Parking space distribution method, computer equipment, readable storage medium and program product

Abstract

The invention relates to a gate position distribution method, computer equipment, a readable storage medium and a program product. The corresponding relation between flight information of all to-be-distributed flights and gate position identifiers of all gate positions in an airport based on sliding time is generated, constraint conditions are generated based on gate position configuration information and the flight information through a distribution model, and the gate position identifiers of all the to-be-distributed flights are distributed on the basis of the corresponding relation and the constraint conditions. And outputting each piece of target gate position information which enables the sliding time of each flight to be shortest. Compared with a traditional method for distributing the parking spaces based on historical artificial experience, the method has the advantages that the flight information, the parking space identification, the parking space configuration information and the constructed corresponding relation are combined, the target parking space information enabling the sliding time of each flight to be shortest is output through the distribution model, and the airport transfer efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of neural networks, and in particular to a parking position allocation method and device, computer equipment, computer readable storage medium and computer program product. BACKGROUND

[0002] For an airport as a transit hub, the transit efficiency affects the service timeliness of express logistics and other freight services. In order to ensure the business processing efficiency of the transit hub airport, it is necessary to reasonably allocate parking positions. At present, the parking position allocation method for the freight airport of the transit hub is usually allocated by artificial based on historical experience. However, the parking position allocation based on artificial historical experience has one-sidedness, which will lead to unreasonable parking position allocation, and further lead to the decline of freight transit efficiency.

[0003] Therefore, the current parking position allocation method for the freight airport has the defect of low efficiency. SUMMARY

[0004] Therefore, it is necessary to provide a parking position allocation method, device, computer equipment, computer readable storage medium and computer program product capable of transit efficiency for the above technical problems.

[0005] In a first aspect, the present application provides a parking position allocation method, which comprises:

[0006] obtaining flight information of each flight to be allocated, obtaining parking position identifiers and parking position configuration information of each parking position in the airport;

[0007] generating a corresponding relationship between each flight information and each parking position identifier based on taxi time;

[0008] inputting the flight information, the parking position configuration information and the corresponding relationship into a trained allocation model, generating a constraint condition according to the parking position configuration information and the flight information by the allocation model, and outputting each target parking position information which makes the taxi time of each flight shortest based on the corresponding relationship and the constraint condition.

[0009] In one embodiment, the obtaining flight information of each flight to be allocated comprises:

[0010] obtaining flight identifiers, planned landing times and planned take-off times corresponding to each flight;

[0011] obtaining the flight information according to the flight identifier, the planned landing time and the planned take-off time.

[0012] In one of the embodiments, the flight information, the stand configuration information and the correspondence are input into a trained allocation model, the allocation model generates constraint conditions according to the stand configuration information and the flight information, and based on the correspondence and the constraint conditions, target stand information for each flight that minimizes taxi time for each flight is output, including:

[0013] The flight information, the stand configuration information and the correspondence are input into a trained allocation model, the allocation model generates constraint conditions according to the stand configuration information, the flight identifier, the planned landing time and the planned takeoff time, and determines each available stand corresponding to each flight as a constraint condition;

[0014] For each flight, based on the correspondence, each taxi path between the flight and each available stand is determined, and based on each taxi path, each taxi time for the flight to taxi to each available stand is determined;

[0015] The target stand information corresponding to the shortest taxi time among each taxi time is output.

[0016] In one of the embodiments, the determination of each available stand corresponding to each flight according to the stand configuration information, the flight identifier, the planned landing time and the planned takeoff time includes:

[0017] According to the stand configuration information, the service type and the reuse time threshold corresponding to each stand are determined;

[0018] For each flight, according to the service type corresponding to the flight identifier of the flight, each candidate stand corresponding to the service type among each stand is determined;

[0019] The allocated flight information corresponding to each candidate stand is obtained, and according to the allocated flight information, the allocated time period corresponding to each candidate stand is determined;

[0020] The preset unavailable time period corresponding to each candidate stand is obtained, and according to the preset unavailable time period, the reuse time threshold and the allocated time period, the available time period corresponding to each candidate stand is determined;

[0021] The planned landing time, the planned takeoff time and the available time period are matched, and according to the matching result, each available stand corresponding to the flight is determined.

[0022] In one of the embodiments, the generation of the correspondence between each flight information and each stand identifier based on taxi time includes:

[0023] obtain a flight identifier in each of the flight information, and determine a row index according to each of the flight identifier;

[0024] obtain a parking position identifier in each of the parking position, and determine a column index according to each of the parking position identifier;

[0025] generate a dense matrix based on taxi time according to the row index, the column index and taxi time of each of the flight to each of the parking position, and obtain the corresponding relationship according to the dense matrix.

[0026] In one of the embodiments, after the output of each of the target parking position information which makes the taxi time of each of the flight shortest based on the corresponding relationship and the constraint condition, the method further comprises:

[0027] input each of the flight identifier and each of the target parking position information into a Kafka queue, and push each of the flight identifier and each of the target parking position information to a management terminal corresponding to each of the flight through the Kafka queue; the management terminal is used to instruct a flight corresponding to each of the flight identifier to stop according to each of the flight identifier and each of the target parking position information.

[0028] In one of the embodiments, the obtaining of the flight information of each of the flight to be allocated and the obtaining of the parking position identifier and the parking position configuration information of each of the parking position in the airport comprises:

[0029] obtain original flight information corresponding to each of the flight, and obtain each of the original parking position identifier and the original parking position configuration information in the airport;

[0030] filter and standardize each of the original flight information, each of the original parking position identifier and each of the original parking position configuration information to obtain each of the flight information, each of the parking position identifier and each of the parking position configuration information.

[0031] In a second aspect, the application provides a parking position allocation device, comprising:

[0032] The obtaining module 500 is used to obtain the flight information of each of the flight to be allocated and obtain the parking position identifier and the parking position configuration information of each of the parking position in the airport.

[0033] The generating module 502 is used to generate a corresponding relationship based on taxi time between each of the flight information and each of the parking position identifier.

[0034] The allocation module 504 is configured to input the flight information, the stand configuration information and the correspondence into a trained allocation model, generate constraint conditions according to the stand configuration information and the flight information by the allocation model, and output each target stand information that makes the taxiing time of each flight shortest based on the correspondence and the constraint conditions.

[0035] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0036] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the above method when executed by a processor.

[0037] In a fifth aspect, the present application provides a computer program product, comprising a computer program, and the computer program implements the steps of the above method when executed by a processor.

[0038] The above stand allocation method, device, computer device, computer readable storage medium and computer program product generate a correspondence between the flight information of each flight to be allocated and the stand identifier of each stand in the airport based on taxiing time, generate constraint conditions based on stand configuration information and flight information by an allocation model, and output each target stand information that makes the taxiing time of each flight shortest based on the correspondence and the constraint conditions. Compared with the traditional stand allocation based on artificial historical experience, the present application combines flight information, stand identifier, stand configuration information and the constructed correspondence, and outputs target stand information that makes the taxiing time of each flight shortest by the allocation model, thereby improving the transfer efficiency in the airport. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0040] Figure 1 It is a flowchart of the stand allocation method in one embodiment;

[0041] Figure 2 It is a schematic diagram of the region division step in one embodiment;

[0042] Figure 3 It is a structural block diagram of the stand allocation device in one embodiment;

[0043] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0045] In one embodiment, such as Figure 1 As shown, a parking space allocation method is provided. This embodiment illustrates the application of this method to a terminal. It is understood that this method can also be applied to a server, and also to a system including a terminal and a server, and implemented through the interaction between the terminal and the server, including the following steps S202 to S206. Wherein:

[0046] Step S202: Obtain flight information for each flight to be assigned, and obtain parking stand identifiers and parking stand configuration information for each parking stand in the airport.

[0047] Cargo airports require multiple flights to dock for cargo transshipment, loading and unloading, and other operations. To ensure the operational efficiency of cargo airports, parking positions need to be allocated to each flight in advance, and the allocated parking positions need to meet efficiency requirements as much as possible, such as shortening the taxiing time of flights in the airport so that they can complete cargo transshipment as quickly as possible.

[0048] The terminal can be a management device at a cargo airport. To allocate parking spaces, the terminal can obtain flight information for each flight to be allocated. This flight information can include information on all flights that need to dock at the aforementioned airport within a preset period, such as flight information for all flights within a single day.

[0049] The aforementioned airport may also include multiple parking stands, and the terminal can obtain the parking stand identifier and configuration information of each parking stand in the airport. The parking stand identifier may include information such as the parking stand number; the parking stand configuration information may include relevant information pre-configured for the parking stand, such as the area to which the parking stand belongs, the types of aircraft that can park there, and the usage rules for the parking stand.

[0050] The terminal can obtain the aforementioned flight information, parking position identifiers, and parking position configuration information by preprocessing the raw data.

[0051] In one embodiment, obtaining flight information for each flight to be assigned and obtaining parking stand identifiers and parking stand configuration information for each parking stand in the airport includes: obtaining the original flight information corresponding to each flight and obtaining the original parking stand identifiers and original parking stand configuration information in the airport; filtering and standardizing the original flight information, original parking stand identifiers and original parking stand configuration information to obtain the flight information, parking stand identifiers and parking stand configuration information.

[0052] In this embodiment, the terminal can obtain the original flight information corresponding to each flight, as well as the original parking stand identifiers and original parking stand configuration information in the airport, from the airport system's database. For example, the terminal can read the relevant data through MySQL. The original flight information, original parking stand identifiers, and original parking stand configuration information can all represent unprocessed flight information, parking stand identifiers, and parking stand configuration information. The terminal can combine business logic to preprocess the original flight information and original parking stand identifiers, performing filtering and standardization, etc., to obtain the aforementioned flight information, parking stand identifiers, and parking stand configuration information.

[0053] Specifically, for each parking stand in the airport, the terminal can obtain information such as the parking stand number as a parking stand identifier. Furthermore, the terminal can also obtain parking stand-related data such as the combined parking stand number, parking stand level, available aircraft types, available airlines, available flight attributes, unavailability start time, and unavailability end time, as parking stand configuration information. When determining whether parking stand allocation is necessary, the terminal can use Kafka to poll parking stand request information at a preset frequency. Upon receiving a request command, the terminal can initiate the parking stand allocation algorithm. The preset frequency can be set according to actual conditions, for example, every 20 seconds.

[0054] Step S204: Generate the correspondence between each flight information and each parking position identifier based on taxiing time.

[0055] Each flight needs to land at a different location within the airport, requiring taxiing from that location to a suitable parking stand. The terminal can optimize parking stand allocation by combining flight information with the mapping between flight and parking stands, thereby reducing taxiing time. Specifically, when optimizing taxiing time, the terminal can generate a time-based mapping between each flight's information and each parking stand identifier. For example, the terminal determines the flight's location based on flight information and the parking stand's location based on the parking stand identifier. Thus, the terminal can use the taxiing time between the flight's location and the parking stand's location as the optimization target in the mapping, generating the mapping between flight information and parking stand identifiers.

[0056] Step S206: Input the flight information, parking stand configuration information and corresponding relationship into the trained allocation model. The allocation model generates constraints based on the parking stand configuration information and flight information, and outputs the target parking stand information that minimizes the taxiing time of each flight based on the corresponding relationship and constraints.

[0057] The terminal can pre-train an allocation model for parking space allocation. Specifically, the terminal can generate corresponding relationship samples based on flight information samples and parking space identifier samples, and iteratively train the allocation model based on these relationship samples, flight information samples, and parking space configuration information samples. In each training iteration, the model parameters are adjusted, and a trained allocation model is obtained when a preset training termination condition is met.

[0058] After obtaining the trained allocation model, the terminal can input the flight information, parking stand configuration information, and corresponding relationships into the model. The allocation model can generate corresponding constraints based on the parking stand configuration information and flight information. These constraints include restrictions on the parking area and parking time for each flight. Based on the corresponding relationships and constraints, the allocation model can determine the target parking stand information for each flight. The corresponding relationships include multiple flights and multiple parking stand identifiers. For each flight, the allocation model can, based on these relationships, use 0-1 decision variables in the airport's corresponding digital twin model to determine the path for the flight to reach the parking stand corresponding to each parking stand identifier, and thus determine the taxiing time for the flight to reach the parking stand corresponding to each parking stand identifier. Therefore, the allocation model can combine the taxiing time between the flight and each parking stand in the above correspondence, as well as the above constraints, to filter out the parking stands that the flight is allowed to park at from each parking stand. Then, from the allowed parking stands, it determines the target parking stand information with the shortest taxiing time as the parking stand for that flight. The terminal can use the allocation model to determine the above target parking stand information for each flight in the above correspondence, and then the terminal uses the allocation model to output the target parking stand information with the shortest taxiing time for each flight.

[0059] In one embodiment, after outputting the target parking position information that minimizes the taxiing time of each flight based on the correspondence and constraints, the method further includes: inputting each flight identifier and each target parking position information into a Kafka queue, and pushing each flight identifier and each target parking position information to the management terminal corresponding to each flight through the Kafka queue; the management terminal is used to instruct the flight corresponding to each flight identifier to park according to each flight identifier and each target parking position information.

[0060] In this embodiment, the terminal can guide each flight to park based on the target parking position information corresponding to each flight. The terminal can output messages using Kafka. For example, the terminal can input the flight identifiers and target parking position information corresponding to each flight into a Kafka queue, and then push these information to the business system, such as the management terminal at the airport, through the Kafka queue. The management terminal can then instruct the flights corresponding to each flight identifier to park based on the flight identifiers and their corresponding target parking positions. For example, after storing the target parking position information corresponding to each flight identifier, the management terminal can, upon receiving a flight parking request, look up the corresponding target parking position information based on the flight identifier and instruct the flight to park at the corresponding parking position. Furthermore, the terminal can also synchronously store the flight identifiers and their corresponding target parking position information in a database for future reference during parking.

[0061] This allows the terminal to pre-allocate cargo parking spaces, including those based on pre-defined airport zoning according to operational areas. Furthermore, the terminal uses an allocation model to allocate parking spaces with the goal of minimizing transit time. This ensures more flights can land at the right locations at the right times, thereby reducing aircraft taxiing time and cargo transport time. Moreover, by comprehensively considering airport zoning, hard constraints on airport operational safety, logistics efficiency requirements, and priority constraints for mitigating operational risks, the terminal outputs a pre-allocation plan to improve transit time targets.

[0062] Specifically, the aforementioned target parking space allocation scheme can encompass various application scenarios. For example, the terminal can allocate parking spaces based on flight scheduling. The parking space algorithm can assist cargo airports in flight scheduling, ensuring that arriving and departing cargo aircraft have suitable parking spaces. The terminal can utilize the aforementioned parking space allocation for space utilization optimization. The parking space algorithm can optimize parking space allocation according to the needs of different types of cargo aircraft and airlines, maximizing the utilization of cargo airport space resources. The terminal can also utilize the aforementioned parking space allocation method for resource management. Through the parking space algorithm, the usage of parking spaces can be monitored in real time, and resources can be allocated according to demand to ensure that each cargo aircraft has sufficient parking space.

[0063] The terminal can utilize the aforementioned parking space allocation method for emergency response. In emergency situations, the parking space algorithm can help quickly reallocate and plan the parking positions of various cargo aircraft to facilitate time-saving operations. The terminal can also use this method for cargo handling and transfer. The algorithm considers the location of cargo handling and transfer facilities to enable direct cargo loading, unloading, and transfer operations within the cargo airport, improving cargo handling efficiency. Furthermore, the terminal can leverage this method for airline cooperation and allocation. The algorithm helps airport managers coordinate cooperation and resource allocation among airlines, ensuring a fair and equitable distribution of appropriate parking spaces to different airlines. Finally, the terminal can support multiple aircraft types. The algorithm considers different types, sizes, and special requirements of cargo aircraft and plans parking positions based on their characteristics to meet the needs of various aircraft.

[0064] The aforementioned parking stand allocation method generates a correspondence between flight information of each flight to be allocated and parking stand identifiers in the airport based on taxiing time. An allocation model then generates constraints based on parking stand configuration information and flight information. Based on the correspondence and constraints, it outputs target parking stand information that minimizes the taxiing time for each flight. Compared to traditional parking stand allocation based on manual historical experience, this solution improves airport transfer efficiency by combining flight information, parking stand identifiers, parking stand configuration information, and the constructed correspondence, and outputting target parking stand information that minimizes the taxiing time for each flight through the allocation model.

[0065] In one embodiment, obtaining flight information for each flight to be assigned includes: obtaining the flight identifier, planned landing time, and planned departure time for each flight; and obtaining flight information based on the flight identifier, planned landing time, and planned departure time.

[0066] In this embodiment, the terminal can obtain various types of flight information as flight information. For example, the terminal can obtain the flight identifier, planned landing time, and planned departure time corresponding to each flight, and obtain the flight information based on the aforementioned flight identifier, planned landing time, and planned departure time.

[0067] The aforementioned flight identifier represents a unique identifier used to identify a flight, such as its flight number. The planned landing time is the estimated time when the flight intends to land at the airport, and the planned departure time is the estimated time when the flight will prepare to take off again after landing at the airport. Therefore, the terminal can combine the aforementioned flight identifier, planned landing time, and planned departure time to allocate parking positions for flights.

[0068] Specifically, the terminal can obtain flight information through Kafka, including but not limited to tail number, aircraft type, aircraft type class, unique arrival identifier, arrival flight number, planned landing time of the arrival flight at this station, origin airport of the arrival flight, arrival type, arrival taxiway head number, unique departure identifier, departure flight number, planned departure time of the departure flight at this station, destination airport of the departure flight, departure type, departure taxiway head number, and other flight-related data as flight information. Additionally, a flight may include multiple Unit Load Devices (ULDs) for cargo transportation; therefore, the flight information obtained by the terminal may also include ULD-related data, including but not limited to pallet / container number, ticket quantity, cargo weight, ULD processing type, container type, tail number of the arrival aircraft, unique arrival identifier, arrival flight number, cabin class of the arrival flight, tail number of the departure aircraft, unique departure identifier, departure flight number, destination airport of the departure flight, and other ULD-related data. The container equipment in different flights represents different business types. Therefore, the terminal can combine the above flight information and the ULD information transported in the flight to allocate parking positions for the flight.

[0069] Through this embodiment, the terminal can combine various types of flight information to form flight information, thereby enabling the terminal to allocate parking spaces based on flight information containing various types of information, which improves the efficiency of airport transfers.

[0070] In one embodiment, flight information, parking stand configuration information, and correspondence are input into a trained allocation model. The allocation model generates constraints based on the parking stand configuration information and flight information, and outputs target parking stand information that minimizes the taxiing time for each flight based on the correspondence and constraints. This includes: inputting flight information, parking stand configuration information, and correspondence into a trained allocation model; the allocation model determines each available parking stand corresponding to each flight based on the parking stand configuration information, flight identifier, planned landing time, and planned departure time, as constraints; for each flight, based on the correspondence, determining each taxiing path between the flight and each available parking stand, and determining each taxiing time for the flight to taxi to each available parking stand based on each taxiing path; and outputting the target parking stand information corresponding to the shortest taxiing time among all taxiing times.

[0071] In this embodiment, the terminal can utilize a trained allocation model to allocate target parking positions. After the terminal inputs the aforementioned flight information, parking position configuration information, and corresponding relationships into the trained allocation model, the allocation model can determine the available parking positions corresponding to each flight based on the parking position configuration information, flight identifiers in the flight information, planned landing times, and planned departure times. Thus, the terminal can use these available parking positions as constraints. Furthermore, each available parking position also carries a permitted parking time period; that is, the constraints consider both the area constraints and parking time constraints of the parking positions.

[0072] Therefore, the allocation model can allocate parking stands to each flight based on constraints. Specifically, for each flight, the allocation model determines the taxiing paths between the flight and each available parking stand based on the aforementioned correspondence, and determines the taxiing time from each taxiing path to the available parking stand. The terminal can then use the allocation model to determine the shortest taxiing time from among these times and use the parking stand information corresponding to this shortest taxiing time as the target parking stand information. After determining the target parking stand information for each flight, the allocation model can output the target parking stand information for each flight. When allocating parking spaces, the allocation model can simultaneously allocate parking spaces for multiple flights and determine the target parking spaces that simultaneously meet the requirements of minimizing taxiing time and avoiding parking space conflicts for each flight. Alternatively, the allocation model can allocate parking spaces to each flight in sequence based on the planned landing time. For flights with later landing times, the allocation model needs to consider the time periods and areas in which already allocated parking spaces are occupied when determining the available parking spaces.

[0073] Specifically, the aforementioned correspondence can be a dense matrix based on taxiing time, where a dense matrix represents a matrix with a large proportion of non-zero elements. The aforementioned allocation model can be an ILP (integer linear programming) model, where variables take integer values. After the terminal establishes a dense matrix based on taxiing time according to flight identifiers and parking stand identifiers, it can define 0-1 decision variables for the relationship between flights and parking stands. The terminal mathematically encodes the objectives of parking stand zoning and minimizing the total cargo taxiing time, determining the objective function with the shortest cargo taxiing time as the goal. An ILP model is then constructed as the allocation model, and this allocation model, based on the aforementioned flight identifiers, planned landing time, and planned departure time, yields constraints on available parking stands determined by zoning settings, reuse time, and interval duration. Among them, the zone setting indicates the business type requirements for flights parking at this parking position, the reuse time indicates that when flights use the same parking position at the same time, the difference between the planned take-off time of the previous aircraft and the planned landing time of the next aircraft must meet the parameter settings, and the interval duration indicates the parking time between parking positions of different business types.

[0074] In specific predictions, the terminal can input information from multiple flights into the allocation model. For example, the terminal can input the flight information, gate information, and the aforementioned correspondence into the allocation model. The allocation model can verify its effectiveness using the GUROBI (a next-generation large-scale mathematical programming optimizer) solver. Based on partition settings, reuse time, and interval duration, the allocation model determines the available parking positions for each flight and performs path planning based on 0-1 decision variables to determine the aforementioned taxiing paths. This then determines the taxiing time for each flight to reach each available parking position. For example, the taxiing time is obtained based on the taxiing path and the aircraft's preset taxiing speed. From these taxiing times, the target parking position information corresponding to the shortest taxiing time is determined. Thus, the allocation model can output the target parking position information for each flight that achieves the shortest taxiing time. The terminal can also calculate the score of the objective function based on the aforementioned target parking position schemes to verify whether the constraints of the parking scheme, including the target parking position information for each flight, are satisfied. If the constraints are not met, the terminal can retrain the allocation model.

[0075] Through this embodiment, the terminal can use the allocation model to allocate parking spaces for each flight within a preset period by combining flight information, parking space information and corresponding relationships, thereby improving the efficiency of airport transfers.

[0076] In one embodiment, determining the available parking stands for each flight based on parking stand configuration information, flight identifier, planned landing time, and planned departure time includes: determining the service type and reuse time threshold corresponding to each parking stand based on the parking stand configuration information; for each flight, determining candidate parking stands corresponding to the service type among the parking stands based on the flight identifier; obtaining the allocated flight information corresponding to each candidate parking stand, and determining the allocated time period corresponding to each candidate parking stand based on the allocated flight information; obtaining the preset unavailable time period corresponding to each candidate parking stand, and determining the available time period corresponding to each candidate parking stand based on the preset unavailable time period, reuse time threshold, and allocated time period; matching the planned landing time, planned departure time, and available time period, and determining the available parking stands corresponding to the flight based on the matching result.

[0077] In this embodiment, the terminal can determine constraints in the allocation model, including determining the available parking positions for each flight. The determination of available parking positions requires consideration of service type and time period. The terminal can use the allocation model, based on parking configuration information, to determine the service type and reuse time threshold corresponding to each parking position. The reuse time threshold indicates that when flights use the same parking position simultaneously, the difference between the planned takeoff time of the preceding aircraft and the planned landing time of the following aircraft must meet the specified parameter settings. For each flight, the terminal can use the allocation model to obtain the flight identifier and determine the corresponding service type based on the flight identifier. For example, the allocation model determines the relevant data of the ULD (Unique Airline Display) carried by the flight based on the flight identifier, and then determines the service type of the flight based on the ULD data. Thus, the allocation model can obtain candidate parking positions from the aforementioned parking positions that meet the above-mentioned service types.

[0078] The allocation model can obtain the allocated flight information corresponding to each candidate parking position and determine the allocated time period corresponding to each candidate parking position based on the allocated flight information. The allocated flight information represents relevant information about the flights already allocated to that parking position, including the parking area and parking duration, so the allocation model can determine the allocated time period based on the parking duration. Additionally, the terminal can pre-determine the unavailable time periods for each candidate parking position as preset unavailable time periods. Thus, the terminal can obtain the preset unavailable time periods corresponding to each candidate parking position and determine the available time periods corresponding to each candidate parking position based on the preset unavailable time periods, the reuse time threshold, and the allocated time periods. After determining the available time periods for each candidate parking position, the terminal can determine the parking time period for the flight based on the flight's scheduled landing time and scheduled departure time, and match the parking time period with the aforementioned available time periods. Based on the matching results, it can determine the available parking positions from multiple candidate parking positions whose available time periods include the parking time periods.

[0079] Specifically, such as Figure 2 As shown, Figure 2 This is a schematic diagram of the area division steps in one embodiment. The terminal can pre-divide the business areas and set time thresholds in the airport's digital twin model. These settings can be used as parameters in the algorithm, including partition settings and reuse time thresholds. Figure 2 For example, based on business scenarios and geographical location, the terminal divides parking spaces into eight business zones according to business type. Each zone corresponds to a different business type, accommodating flights of different business types. These zones include the south side of the West U-Trough, the left half of the West U-Trough, the right half of the West U-Trough, the upper left and middle sections of the North Pivot, the lower left section of the North Pivot, the right half of the East U-Trough, and the left half of the East U-Trough. Each zone is configured with an adjacent time interval, and parameters such as the reuse time threshold and business type are set for each parking space within each zone. Therefore, the allocation model can determine the available parking spaces using the zoning settings and reuse time thresholds configured in the aforementioned digital twin model.

[0080] Through this embodiment, the terminal can combine pre-set partition information, reuse time threshold, unavailable time period and allocated time period, and combine the flight take-off and landing time to determine the available parking positions for the flight, and then determine the parking position with the shortest taxiing time based on the available parking positions, thereby improving the efficiency of airport transfers.

[0081] In one embodiment, generating a correspondence between each flight information and each parking stand identifier based on taxiing time includes: obtaining the flight identifier from each flight information; determining the row index based on each flight identifier; determining the column index based on each parking stand identifier; generating a dense matrix based on taxiing time based on the row index, column index, and taxiing time of each flight to each parking stand; and obtaining the correspondence based on the dense matrix.

[0082] In this embodiment, the above correspondence can be a dense matrix. The terminal can construct a dense matrix based on taxiing time based on the relevant information of flights and parking positions, and then use the dense matrix to allocate parking positions.

[0083] For example, after obtaining the flight identifiers from each flight information, the terminal can use these flight identifiers as row indices; after obtaining the gate identifiers, the terminal can determine the column indices based on these gate identifiers. The row and column indices can be parameters used to construct a dense matrix. Based on the flight indices, column indices, and the taxiing times of each flight to each gate, the terminal generates a dense matrix based on taxiing times. The taxiing times in this dense matrix can be a state to be determined; the terminal can use an allocation model to determine the taxiing times between each flight and each gate in the dense matrix.

[0084] Specifically, the terminal constructs a dense matrix of taxiing times from flight to parking stand using flight-related data and parking stand-related data. Here, the flight identifier can be a unique flight number, and the parking stand identifier can be a parking stand number. The terminal constructs a dense matrix based on taxiing time, using each flight number as a row index and the parking stand number as a column index, to represent the aforementioned correspondence. The terminal can then utilize this correspondence in the allocation model to allocate parking stands.

[0085] Through this embodiment, the terminal can combine flight identifiers and parking stand identifiers to construct a dense matrix that associates each flight with each parking stand based on taxiing time, serving as the aforementioned correspondence. This correspondence is then used to allocate parking stands with the shortest taxiing time to each flight, thereby improving the efficiency of airport transfers.

[0086] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0087] Based on the same inventive concept, this application also provides a parking space allocation device for implementing the parking space allocation method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more parking space allocation device embodiments provided below can be found in the limitations of the parking space allocation method described above, and will not be repeated here.

[0088] In one exemplary embodiment, such as Figure 3 As shown, a parking space allocation device is provided, including: an acquisition module 500, a generation module 502, and an allocation module 504, wherein:

[0089] The acquisition module 500 is used to acquire flight information of each flight to be assigned, and to acquire parking stand identifiers and parking stand configuration information of each parking stand in the airport.

[0090] The generation module 502 is used to generate the correspondence between each flight information and each parking position identifier based on taxiing time.

[0091] The allocation module 504 is used to input flight information, parking stand configuration information and corresponding relationships into the trained allocation model. The allocation model generates constraints based on the parking stand configuration information and flight information, and outputs the target parking stand information that minimizes the taxiing time of each flight based on the corresponding relationships and constraints.

[0092] In one embodiment, the acquisition module 500 is used to acquire the flight identifier, planned landing time, and planned departure time corresponding to each flight; and to obtain flight information based on the flight identifier, planned landing time, and planned departure time.

[0093] In one embodiment, the allocation module 504 is used to input flight information, parking stand configuration information, and corresponding relationships into a trained allocation model. The allocation model determines each available parking stand corresponding to each flight based on the parking stand configuration information, flight identifier, planned landing time, and planned takeoff time, as a constraint condition. For each flight, based on the corresponding relationship, it determines each taxiing path between the flight and each available parking stand, and determines each taxiing time for the flight to taxi to each available parking stand based on each taxiing path. It outputs the target parking stand information corresponding to the shortest taxiing time among all taxiing times.

[0094] In one embodiment, the allocation module 504 is configured to: determine the service type and reuse time threshold corresponding to each parking stand based on the parking stand configuration information; for each flight, determine each candidate parking stand corresponding to the service type based on the flight identifier of the flight; obtain the allocated flight information corresponding to each candidate parking stand, and determine the allocated time period corresponding to each candidate parking stand based on the allocated flight information; obtain the preset unavailable time period corresponding to each candidate parking stand, and determine the available time period corresponding to each candidate parking stand based on the preset unavailable time period, reuse time threshold, and allocated time period; match the planned landing time, planned departure time, and available time period, and determine each available parking stand corresponding to the flight based on the matching result.

[0095] In one embodiment, the generation module 502 is used to obtain the flight identifier in each flight information, determine the row index based on each flight identifier, determine the column index based on each parking stand identifier, generate a dense matrix based on the taxiing time based on the row index, column index and the taxiing time of each flight to each parking stand, and obtain the corresponding relationship based on the dense matrix.

[0096] In one embodiment, the above-mentioned device further includes: a push module, used to input each flight identifier and each target parking position information into the Kafka queue, and push each flight identifier and each target parking position information to the management terminal corresponding to each flight through the Kafka queue; the management terminal is used to instruct the flight corresponding to each flight identifier to park according to each flight identifier and each target parking position information.

[0097] In one embodiment, the acquisition module 500 is used to acquire the original flight information corresponding to each flight, acquire the original parking stand identifiers and original parking stand configuration information in the airport; and filter and standardize the original flight information, original parking stand identifiers and original parking stand configuration information to obtain the flight information, parking stand identifiers and parking stand configuration information.

[0098] Each module in the aforementioned parking space allocation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0099] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a stop position allocation method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0100] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0101] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the stop bit allocation method described above.

[0102] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the stop bit allocation method described above.

[0103] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the stop bit allocation method described above.

[0104] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0105] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0106] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0107] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method of allocating a parking space, characterized in that, The method comprises: obtaining flight information of each flight to be allocated, obtaining parking space identifiers and parking space configuration information of each parking space in the airport; generating a correspondence relationship between each flight information and each parking space identifier based on taxi time; inputting the flight information, the parking space configuration information and the correspondence relationship into a trained allocation model, generating constraint conditions according to the parking space configuration information and the flight information by the allocation model, and outputting target parking space information that makes the taxi time of each flight shortest based on the correspondence relationship and the constraint conditions.

2. The method of claim 1, wherein, The method comprises: obtaining flight information of each flight to be allocated, obtaining parking space identifiers and parking space configuration information of each parking space in the airport; generating a correspondence relationship between each flight information and each parking space identifier based on taxi time; 3. The method of claim 2, wherein, inputting the flight information, the parking space configuration information and the correspondence relationship into a trained allocation model, generating constraint conditions according to the parking space configuration information and the flight information by the allocation model, and outputting target parking space information that makes the taxi time of each flight shortest based on the correspondence relationship and the constraint conditions. The method comprises: obtaining flight information of each flight to be allocated, obtaining parking space identifiers and parking space configuration information of each parking space in the airport; generating a correspondence relationship between each flight information and each parking space identifier based on taxi time; 4. The method of claim 3, wherein, inputting the flight information, the parking space configuration information and the correspondence relationship into a trained allocation model, generating constraint conditions according to the parking space configuration information and the flight information by the allocation model, and outputting target parking space information that makes the taxi time of each flight shortest based on the correspondence relationship and the constraint conditions. The method comprises: obtaining flight information of each flight to be allocated, obtaining parking space identifiers and parking space configuration information of each parking space in the airport; generating a correspondence relationship between each flight information and each parking space identifier based on taxi time; inputting the flight information, the parking space configuration information and the correspondence relationship into a trained allocation model, generating constraint conditions according to the parking space configuration information and the flight information by the allocation model, and outputting target parking space information that makes the taxi time of each flight shortest based on the correspondence relationship and the constraint conditions. The method comprises:

5. The method of claim 1, wherein, obtaining flight information of each flight to be allocated, obtaining parking space identifiers and parking space configuration information of each parking space in the airport; generating a correspondence relationship between each flight information and each parking space identifier based on taxi time; inputting the flight information, the parking space configuration information and the correspondence relationship into a trained allocation model, generating constraint conditions according to the parking space configuration information and the flight information by the allocation model, and outputting target parking space information that makes the taxi time of each flight shortest based on the correspondence relationship and the constraint conditions. The method comprises: obtaining flight information of each flight to be allocated, obtaining parking space identifiers and parking space configuration information of each parking space in the airport; generating a correspondence relationship between each flight information and each parking space identifier based on taxi time; inputting the flight information, the parking space configuration information and the correspondence relationship into a trained allocation model, generating constraint conditions according to the parking space configuration information and the flight information by the allocation model, and outputting target parking space information that makes the taxi time of each flight shortest based on the correspondence relationship and the constraint conditions. The method comprises: obtaining flight information of each flight to be allocated, obtaining parking space identifiers and parking space configuration information of each parking space in the airport; generating a correspondence relationship between each flight information and each parking space identifier based on taxi time; inputting the flight information, the parking space configuration information and the correspondence relationship into a trained allocation model, generating constraint conditions according to the parking space configuration information and the flight information by the allocation model, and outputting target parking space information that makes the taxi time of each flight shortest based on the correspondence relationship and the constraint conditions. The method comprises: obtaining flight information of each flight to be allocated, obtaining parking space identifiers and parking space configuration information of each parking space in the airport; generating a correspondence relationship between each flight information and each parking space identifier based on taxi time; inputting the flight information, the parking space configuration information and the correspondence relationship into a trained allocation model, generating constraint conditions according to the parking space configuration information and the flight information by the allocation model, and outputting target parking space information that makes the taxi time of each flight shortest based on the correspondence relationship and the constraint conditions. Obtaining a flight identifier in each of the flight information, and determining a row index according to each of the flight identifier; Obtaining a parking space identifier in each of the parking space information, and determining a column index according to each of the parking space identifier; Generating a dense matrix based on the taxiing time according to the row index, the column index and the taxiing time of each of the flight to each of the parking space, and obtaining the corresponding relationship according to the dense matrix.

6. The method according to any one of claims 2 to 5, characterized in that, After the corresponding relationship and the constraint condition are obtained, the method further comprises: Inputting each of the flight identifier and each of the target parking space information into a Kafka queue, and pushing each of the flight identifier and each of the target parking space information to a management terminal corresponding to each of the flight through the Kafka queue; the management terminal is configured to instruct a flight corresponding to each of the flight identifier to stop according to each of the flight identifier and each of the target parking space information.

7. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: Obtaining original flight information corresponding to each of the flight, and obtaining each of the original parking space identifier and the original parking space configuration information in the airport; Filtering and standardizing each of the original flight information, each of the original parking space identifier and each of the original parking space configuration information to obtain each of the flight information, each of the parking space identifier and each of the parking space configuration information. 8.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-7. The processor executes the computer program to realize the steps of the method in any one of claims 1 to 7.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method in any one of claims 1 to 7.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method in any one of claims 1 to 7.

Images