CN111145596A

CN111145596A - Method and device for predicting delay time

Info

Publication number: CN111145596A
Application number: CN201911236240.0A
Authority: CN
Inventors: 罗文洲; 谭玮; 郭鹏飞; 裴成; 王磊; 张辉; 肖禹
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2019-12-05
Filing date: 2019-12-05
Publication date: 2020-05-12

Abstract

Embodiments of the present application provide a method and device for predicting delay duration. The delay duration of the target flight can be predicted through the present application, wherein, the delay duration of the target flight is predicted due to the combination of delay parameters of various dimensions of the target flight, and the delay parameters at least include: weather parameters at the scheduled departure time of the target flight, the target flight The air traffic control parameters, the delay time of the previous flight of the target flight, the minimum transit time of the target flight, and the mechanical failure parameters of the target flight, etc.; and the delay of the target flight is predicted by combining multiple types of delay parameters and target prediction models. The length of the delay makes the predicted delay time more accurate, which is helpful for the airline's flight scheduling, ground crew scheduling and emergency plan formulation, thus improving the airline's service quality and enhancing the airline's competitiveness. important practical significance.

Description

Method and device for predicting delay duration

Technical Field

The present application relates to the field of intelligent traffic technologies, and in particular, to a method and an apparatus for predicting a delay duration.

Background

At present, the flight delay problem of civil aviation is attracted to more and more professionals. The delayed flight not only brings direct economic loss to airports and airlines, but also causes great inconvenience to the normal traveling of passengers, and can seriously disturb the normal order of the airports.

If the delay time of future flights can be estimated, flight scheduling, flight-to-ground-service scheduling and emergency scheme formulation of an airline company are facilitated, so that the method has important practical significance for improving the service quality of the airline company and improving the competitiveness of the airline company.

However, how to estimate the delay time of the flight is an urgent technical problem to be solved.

Disclosure of Invention

The embodiment of the application shows a method and a device for predicting delay duration.

In a first aspect, an embodiment of the present application shows a method for predicting a delay duration, where the method includes:

receiving an acquisition request of the delay time of a target flight;

obtaining a plurality of types of delay parameters for delaying the takeoff time of the target flight from a database according to the obtaining request, wherein the delay parameters at least comprise: weather parameters of a scheduled takeoff time of a target flight, aviation control parameters of the target flight, delay time of a preamble flight of the target flight, minimum station-crossing time of the target flight and mechanical fault parameters of the target flight;

and inputting a plurality of delay parameters of the types into a target prediction model to obtain the delay duration of the target flight output by the target prediction model.

In an optional implementation, the method further includes:

and in the case that the user selects among a plurality of flights, outputting the delay time length of each flight to the user.

The method further comprises the following steps:

and storing the corresponding relation between the flight identification of the target flight and the delay time of the target flight.

In an optional implementation, the method further includes:

the delay time of each flight is output to the airline's staff.

In an optional implementation, the method further includes:

and at least automatically adjusting flight scheduling, flight ground service scheduling and emergency schemes of the airline according to the delay time of each flight.

In an optional implementation manner, the obtaining a plurality of delay parameters for delaying the target flight includes:

for any one kind of delay parameter, acquiring a time interval of the kind of delay parameter suitable for the target flight;

and obtaining a plurality of delay parameters of the types of the target flight in the time interval.

In an optional implementation, the method further includes:

and if the obtained plurality of the types of delay parameters positioned in the time interval are missing, completing the types of delay parameters positioned in the time interval.

In an optional implementation, completing the class of delinquent parameters located within the time interval includes:

determining a parameter to be supplemented according to a plurality of delay parameters of the types;

and combining the parameters to be compensated and the plurality of kinds of delay parameters into the kinds of delay parameters in the time interval.

In an optional implementation manner, the determining a parameter to be supplemented according to the plurality of delay parameters includes:

determining a degree of fluctuation between the plurality of delay parameters;

calculating a first average parameter among a plurality of delay parameters of the type under the condition that the fluctuation degree is smaller than a preset degree;

and determining the first average parameter as the parameter to be compensated.

determining the location of missing delinquent parameters within a plurality of said classes of delinquent parameters;

determining a degree of fluctuation between a preset number of delay parameters adjacent to the location among a plurality of the kinds of delay parameters;

under the condition that the fluctuation degree is smaller than the preset degree, calculating and determining a parameter to be supplemented according to a plurality of delay parameters of the types;

and determining the second average parameter as the parameter to be compensated.

and under the condition that the fluctuation degree is smaller than the preset degree, determining a delay parameter adjacent to the position as the parameter to be compensated.

In an optional implementation, the method further includes:

obtaining a plurality of sample parameter sets, wherein each sample parameter set comprises a plurality of sample delay parameters for delaying the takeoff time of a sample flight, and the sample delay parameters at least comprise: a sample weather parameter of a sample scheduled takeoff time of the sample flight, a sample airline regulatory parameter of the sample flight, a sample delay duration of a sample preamble flight of the sample flight, a sample minimum station-crossing duration of the sample flight, a sample mechanical failure parameter of the sample flight, and an actual delay duration of the sample flight;

training the model by using a plurality of sample parameter sets until weights in the model are converged to obtain a reference prediction model;

removing the sample parameter sets which are mismatched between the delay time length predicted by using the sample delay parameters and the reference prediction model and the actual delay time length contained in the sample parameter sets;

and training the model by using the residual sample parameter set until the weights in the model are converged to obtain the target prediction model.

In an alternative implementation, the model includes at least:

the method comprises a Logistic Regression model Logistic Regression, an extreme Random forest Regression model Extra Treesregressor, a Random forest Regression model Random Foreset Regressor, a Boosting Tree model Boosting Tree and a Gradient Boosting Decision Tree model.

In an optional implementation manner, the removing, from the plurality of sample parameter sets, a sample parameter set that does not match between the delay duration predicted by using the sample delay parameters included therein and the reference prediction model and the actual delay duration included therein includes:

for any sample parameter set, predicting delay duration by using sample delay parameters in the sample parameter set;

obtaining a difference value or a ratio value between the predicted delay time length and the actual delay time length in the sample parameter set;

removing the sample parameter set from the plurality of sample parameter sets if the difference or ratio is greater than a preset threshold.

for each sample parameter set, predicting a delay duration using sample delay parameters in the sample parameter set;

determining a positive-too distribution of a plurality of predicted delay time lengths;

removing sample parameter sets corresponding to delay time lengths distributed outside intervals (mu-3 sigma, mu +3 sigma) in the plurality of sample parameter sets;

wherein μ is an expectation among a plurality of delay time periods, and σ is a standard deviation among the plurality of delay time periods.

In a second aspect, an embodiment of the present application illustrates a method for predicting a delay time duration, where the method includes:

receiving an acquisition request of delay time of a target traffic shift;

and acquiring a plurality of types of delay parameters for delaying the time of executing the transportation operation of the target transportation shift from a database according to the acquisition request, wherein the delay parameters at least comprise: a weather parameter at a predetermined starting time of a target traffic shift for performing a traffic operation, a traffic control parameter for the target traffic shift, a delay duration for a preceding traffic shift of the target traffic shift, a minimum transit duration for the target traffic shift, and a mechanical fault parameter for the target traffic shift;

and inputting a plurality of delay parameters of the types into a target prediction model to obtain the delay time of the target traffic shift output by the target prediction model.

In an optional implementation, the method further includes:

and under the condition that the user selects from a plurality of traffic shifts, outputting the delay time length of each traffic shift to the user.

In an optional implementation, the method further includes:

and storing the corresponding relation between the traffic shift identification of the target traffic shift and the delay time of the target traffic shift.

In an optional implementation, the method further includes:

and outputting the delay time of each traffic shift to the staff of the traffic company.

In an optional implementation, the method further includes:

and automatically adjusting the traffic shift scheduling, the traffic worker scheduling and the emergency scheme of the traffic transport company at least according to the delay time of each traffic shift.

In an optional implementation manner, the obtaining a plurality of delay parameters for delaying the target traffic shift includes:

for any one kind of delay parameter, acquiring a time interval of the kind of delay parameter suitable for the target traffic shift;

and obtaining a plurality of delay parameters of the types of the target traffic shift in the time interval.

In an optional implementation, the method further includes:

obtaining a plurality of sample parameter sets, wherein each sample parameter set comprises a plurality of sample delay parameters for delaying the time of executing the transportation operation of the sample transportation shift, and the sample delay parameters at least comprise: the sample weather parameter of the sample traffic shift at the time when the sample traffic shift is scheduled to perform the traffic operation, the sample traffic control parameter of the sample traffic shift, the sample delay time of the sample preamble traffic shift of the sample traffic shift, the sample minimum station crossing time of the sample traffic shift, the sample mechanical fault parameter of the sample traffic shift, and the actual delay time of the sample traffic shift;

In a third aspect, an embodiment of the present application shows an apparatus for predicting a delay time duration, where the apparatus includes:

the first receiving module is used for receiving an acquisition request of the delay duration of the target flight;

a first obtaining module, configured to obtain, from a database according to the obtaining request, multiple types of delay parameters for delaying a departure time of a target flight, where the delay parameters at least include: weather parameters of a scheduled takeoff time of a target flight, aviation control parameters of the target flight, delay time of a preamble flight of the target flight, minimum station-crossing time of the target flight and mechanical fault parameters of the target flight;

and the first input module is used for inputting the delay parameters of the types into a target prediction model to obtain the delay duration of the target flight output by the target prediction model.

In an optional implementation, the apparatus further comprises:

and the first output module is used for outputting the delay time of each flight to the user under the condition that the user selects from a plurality of flights.

In an optional implementation, the apparatus further comprises:

and the first storage module is used for storing the corresponding relation between the flight identifier of the target flight and the delay duration of the target flight.

In an optional implementation, the apparatus further comprises:

and the second output module is used for outputting the delay time of each flight to the staff of the airline company.

In an optional implementation, the apparatus further comprises:

the first adjusting module is used for at least automatically adjusting the flight scheduling, the ground service scheduling and the emergency scheme of the airline company according to the delay time of each flight.

In an optional implementation manner, the first obtaining module includes:

a first obtaining unit, configured to obtain, for any one of the categories of delay parameters, a time interval of the category of delay parameters applicable to the target flight;

a second obtaining unit, configured to obtain delay parameters of the plurality of categories of the target flight located in the time interval.

In an optional implementation manner, the first obtaining module further includes:

and a completion unit, configured to complete the delay parameters of the types located in the time interval when there is a lack of the obtained delay parameters of the types located in the time interval.

In an optional implementation manner, the completion unit includes:

the first determining subunit is used for determining the parameters to be supplemented according to a plurality of delay parameters of the types;

and the combination subunit is used for combining the parameter to be compensated and the plurality of delay parameters of the types into the delay parameters of the types in the time interval.

In an optional implementation manner, the first determining subunit is specifically configured to: determining a degree of fluctuation between the plurality of delay parameters; calculating a first average parameter among a plurality of delay parameters of the type under the condition that the fluctuation degree is smaller than a preset degree; and determining the first average parameter as the parameter to be compensated.

In an optional implementation manner, the first determining subunit is specifically configured to: determining the location of missing delinquent parameters within a plurality of said classes of delinquent parameters; determining a degree of fluctuation between a preset number of delay parameters adjacent to the location among a plurality of the kinds of delay parameters; under the condition that the fluctuation degree is smaller than the preset degree, calculating and determining a parameter to be supplemented according to a plurality of delay parameters of the types; and determining the second average parameter as the parameter to be compensated.

In an optional implementation manner, the first determining subunit is specifically configured to: determining the location of missing delinquent parameters within a plurality of said classes of delinquent parameters; determining a degree of fluctuation between a preset number of delay parameters adjacent to the location among a plurality of the kinds of delay parameters; and under the condition that the fluctuation degree is smaller than the preset degree, determining a delay parameter adjacent to the position as the parameter to be compensated.

In an optional implementation, the apparatus further comprises:

a second obtaining module, configured to obtain multiple sample parameter sets, where each sample parameter set includes multiple sample delay parameters for delaying a departure time of a sample flight, and the sample delay parameters at least include: a sample weather parameter of a sample scheduled takeoff time of the sample flight, a sample airline regulatory parameter of the sample flight, a sample delay duration of a sample preamble flight of the sample flight, a sample minimum station-crossing duration of the sample flight, a sample mechanical failure parameter of the sample flight, and an actual delay duration of the sample flight;

the first training module is used for training the model by using a plurality of sample parameter sets until weights in the model are converged to obtain a reference prediction model;

the first removing module is used for removing sample parameter sets which are mismatched between the delay duration predicted by using the sample delay parameters and the reference prediction model and the actual delay duration included in the sample parameter sets;

and the second training module is used for training the model by using the residual sample parameter set until the weights in the model are converged to obtain the target prediction model.

In an alternative implementation, the model includes at least:

In an optional implementation manner, the first removing module includes:

a first prediction unit, configured to predict, for any one sample parameter set, a delay duration using a sample delay parameter in the sample parameter set;

a third obtaining unit, configured to obtain a difference or a ratio between the predicted delay time and an actual delay time in the sample parameter set;

a first removing unit configured to remove the sample parameter set from the plurality of sample parameter sets if the difference or ratio is greater than a preset threshold.

In an optional implementation manner, the first removing module includes:

a second prediction unit for predicting, for each sample parameter set, a delay duration using sample delay parameters in the sample parameter set;

a determining unit, configured to determine a positive-too distribution of the plurality of predicted delay durations;

a second removing unit configured to remove, from the plurality of sample parameter sets, sample parameter sets corresponding to delay durations distributed outside the interval (μ -3 σ, μ +3 σ);

In a fourth aspect, an embodiment of the present application illustrates an apparatus for predicting a delay time duration, where the apparatus includes:

the second receiving module is used for receiving an acquisition request of the delay time of the target traffic shift;

a third obtaining module, configured to obtain, from the database according to the obtaining request, multiple types of delay parameters for delaying a time of performing a transportation operation of a target transportation shift, where the delay parameters at least include: a weather parameter at a predetermined starting time of a target traffic shift for performing a traffic operation, a traffic control parameter for the target traffic shift, a delay duration for a preceding traffic shift of the target traffic shift, a minimum transit duration for the target traffic shift, and a mechanical fault parameter for the target traffic shift;

and the second input module is used for inputting the delay parameters of the types into a target prediction model to obtain the delay time of the target traffic shift output by the target prediction model.

In an optional implementation, the apparatus further comprises:

and the third output module is used for outputting the delay time length of each traffic shift to the user under the condition that the user selects from a plurality of traffic shifts.

In an optional implementation, the apparatus further comprises:

and the second storage module is used for storing the corresponding relation between the traffic shift identification of the target traffic shift and the delay time of the target traffic shift.

In an optional implementation, the apparatus further comprises:

and the fourth output module is used for outputting the delay time of each traffic shift to the staff of the traffic company.

In an optional implementation, the apparatus further comprises:

and the second adjusting module is used for at least automatically adjusting the traffic shift scheduling, the traffic worker scheduling and the emergency scheme of the traffic transport company according to the delay time of each traffic shift.

In an optional implementation manner, the second obtaining module includes:

a fourth obtaining unit, configured to obtain, for any one of the types of delay parameters, a time interval of the type of delay parameter applicable to the target traffic shift;

a fifth obtaining unit, configured to obtain delay parameters of the multiple categories of the target traffic shift located in the time interval.

In an optional implementation, the apparatus further comprises:

a fourth obtaining module, configured to obtain multiple sample parameter sets, where each sample parameter set includes multiple sample delay parameters used for delaying a time of performing a transportation operation of a sample transportation shift, and the sample delay parameters at least include: the sample weather parameter of the sample traffic shift at the time when the sample traffic shift is scheduled to perform the traffic operation, the sample traffic control parameter of the sample traffic shift, the sample delay time of the sample preamble traffic shift of the sample traffic shift, the sample minimum station crossing time of the sample traffic shift, the sample mechanical fault parameter of the sample traffic shift, and the actual delay time of the sample traffic shift;

the third training module is used for training the model by using a plurality of sample parameter sets until the weights in the model are converged to obtain a reference prediction model;

the second removing module is used for removing sample parameter sets which are mismatched between the delay duration predicted by using the sample delay parameters and the reference prediction model and the actual delay duration included in the sample parameter sets;

and the fourth training module is used for training the model by using the residual sample parameter set until the weights in the model are converged to obtain the target prediction model.

In a fifth aspect, an embodiment of the present application illustrates an electronic device, including:

a processor; and

a memory having executable code stored thereon, which when executed causes the processor to perform the method of predicting a latency period as described in the first aspect.

In a sixth aspect, embodiments of the present application show one or more machine-readable media having stored thereon executable code that, when executed, causes a processor to perform a method of predicting a latency period as described in the first aspect.

In a seventh aspect, an embodiment of the present application shows an electronic device, where the electronic device includes:

a processor; and

a memory having executable code stored thereon, which when executed causes the processor to perform the method of predicting a latency period as described in the second aspect.

In an eighth aspect, embodiments of the present application show one or more machine-readable media having executable code stored thereon, which when executed, causes a processor to perform the method for predicting a delay period according to the second aspect.

Compared with the prior art, the embodiment of the application has the following advantages:

in the application, a request for obtaining the delay duration of a target flight is received; and acquiring a plurality of types of delay parameters for delaying the takeoff time of the target flight from a database according to the acquisition request, wherein the delay parameters at least comprise: weather parameters of a scheduled takeoff time of the target flight, aviation control parameters of the target flight, delay time of a preamble flight of the target flight, minimum station-passing time of the target flight, mechanical fault parameters of the target flight and the like; and inputting the delay parameters of multiple types into the target prediction model to obtain the delay duration of the target flight output by the target prediction model.

The method and the device can predict the delay time of the target flight, wherein the delay time of the target flight is predicted by combining delay parameters of various dimensions of the target flight, so that the accuracy of the predicted delay time is high, and flight scheduling, flight ground-service scheduling and emergency scheme of an airline company are facilitated to be formulated, so that the method and the device have important practical significance for improving the service quality of the airline company and improving the competitiveness of the airline company.

Drawings

FIG. 1 is a schematic diagram of an architecture of the present application, shown in accordance with an exemplary embodiment.

FIG. 2 illustrates a flow diagram of a method for predicting a delay period in accordance with an exemplary embodiment.

FIG. 3 is a flow diagram illustrating a method of completing a delinquent parameter in accordance with an exemplary embodiment.

FIG. 4 is a flow diagram illustrating a method of training a target prediction model in accordance with an exemplary embodiment.

FIG. 5 illustrates a flow chart of a method for predicting a delay period in accordance with an exemplary embodiment.

FIG. 6 is a flow diagram illustrating a method of training a target prediction model in accordance with an exemplary embodiment.

Fig. 7 is a block diagram illustrating an apparatus for predicting a delay period according to an example embodiment.

Fig. 8 is a block diagram illustrating an apparatus for predicting a delay period according to an example embodiment.

FIG. 9 is a block diagram illustrating a prediction of a delay period in accordance with an example embodiment.

Detailed Description

In order to make the aforementioned objects, features and advantages of the present application more comprehensible, the present application is described in further detail with reference to the accompanying drawings and the detailed description.

Referring to fig. 1, the architecture of the present application is illustrated, but not limited to the scope of the present application.

Various delay parameters for a plurality of sample flights may be obtained first.

Sometimes, the obtained delay parameters may be missing due to technical reasons or artificial reasons, and the precision of the prediction model trained by using the missing delay parameters is low, so that the delay duration of the flight predicted by using the prediction model is inaccurate. Therefore, in the case that the obtained delay parameter has a deficiency, the delay parameter can be supplemented, and the accuracy of the delay duration of the target flight predicted by using the supplemented delay parameter is higher than the accuracy of the delay duration of the target flight predicted by using the deficient delay parameter.

And training the model by using various delay parameters of a plurality of sample flights until the weights in the model are converged to obtain a reference prediction model.

And then, various flight delay parameters of the sample flight can be respectively output to the reference prediction model to obtain the predicted delay time of each sample flight output by the reference prediction model.

The actual delay period for each sample flight may then be obtained.

For any sample flight, whether the predicted delay time length is matched with the actual delay time length can be determined, and if not, various delay parameters of the sample flight are removed; the above operation is also performed for none of the other sample flights.

And then training the model by using various delay parameters of the rest sample flights until the weights in the model are converged to obtain a target prediction model.

Then, the target prediction model may be applied, for example, various delay parameters of the target flight are input into the target prediction model, so as to obtain the delay duration of the target flight output by the target prediction model.

Fig. 2 is a flowchart illustrating a method for predicting a delay time period according to an exemplary embodiment, where the method is applied to an electronic device, and an operation management system of an airline company is installed on the electronic device, as shown in fig. 2, and the method includes the following steps.

In step S101, receiving a request for obtaining a delay duration of a target flight;

in one scenario, in the case that the user needs to select among a plurality of flights, sometimes the user needs to refer to at least part of the delay duration of the flight and then select the flight based on the delay duration, so that the user can input an acquisition request of the delay duration of the target flight to the electronic device, the target flight includes at least one flight of the plurality of flights, and the electronic device receives the acquisition request of the delay duration of the target flight and then executes step S102.

In another scenario, when the staff of the airline adjusts the flight scheduling, the ground service scheduling, and the emergency plan of the airline to improve the service quality of the airline and improve the competitiveness of the airline, sometimes the staff of the airline may need to refer to the delay duration of some flights and then adjust the flight scheduling, the ground service scheduling, and the emergency plan of the airline according to the delay duration of each flight, so that the staff of the airline may input an acquisition request of the delay duration of a target flight to the electronic device, where the target flight includes at least one flight of the flights, and the electronic device receives the acquisition request of the delay duration of the target flight and then executes step S102.

In another scenario, the other system needs to use the delay duration of some flights to make statistics of some big data, and so on, and thus the other system may send an acquisition request of the delay duration of the target flight to the electronic device, where the target flight includes at least one flight of the plurality of flights, and the electronic device receives the acquisition request of the delay duration of the target flight sent by the other system, and then performs step S102.

In step S102, a plurality of types of delay parameters for delaying the departure time of the target flight are acquired from the database according to the acquisition request, and the delay parameters at least include: weather parameters of a scheduled takeoff time of the target flight, aviation control parameters of the target flight, delay time of a preamble flight of the target flight, minimum station-passing time of the target flight, mechanical fault parameters of the target flight and the like;

in the present application, the weather parameter of the scheduled takeoff time of the target flight may include a weather condition of a time interval in which the scheduled takeoff time of the target flight is located, for example, a weather condition of 7 days before and after the scheduled takeoff time of the target flight for 3 days, and the weather condition includes a weather condition of a takeoff place of the flight, a weather condition of a landing place, and a weather condition of each place of the airline located at the takeoff place and the landing place. If the weather condition is normal and the takeoff requirement is met, the target flight can take off normally, if the weather condition is severe and the takeoff requirement is not met, the target flight cannot take off on time, and the takeoff time of the target flight needs to be delayed.

The air control parameter of the target flight includes an air control condition set by the air control bureau for a time interval in which the scheduled takeoff time of the target flight is located, for example, the air control parameter of two to three hours before and after the scheduled takeoff time of the target flight.

The aviation control conditions comprise the aviation control conditions of a takeoff place and a landing place of a flight, and the aviation control conditions of various places on an air route of the takeoff place and the landing place.

If the target flight is not controlled by the air, the target flight can take off normally, and if the target flight is controlled by the air, the target flight cannot take off normally, and the taking off time of the target flight needs to be delayed.

The minimum station-crossing time of the target flight includes at least a time period during which an aircraft performing the target flight needs to stay at the takeoff location, and the like. The longer the minimum station-crossing time of the target flight is, the longer the time that the departure time of the target flight is delayed is possibly caused, and the shorter the minimum station-crossing time of the target flight is, the shorter the time that the departure time of the target flight is delayed is possibly caused.

The target flight and a flight before the target flight may share one aircraft, the flight before the target flight is a preorder flight of the target flight, and the target flight can start to execute the flight task after the modesty flight completes the flight task, so that whether the preorder flight of the target flight delays or not directly affects the delay time of the target flight.

The longer the delay period of the preceding flight, the longer the time that may result in the departure time of the target flight being delayed. The shorter the delay period of the preceding flight, the shorter the time that may result in the departure time of the target flight being delayed.

If the target flight has the mechanical fault, the target flight cannot take off normally, the take-off cannot be carried out until the mechanical fault is removed after the mechanical fault is delayed, and more time is needed to remove the mechanical fault when the mechanical fault is more serious, so the time for delaying the take-off time of the target flight is longer.

When the weather parameter of the scheduled takeoff time of the target flight is obtained, the electronic equipment can establish communication connection with a database of the weather station, and then the weather parameter of the scheduled takeoff time stored in the database of the weather station is called based on the communication connection.

When acquiring the airline control parameter of the target flight, the electronic device may establish a communication connection with a database of the airline control department, and then call the airline control parameter of the target flight stored in the database of the airline control department based on the communication connection.

When the delay time of the preamble flight of the target flight is obtained, the electronic device may establish a communication connection with a database of the airline regulatory department, and then call the delay time of the preamble flight of the target flight stored in the database of the airline regulatory department based on the communication connection.

When the minimum station-crossing time of the target flight and the mechanical fault parameter of the target flight are obtained, the electronic device may establish a communication connection with a database of the airline company, and then call the minimum station-crossing time of the target flight and the mechanical fault parameter of the target flight stored in the database of the airline company based on the communication connection.

In step S103, the delay parameters of a plurality of types are input into the target prediction model, and the delay time of the target flight output by the target prediction model is obtained.

In the present application, the delay duration of the target flight may be predicted according to multiple kinds of delay parameters based on the neural network model, for example, the multiple kinds of delay parameters are input into the target prediction model to obtain the delay duration of the target flight output by the target prediction model, and a specific training method of the target prediction model may be referred to in the following embodiments and is not described in detail herein.

Further, after the delay time of each flight is determined, under the condition that the user selects from a plurality of flights, the delay time of each flight is output to the user, so that the user can select the flight according to the delay time of each flight.

Furthermore, after the delay time of each flight is determined, the delay time of each flight can be output to the staff of the airline company, so that the staff of the airline company can adjust the flight scheduling, the ground service scheduling and the emergency scheme of the airline company according to the delay time of each flight, and therefore the service quality of the airline company can be improved, and the competitiveness of the airline company can be improved.

Further, after the delay duration of the target flight is determined, the corresponding relationship between the flight identifier of the target flight and the delay duration of the target flight may also be stored, so that the delay duration of the target flight may be looked up in the corresponding relationship between the flight identifier of the target flight and the delay duration of the target flight based on the flight identifier of the target flight when the user or the staff of the airline needs to check the delay duration of the target flight, and the user or the staff of the airline may further refer to the delay duration of the target flight, for example, to help the user to select a flight according to the delay duration of each flight, or to help the staff of the airline to adjust the flight scheduling, the flight ground scheduling and the emergency plan of the airline according to the delay duration of each flight, thereby improving the service quality of the airline, and to improve the competitiveness of airlines.

However, the staff of the airline company adjusts the flight scheduling, the flight ground service scheduling, and the emergency plan of the airline company according to the delay time of each flight, which consumes more human resources, resulting in higher labor cost.

Therefore, in order to save human resources and reduce labor cost, in another embodiment of the application, after the delay duration of each flight is determined, the electronic device may automatically adjust at least the flight scheduling, the flight-to-ground-service scheduling and the emergency plan of the airline according to the delay duration of each flight, without the participation of the staff of the airline, so that human resources can be saved, and labor cost is reduced.

In step S101, for any one of the plurality of types of delay parameters, a time interval of the delay parameter of the type suitable for the target flight is acquired, and then a plurality of delay parameters of the type of the target flight located in the time interval are acquired. The above-described operation is also performed for each of the other ones of the plurality of kinds of delay parameters.

For example, when the weather parameter of the scheduled takeoff time of the target flight is acquired, the weather data of 3 days before and after the scheduled takeoff time of the target flight, the weather data of 7 days in total, and the like may be acquired. And when acquiring the aviation control parameters of the target flight, acquiring the aviation control parameters of two hours and three hours before and after the scheduled takeoff time of the target flight, and when acquiring the mechanical fault parameters of the target flight, acquiring the mechanical fault parameters of 1 day before and after the scheduled takeoff time of the target flight, the mechanical fault parameters of 3 days in total, and the like.

In the present application, the length of the time interval corresponding to each delay parameter may be obtained based on historical experience statistics, for example, the accuracy of predicting the delay duration of a flight by using delay parameters corresponding to different time intervals may be determined in advance, and the time interval corresponding to the delay duration with the highest accuracy may be screened.

However, sometimes, it may be a technical reason or a human reason, there may be a missing delay parameter of the kind obtained, for example, when obtaining the weather parameter of the scheduled takeoff time of the target flight, it is necessary to obtain the weather data of 3 days before and after the scheduled takeoff time of the target flight, and the weather data of 7 days in total, but there may be a missing weather data of some days, and the weather data of the day cannot be obtained.

The use of missing delay parameters may result in inaccurate predicted delay durations when predicting the delay duration of a target flight.

Therefore, in order to improve the accuracy of the predicted delay duration of the target flight in the time interval when the obtained plurality of delay parameters of the category located in the time interval are missing, the delay parameters of the category located in the time interval can be supplemented, and the accuracy of the delay duration of the target flight predicted by using the supplemented delay parameters is higher than the accuracy of the delay duration of the target flight predicted by using the missing delay parameters.

In one embodiment of the present application, referring to fig. 3, the delay parameter of the kind located in the time interval may be complemented by:

in step S201, determining a parameter to be supplemented according to a plurality of delay parameters of the category;

in one embodiment of the present application, a degree of fluctuation between a plurality of delay parameters may be determined; wherein the variance or standard deviation between the plurality of delay parameters may be calculated as the degree of fluctuation between the plurality of delay parameters. Under the condition that the fluctuation degree is smaller than the preset degree, calculating a first average parameter among a plurality of delay parameters; the preset degree may be a numerical value set empirically in advance, and the specific size of the data may be set according to actual conditions, which is not limited in this application. The first average may then be determined as the parameter to be complemented.

In another embodiment of the present application, the location of a missing delinquent parameter in a plurality of delinquent parameters of that category is determined; in the application, a plurality of delay data corresponding to the delay parameter in the time interval are acquired, for example, when the weather parameter of the scheduled takeoff time of the target flight is acquired, weather data of three days before and after the scheduled takeoff time of the target flight is acquired, weather data of 7 days in total, for example, weather data of 11 month and 1 day, weather data of 11 month and 2 days, weather data of 11 month and 3 days, weather data of 11 month and 4 days, weather data of 11 month and 5 days, weather data of 11 month and 6 days, and weather data of 11 month and 7 days are acquired, and if the weather data of 11 month and 4 days is not acquired, the position of the missing weather data of 11 month and 4 days in the weather data of 7 days is the fourth position.

Then determining the fluctuation degree between a preset number of delay parameters adjacent to the position in the delay parameters of multiple types; the preset number includes 1, 2, or 3, for example, in combination with the foregoing example, the fluctuation degree between the weather data of day 11, month 3 and day 11, month 5, or the fluctuation degree between the weather data of day 11, month 2, month 3, month 5, and month 6 may be determined.

Under the condition that the fluctuation degree is smaller than the preset degree, calculating and determining a parameter to be supplemented according to a plurality of delay parameters of the type; and determining the second average parameter as the parameter to be complemented.

In another embodiment of the present application, the location of a missing delinquent parameter in a plurality of delinquent parameters of that category may be determined; determining the fluctuation degree between a preset number of delay parameters adjacent to the position in a plurality of delay parameters of the type; and under the condition that the fluctuation degree is less than the preset degree, determining a delay parameter adjacent to the position as a parameter to be supplemented.

In step S202, the parameter to be compensated and a plurality of delay parameters of the category are combined into a delay parameter of the category located in the time interval.

The data to be complemented and a plurality of delay parameters of the category may be combined into the delay parameters of the category located in the time interval according to the order of their respective corresponding times.

In an embodiment of the present application, the target prediction model may be trained in advance, and referring to fig. 4, a specific training process includes:

in step S301, a plurality of sample data sets are obtained, where each sample data set includes a plurality of sample delay parameters for delaying the takeoff time of a sample flight, and the sample delay parameters at least include: the method comprises the steps of obtaining a sample weather parameter of a sample scheduled takeoff time of a sample flight, a sample aviation control parameter of the sample flight, a sample delay time of a sample preamble flight of the sample flight, a sample minimum station-passing time of the sample flight, a sample mechanical fault parameter of the sample flight and an actual delay time of the sample flight;

in step S302, training the model using a plurality of sample data sets until the weights in the model all converge to obtain a reference prediction model;

in the present application, the model comprises at least: a Logistic Regression model, an extreme Random forest Regression model, a Boosting Tree model, and a Gradient Boosting Decision Tree model.

In step S303, sample data sets that do not match between the delay duration predicted by using the sample delay parameters and the reference prediction model included in the sample data sets and the actual delay duration included in the sample data sets are removed;

in one embodiment of the application, for any sample data set, sample delay parameters in the sample data set are used for predicting delay duration; then obtaining the difference or ratio between the predicted delay time and the actual delay time in the sample data set; and removing the sample data set from the plurality of sample data sets under the condition that the difference value or the ratio value is larger than a preset threshold value. In case the difference or ratio is smaller than a preset threshold, the sample data set may be retained. The above operation is also performed for each of the other sample data sets.

In another embodiment of the present application, for each sample data set, sample delay parameters in the sample data set are used to predict delay durations, so as to obtain a plurality of delay durations, and then it is possible to determine a positive-too distribution of the predicted plurality of delay durations; removing sample data sets corresponding to delay time lengths distributed outside intervals (mu-3 sigma, mu +3 sigma) in a plurality of sample data sets; where μ is the expectation between the plurality of delay periods and σ is the standard deviation between the plurality of delay periods.

Of course, the sample data set that is not matched between the delay duration predicted by using the sample delay parameters and the reference prediction model and the actual delay duration included therein may also be removed by other manners, and the specific removal method is not limited in the present application.

In step S304, the model is trained using the remaining sample data sets until the weights in the model all converge, so as to obtain a target prediction model.

In the application, if the delay duration predicted by the sample delay parameters and the reference prediction model included in some sample data sets is not matched with the actual delay duration included in the sample data sets, in order to improve the prediction accuracy of the trained model, the sample data sets which are not matched between the delay duration predicted by the sample delay parameters and the reference prediction model included in the sample data sets and the actual delay duration included in the sample data sets can be removed; and then training the model by using the residual sample data set until the weights in the model are all converged to obtain a target prediction model, and improving the prediction accuracy of the trained target prediction model by the training mode.

After the target prediction model is obtained through training, the delay parameters of multiple types can be input into the target prediction model, and the delay duration of the target flight output by the target prediction model is obtained.

Fig. 5 is a flowchart illustrating a method for predicting a delay time period according to an exemplary embodiment, where the method is applied to an electronic device, and an operation management system of a transportation company is installed on the electronic device, as shown in fig. 5, and the method includes the following steps.

In step S401, an acquisition request of a delay duration of a target traffic shift is received;

the target traffic shift includes a civil aviation shift, a train shift, an automobile shift, a ferry shift, a logistics shift, an unmanned plane shift, etc. of the airline.

The step may specifically refer to the related description of step S101, and is not described in detail here.

In step S402, a plurality of types of delay parameters for delaying the time of execution of the transportation task of the target transportation shift are acquired from the database in accordance with the acquisition request, and the delay parameters include at least: weather parameters of a preset starting moment of executing the traffic transportation operation of the target traffic shift, traffic control parameters of the target traffic shift, delay time of a preamble traffic shift of the target traffic shift, minimum station crossing time of the target traffic shift and mechanical fault parameters of the target traffic shift;

the step may specifically refer to the related description of step S102, and is not described in detail here.

In step S403, the delay parameters of a plurality of types are input into the target prediction model, and the delay time of the target traffic shift output by the target prediction model is obtained.

The step can be specifically referred to the related description of step S103, and is not described in detail here.

In the application, an acquisition request of a delay time length of a target traffic shift is received; and obtaining a plurality of types of delay parameters for delaying the time of executing the transportation operation of the target transportation shift from the database according to the obtaining request, wherein the delay parameters at least comprise: weather parameters of a preset starting moment of executing the traffic transportation operation of the target traffic shift, traffic control parameters of the target traffic shift, delay time of a preamble traffic shift of the target traffic shift, minimum station crossing time of the target traffic shift and mechanical fault parameters of the target traffic shift; and inputting the delay parameters of multiple types into the target prediction model to obtain the delay time of the target traffic shift output by the target prediction model.

The delay time of the target traffic shift can be predicted through the method and the device, and the delay time of the target traffic shift is predicted by combining delay parameters of multiple dimensions of the target traffic shift, so that the accuracy of the predicted delay time is high, and the method and the device are beneficial to the formulation of traffic shift scheduling, traffic worker scheduling and emergency schemes of a traffic transport company, and have important practical significance for improving the service quality of the traffic transport company and the competitiveness of the traffic transport company.

Further, after the delay time of each traffic shift is determined, the delay time of each traffic shift is output to the user under the condition that the user selects from a plurality of traffic shifts, so that the user can select the traffic shift according to the delay time of each traffic shift.

Furthermore, after the delay time of each traffic shift is determined, the delay time of each traffic shift can be output to the staff of the traffic company, so that the staff of the traffic company can adjust the traffic shift scheduling, the traffic staff scheduling and the emergency scheme of the traffic company according to the delay time of each traffic shift, and therefore the service quality of the traffic company can be improved, and the competitiveness of the traffic company can be improved.

Further, after the delay duration of the target traffic shift is determined, the corresponding relationship between the traffic shift identifier of the target traffic shift and the delay duration of the target traffic shift may also be stored, so that the delay duration of the target traffic shift may be looked up in the corresponding relationship between the traffic shift identifier of the target traffic shift and the delay duration of the target traffic shift based on the traffic shift identifier of the target traffic shift, and the delay duration of the target traffic shift may be referred to by the user or the staff of the traffic transport company, for example, to help the user to select a flight according to the delay duration of each traffic shift, or to help the staff of the airline company to adjust the delay duration of the traffic shift of the traffic transport company according to the delay duration of each traffic shift, The scheduling and emergency scheme of the traffic workers can improve the service quality of the traffic company and improve the competitiveness of the traffic company.

However, the staff of the transportation company adjusts the flight scheduling, the transportation staff and the emergency plan of the transportation company according to the delay time of each transportation shift, which consumes more human resources, resulting in higher labor cost.

Therefore, in order to save human resources and reduce labor cost, in another embodiment of the application, after the delay duration of each transportation shift is determined, the electronic device can automatically adjust the transportation shift scheduling, the traffic worker scheduling and the emergency scheme of the transportation company at least according to the delay duration of each transportation shift, without participation of the workers of the transportation company, so that human resources can be saved, and labor cost is reduced.

In step S101, for any one of the delay parameters of the plurality of types, a time interval of the delay parameter of the type suitable for the target traffic shift may be acquired, and then the delay parameters of the plurality of types of the target traffic shift located in the time interval may be acquired. The above-described operation is also performed for each of the other ones of the plurality of kinds of delay parameters.

For example, in acquiring the weather parameter of the scheduled start execution time of the execution of the transportation job for the target transportation shift, the weather data of 3 days before and after the scheduled start execution time of the execution of the transportation job for the target transportation shift, the weather data of 7 days in total, and the like may be acquired. And when acquiring the traffic control parameters of the target traffic shift, acquiring the air control parameters two or three hours before and after the scheduled initial execution time of the target traffic shift for executing the transportation operation, and when acquiring the mechanical fault parameters of the target traffic shift, acquiring the mechanical fault parameters of the target traffic shift 1 day before and after the scheduled initial execution time of the target traffic shift for executing the transportation operation, the mechanical fault parameters of 3 days in total, and the like.

In an embodiment of the present application, the target prediction model may be trained in advance, and referring to fig. 6, a specific training process includes:

in step S501, a plurality of sample parameter sets are obtained, each sample parameter set including a plurality of sample delay parameters for delaying the time of executing the transportation job of the sample transportation shift, and the sample delay parameters at least include: the method comprises the following steps that a sample weather parameter of a sample traffic shift at the moment when a traffic operation is scheduled to be executed by a sample of the sample traffic shift, a sample traffic control parameter of the sample traffic shift, a sample delay time of a sample preamble traffic shift of the sample traffic shift, a sample minimum station-crossing time of the sample traffic shift, a sample mechanical fault parameter of the sample traffic shift and an actual delay time of the sample traffic shift;

the step may specifically refer to the related description of step S301, and is not described in detail here.

In step S502, training the model using a plurality of sample parameter sets until the weights in the model all converge to obtain a reference prediction model;

the step may specifically refer to the related description of step S302, and is not described in detail here.

In step S503, in the plurality of sample parameter sets, removing the sample parameter set that does not match between the delay duration predicted by using the sample delay parameters included therein and the reference prediction model and the actual delay duration included therein;

the step may specifically refer to the related description of step S303, and is not described in detail here.

In step S504, the model is trained using the remaining sample parameter sets until the weights in the model all converge, so as to obtain a target prediction model.

The step may specifically refer to the related description of step S304, and is not described in detail here.

Fig. 7 is a block diagram illustrating an apparatus for predicting a delay time period according to an exemplary embodiment, as shown in fig. 7, the apparatus including:

the first receiving module 11 is configured to receive an acquisition request of a delay duration of a target flight;

a first obtaining module 12, configured to obtain, according to the obtaining request, multiple types of delay parameters for delaying the departure time of the target flight from a database, where the delay parameters at least include: weather parameters of a scheduled takeoff time of a target flight, aviation control parameters of the target flight, delay time of a preamble flight of the target flight, minimum station-crossing time of the target flight and mechanical fault parameters of the target flight;

the first input module 13 is configured to input a plurality of delay parameters of the types into a target prediction model, so as to obtain a delay duration of the target flight output by the target prediction model.

In an optional implementation, the apparatus further comprises:

In an optional implementation manner, the first obtaining module includes:

In an optional implementation manner, the completion unit includes:

In an optional implementation, the apparatus further comprises:

In an alternative implementation, the model includes at least:

In an optional implementation manner, the first removing module includes:

Fig. 8 is a block diagram illustrating an apparatus for predicting a delay time period according to an exemplary embodiment, as shown in fig. 8, the apparatus including:

the second receiving module 21 is configured to receive an acquisition request of a delay duration of a target traffic shift;

a third obtaining module 22, configured to obtain, from the database according to the obtaining request, multiple types of delay parameters for delaying the time of performing the transportation operation of the target transportation shift, where the delay parameters at least include: a weather parameter at a predetermined starting time of a target traffic shift for performing a traffic operation, a traffic control parameter for the target traffic shift, a delay duration for a preceding traffic shift of the target traffic shift, a minimum transit duration for the target traffic shift, and a mechanical fault parameter for the target traffic shift;

and the second input module 23 is configured to input the delay parameters of the multiple categories into a target prediction model, so as to obtain the delay duration of the target traffic shift output by the target prediction model.

In an optional implementation, the apparatus further comprises:

In an optional implementation manner, the second obtaining module includes:

In an optional implementation, the apparatus further comprises:

In the application, an acquisition request of a delay time length of a target traffic shift is received; and obtaining a plurality of types of delay parameters for delaying the time of executing the transportation operation of the target transportation shift from the database according to the obtaining request, wherein the delay parameters at least comprise: the weather parameter of the preset starting time of the execution of the transportation operation of the target transportation shift, the traffic control parameter of the target transportation shift, the delay time of the preorder transportation shift of the target transportation shift, the minimum station-crossing time of the target transportation shift and the mechanical fault parameter of the target transportation shift; and inputting the delay parameters of multiple types into the target prediction model to obtain the delay time of the target traffic shift output by the target prediction model.

The present application further provides a non-transitory, readable storage medium, where one or more modules (programs) are stored, and when the one or more modules are applied to a device, the device may execute instructions (instructions) of method steps in this application.

Embodiments of the present application provide one or more machine-readable media having instructions stored thereon, which when executed by one or more processors, cause an electronic device to perform a method of predicting a latency period as described in one or more of the above embodiments. In the embodiment of the application, the electronic device comprises a server, a gateway, a sub-device and the like, wherein the sub-device is a device such as an internet of things device.

Embodiments of the present disclosure may be implemented as an apparatus, which may include electronic devices such as servers (clusters), terminal devices such as IoT devices, and the like, using any suitable hardware, firmware, software, or any combination thereof, for a desired configuration.

Fig. 9 schematically illustrates an example apparatus 1300 that can be used to implement various embodiments described herein.

For one embodiment, fig. 9 illustrates an example apparatus 1300 having one or more processors 1302, a control module (chipset) 1304 coupled to at least one of the processor(s) 1302, memory 1306 coupled to the control module 1304, non-volatile memory (NVM)/storage 1308 coupled to the control module 1304, one or more input/output devices 1310 coupled to the control module 1304, and a network interface 1312 coupled to the control module 1306.

Processor 1302 may include one or more single-core or multi-core processors, and processor 1302 may include any combination of general-purpose or special-purpose processors (e.g., graphics processors, application processors, baseband processors, etc.). In some embodiments, the apparatus 1300 can be a server device such as a gateway or a controller as described in the embodiments of the present application.

In some embodiments, apparatus 1300 may include one or more computer-readable media (e.g., memory 1306 or NVM/storage 1308) having instructions 1314 and one or more processors 1302, which in combination with the one or more computer-readable media, are configured to execute instructions 1314 to implement modules to perform actions described in this disclosure.

For one embodiment, control module 1304 may include any suitable interface controllers to provide any suitable interface to at least one of the processor(s) 1302 and/or any suitable device or component in communication with control module 1304.

The control module 1304 may include a memory controller module to provide an interface to the memory 1306. The memory controller module may be a hardware module, a software module, and/or a firmware module.

Memory 1306 may be used, for example, to load and store data and/or instructions 1314 for device 1300. For one embodiment, memory 1306 may comprise any suitable volatile memory, such as suitable DRAM. In some embodiments, the memory 1306 may include a double data rate event class four synchronous dynamic random access memory (DDR4 SDRAM).

For one embodiment, control module 1304 may include one or more input/output controllers to provide an interface to NVM/storage 1308 and input/output device(s) 1310.

For example, NVM/storage 1308 may be used to store data and/or instructions 1314. NVM/storage 1308 may include any suitable non-volatile memory (e.g., flash memory) and/or may include any suitable non-volatile storage device(s) (e.g., one or more Hard Disk Drives (HDDs), one or more Compact Disc (CD) drives, and/or one or more Digital Versatile Disc (DVD) drives).

NVM/storage 1308 may include storage resources that are physically part of the device on which apparatus 1300 is installed, or it may be accessible by the device and need not be part of the device. For example, NVM/storage 1308 may be accessible over a network via input/output device(s) 1310.

Input/output device(s) 1310 may provide an interface for apparatus 1300 to communicate with any other suitable device, input/output device(s) 1310 may include communication components, audio components, sensor components, and so forth. The network interface 1312 may provide an interface for the device 1300 to communicate over one or more networks, and the device 1300 may wirelessly communicate with one or more components of a wireless network according to any of one or more wireless network standards and/or protocols, such as access to a communication standard-based wireless network, e.g., WiFi, 2G, 3G, 4G, 5G, etc., or a combination thereof.

For one embodiment, at least one of the processor(s) 1302 may be packaged together with logic for one or more controllers (e.g., memory controller modules) of the control module 1304. For one embodiment, at least one of the processor(s) 1302 may be packaged together with logic for one or more controllers of the control module 1304 to form a System In Package (SiP). For one embodiment, at least one of the processor(s) 1302 may be integrated on the same die with logic for one or more controller(s) of the control module 1304. For one embodiment, at least one of the processor(s) 1302 may be integrated on the same die with logic of one or more controllers of the control module 1304 to form a system on chip (SoC).

In various embodiments, apparatus 1300 may be, but is not limited to being: a server, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet, a netbook, etc.), among other terminal devices. In various embodiments, apparatus 1300 may have more or fewer components and/or different architectures. For example, in some embodiments, device 1300 includes one or more cameras, a keyboard, a Liquid Crystal Display (LCD) screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, an Application Specific Integrated Circuit (ASIC), and speakers.

An embodiment of the present application provides an electronic device, including: one or more processors; and one or more machine readable media having instructions stored thereon, which when executed by the one or more processors, cause the processors to perform a method of estimating a delay period for a flight as described in one or more of the embodiments of the present application.

For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.

The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.

Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present application have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the true scope of the embodiments of the application.

Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.

The method and the device for predicting the delay time provided by the application are introduced in detail, a specific example is applied in the text to explain the principle and the implementation mode of the application, and the description of the embodiment is only used for helping to understand the method and the core idea of the application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. A method for predicting a delay time, the method comprising:

receiving an acquisition request of the delay time of a target flight;

2. The method of claim 1, further comprising:

3. The method of claim 1, further comprising:

4. The method of claim 1, further comprising:

the delay time of each flight is output to the airline's staff.

5. The method of claim 1, further comprising:

6. The method of claim 1, wherein obtaining a plurality of deferral parameters for deferring a target flight comprises:

7. The method of claim 6, further comprising:

8. The method of claim 7, wherein completing the class of delinquent parameters within the time interval comprises:

9. The method of claim 8, wherein determining a parameter to be complemented from the plurality of delay parameters comprises:

determining a degree of fluctuation between the plurality of delay parameters;

and determining the first average parameter as the parameter to be compensated.

10. The method of claim 8, wherein determining a parameter to be complemented from the plurality of delay parameters comprises:

11. The method of claim 8, wherein determining a parameter to be complemented from the plurality of delay parameters comprises:

12. The method of claim 1, further comprising:

13. The method according to claim 12, characterized in that the model comprises at least:

14. The method according to claim 12, wherein said removing, from said plurality of sample parameter sets, the sample parameter set that does not match between the delay duration predicted using the sample delay parameter included therein and the reference prediction model and the actual delay duration included therein comprises:

15. The method according to claim 12, wherein said removing, from said plurality of sample parameter sets, the sample parameter set that does not match between the delay duration predicted using the sample delay parameter included therein and the reference prediction model and the actual delay duration included therein comprises:

16. A method for predicting a delay time, the method comprising:

receiving an acquisition request of delay time of a target traffic shift;

17. The method of claim 16, further comprising:

18. The method of claim 16, further comprising:

19. The method of claim 16, further comprising:

20. The method of claim 16, further comprising:

21. The method of claim 16, wherein obtaining a plurality of delay parameters for delaying a target traffic shift comprises:

22. The method of claim 16, further comprising:

23. An apparatus for predicting a delay time period, the apparatus comprising:

24. The apparatus of claim 23, further comprising:

25. The apparatus of claim 23, further comprising:

26. The apparatus of claim 23, further comprising:

27. The apparatus of claim 23, further comprising:

28. The apparatus of claim 23, wherein the first obtaining module comprises:

29. The apparatus of claim 28, wherein the first obtaining module further comprises:

30. The apparatus of claim 29, wherein the completion unit comprises:

31. The apparatus according to claim 30, wherein the first determining subunit is specifically configured to: determining a degree of fluctuation between the plurality of delay parameters; calculating a first average parameter among a plurality of delay parameters of the type under the condition that the fluctuation degree is smaller than a preset degree; and determining the first average parameter as the parameter to be compensated.

32. The apparatus according to claim 30, wherein the first determining subunit is specifically configured to: determining the location of missing delinquent parameters within a plurality of said classes of delinquent parameters; determining a degree of fluctuation between a preset number of delay parameters adjacent to the location among a plurality of the kinds of delay parameters; under the condition that the fluctuation degree is smaller than the preset degree, calculating and determining a parameter to be supplemented according to a plurality of delay parameters of the types; and determining the second average parameter as the parameter to be compensated.

33. The apparatus according to claim 30, wherein the first determining subunit is specifically configured to: determining the location of missing delinquent parameters within a plurality of said classes of delinquent parameters; determining a degree of fluctuation between a preset number of delay parameters adjacent to the location among a plurality of the kinds of delay parameters; and under the condition that the fluctuation degree is smaller than the preset degree, determining a delay parameter adjacent to the position as the parameter to be compensated.

34. The apparatus of claim 23, further comprising:

35. The apparatus of claim 34, wherein the model comprises at least:

36. The apparatus of claim 34, wherein the first removal module comprises:

37. The apparatus of claim 34, wherein the first removal module comprises:

38. An apparatus for predicting a delay time period, the apparatus comprising:

39. The apparatus of claim 38, further comprising:

40. The apparatus of claim 38, further comprising:

41. The apparatus of claim 38, further comprising:

42. The apparatus of claim 38, further comprising:

43. The apparatus of claim 38, wherein the second obtaining module comprises:

44. The apparatus of claim 38, further comprising:

45. An electronic device, characterized in that the electronic device comprises:

a processor; and

a memory having executable code stored thereon, which when executed causes the processor to perform a method of predicting a latency period as claimed in any one of claims 1 to 15.

46. One or more machine-readable media having stored thereon executable code that, when executed, causes a processor to perform a method of predicting a latency period as recited in any one of claims 1-15.

47. An electronic device, characterized in that the electronic device comprises:

a processor; and

a memory having executable code stored thereon, which when executed causes the processor to perform a method of predicting a latency period as claimed in any one of claims 16 to 22.

48. One or more machine-readable media having stored thereon executable code that, when executed, causes a processor to perform a method of predicting a latency period as recited in any one of claims 16-22.