CN111079274B - Intelligent allocation method for machine position, computer device and storage medium - Google Patents
Intelligent allocation method for machine position, computer device and storage medium Download PDFInfo
- Publication number
- CN111079274B CN111079274B CN201911229380.5A CN201911229380A CN111079274B CN 111079274 B CN111079274 B CN 111079274B CN 201911229380 A CN201911229380 A CN 201911229380A CN 111079274 B CN111079274 B CN 111079274B
- Authority
- CN
- China
- Prior art keywords
- machine position
- airport
- reinforcement learning
- allocation
- flight
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000003860 storage Methods 0.000 title claims abstract description 11
- 238000012549 training Methods 0.000 claims abstract description 92
- 238000009826 distribution Methods 0.000 claims abstract description 43
- 238000013507 mapping Methods 0.000 claims abstract description 9
- 230000002787 reinforcement Effects 0.000 claims description 89
- 238000004088 simulation Methods 0.000 claims description 47
- 238000004422 calculation algorithm Methods 0.000 claims description 26
- 230000008859 change Effects 0.000 claims description 15
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 description 11
- 238000004891 communication Methods 0.000 description 7
- 230000010006 flight Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000003032 molecular docking Methods 0.000 description 3
- 230000001413 cellular effect Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000004904 shortening Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a machine position intelligent distribution method, which comprises the steps of obtaining historical flight associated data of an airport and a historical machine position distribution scheme; and learning based on the historical flight association data and the historical machine position allocation scheme to obtain a machine position allocation training model, wherein the machine position allocation training model comprises a mapping relation between the flight association data and the machine position allocation scheme, and is used for outputting the machine position allocation scheme of the airport based on the real-time flight association data of the airport. The invention also provides a computer device and a storage medium for realizing the intelligent allocation method of the machine position. The invention can effectively distribute airport positions.
Description
Technical Field
The invention relates to the technical field of airport operation optimization, in particular to a machine position intelligent distribution method, a computer device and a storage medium.
Background
The airport position allocation refers to that an airport operation command center allocates proper positions for flights entering ports, and is used for airplane parking, boarding and disembarking, airplane maintenance and the like, and is a core task for resource allocation and scheduling of airports. Reasonable machine position distribution can effectively improve the operation efficiency of an airport and improve the satisfaction of passengers. Meanwhile, the airplane allocation task is a difficult point in airport business, a dispatcher needs to fully know airplane situation, airplane type and ground clothing situation, and meanwhile, the immediate situation of weather and various real-time information are comprehensively analyzed and adjusted, so that any error cannot be caused. The level of expertise required by the relevant personnel is high and the task is laborious.
The existing machine resource management mainly relies on airport commanders to perform manual distribution, the automation and informatization degree of the system are low, a large amount of manpower is required to be consumed, and the resource utilization rate is low.
Disclosure of Invention
In view of the foregoing, it is necessary to provide a machine position intelligent allocation method, a computer device and a storage medium, which are used for automatically allocating machine positions of an airport, improving the working efficiency of airport personnel and reducing the consumption of human resources.
The first aspect of the invention provides a smart allocation method for machine positions, comprising the following steps:
acquiring historical flight related data of an airport and a historical airplane position allocation scheme;
and learning based on the historical flight association data and the historical machine position allocation scheme to obtain a machine position allocation training model, wherein the machine position allocation training model comprises a mapping relation between the flight association data and the machine position allocation scheme, and is used for outputting the machine position allocation scheme of the airport based on the real-time flight association data of the airport.
Preferably, the historical flight related data includes flight position information, aircraft information, flight information, model information, passenger information, conflict information, taxi information, weather information.
Preferentially, the learning based on the historical flight related data and the historical machine allocation scheme, and the obtaining the machine allocation training model includes:
constructing a simulation environment and a reinforcement learning environment based on the historical flight related data and the historical machine position allocation scheme;
and performing reinforcement learning through a reinforcement learning algorithm based on the simulation environment and the reinforcement learning environment to obtain the machine position distribution training model.
Preferably, the constructing the simulation environment includes:
simulating the airport location and weather of the airport;
simulating a airport position allocation scheme of the airport; and
and simulating the boarding situation of passengers at the airport.
Preferably, the boarding of the passenger comprises: whether a ferry vehicle is used when the passenger boarding, and the distance from the boarding gate to the airplane.
Preferably, the building the reinforcement learning environment includes:
constructing the reinforcement learning environment based on reinforcement learning scheduling objectives, the scheduling objectives including: the situation of using a ferry vehicle when a passenger boarding is reduced, and the distance from a boarding gate to the boarding of the passenger to be walked is shortened.
Preferably, the performing reinforcement learning through reinforcement learning algorithm based on the simulation environment and the reinforcement learning environment, and obtaining the machine position allocation training model includes:
Training an initial machine position allocation training model through a reinforcement learning algorithm based on the simulation environment and the reinforcement learning environment, and outputting an initial machine position allocation scheme, wherein the initial machine position allocation scheme indicates the allocation scheme of the machine position of the airport simulated in the simulation environment;
distributing all the positions of the simulated airports in the simulation environment based on the initial position distribution scheme to obtain the change of the boarding condition of the passengers of the simulated airports in the simulation environment;
distributing training model feedback rewards to the initial positions based on the variation of the boarding condition of the passengers and the difference between the scheduling targets;
adjusting parameters of the initial machine position distribution training model based on the rewards to obtain the machine position distribution training model; wherein the reward represents a positive or negative rating of the initial level allocation scheme, the positive rating representing a tendency of the change in the boarding condition of the passenger toward the scheduling target, and the negative rating representing a departure of the change in the boarding condition of the passenger from the scheduling target.
Preferably, the performing reinforcement learning through reinforcement learning algorithm based on the simulation environment and the reinforcement learning environment, and obtaining the machine position allocation training model includes:
Training a neural network based on the historical flight related data to obtain a prediction model, wherein the prediction model is used for predicting the flight delay probability and the residual machine position; and
and performing reinforcement learning through a reinforcement learning algorithm based on the flight delay probability predicted by the prediction model, the rest machine positions, the simulation environment and the reinforcement learning environment to obtain the machine position distribution training model.
A second aspect of the present invention provides a computer apparatus, the computer apparatus comprising a processor and a memory, the memory for storing at least one instruction, the processor for executing the at least one instruction to implement the machine-location intelligent allocation method.
A third aspect of the present invention provides a computer readable storage medium storing at least one instruction that when executed by a processor implements the method of intelligent allocation of machine bits.
Compared with the prior art, the intelligent machine position distribution method, the computer device and the storage medium provided by the invention have the advantages that the historical flight related data and the historical machine position distribution scheme of the airport are obtained; and learning based on the historical flight association data and the historical machine position allocation scheme to obtain a machine position allocation training model, wherein the machine position allocation training model comprises a mapping relation between the flight association data and the machine position allocation scheme, and is used for outputting the machine position allocation scheme of the airport based on the real-time flight association data of the airport. The invention can automatically allocate the airport positions based on the implementation flight related data of the airport, thereby improving the working efficiency of airport personnel and reducing the consumption of human resources.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of an application environment of a smart allocation method for a machine location according to a preferred embodiment of the present invention.
FIG. 2 is a flow chart of a smart allocation method according to a preferred embodiment of the present invention.
FIG. 3 is a functional block diagram of the intelligent distribution system according to the preferred embodiment of the present invention.
Fig. 4 is a block diagram of a computer device according to a preferred embodiment of the present invention.
Description of the main reference signs
| Computer device | 3 |
| Big data platform | 4 |
| Airport | 5 |
| Intelligent machine position distribution system | 30 |
| Acquisition module | 301 |
| Execution module | 302 |
| Memory device | 31 |
| Processor and method for controlling the same | 32 |
| Communication bus | 33 |
The invention will be further described in the following detailed description in conjunction with the above-described figures.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings. It should be noted that, without conflict, the embodiments of the present invention and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, and the described embodiments are merely some, rather than all, embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
Referring to fig. 1, an application environment architecture diagram of a machine location intelligent allocation method according to a preferred embodiment of the present invention is shown.
The intelligent allocation method of the machine position is applied to an environment formed by one or more computer devices and/or a big data platform. For example, in an environment consisting of a computer device 3 and a big data platform 4. In one embodiment, the computer device 3 and big data platform 4 may establish a communication connection via wired (e.g., USB (Universal Serial Bus, universal serial bus)) or wireless means, which may be any type of conventional wireless communication technology, such as radio, wireless Fidelity (Wireless Fidelity, WIFI), cellular, satellite, broadcast, etc.
In this embodiment, the computer apparatus 3 may be a personal computer, a server, or other computing device. The big data platform 4 stores historical flight-related data for the airport 5 and a historical airport-level allocation scheme.
In this embodiment, the historical flight related data refers to the flight related data of the airport 5 before or within a preset period (for example, within one year). The flight related data includes, but is not limited to, flight position information, aircraft information, flight information, model information, guest information, collision information, taxi information, weather information, and the like.
The gate information may refer to a gate number, a corresponding gate type (may refer to a gate for docking a large aircraft or a gate for a small aircraft). The aircraft information may refer to an aircraft model, an aircraft type such as passenger aircraft or cargo aircraft. The flight information may refer to the departure time and the landing time, the departure place and the landing place of the aircraft. The model information may refer to an aircraft being one of a large aircraft, a medium aircraft, a small aircraft, or an aircraft model. The guest information may refer to whether a particular passenger such as a patient, an important passenger (e.g., a politician), etc. is present on the aircraft. The conflict information may refer to a conflict that occurs between two flights. For example, when an aircraft that was first parked at a certain flight level leaves the certain flight level less than a preset time period (e.g., 15 minutes) from the time point when the next aircraft is parked at the certain flight level. The taxiing information may refer to a distance that the aircraft is to taxi from a stand to leave the ground, a distance that the aircraft is to taxi from a landing to a stand, etc. The weather information may refer to the weather conditions of the aircraft during flight, such as the weather conditions at take-off, the weather conditions at landing.
The historical position allocation scheme refers to position allocation conditions of each flight of the airport 5 before or within a preset period (for example, within one year).
In this embodiment, the big data platform 4 may obtain the historical flight-related data of the airport 5 from an ADS-B (Automatic dependent surveillance-broadcast auto-correlation monitoring) system.
It should be noted that the ADS-B system is an aircraft monitoring technology, and an aircraft determines its position through a satellite navigation system and performs periodic broadcasting so that it can be tracked. The air traffic control ground station may receive this information and act as an alternative to the secondary radar, eliminating the need to transmit an interrogation signal from the ground.
In this embodiment, the computer device 3 may obtain the historical flight related data and the historical airplane position allocation scheme of the airport 5 from the big data platform 4, and learn to obtain the airplane position allocation training model based on the historical flight related data and the historical airplane position allocation scheme, so that the airplane position of the airport 5 may be automatically allocated by using the airplane position allocation training model. The description of fig. 2 is given below.
FIG. 2 is a flow chart of a smart allocation method according to a preferred embodiment of the present invention.
In this embodiment, the method for intelligent allocation of the machine location may be applied to a computer device, and for a computer device that needs intelligent allocation of the machine location, the function for intelligent allocation of the machine location provided by the method of the present invention may be directly integrated on the computer device, or may be run on the computer device in the form of a software development kit (Software Development Kit, SDK).
As shown in fig. 2, the intelligent allocation method for the machine position specifically includes the following steps, the order of the steps in the flowchart may be changed according to different requirements, and some steps may be omitted.
Step S1, the computer device 3 acquires historical flight related data and a historical airplane position allocation scheme of the airport 5 from the big data platform 4.
As previously mentioned, the historical flight-related data refers to the flight-related data of the airport 5 before or within a preset period of time (e.g., within one year). The flight related data includes, but is not limited to, flight position information, aircraft information, flight information, model information, guest information, collision information, taxi information, weather information, and the like.
The gate information may refer to a gate number, a corresponding gate type (may refer to a gate for docking a large aircraft or a gate for a small aircraft). The aircraft information may refer to an aircraft model, an aircraft type such as passenger aircraft or cargo aircraft. The flight information may refer to the departure time and the landing time, the departure place and the landing place of the aircraft. The model information may refer to an aircraft being one of a large aircraft, a medium aircraft, a small aircraft, or an aircraft model. The guest information may refer to whether a particular passenger such as a patient, an important passenger (e.g., a politician), etc. is present on the aircraft. The conflict information may refer to a conflict that occurs between two flights. For example, when an aircraft that was first parked at a certain flight level leaves the certain flight level less than a preset time period (e.g., 15 minutes) from the time point when the next aircraft is parked at the certain flight level. The taxiing information may refer to a distance that the aircraft is to taxi from a stand to leave the ground, a distance that the aircraft is to taxi from a landing to a stand, etc. The weather information may refer to the weather conditions of the aircraft during flight, such as the weather conditions at take-off, the weather conditions at landing.
The historical position allocation scheme refers to position allocation conditions of each flight of the airport 5 before or within a preset period (for example, within one year).
And step S2, the computer device 3 learns based on the historical flight related data and the historical machine position allocation scheme to obtain a machine position allocation training model. The machine position allocation training model comprises a mapping relation between flight association data and a machine position allocation scheme.
In one embodiment, the computer device 3 may train the get crew allocation training model based on the historical flight crew association data using machine learning, reinforcement learning (Reinforcement learning), linear programming, evolutionary learning, search and recommendation, and like algorithms.
In this embodiment, the learning based on the historical flight related data and the historical crew allocation scheme to obtain the crew allocation training model includes (a 1) - (a 2):
(a1) Constructing a simulation environment and a reinforcement learning (Reinforcement Learning) environment based on the historical flight related data and the historical machine position allocation scheme; and
(a2) And performing reinforcement learning through a reinforcement learning algorithm based on the simulation environment and the reinforcement learning environment to obtain the machine position distribution training model.
In one embodiment, the reinforcement learning algorithm includes, but is not limited to, Q learning, sarsa.
In one embodiment, the building a simulation environment includes: simulating each airport location and weather of the airport 5; simulating a airport position allocation scheme of the airport 5; and simulating boarding of passengers at said airport 5.
In one embodiment, the building the reinforcement learning environment includes:
the reinforcement learning environment is constructed based on reinforcement learning scheduling objectives including, but not limited to, reducing the use of ferry cars when passengers board their aircraft, shortening the distance the passenger will travel from boarding gate to boarding the aircraft. The boarding condition of the passenger refers to whether a ferry vehicle is used when the passenger boarding, and the distance from the boarding gate to the airplane is the distance from the passenger to the airplane.
In one embodiment, the performing reinforcement learning through reinforcement learning algorithm based on the simulation environment and the reinforcement learning environment, to obtain the machine position allocation training model includes:
training an initial machine position allocation training model through a reinforcement learning algorithm based on the simulation environment and the reinforcement learning environment, and outputting an initial machine position allocation scheme, wherein the initial machine position allocation scheme indicates the allocation scheme of the machine position of the airport simulated in the simulation environment;
Distributing all the positions of the simulated airports in the simulation environment based on the initial position distribution scheme to obtain the change of the boarding condition of the passengers of the simulated airports in the simulation environment;
distributing training model feedback rewards to the initial positions based on the variation of the boarding condition of the passengers and the difference between the scheduling targets;
adjusting parameters of the initial machine position distribution training model based on the rewards to obtain the machine position distribution training model; wherein the reward represents a positive or negative rating of the initial level allocation scheme, the positive rating representing a tendency of the change in the boarding condition of the passenger toward the scheduling target, and the negative rating representing a departure of the change in the boarding condition of the passenger from the scheduling target.
In one embodiment, the initial machine allocation training model is a neural network module.
In other embodiments, the computer device 3 may also train a neural network (e.g., a convolutional neural network) to obtain a predictive model based on historical flight-related data of the airport 5. The prediction model is used for predicting the flight delay probability and the rest of the airplane positions.
Specifically, the computer device 3 may train the neural network to obtain the predictive model based on the airplane position information, the aircraft information, the flight information, and the weather information included in the historical flight-related data.
In other embodiments, the computer apparatus 3 performs reinforcement learning through a reinforcement learning algorithm based on the flight delay probability predicted by the prediction model, the remaining flight positions, the simulation environment, and the reinforcement learning environment, to obtain the flight position allocation training model.
And step S3, the computer device 3 stores the machine position allocation training model. For example, the model of the machine allocation training model is stored in a memory of the computer device 3 or in an external device, such as another memory device, which is communicatively connected to the computer device 3.
In practical application, a device such as the computer device 3 or other devices that needs to utilize the machine position allocation training model may download the machine position allocation training model, so that the machine position allocation training model is utilized to output the machine position allocation scheme of the airport 5 based on the real-time flight related data of the airport 5, and allocate the machine position for the flights of the airport 5.
Specifically, after the device that needs to utilize the machine position allocation training model downloads the machine position allocation training model, real-time flight related data of the airport 5 can be obtained from the big data platform 4, so that a real-time allocation scheme of the airport 5 can be obtained by utilizing the machine position allocation training model, manual allocation is not needed, manpower consumption is reduced, and machine position allocation efficiency is improved.
In summary, in the machine position intelligent allocation method provided by the embodiment of the invention, the historical flight associated data and the historical machine position allocation scheme of the airport are obtained; learning based on the historical flight associated data and the historical machine position allocation scheme to obtain a machine position allocation training model, wherein the machine position allocation training model comprises a mapping relation between the flight associated data and the machine position allocation scheme; and outputting the airport position allocation scheme based on the real-time flight related data of the airport by using the airplane position allocation training model. The airport position automatic allocation device can automatically allocate airport positions, improves the working efficiency of airport personnel and reduces the consumption of human resources.
The foregoing fig. 1 describes the smart machine allocation method of the present invention in detail, and the following describes, with reference to fig. 3 and fig. 4, a functional module of a software system implementing the smart machine allocation method and a hardware device architecture implementing the smart machine allocation method.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
Referring to fig. 3, a block diagram of a smart distribution system according to a preferred embodiment of the present invention is shown.
In some embodiments, the smart distribution system 30 operates in the computer device 3. The smart distribution system 30 may include a plurality of functional modules that are comprised of program code segments. Program code for each program segment in the smart distribution system 30 may be stored in the memory 31 of the computer device 3 and executed by the at least one processor 32 to implement the smart distribution function (see fig. 2 for details).
In this embodiment, the smart distribution system 30 may be divided into a plurality of functional modules according to the functions performed by the smart distribution system. The functional module may include: an acquisition module 301 and an execution module 302. The module referred to in the present invention refers to a series of computer program segments capable of being executed by at least one processor and of performing a fixed function, stored in a memory. In the present embodiment, the functions of the respective modules will be described in detail in the following embodiments.
The acquiring module 301 acquires the historical flight related data and the historical airplane position allocation scheme of the airport 5 from the big data platform 4.
As previously mentioned, the historical flight-related data refers to the flight-related data of the airport 5 before or within a preset period of time (e.g., within one year). The flight related data includes, but is not limited to, flight position information, aircraft information, flight information, model information, guest information, collision information, taxi information, weather information, and the like.
The gate information may refer to a gate number, a corresponding gate type (may refer to a gate for docking a large aircraft or a gate for a small aircraft). The aircraft information may refer to an aircraft model, an aircraft type such as passenger aircraft or cargo aircraft. The flight information may refer to the departure time and the landing time, the departure place and the landing place of the aircraft. The model information may refer to an aircraft being one of a large aircraft, a medium aircraft, a small aircraft, or an aircraft model. The guest information may refer to whether a particular passenger such as a patient, an important passenger (e.g., a politician), etc. is present on the aircraft. The conflict information may refer to a conflict that occurs between two flights. For example, when an aircraft that was first parked at a certain flight level leaves the certain flight level less than a preset time period (e.g., 15 minutes) from the time point when the next aircraft is parked at the certain flight level. The taxiing information may refer to a distance that the aircraft is to taxi from a stand to leave the ground, a distance that the aircraft is to taxi from a landing to a stand, etc. The weather information may refer to the weather conditions of the aircraft during flight, such as the weather conditions at take-off, the weather conditions at landing.
The historical position allocation scheme refers to position allocation conditions of each flight of the airport 5 before or within a preset period (for example, within one year).
The execution module 302 learns based on the historical flight related data and the historical machine allocation scheme to obtain a machine allocation training model. The machine position allocation training model comprises a mapping relation between flight association data and a machine position allocation scheme.
In one embodiment, the execution module 302 may train the get crew allocation training model based on the historical flight crew association data using machine learning, reinforcement learning (Reinforcement learning), linear programming, evolutionary learning, search and recommendation, and like algorithms. In this embodiment, the learning based on the historical flight related data and the historical crew allocation scheme to obtain the crew allocation training model includes (a 1) - (a 2):
(a1) Constructing a simulation environment and a reinforcement learning (Reinforcement Learning) environment based on the historical flight related data and the historical machine position allocation scheme; and
(a2) And performing reinforcement learning through a reinforcement learning algorithm based on the simulation environment and the reinforcement learning environment to obtain the machine position distribution training model.
In one embodiment, the reinforcement learning algorithm includes, but is not limited to, Q learning, sarsa.
In one embodiment, the building a simulation environment includes: simulating each airport location and weather of the airport 5; simulating a airport position allocation scheme of the airport 5; and simulating boarding of passengers at said airport 5.
In one embodiment, the building the reinforcement learning environment includes:
the reinforcement learning environment is constructed based on reinforcement learning scheduling objectives including, but not limited to, reducing the use of ferry cars when passengers board their aircraft, shortening the distance the passenger will travel from boarding gate to boarding the aircraft. The boarding condition of the passenger refers to whether a ferry vehicle is used when the passenger boarding, and the distance from the boarding gate to the airplane is the distance from the passenger to the airplane.
In one embodiment, the performing reinforcement learning through reinforcement learning algorithm based on the simulation environment and the reinforcement learning environment, to obtain the machine position allocation training model includes:
training an initial machine position allocation training model through a reinforcement learning algorithm based on the simulation environment and the reinforcement learning environment, and outputting an initial machine position allocation scheme, wherein the initial machine position allocation scheme indicates the allocation scheme of the machine position of the airport simulated in the simulation environment;
Distributing all the positions of the simulated airports in the simulation environment based on the initial position distribution scheme to obtain the change of the boarding condition of the passengers of the simulated airports in the simulation environment;
distributing training model feedback rewards to the initial positions based on the variation of the boarding condition of the passengers and the difference between the scheduling targets;
adjusting parameters of the initial machine position distribution training model based on the rewards to obtain the machine position distribution training model; wherein the reward represents a positive or negative rating of the initial level allocation scheme, the positive rating representing a tendency of the change in the boarding condition of the passenger toward the scheduling target, and the negative rating representing a departure of the change in the boarding condition of the passenger from the scheduling target.
In one embodiment, the initial machine allocation training model is a neural network module.
In other embodiments, the execution module 302 also trains a neural network (e.g., convolutional neural network) to obtain a predictive model based on the historical flight-related data of the airport 5. The prediction model is used for predicting the flight delay probability and the rest of the airplane positions.
Specifically, the execution module 302 may train the neural network to obtain the predictive model based on the flight location information, aircraft information, flight information, and weather information included in the historical flight association data.
In one embodiment, the execution module 302 further performs reinforcement learning through reinforcement learning algorithm based on the flight delay probability predicted by the prediction model, and the remaining flight positions, the simulation environment and the reinforcement learning environment, to obtain the flight position distribution training model.
The execution module 302 saves the machine allocation training model. For example, the model of the machine allocation training model is stored in a memory of the computer device 3 or in an external device, such as another memory device, which is communicatively connected to the computer device 3.
In practical application, a device such as the computer device 3 or other devices that needs to utilize the machine position allocation training model may download the machine position allocation training model, so that the machine position allocation training model is utilized to output the machine position allocation scheme of the airport 5 based on the real-time flight related data of the airport 5, and allocate the machine position for the flights of the airport 5.
Specifically, after the device that needs to utilize the machine position allocation training model downloads the machine position allocation training model, real-time flight related data of the airport 5 can be obtained from the big data platform 4, so that a real-time allocation scheme of the airport 5 can be obtained by utilizing the machine position allocation training model, manual allocation is not needed, manpower consumption is reduced, and machine position allocation efficiency is improved.
In summary, in the intelligent machine position distribution system provided by the embodiment of the invention, the historical flight associated data and the historical machine position distribution scheme of the airport are obtained; and learning based on the historical flight association data and the historical machine position allocation scheme to obtain a machine position allocation training model, wherein the machine position allocation training model comprises a mapping relation between the flight association data and the machine position allocation scheme, and is used for outputting the machine position allocation scheme of the airport based on the real-time flight association data of the airport. The airport position automatic allocation device can automatically allocate airport positions, improves the working efficiency of airport personnel and reduces the consumption of human resources.
Referring to fig. 4, a schematic structure of a computer device according to a preferred embodiment of the invention is shown. In the preferred embodiment of the invention, the computer device 3 includes a memory 31, at least one processor 32, at least one communication bus 33. It will be appreciated by those skilled in the art that the configuration of the computer device shown in fig. 4 is not limiting of the embodiments of the present invention, and that either a bus-type configuration or a star-type configuration is possible, and that the computer device 3 may also include more or less other hardware or software than that shown, or a different arrangement of components.
In this embodiment, the computer device 3 and a big data platform 4 can be connected by wired (e.g. USB (Universal Serial Bus, universal serial bus)) or wireless means, which can be any type of conventional wireless communication technology, such as radio, wireless fidelity (Wireless Fidelity, WIFI), cellular, satellite, broadcast, etc.
In this embodiment, the computer apparatus 3 may be a personal computer, a server, or other computing device.
In some embodiments, the computer device 3 includes a terminal capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and its hardware includes, but is not limited to, a microprocessor, an application specific integrated circuit, a programmable gate array, a digital processor, an embedded device, and the like.
It should be noted that the computer device 3 is only used as an example, and other electronic products that may be present in the present invention or may be present in the future are also included in the scope of the present invention by way of reference.
In some embodiments, the memory 31 is used to store program code and various data, such as a smart distribution system 30 installed in the computer device 3, and to enable high-speed, automatic access to programs or data during operation of the computer device 3. The Memory 31 includes a Read-Only Memory (ROM), a programmable Read-Only Memory (PROM), an erasable programmable Read-Only Memory (EPROM), a One-time programmable Read-Only Memory (One-time Programmable Read-Only Memory, OTPROM), an Electrically erasable rewritable Read-Only Memory (EEPROM), a compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM) or other optical disc Memory, a magnetic tape Memory, or any other computer readable storage medium that can be used to carry or store data.
In some embodiments, the at least one processor 32 may be comprised of an integrated circuit, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The at least one processor 32 is a Control Unit (Control Unit) of the computer apparatus 3, connects the respective components of the entire computer apparatus 3 using various interfaces and lines, and executes various functions of the computer apparatus 3 and processes data, such as a function of performing intelligent allocation of a machine location, by running or executing programs or modules stored in the memory 31, and calling data stored in the memory 31.
In some embodiments, the at least one communication bus 33 is arranged to enable connected communication between the memory 31 and the at least one processor 32 or the like.
Although not shown, the computer device 3 may further include a power source (such as a battery) for powering the various components, and preferably the power source may be logically connected to the at least one processor 32 via a power management device, such that functions of managing charging, discharging, and power consumption are performed by the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The computer device 3 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described in detail herein.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The integrated units implemented in the form of software functional modules described above may be stored in a computer readable storage medium. The software functional modules described above are stored in a storage medium and include instructions for causing a computer device (which may be a server, a personal computer, etc.) or a processor (processor) to perform portions of the methods described in the various embodiments of the invention.
In a further embodiment, in connection with fig. 3, the at least one processor 32 may execute the operating device of the computer device 3 as well as various installed applications (such as the smart distribution system 30), program code, etc., such as the various modules described above.
The memory 31 has program code stored therein, and the at least one processor 32 can invoke the program code stored in the memory 31 to perform related functions. For example, each of the modules depicted in fig. 3 is a program code stored in the memory 31 and executed by the at least one processor 32 to implement the functions of the respective modules for the purpose of intelligent allocation of machine bits.
In one embodiment of the present invention, the memory 31 stores one or more instructions (i.e., at least one instruction) that are executed by the at least one processor 32 for the purpose of intelligent allocation of machine bits.
Referring to fig. 1, a specific implementation method of the at least one instruction by the at least one processor 32 includes:
acquiring historical flight related data of an airport and a historical airplane position allocation scheme;
and learning based on the historical flight association data and the historical machine position allocation scheme to obtain a machine position allocation training model, wherein the machine position allocation training model comprises a mapping relation between the flight association data and the machine position allocation scheme, and is used for outputting the machine position allocation scheme of the airport based on the real-time flight association data of the airport.
According to a preferred embodiment of the present invention, the historical flight-related data includes flight position information, aircraft information, flight information, model information, guest information, collision information, taxi information, weather information.
According to a preferred embodiment of the present invention, the learning based on the historical flight related data and the historical machine allocation scheme, to obtain a machine allocation training model includes:
Constructing a simulation environment and a reinforcement learning environment based on the historical flight related data and the historical machine position allocation scheme;
and performing reinforcement learning through a reinforcement learning algorithm based on the simulation environment and the reinforcement learning environment to obtain the machine position distribution training model.
According to a preferred embodiment of the present invention, the constructing a simulation environment includes:
simulating the airport location and weather of the airport;
simulating a airport position allocation scheme of the airport; and
and simulating the boarding situation of passengers at the airport.
According to a preferred embodiment of the present invention, the boarding of the passenger comprises: whether a ferry vehicle is used when the passenger boarding, and the distance from the boarding gate to the airplane.
According to a preferred embodiment of the present invention, the constructing the reinforcement learning environment includes:
constructing the reinforcement learning environment based on reinforcement learning scheduling objectives, the scheduling objectives including: the situation of using a ferry vehicle when a passenger boarding is reduced, and the distance from a boarding gate to the boarding of the passenger to be walked is shortened.
According to a preferred embodiment of the present invention, the performing reinforcement learning by reinforcement learning algorithm based on the simulation environment and the reinforcement learning environment, to obtain the machine position allocation training model includes:
Training an initial machine position allocation training model through a reinforcement learning algorithm based on the simulation environment and the reinforcement learning environment, and outputting an initial machine position allocation scheme, wherein the initial machine position allocation scheme indicates the allocation scheme of the machine position of the airport simulated in the simulation environment;
distributing all the positions of the simulated airports in the simulation environment based on the initial position distribution scheme to obtain the change of the boarding condition of the passengers of the simulated airports in the simulation environment;
distributing training model feedback rewards to the initial positions based on the variation of the boarding condition of the passengers and the difference between the scheduling targets;
adjusting parameters of the initial machine position distribution training model based on the rewards to obtain the machine position distribution training model; wherein the reward represents a positive or negative rating of the initial level allocation scheme, the positive rating representing a tendency of the change in the boarding condition of the passenger toward the scheduling target, and the negative rating representing a departure of the change in the boarding condition of the passenger from the scheduling target.
According to a preferred embodiment of the present invention, the performing reinforcement learning by reinforcement learning algorithm based on the simulation environment and the reinforcement learning environment, to obtain the machine position allocation training model includes:
Training a neural network based on the historical flight related data to obtain a prediction model, wherein the prediction model is used for predicting the flight delay probability and the residual machine position; and
and performing reinforcement learning through a reinforcement learning algorithm based on the flight delay probability predicted by the prediction model, the rest machine positions, the simulation environment and the reinforcement learning environment to obtain the machine position distribution training model.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or 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 solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it will be obvious that the term "comprising" does not exclude other elements or that the singular does not exclude a plurality. A plurality of units or means recited in the apparatus claims can also be implemented by means of one unit or means in software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (7)
1. A machine location intelligent allocation method, the method comprising:
acquiring historical flight related data of an airport and a historical airplane position allocation scheme;
learning based on the historical flight related data and the historical machine position allocation scheme to obtain a machine position allocation training model, wherein the machine position allocation training model comprises a mapping relation between the flight related data and the machine position allocation scheme, the machine position allocation training model is used for outputting the machine position allocation scheme of the airport based on the real-time flight related data of the airport, learning is performed based on the historical flight related data and the historical machine position allocation scheme, and the machine position allocation training model comprises:
constructing a simulation environment and a reinforcement learning environment based on the historical flight related data and the historical machine position allocation scheme; the building of the simulation environment comprises the following steps: simulating the airport location and weather of the airport; simulating a airport position allocation scheme of the airport; simulating the boarding situation of passengers at the airport;
based on the simulation environment and the reinforcement learning environment, reinforcement learning is performed through a reinforcement learning algorithm, and the machine position allocation training model is obtained, and comprises the following steps:
Training an initial machine position allocation training model through a reinforcement learning algorithm based on the simulation environment and the reinforcement learning environment, and outputting an initial machine position allocation scheme, wherein the initial machine position allocation scheme indicates the allocation scheme of the machine position of the airport simulated in the simulation environment;
distributing all the positions of the simulated airports in the simulation environment based on the initial position distribution scheme to obtain the change of the boarding condition of the passengers of the simulated airports in the simulation environment;
distributing training model feedback rewards to the initial machine position based on the variation of the boarding condition of the passengers and the difference between the scheduling targets;
adjusting parameters of the initial machine position distribution training model based on the rewards to obtain the machine position distribution training model; wherein the reward represents a positive or negative rating of the initial level allocation scheme, the positive rating representing a tendency of the change in the boarding condition of the passenger toward the scheduling target, and the negative rating representing a departure of the change in the boarding condition of the passenger from the scheduling target.
2. The method of claim 1, wherein the historical flight-related data includes flight information, aircraft information, flight information, model information, guest information, conflict information, taxi information, weather information.
3. The intelligent allocation method of airplane position according to claim 1, wherein said boarding of a passenger comprises: whether a ferry vehicle is used when the passenger boarding, and the distance from the boarding gate to the airplane.
4. The machine location intelligent distribution method according to claim 1, wherein the constructing the reinforcement learning environment includes:
constructing the reinforcement learning environment based on reinforcement learning scheduling objectives, the scheduling objectives including: the situation of using a ferry vehicle when a passenger boarding is reduced, and the distance from a boarding gate to the boarding of the passenger to be walked is shortened.
5. The method of claim 1, wherein the performing reinforcement learning by reinforcement learning algorithm based on the simulation environment and the reinforcement learning environment to obtain the machine allocation training model comprises:
training a neural network based on the historical flight related data to obtain a prediction model, wherein the prediction model is used for predicting the flight delay probability and the residual machine position; and
and performing reinforcement learning through a reinforcement learning algorithm based on the flight delay probability predicted by the prediction model, the rest machine positions, the simulation environment and the reinforcement learning environment to obtain the machine position distribution training model.
6. A computer device, characterized in that it comprises a processor and a memory, said memory being adapted to store at least one instruction, said processor being adapted to execute said at least one instruction to implement the smart allocation method of machine bits according to any one of claims 1 to 5.
7. A computer readable storage medium storing at least one instruction which when executed by a processor implements the method of intelligent allocation of machine bits according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911229380.5A CN111079274B (en) | 2019-12-04 | 2019-12-04 | Intelligent allocation method for machine position, computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911229380.5A CN111079274B (en) | 2019-12-04 | 2019-12-04 | Intelligent allocation method for machine position, computer device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111079274A CN111079274A (en) | 2020-04-28 |
| CN111079274B true CN111079274B (en) | 2024-04-09 |
Family
ID=70312897
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911229380.5A Active CN111079274B (en) | 2019-12-04 | 2019-12-04 | Intelligent allocation method for machine position, computer device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111079274B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112819285B (en) * | 2021-01-05 | 2023-09-26 | 北京百度网讯科技有限公司 | Flight matching processing and training method, device and equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106558261A (en) * | 2016-12-14 | 2017-04-05 | 天津盛扬信远科技有限公司 | A kind of airport floor manager analog machine |
| CN107578159A (en) * | 2017-08-29 | 2018-01-12 | 飞友科技有限公司 | It is a kind of to adapt to the abnormal seat in the plane auto-allocation method of flight itineraries |
| DE102017116192A1 (en) * | 2016-07-19 | 2018-01-25 | Ford Global Technologies, Llc | Using virtual data to test and train parking lot detection systems |
| CN108038508A (en) * | 2017-12-12 | 2018-05-15 | 携程旅游网络技术（上海）有限公司 | Method for pushing, system, storage medium and the electronic equipment of connecting flight |
| EP3444762A1 (en) * | 2017-08-15 | 2019-02-20 | Honeywell International Inc. | Aircraft stand management |
| CN109859532A (en) * | 2019-02-28 | 2019-06-07 | 深圳市北斗智能科技有限公司 | A kind of the break indices method and relevant apparatus of multi-constraint condition |
| CN109872064A (en) * | 2019-02-12 | 2019-06-11 | 民航成都信息技术有限公司 | A kind of Airport Resources distribution method, device, equipment and medium |
| CN109871990A (en) * | 2019-01-30 | 2019-06-11 | 西南交通大学 | Consider the break indices method of transit passenger's most short route time |
| CN109872033A (en) * | 2018-12-29 | 2019-06-11 | 华中科技大学 | A kind of Airport Gate Position Scheduling method |
| CN110163491A (en) * | 2019-04-30 | 2019-08-23 | 中国电子科技集团公司第二十八研究所 | A kind of the aircraft gate dispatching method and scheduling system of the real-time elasticity optimizing handling capacity |
-
2019
- 2019-12-04 CN CN201911229380.5A patent/CN111079274B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102017116192A1 (en) * | 2016-07-19 | 2018-01-25 | Ford Global Technologies, Llc | Using virtual data to test and train parking lot detection systems |
| CN106558261A (en) * | 2016-12-14 | 2017-04-05 | 天津盛扬信远科技有限公司 | A kind of airport floor manager analog machine |
| EP3444762A1 (en) * | 2017-08-15 | 2019-02-20 | Honeywell International Inc. | Aircraft stand management |
| CN107578159A (en) * | 2017-08-29 | 2018-01-12 | 飞友科技有限公司 | It is a kind of to adapt to the abnormal seat in the plane auto-allocation method of flight itineraries |
| CN108038508A (en) * | 2017-12-12 | 2018-05-15 | 携程旅游网络技术（上海）有限公司 | Method for pushing, system, storage medium and the electronic equipment of connecting flight |
| CN109872033A (en) * | 2018-12-29 | 2019-06-11 | 华中科技大学 | A kind of Airport Gate Position Scheduling method |
| CN109871990A (en) * | 2019-01-30 | 2019-06-11 | 西南交通大学 | Consider the break indices method of transit passenger's most short route time |
| CN109872064A (en) * | 2019-02-12 | 2019-06-11 | 民航成都信息技术有限公司 | A kind of Airport Resources distribution method, device, equipment and medium |
| CN109859532A (en) * | 2019-02-28 | 2019-06-07 | 深圳市北斗智能科技有限公司 | A kind of the break indices method and relevant apparatus of multi-constraint condition |
| CN110163491A (en) * | 2019-04-30 | 2019-08-23 | 中国电子科技集团公司第二十八研究所 | A kind of the aircraft gate dispatching method and scheduling system of the real-time elasticity optimizing handling capacity |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111079274A (en) | 2020-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107169677B (en) | Centralized dispatching command system for civil airport apron security vehicles | |
| US10909857B2 (en) | Blockchain airspace management system | |
| US20190057327A1 (en) | Cumulative model for scheduling and resource allocation for airline operations | |
| EP3321867A1 (en) | A method for maintaining aircraft and a configuration system and a computing device thereof | |
| US20180012499A1 (en) | System and Method for Predicting Aircraft Taxi Time | |
| CN108615411B (en) | Method and device for processing flight information | |
| JP2022527429A (en) | How and system to operate a vehicle fleet | |
| Liu et al. | Robust assignment of airport gates with operational safety constraints | |
| WO2019186594A1 (en) | Method and system for auto task allocation & recommending ground equipment, manpower to improve turnaround time of aircrafts in airport | |
| CN111145596A (en) | Method and device for predicting delay duration | |
| CN114282823A (en) | Vehicle scheduling method and device, storage medium and electronic equipment | |
| CN114358446B (en) | Robust optimization method for airport resource scheduling | |
| CN111079274B (en) | Intelligent allocation method for machine position, computer device and storage medium | |
| EP4109360A1 (en) | Systems and methods for determining vehicle capability for dispatch | |
| US20220139232A1 (en) | Systems and methods for predicting flight data | |
| US20180229856A1 (en) | Monitoring aircraft operational parameters during turnaround of an aircraft | |
| Karaman | Simulating air transportation networks under capacity constraints: Transforming into a multi-hub infrastructure | |
| CN113095543B (en) | Distribution method and system for airport stand and taxiway | |
| Das et al. | Deep Learning Based Negotiation Strategy Selection for Cooperative Conflict Resolution in Urban Air Mobility | |
| CN112819993A (en) | System and method for predicting flight data | |
| CN111737006A (en) | Full network traffic scheduling optimization method, device, computer equipment and storage medium | |
| Moeller | Airport Technology Management | |
| CN117993580B (en) | Multi-agent cooperation-based stand allocation method, equipment and medium | |
| Aristo et al. | Indonesia's New Capital City Development Strategy from Mobility Optimization Perspective | |
| El Asri et al. | Aircraft Ground Handling Operations: A Literary Review |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |