CN111737634A - Flight income prediction method, system, electronic equipment and readable storage medium - Google Patents

Flight income prediction method, system, electronic equipment and readable storage medium Download PDF

Info

Publication number
CN111737634A
CN111737634A CN202010580692.7A CN202010580692A CN111737634A CN 111737634 A CN111737634 A CN 111737634A CN 202010580692 A CN202010580692 A CN 202010580692A CN 111737634 A CN111737634 A CN 111737634A
Authority
CN
China
Prior art keywords
flight
income
seat
data
revenue
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.)
Pending
Application number
CN202010580692.7A
Other languages
Chinese (zh)
Inventor
牛田歌
王莉
贾磊
肖铨武
朱艳华
陈薇远
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ctrip Travel Network Technology Shanghai Co Ltd
Original Assignee
Ctrip Travel Network Technology Shanghai Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ctrip Travel Network Technology Shanghai Co Ltd filed Critical Ctrip Travel Network Technology Shanghai Co Ltd
Priority to CN202010580692.7A priority Critical patent/CN111737634A/en
Publication of CN111737634A publication Critical patent/CN111737634A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • 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
    • 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Mathematical Physics (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Operations Research (AREA)
  • Development Economics (AREA)
  • Mathematical Analysis (AREA)
  • Game Theory and Decision Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Algebra (AREA)
  • Pure & Applied Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a flight income prediction method, a flight income prediction system, electronic equipment and a readable storage medium, wherein the prediction method comprises the following steps: acquiring a flight to be predicted and a time period to be predicted of the flight to be predicted; acquiring historical income data of all flights in a historical time period corresponding to the time period to be predicted; calculating to obtain single-seat income data of each flight and the category attribute of each flight according to historical income data; extracting target single-seat income data of flights with the same target category attribute from historical income data according to the target category attribute of the flight to be predicted, and calculating to obtain a single-seat income peak value and a single-seat income valley value; and determining the prediction income range of the flight to be predicted in the time period to be predicted according to the single-seat income peak value and the single-seat income valley value. According to the method, single-dimensional single-seat income data is introduced into each flight in the airline, and the flights are classified according to the single-seat income data, so that the accuracy of flight income prediction is further improved.

Description

Flight income prediction method, system, electronic equipment and readable storage medium
Technical Field
The invention belongs to the field of flight income prediction, and particularly relates to a flight income prediction method, a flight income prediction system, electronic equipment and a readable storage medium.
Background
For an airline company, the income of each flight is a component of the income of the airline company, and whether the prediction is accurate or not relates to the effect of scheduling of the airplane and applying for planning at the future flight time. Generally, when flight income prediction is performed, due to multidimensional factors such as different periods, different flight-shared situations, different moments and the like, great difficulty is caused to prediction work, and great risk also exists. According to the method and the device, accurate prediction data are provided finally by mining the characteristics of flight income, the category attribute of the flight and the income expression of the flight, and further the quantification of flight item risks is realized.
Disclosure of Invention
The invention aims to overcome the defect of high difficulty in flight input prediction in the prior art, and provides a flight income prediction method, a flight income prediction system, electronic equipment and a readable storage medium.
The invention solves the technical problems through the following technical scheme:
a flight revenue prediction method, the prediction method comprising:
acquiring a flight to be predicted and a time period to be predicted of the flight to be predicted;
acquiring historical income data of all flights in a historical time period corresponding to the time period to be predicted, wherein the historical income data comprises the air ticket price and the number of ticket buyers of each flight;
calculating to obtain single-seat income data of each flight according to the historical income data, and determining the category attribute of each flight according to the single-seat income data; the single-seat revenue data is used for representing the revenue level of each flight, and the category attribute is used for representing the revenue level grade of each flight;
extracting target single-seat income data of flights with the same target class attribute from the historical income data according to the target class attribute of the flight to be predicted;
calculating to obtain a single-seat income peak value and a single-seat income valley value according to the target single-seat income data;
and determining the prediction income range of the flight to be predicted in the time period to be predicted according to the single-seat income peak value and the single-seat income valley value.
Preferably, in the step of calculating the single-seat income data of each flight according to the historical income data, solving the single-seat income data by using the following formula specifically includes:
Figure BDA0002552212980000021
Figure BDA0002552212980000022
wherein x is the income of a single seat,
Figure BDA0002552212980000023
is the average price of the air ticket, m is the number of seats of the flight, xaiIs the price, x, of the ith air ticketbiThe number of people who purchased the ith ticket.
Preferably, the step of determining the category attribute of each flight according to the single-seat income data specifically includes:
dividing the historical time period according to a unit cycle;
respectively calculating the unit seat income of each flight in each unit period;
sequencing each flight according to the unit single seat income to obtain income sequencing data of all flights in each unit period;
determining the category attribute from the revenue ranking data.
Preferably, before the step of extracting the destination single-seat income data of the flight with the same destination category attribute from the historical income data according to the destination category attribute of the flight to be predicted, the prediction method further comprises the following steps:
presetting a data extraction rule, wherein the data extraction rule comprises the following steps: removing the single-seat income data with a first preset percentage before income ranking and the single-seat income data with a second preset percentage after income ranking from the single-seat income data of flights with the same target category attribute;
and in the step of extracting the target single-seat income data of the flights with the same target class attribute from the historical income data according to the target class attribute of the flight to be predicted, extracting the target single-seat income data according to the data extraction rule.
Preferably, the category attributes include high-grade flights, medium-grade flights and low-grade flights;
if the target category attribute is high-grade flight, the first preset percentage is 15%, and the second preset percentage is 15%;
if the target type attribute is a medium-grade flight, the first preset percentage is 25%, and the second preset percentage is 5%;
if the target type attribute is a low-grade flight, the first preset percentage is 30%, and the second preset percentage is 0%.
Preferably, the step of calculating the peak value and the valley value of the single-seat income according to the target single-seat income data specifically includes:
calculating to obtain a single-seat income average value according to the target single-seat income data;
dividing flights corresponding to the target single seat income data into peak flights and low-valley flights according to the single seat income average value;
and calculating to obtain the single-seat income peak value according to the single-seat income data of the peak flight, and calculating to obtain the single-seat income valley value according to the single-seat income data of the low-valley flight.
Preferably, the step of dividing the flight corresponding to the target single-seat income data into a peak flight and a low-valley flight according to the average single-seat income value specifically includes:
if the frequency that the single-seat income of any flight in the corresponding flights is higher than the average value of the single-seat income is higher than the frequency that the single-seat income is lower than the average value of the single-seat income, determining that the flight is a peak flight;
and if the frequency that the single-seat income of any flight in the corresponding flights is higher than the average value of the single-seat income is not more than the frequency that the single-seat income is lower than the average value of the single-seat income, determining that the flight is a low-valley flight.
Preferably, the step of determining the prediction income range of the flight to be predicted in the time period to be predicted according to the single-seat income peak value and the single-seat income valley value specifically includes:
and calculating to obtain the prediction income range according to the seat number of the flight to be predicted, the time period to be predicted, the single-seat income peak value and the single-seat income valley value.
A flight income prediction system comprises a prediction object acquisition module, a historical data acquisition module, a first calculation module, a category attribute determination module, a data extraction module, a second calculation module and a prediction module;
the prediction object acquisition module is used for acquiring a flight to be predicted and a time period to be predicted of the flight to be predicted;
the historical data acquisition module is used for acquiring historical income data of all flights in a historical time period corresponding to the time period to be predicted, and the historical income data comprises the air ticket price and the number of ticket buyers of each flight;
the first calculation module is used for calculating and obtaining single-seat income data of each flight according to the historical income data;
the category attribute determining module is used for determining the category attribute of each flight according to the single-seat income data; the single-seat revenue data is used for representing the revenue level of each flight, and the category attribute is used for representing the revenue level grade of each flight;
the data extraction module is used for extracting target single-seat income data of flights with the same target class attribute from the historical income data according to the target class attribute of the flight to be predicted;
the second calculation module is used for calculating a single-seat income peak value and a single-seat income valley value according to the target single-seat income data;
the prediction module is used for determining the prediction income range of the flight to be predicted in the time period to be predicted according to the single-seat income peak value and the single-seat income valley value.
Preferably, the first calculation module solves the single-seat income data by the following formula, and specifically includes:
Figure BDA0002552212980000041
Figure BDA0002552212980000042
wherein x is the income of a single seat,
Figure BDA0002552212980000043
is the average price of the air ticket, m is the number of seats of the flight, xaiIs the price, x, of the ith air ticketbiThe number of people who purchased the ith ticket.
Preferably, the category attribute determination module comprises a period division unit, a first calculation unit and a sorting unit;
the cycle dividing unit is used for dividing the historical time period according to a unit cycle;
the first calculating unit is used for respectively calculating the unit single seat income of each flight in each unit period;
the sequencing unit is used for sequencing each flight according to the unit single seat income to obtain income sequencing data of all flights in each unit period;
the category attribute determination module is configured to determine the category attribute from the revenue ranking data.
Preferably, the prediction system further comprises a preset module;
the preset module is used for presetting a data extraction rule, and the data extraction rule comprises: removing the single-seat income data with a first preset percentage before income ranking and the single-seat income data with a second preset percentage after income ranking from the single-seat income data of flights with the same target category attribute;
and the data extraction module is used for extracting the target single-seat income data according to the data extraction rule.
Preferably, the category attributes include high-grade flights, medium-grade flights and low-grade flights;
if the target category attribute is high-grade flight, the first preset percentage is 15%, and the second preset percentage is 15%;
if the target type attribute is a medium-grade flight, the first preset percentage is 25%, and the second preset percentage is 5%;
if the target type attribute is a low-grade flight, the first preset percentage is 30%, and the second preset percentage is 0%.
Preferably, the second computing module comprises a second computing unit and a flight dividing unit;
the second calculating unit is used for calculating to obtain a single-seat income average value according to the target single-seat income data;
the flight dividing unit is used for dividing flights corresponding to the target single-seat income data into peak flights and low-valley flights according to the single-seat income average value;
the second calculation module is used for calculating to obtain the single-seat income peak value according to the single-seat income data of the peak flight and calculating to obtain the single-seat income valley value according to the single-seat income data of the low-valley flight.
Preferably, the flight dividing unit is configured to determine that any flight is a peak flight when the frequency of the single-seat income of any flight in the corresponding flights is higher than the frequency of the single-seat income average value and lower than the single-seat income average value;
the flight dividing unit is further used for confirming that any flight is a low-valley flight when the frequency that the single-seat income of any flight in the corresponding flights is higher than the average value of the single-seat income is not more than the frequency that the single-seat income is lower than the average value of the single-seat income.
Preferably, the prediction module is configured to calculate the prediction income range according to the seat number of the flight to be predicted, the time period to be predicted, the peak value of single-seat income, and the valley value of single-seat income.
An electronic device comprises a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the flight income prediction method when executing the computer program.
A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the flight revenue prediction method described above.
The positive progress effects of the invention are as follows: according to the method, single-dimensional single-seat income data is introduced into each flight in the airline, and the flights are classified according to the single-seat income data, so that the data-dependent precision of flight income measurement and calculation is improved, the category of the target flight can be accurately positioned, and the accuracy of flight income prediction is further improved.
Drawings
Fig. 1 is a flowchart of a flight revenue prediction method according to embodiment 1 of the present invention.
Fig. 2 is a flowchart of step 40 in the flight revenue prediction method according to embodiment 2 of the present invention.
Fig. 3 is a flowchart of a flight revenue prediction method according to embodiment 2 of the present invention.
Fig. 4 is a flowchart of step 60 of the flight income prediction method according to embodiment 3 of the present invention.
Fig. 5 is a block diagram of a flight revenue prediction system according to embodiment 4 of the present invention.
Fig. 6 is a schematic block diagram of a category attribute determination module in the flight revenue prediction system according to embodiment 5 of the present invention.
Fig. 7 is a block diagram of a flight revenue prediction system according to embodiment 5 of the present invention.
Fig. 8 is a block diagram of a second calculation module in the flight revenue prediction system according to embodiment 6 of the present invention.
Fig. 9 is a schematic structural diagram of an electronic device according to embodiment 7 of the present invention.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
Example 1
A flight revenue prediction method, as shown in fig. 1, the prediction method comprising:
step 10, acquiring a flight to be predicted and a time period to be predicted of the flight to be predicted;
step 20, acquiring historical income data of all flights in a historical time period corresponding to the time period to be predicted; the historical revenue data includes a ticket price and a number of ticket purchasers for each flight;
it should be noted that after acquiring the historical revenue data, the data may be subjected to a preliminary screening filtering as needed, including but not limited to the following: the shared flights are normalized, the shared flights exist in part of flights, only the records of the main carrier flights are reserved, and the records of the shared flights are deleted; temporary flight processing, temporary flight due to emergency reasons, and flight data for flight compensation lack objectivity and are not reserved.
In addition, if the flight income prediction of a flight in 9 months 2020 is predicted, when the historical data is selected, the historical time period at least includes 9 months in 2019, generally, the data of a whole year is selected, and the range of the time period can be increased or decreased according to the requirement.
Step 30, calculating to obtain single seat income data of each flight according to the historical income data;
step 40, determining the category attribute of each flight according to the single-seat income data; the single-seat revenue data is used for representing the revenue level of each flight, and the category attribute is used for representing the revenue level grade of each flight;
step 50, extracting target single-seat income data of the flights with the same target class attributes from the historical income data according to the target class attributes of the flights to be predicted;
step 60, calculating to obtain a single-seat income peak value and a single-seat income valley value according to the target single-seat income data;
and step 70, determining the prediction income range of the flight to be predicted in the time period to be predicted according to the single-seat income peak value and the single-seat income valley value.
In this embodiment, the solving the single-seat income data in step 30 by using the following formula specifically includes:
Figure BDA0002552212980000081
Figure BDA0002552212980000082
wherein x is the income of a single seat,
Figure BDA0002552212980000083
is the average price of the air ticket, m is the number of seats of the flight, xaiIs the price, x, of the ith air ticketbiThe number of people who purchased the ith ticket.
In this embodiment, step 70 specifically includes:
and calculating to obtain the prediction income range according to the seat number of the flight to be predicted, the time period to be predicted, the single-seat income peak value and the single-seat income valley value.
It should be noted that after obtaining the prediction income range, the risk value of the income of the flight at the prediction time can be further calculated. For example, the (peak value of predicted income-valley value of predicted income)/4 is used for representing the risk value, the index can reflect the possible loss amount that the actual flight income is lower than the predicted income, the risk value and the measured and known information and the predicted interval form a positive correlation relationship, the more the known information, the narrower the predicted interval and the smaller the risk value; on the contrary, the less the known information is, the larger the estimation interval is, the larger the risk value is.
In the embodiment, single-dimensional single-seat income data is introduced into each flight in the airline, and the flights are classified according to the single-seat income data, so that the data-dependent precision of flight income measurement and calculation is improved, the category of the target flight can be accurately positioned, and the accuracy of flight income prediction is further improved.
Example 2
The flight revenue prediction method of this embodiment is further improved based on embodiment 1, as shown in fig. 2, step 40 specifically includes:
step 401, dividing the historical time period according to a unit cycle; when the period is divided, the unit of the time period to be predicted can be referred to, and if the unit is a month, the division can be performed according to the month.
Step 402, respectively calculating unit seat income of each flight in each unit period;
step 403, sequencing each flight according to the unit single seat income to obtain income sequencing data of all flights in each unit period;
step 404, determining the category attribute according to the revenue ranking data.
It should be noted that after the sorting data is obtained, the category attributes may be divided according to the priority of the sorting, or may be further divided according to the median or average number. For example, if the average is further divided, the division is performed by the following methods: high-grade flights, namely, the income of single seats is kept above an average line in the dimension of each month in the same period of history; the medium-grade flights, namely within the dimension of each month in the historical period, the income of the single seat is partially kept above the average line and partially falls below the average line; low-grade flights, i.e., individual seat revenues falling below the average line in the historical contemporaneous month dimension.
In this embodiment, referring to fig. 3, before step 50, the prediction method further includes:
step 411, presetting a data extraction rule, where the data extraction rule includes: removing the single-seat income data with a first preset percentage before income ranking and the single-seat income data with a second preset percentage after income ranking from the single-seat income data of flights with the same target category attribute;
further, in step 50, extracting the target single-seat income data according to the data extraction rule.
If the target category attribute is high-grade flights, the first preset percentage is 15%, the second preset percentage is 15%, and single-seat income data of other 70% flights are used as measurement and calculation data;
if the target category attribute is a medium-grade flight, the first preset percentage is 25%, the second preset percentage is 5%, and single-seat income data of other 70% flights are used as measurement and calculation data;
if the target category attribute is low-grade flights, the first preset percentage is 30%, the second preset percentage is 0%, and single-seat income data of other 70% flights are used as measurement and calculation data.
In this embodiment, the unit single-seat income is calculated according to the division period with the flight number as the dimension, the income level of each flight in a certain period can be displayed, and the flights are divided into three grades, namely high, medium and low, according to the performance level of measuring and calculating the unit single-seat income of each flight amount.
Example 3
The flight revenue prediction method of this embodiment is further improved based on embodiment 1, as shown in fig. 4, step 60 specifically includes:
601, calculating to obtain a single-seat income average value according to the target single-seat income data;
step 602, dividing flights corresponding to the target single seat income data into peak flights and low-valley flights according to the single seat income average value;
and 603, calculating to obtain the single-seat income peak value according to the single-seat income data of the peak flight, and calculating to obtain the single-seat income valley value according to the single-seat income data of the valley flight.
Wherein step 602 specifically includes:
if the frequency that the single-seat income of any flight in the corresponding flights is higher than the average value of the single-seat income is higher than the frequency that the single-seat income is lower than the average value of the single-seat income, determining that the flight is a peak flight; and if the frequency that the single-seat income of any flight in the corresponding flights is higher than the average value of the single-seat income is not more than the frequency that the single-seat income is lower than the average value of the single-seat income, determining that the flight is a low-valley flight.
In this embodiment, flights are further classified according to the average value of the single-seat income, and are divided into peak flights and low-valley flights, and the peak single-seat income and the low-valley single-seat income in each division period are further calculated, so as to obtain the upper limit and the lower limit of the unit estimated interval of the flight to be predicted in the corresponding unit period.
Example 4
A flight income prediction system is shown in figure 5 and comprises a prediction object acquisition module 1, a historical data acquisition module 2, a first calculation module 3, a category attribute determination module 4, a data extraction module 5, a second calculation module 6 and a prediction module 7;
the prediction object obtaining module 1 is used for obtaining a flight to be predicted and a time period to be predicted of the flight to be predicted;
the historical data acquisition module 2 is used for acquiring historical income data of all flights in a historical time period corresponding to the time period to be predicted, wherein the historical income data comprises the air ticket price and the number of ticket buyers of each flight;
it should be noted that after acquiring the historical revenue data, the data may be subjected to a preliminary screening filtering as needed, including but not limited to the following: the shared flights are normalized, the shared flights exist in part of flights, only the records of the main carrier flights are reserved, and the records of the shared flights are deleted; temporary flight processing, temporary flight due to emergency reasons, and flight data for flight compensation lack objectivity and are not reserved.
In addition, if the flight income prediction of a flight in 9 months 2020 is predicted, when the historical data is selected, the historical time period at least includes 9 months in 2019, generally, the data of a whole year is selected, and the range of the time period can be increased or decreased according to the requirement.
The first calculation module 3 is used for calculating the single-seat income data of each flight according to the historical income data;
the category attribute determining module 4 is used for determining the category attribute of each flight according to the single-seat income data; the single-seat revenue data is used for representing the revenue level of each flight, and the category attribute is used for representing the revenue level grade of each flight;
the data extraction module 5 is configured to extract target single-seat revenue data of flights with the same target category attribute from the historical revenue data according to the target category attribute of the flight to be predicted;
the second calculation module 6 is configured to calculate a peak value of the single-seat income and a valley value of the single-seat income according to the target single-seat income data;
the prediction module 7 is configured to determine a prediction revenue range of the flight to be predicted in the time period to be predicted according to the single-seat revenue peak value and the single-seat revenue valley value.
In this embodiment, the first calculating module 3 solves the single-seat income data through the following formula, and specifically includes:
Figure BDA0002552212980000111
Figure BDA0002552212980000112
wherein x is the income of a single seat,
Figure BDA0002552212980000113
is the average price of the air ticket, m is the number of seats of the flight, xaiIs the price, x, of the ith air ticketbiThe number of people who purchased the ith ticket.
In this embodiment, the prediction module 7 is configured to calculate the prediction income range according to the seat number of the flight to be predicted, the time period to be predicted, the peak value of the single-seat income, and the valley value of the single-seat income.
It should be noted that after obtaining the prediction income range, the risk value of the income of the flight at the prediction time can be further calculated. For example, the (peak value of predicted income-valley value of predicted income)/4 is used for representing the risk value, the index can reflect the possible loss amount that the actual flight income is lower than the predicted income, the risk value and the measured and known information and the predicted interval form a positive correlation relationship, the more the known information, the narrower the predicted interval and the smaller the risk value; on the contrary, the less the known information is, the larger the estimation interval is, the larger the risk value is.
In the embodiment, single-dimensional single-seat income data is introduced into each flight in the airline, and the flights are classified according to the single-seat income data, so that the data-dependent precision of flight income measurement and calculation is improved, the category of the target flight can be accurately positioned, and the accuracy of flight income prediction is further improved.
Example 5
The flight revenue prediction system of the present embodiment is a further improvement on the basis of embodiment 4, and as shown in fig. 6, the category attribute determination module 4 includes a period dividing unit 41, a first calculation unit 42, and a sorting unit 43;
the period dividing unit 41 is configured to divide the history time period according to a unit period; when the period is divided, the unit of the time period to be predicted can be referred to, and if the unit is a month, the division can be performed according to the month.
The first calculating unit 42 is configured to calculate unit seat income of each flight in each unit period;
the sorting unit 43 is configured to sort each flight according to the unit single seat income to obtain income sorting data of all flights in each unit period;
the category attribute determination module 4 is configured to determine the category attribute according to the revenue ranking data.
It should be noted that after the sorting data is obtained, the category attributes may be divided according to the priority of the sorting, or may be further divided according to the median or average number. For example, if the average is further divided, the division is performed by the following methods: high-grade flights, namely, the income of single seats is kept above an average line in the dimension of each month in the same period of history; the medium-grade flights, namely within the dimension of each month in the historical period, the income of the single seat is partially kept above the average line and partially falls below the average line; low-grade flights, i.e., individual seat revenues falling below the average line in the historical contemporaneous month dimension.
In this embodiment, referring to fig. 7, the prediction system further includes a preset module 8;
the preset module 8 is configured to preset a data extraction rule, where the data extraction rule includes: removing the single-seat income data with a first preset percentage before income ranking and the single-seat income data with a second preset percentage after income ranking from the single-seat income data of flights with the same target category attribute;
and the data extraction module 5 is used for extracting target single-seat income data according to the data extraction rule.
If the target category attribute is high-grade flights, the first preset percentage is 15%, the second preset percentage is 15%, and single-seat income data of other 70% flights are used as measurement and calculation data;
if the target category attribute is a medium-grade flight, the first preset percentage is 25%, the second preset percentage is 5%, and single-seat income data of other 70% flights are used as measurement and calculation data;
if the target category attribute is low-grade flights, the first preset percentage is 30%, the second preset percentage is 0%, and single-seat income data of other 70% flights are used as measurement and calculation data.
In this embodiment, the unit single-seat income is calculated according to the division period with the flight number as the dimension, the income level of each flight in a certain period can be displayed, and the flights are divided into three grades, namely high, medium and low, according to the performance level of measuring and calculating the unit single-seat income of each flight amount.
Example 6
The flight income prediction system of the present embodiment is a further improvement on the basis of embodiment 4, as shown in fig. 8, the second calculation module 6 includes a second calculation unit 61 and a flight division unit 62;
the second calculating unit 61 is configured to calculate an average value of the income of a single seat according to the income data of the target single seat;
the flight dividing unit 62 is configured to divide flights corresponding to the target single-seat income data into peak flights and low-valley flights according to the single-seat income average value;
the second calculating module 6 is configured to calculate the peak value of the single-seat income according to the single-seat income data of the peak flight, and is further configured to calculate the valley value of the single-seat income according to the single-seat income data of the low-valley flight.
The flight dividing unit 62 is configured to determine that any flight is a peak flight when the frequency of the single-seat income of any flight in the corresponding flights is higher than the average value of the single-seat income and lower than the average value of the single-seat income;
the flight dividing unit 62 is further configured to confirm that any flight is a low-valley flight when the frequency of the single-seat income of any flight in the corresponding flights is higher than the average value of the single-seat income is not more than the frequency of the average value of the single-seat income.
In this embodiment, flights are further classified according to the average value of the single-seat income, and are divided into peak flights and low-valley flights, and the peak single-seat income and the low-valley single-seat income in each division period are further calculated, so as to obtain the upper limit and the lower limit of the unit estimated interval of the flight to be predicted in the corresponding unit period.
Example 7
An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the flight revenue prediction method of any of embodiments 1-3 when executing the computer program.
Fig. 9 is a schematic structural diagram of an electronic device provided in this embodiment. FIG. 9 illustrates a block diagram of an exemplary electronic device 90 suitable for use in implementing embodiments of the present invention. The electronic device 90 shown in fig. 9 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiment of the present invention.
As shown in fig. 9, the electronic device 90 may be embodied in the form of a general purpose computing device, which may be, for example, a server device. The components of the electronic device 90 may include, but are not limited to: at least one processor 91, at least one memory 92, and a bus 93 that connects the various system components (including the memory 92 and the processor 91).
The bus 93 includes a data bus, an address bus, and a control bus.
Memory 92 may include volatile memory, such as Random Access Memory (RAM)921 and/or cache memory 922, and may further include Read Only Memory (ROM) 923.
Memory 92 may also include a program tool 925 having a set (at least one) of program modules 924, such program modules 924 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The processor 91 executes various functional applications and data processing by running a computer program stored in the memory 92.
The electronic device 90 may also communicate with one or more external devices 94 (e.g., keyboard, pointing device, etc.). Such communication may be through an input/output (I/O) interface 95. Also, the electronic device 90 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet) via a network adapter 96. The network adapter 96 communicates with the other modules of the electronic device 90 via the bus 93. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 90, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.
It should be noted that although in the above detailed description several units/modules or sub-units/modules of the electronic device are mentioned, such a division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more of the units/modules described above may be embodied in one unit/module, according to embodiments of the application. Conversely, the features and functions of one unit/module described above may be further divided into embodiments by a plurality of units/modules.
Example 8
A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, carries out the steps of the flight revenue prediction method of any one of embodiments 1 to 3.
More specific examples, among others, that the readable storage medium may employ may include, but are not limited to: a portable disk, a hard disk, random access memory, read only memory, erasable programmable read only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing.
In a possible implementation, the invention may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps of implementing the flight revenue prediction method according to any one of embodiments 1 to 3, when the program product is run on the terminal device.
Where program code for carrying out the invention is written in any combination of one or more programming languages, the program code may be executed entirely on the user device, partly on the user device, as a stand-alone software package, partly on the user device and partly on a remote device or entirely on the remote device.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.

Claims (18)

1. A flight revenue prediction method, the prediction method comprising:
acquiring a flight to be predicted and a time period to be predicted of the flight to be predicted;
acquiring historical income data of all flights in a historical time period corresponding to the time period to be predicted, wherein the historical income data comprises the air ticket price and the number of ticket buyers of each flight;
calculating to obtain single-seat income data of each flight according to the historical income data, and determining the category attribute of each flight according to the single-seat income data; the single-seat revenue data is used for representing the revenue level of each flight, and the category attribute is used for representing the revenue level grade of each flight;
extracting target single-seat income data of flights with the same target class attribute from the historical income data according to the target class attribute of the flight to be predicted;
calculating to obtain a single-seat income peak value and a single-seat income valley value according to the target single-seat income data;
and determining the prediction income range of the flight to be predicted in the time period to be predicted according to the single-seat income peak value and the single-seat income valley value.
2. The flight revenue prediction method of claim 1, wherein the step of calculating the single seat revenue data for each flight based on the historical revenue data comprises solving the single seat revenue data using the following equation:
Figure FDA0002552212970000011
Figure FDA0002552212970000012
wherein x is the income of a single seat,
Figure FDA0002552212970000013
is the average price of the air ticket, m is the number of seats of the flight, xaiIs the price, x, of the ith air ticketbiThe number of people who purchased the ith ticket.
3. The flight revenue prediction method of claim 1, wherein the step of determining a category attribute for each flight based on the single seat revenue data specifically comprises:
dividing the historical time period according to a unit cycle;
respectively calculating the unit seat income of each flight in each unit period;
sequencing each flight according to the unit single seat income to obtain income sequencing data of all flights in each unit period;
determining the category attribute from the revenue ranking data.
4. A flight revenue prediction method according to claim 1, wherein the prediction method further comprises, before the step of extracting from the historical revenue data the target single seat revenue data for flights with the same target class attribute as the flight to be predicted according to the target class attribute:
presetting a data extraction rule, wherein the data extraction rule comprises the following steps: removing the single-seat income data with a first preset percentage before income ranking and the single-seat income data with a second preset percentage after income ranking from the single-seat income data of flights with the same target category attribute;
and in the step of extracting the target single-seat income data of the flights with the same target class attribute from the historical income data according to the target class attribute of the flight to be predicted, extracting the target single-seat income data according to the data extraction rule.
5. The flight revenue prediction method of claim 4, wherein the category attributes include high-grade flights, medium-grade flights, and low-grade flights;
if the target category attribute is high-grade flight, the first preset percentage is 15%, and the second preset percentage is 15%;
if the target type attribute is a medium-grade flight, the first preset percentage is 25%, and the second preset percentage is 5%;
if the target type attribute is a low-grade flight, the first preset percentage is 30%, and the second preset percentage is 0%.
6. The method of claim 1, wherein the step of calculating a peak revenue-per-seat value and a trough revenue-per-seat value based on the target revenue-per-seat data comprises:
calculating to obtain a single-seat income average value according to the target single-seat income data;
dividing flights corresponding to the target single seat income data into peak flights and low-valley flights according to the single seat income average value;
and calculating to obtain the single-seat income peak value according to the single-seat income data of the peak flight, and calculating to obtain the single-seat income valley value according to the single-seat income data of the low-valley flight.
7. The flight revenue prediction method of claim 6, wherein the step of classifying flights corresponding to the target single seat revenue data into peak flights and valley flights based on the average single seat revenue value specifically comprises:
if the frequency that the single-seat income of any flight in the corresponding flights is higher than the average value of the single-seat income is higher than the frequency that the single-seat income is lower than the average value of the single-seat income, determining that the flight is a peak flight;
and if the frequency that the single-seat income of any flight in the corresponding flights is higher than the average value of the single-seat income is not more than the frequency that the single-seat income is lower than the average value of the single-seat income, determining that the flight is a low-valley flight.
8. The flight revenue prediction method of claim 1, wherein the step of determining the prediction revenue range of the flight to be predicted in the time period to be predicted according to the peak value and the valley value of the single-seat revenue specifically comprises:
and calculating to obtain the prediction income range according to the seat number of the flight to be predicted, the time period to be predicted, the single-seat income peak value and the single-seat income valley value.
9. The flight income prediction system is characterized by comprising a prediction object acquisition module, a historical data acquisition module, a first calculation module, a category attribute determination module, a data extraction module, a second calculation module and a prediction module;
the prediction object acquisition module is used for acquiring a flight to be predicted and a time period to be predicted of the flight to be predicted;
the historical data acquisition module is used for acquiring historical income data of all flights in a historical time period corresponding to the time period to be predicted, and the historical income data comprises the air ticket price and the number of ticket buyers of each flight;
the first calculation module is used for calculating and obtaining single-seat income data of each flight according to the historical income data;
the category attribute determining module is used for determining the category attribute of each flight according to the single-seat income data; the single-seat revenue data is used for representing the revenue level of each flight, and the category attribute is used for representing the revenue level grade of each flight;
the data extraction module is used for extracting target single-seat income data of flights with the same target class attribute from the historical income data according to the target class attribute of the flight to be predicted;
the second calculation module is used for calculating a single-seat income peak value and a single-seat income valley value according to the target single-seat income data;
the prediction module is used for determining the prediction income range of the flight to be predicted in the time period to be predicted according to the single-seat income peak value and the single-seat income valley value.
10. The flight revenue prediction system of claim 9, wherein the first calculation module solves the single seat revenue data by the following equation, in particular comprising:
Figure FDA0002552212970000041
Figure FDA0002552212970000042
wherein x is the income of a single seat,
Figure FDA0002552212970000043
is the average price of the air ticket, m is the number of seats of the flight, xaiIs the price, x, of the ith air ticketbiThe number of people who purchased the ith ticket.
11. The flight revenue prediction system of claim 9, wherein the category attribute determination module includes a period division unit, a first calculation unit, and a ranking unit;
the cycle dividing unit is used for dividing the historical time period according to a unit cycle;
the first calculating unit is used for respectively calculating the unit single seat income of each flight in each unit period;
the sequencing unit is used for sequencing each flight according to the unit single seat income to obtain income sequencing data of all flights in each unit period;
the category attribute determination module is configured to determine the category attribute from the revenue ranking data.
12. The flight revenue prediction system of claim 9, wherein the prediction system further comprises a preset module;
the preset module is used for presetting a data extraction rule, and the data extraction rule comprises: removing the single-seat income data with a first preset percentage before income ranking and the single-seat income data with a second preset percentage after income ranking from the single-seat income data of flights with the same target category attribute;
and the data extraction module is used for extracting the target single-seat income data according to the data extraction rule.
13. The flight revenue prediction system of claim 12, wherein the category attributes include high-grade flights, medium-grade flights, and low-grade flights;
if the target category attribute is high-grade flight, the first preset percentage is 15%, and the second preset percentage is 15%;
if the target type attribute is a medium-grade flight, the first preset percentage is 25%, and the second preset percentage is 5%;
if the target type attribute is a low-grade flight, the first preset percentage is 30%, and the second preset percentage is 0%.
14. The flight revenue prediction system of claim 9, wherein the second calculation module includes a second calculation unit and a flight division unit;
the second calculating unit is used for calculating to obtain a single-seat income average value according to the target single-seat income data;
the flight dividing unit is used for dividing flights corresponding to the target single-seat income data into peak flights and low-valley flights according to the single-seat income average value;
the second calculation module is used for calculating to obtain the single-seat income peak value according to the single-seat income data of the peak flight and calculating to obtain the single-seat income valley value according to the single-seat income data of the low-valley flight.
15. The flight revenue prediction system of claim 14,
the flight dividing unit is used for confirming that any flight is a peak flight when the frequency that the single-seat income of any flight in the corresponding flights is higher than the average value of the single-seat income is higher than the frequency that the single-seat income is lower than the average value of the single-seat income;
the flight dividing unit is further used for confirming that any flight is a low-valley flight when the frequency that the single-seat income of any flight in the corresponding flights is higher than the average value of the single-seat income is not more than the frequency that the single-seat income is lower than the average value of the single-seat income.
16. The flight revenue prediction system of claim 9, wherein the prediction module is configured to calculate the prediction revenue range based on the number of seats of the flight to be predicted, the time period to be predicted, the peak value of single-seat revenue, and the valley value of single-seat revenue.
17. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the flight revenue prediction method of any one of claims 1 to 8 when executing the computer program.
18. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the steps of the flight revenue prediction method according to any one of claims 1 to 8.
CN202010580692.7A 2020-06-23 2020-06-23 Flight income prediction method, system, electronic equipment and readable storage medium Pending CN111737634A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010580692.7A CN111737634A (en) 2020-06-23 2020-06-23 Flight income prediction method, system, electronic equipment and readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010580692.7A CN111737634A (en) 2020-06-23 2020-06-23 Flight income prediction method, system, electronic equipment and readable storage medium

Publications (1)

Publication Number Publication Date
CN111737634A true CN111737634A (en) 2020-10-02

Family

ID=72650674

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010580692.7A Pending CN111737634A (en) 2020-06-23 2020-06-23 Flight income prediction method, system, electronic equipment and readable storage medium

Country Status (1)

Country Link
CN (1) CN111737634A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022252850A1 (en) * 2021-05-31 2022-12-08 中国民航信息网络股份有限公司 Seasonal classification method and apparatus for flights, and machine-readable medium

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022252850A1 (en) * 2021-05-31 2022-12-08 中国民航信息网络股份有限公司 Seasonal classification method and apparatus for flights, and machine-readable medium

Similar Documents

Publication Publication Date Title
US7761548B2 (en) Dynamic server consolidation and rationalization modeling tool
US20130238399A1 (en) Computer-Implemented Systems and Methods for Scenario Analysis
CN112116184A (en) Factory risk estimation using historical inspection data
CN109740036B (en) Hotel ordering method and device for OTA platform
JP2001125962A (en) Support system for management consulting and decision making in management
CN109978342A (en) Electronic device, methods of risk assessment and computer readable storage medium
CN111027837B (en) Method, system, equipment and medium for determining reference route of newly-added international route
US20090276290A1 (en) System and method of optimizing commercial real estate transactions
CN110751403A (en) Credit scoring method and device
US11348146B2 (en) Item-specific value optimization tool
WO2019196502A1 (en) Marketing activity quality assessment method, server, and computer readable storage medium
CN111737634A (en) Flight income prediction method, system, electronic equipment and readable storage medium
CN113742069A (en) Capacity prediction method and device based on artificial intelligence and storage medium
CN113283806A (en) Enterprise information evaluation method and device, computer equipment and storage medium
CN116362788B (en) Method, device, equipment and storage medium for predicting opening of new airlines
CN112948705A (en) Intelligent matching method, device and medium based on policy big data
CN114372231A (en) Method and device for evaluating flight locking opportunity
CN113435746B (en) User workload scoring method and device, electronic equipment and storage medium
CN111475702B (en) Method, system, equipment and medium for warning air-route price based on crawler technology
CN112907141A (en) Pressure testing method, device, equipment and storage medium
US10504054B2 (en) Travel inventory demand simulation
CN112308344A (en) Method and device for predicting reservation value of non-departure flight and electronic equipment
CN112132689A (en) Recommendation method and device based on time sequence factor event
WO2015191592A1 (en) System and method for generating descriptive measures that assesses the financial health of a business
Fragassa Analysis of Production and Failure Data in Automotive: From Raw Data to Predictive Modeling and Spare Parts

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