Passenger overflow and recapture method and system based on passenger selection Logit model, and electronic equipment

Abstract

The invention discloses a passenger overflow and recapture method and system based on a passenger selection Logit model, and electronic equipment, and belongs to the technical field of air route network planning. Comprising the following steps: predicting Oamp based on a known passenger selection Logit model; d, calculating the total quantity demanded of the flight according to the quantity demanded of the travel, and calculating the total number of overflowed passengers of the flight and the Oamp according to a Spill model; d stroke overflow value, Oamp; d, gathering all passengers overflowing from the journey in the market to a common Oamp; and D, in the market overflow resource pool, deleting the redefined overflow pool TOW curve after all the full-person itineraries, and then using the itinerary attributes and the redefined overflow pool TOW curve to calculate and delete the new market share of the remaining itineraries after the full-person itineraries by using a Logit model, namely capturing the itinerary demand to obtain the passenger flow volume. Big data is utilized to reasonably and scientifically predict airline market occupancy and market jam points, so that airline decision makers can scientifically formulate airline network planning.

Description

Technical Field

[0001] This application relates to the technical field of airline route network planning, and specifically relates to a passenger spill and recapture model method, system, and electronic device based on big data analysis, which are used to improve flight seat utilization and airline revenue. Background Art

[0002] Airline network revenue management is a very important means for modern airlines to improve market competitiveness. In the face of the complex airline route network, it is a major problem whether the limited resources of airlines can maximize the satisfaction of passengers' travel needs. Among them, passenger spill management is one of the important means to meet passengers' travel needs. However, the problem of passenger spill often occurs when passengers have to switch to other alternative flights because their first-choice flights are full. The main reasons for this problem are: (1) The limited seat capacity of the aircraft cannot meet the needs of passengers; (2) Improper seat control strategies result in the waste of high-fare cabins and the spill of low-fare cabins for standby; (3) The overbooking quantity is insufficient, resulting in empty seats when the flight closes. Airlines need to adopt effective means to meet passengers' needs, expand airline revenue, and achieve a win-win situation.

[0003] China has become the second largest civil aviation market after the United States. Every year, 700 million person-times of passengers in China take civil aviation flights for business or leisure vacations and fly to all over the world. The popular domestic routes in China include the Beijing-Shanghai route, the Beijing-Guangzhou route, and the Beijing-Chengdu route, etc. Due to the good market between Beijing and Shanghai (BJS-SHA) and the large number of flights, most passengers choose nonstop and round-trip flight itinerary combinations. Abroad, there are routes to Europe, America, Japan, and South Korea. Chinese passengers have more diverse choices. Some choose nonstop flights, while some choose to transfer in Beijing, or in Japan and South Korea, or in Europe and America. In such an O&D market, there are hundreds or thousands of itinerary combinations for passengers to choose from. Some itineraries are nonstop, with only one leg or flight; some itineraries involve flight connections, with two flights (legs) and at least three segments. Some are transfers within the same airline, while some are transfers between different airlines or code-sharing intermodal transport within the same alliance. However, due to the limited number of aircraft of airlines, it is impossible to meet the requirements of all passengers in the world to fly directly to their destinations. The airline route network planning is extremely important and is the key and source of airline profitability. The prediction and management of passenger flow in the route network are the key. Which flows are insufficient and which are bottlenecks? If there are bottlenecks, it will cause passenger spill and revenue loss, and insufficient flow will cause waste of empty seats on the aircraft. Traditional manual management cannot predict passenger flow and flight occupancy rate, nor can it evaluate whether the aircraft size is sufficient. It can only adopt temporary adjustment measures before the flight takes off, and can only change from large to small.

[0004] This patent targets flight big data and uses mathematical modeling methods to reasonably and scientifically predict airline market shares, market bottlenecks, and passenger selection methods, allowing airline decision makers to better scientifically formulate airline route network plans based on market needs. Summary of the invention

[0005] The embodiments of the present application provide a method, system and electronic device for passenger overflow and recapture based on a passenger selection Logit model to solve the problems existing in the related art.

[0006] In the first aspect, the present application proposes a passenger spillover and recapture method based on a passenger selection logit model, comprising:

[0007] Based on the known passenger choice Logit model, the demand for O&D itineraries is predicted to obtain the O&D itinerary demand (i) passing through the flight segment (or flight);

[0008] Calculate the total demand for the flight segment (or flight) demand(j) and the effective capacity of the aircraft operating the flight, and calculate the total number of passengers spilled by the flight segment spill(j) based on the Spill model;

[0009] Allocate the total number of overflow passengers of the flight, spill(j), to the flights in the itinerary according to certain rules, and obtain the overflow value of the flight of each itinerary, Spill(i,j);

[0010] Transform each segment-level spill spill(i,j) in the O&D itinerary into the O&D itinerary spill value spill(i), and aggregate all passengers with itinerary spills in the O&D market into a common O&D market spill resource pool (spillpool);

[0011] Re-define the TOW curve of the spill pool after deleting all full trips from all trips in the common O&D market spill pool, and then use the trip attributes and the re-defined TOW curve of the spill pool to calculate the new market share of the remaining trips and the recapture trip demand by using the Logit model, which is equal to the product of the new market share of the trip and the SPILLPOOL;

[0012] The remaining itinerary passenger flow traffic after reacquiring a full flight is no longer considered, which is the sum of the recaptured itinerary demand and the original demand.

[0013] In a second aspect, the embodiment of the present application provides a passenger overflow and recapture system based on a passenger selection Logit model, including:

[0014] The itinerary demand module is used to predict the demand for O&D itineraries based on the known passenger selection Logit model, and obtain the O&D itinerary demand demand(i) passing through the flight segment (or flight).

[0015] The flight overflow module is used to calculate the total demand demand(j) of the flight segment (or flight) and the effective capacity of the aircraft operating the flight, and calculate the total number of flight passenger overflow spill(j) of the flight segment based on the Spill model.

[0016] The overflow allocation module is used to allocate the total overflow number of the flight, spill(j), to the flights in the itinerary according to a certain rule, and obtain the overflow value Spill(i, j) of the flight in each itinerary.

[0017] The itinerary overflow module is used to transform each segment-level overflow spill(i,j) in the O&D itinerary into the O&D itinerary overflow value spill(i), and aggregate all itinerary overflow passengers in the O&D market into a common O&D market overflow resource pool (spillpool).

[0018] The recapture module is used to redefine the TOW curve of the spill pool after deleting all full trips from all trips in the common O&D market spill pool, and then use the trip attributes and the redefined TOW curve of the spill pool to calculate the new market share of the remaining trips and the recapture trip demand by the Logit model, which is equal to the product of the new market share of the trip and the SPILLPOOL.

[0019] The itinerary demand correction module is used to no longer consider the remaining itinerary new demand after re-acquiring the full flight, which is the sum of the re-captured itinerary demand and the original demand.

[0020] 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.

[0021] Compared with the prior art, this application has the following advantages:

[0022] According to the embodiments of the present application, when passengers choose a travel itinerary, often their first choice cannot be satisfied. Affected by factors such as the contradiction between supply and demand, time, and air ticket prices, airline route network planning is often affected by various factors such as resource limitations, traffic rights, and airline strategies. As a result, passengers cannot buy tickets for their ideal routes and turn to other itinerary tickets. This patent mainly uses historical flight and passenger data and model methods to scientifically predict how many passengers are restricted by the airline route network and transfer to other airlines or other flights to complete their travel purposes. Whether calculating market share or correcting the recapture demand generated by those passengers who cannot take their ideal flights and then choose other flights, a nested logit model with travel time stratification is used to scientifically and reasonably predict. The passengers who cannot make the trip are calculated using the Spill model scientifically and reasonably, so as to accurately predict whether all flights in the route network are full and the flow direction of passengers after they are full, overcome the disadvantages of manual judgment and prediction empiricism, and use the method of this patent to scientifically reveal statistical laws, overcoming the disadvantages of difficult manual data collection, high cost, and poor accuracy.

[0023] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the present application more obvious and understandable, the following specifically illustrates the specific implementation manners of the present application. Brief Description of the Drawings

[0024] In the drawings, unless otherwise specified, the same reference numerals throughout the several views denote 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.

[0025] Figure 1 is a flowchart showing a method for passenger spillover and recapture based on a passenger selection Logit model according to an embodiment of the present application;

[0026] Figure 2 is a flowchart showing flight passenger spillover and reallocation on an itinerary according to an embodiment of the present application;

[0027] Figure 3 is a diagram showing the probability of restoring the spilled itinerary in the spill pool at the TOW hour point according to an embodiment of the present application;

[0028] Figure 4 is a flowchart showing the recapture of the remaining itinerary in the O&D market according to an embodiment of the present application;

[0029] Figure 5 is a structural diagram showing a passenger spillover and recapture system according to an embodiment of the present application; and

[0030] Figure 6 It is a block diagram of a passenger spillover and recapture electronic device showing an embodiment of the present application. Detailed implementation manners

[0031] In the following, only some exemplary embodiments are simply described. As those skilled in the art can recognize, the described embodiments can be modified in various different ways without departing from the concept or scope of the present application. Therefore, the drawings and the description are considered to be exemplary in nature and not restrictive.

[0032] To facilitate the understanding of the technical solutions of the embodiments of the present application, the related technologies of the embodiments of the present application are described below. The following related technologies can be arbitrarily combined with the technical solutions of the embodiments of the present application as optional solutions, and all of them fall within the protection scope of the embodiments of the present application. The detailed implementation manners are as follows:

[0033] An embodiment of the present application provides a method 100 for passenger spillover and recapture based on a passenger choice Logit model. The method 100 for passenger spillover and recapture based on a passenger choice Logit model can be executed on a computer device, especially on a computing device of an airline, or can be executed in the cloud through cloud computing. No matter which computer entity it is executed on, it can be shared among all airlines through uploading and sharing. The following will refer to Figure 1 to describe a method 100 for passenger spillover and recapture based on a passenger choice Logit model of the present application. Figure 1 It is a flowchart of a method for passenger spillover and recapture based on a passenger choice Logit model showing an embodiment of the present application. As Figure 1 shown, the method 100 for passenger spillover and recapture based on a passenger choice Logit model includes the following steps S1 to S6. The following will describe steps S1 to S6 in combination with specific embodiments.

[0034] First, enter step S1. In step S1, based on the known passenger choice Logit model, predict the demand for O&D trips, and obtain the O&D trip demand demand(i) for the flight segment (or flight) passing through.

[0035] The travel of air passengers shows certain regularity with the change of seasons in a year. Generally, winter and spring are off-seasons, summer and autumn are peak seasons, and large holidays are also peak passenger flow periods. Especially, July to September is the peak period when students, tourism, and business trips overlap. Airlines also release flight plans or flight schedules showing the same pattern as the market. Flight schedules generally show a weekly cycle of flight operations. Airlines' plans and decisions are based on weekly flight and passenger data, so it is necessary to reasonably select a representative typical week.

[0036] The data sources in this embodiment are the post-departure data PDD of airlines, the revenue settlement data RA, the flight schedule data of this airline, the flight schedule data of foreign airlines from OAG, MIDT, and GDS. The passenger travel history data can reflect the preferences of passengers' travel choices, and a Logit model is regressed through the model. The nested logit model is used to map the passenger utility function value to the trip share percentage ms(i). Divided by the departure time of the trip, starting from 0:00 on Sunday of a typical week, with a time interval of 1 hour, until 23:00 on Saturday, there are a total of 24 * 7 = 168 time points. The passenger flow proportion p(t) at each point is statistically obtained through historical data. Calculate the market share of a certain trip i among k trips. Its specific mathematical expression is While satisfying the market share integrity requirement, the mathematical expression of the utility function is U i,t = β 1 X 1t +…+ β n X nt , where p(t) is the proportion of passenger flow at time t for the TOW of the trip. Among them, X 1t ,..., X nt may be dynamic attributes related to time t or static attributes unrelated to time t. That is to say, the market share of the passenger trip is determined by the passenger preference attributes.

[0037] Exemplarily, take the CA855 flight from PEK to LHR on August 9, 2023 as an example. There are 564 passenger trips passing through CA855. As shown in Table 1, the first 19 trips with more demand are selected. The demand size is directly related to dynamic attributes such as the departure time, and is also related to static attributes such as non-stop flight, transfer, number of transfers, relative fare, and aircraft type, as well as the TOW of the passenger's departure airport. In the embodiment, there is only a non-stop trip from PEK to LHR, and the other 18 trips depart from airports in China, New Zealand, Australia, Japan, and South Korea. According to the Logit model and the corresponding historical TOW curve data of the trips, the market share Market_share and the passenger demand of the trips are shown in Table 1. Among them, for trip 1, from PEK to LHR, flight CA855, the demand dmd = 43.35 is the largest; for trip 2, from Chengdu Tianfu TFU to LHR, connecting with CA1418 and then CA855, the demand dmd = 21.72; for trip 3, from Auckland AKL to LHR, connecting with CA784 the previous day and then CA855, the demand dmd = 12.09.

[0038] Table 1: Trips passing through CA855 and demand, spillover, and recapture

[0039]

[0040] Next, enter step S2. In step S2, calculate the total demand demand(j) of the flight segment (or flight) and the effective capacity of the aircraft operating the flight, and calculate the total number of spilled passengers spill(j) of the flight segment according to the Spill model.

[0041] The Spill model consists of the effective capacity when the aircraft is full, the average load factor LFCF when passengers spill, and the probability of passengers taking the flight. The passenger spill value can be calculated using the passenger spill Spill model. Among them, the effective capacity = the average load factor LFCF when passengers spill * the total number of seats on the aircraft.

[0042] In one embodiment, the total demand for 584 itineraries containing flight CA855 is dmd(CA855) = 311 people. However, the model of CA855 is A359, the total number of seats on the aircraft is C = 312, and generally LFCF = 0.95. The effective capacity = the average load factor LFCF when passengers spill * the total number of seats on the aircraft = 296.

[0043] Exemplarily, the total number of spilled passengers spill(j) of flight CA855 is calculated to be 25 according to the Spill model.

[0044] Next, enter step S3. In step S3, allocate the total number of spilled passengers spill(j) of the flight to the flights in the itinerary according to certain rules to obtain the spill value Spill(i,j) of each flight in the itinerary.

[0045] Exemplarily, as Figure 2 shown, the spill allocation principle is to allocate the flight segment spill(j) to the itinerary passing through it spill(i,j) in proportion to the demand demand of the O&D itinerary and inversely proportional to the unit fare. The calculation method is:

[0046]

[0047] In one embodiment, in itinerary 5, the effective capacity = 296 and Fare = 1. Then, the spill of CA855 in the SYD-LHR itinerary is:

[0048] Spill(5,CA855) = 8.58 / 311 * 25 = 0.69

[0049] Similarly, the spill of CA174 in itinerary 5 is calculated as: Spill(5,CA174) = 0.78.

[0050] Next, proceed to step S4. In step S4, each segment-level spill (i, j) in the O&D itinerary is transformed into the O&D itinerary spill value spill(i), and the passengers spilled from all itineraries in the O&D market are aggregated into a common O&D market spill resource pool (spillpool).

[0051] In one embodiment, as Figure 2 shown, the transformation of the segment-level spill (i, j) into the O&D itinerary spill value spill(i) includes taking the maximum value of the segment spills in the O&D itinerary as the O&D itinerary spill value, i.e., spill(i) = max j [spill(i, j)]. If spill(i) - spill(i, j) = Δ > 0, then spill(j) needs to be changed to

[0052] In this way, after n itineraries

[0053]

[0054] In one embodiment, as Figure 2 shown, in itinerary 5, the spills of CA855 and CA174 in the SYD-LHR itinerary are: Spill(5, CA855) = 0.69, Spill(5, CA174) = 0.78, then Spill(5) = max(0.69, 0.78) = 0.78. The O&D itinerary SYD-LHR spill value is 0.78. Similarly, the spill values of all 584 itineraries can be calculated. See the Spill column in Table 1. There are a total of 25 spill values for the itineraries that only fly through CA855. There are 25 spilled passengers flying through flight CA855 in the Spillpool. Similarly, the spills of all spilled flights are put into the spill pool spillpool as the size for re-capture related to the O&D market size.

[0055] The passenger flow of the itinerary with spill traffic(i) = demand(i) - spill(i).

[0056] Next, proceed to step S5. In step S5, for all itineraries in the common O&D market spill resource pool (spillpool), after deleting all full-capacity itineraries, redefine the TOW curve of the spill pool, and then use the itinerary attributes and the redefined TOW curve of the spill pool. Using the Logit model, calculate the new market share of the remaining itineraries and the re-capture itinerary demand is equal to the product of the new market share of the itinerary and the SPILLPOOL.

[0057] In one embodiment, a fully-booked itinerary is defined as an itinerary with at least one fully-booked flight segment. A flight segment is considered fully-booked when the number of passengers on the flight exceeds capacity * LFCF * PCR, where capacity is the total number of seats on the aircraft, the Passenger Capacity Ratio (PCR) is generally defined in the industry as 0.98, and the Load Factor at Capacity Factor (LFCF) is 0.95 when there is passenger spillage.

[0058] In one embodiment, the probability of Take-Off Weight (TOW = j) p(t) for each market is equal to the ratio of the value of Spill (flight departing at j hours) to SPILLPOOL.

[0059]

[0060] The logit model is nested by time, dividing a week into 168 discrete points, i.e., discrete integer-hour times t = 0, 1,..., 167.

[0061] In one embodiment, as Figure 3 shown, the TOW probability of spillage from a flight departing at j hours is redistributed to the curve values of the Take-Off Weight (TOW) for the origin-destination (O&D) market at integer hours. Suppose the spillage value of a flight is spill(dep), T and T + 1 are integer-hour times, the flight departure time is mm minutes away from the integer hour time, and 60 - mm minutes away from the integer hour time T + 1. Then, according to the proportional distribution principle, the number of spillage passengers allocated to the integer hour is:

[0062] Spill(T) = (60 - mm) / 60 * spill(dep),

[0063] Spill(T + 1) = mm / 60 * spill(dep),

[0064] satisfying spill(T) + Spill(T + 1) = spill(dep).

[0065] Using the nested logit model, the passenger utility function value is mapped to the percentage share of itinerary ms(i). It is divided by the departure time of the SPILLPOOL itinerary, starting from 0:00 on Sunday of a typical week, with a time interval of 1 hour, until 23:00 on Saturday, for a total of 24 * 7 = 168 time points. Through the SPILLPOOL data statistics, the passenger flow ratio p(t) at each point is calculated. The market share of a certain itinerary i among the remaining k SPILLPOOL itineraries after removing fully-booked itineraries is calculated. The specific mathematical expression is While satisfying the market share integrity requirement, the mathematical expression of the utility function is U i,t = β 1 X 1t +…+ β n Xnt , where p(t) is the proportion of the passenger flow of the TOW of the SPILLPOOL itinerary at time t, where X 1t ,..., X nt may be a dynamic attribute, related to time t, or a static attribute, unrelated to time t. That is to say, the passenger itinerary market share is determined by the passenger preference attributes.

[0066] Illustratively, as shown in Table 1 and Figure 3 shown, for itinerary 1, i.e., PEK-LHR, there are 1.57 spillover passengers. The departure time of this itinerary is 16:15. Restored to 16:00 in the TOW, p(t) = 45 / 60 * 1.57 = 1.18, and at 17:00, p(t) = 15 / 60 * 1.57 = 0.39. According to the Logit model, the remaining itinerary allocation in the O&D market of PEK-LHR is calculated. If PEK-FRT-LHR is not full, the 1.57 passengers can be recaptured on the PEK-FRT-LHR flight of this itinerary. For itinerary 13, i.e., SHE-LHR (CA1652 / CA855), there are 3.39 spillover passengers, and for itinerary 14, i.e., SHE-LHR (CA1602 / CA855), there are 3.22 spillover passengers. The departure time of CA1652 flight is 11:45, and the departure time of CA1602 flight is 10:55. Restored to 10 o'clock in the TOW, p(t) = 5 / 60 * 3.22 = 0.27, at 11 o'clock in the TOW, p(t) = 55 / 60 * 3.22 + 15 / 60 * 3.39 = 3.80, and at 12 o'clock in the TOW, p(t) = 15 / 60 * 3.39 = 0.85. In this way, ms(i) and the number of recaptured passengers recapture(i) are calculated according to the Logit model.

[0067] Next, enter step S6. In step S6, no longer considering the passenger flow traffic of the remaining itinerary after re-acquiring the full flight is the sum of the recapture itinerary demand and the original demand.

[0068] In one embodiment, as Figure 4 shown, there are spillover passengers in the O&D market in the spillpool, and the remaining itinerary in the same O&D market is used to recapture the passengers in the spillpool, and the share of recapture is calculated:

[0069]

[0070] The recaptured passengers are

[0071] Recapture(i) = ms(i) * spillpool

[0072] Thus, the remaining itinerary passenger flow traffic(i) = demand(i) + recapture(i).

[0073] In step S1, all itinerary demands demand(i), which are also the original itinerary demands, can be calculated according to the Logit model. In step S2, for the flight j, for all n itineraries passing through flight j, the total demand of flight j is calculated, that is And the spill spill(j) of flight j is calculated. In step S3, the flight spill is allocated to the n itineraries passing through the flight, that is Spill(i,j). In step S4, each segment-level spill spill(i,j) in the O&D itinerary is transformed into the O&D itinerary spill value spill(i) = max j [spill(i,j)]. The passengers overflowing from all itineraries in the O&D market are aggregated into a common O&D market overflow resource pool (spillpool). In step S5, for all itineraries in the common O&D market overflow resource pool (spillpool), after deleting all full-capacity itineraries, the redefined overflow pool TOW curve is used, and then using the itinerary attributes and the redefined overflow pool TOW curve, the Logit model is used to calculate the new market share of the remaining itineraries and the recapture itinerary demand is equal to the product of the new market share of the itinerary and the SPILLPOOL. Thus, there is

[0074] Dmd = demand(i),

[0075] Traffic = demand(i) - spill(i) + recapture(i).

[0076] In an embodiment, the itinerary market share Mkt share, itinerary demand dmd, itinerary spill spill, passenger flow traffic, and recaptured passengers Recap as shown in Table 1 are obtained.

[0077] Corresponding to the application scenario and method of the method provided in the embodiments of the present application, an embodiment of the present application further provides a system for passenger overflow and recapture based on the passenger selection Logit model, and the system is deployed on a computer device. The following will refer to Figure 5 The system for passenger overflow and recapture based on the passenger selection Logit model of the present application will be described. Figure 5 It is a structural block diagram showing the system for passenger overflow and recapture based on the passenger selection Logit model of an embodiment of the present application. As Figure 5As shown in the figure, the passenger spillover and recapture system 500 based on the passenger choice Logit model may include: a trip demand module 501, a flight spillover module 502, a spillover allocation module 503, a trip spillover module 504, a recapture module 505, and a trip demand correction module 506.

[0078] The trip demand module 501 is used to predict the demand for O&D trips based on the known passenger choice Logit model, and obtain the O&D trip demand demand(i) for the flight segment (or flight).

[0079] The flight spillover module 502 is used to calculate the total demand demand(j) for the flight segment (or flight) and the effective capacity of the aircraft flying the flight, and calculate the total number of flight passenger spillovers spill(j) for the flight segment according to the Spill model.

[0080] The spillover allocation module 503 is used to allocate the total number of spillovers spill(j) of the flight to the flights in the trip according to certain rules, and obtain the spill value Spill(i,j) of each flight in the trip.

[0081] The trip spillover module 504 is used to transform the spill of each flight segment in the O&D trip into the O&D trip spill value spill(i), and summarize all the spilled passengers in the O&D market into a common O&D market spill resource pool (spillpool).

[0082] The recapture module 505 is used to redefine the TOW curve of the spill pool after deleting all full trips for all trips in the common O&D market spill resource pool (spillpool), and then use the trip attributes and the redefined TOW curve of the spill pool, and use the Logit model to calculate the new market share of the remaining trips and the recapture trip demand is equal to the product of the new market share of the trip and the SPILLPOOL.

[0083] The trip demand correction module 506 is used to no longer consider that the new demand for the remaining trips after re-acquiring the full flights is the sum of the recapture trip demand and the original demand.

[0084] For the functions of the modules in each system of the embodiments of the present application, reference may be made to the corresponding descriptions in the above methods, and they have corresponding beneficial effects, which will not be elaborated here.

[0085] Figure 6 is a block diagram showing an electronic device according to an embodiment of the present application. As Figure 6As shown, the electronic device includes: a memory 601 and a processor 602. The memory 601 stores a computer program that can run on the processor 602. When the processor 602 executes the computer program, the method in the above embodiment is implemented. The number of the memory 601 and the processor 602 can be one or more.

[0086] The electronic device further includes: a communication interface 603, configured to communicate with external devices and perform data interaction and transmission.

[0087] If the memory 601, the processor 602, and the communication interface 603 are implemented independently, the memory 601, the processor 602, and the communication interface 603 can be interconnected through a bus and complete communication with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 6 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0088] Optionally, in specific implementation, if the memory 601, the processor 602, and the communication interface 603 are integrated on a chip, the memory 601, the processor 602, and the communication interface 603 can complete communication with each other through an internal interface.

[0089] It should be understood that the above processor can be a Central Processing Unit (CPU), or can also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. It is worth noting that the processor can be a processor that supports the Advanced RISC Machines (ARM) architecture.

[0090] 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 memories. 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 example but not limitation, 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 (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus random access memory (DR RAM).

[0091] In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it may 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 processes or functions according to the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0092] In the description of this specification, the descriptions with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0093] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" can explicitly or implicitly include at least one of such features. In the description of this application, "a plurality of" means two or more unless otherwise specifically defined.

[0094] Any process or method described in the flowchart or otherwise described herein can be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a specific logical function or process. And the scope of the preferred embodiments of this application includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in a reverse order according to the involved functions, rather than in the order shown or discussed.

[0095] The logic and / or steps described in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing a logical function, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, system, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with such instruction execution systems, apparatuses, or devices.

[0096] It should be understood that each part of this application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the method in the above embodiments can be completed by a program instructing relevant hardware, and this program can be stored in a computer-readable storage medium. When this program is executed, it includes one or a combination of the steps of the method embodiment.

[0097] In addition, in each embodiment of the present application, each functional module can be integrated into one processing module, or each module can exist physically alone, or two or more modules 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 magnetic disk, an optical disc, etc.

[0098] As mentioned above, it is only an exemplary embodiment of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope recorded in the present application can easily think of various changes or substitutions, and these should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A passenger spillover and recapture method based on passenger selection logit model, characterized in that the steps include: Step S1, predicting the demand for O&D itineraries based on a known passenger selection Logit model, and obtaining the demand for O&D itineraries that fly through the flight segment (or flight); Step S2, calculating the total demand for the flight segment (or flight) and the effective capacity of the aircraft operating the flight, and calculating the total number of passengers overflowing from the flight segment according to the Spill model; Step S3, allocating the total overflow passengers of the flight to the flights in the itinerary according to a certain rule, and obtaining the overflow value of the flight in each itinerary; Step S4, transforming each segment-level overflow in the O&D itinerary into the O&D itinerary overflow value, and aggregating passengers with overflow from all itineraries in the O&D market into a common O&D market overflow resource pool (spillpool); Step S5, deleting all full trips from all trips in the common O&D market spillover resource pool (spillpool) to redefine the TOW curve of the spillover pool, and then using the trip attributes and the redefined TOW curve of the spillover pool to calculate the new market share of the remaining trips and the recapture trip demand by using the Logit model, which is equal to the product of the new market share of the trip and the spillpool; Step S6, the remaining itinerary passenger flow traffic after reacquiring the full flight is no longer considered, which is the sum of the recaptured itinerary demand and the original demand.

2. The method according to claim 1, characterized in that The Spill model includes: The Spill model is composed of the effective capacity when the aircraft is fully occupied, the average passenger load factor LFCF when passengers overflow, and the probability of passengers boarding the aircraft. The passenger overflow Spill model can be used to calculate the passenger overflow value, where the effective capacity = the average passenger load factor LFCF when passengers overflow * the total number of seats on the aircraft.

3. The method according to claim 1, characterized in that The certain rule allocation includes: The spill(j) of the flight segment is distributed to the spill(i,j) of the flight segment passing through it in proportion to the demand of the O&D itinerary and inversely proportional to the unit fare. The calculation method is:

4. The method according to claim 1, characterized in that: The transformation of the segment-level overflow spill(i,j) into the O&D trip overflow value spill(i) includes: The maximum value of the overflow of the flight segments in the O&D itinerary is taken as the O&D itinerary overflow value, that is, spill(i) = max j [spill(i,j)].

5. The method according to claim 1, characterized in that The full itinerary specifically includes: A full itinerary is defined as an itinerary with at least one full flight segment. A full flight segment means that the number of passengers on the flight exceeds capacity*LFCF*PCR, where capacity is the total number of seats on the aircraft. The industry generally defines the passenger capacity ratio PCR as 0.98, and the average passenger load factor LFCF when there is passenger overflow is 0.

95.

6. The method according to claim 1, characterized in that The redefinition of the TOW curve includes: The TOW probability (TOW=j) of each market is equal to the ratio of Spill (flight departing at hour j) value to SPILLPOOL. The logit model is nested by time, dividing a week into 168 discrete points, i.e., discrete hourly times t=0, 1, ..., 167.

7. The method according to claim 1, characterized in that The logit model specifically includes: The logit function is used to map the passenger utility function value to the trip share percentage ms(i). The passenger trip market share is determined by the passenger preference attributes, and its specific mathematical expression is: The mathematical expression of the utility function is U i,t =β1X 1t +Σ+β n X nt , p(t) is the passenger flow ratio of TOW of the trip at time t, where X 1t ,...,X nt It may be a dynamic attribute related to TOW time t, or it may be a static attribute independent of TOW time t.

8. The method according to claim 1, characterized in that: The recapture trip requirements include: The recaptured itinerary demand is equal to the product of the itinerary's new market share and SPILLPOOL; if there is spillover in the recaptured segment, the passenger spillover needs to be recalculated until one of the following conditions is met: - There are no passengers in the SPILLPOOL, or - all trips in the market are full as stated, or -After a certain number of iterations.

9. A passenger spillover and recapture system based on passenger choice logit model, characterized in that: The system comprises: The itinerary demand module is used to predict the demand for O&D itineraries based on the known passenger selection Logit model, and obtain the O&D itinerary demand demand(i) passing through the flight segment (or flight). The flight overflow module is used to calculate the total demand demand(j) of the flight segment (or flight) and the effective capacity of the aircraft operating the flight, and calculate the total number of flight passenger overflow spill(j) of the flight segment based on the Spill model. The overflow allocation module is used to allocate the total overflow number of the flight, spill(j), to the flights in the itinerary according to a certain rule, and obtain the overflow value Spill(i, j) of the flight in each itinerary. The itinerary overflow module is used to transform each segment-level overflow spill(i,j) in the O&D itinerary into the O&D itinerary overflow value spill(i), and aggregate all itinerary overflow passengers in the O&D market into a common O&D market overflow resource pool (spillpool). The recapture module is used to redefine the TOW curve of the spill pool after deleting all full trips from all trips in the common O&D market spill pool, and then use the trip attributes and the redefined TOW curve of the spill pool to calculate the new market share of the remaining trips and the recapture trip demand by the Logit model, which is equal to the product of the new market share of the trip and the SPILLPOOL. The itinerary demand correction module is used to no longer consider the remaining itinerary new demand after re-acquiring the full flight, which is the sum of the re-captured itinerary demand and the original demand.

10. 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 8 when executing the computer program.

Images