CN112329993A - Method and system for predicting number of passengers on flight and electronic equipment - Google Patents
Method and system for predicting number of passengers on flight and electronic equipment Download PDFInfo
- Publication number
- CN112329993A CN112329993A CN202011141816.8A CN202011141816A CN112329993A CN 112329993 A CN112329993 A CN 112329993A CN 202011141816 A CN202011141816 A CN 202011141816A CN 112329993 A CN112329993 A CN 112329993A
- Authority
- CN
- China
- Prior art keywords
- flight
- predicted value
- passengers
- day
- minimum
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000010006 flight Effects 0.000 claims abstract description 49
- 238000012937 correction Methods 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 239000013589 supplement Substances 0.000 claims 1
- 238000011161 development Methods 0.000 abstract description 9
- 238000009472 formulation Methods 0.000 abstract description 8
- 239000000203 mixture Substances 0.000 abstract description 8
- 230000009286 beneficial effect Effects 0.000 description 9
- 238000005311 autocorrelation function Methods 0.000 description 4
- 238000013178 mathematical model Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000000295 complement effect Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000005314 correlation function Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
- G06F18/295—Markov models or related models, e.g. semi-Markov models; Markov random fields; Networks embedding Markov models
-
- G06Q50/40—
Abstract
The invention relates to a method, a system and electronic equipment for predicting the number of passengers on flights, which obtains the final predicted value of the number of passengers on each flight on the same airline in the M +1 th day according to the maximum predicted value and the minimum predicted value of the number of passengers on a single flight in the M +1 th day and the weight predicted value corresponding to each flight in the M +1 th day, by taking into account all flights of the same airline as a whole, that is, associating all airlines on the same airline, the variance in the number of passengers predicted by the historical number of passengers for a single flight is reduced, so that the final predicted value of the number of passengers per flight of the same route on day M +1 is closer to the actual number of passengers per flight on day M +1, namely, the prediction accuracy of the number of passengers on the flight is improved so as to provide experimental support for the formulation of the development policy of the airline company.
Description
Technical Field
The invention relates to the technical field of aviation information, in particular to a method and a system for predicting the number of flight passengers and electronic equipment.
Background
According to the data of international air telecommunications company (SITA), the number of passengers traveling by airplane is expected to be doubled in the next 20 years, so that for the airline companies, the change rule of the number of passengers on flights is mastered, and the empirical support can be provided for the development policy of the airline companies.
At present, an airline company usually predicts the number of passengers in the next operation of any flight by establishing a mathematical model according to the number of passengers in the past 1 year, 2 years and the like of the flight, but because the number of passengers of each flight on a corresponding flight is not considered, the predicted number of passengers often has large deviation, and thus, the airline company cannot provide experimental support for developing policies.
Disclosure of Invention
The invention provides a method, a system and electronic equipment for predicting the number of passengers on a flight, aiming at solving the technical problem of how to improve the accuracy of predicting the number of passengers on the flight and solving the problem that the number of passengers on each flight on a corresponding flight is not considered in the prior art. And the technical problem of large deviation of the predicted number of passengers on the flights is caused.
The technical scheme of the method for predicting the number of passengers on the flight is as follows:
s1, respectively predicting a maximum predicted value and a minimum predicted value of the number of passengers of a single flight in the M +1 th day according to the maximum number and the minimum number of passengers in the number of passengers of a plurality of flights aiming at the same airline in each day in continuous M days, and predicting a weight predicted value corresponding to each flight in the M +1 th day according to the number of passengers of each flight in each day in continuous M days, wherein M is a positive integer;
s2, obtaining a final predicted value of the passenger number of each flight in the M +1 th day according to the maximum predicted value and the minimum predicted value of the passenger number of the single flight in the M +1 th day and the weight predicted value corresponding to each flight in the M +1 th day.
The method for predicting the number of passengers on the flight has the following beneficial effects:
firstly, respectively predicting the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the (M + 1) th day, then predicting the weight predicted value corresponding to each flight in the (M + 1) th day, finally obtaining the final predicted value of the number of passengers of each flight of the same airline in the (M + 1) th day according to the maximum predicted value and the minimum predicted value of the number of passengers of the single flight in the (M + 1) th day and the weight predicted value corresponding to each flight in the (M + 1) th day, and reducing the deviation of the number of passengers predicted by the historical number of passengers of the single flight by integrally considering all flights of the same airline, namely, associating all airlines on the same airline, so that the final predicted value of the number of passengers of each flight of the same airline in the (M + 1) th day is closer to the real number of passengers of each flight in the (M + 1) th day, namely, the prediction accuracy of the number of passengers of the flights, so as to provide evidence support for the formulation of the development policy of the airline company.
On the basis of the scheme, the method for predicting the number of the passengers on the flight can be further improved as follows.
Further, the S2 includes:
the final predicted value of the passenger number of each flight on the M +1 th day is obtained through a first formula:
wherein, PiFinal forecast, P, representing the number of passengers for the ith flight′Maximum predicted value representing the number of passengers corresponding to day M +1, P' representing the minimum predicted value of the number of passengers corresponding to day M +1, N representing the total number of flights for the same flight line, deltaiAnd representing the weight predicted value corresponding to the ith flight in the M +1 th day, wherein i is a positive integer and is less than or equal to N.
Further, after the predicting obtains the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the M +1 th day, the method further comprises the following steps:
and according to the influence data of each flight in each day in continuous multiple days, obtaining correction coefficients corresponding to the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the M +1 th day respectively, and correcting the maximum predicted value and the minimum predicted value by using the correction coefficients corresponding to the maximum predicted value and the minimum predicted value of the number of passengers of the single flight in the M +1 th day respectively.
The beneficial effect of adopting the further scheme is that: the maximum predicted value and the minimum predicted value are corrected respectively by using the correction coefficients respectively corresponding to the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the (M + 1) th day, so that the accuracy of the maximum predicted value and the accuracy of the minimum predicted value are higher, and the prediction accuracy of the number of passengers of the flight is further improved.
Further, the S1 is preceded by: and judging whether the number of passengers on a plurality of flights of the same route in each day in continuous M days is missing or not, and if so, supplementing the missing number of passengers by using an interpolation method.
The beneficial effect of adopting the further scheme is that: supposing that the number of passengers of a flight in a certain day is 0 when the flight is stopped due to objective factors such as weather, the number of the missing passengers is supplemented by an interpolation method to eliminate errors caused by the objective factors, so that the prediction accuracy of the number of passengers of the flight is further improved.
Further, still include: and displaying the flight information of each flight and the final predicted value of the passenger number of each flight in the M +1 th day on the aviation network map.
The beneficial effect of adopting the further scheme is as follows: the flight information of each flight and the final predicted value of the number of passengers can be conveniently and visually checked by an airline company, and the user experience is improved.
The technical scheme of the flight passenger number prediction system is as follows:
the system comprises an initial prediction module and a final calculation module;
the initial prediction module is used for respectively predicting the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the M +1 th day according to the maximum number and the minimum number of passengers in the number of passengers of a plurality of flights aiming at the same airline in each day in the continuous M days, and predicting the weight predicted value corresponding to each flight in the M +1 th day according to the number of passengers of each flight in each day in the continuous M days, wherein M is a positive integer;
and the final calculation module is used for obtaining the final predicted value of the passenger number of each flight in the M +1 th day according to the maximum predicted value and the minimum predicted value of the passenger number of the single flight in the M +1 th day and the weight predicted value corresponding to each flight in the M +1 th day.
The flight passenger number prediction system has the following beneficial effects:
firstly, respectively predicting the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the (M + 1) th day, then predicting the weight predicted value corresponding to each flight in the (M + 1) th day, finally obtaining the final predicted value of the number of passengers of each flight of the same airline in the (M + 1) th day according to the maximum predicted value and the minimum predicted value of the number of passengers of the single flight in the (M + 1) th day and the weight predicted value corresponding to each flight in the (M + 1) th day, and reducing the deviation of the number of passengers predicted by the historical number of passengers of the single flight by integrally considering all flights of the same airline, namely, associating all airlines on the same airline, so that the final predicted value of the number of passengers of each flight of the same airline in the (M + 1) th day is closer to the real number of passengers of each flight in the (M + 1) th day, namely, the prediction accuracy of the number of passengers of the flights, so as to provide evidence support for the formulation of the development policy of the airline company.
On the basis of the scheme, the system for predicting the number of the passengers on the flight can be further improved as follows.
Further, the final calculation module is specifically configured to:
the final predicted value of the passenger number of each flight on the M +1 th day is obtained through a first formula:
wherein, PiFinal forecast, P, representing the number of passengers for the ith flight′Maximum predicted value representing the number of passengers corresponding to day M +1, P' representing the minimum predicted value of the number of passengers corresponding to day M +1, N representing the total number of flights for the same flight line, deltaiAnd representing the weight predicted value corresponding to the ith flight in the M +1 th day, wherein i is a positive integer and is less than or equal to N.
Further, the system further comprises a correction module, wherein the correction module is specifically configured to:
and according to the influence data of each flight in each day in continuous multiple days, obtaining correction coefficients corresponding to the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the M +1 th day respectively, and correcting the maximum predicted value and the minimum predicted value by using the correction coefficients corresponding to the maximum predicted value and the minimum predicted value of the number of passengers of the single flight in the M +1 th day respectively.
The beneficial effect of adopting the further scheme is that: the maximum predicted value and the minimum predicted value are corrected respectively by using the correction coefficients respectively corresponding to the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the (M + 1) th day, so that the accuracy of the maximum predicted value and the accuracy of the minimum predicted value are higher, and the prediction accuracy of the number of passengers of the flight is further improved.
Further, the initial prediction module is further used for judging whether the number of passengers on a plurality of flights of the same route in each day in continuous M days is missing or not, and if so, the missing number of passengers is supplemented by utilizing an interpolation method.
The beneficial effect of adopting the further scheme is that: supposing that the number of passengers of a flight in a certain day is 0 when the flight is stopped due to objective factors such as weather, the number of the missing passengers is supplemented by an interpolation method to eliminate errors caused by the objective factors, so that the prediction accuracy of the number of passengers of the flight is further improved.
And further, the display module is used for displaying the flight information of each flight and the final predicted value of the passenger number of each flight in the M +1 th day on the aviation network map.
The beneficial effect of adopting the further scheme is as follows: the flight information of each flight and the final predicted value of the number of passengers can be conveniently and visually checked by an airline company, and the user experience is improved.
The technical scheme of the electronic equipment is as follows:
comprising a memory, a processor and a program stored on the memory and running on the processor, wherein the processor when executing the program performs the steps of a method of predicting flight passenger number as described in any one of the above.
The electronic equipment has the following beneficial effects:
firstly, respectively predicting the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the (M + 1) th day, then predicting the weight predicted value corresponding to each flight in the (M + 1) th day, finally obtaining the final predicted value of the number of passengers of each flight of the same airline in the (M + 1) th day according to the maximum predicted value and the minimum predicted value of the number of passengers of the single flight in the (M + 1) th day and the weight predicted value corresponding to each flight in the (M + 1) th day, and reducing the deviation of the number of passengers predicted by the historical number of passengers of the single flight by integrally considering all flights of the same airline, namely, associating all airlines on the same airline, so that the final predicted value of the number of passengers of each flight of the same airline in the (M + 1) th day is closer to the real number of passengers of each flight in the (M + 1) th day, namely, the prediction accuracy of the number of passengers of the flights, so as to provide evidence support for the formulation of the development policy of the airline company.
Drawings
Fig. 1 is a flow chart illustrating a method for predicting the number of passengers on a flight according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a system for predicting flight passenger number according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;
Detailed Description
As shown in fig. 1, a method for predicting the number of passengers on an airline flight according to an embodiment of the present invention includes the following steps:
s1, respectively predicting a maximum predicted value and a minimum predicted value of the number of passengers of a single flight in the M +1 th day according to the maximum number and the minimum number of passengers in the number of passengers of a plurality of flights aiming at the same airline in each day in continuous M days, and predicting a weight predicted value corresponding to each flight in the M +1 th day according to the number of passengers of each flight in each day in continuous M days, wherein M is a positive integer;
s2, obtaining a final predicted value of the passenger number of each flight in the M +1 th day according to the maximum predicted value and the minimum predicted value of the passenger number of the single flight in the M +1 th day and the weight predicted value corresponding to each flight in the M +1 th day.
Firstly, respectively predicting the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the (M + 1) th day, then predicting the weight predicted value corresponding to each flight in the (M + 1) th day, finally obtaining the final predicted value of the number of passengers of each flight of the same airline in the (M + 1) th day according to the maximum predicted value and the minimum predicted value of the number of passengers of the single flight in the (M + 1) th day and the weight predicted value corresponding to each flight in the (M + 1) th day, and reducing the deviation of the number of passengers predicted by the historical number of passengers of the single flight by integrally considering all flights of the same airline, namely, associating all airlines on the same airline, so that the final predicted value of the number of passengers of each flight of the same airline in the (M + 1) th day is closer to the real number of passengers of each flight in the (M + 1) th day, namely, the prediction accuracy of the number of passengers of the flights, so as to provide evidence support for the formulation of the development policy of the airline company.
Where M may be set according to actual conditions, for example, M is 200, 300, etc., and M is 200, and a straight flight route from beijing to Chongqing is used for explanation, specifically:
the straight flight route from Beijing to Chongqing has a plurality of flights in the same day, such as CA1435 flight, east aviation MU3952 flight and the like of Chinese aviation, the takeoff time of each flight is different, 20 flights from Beijing to Chongqing in the first day are assumed, for convenience of expression, the flights are respectively marked as a first flight, a second flight … … nineteenth flight and a twentieth flight, each flight in the first day respectively corresponds to a passenger number, then comparison is carried out to obtain the maximum passenger number and the minimum passenger number in the day, and so on, 200 maximum passenger number and 200 minimum passenger number are obtained, then the maximum predicted value and the minimum predicted value of the passenger number of a single flight in the 201 day are respectively predicted according to the 200 maximum passenger number and the 200 minimum passenger number, wherein the maximum predicted value of the passenger number of a single flight is predicted based on the 200 maximum passenger number through a self-regression sliding average model, specifically, the method comprises the following steps:
taking the first day, the second day, the … … the first hundred ninety nine days and the second hundred days as time series data, then establishing a first autoregressive moving average model according to the maximum predicted value corresponding to the first day, the maximum predicted value corresponding to the second day … … the first hundred ninety nine days and the maximum predicted value corresponding to the second hundred days, and respectively predicting the maximum predicted value of the number of passengers of a single flight in the 201 th day according to the first autoregressive moving average model, wherein the mode of establishing the first autoregressive moving average model comprises the following steps:
s10, performing a smoothing process on the time series data of the first day, the second day, the … … first hundred ninety nine days, and the second hundred days by using a certain method, such as a first order difference method or an EMD (Empirical Mode Decomposition), wherein the certain method is well known to those skilled in the art and is not described herein;
s11, since the autocorrelation function and the partial correlation function of the stationary sequence obtained by smoothing the time series data of the first day, the second day, the … … -the one hundred ninety nine days and the second hundred days are all fixed, the model identification can be carried out according to the autocorrelation function and the partial correlation function;
s12, estimating parameters of the autoregressive moving average model by using a least-squares method;
s13, determining the order of the autoregressive moving average model by combining an autocorrelation function, a partial autocorrelation function order-fixing method and a criterion function order-fixing method;
s14, building an autoregressive moving average model according to the model identification result, the estimated parameters and the order of the autoregressive moving average model, predicting errors by using a minimum variance principle, and if the predicted errors are within a preset error range, determining that the model is the first autoregressive moving average model.
And by analogy, the first day, the second day, the one hundred ninety nine days and the second hundred days of … … are taken as time series data, then a second autoregressive moving average model is established according to the minimum predicted value corresponding to the first day, the minimum predicted value corresponding to the second day … …, the one hundred ninety nine days and the minimum predicted value corresponding to the second hundred days, and the minimum predicted values of the number of passengers of a single flight in the 201 th day are respectively predicted according to the second autoregressive moving average model.
The technical effect of the method for predicting the number of passengers on flights of the application is explained by taking a first flight as an example, a mathematical model is established by only using the historical number of passengers on the first flight to predict the predicted value of the number of passengers on the first flight in the (M + 1) th flight, at this time, the number of passengers on the nineteenth flight and the twentieth flight of the second flight … … is not considered, and in fact, since the nineteenth flight and the twentieth flight of the first flight, the second flight … … belong to the same airline, the passengers can select the flights after comparing the flights when selecting the flights;
that is, there must be a connection between the first flight, the second flight … …, the nineteenth flight, and the twentieth flight, which is embodied by: the passengers are compared and then selected when selecting flights, that is, the number of passengers of the flight line per day is a relatively fixed value, for example, when the passenger does not select the first flight, the passenger selects the nineteenth flight or the twentieth flight of the second flight … …, if a mathematical model is established by singly using the historical number of passengers of the first flight to predict the predicted value of the number of passengers of the first flight in the M +1 st day, the connection among a plurality of flights corresponding to the same flight line is manually abandoned, so that the deviation of the predicted number of passengers is large, but the application associates all the flight lines on the same flight line to ensure that the fitting degree of the established autoregressive sliding average model is higher, so that the final predicted value of the number of passengers of each flight line of the same flight line in the M +1 st day is closer to the real number of passengers of each flight line in the M +1 st day, namely, the prediction accuracy of the number of passengers on the flight is improved so as to provide demonstration support for the formulation of the development policy of the airline company, specifically:
the airline may apply for adjusting the departure time, price, etc. of a flight to a management department such as an airport according to the final predicted value of the number of passengers per flight to increase the number of passengers on the flight, reduce invalid or costly flights, and increase revenue, for example, if the final predicted value of the number of passengers on the first flight is 100 people and the final predicted value of the number of passengers on the first flight is 300 people in the M +1 th day, the airline operating the first flight may apply for adjusting the departure time of the flight to approach the departure time of the second flight to increase the number of passengers on the first flight and increase revenue.
Wherein, according to the passenger number of the first flight, the nineteenth flight and the twentieth flight of the second flight … … in the first day, the weight value of each flight in the first day is obtained, and by analogy, the weight value of each flight in the second day, the one hundred ninety nine days in the … … and the second hundred days is obtained; and then, training based on an autoregressive integral moving average model, a convolutional neural network, a gray prediction model, a bayesian network model, a markov model or a hidden markov model to obtain a weight prediction model, wherein the training process is known by persons in the field and is not described herein, and the weight value of each flight per day is trained in the form of an array, a vector or a matrix.
Preferably, in the above technical solution, S2 includes:
the final predicted value of the passenger number of each flight on the M +1 th day is obtained through a first formula:
wherein, PiFinal forecast, P, representing the number of passengers for the ith flight′Maximum predicted value representing the number of passengers corresponding to day M +1, P' representing the minimum predicted value of the number of passengers corresponding to day M +1, N representing the total number of flights for the same flight line, deltaiAnd representing the weight predicted value corresponding to the ith flight in the M +1 th day, wherein i is a positive integer and is less than or equal to N.
By way of a simplest example, assuming that the number of passengers on the first to tenth flights is 100 and the number of passengers on the eleventh to twentieth flights is 200 within 200 days, it can be known from common knowledge that the final predicted values of the number of passengers on the first to tenth flights are 100 on the 201 th day and 200 on the eleventh to twentieth flights on the 201 th day;
when the prediction method for the number of passengers on flights is used for prediction, it is known that the maximum predicted value and the minimum predicted value of the number of passengers on a single flight on the M +1 th day are respectively predicted to be 200 and 100, the predicted weight values of the first flight to the tenth flight on the 201 th day are 100/(100 × 10+200 × 10) ═ 1/30, and the predicted weight values of the first flight to the tenth flight on the 201 th day are 20/(100 × 10+200 × 10) — 1/15, so that:
1) taking the first flight as an example, i is 1,
2) when the eleventh flight is taken as an example, i is 11,
the final predicted value of the first flight and the final predicted value of the eleventh flight are respectively the same as the final predicted value of the first flight and the final predicted value of the eleventh flight obtained according to the common sense, and the correctness of the first formula is explained.
Preferably, in the above technical solution, before obtaining the final predicted value of the number of passengers on each flight in the M +1 th day, the method further includes:
and according to the influence data of each flight in each day in continuous multiple days, obtaining correction coefficients corresponding to the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the M +1 th day respectively, and correcting the maximum predicted value and the minimum predicted value by using the correction coefficients corresponding to the maximum predicted value and the minimum predicted value of the number of passengers of the single flight in the M +1 th day respectively.
The maximum predicted value and the minimum predicted value are corrected respectively by using the correction coefficients respectively corresponding to the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the (M + 1) th day, so that the accuracy of the maximum predicted value and the accuracy of the minimum predicted value are higher, and the prediction accuracy of the number of passengers of the flight is further improved.
The obtaining of the correction coefficient corresponding to the maximum predicted value of the passenger number of the single flight in the M +1 th day according to the influence data of each flight in each day of the continuous multiple days specifically includes:
s20, obtaining influence data corresponding to each flight, specifically:
wherein the impact data comprises: weather data when the flight takes off, weather data when the flight lands, traffic data of a take-off airport when the flight takes off, traffic data of a landing airport when the flight lands, and the like, specifically:
1) assigning weights to different weathers, for example, assigning a weight of 1 to a sunny weather, a weight of 0.8 to a cloudy weather, a weight of 0.5 to a light rain weather, and the like;
2) the weight distribution is carried out according to the traffic condition, for example: if 10 sites exist within 3 kilometers of the take-off airport, the weight of the sites is assigned to be 1, if 8 sites exist within 3 kilometers of the take-off airport, the weight of the sites is assigned to be 0.8, and if 7 sites exist within 3 kilometers of the take-off airport, the weight of the sites is assigned to be 0.7 and the like; at this time, the influence data specifically includes weighted values corresponding to weather data when the flight takes off, weather data when the flight lands, traffic data of a takeoff airport when the flight takes off, and traffic data of a landing airport when the flight lands;
s21, acquiring the deviation between the actual passenger number of each flight in multiple days and the predicted maximum predicted value of each flight in each day by S1-S2, and further acquiring a correction coefficient;
s22, taking the influence data of each flight in each day in multiple days as independent variables, taking the correction coefficient corresponding to each flight in each day in multiple days as dependent variables, and training out a correction coefficient prediction model based on a convolutional neural network, a gray prediction model and the like;
s23, inputting the influence data of each flight in the M +1 th day into a correction coefficient prediction model to obtain correction coefficients respectively corresponding to the maximum predicted values of the number of passengers of a single flight in the M +1 th day;
and by analogy, obtaining correction coefficients corresponding to the minimum predicted values of the number of passengers of a single flight in the M +1 th day respectively.
Preferably, in the above technical solution, S1 further includes: and judging whether the number of passengers on a plurality of flights of the same route in each day in continuous M days is missing or not, and if so, supplementing the missing number of passengers by using an interpolation method.
Supposing that the number of passengers of a flight in a certain day is 0 when the flight is stopped due to objective factors such as weather, the number of the missing passengers is supplemented by an interpolation method to eliminate errors caused by the objective factors, so that the prediction accuracy of the number of passengers of the flight is further improved.
The difference method can be a natural neighborhood method, a spline function, a polynomial interpolation method and the like to complement the number of the missing passengers, and the basic idea is as follows: after the number of passengers in a plurality of days before and after the number of the missing passengers is fitted, a curve or a straight line is fitted, and the number of the missing passengers is obtained according to the curve or the straight line fitted.
Preferably, in the above technical solution, the method further comprises: the flight information of each flight and the final predicted value of the number of passengers of each flight in the M +1 th day are displayed on the aviation network map, wherein the flight information comprises an initial airport, a transit airport, a landing airport, initial time, transit time, landing time and the like, and the flight information of each flight and the final predicted value of the number of passengers of each flight in the M +1 th day can be attached to an airline corresponding to the flight on the aviation network map, so that an airline company can visually check the flight information of each flight and the final predicted value of the number of passengers, and user experience is improved.
In the foregoing embodiments, although the steps are numbered as S1, S2, etc., but only the specific embodiments are given in this application, and those skilled in the art may adjust the execution order of S1, S2, etc. according to the actual situation, which is also within the protection scope of the present invention, and it is understood that some embodiments may include some or all of the above embodiments.
As shown in fig. 2, a system 200 for predicting the number of passengers on a flight according to an embodiment of the present invention includes an initial prediction module 210 and a final calculation module 220;
the initial prediction module 210 is configured to respectively predict a maximum predicted value and a minimum predicted value of the number of passengers of a single flight in the M +1 th day according to the maximum number of passengers and the minimum number of passengers in the number of passengers of multiple flights for the same airline in each day in consecutive M days, and predict a weight predicted value corresponding to each flight in the M +1 th day according to the number of passengers of each flight in each day in consecutive M days, where M is a positive integer;
the final calculation module 220 is configured to obtain a final predicted value of the number of passengers on each flight in the M +1 th day according to the maximum predicted value and the minimum predicted value of the number of passengers on a single flight in the M +1 th day and the weight predicted value corresponding to each flight in the M +1 th day.
Firstly, respectively predicting the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the (M + 1) th day, then predicting the weight predicted value corresponding to each flight in the (M + 1) th day, finally obtaining the final predicted value of the number of passengers of each flight of the same airline in the (M + 1) th day according to the maximum predicted value and the minimum predicted value of the number of passengers of the single flight in the (M + 1) th day and the weight predicted value corresponding to each flight in the (M + 1) th day, and reducing the deviation of the number of passengers predicted by the historical number of passengers of the single flight by integrally considering all flights of the same airline, namely, associating all airlines on the same airline, so that the final predicted value of the number of passengers of each flight of the same airline in the (M + 1) th day is closer to the real number of passengers of each flight in the (M + 1) th day, namely, the prediction accuracy of the number of passengers of the flights, so as to provide evidence support for the formulation of the development policy of the airline company.
Preferably, in the above technical solution, the final calculating module 220 is specifically configured to:
the final predicted value of the passenger number of each flight on the M +1 th day is obtained through a first formula:
wherein, PiFinal forecast, P, representing the number of passengers for the ith flight′Maximum predicted value representing the number of passengers corresponding to day M +1, P' representing the minimum predicted value of the number of passengers corresponding to day M +1, N representing the total number of flights for the same flight line, deltaiAnd representing the weight predicted value corresponding to the ith flight in the M +1 th day, wherein i is a positive integer and is less than or equal to N.
Preferably, in the above technical solution, the apparatus further includes a modification module, and the modification module is specifically configured to:
and according to the influence data of each flight in each day in continuous multiple days, obtaining correction coefficients corresponding to the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the M +1 th day respectively, and correcting the maximum predicted value and the minimum predicted value by using the correction coefficients corresponding to the maximum predicted value and the minimum predicted value of the number of passengers of the single flight in the M +1 th day respectively.
The maximum predicted value and the minimum predicted value are corrected respectively by using the correction coefficients respectively corresponding to the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the (M + 1) th day, so that the accuracy of the maximum predicted value and the accuracy of the minimum predicted value are higher, and the prediction accuracy of the number of passengers of the flight is further improved.
Preferably, in the above technical solution, the initial prediction module 210 is further configured to determine whether the number of passengers on multiple flights of the same route in each day of consecutive M days is missing, and if so, complement the missing number of passengers by using an interpolation method.
Supposing that the number of passengers of a flight in a certain day is 0 when the flight is stopped due to objective factors such as weather, the number of the missing passengers is supplemented by an interpolation method to eliminate errors caused by the objective factors, so that the prediction accuracy of the number of passengers of the flight is further improved.
Preferably, in the above technical solution, the system further comprises a display module, and the display module is configured to display the flight information of each flight and the final predicted value of the number of passengers on each flight in the M +1 th day on the airline network map. The flight information of each flight and the final predicted value of the number of passengers can be conveniently and visually checked by an airline company, and the user experience is improved.
The above-mentioned parameters and steps of each unit module in the system 200 for predicting the number of passengers on a flight according to the present invention can refer to the above-mentioned parameters and steps in the embodiment of the method for predicting the number of passengers on a flight, and are not described herein again.
As shown in fig. 3, an electronic device 300 according to an embodiment of the present invention includes a memory 310, a processor 320, and a program 330 stored in the memory 310 and running on the processor 320, wherein when the program 330 is executed by the processor 320, the steps of a flight passenger number prediction method implemented by any one of the above embodiments are implemented.
Firstly, respectively predicting the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the (M + 1) th day, then predicting the weight predicted value corresponding to each flight in the (M + 1) th day, finally obtaining the final predicted value of the number of passengers of each flight of the same airline in the (M + 1) th day according to the maximum predicted value and the minimum predicted value of the number of passengers of the single flight in the (M + 1) th day and the weight predicted value corresponding to each flight in the (M + 1) th day, and reducing the deviation of the number of passengers predicted by the historical number of passengers of the single flight by integrally considering all flights of the same airline, namely, associating all airlines on the same airline, so that the final predicted value of the number of passengers of each flight of the same airline in the (M + 1) th day is closer to the real number of passengers of each flight in the (M + 1) th day, namely, the prediction accuracy of the number of passengers of the flights, so as to provide evidence support for the formulation of the development policy of the airline company.
The electronic device 300 may be a computer, a mobile phone, or the like, and correspondingly, the program 330 is computer software or a mobile phone APP, and the parameters and steps in the electronic device 300 according to the present invention may refer to the parameters and steps in the above embodiment of the method for predicting the number of passengers on a flight, which is not described herein again.
In the present invention, the terms "first", "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A method for predicting flight passenger number, comprising:
s1, respectively predicting a maximum predicted value and a minimum predicted value of the number of passengers of a single flight in the M +1 th day according to the maximum number and the minimum number of passengers in the number of passengers of a plurality of flights aiming at the same airline in each day in continuous M days, and predicting a weight predicted value corresponding to each flight in the M +1 th day according to the number of passengers of each flight in each day in continuous M days, wherein M is a positive integer;
s2, obtaining a final predicted value of the passenger number of each flight in the M +1 th day according to the maximum predicted value and the minimum predicted value of the passenger number of the single flight in the M +1 th day and the weight predicted value corresponding to each flight in the M +1 th day.
2. The method for predicting the number of passengers on an airline as claimed in claim 1, wherein said S2 comprises:
the final predicted value of the passenger number of each flight on the M +1 th day is obtained through a first formula:
wherein, PiFinal forecast, P, representing the number of passengers for the ith flight′Maximum predicted value representing the number of passengers corresponding to day M +1, P' representing the minimum predicted value of the number of passengers corresponding to day M +1, N representing the total number of flights for the same flight line, deltaiAnd representing the weight predicted value corresponding to the ith flight in the M +1 th day, wherein i is a positive integer and is less than or equal to N.
3. The method for predicting passenger number of flight according to claim 1 or 2, wherein after the predicting obtains the maximum predicted value and the minimum predicted value of passenger number of single flight in M +1 day, the method further comprises:
and according to the influence data of each flight in each day in continuous multiple days, obtaining correction coefficients corresponding to the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the M +1 th day respectively, and correcting the maximum predicted value and the minimum predicted value by using the correction coefficients corresponding to the maximum predicted value and the minimum predicted value of the number of passengers of the single flight in the M +1 th day respectively.
4. The method for predicting the number of passengers on an airline according to claim 1 or 2, wherein the step S1 is preceded by the steps of: and judging whether the number of passengers on a plurality of flights of the same route in each day in continuous M days is missing or not, and if so, supplementing the missing number of passengers by using an interpolation method.
5. The method for predicting the number of passengers on an airline according to claim 1 or 2, further comprising: and displaying the flight information of each flight and the final predicted value of the passenger number of each flight in the M +1 th day on the aviation network map.
6. A prediction system for flight passenger number is characterized by comprising an initial prediction module and a final calculation module;
the initial prediction module is used for respectively predicting the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the M +1 th day according to the maximum number and the minimum number of passengers in the number of passengers of a plurality of flights aiming at the same airline in each day in the continuous M days, and predicting the weight predicted value corresponding to each flight in the M +1 th day according to the number of passengers of each flight in each day in the continuous M days, wherein M is a positive integer;
and the final calculation module is used for obtaining the final predicted value of the passenger number of each flight in the M +1 th day according to the maximum predicted value and the minimum predicted value of the passenger number of the single flight in the M +1 th day and the weight predicted value corresponding to each flight in the M +1 th day.
7. The system of claim 6, wherein the final computing module is specifically configured to:
the final predicted value of the passenger number of each flight on the M +1 th day is obtained through a first formula:
wherein, PiFinal forecast, P, representing the number of passengers for the ith flight′Maximum predicted value representing the number of passengers corresponding to day M +1, P' representing the minimum predicted value of the number of passengers corresponding to day M +1, N representing the total number of flights for the same flight line, deltaiAnd representing the weight predicted value corresponding to the ith flight in the M +1 th day, wherein i is a positive integer and is less than or equal to N.
8. The system of claim 6 or 7, further comprising a correction module, the correction module being specifically configured to:
and according to the influence data of each flight in each day in continuous multiple days, obtaining correction coefficients corresponding to the maximum predicted value and the minimum predicted value of the number of passengers of a single flight in the M +1 th day respectively, and correcting the maximum predicted value and the minimum predicted value by using the correction coefficients corresponding to the maximum predicted value and the minimum predicted value of the number of passengers of the single flight in the M +1 th day respectively.
9. The system of claim 6 or 7, wherein the initial prediction module is further configured to determine whether there is a missing number of passengers for multiple flights of the same airline per day for M consecutive days, and if so, to supplement the missing number of passengers by interpolation.
10. An electronic device comprising a memory, a processor and a program stored on the memory and running on the processor, wherein the processor when executing the program implements the steps of a method of predicting a number of airline passengers as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011141816.8A CN112329993B (en) | 2020-10-22 | 2020-10-22 | Method, system and electronic device for predicting number of flight passengers |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011141816.8A CN112329993B (en) | 2020-10-22 | 2020-10-22 | Method, system and electronic device for predicting number of flight passengers |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112329993A true CN112329993A (en) | 2021-02-05 |
| CN112329993B CN112329993B (en) | 2024-03-19 |
Family
ID=74311405
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011141816.8A Active CN112329993B (en) | 2020-10-22 | 2020-10-22 | Method, system and electronic device for predicting number of flight passengers |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112329993B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020177943A1 (en) * | 2001-04-09 | 2002-11-28 | Beardsworth Louis Jc | Schedule activated management system for optimizing aircraft arrivals at congested airports |
| US8200514B1 (en) * | 2006-02-17 | 2012-06-12 | Farecast, Inc. | Travel-related prediction system |
| CN110288121A (en) * | 2019-05-16 | 2019-09-27 | 北京交通大学 | Flight based on multiple time granularity attention mechanism visits rate prediction technique |
| CN111325380A (en) * | 2019-12-29 | 2020-06-23 | 航天信息股份有限公司 | Method and system for determining flight passenger seat rate based on multi-granularity time attention mechanism |
-
2020
- 2020-10-22 CN CN202011141816.8A patent/CN112329993B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020177943A1 (en) * | 2001-04-09 | 2002-11-28 | Beardsworth Louis Jc | Schedule activated management system for optimizing aircraft arrivals at congested airports |
| US8200514B1 (en) * | 2006-02-17 | 2012-06-12 | Farecast, Inc. | Travel-related prediction system |
| CN110288121A (en) * | 2019-05-16 | 2019-09-27 | 北京交通大学 | Flight based on multiple time granularity attention mechanism visits rate prediction technique |
| CN111325380A (en) * | 2019-12-29 | 2020-06-23 | 航天信息股份有限公司 | Method and system for determining flight passenger seat rate based on multi-granularity time attention mechanism |
Non-Patent Citations (1)
| Title |
|---|
| 陶皖主编: "《大数据导论》", vol. 1, 西安电子科技大学出版社, pages: 29 - 30 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112329993B (en) | 2024-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110334839B (en) | Flight delay prediction method, device, equipment and storage medium | |
| CN111144631B (en) | Real-time probability prediction method for flight delay based on Bayesian network algorithm | |
| CN109787855A (en) | Server Load Prediction method and system based on Markov chain and time series models | |
| US20180012499A1 (en) | System and Method for Predicting Aircraft Taxi Time | |
| EP3065019B1 (en) | Method for optimum maximum range cruise speed in an aircraft | |
| US10373507B2 (en) | System and method for calculating estimated time of runway landing and gate arrival for aircraft | |
| WO2003054830A2 (en) | System and method for estimating aircraft flight delay | |
| US11507905B2 (en) | Satellite scheduling system | |
| CN110276467B (en) | Logistics scheduling method, logistics scheduling server and logistics scheduling system | |
| CN111695842B (en) | Distribution scheme determining method, distribution scheme determining device, electronic equipment and computer storage medium | |
| TW202038182A (en) | Flight schedule adjusting method, device, electronic device, and storage medium in which the method includes acquiring an adjusting parameter for a flight schedule and determining at least one target flight schedule adjusting solution according to the adjusting parameter | |
| CN111192090A (en) | Seat allocation method and device for flight, storage medium and electronic equipment | |
| Kang et al. | Improving airline fuel efficiency via fuel burn prediction and uncertainty estimation | |
| CN110322169A (en) | A kind of method and device of task publication | |
| CN111582919A (en) | Flight passenger seat rate prediction method and system | |
| US8140199B2 (en) | System and method for predicting aircraft gate arrival times | |
| CN115239022A (en) | Passenger flow volume prediction method, device, equipment and storage medium | |
| US20210372839A1 (en) | Dynamic fuel tankering | |
| CN110009939B (en) | Flight delay prediction and sweep analysis method based on ASM | |
| CN112329993A (en) | Method and system for predicting number of passengers on flight and electronic equipment | |
| CN116030617A (en) | Method and device for predicting traffic flow based on road OD data | |
| CN112819215A (en) | Recommendation strategy training method and device, electronic equipment and readable storage medium | |
| CN112819317A (en) | Integrated recovery system for airplane, passenger and aircraft of abnormal flight | |
| CN112329992A (en) | Flight passenger seat rate prediction method, system and electronic equipment | |
| CN115310732B (en) | Flight delay prediction method and system |
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 |