels provided in an embodiment of the present application. Figure 4 As shown, an airport baggage carousel scheduling method is provided in an embodiment of the present application, wherein "obtaining the occupancy time of the baggage carousel by the target flight" in step S103 can adopt steps S1033 to S1035, and these steps are described in detail below.
[0099] S1033, obtaining the total weight and total number of pieces of baggage of the target flight, and obtaining the maximum carrying weight and maximum carrying number of the baggage carousel.
[0100] In the embodiment of the present application, assuming that there are m target flights, for the i-th flight, its total baggage weight w can be obtained. i and the total number of pieces of luggage p i At the same time, assuming there are n luggage carousels, the maximum load w of the j-th luggage carousel can be obtained max and the maximum number of load-bearing parts p max .
[0101] S1034, sorting the target flights in order of predicted time from early to late.
[0102] In the embodiment of the present application, for the ith flight, the predicted time of arrival at the baggage carousel is t i . Sort the predicted times of m flights in order from early to late, t1, t2, ..., t m , in this way, the sorting results of m flights can be obtained.
[0103] S1035, merging flights based on the sorting results of the target flights, where the two adjacent flights to be merged meet the following conditions: the time difference of the predicted time is less than the corresponding second threshold, the sum of the total baggage weight is less than the maximum carrying weight, and the sum of the total number of baggage pieces is less than the maximum number of pieces carried.
[0104] In the embodiment of the present application, according to the sorting results of m flights, two consecutive flights are traversed in sequence. Assuming that the two flights currently traversed are a and b, the predicted time t of the two flights is obtained. a and t b , the total weight of their respective luggage w a and w b , the total number of luggage pieces of each a and p b, assuming the third threshold is 10min, if the condition 0≤t is met b -t a ≤10min, and w a +w b ≤w max , and p a +p b ≤p max , then merge flight a and flight b into one flight ab and put it into the sorted result of m flights to continue the next traversal. This will merge at least two flights that meet the conditions and assign them to the same baggage carousel. Of course, the predicted arrival time of the merged flight ab at the baggage carousel is t a , the length of time it occupies the baggage carousel is max(t a + c a , t b + c b )-t a , where c a is the time flight a occupies the baggage carousel, c b is the time flight b occupies the baggage carousel.
[0105] S104, allocating a target baggage carousel for the target flight from the baggage carousels by comparing the predicted time and the idle time, and updating the target idle time corresponding to the target baggage carousel according to the predicted time and the occupied time.
[0106] In the embodiment of the present application, by comparing the predicted time and the idle time, a baggage carousel with the closest time to the target flight can be allocated from the baggage carousels as the target baggage carousel, and then the idle time corresponding to the target baggage carousel, that is, the target idle time, is updated. Specifically, the target idle time = predicted time + occupied time.
[0107] In a possible implementation, the allocation and scheduling can be performed according to the working status of the baggage carousel. Figure 5 , Figure 5 This is another partial flow chart of a method for scheduling airport baggage carousels provided in an embodiment of the present application. Figure 5 As shown, an airport baggage carousel scheduling method is provided in an embodiment of the present application, wherein in step S104, "obtaining the occupancy time of the baggage carousel by the target flight" can adopt steps S1041 to S10411, and these steps are described in detail below.
[0108] S1041, obtaining the working status of the luggage carousel, which can be an open state or a closed state.
[0109] In the embodiment of the present application, the working state of the j-th luggage carousel can be obtained, and the working state is an open state or a closed state. For example, when the working state is -1, it means that the j-th luggage carousel is in a closed state, and when the working state is not -1, it means that the j-th luggage carousel is in an open state.
[0110] S1042: Determine a first luggage carousel in an open state and a second luggage carousel in a closed state among the luggage carousels.
[0111] In the embodiment of the present application, for n luggage carousels, they can be divided into two types: the first luggage carousel and the second luggage carousel according to their respective working states. For the j-th luggage carousel, if its working state is the open state, it is the first luggage carousel, otherwise, if its working state is the closed state, it is the second luggage carousel.
[0112] S1043, determine whether the first baggage carousel is empty; if so, execute step S1044; if not, execute step S1045.
[0113] In the embodiment of the present application, if the first luggage carousel is empty, it means that all the n luggage carousels are in a closed state. Conversely, if the first luggage carousel is not empty, it means that there is a first luggage carousel in an open state among the n luggage carousels.
[0114] S1044: Select one of the second luggage carousels as the target luggage carousel, and control the target luggage carousel to switch from a closed state to an open state.
[0115] In the embodiment of the present application, if the first luggage carousel is empty, any one of the second luggage carousels is selected as the target luggage carousel, and the working state of the target luggage carousel is switched from the closed state to the open state.
[0116] S1045, determining whether there is a third luggage carousel in the first luggage carousel whose idle time is earlier than the predicted time; if so, executing step S1046; if not, executing step S1047.
[0117] In the embodiment of the present application, if the first luggage carousel is not empty, it is further determined whether there are one or more luggage carousels that meet the condition that the idle time is earlier than the predicted time, and the luggage carousel that meets the condition is used as the third luggage carousel.
[0118] S1046: Select the third baggage carousel with the latest idle time as the target baggage carousel.
[0119] In the embodiment of the present application, if there is a third baggage carousel, the baggage carousel with the longest idle time is used as the target baggage carousel, so as to allocate as many flights as possible to the baggage carousel, thereby ensuring that the least baggage carousels are started and the most work is completed.
[0120] S1047, determining whether there is a fourth baggage carousel in the first baggage carousel whose idle time and predicted time have a time difference less than the corresponding third threshold; if so, executing step S1048; if not, executing step S1049.
[0121] In the embodiment of the present application, if there is no third luggage carousel, it is further determined whether there are one or more luggage carousels among the first luggage carousels that satisfy the condition that the time difference between the idle time and the predicted time is less than the corresponding fourth threshold value (for example, 10 minutes), and the luggage carousel that satisfies the condition is used as the fourth luggage carousel.
[0122] That is, when there is no baggage carousel whose idle time is earlier than the predicted time in the first baggage carousel, it means that the target flight needs to wait for a period of time (less than 10 minutes) after arriving at the airport before an idle baggage carousel operates for it.
[0123] S1048: Select the fourth baggage carousel with the earliest idle time as the target baggage carousel.
[0124] In the embodiment of the present application, if there is a fourth luggage carousel, the luggage carousel with the earliest idle time is used as the target luggage carousel, so as to ensure that the waiting time of the passenger is the shortest.
[0125] S1049, determine whether the second baggage carousel is empty; if so, execute step S10410; if not, execute step S10411.
[0126] In the embodiment of the present application, if the fourth luggage carousel does not exist, in order to avoid the passengers waiting for a long time, it is further determined whether the second luggage carousel is empty.
[0127] S10410: Select the first baggage carousel with the earliest idle time as the target baggage carousel.
[0128] In the embodiment of the present application, if the second baggage carousel is empty, it means that all baggage carousels are in operation. This requires the target flight to wait for the earliest baggage carousel to work for it after arriving at the airport. At this time, the baggage carousel with the earliest idle time among the first baggage carousels is used as the target baggage carousel.
[0129] S10411, selecting one of the second luggage carousels as the target luggage carousel, and controlling the target luggage carousel to switch from a closed state to an open state.
[0130] In the embodiment of the present application, if the second luggage carousel is not empty, it means that there is an inoperative luggage carousel, any one of the second luggage carousels is selected as the target luggage carousel, and the working state of the target luggage carousel is switched from the closed state to the open state.
[0131] On this basis, in order to save airport energy, the baggage carousel can be turned off when it is idle for a long time. In this regard, an airport baggage carousel scheduling method provided in an embodiment of the present application includes the following steps:
[0132] The idle time of the first luggage carousel is counted, and when the idle time is greater than the corresponding fifth threshold, the first luggage carousel is controlled to switch from the open state to the closed state.
[0133] In the embodiment of the present application, the idle time of each luggage carousel in the first luggage carousel is counted, and when the idle time is greater than the corresponding fourth threshold (for example, 1 hour), the corresponding luggage carousel is switched from the open state to the closed state.
[0134] Through the above description, an airport baggage carousel scheduling method provided in an embodiment of the present application predicts the time when a flight arrives at a baggage carousel, and allocates a baggage carousel to the flight by comparing the time with the idle time of the baggage carousel, thereby optimizing the scheduling of baggage carousels, ensuring the rationality and orderliness of the scheduling, improving the airport service quality, and saving airport resources.
[0135] A method for scheduling an airport baggage carousel provided by an embodiment of the present application is introduced above. A device for executing the above-mentioned method for scheduling an airport baggage carousel will be introduced below.
[0136] See also Figure 6 , Figure 6 This is a schematic diagram of the structure of an airport baggage carousel scheduling device provided in an embodiment of the present application. Figure 6 As shown, an airport baggage carousel scheduling device provided in an embodiment of the present application includes:
[0137] A model training module 10, used for pre-training a time prediction model;
[0138] The time prediction module 20 is used to obtain the first flight description of the target flight and perform feature coding on the first flight description; retrieve the time prediction model and input the feature coding result of the first flight description into the time prediction model to obtain the predicted time of the target flight arriving at the baggage carousel;
[0139] The carousel scheduling module 30 is used to obtain the occupancy time of the baggage carousel by the target flight and the idle time of the baggage carousel; by comparing the predicted time and the idle time, a target baggage carousel is allocated to the target flight from the baggage carousels, and the target idle time corresponding to the target baggage carousel is updated according to the predicted time and the occupancy time.
[0140] In a possible implementation, the model training module 10 is specifically used to:
[0141] The Xgboost model is hyperparameter-adjusted using grid search to use the Xgboost models under different hyperparameters as the base models respectively; the second flight description of the scheduled flight is obtained and the second flight description is feature-encoded; a training set, a validation set and a test set are divided from the feature encoding result of the second description text; a training sample for this training is determined from the training set, and the training sample is input into the base model for training to adjust the weight parameter of the base model; the base model after this training is verified using the validation set to obtain the first accuracy of the base model after this training; when the first accuracy is less than the corresponding first threshold, the weight parameter of the base model is reversely adjusted, and the step of determining the training sample for this training from the training set is returned to be executed; when the first accuracy is greater than or equal to the corresponding first threshold, the training is terminated, and the base model after this training is used as the candidate time prediction model; for multiple candidate time prediction models corresponding to different hyperparameters, each candidate time prediction model is tested using the test set to obtain the second accuracy of each candidate time prediction model; the candidate time prediction model with the highest second accuracy among the multiple candidate time prediction models is used as the time prediction model.
[0142] In a possible implementation, the carousel scheduling module 30 for obtaining the occupancy time of the baggage carousel by the target flight is specifically used to:
[0143] The flights among the target flights whose predicted time is within the specified time period are taken as the flights to be scheduled; and the occupancy time of the baggage carousel by the flights to be scheduled is obtained.
[0144] In a possible implementation, the carousel scheduling module 30 for obtaining the occupancy time of the baggage carousel by the target flight is specifically used to:
[0145] Obtain the total baggage weight and total number of baggage pieces of the target flight, as well as the maximum load-bearing weight and maximum load-bearing number of the baggage carousel; sort the target flights in order of predicted time from early to late; merge flights based on the sorting results of the target flights, and the two adjacent flights to be merged meet the conditions that the time difference of the predicted time is less than the corresponding second threshold, the sum of the total baggage weight is less than the maximum load-bearing weight, and the sum of the total number of baggage pieces is less than the maximum load-bearing number.
[0146] In a possible implementation, the carousel scheduling module 30 for allocating a target baggage carousel for a target flight from the baggage carousels by comparing the predicted time and the idle time is specifically configured to:
[0147] Obtain the working state of the luggage carousel, which is an open state or a closed state; determine the first luggage carousel in the open state and the second luggage carousel in the closed state among the luggage carousels; determine whether the first luggage carousel is empty; if the first luggage carousel is empty, select one of the second luggage carousels as the target luggage carousel, and control the target luggage carousel to switch from the closed state to the open state; if the first luggage carousel is not empty, determine whether there is a third luggage carousel in the first luggage carousel whose idle time is earlier than the predicted time; if there is a third luggage carousel, select the one with the latest idle time among the third luggage carousels as the target luggage carousel ; if the third luggage carousel does not exist, determine whether there is a fourth luggage carousel among the first luggage carousels whose time difference between the idle time and the predicted time is less than the corresponding third threshold value; if the fourth luggage carousel exists, select the one with the earliest idle time among the fourth luggage carousels as the target luggage carousel; if the fourth luggage carousel does not exist, determine whether the second luggage carousel is empty; if the second luggage carousel is empty, select the one with the earliest idle time among the first luggage carousels as the target luggage carousel; if the second luggage carousel is not empty, select one of the second luggage carousels as the target luggage carousel, and control the target luggage carousel to switch from a closed state to an open state.
[0148] In a possible implementation, the turntable scheduling module 30 is further used to:
[0149] The idle time of the first luggage carousel is counted, and when the idle time is greater than the corresponding fourth threshold, the first luggage carousel is controlled to switch from the open state to the closed state.
[0150] It should be noted that the detailed functions of each module in the embodiment of the present application can be found in the corresponding public part of the above-mentioned airport baggage carousel scheduling method embodiment, and will not be repeated here.
[0151] The present application also provides an electronic device in an embodiment. Figure 7 , Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device in the embodiment of the present application may include but is not limited to fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 7 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0152] like Figure 7As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage device 708 to a random access memory (RAM) 703. When the electronic device is powered on, various programs and data required for the operation of the electronic device are also stored in the RAM 703. The processing device 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.
[0153] Typically, the following devices may be connected to the I / O interface 705: an input device 706 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 707 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 708 including, for example, a memory card, a hard disk, etc.; and a communication device 709. The communication device 709 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.
[0154] An embodiment of the present application also provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any of the airport baggage carousel scheduling methods provided in the embodiments of the present application.
[0155] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any of the airport baggage carousel scheduling methods provided in the embodiment of the present application.
[0156] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.
[0157] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.
[0158] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.
[0159] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.
Claims
1. A method for dispatching baggage carousels at an airport, It is characterized in that The airport baggage carousel scheduling method comprises: Obtaining a first flight description of a target flight, and performing feature encoding on the first flight description; Retrieving a pre-trained time prediction model, and inputting the feature encoding result of the first flight description into the time prediction model to obtain a predicted time for the target flight to arrive at the baggage carousel; Obtaining the duration of occupancy of the baggage carousel by the target flight, and obtaining the idle time of the baggage carousel; By comparing the predicted time and the idle time, a target baggage carousel is allocated to the target flight from the baggage carousels, and the target idle time corresponding to the target baggage carousel is updated according to the predicted time and the occupancy duration.
2. The airport baggage carousel scheduling method according to claim 1, It is characterized in that The training process of the time prediction model includes: Using grid search to adjust the hyperparameters of the Xgboost model, so that the Xgboost models under different hyperparameters are respectively used as base models; Obtaining a second flight description of the scheduled flight, and performing feature encoding on the second flight description; Dividing the feature encoding result of the second description text into a training set, a validation set and a test set; Determining training samples for this training from the training set, and inputting the training samples into the basic model for training to adjust the weight parameters of the basic model; Using the validation set to validate the basic model after this training to obtain a first accuracy rate of the basic model after this training; When the first accuracy rate is less than the corresponding first threshold, the weight parameters of the basic model are adjusted in reverse, and the step of determining the training samples for the current training from the training set is returned to be executed; When the first accuracy rate is greater than or equal to the corresponding first threshold, the training is terminated, and the basic model after the training is used as a candidate time prediction model; For multiple candidate time prediction models corresponding to different hyperparameters, each candidate time prediction model is tested using a test set to obtain a second accuracy rate of each candidate time prediction model; The candidate time prediction model with the second highest accuracy among the multiple candidate time prediction models is used as the time prediction model.
3. The airport baggage carousel scheduling method according to claim 1, It is characterized in that The obtaining of the occupancy time of the baggage carousel by the target flight includes: The flights among the target flights whose predicted times are within the specified time period are taken as flights to be scheduled; Obtain the occupancy time of the baggage carousel by the flight to be scheduled.
4. The airport baggage carousel scheduling method according to claim 1, It is characterized in that The obtaining of the occupancy time of the baggage carousel by the target flight includes: Obtaining the total weight and total number of pieces of baggage of the target flight, and obtaining the maximum load weight and maximum load number of pieces of baggage carousel; Sorting the target flights according to the order of the predicted time from early to late; Flights are merged based on the sorting results of the target flights, and the two adjacent flights to be merged meet the following conditions: the time difference of the predicted time is less than the corresponding second threshold, the sum of the total baggage weight is less than the maximum carrying weight, and the sum of the total number of baggage pieces is less than the maximum carrying number of pieces.
5. The airport baggage carousel scheduling method according to claim 1, It is characterized in that The allocating a target baggage carousel for the target flight from the baggage carousels by comparing the predicted time and the idle time comprises: Acquire the working state of the luggage carousel, where the working state is an open state or a closed state; determining a first luggage carousel in the open state and a second luggage carousel in the closed state among the luggage carousels; Determining whether the first baggage carousel is empty; If the first luggage carousel is empty, selecting one of the second luggage carousels as a target luggage carousel, and controlling the target luggage carousel to switch from a closed state to an open state; If the first baggage carousel is not empty, determining whether there is a third baggage carousel among the first baggage carousels whose idle time is earlier than the predicted time; If the third baggage carousel exists, selecting the one of the third baggage carousels with the latest idle time as the target baggage carousel; If the third baggage carousel does not exist, determining whether there is a fourth baggage carousel among the first baggage carousels, the time difference between the idle time and the predicted time being less than a corresponding third threshold; If the fourth baggage carousel exists, selecting the one of the fourth baggage carousels with the earliest idle time as the target baggage carousel; If the fourth baggage carousel does not exist, determining whether the second baggage carousel is empty; If the second baggage carousel is empty, selecting the first baggage carousel with the earliest idle time as the target baggage carousel; If the second luggage carousels are not empty, one of the second luggage carousels is selected as a target luggage carousel, and the target luggage carousel is controlled to switch from a closed state to an open state.
6. The airport baggage carousel scheduling method according to claim 5, It is characterized in that The airport baggage carousel scheduling method also includes: The idle time of the first luggage carousel is counted, and when the idle time is greater than a corresponding fourth threshold, the first luggage carousel is controlled to switch from an open state to a closed state.
7. An airport baggage carousel dispatching device, It is characterized in that The airport baggage carousel dispatching device comprises: Model training module, used to pre-train the time prediction model; A time prediction module is used to obtain a first flight description of a target flight and perform feature coding on the first flight description; retrieve the time prediction model and input the feature coding result of the first flight description into the time prediction model to obtain a predicted time for the target flight to arrive at the baggage carousel; The carousel scheduling module is used to obtain the occupancy time of the baggage carousel by the target flight and the idle time of the baggage carousel; by comparing the predicted time with the idle time, a target baggage carousel is allocated to the target flight from the baggage carousels, and the target idle time corresponding to the target baggage carousel is updated according to the predicted time and the occupancy time.
8. A computer program product, It is characterized in that The method comprises computer-readable instructions, and when the computer-readable instructions are executed on an electronic device, the electronic device implements the airport baggage carousel scheduling method according to any one of claims 1 to 6.
9. An electronic device, It is characterized in that The method comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the airport baggage carousel scheduling method as described in any one of claims 1 to 6.
10. A computer storage medium, It is characterized in that The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the airport baggage carousel scheduling method as described in any one of claims 1 to 6.
