Methods, systems, devices, and storage media to predict market demand values for reachable flights

Abstract

The application belongs to the technical field of aviation revenue management, and provides a method, system, device and storage medium for predicting a reachable market demand value of a flight, the method comprising: acquiring all flight information of a specified flight leg of a specified airline; based on the flight information, acquiring inventory data and historical market demand values of a future flight Dcp; based on the inventory data, predicting market demand values of the leg seats of the latest Dcp of the future flight; based on the historical market demand values, establishing a historical flight data pool with a granularity of seat level for the future flight; based on the historical flight data pool, drawing a flight booking curve for the leg seats of the future flight; and predicting reachable demand values of all seats of the future flight. The application uses a revenue management system to calculate the reachable demand values of the leg (seats) at the time of departure, to reflect market limiting factors, and to improve the function of the revenue management system, the performance of the revenue management system and the work efficiency of the airline revenue management.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of aviation revenue management, and particularly relates to a method, system, device and storage medium for predicting a reachable market demand value of a flight. BACKGROUND

[0002] Revenue management is a scientific method used by airlines to manage prices and seats, so that each seat of each leg of each flight is sold to different types of passengers at different prices in a timely manner, thereby maximizing revenue.

[0003] The revenue management system (basic version) is a system that uses flight plans, inventory, departure and fare data to automatically manage the inventory of un-departed flights based on prediction and optimization models. In the revenue management system, a certain un-departed predicted target flight is determined as follows: the actual booking number of a certain future flight leg (cabin) in the latest Dcp is less than the historical average booking number of the Dcp, or the certain future flight leg (cabin) is locked when the latest Dcp is locked, indicating that the market demand at this time is affected by certain limiting factors (number of aircraft seats, protection number, etc.).

[0004] The purpose of the technology and method of the revenue management system (basic version) is to determine the reachable demand value of each leg (cabin) of a certain future flight Future Departure when it departs. The reachable market demand value plays an important role in revenue management business and revenue management system, and is the main output of the prediction module and the main input of the optimization module in the revenue management system. It is not realistic to perform manual mass calculations, and the lack of prediction theory and technical support in the revenue management system is a long-standing problem in the construction of revenue management work and revenue management system.

[0005] How to solve the above problems and difficulties, and meet the market demand value prediction of each granularity from flight leg to cabin level, is a domestic blank that has not been filled in the systematic operation of market demand value prediction business. SUMMARY

[0006] To solve the above problems, the application provides a method, system, device and storage medium for predicting a reachable market demand value of a flight.

[0007] The method for predicting a reachable market demand value of a flight provided by the application comprises the following steps:

[0008] S1, obtaining all flight information of a specified flight leg of a specified airline; based on the flight information, obtaining inventory data and historical market demand values of a certain future flight Dcp;

[0009] S2, predicting market demand values of the leg cabin of the latest Dcp of the certain future flight based on the inventory data.

[0010] S3, establishing a historical flight data pool with a granularity of a cabin class for the certain future flight based on the historical market demand value;

[0011] S4, drawing a flight booking curve for a leg cabin of the certain future flight based on the historical flight data pool;

[0012] S5, predicting an achievable demand value of all cabins of the certain future flight.

[0013] Further, the all flight information of the specified airline and the specified flight leg is acquired, specifically including:

[0014] The full information and the incremental information of the specified airline and the specified flight leg are acquired and sorted into a database; the incremental information is the latest flight data in the night maintenance time from 2:00 to 4:00 every night.

[0015] Further, the inventory data of a certain future flight Dcp is acquired based on the flight information, specifically including:

[0016] The historical 3-year flight inventory data of the specified airline and the specified flight leg, which is based on the date of the day or the system date of the revenue management system, is acquired as the inventory data of the departed flight;

[0017] The future 1-year flight inventory data of the specified airline and the specified flight leg, which is based on the date of the day or the system date of the revenue management system, is acquired as the inventory data of the undeparted flight.

[0018] Further, the flight information further includes the ASTD aviation standard data provided by the ICS flight control system, and the ASTD aviation standard data specifically includes:

[0019] Flight schedule data SCH: airline, flight number, origin, destination, flight departure date and time, flight arrival date and time;

[0020] Flight booking data INV: electronic ticket mark, cabin structure table, flight physical layout number, maximum number of sellable seats;

[0021] Flight operation data FLT: actual flight departure time.

[0022] Further, the flight booking curve for the leg cabin of the certain future flight is drawn based on the historical flight data pool, specifically including:

[0023] The flight booking curve includes the historical departed flight booking curve, the undeparted flight booking curve and the future flight predicted booking curve;

[0024] The flight booking curve is composed of the booking number of each Dcp, and the booking number of each Dcp is the average of all corresponding Dcp booking numbers in the historical flight data pool;

[0025] If Class i has N records in the historical flight data pool, the booking number of the jth Dcp point on the flight booking curve of Class i is:

[0026]

[0027] Wherein, Class i _DCP j _H is the booking number of the jth Dcp in the flight booking curve of Class i , and Class i _BKD m is the booking number of Class i on the mth record in the historical flight data pool of Class i .

[0028] Further, the predicted achievable demand value of all cabins of a future flight specifically includes:

[0029] S5-1, comparing the booking number BKD of the segment cabin Class i of the latest Dcp of a future flight with the booking number BKD of the corresponding Dcp on the flight booking curve;

[0030] If the booking number BKD of the segment cabin Classi of the latest Dcp of a future flight is less than the booking number BKD of the corresponding Dcp on the flight booking curve, step S5-4 is entered, otherwise step S5-6 is entered;

[0031] S5-2, judging whether the segment cabin Class i of the latest Dcp of a future flight is in the locked cabin Posted state;

[0032] If the segment cabin Class i of the latest Dcp of a future flight is not in the locked cabin Posted state, step S5-5 is entered, otherwise step S5-6 is entered;

[0033] S5-3, calculating the achievable demand value AchievableDemand of the segment cabin Class i of the latest Dcp of a future flight;

[0034] If the booking value BKD of the segment cabin of the latest Dcp of a future flight is greater than the historical average booking number and is not locked, the predicted achievable demand value of the flight segment cabin in the Dcp 23The market demand value of the point is taken as the achievable demand value, that is, AchievableDemand = Demand;

[0035] S5-4. Calculate the class of the latest Dcp for a future flight i The difference between the number of bookings BKD and the number of bookings corresponding to Dcp on the flight booking curve is calculated as follows:

[0036] Difference = i_DCP A _Future-i_DCP A _History

[0037] S5-5. Number of seats corresponding to the flight booking curve i_Dcp 23 _History, calculate the Class of a future flight segment i In DCP 23 The Achievable Demand value is calculated as follows:

[0038] Achievable Demand = i_DCP 23 _History+Difference

[0039] Among them, i_DCP 23 _History is the corresponding DCP on the flight booking curve 23 Number of reservations;

[0040] S5-6. Determine all the classes for a future flight segment i Whether all the AchievableDemand values ​​are calculated;

[0041] S5-7. Output the achievable demand value Achievable Demand.

[0042] Furthermore, the method for determining whether the space is in the Posted state is as follows:

[0043] In the TravelSky ICS system, the main judgment basis is:

[0044] If the maximum available value LSS of the flight booking INV inventory data for the class is a positive integer and the class sales status IND is EK\EAK\ELK\EALK, the class of the flight segment is not locked and posted, and the class is in the saleable state;

[0045] The cabin of the flight segment is locked posted and the cabin of the flight segment is stopped for sale when the maximum available value LSS of the flight booking inventory data of the cabin is less than or equal to 0 or the cabin sales state IND is identified as EPK\EALP\EAPK\EALPK;

[0046] In the foreign ICS system, the main judgment basis is:

[0047] The cabin of the flight segment is locked posted and the cabin of the flight segment is stopped for sale when the BKD booking number of the cabin of the flight segment reaches the AU maximum available value of the cabin class. i The cabin of the flight segment is not locked posted and the cabin is in a saleable state.

[0048] The application further provides a system for predicting a reachable market demand value of a flight, and the system comprises:

[0049] An acquisition module is configured to acquire all flight information of a specified flight segment of a specified airline, and based on the flight information, acquire inventory data and historical market demand values of a future flight Dcp;

[0050] A market demand value prediction module is configured to predict a market demand value of a segment cabin of a latest future flight Dcp based on the inventory data.

[0051] A historical flight data pool construction module is configured to construct a historical flight data pool with a granularity of a cabin level for the future flight based on the historical market demand values.

[0052] A flight booking curve drawing module is configured to draw a flight booking curve for the segment cabin of the future flight based on the historical flight data pool.

[0053] A reachable demand value prediction module is configured to predict reachable demand values of all cabins of the future flight.

[0054] The application further provides a device comprising a processor coupled with a memory, and the processor is configured to read and execute a computer program stored in the memory to implement the aforementioned method for predicting a reachable market demand value of a flight.

[0055] The application further provides a computer readable storage medium storing a program or instructions, and when the program or instructions are run on a computer, the computer is caused to execute the aforementioned method for predicting a reachable market demand value of a flight.

[0056] Compared with the prior art, the application has the following advantages:

[0057] The present application uses a revenue management system to embody market limiting factors by calculating the reachable demand value of a flight segment (cabin) at departure time, perfects the function of the revenue management system, improves the performance of the revenue management system and the work efficiency of the airline revenue management. BRIEF DESCRIPTION OF DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings described below are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0059] Figure 1 The flowchart of a method for predicting the reachable market demand value of a flight according to the present application;

[0060] Figure 2 The structural schematic diagram of a system for predicting the reachable market demand value of a flight according to the present application;

[0061] Figure 3 The structural schematic diagram of an electronic device according to the present application;

[0062] Figure 4 The business flowchart of predicting the market demand value of a flight segment (cabin) of a specified airline according to the embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0064] The following is the explanation of some professional terms of the present application:

[0065] Revenue management system (basic version): a system for automatically managing the inventory of an un-departed flight based on a prediction and optimization model, using flight plan, inventory, departure and fare data.

[0066] Inventory: refers to a series of information affecting the decision of selling a seat on a flight, such as availability of a seat on a flight (Availability), seat booking value (Seat Sold), number of available seats (Seat Open) and various control parameters (Inventory Parameter).

[0067] ICS (Inventory Control System): Airline reservation system mentioned in this paper, also known as inventory control system.

[0068] Data Collection Point Dcp (Data Collection Point): Set by the airline according to its own route quality, flight attributes and other factors, determined by the distance from the departure day, and the data collection code is in one-to-one correspondence with the distance from the departure day; Usually the airline will set Dcp to 24, the closer to the departure day, the larger the Dcp value. For example: Data collection point Dcp is called departure Dcp, corresponding to the distance from the departure day is 0 days.

[0069] Fixed-DCP (Fixed-DCP): Data collection point set by the airline, determined by the distance from the departure day, and the airline can set two sets of data collection points for domestic and international flights in the flight control system (or revenue management system).

[0070] Floating-DCP (Floating-DCP): Data collection point in the category of non-fixed data collection point; For example: The distance from the port date of the designated flight is 20 days, but Dcp 11 corresponding to the distance from the port day is 24 days, Dcp 12 corresponding to the distance from the port day is 18 days, then this data collection point is a floating data collection point, which can be recorded as Dcp 11.5 .

[0071] Final-DCP (Final-DCP): The data collection point for the departure day of the flight, also known as departure Dcp;

[0072] Last actual-DCP (Last actual-DCP): The latest data collection point for the data collection point of the non-departure flight; The revenue management prediction and optimization module applies the inventory of the flight segment level based on the Last actual-DCP as the independent variable data.

[0073] BKD (Booking): The number of seats, sleeping spaces, luggage or cargo spaces or weights that passengers have booked and pre-allocated to passengers;

[0074] Class (Class): The fare paid by passengers for the services and seats provided to them;

[0075] Achievable Demand (Achievable Demand): It can be understood as achievable demand, and under certain price and service conditions within a booking period, the number of passengers who can purchase the flight product composed of such price or service.

[0076] Posted (Posted): The state or action of stopping the sale of a segment (class level).

[0077] Authorized Booking Level (foreign ICS logic, denoted as AU);

[0078] LSS (domestic ICS logic): the number of seats at the cabin level allowed to be sold;

[0079] Demand: the number of passengers who are willing and able to purchase a flight product composed of a certain price or service under the precondition of a booking period and a certain price and service.

[0080] Bkg: the number of seats, sleeping spaces, luggage or cargo spaces or weights that a passenger has booked and pre-allocated to the passenger.

[0081] Demand: the number of passengers who are willing and able to purchase a flight product composed of a certain price or service under the precondition of a booking period and a certain price and service.

[0082] In one embodiment of the present application, a method for predicting a flight achievable market demand value is provided, as shown in Figure 1 and Figure 4 The method comprises the following steps:

[0083] S1. Obtain all flight information of a specified flight segment of a specified airline according to the two-letter code of the airline; based on the flight information, obtain inventory data and historical market demand value of a future flight Dcp;

[0084] The obtaining of all flight information of the specified flight segment of the specified airline comprises the following steps:

[0085] Obtain full information and incremental information of the specified flight segment of the specified airline, and organize the information into a database; the incremental information is the latest flight data within the night maintenance time from 2:00 to 4:00 every night.

[0086] The obtaining of inventory data of the future flight Dcp based on the flight information comprises the following steps:

[0087] Obtain flight inventory data of the already-departed flights of the specified flight segment of the specified airline for the past 3 years based on the current date or the system date of the revenue management system, as the flight inventory data of the already-departed flights;

[0088] Obtain flight inventory data of the future flights of the specified flight segment of the specified airline for the next year based on the current date or the system date of the revenue management system, as the flight inventory data of the not-yet-departed flights.

[0089] The flight information further comprises ASTD aviation standard data provided by the ICS flight control system, which comprises:

[0090] Flight schedule data SCH: airline, flight number, origin, destination, flight departure date and time, flight arrival date and time;

[0091] Flight booking data INV: electronic ticket mark, cabin structure table, flight physical layout number, maximum number of seats available for sale;

[0092] Flight operation data FLT: actual departure time of the flight.

[0093] S2, based on the inventory data, predicting the market demand value of the segment cabin of the latest Dcp of a certain future flight;

[0094] S3, based on the market demand value, establishing a historical flight data pool with a granularity of cabin class for the certain future flight.

[0095] S4, based on the historical flight data pool, drawing a flight booking curve for the segment cabin of the certain future flight;

[0096] The flight booking curve includes the booking curve of the historical flight that has departed, the booking curve of the flight that has not departed, and the future predicted booking curve;

[0097] Wherein, the flight booking curve is composed of the booking number of each Dcp, and the booking number of each Dcp is the average value of all corresponding Dcp booking numbers in the historical flight data pool;

[0098] If the historical flight data pool of Class i has N records, the booking number of the jth Dcp point on the flight booking curve of Class i is:

[0099]

[0100] Wherein, Class i _DCP j _H is the booking number of the jth Dcp in the flight booking curve of Class i , and Class i _BKD m is the booking number of Class i on the mth record in the historical flight data pool of Class i .

[0101] S5, predicting the achievable demand value AchievableDemand of all cabins Class i of the certain future flight, specifically including:

[0102] S5-1. Compare the class of the latest DCP of a future flight i The size of the number of bookings BKD and the number of bookings BKD corresponding to Dcp on the flight booking curve;

[0103] If the latest Dcp class of a future flight i If the number of bookings BKD of the flight is less than the number of bookings BKD of the flight corresponding to Dcp on the flight booking curve, then the process goes to step S5-4; otherwise, the process goes to step S5-6;

[0104] For example: For a future flight, the current flight class is the highest class Y in economy class, and the latest Dcp is Dcp 10 , Y cabin in Dcp 10 The number of seats booked BKD is 40, that is, Y_Dcp 10 _Future=40, and the flight booking curve Dcp 10 The number of seats booked BKD is 50, that is, Y_Dcp 10 _History=50, so go to step S5-4.

[0105] S5-2. Determine the class of the latest Dcp of a future flight i Whether it is in the locked state;

[0106] If the latest Dcp class of a future flight i If the state is not Posted, go to step S5-5; otherwise, go to step S5-6.

[0107] The method for determining whether the space is posted is as follows:

[0108] In the TravelSky ICS system, the main judgment basis is:

[0109] If the maximum available value LSS of the flight booking INV inventory data for the class is a positive integer and the class sales status IND is EK\EAK\ELK\EALK, the class of the flight segment is not locked and posted, and the class is in the saleable state;

[0110] If the maximum available value LSS of the flight booking INV inventory data of the class is less than or equal to 0, or the class sales status IND is marked as EPK\EALP\EAPK\EALPK, the class of the flight segment is locked and posted, and the class of the flight segment is stopped from sale.

[0111] In overseas ICS systems, the main criteria for judgment are:

[0112] The number of BKD bookings for the class of the flight segment reaches that of the class i If the maximum available value of AU (Available Units) is reached, the space for this flight segment is posted and the space for this flight segment is no longer available for sale; otherwise, the space for this flight segment is not posted and is available for sale.

[0113] For example: For a future flight, the current flight class is the highest class Y in economy class, and the latest Dcp is Dcp 10 , Y cabin in Dcp 10 The number of seats booked BKD is 40, that is, Y_Dcp 10 _Future=40, and the maximum available value LSS of cabin Y at this time is LSS=45, that is, cabin Y is not locked, so enter step S5-5.

[0114] S5-3. Calculate the class of the latest Dcp of a future flight i AchievableDemand;

[0115] If the booking value BKD of the latest Dcp segment of a future flight is greater than the historical average booking number and is not locked, the predicted segment class of the flight will be 23 The market demand value of the point is taken as the achievable demand value, that is, AchievableDemand = Demand;

[0116] For example: For a future flight, the current flight class is the highest class Y in economy class, and the latest Dcp is Dcp 10 , Y cabin in Dcp 10 The number of bookings BKD is 40, and the flight booking curve Dcp 10 The number of seats booked BKD is 38, that is, Y_Dcp 10 _Future>Y_Dcp 10 _History;

[0117] The maximum available LSS value of cabin Y is 45, which is the unlocked state;

[0118] The predicted Dcp of cabin Y at departure 23 The market demand value of Demand is 80;

[0119] Therefore, the Achievable Demand of cabin Y is equal to Dcp at departure time. 23 The market demand value, Demand, is 80.

[0120] S5-4, calculate the booking number BKD of the leg of a future flight in the latest DCP of the flight i and the difference Difference between the booking number BKD of the corresponding DCP on the booking curve of the flight, the calculation formula is:

[0121] Difference = i_DCP A _Future - i_DCP A _History

[0122] For example: for a future flight, the current processing flight cabin class is the highest economy cabin Y cabin, the latest DCP is DCP 10 , the booking number BKD of Y cabin in DCP 10 is 40, and the booking number BKD of DCP 10 on the booking curve of the flight is 50, then

[0123] Difference = YDcp 10 Future - YDcp 10 History = -10

[0124] S5-5, according to the booking number i_DCP 23 _History of the corresponding DCP on the booking curve of the flight, calculate the Achievable Demand of the leg Class i in DCP 23 of a future flight, the calculation formula is:

[0125] Achievable Demand = i_DCP 23 _History + Difference

[0126] Wherein, i_DCP 23 _History is the booking number of the corresponding DCP 23 on the booking curve of the flight;

[0127] For example: for a future flight, the current processing flight cabin class is the highest economy cabin Y cabin, the market demand value Demand of Y cabin in DCP 23 on the booking curve is 80, and Difference is calculated by step S5-4 as -10, then the Achievable Demand of cabin Y cabin at DCP 23 point is 80 + (-10) = 70.

[0128] S5-6, judge whether the Achievable Demand of all cabin classes i of the leg of a future flight is calculated.

[0129] S5-7, output achievable demand value.

[0130] Embodiments of the present application also provide a system for predicting an achievable market demand value of a flight, as shown in the accompanying drawings, the system comprises: Figure 2

[0131] An acquisition module 201 is configured to acquire all flight information of a specified airline and a specified flight leg, and based on the flight information, acquire inventory data and a historical market demand value of a future flight Dcp;

[0132] A prediction module 202 is configured to predict a market demand value of a leg seat of a latest future flight Dcp based on the inventory data;

[0133] A historical flight data pool construction module 203 is configured to establish a historical flight data pool of the future flight in a granularity to a seat level based on the historical market demand value;

[0134] A flight booking curve drawing module 204 is configured to draw a flight booking curve of a leg seat of the future flight based on the historical flight data pool;

[0135] An achievable demand value prediction module 205 is configured to predict an achievable demand value of all seats of the future flight.

[0136] As shown in the accompanying drawings, embodiments of the present application also provide an apparatus, comprising: a processor 301 coupled with a memory 302, the processor 301 is configured to read and execute a computer program stored in the memory 302, so as to implement a method for predicting an achievable market demand value of a flight as described in the above method embodiments. Figure 3 Embodiments of the present application also provide a computer readable storage medium storing a program or instructions, when the above program or instructions run on a computer, the computer is caused to execute a method for predicting an achievable market demand value of a flight as described in the above method embodiments.

[0137]

[0138] ​​Obviously, those skilled in the art should understand that each module or each step of the above-mentioned embodiments of the present application can be realized by a general computing device, which can be centralized on a single computing device or distributed on a network composed of multiple computing devices, and optionally, each module or each step can be realized by program codes executable by a computing device, so that each module or each step can be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described can be executed in different orders, or each module can be manufactured as an individual integrated circuit module, or multiple modules or steps can be manufactured as a single integrated circuit module. Therefore, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0139] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. The embodiments of the present application can be variously changed and modified by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for predicting the market demand value of a flight, characterized in that: The method comprises: S1. Obtain all flight information for a specified flight segment of a specified airline; based on the flight information, obtain inventory data and historical market demand value for a future flight DCP; S2. Based on the inventory data, predict the market demand value of the flight segment space with the latest DCP of a future flight; S3. Based on the historical market demand value, establish a historical flight data pool with granularity down to the cabin level for the future flight; specifically, the following steps are involved: The flight booking curve includes the historical booking curve of departing flights, the booking curve of flights that have not departed, and the predicted booking curve of future flights; The flight booking curve is composed of the number of bookings for each DCP, and the number of bookings for each DCP is the average number of bookings for all corresponding DCPs in the historical flight data pool; if There are N records in the historical flight data pool, then The number of reservations for the jth Dcp point on the flight booking curve is: in, for The number of bookings for the jth DCP in the flight booking curve, for The mth record in the historical flight data pool Number of reservations; S4. Drawing a flight booking curve for the flight segments and cabin space of the future flight based on the historical flight data pool; S5. Predict the available demand value of all seats on the future flight; specifically including: S5-1. Compare the latest Dcp of the future flight's flight segment seats The size of the number of bookings BKD and the number of bookings BKD corresponding to Dcp on the flight booking curve; If the latest Dcp class space of a future flight If the number of bookings BKD of the flight is less than the number of bookings BKD of the flight corresponding to Dcp on the flight booking curve, then the process goes to step S5-4; otherwise, the process goes to step S5-2; S5-2. Determine the latest DCP class space for a future flight Whether it is in the locked state; If the latest Dcp class space of a future flight If the state is not Posted, go to step S5-3, otherwise go to step S5-6; S5-3. Calculate the latest Dcp class space for a future flight Achievable Demand; If the booking value BKD of the latest Dcp of a future flight is greater than the historical average booking number and is not locked, the predicted class of the flight segment will be The market demand value of the point is taken as the achievable demand value, that is, ; S5-4. Calculate the latest Dcp class space for a future flight The difference between the number of bookings BKD and the number of bookings corresponding to Dcp on the flight booking curve is calculated as follows: S5-5. Number of seats booked based on flight booking curve , calculate a future flight segment exist The Achievable Demand value is calculated as follows: in, Corresponding to the flight booking curve Number of reservations; S5-6. Determine all available seats for a future flight segment Whether all the Achievable Demand values ​​are calculated; S5-7. Output the achievable demand value Achievable Demand.

2. The method according to claim 1, characterized in that The method of obtaining all flight information of a specified flight segment of a specified airline specifically includes: Obtain the full and incremental information of a specified flight segment of a specified airline and organize and store them in the database; the incremental information is the latest flight data during the night maintenance time from 02:00 to 04:00 every night.

3. The method according to claim 1, characterized in that The obtaining of inventory data of a future flight Dcp based on the flight information specifically includes: Obtain the flight inventory data of the specified airline's specified flight segment for the past three years, based on the current date or the system date of the revenue management system, as the departed flight inventory data; Obtain flight inventory data for a specified flight segment of a specified airline, based on the current date or the system date of the revenue management system, for the next year as the flight inventory data for flights that have not departed.

4. The method according to claim 1, wherein The flight information also includes ASTD aviation standard data provided by the ICS flight control system. The ASTD aviation standard data specifically includes: Flight schedule data SCH: airline, flight number, origin, destination, flight departure date and time, flight arrival date and time; Flight booking data INV: electronic ticket identification, cabin structure table, flight physical layout number, maximum number of seats available for sale on the flight; Flight operation data FLT: actual departure time of the flight.

5. The method according to claim 1, wherein The method to determine whether the space is in the Posted state is: In the TravelSky ICS system, the main judgment basis is: If the maximum available value LSS of the flight booking INV inventory data for the class is a positive integer and the class sales status IND is EK\EAK\ELK\EALK, the class of the flight segment is not locked and posted, and the class is in the saleable state; If the maximum available value LSS of the flight booking INV inventory data of the class is less than or equal to 0, or the class sales status IND is EPK\EALP\EAPK\EALPK, the class of the flight segment is locked and posted, and the class of the flight segment is no longer available for sale; In overseas ICS systems, the main criteria for judgment are: The number of BKD bookings for the class of service for the flight segment reaches that class If the AU value is greater than the maximum available value, the space for this flight segment is locked and posted, and the space for this flight segment is no longer available for sale; otherwise, the space for this flight segment is not locked and posted, and the space is available for sale.

6. A system for predicting the market demand value of a flight, characterized in that: The system comprises: An acquisition module is used to obtain all flight information of a specified flight segment of a specified airline; based on the flight information, obtain inventory data and historical market demand value of a future flight DCP; A module for predicting market demand value, configured to predict the market demand value of the flight segment space of the latest DCP of a future flight based on the inventory data; Constructing a historical flight data pool module, for establishing a historical flight data pool with granularity down to cabin level for a certain future flight based on the historical market demand value; specifically including: The flight booking curve includes the historical booking curve of departing flights, the booking curve of flights that have not departed, and the predicted booking curve of future flights; The flight booking curve is composed of the number of bookings for each DCP, and the number of bookings for each DCP is the average number of bookings for all corresponding DCPs in the historical flight data pool; if There are N records in the historical flight data pool, then The number of reservations for the jth Dcp point on the flight reservation curve is: in, for The number of seats booked for the jth DCP in the flight booking curve, for The mth record in the historical flight data pool Number of reservations; A flight booking curve drawing module is used to draw a flight booking curve for the flight segment class of the future flight based on the historical flight data pool; The module for predicting the achievable demand value is used to predict the achievable demand value of all seats of a certain future flight; S5-1, comparing the latest Dcp of a certain future flight's flight segment seats The size of the number of bookings BKD and the number of bookings BKD corresponding to Dcp on the flight booking curve; If the latest Dcp class space of a future flight If the number of bookings BKD of the flight is less than the number of bookings BKD of the flight corresponding to Dcp on the flight booking curve, then the process goes to step S5-4; otherwise, the process goes to step S5-2; S5-2. Determine the latest DCP class space for a future flight Whether it is in the locked state; If the latest Dcp class space of a future flight If the state is not Posted, go to step S5-3, otherwise go to step S5-6; S5-3. Calculate the latest Dcp class space for a future flight Achievable Demand; If the booking value BKD of the latest Dcp of a future flight is greater than the historical average booking number and is not locked, the predicted class of the flight segment will be The market demand value of the point is taken as the achievable demand value, that is, ; S5-4. Calculate the latest Dcp class space for a future flight The difference between the number of bookings BKD and the number of bookings corresponding to Dcp on the flight booking curve is calculated as follows: S5-5. Number of seats booked based on flight booking curve , calculate a future flight segment exist The Achievable Demand value is calculated as follows: in, Corresponding to the flight booking curve Number of reservations; S5-6. Determine all available seats for a future flight segment Whether all the Achievable Demand values ​​are calculated; S5-7. Output the achievable demand value Achievable Demand.

7. A device, characterized in that comprising a processor coupled to a memory; The processor is configured to read and execute the computer program stored in the memory to implement a method for predicting the market demand value of a flight according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that A program or instruction is stored, and when the program or instruction is run on a computer, the computer is caused to execute a method for predicting the market demand value of a flight as described in any one of claims 1 to 5.

Images