Flight reservation quota configuration method and device and electronic equipment

Abstract

The invention provides a seat reservation limit configuration method and device and electronic equipment. The method comprises the following steps: selecting a time period, acquiring passenger data of each shipping space of a flight in the time period, and counting a mean value and a variance of the passenger data; under the condition that passengers are sensitive to air ticket prices, the lower limit protection level of each shipping space is calculated according to a linear nested multi-shipping space EMSR algorithm principle; under the condition that passengers are not sensitive to air ticket prices, the upper limit protection level of each shipping space is calculated according to the two-shipping-space seat stock control algorithm principle under linear nesting; based on the lower boundaries and the upper boundaries of all the shipping space protection levels, according to the degree of manually judging the light season and the peak season, a reasonable shipping space protection level is selected from the upper boundaries and the lower boundaries of the shipping space keeping levels in sequence according to the high-to-low sequence of the shipping spaces; and according to a nested shipping space reservation quota calculation principle, calculating the reservation quota of each shipping space from high to low in sequence. The method can better meet the requirements of passengers according to the supply and demand changes of the market, and overcomes the embarrassing situations that the air ticket price is reduced spirally, the supply is over demand and the income is lost due to the traditional algorithm.

Description

Technical Field

[0001] The present application relates to the field of cabin space control technology, and in particular to a method, device and electronic device for configuring flight booking limits. Background Art

[0002] The design of airline seat products provides an effective way to differentiate passengers. Airline ticket products with corresponding fares are sold to different passenger segments, which not only meets passenger needs, but also prevents airlines from losing passengers and increases revenue. Business travelers are generally sensitive to time and service, and often change flights due to business matters. In order to ensure the flexibility of flight refunds and changes, they have to buy tickets without discounts, so as to obtain high-level services from airlines and reduce the impact on business. Leisure travelers are generally sensitive to air ticket prices, and have to arrange travel plans in advance. They use the airline's air ticket discount rules to lock in travel time and take flights on time in advance, obtain better air tickets from airlines, sacrifice the flexibility of the itinerary, and once the itinerary changes, they will inevitably pay a relatively high price, which is not worth the loss. The core of airlines' control of cabin space is to reserve enough air ticket seats for business travelers based on market judgment, so as to avoid the situation where business travelers have no tickets to book and cannot travel due to late booking. In a related technology, an EMSR (expected marginal seat revenue) algorithm is used to predict the booking limit configuration of each logical class. This method uses historical scheduled flight passenger data to predict the booking limit configuration of each class, pursuing average revenue over a relatively long period of time. This method only fully considers that passengers are sensitive to the price of air tickets. Therefore, the EMSR algorithm will cause the price of air tickets to spiral downward, and business passengers may not be able to buy air tickets when the flight is about to take off. The shortcoming of this method is that it underestimates the price insensitivity of business passengers. The algorithm cannot reserve more seats for these business passengers, which is even more serious during the peak season. In order to overcome the shortcomings of this method, this patent uses artificial experience judgment to adjust the parameter of off-peak season so that the cabin limit can better follow market changes, and the cabin booking limit configuration can be adjusted in real time according to the real-time market situation during the entire air ticket sales period of the airline. Summary of the invention

[0003] The embodiments of the present application provide a method, device and electronic device for configuring flight booking limits to solve the problems existing in the related art.

[0004] In a first aspect, the present application proposes a reservation limit configuration prediction method, the characteristics of which include:

[0005] Step S1, reasonably selecting a time period with similar market rules in history according to the market characteristics of the time period to be predicted, obtaining passenger data of each cabin class of flights in the time period, and calculating the mean and variance thereof;

[0006] Step S2, in the case where passengers are sensitive to air ticket prices, the lower limit protection level of each cabin is calculated according to the principle of linear nested multi-cabin EMSR algorithm;

[0007] Step S3, in the case where passengers are not sensitive to air ticket prices, the upper limit protection level of each class relative to the lowest class is calculated based on the principle of the two-class seat inventory control algorithm under linear nesting;

[0008] Step S4, using the protection level of each cabin described in S2 and S3 as the lower and upper limits of the protection level of the cabin, and selecting a reasonable cabin protection level within the upper and lower limits of the cabin retention level in descending order of cabins according to the degree of artificial judgment of the off-season and peak season;

[0009] Step S5, according to the nested class booking limit calculation principle, calculate the booking limit of each class from high to low.

[0010] In a second aspect, an embodiment of the present application provides a device for configuring a flight booking limit, including:

[0011] The acquisition unit is used to obtain historical cabin data. According to the market characteristics of the time period to be predicted, a time period with similar market rules in history is reasonably selected to obtain passenger data of each cabin of the flight in the time period, and to calculate the mean and variance thereof;

[0012] Prediction unit 1 is used to predict the protection level of cabins dominated by leisure tourists. In the case where passengers are sensitive to air ticket prices, the protection level of each cabin is calculated based on the principle of EMSR algorithm;

[0013] Prediction unit 2 is used to predict the level of protection for cabins dominated by business travelers. In the case where passengers are not sensitive to air ticket prices, the upper limit protection level of each cabin relative to the lowest cabin is calculated based on the principle of the two-cabin seat inventory control algorithm under linear nesting.

[0014] A determination unit is used to use the protection level of each cabin described in S2 and S3 as the lower limit and upper limit of the protection level of the cabin, and select a reasonable cabin protection level in the interval between the upper limit and the lower limit of the cabin retention level in descending order of cabins according to the degree of artificial judgment of the off-season and peak season;

[0015] The calculation unit is used to calculate the booking limit of each cabin from high to low according to the nested cabin booking limit calculation principle.

[0016] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor implements any of the above methods when executing the computer program.

[0017] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the above is implemented.

[0018] Compared with the prior art, this application has the following advantages:

[0019] According to the embodiments of the present application, through historical data analysis, when the market demand is insufficient in the off-season, price means are used to attract more passengers to choose air travel, and the number of passengers who are sensitive to ticket prices is predicted through an algorithm, and the lower limit of the number of passengers in each cabin is estimated; and during the peak season, more seats with higher prices are reserved to facilitate the air travel needs of business passengers, and the upper limit of the number of passengers in each cabin is also predicted through an algorithm. The airline's seat control personnel can adjust the cabin booking limit according to market changes in the off-season and peak-season, solve the problem of spiral decline in air tickets caused by the EMSR algorithm widely used in the industry's revenue management, improve the accuracy of cabin control and the degree of matching with the market, ensure the balance between cabin supply and actual passenger demand, and maximize revenue.

[0020] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments according to the present application and should not be regarded as limiting the scope of the present application.

[0022] Figure 1 is a flow chart showing a method for configuring a reservation limit according to an embodiment of the present application;

[0023] Figure 2 is a schematic diagram showing a linear nested multi-bay protection level EMSR according to an embodiment of the present application;

[0024] Figure 3 is a flow chart showing a linear nested linear nested multi-bay protection level EMSR according to an embodiment of the present application;

[0025] Figure 4 is a protection level flow chart showing a linear nested two-bay protection level in one embodiment of the present application; and

[0026] Figure 5 It is a flow chart showing the calculation of booking limit configuration by a human-machine hybrid algorithm according to an embodiment of the present application.

[0027] Figure 6 The invention is a device for illustrating a reservation limit configuration according to an embodiment of the present application.

[0028] Figure 7 The electronic device illustrates the reservation limit configuration according to an embodiment of the present application. DETAILED DESCRIPTION

[0029] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the concept or scope of the present application. Therefore, the drawings and descriptions are considered to be exemplary in nature and not restrictive.

[0030] To facilitate understanding of the technical solutions of the embodiments of the present application, the following describes the related technologies of the embodiments of the present application. The following related technologies can be combined with the technical solutions of the embodiments of the present application as optional solutions, and they all belong to the protection scope of the embodiments of the present application.

[0031] An embodiment of the present application provides a method 100 for configuring a seat limit. The method 100 can be executed on a computer device, especially on a computing device of an airline, or on a cloud through cloud computing. Regardless of which computer is used for execution, the method can be shared among all airlines through uploading and sharing. Figure 1 The reservation limit configuration method 100 of the present application is described. Figure 1 FIG. 1 is a flow chart showing a method for configuring a seat reservation limit according to an embodiment of the present application. Figure 1 As shown, the reservation limit configuration method 100 includes the following steps S1 to S5. Steps S1 to S5 will be described below in conjunction with a specific embodiment.

[0032] First, enter step S1. In step S1, according to the market characteristics of the time period to be predicted, a time period with similar market rules in history is reasonably selected, and the passenger data of each cabin of the flight in the time period is obtained, and the mean and variance thereof are calculated.

[0033] Airlines can generally divide the cabins with physical space characteristics into first class, business class, and economy class. The same physical cabin can be subdivided into multiple different logical cabins according to airline restrictions. Physical cabins are cabins with different seat layouts and services. Logical cabins are cabins with the same seat layout and services but with different ticket restrictions. For example, the economy class can be divided into 5 logical cabins. These 5 logical cabins have the same seat layout and services, but have different prices and ticket usage conditions. These 5 logical cabins are sorted in descending order of ticket prices: full economy price Y, basic discount U, preferred discount V, special discount W, and super special price T. Among them, the higher the ticket price, the higher the cabin level. Some airlines stipulate that when customers refund or change tickets with different discounts, the refund amount is different, which may include that tickets purchased at a 70% discount cannot be refunded or changed; tickets purchased at a 50% discount can be refunded 40% and can be changed; tickets purchased at a 20% discount can be refunded 60% and can be changed; and tickets purchased at a full price can be refunded 90% and can be changed.

[0034] Airlines have distinct peak and off-peak seasons throughout the year. Generally, July to October is the peak season, and December to March is the off-season. There are more air travel during holidays and weekends. The markets in these time periods have obvious similarities. When making passenger forecasts, we must make full use of this similarity to improve the accuracy of the forecast. Therefore, we must select the corresponding forecast time period and flight data based on the time characteristics of the forecast market, and use the statistical characteristics of historical flight data to predict the future number of passengers traveling and control the booking limits of each cabin.

[0035] Next, enter step S2. In step S2, in the case where passengers are sensitive to air ticket prices, the lower limit protection level of each class is calculated based on the principle of linear nested multi-class EMSR algorithm;

[0036] The protection level (PL) is the number of seats reserved for this class. The booking limit (BL) is the maximum number of seats that can be booked for this class. Since the booking limit of the highest class is the capacity C of this class, the protection level of the highest class will affect the booking limit of the next class. The calculation principle is that the sum of the protection level of this class and above and the booking limit of the next class is not greater than the total capacity of the class.

[0037] Figure 3 is a linear nested linear nested multi-cabin protection level EMSR flow chart showing an embodiment of the present application, such as Figure 3 As shown, the linear nested multi-cabin protection level EMSR method is as follows: Step S310 to Step S350. That is, based on the average number of passengers in each cabin μ i , passenger number variance Fares for each class of service i , get the number of seats reserved for cabin i in all cabins j of the lower level According to the principle of linear nested multi-cabin EMSR algorithm, Figure 2 As shown, In this way, the protection level of each compartment is calculated by the following formula: Among them, i represents the current cabin, m represents the lowest cabin level, and m-1 represents the cabin above the m-level cabin. represents the number of seats reserved for class i in class j of lower grade, norminv represents the inverse function of the normal distribution function, and f i represents the fare for class i of the cabin, f j represents the fare of the lower class fare j, μ i represents the mean number of passengers in cabin i, represents the variance of the number of passengers in cabin i.

[0038] The cycle continues until the next lowest cabin is reached.

[0039] The number of seats reserved in the current class based on the lower class Calculate the protection level NP of the space j as

[0040] Next, enter step S3. In step S3, in the case where passengers are not sensitive to air ticket prices, the upper limit protection level of each class relative to the lowest class is calculated based on the principle of the two-class seat inventory control algorithm under linear nesting;

[0041] Figure 4 FIG. 1 is a flowchart showing the principle of calculating the protection level of a two-class seat inventory control algorithm under linear nesting according to an embodiment of the present application. Figure 4 As shown, the two-class seat inventory control algorithm principle calculates the protection level method as follows: Step S410 to Step S450. Based on the mean number of passengers in each class, the variance of the number of passengers, and the ticket price of each level of class, the number of seats reserved for class i in the lowest class is obtained. Since the number of reserved seats for the class i relative to the lowest class is calculated, the protection level of the class is calculated, and the number of seats reserved for the current class in the lowest class is obtained. The protection level NP of the compartment i is calculated by the following formula: Among them, i represents cabin i, m represents the lowest level cabin, and norminv represents the inverse function of the normal distribution function.

[0042] Next, enter step S4. In step S4, according to the protection level of each cabin described in S2 and S3 as the lower and upper limits of the protection level of the cabin, according to the degree of artificial judgment of the off-season and peak season, a reasonable cabin protection level is selected in the interval between the upper and lower limits of the cabin retention level in descending order of cabins;

[0043] Figure 5 is a flow chart showing the calculation of the reservation limit configuration by the human-machine hybrid algorithm under the linear nesting in one embodiment of the present application. Figure 5 As shown, the method for calculating the booking limit configuration by the human-machine hybrid algorithm under the linear nesting is as follows: Step S510 to Step S550. That is, the flight seat control personnel roughly judge the market off-season and peak season based on their work experience. Here, the off-season parameter is set to α, with a value range of 0 to 1. If the market is judged to be in the peak season, α takes a value close to 1, and if the market is judged to be in the off-season, α takes a value close to 0. The reasonable protection level of each cabin is The value of i ranges from 1 to m-1.

[0044] Next, the process proceeds to step S5. In step S5, the booking limits of each class are calculated in order from high to low according to the nested class booking limit calculation principle.

[0045] Assuming that the total capacity of the cabin is C and the cabin booking limit value is BL, based on the obtained cabin protection level, the cabin booking limit value BL is calculated according to the nested cabin booking limit calculation principle, specifically including:

[0046] BL1=C, Among them, the flight has m cabins, i = 1, 2, ..., m-1 represents the cabin number from high to low, 1 represents the highest level, and m represents the lowest level. It can be seen that the booking limit of the lowest cabin m is determined by the cumulative protection level of all cabins above this level, and has nothing to do with the protection level of the lowest level itself. It shows that in order to meet the needs of passengers in higher cabins, the remaining seats can be used for the needs of passengers in lower cabins.

[0047] Take an example to illustrate the calculation process of the protection level of cabins 1 and 2. Assume that a flight has m cabins, cabin 1 is the highest cabin, and cabin m is the lowest cabin. In step S2, according to the linear nested multi-cabin principle, Figure 2 As shown in the figure, for the sake of simplicity, in three cabin scenarios, the calculation principle and relationship of each cabin protection level, booking limit and reserved seats from low cabin to high cabin are explained. In the off-season, passengers are sensitive to ticket prices. For the highest cabin 1, according to the multi-cabin EMSR principle, the following formula is available: P is the normal probability cumulative function, so the protection level of the highest cabin 1 is calculated as During the peak season, assuming that passengers are not sensitive to ticket prices, we assume that: EMSR1 = EMSRm =f m , calculated according to the principle of two-class seat inventory control algorithm under linear nesting Since f2>f m , the probability distribution cumulative function is an increasing function, then The protection level range for the highest compartment 1 is Airline seat control experts can make their own judgment on the market. If the market is in the peak season, the protection level of the highest cabin 1 is greater, and choose to be close to If the market is off-season, the protection level of the highest cabin 1 is smaller, choose close to Similarly, the protection level of cabin 2 is calculated according to the linear nested multi-cabin principle: Calculated according to the principle of two-class seat inventory control algorithm under linear nesting The protection level range of bay 2 is and If the market is in peak season, the protection level of cabin 2 is close to If the market is off season, the protection level of cabin 2 is close to

[0048] Similarly, the protection level range of cabin i is and If the market is in peak season, the protection level of cabin i is close to If the market is off-season, the protection level of cabin j is close to

[0049] In one embodiment, firstly, the time interval to be predicted is clearly defined, the market characteristics within this time period are analyzed, and a time period with similar market rules in history is reasonably selected to obtain the passenger data of each cabin of the flight in the said time period, and its mean and variance are statistically calculated; specifically, it includes: assuming that the booking limit of all cabins of a certain flight from June to August 2024 is to be predicted, the time interval of historical data is selected from June 1, 2023 to August 31, 2023, and based on the three-month flight historical data, the statistical mean number of passengers in all cabins of the said flight, the variance of the number of passengers, and the ticket price of each class of cabin are obtained. Based on the mean number of passengers, the variance of the number of passengers, and the ticket price of all current classes of cabins, the upper and lower bounds of the protection level of all cabins are predicted through an algorithm, the market off-season and peak season situation is judged according to expert experience, and the protection level of each cabin is reasonably set, so as to obtain the booking limit of each cabin, so that the cabin size of the airline flight matches the market passenger demand and meets the travel needs of passengers.

[0050] In one embodiment, the statistical data of a flight from June 1, 2023 to August 31, 2023 in a statistical period are shown in Table 1 below. The aircraft model selected for this flight is B77W (there are 355 seats in the economy class), and the airline further divides the economy class of this flight into 5 logical classes, which are sorted in descending order according to the ticket price, such as economy full price Y, basic discount U, preferred discount V, special discount W, and super special price T. Among them, the class with a higher ticket price has a higher grade. Therefore, these 5 logical classes are sorted in descending order according to the class level as economy full price Y, basic discount U, preferred discount V, special discount W, and super special price T. In Table 1, the mean μ j represents the mean number of passengers in the corresponding cabin, and the standard deviation σ j represents the standard deviation of the number of passengers in the corresponding cabin, and the ticket price f j Using relative fares, the full-fare economy Y class is set to a unit value of 1.

[0051] Cabin Economy Full Price Y Basic Discount U Preferred discount V Special discount W Super Special T <![CDATA[Mean μ j > 149 62 20 10 33 <![CDATA[Standard deviation σ j > 89 53 28 25 32 <![CDATA[Ticket price f j > 1 0.87 0.68 0.45 0.28

[0052] Table 1

[0053] In one embodiment, the method 100 for configuring flight booking limits provided in the embodiment of the present application is used to illustrate the configuration of booking limits, and the EMSR algorithm used in the related art will be described below.

[0054] In the off-season, the number of business travelers has dropped significantly, and airlines have to lower ticket prices to attract more passengers. At this time, the airline seat control staff sets the parameter α = 0. In view of the situation that passengers are sensitive to ticket prices, the EMSR algorithm principle of linear nested multi-class is used to calculate the lower limit protection level of each class. First, the EMSR algorithm is used to calculate the lower limit protection level of each class based on the data in Table 1. calculate.

[0055]

[0056]

[0057]

[0058] Table 2

[0059] According to the data in Table 2, the protection level of each cabin (Y, U, V, W) is calculated as follows:

[0060] Cabin Y: NP1=49

[0061] Cabin U: NP2 = 108 + 21 - 49 = 80

[0062] Cabin V: NP3 = 161 + 60 + 9 - 108 - 21 = 101

[0063] Cabin W: NP4 = 201 + 87 + 27 + 3-161-60-9 = 88

[0064] By using the separation cabin booking limit prediction algorithm, the booking limits of each cabin under EMSR are obtained (see Table 3)

[0065] Cabin Y: BL1 = C = 355

[0066] Cabin U: BL2 = C-NP1 = 355-49 = 306

[0067] Cabin V: BL3 = C-NP1-NP2 = 306-80 = 226

[0068] Cabin W: BL4 = C-NP1-NP2-NP3 = 226-101 = 125

[0069] Cabin T: BL5 = max (0,125-88) = 37

[0070] Cabin Y U V W T Mean 149 62 20 10 33 Standard Deviation 89 53 28 25 32 EMSR Nested Protection Level NP 49 80 101 88 37 EMSR nested booking limit configuration BL 355 306 226 125 37

[0071] Table 3

[0072] According to the nested booking limit configuration predicted in Table 2, the separated booking limit configuration of each class can be obtained. Under the multi-class EMSR theory, assuming that the flight sales are full and passengers buy tickets for lower-class classes first and then higher-class classes, the seats in T class are allocated to 44, the seats in W class are allocated to 80, the seats in V class are allocated to 70, the seats in U class are allocated to 112, and the seats in Y class are allocated to 49. The total revenue R1=49*1+80*0.87+101*0.68+88*0.45+44*0.28=239.2.

[0073] If the market is in the peak season, passengers are not sensitive to air tickets. Airlines have to raise air tickets in the face of strong demand. At this time, the airline seat control personnel set the parameter α = 1. In the case where passengers are not sensitive to air ticket prices, the protection level of each cabin is calculated based on the principle of the linear nested two-cabin EMSR algorithm. First, the data in Table 1 are used to use the EMSR algorithm Calculation, see Table 3.

[0074]

[0075] The booking limit of each cabin can be predicted by the following formula: b1 = C, C=355,i=1,2,...,m-1,for the description of each parameter in these formulas, please refer to the description of the parameters in the above embodiment.

[0076] Cabin Y U V W T <![CDATA[Mean μ j > 149 62 20 10 33 <![CDATA[Standard deviation σ j > 89 53 28 25 32 The patent protection level NP 201 87 27 3 37 This patent nests the cabin booking limit BL 355 154 67 40 37

[0077] Table 4

[0078] The calculated results are shown in Table 4. Through the separation class booking limit prediction algorithm, it is obtained that the booking limits of each class (Y, U, V, W, T) under the algorithm of this patent are 355, 355-201=154, 154-87=67, 67-27=40, 40-3=37, see Table 4.

[0079] In fact, there are two types of passengers, one is price-sensitive leisure passengers, and the other is price-insensitive business passengers. Therefore, for these business passengers, especially in the peak season, they often cannot board the flight due to full seats and ticket restrictions. In order to facilitate travel flexibility, even if there are low-priced tickets, business passengers will not choose the lowest ticket. At this time, the protection number of each cabin is obtained by the patented algorithm: 201 seats for Y cabin, 87 seats for U cabin, 27 seats for V cabin, 3 seats for W cabin, and 37 seats for the lowest cabin T cabin. The total income R1=201*1+87*0.87+27*0.68+3*0.45+37*0.28=306.76. At this time, the total revenue in the peak season is significantly higher than the multi-cabin EMSR method used in the off-season.

[0080] Since the market is changing rapidly, this patent can adjust a parameter α based on the experience of the seat control personnel, with a value range of 0 to 1. If it is judged that the market is in the peak season, α is close to 1, and if it is judged that the market is in the off-season, α is close to 0. The reasonable protection level of each cabin is The value range of i is 1 to m-1. In this way, the seat control experts can make full use of the market judgment to adjust the protection level of each cabin, so as to achieve a more accurate control of the cabin.

[0081] Corresponding to the application scenario and method of the method provided in the embodiment of the present application, an embodiment of the present application also provides a reservation limit configuration device, which is deployed on a computer device. Figure 6 The reservation limit configuration device of the present application is described. Figure 6 1 is a structural block diagram showing a device for configuring a reservation limit according to an embodiment of the present application. Figure 6 As shown, the reservation limit configuration device 600 may include: an acquisition unit 601, a prediction unit 1 602, a prediction unit 2 603, a determination unit 604 and a calculation unit 605.

[0082] The acquisition unit 601 is used to obtain historical cabin data, reasonably select a time period with similar market rules in history according to the market characteristics of the time period to be predicted, obtain passenger data of each cabin of the flight in the time period, and calculate the mean and variance thereof;

[0083] The prediction unit 1 602 is used to predict the cabin protection level of the majority of leisure tourists. In the case where the passengers are sensitive to the air ticket price, the protection level of each cabin is calculated according to the EMSR algorithm principle;

[0084] The second prediction unit 603 is used to predict the class protection level of business passengers, and in the case where passengers are not sensitive to air ticket prices, the upper limit protection level of each class relative to the lowest class is calculated based on the principle of the two-class seat inventory control algorithm under linear nesting;

[0085] The determination unit 604 is used to use the protection level of each cabin described in S2 and S3 as the lower limit and upper limit of the protection level of the cabin, and select a reasonable cabin protection level in the interval between the upper limit and the lower limit of the cabin retention level in descending order of the cabin according to the degree of the off-season and peak season manually determined;

[0086] The calculation unit 605 is used to calculate the booking limit of each class from high to low according to the nested class booking limit calculation principle.

[0087] The functions of each module in each device in the embodiments of the present application can be found in the corresponding description in the above method, and have corresponding beneficial effects, which will not be repeated here.

[0088] Figure 7 is a block diagram of an electronic device according to an embodiment of the present application. Figure 7 As shown, the electronic device includes: a memory 701 and a processor 702. The memory 701 stores a computer program that can be run on the processor 702. When the processor 702 executes the computer program, the method in the above embodiment is implemented. The number of the memory 701 and the processor 702 can be one or more.

[0089] The electronic device also includes:

[0090] The communication interface 703 is used to communicate with external devices and perform data exchange transmission.

[0091] If the memory 701, the processor 702 and the communication interface 703 are implemented independently, the memory 701, the processor 702 and the communication interface 703 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0092] Optionally, in a specific implementation, if the memory 701, the processor 702 and the communication interface 703 are integrated on a chip, the memory 701, the processor 702 and the communication interface 703 can communicate with each other through an internal interface.

[0093] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor supporting the Advanced RISC Machines (ARM) architecture.

[0094] Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of exemplary but not limiting description, many forms of RAM are available. For example, static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (DR RAM).

[0095] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0096] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0097] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0098] Any process or method described in the flow chart or otherwise described herein can be understood as a module, fragment or portion of a code representing one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.

[0099] The logic and / or steps described in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or used in combination with these instruction execution systems, devices or apparatuses.

[0100] It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium, and when the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0101] In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.

[0102] The above is only an exemplary embodiment of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope recorded in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A reservation limit configuration prediction method, the characteristics of which include: Step S1, reasonably selecting a time period with similar market rules in history according to the market characteristics of the time period to be predicted, obtaining passenger data of each cabin class of flights in the time period, and calculating the mean and variance thereof; Step S2, in the case where passengers are sensitive to air ticket prices, the lower limit protection level of each cabin is calculated according to the principle of linear nested multi-cabin EMSR algorithm; Step S3, in the case where passengers are not sensitive to air ticket prices, the upper limit protection level of each class relative to the lowest class is calculated based on the principle of the two-class seat inventory control algorithm under linear nesting; Step S4, based on the seats at each cabin protection level described in steps S2 and S3 as the lower and upper limits of the cabin protection level, according to the degree of artificial judgment of the off-season and peak season, select a reasonable cabin protection level in the interval between the upper and lower limits of the cabin retention level in descending order of cabin space; Step S5, according to the nested class booking limit calculation principle, calculate the booking limit of each class from high to low.

2. According to the method for predicting seat limit allocation according to claim 1, the method for calculating the protection level of each cabin by the linear nested multi-cabin EMSR algorithm principle described in step S2 is characterized in that include: Based on the average number of passengers in each class, the variance of the number of passengers, and the ticket prices of each class of cabins, obtain the number of seats reserved for the current cabin by the lower-class cabin, which is calculated by the following formula: j = 1, 2,..., m - 1, i < j where i and j represent cabins, and m represents the lowest-class cabin. represents the number of seats reserved for cabin i by the lower-class cabin j, norminv represents the inverse function of the normal distribution function, f i represents the ticket price of class i of the cabin, f j represents the ticket price of the cabin j, μ i represents the average number of passengers in cabin i, represents the variance of the number of passengers in cabin i; The number of seats reserved for current class i based on class j Calculate the protection level NP of the space j as .

3. A reservation limit configuration prediction method according to claim 1, wherein: The linear nested two-class seat inventory control algorithm principle in step S3 calculates the current class protection level, and its characteristics specifically include: Based on the mean number of passengers in each class, the variance of the number of passengers, and the ticket prices of each class, obtain the number of seats reserved for the current class in the lowest class The protection level NP of the compartment i is calculated by the following formula: i=1,2,...,m-1, where i represents cabin i, m represents the lowest cabin level, and norminv represents the inverse function of the normal distribution function.

4. A reservation limit configuration prediction method according to claim 1, wherein: The degree of off-season and peak-season in step S4 is characterized by artificially setting the off-season and peak-season parameter to α, with a value range of 0 to 1. If the market is judged to be in the peak season, α is close to 1, and if the market is judged to be in the off-season, α is close to 0. The reasonable protection level of each cabin is The value of i ranges from 1 to m-1.

5. A reservation limit configuration prediction method according to claim 1, wherein: The nested class booking limit calculation principle described in step S5 has specific characteristics: the booking limit of each class is the difference between the total class capacity and the sum of the protection levels of all classes higher than the class; the highest class is the class with the highest fare, and its booking limit is the total class capacity; the lowest class is the class with the lowest fare level, and its booking limit is not restricted by its own protection level, but by the accumulation of the protection levels of all classes higher than the class.

6. A reservation limit configuration prediction device, wherein the unit implements the corresponding method described in claims 1-5 when executing the computer program. It comprises: The acquisition unit is used to obtain historical cabin data. According to the market characteristics of the time period to be predicted, a time period with similar market rules in history is reasonably selected to obtain passenger data of each cabin of the flight in the time period, and to calculate the mean and variance thereof; Prediction unit 1 is used to predict the cabin protection level for the majority of leisure tourists. In the case where passengers are sensitive to air ticket prices, the lower limit protection level of each cabin is calculated based on the EMSR algorithm principle of linear nested multi-cabin; Prediction unit 2 is used to predict the level of protection for cabins dominated by business travelers. In the case where passengers are not sensitive to air ticket prices, the upper limit protection level of each cabin relative to the lowest cabin is calculated based on the principle of the two-cabin seat inventory control algorithm under linear nesting. A determination unit is used to use the seats with protection levels of each class as the lower and upper limits of the protection level of the class according to S2 and S3, and select a reasonable class protection level within the upper and lower limits of the class protection level in descending order of the class according to the degree of the off-season and peak season manually; The calculation unit is used to calculate the booking limit of each cabin from high to low according to the nested cabin booking limit calculation principle.

7. An electronic device comprising a memory, a processor and a computer program stored in the memory, wherein the processor implements the method according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images