Flight timetable optimization method and device, electronic equipment and storage medium

Abstract

The invention discloses a flight timetable optimization method and device, electronic equipment and a storage medium, and relates to the technical field of aviation, and the method comprises the steps: obtaining candidate flight time pairs of all airlines; determining a candidate scheme according to the candidate flight time pair; the candidate schemes comprise flight time pairs and candidate flight time pairs configured for each flight route in the historical flight time table; for each candidate scheme, calculating a first revenue according to the revenue of each route in the candidate scheme; wherein the income of each air route is obtained based on prediction of a first model, and the first model is further used for predicting the income of the air route at least according to the flight time pair and the candidate flight time pair; and determining a target scheme according to the first income of each candidate scheme. On the basis, the operation efficiency of the airline company can be improved, the aviation resource configuration is optimized, and the income of the airline company is maximized.

Description

Technical Field

[0001] This application relates to the field of aviation technology, and in particular to a method, apparatus, electronic device and storage medium for optimizing flight schedules. Background Technology

[0002] With the rapid development of the global air transport market, airlines are facing an increasingly competitive environment. The contradiction between passenger demand and existing capacity is becoming more and more prominent, resulting in airlines' existing flight schedules being unable to meet the ever-changing passenger demand. While popular routes are hard to come by, less popular routes have high vacancy rates, thus affecting the airlines' revenue.

[0003] Therefore, there is an urgent need for a flight schedule optimization method to improve airline operational efficiency, optimize resource allocation, and maximize revenue through flight schedule optimization. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and storage medium for optimizing flight schedules, which can improve the operational efficiency of airlines, optimize resource allocation, and thereby maximize revenue.

[0005] In a first aspect, this application provides a flight schedule optimization method, comprising: obtaining candidate flight time pairs for each route; wherein, the flight time pair includes the departure time and arrival time of the flight; the candidate flight time pairs are determined based on the flight time pair increments for each route; the flight time pair increments for each route are predicted based on a first model, the first model being used to predict the flight time pair increments for the route based on at least one of the historical passenger volume, flight frequency, and aircraft type; determining candidate schemes based on the candidate flight time pairs; the candidate schemes include flight time pairs configured for each route in the historical flight schedule and candidate flight time pairs; calculating a first benefit for each candidate scheme based on the benefit of each route in the candidate scheme; wherein, the benefit of each route is predicted based on the first model, the first model being used to predict the benefit of the route based on at least the flight time pairs and candidate flight time pairs; and determining a target scheme based on the first benefit of each candidate scheme.

[0006] This application determines candidate flight schedules by obtaining candidate flight time pairs for each route. For each candidate schedule, a first revenue is calculated based on the revenue of each route within the candidate schedule. By comparing the first revenues, a target schedule is determined as the optimized flight timetable. Based on this, the operational efficiency of airlines can be improved, the allocation of aviation resources can be optimized, and thus airlines can maximize their revenue.

[0007] One possible implementation, the above "calculating the first benefit based on the benefits of each route in each candidate scheme" specifically includes: calculating the first benefit for each candidate scheme according to a pre-defined objective function; wherein the objective function is as follows:

[0008]

[0009] Where I represents the set of routes; J represents the set of flight time pairs; j represents a flight time pair; K represents the set of flight time pairs; R ij X represents the benefit of configuring flight times for route i to route j; ij =1 indicates that flight schedule pair j has been configured for route i; otherwise, X ij =0; y k =0 indicates that flight time k has been reassigned; otherwise, y k =1; R k,r Let r represent the revenue of flight time k itself; L represent the historical flight timetable; R′ represent the revenue of flight time k itself. ij This represents the benefit of configuring flight times for route i on route j in the historical flight timetable; X′ ij =1 indicates that route i in the historical flight timetable has been configured with flight time pair j; otherwise, X′ ij =0.

[0010] Another possible implementation is that the flight schedule satisfies either a first flight time constraint or a second flight time constraint; the first flight time constraint indicates that the sum of the flight's departure time and flight time is less than or equal to the flight's arrival time; the second flight time constraint indicates that the sum of the flight's departure time and flight time is less than or equal to the sum of the flight's arrival time and a preset flexible time.

[0011] Another possible implementation includes a first candidate scheme and a second candidate scheme; the first candidate scheme is the candidate scheme under the condition that the flight time constraint is satisfied; the second candidate scheme is the candidate scheme under the condition that the flight time constraint is satisfied.

[0012] Another possible implementation, the above method further includes: determining a first target scheme based on the first benefit of each first candidate scheme; determining the incremental demand routes in each first candidate scheme; the incremental demand routes represent routes with candidate flight time pairs; for each first candidate scheme, rewarding each incremental demand route in the first candidate scheme according to a preset rule to determine a second benefit; the second benefit is obtained based on the first benefit and the benefit reward; the preset rule represents the relationship between the benefits of candidate flight time pairs and candidate flight time pairs; determining a second target scheme based on the second benefit of each first candidate scheme; and determining a first optimization scheme based on the first benefit of the first target scheme and the second benefit of the second target scheme.

[0013] Another possible implementation, the above method further includes: determining a third target scheme based on the first benefit of each second candidate scheme; determining the incremental demand routes in each second candidate scheme; for each second candidate scheme, awarding a benefit to each incremental demand route in the second candidate scheme according to a preset rule to determine a third benefit; the third benefit is obtained based on the first benefit and the benefit award; determining a fourth target scheme based on the third benefit of each second candidate scheme; and determining a second optimization scheme based on the first benefit of the third target scheme and the third benefit of the fourth target scheme.

[0014] Another possible implementation is that the route needs to meet the flight frequency constraint; the flight frequency constraint indicates that the flight frequency of the route is less than or equal to the maximum flight frequency of the route.

[0015] Secondly, this application provides a flight schedule optimization apparatus, comprising: an acquisition unit, configured to acquire candidate flight time pairs for each route; wherein the flight time pair includes the departure time and arrival time of the flight; the candidate flight time pairs are determined based on the flight time pair increments for each route; the flight time pair increments for each route are predicted based on a first model, the first model being used to predict the flight time pair increments for the route based on at least one of the historical passenger volume, flight frequency, and aircraft type; a determination unit, configured to determine candidate schemes based on the candidate flight time pairs; the candidate schemes include flight time pairs configured for each route in the historical flight schedule and candidate flight time pairs; a calculation unit, configured to calculate a first benefit for each candidate scheme based on the benefit of each route in the candidate scheme; wherein the benefit of each route is predicted based on the first model, the first model being used to predict the benefit of the route based on at least the flight time pairs and candidate flight time pairs; and a determination unit, further configured to determine a target scheme based on the first benefit of each candidate scheme.

[0016] One possible implementation involves a computational unit specifically used to calculate the first benefit for each candidate solution based on a pre-defined objective function; wherein the objective function is as follows:

[0017]

[0018] Where I represents the set of routes; J represents the set of flight time pairs; j represents a flight time pair; K represents the set of flight time pairs; R ij X represents the benefit of configuring flight times for route i to route j; ij =1 indicates that flight schedule pair j has been configured for route i; otherwise, X ij =0; y k =0 indicates that flight time k has been reassigned; otherwise, y k =1; R k,rLet r represent the revenue of flight time k itself; L represent the historical flight timetable; R′ represent the revenue of flight time k itself. ij This represents the benefit of configuring flight times for route i on route j in the historical flight timetable; X′ ij =1 indicates that route i in the historical flight timetable has been configured with flight time pair j; otherwise, X′ ij =0.

[0019] Another possible implementation is that the flight schedule satisfies either a first flight time constraint or a second flight time constraint; the first flight time constraint indicates that the sum of the flight's departure time and flight time is less than or equal to the flight's arrival time; the second flight time constraint indicates that the sum of the flight's departure time and flight time is less than or equal to the sum of the flight's arrival time and a preset flexible time.

[0020] Another possible implementation includes a first candidate scheme and a second candidate scheme; the first candidate scheme is the candidate scheme under the condition that the flight time constraint is satisfied; the second candidate scheme is the candidate scheme under the condition that the flight time constraint is satisfied.

[0021] Another possible implementation involves a determining unit, specifically configured to: determine a first target scheme based on the first benefit of each first candidate scheme; determine the incremental demand routes in each first candidate scheme; the incremental demand routes represent routes with candidate flight time pairs; for each first candidate scheme, award a benefit to each incremental demand route in the first candidate scheme according to a preset rule to determine a second benefit; the second benefit is obtained based on the first benefit and the benefit award; the preset rule represents the relationship between the benefits of candidate flight time pairs; determine a second target scheme based on the second benefit of each first candidate scheme; and determine a first optimization scheme based on the first benefit of the first target scheme and the second benefit of the second target scheme.

[0022] Another possible implementation involves a determining unit that is further configured to: determine a third target scheme based on the first benefit of each second candidate scheme; determine the incremental demand routes in each second candidate scheme; award a benefit to each incremental demand route in each second candidate scheme according to a preset rule, and determine a third benefit; the third benefit is obtained based on the first benefit and the benefit award; determine a fourth target scheme based on the third benefit of each second candidate scheme; and determine a second optimization scheme based on the first benefit of the third target scheme and the third benefit of the fourth target scheme.

[0023] Another possible implementation is that the route needs to meet the flight frequency constraint; the flight frequency constraint indicates that the flight frequency of the route is less than or equal to the maximum flight frequency of the route.

[0024] Thirdly, this application provides an electronic device comprising: a processor and a memory; the memory storing processor-executable instructions; when the processor is configured to execute the instructions, causing the electronic device to implement the method of the first aspect described above.

[0025] Fourthly, this application provides a computer-readable storage medium comprising: computer software instructions; which, when executed in an electronic device, cause the electronic device to implement the method described in the first aspect.

[0026] Fifthly, this application provides a computer program product comprising a computer program; when the computer program is run in an electronic device, the electronic device performs the method described in the first aspect.

[0027] The beneficial effects of the second to fifth aspects mentioned above are described in the corresponding description of the first aspect and will not be repeated here. Attached Figure Description

[0028] Figure 1 A flowchart illustrating a flight timetable optimization method provided in this application embodiment;

[0029] Figure 2 A flowchart illustrating another flight timetable optimization method provided in this application embodiment;

[0030] Figure 3 A flowchart illustrating another flight timetable optimization method provided in this application embodiment;

[0031] Figure 4 A schematic diagram of the composition of a flight timetable optimization device provided in this application embodiment;

[0032] Figure 5 This is a schematic diagram of the composition of an electronic device provided in an embodiment of this application. Detailed Implementation

[0033] The following section will describe in detail a flight timetable optimization method provided in this application, with reference to the accompanying drawings.

[0034] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0035] The terms "first" and "second," etc., used in the specification and drawings of this application are used to distinguish different objects or to distinguish different treatments of the same object, rather than to describe a specific order of objects.

[0036] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.

[0037] It should be noted that in the embodiments of this application, the words "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0038] To facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish the same or similar items with essentially the same function and effect. Those skilled in the art can understand that the terms "first" and "second" are not intended to limit the quantity or execution order.

[0039] In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0040] With the rapid development of the global air transport market, airlines face an increasingly competitive environment, and the contradiction between passenger demand and existing capacity is becoming more and more prominent, resulting in existing flight schedules being unable to meet ever-changing passenger demands. During airline operations, there are often situations where tickets for popular routes are hard to come by, while less popular routes have high vacancy rates, which can lead to revenue losses for airlines.

[0041] To address the aforementioned technical problems, this application provides a flight schedule optimization method, apparatus, electronic device, and storage medium. The approach involves: acquiring candidate flight time pairs for each route and determining candidate schemes based on these pairs; calculating a first benefit for each candidate scheme based on the benefits of each route within that scheme; and determining a target scheme based on the first benefits of each candidate scheme. This approach can improve airline operational efficiency, optimize aviation resource allocation, and ultimately maximize airline revenue.

[0042] The embodiments provided in this application will now be described in detail with reference to the accompanying drawings.

[0043] See Figure 1 This is a flowchart illustrating a flight timetable optimization method provided in an embodiment of this application. Figure 1As shown, the flight timetable optimization method provided in this application specifically includes the following steps S101-S104.

[0044] S101: Obtain candidate flight time pairs for each route; wherein, the flight time pair includes the departure time and arrival time of the flight; the candidate flight time pairs are determined based on the flight time pair increments for each route; the flight time pair increments for each route are predicted based on a first model, which is used to predict the flight time pair increments for a route based on at least one of the following: historical passenger volume, flight frequency, and aircraft type.

[0045] In some embodiments, the incremental flight time pairs for each route will differ due to varying passenger demand. Therefore, for each route, the incremental flight time pairs can be predicted separately using the first model. Then, based on the incremental flight time pairs for each route, a corresponding number of flight time pairs are selected as candidate flight time pairs.

[0046] It is understandable that there may be multiple unused flight time pairs on each route. Therefore, when selecting flight time pairs as candidate flight time pairs, multiple candidate flight time pairs can be obtained.

[0047] In some embodiments, the first model is used to predict the incremental flight time pairs for a flight route. The first model is trained by constructing a predictive feature set that influences passenger demand for flights. For example, the first model may be a TIME-LLM model.

[0048] Specifically, as shown in Table 1, the quantitative indicators and calculation formulas affecting passenger demand for flights are presented.

[0049] Table 1

[0050]

[0051]

[0052] As shown in Table 1, by extracting, processing, and transforming key information from Table 1, such as GDP, average ticket price, population size, high-speed rail competition index, number of tourists, destination attractiveness index, proportion of business travelers, and punctuality rate, a passenger demand forecasting feature set is constructed. This passenger demand forecasting feature set includes route distance, departure time, aircraft type, average ticket price, timetable fulfillment rate, destination GDP, high-speed rail competition index, and flight frequency.

[0053] Furthermore, based on the passenger demand prediction feature set, a first model is trained so that the first model can predict the incremental flight schedule of a route based on at least one of the following: historical passenger numbers, flight frequency, and aircraft type.

[0054] Thus, the first model can achieve high prediction accuracy in a short period of time. Moreover, the model can not only predict multiple features to multiple features, but also multiple features to single features, and can also predict a future point in time or multiple future points in time.

[0055] S102: Determine candidate schemes based on candidate flight time pairs; candidate schemes include flight time pairs configured for each route in the historical flight timetable and candidate flight time pairs.

[0056] In some embodiments, candidate schemes are determined based on candidate flight time pairs. Since there may be multiple candidate flight time pairs, there may also be multiple candidate schemes. Each candidate scheme includes route time pairs configured for each route in the historical flight timetable and candidate flight time pairs.

[0057] Specifically, the historical flight timetable is the flight timetable before optimization. When the route time pairs configured in the historical flight timetable cannot meet passenger demand, the historical flight timetable is optimized based on the candidate flight time pairs determined by the incremental flight time pairs of each route, and candidate solutions are generated.

[0058] S103: For each candidate scheme, calculate the first revenue based on the revenue of each route in the candidate scheme; wherein, the revenue of each route is predicted based on the first model, and the first model is also used to predict the revenue of the route at least based on the flight time pair and the candidate flight time pair.

[0059] In some embodiments, the first model is further used to predict the revenue of each route. The first model can also be trained by constructing a predictive feature set that influences the revenue of each route.

[0060] Specifically, as shown in Table 2, the quantitative indicators and calculation formulas that affect route revenue are presented.

[0061] Table 2

[0062]

[0063] As shown in Table 2, by extracting, processing, and transforming key information from Table 2, such as route revenue, flight frequency, available seat kilometers, revenue per seat kilometer, frequent flyer revenue share, total market demand, business traveler share, and on-time performance, a route revenue prediction feature set is constructed. This feature set includes route distance, departure time, aircraft type, load factor, average ticket price, on-time performance, destination GDP, and flight frequency.

[0064] Furthermore, based on the route revenue prediction feature set, a first model is trained so that the first model can predict the route revenue at least based on the flight time pairs and candidate flight time pairs.

[0065] The prediction accuracy of the first model can be determined using its coefficient of determination, mean absolute error, and mean error deviation. The coefficient of determination measures the model's ability to explain data variability. It is calculated by comparing the mean squared error between predicted and actual values, reflecting the proportion of data variance explained by the model. Its value ranges from 0 to 1; the closer the value is to 1, the better the model fits the data and the stronger its explanatory power.

[0066] Mean Absolute Error (MAO) is the average of the absolute errors between predicted and actual values, used to measure the average accuracy of a model's predictions. It is calculated by averaging the absolute values ​​of the differences between each predicted and actual value. The closer the MAO is to 0, the closer the model's prediction is to the actual value, and the smaller the error.

[0067] Mean error deviation (MEP) is the average error between predicted and actual values. It measures the systematic bias of a model by averaging the differences between the predicted and actual values. A positive value indicates that the model overestimates, while a negative value indicates that the model underestimates. Ideally, MEP should be close to zero, indicating that the model has no systematic bias.

[0068] S104: Determine the target solution based on the first benefit of each candidate solution.

[0069] In some embodiments, the first benefit of each candidate solution is compared, and the candidate solution with the highest first benefit is determined as the target solution.

[0070] Based on this, the flight schedule optimization method provided in this application determines candidate schemes by obtaining candidate flight schedule pairs for each route. For each candidate scheme, a first benefit is calculated based on the revenue of each route within the candidate scheme. By comparing the first benefits, a target scheme is determined as the optimized flight schedule. This method can improve the operational efficiency of airlines, optimize the allocation of aviation resources, and thus maximize the revenue of airlines.

[0071] In one possible implementation, for each candidate solution, the first benefit is calculated according to a pre-defined objective function; wherein the objective function is specifically shown in Formula 1:

[0072]

[0073] Where I represents the set of routes; J represents the set of flight time pairs; j represents a flight time pair; K represents the set of flight time pairs; R ij X represents the benefit of configuring flight times for route i to route j; ij =1 indicates that flight schedule pair j has been configured for route i; otherwise, X ij =0; y k=0 indicates that flight time k has been reassigned; otherwise, y k =1; R k,r Let r represent the revenue of flight time k itself; L represent the historical flight timetable; R′ represent the revenue of flight time k itself. ij This represents the benefit of configuring flight times for route i on route j in the historical flight timetable; X′ ij =1 indicates that route i in the historical flight timetable has been configured with flight time pair j; otherwise, X′ ij =0.

[0074] Specifically, the objective function characterizes the candidate solution's ability to maximize incremental revenue based on historical flight schedules. Based on the objective function, the first revenue for each candidate solution can be calculated.

[0075] It should be noted that when the number of unused flight slot pairs on each route is less than the increase in flight slot pairs, the demand for additional flight slot pairs can be met by setting flight slots. Correspondingly, if there are configured flight slots in the candidate solutions, the revenue from those flight slots themselves needs to be added to the first revenue of the candidate solutions.

[0076] In some embodiments, the configuration of flight time pairs needs to satisfy uniqueness and mutual exclusion constraints. The uniqueness constraint means that each flight time pair can only be configured once. The mutual exclusion constraint means that the configuration and discarding of each flight time pair are mutually exclusive.

[0077] Specifically, the uniqueness constraint is shown in Formula 2:

[0078]

[0079] The mutual exclusion constraint is shown in Formula 3:

[0080]

[0081] Where, x ij =1 indicates that flight schedule pair j has been configured for route i; otherwise, x = 1. ij =0; y ij =1 indicates that route i has discarded flight time pairs j; otherwise, y = 1. ij =0.

[0082] Based on the aforementioned technical methods, the first benefit of each candidate solution can be calculated using a pre-defined objective function. This allows for a more direct demonstration of the merits of each candidate solution, thereby accurately determining the target solution.

[0083] In one possible implementation, the flight schedule satisfies either a first flight time constraint or a second flight time constraint; the first flight time constraint indicates that the sum of the flight's departure time and flight time is less than or equal to the flight's arrival time; the second flight time constraint indicates that the sum of the flight's departure time and flight time is less than or equal to the sum of the flight's arrival time and a preset flexible time.

[0084] In some embodiments, the flight time of a flight timetable needs to meet the airline's requirements; that is, the on-time departure rate of flights on the route needs to meet the airline's requirements. The on-time departure rate refers to the proportion of flights that depart within a preset time range to the total number of flights. The preset time range may include a preset flexible time; for example, the preset flexible time may be plus or minus 15 minutes.

[0085] Specifically, flight schedules must satisfy either the first flight time constraint or the second flight time constraint. The first flight time constraint is detailed in Formula 4:

[0086]

[0087] Where t represents flight number, D t Indicates the departure time of flight t; F t A represents the flight time of flight t; t This indicates the arrival time of flight t.

[0088] The second flight time constraint is specifically shown in Formula 5:

[0089]

[0090] Based on the aforementioned technical means, by constraining the flight time of the flight schedule and considering the preset flexible time, the overall flight departure punctuality rate will not be reduced. In addition, the search range of the optimal solution can be expanded, resulting in more diverse flight schedule optimization schemes and making the optimization results more accurate.

[0091] In one possible implementation, the candidate solutions include a first candidate solution and a second candidate solution; the first candidate solution is the candidate solution under the condition that the flight time constraint is satisfied; the second candidate solution is the candidate solution under the condition that the flight time constraint is satisfied.

[0092] Specifically, the candidate solutions obtained for flight time pairs differ depending on whether they satisfy the first or second flight time constraint. Because the second flight time constraint takes into account a preset flexible time, the search range for flight time pairs is expanded, resulting in more candidate solutions compared to the first constraint.

[0093] However, having more candidate solutions does not necessarily mean that the final target solution will have a higher return. Therefore, it is necessary to calculate the returns for the two different scenarios separately in order to determine the solution with higher returns.

[0094] See Figure 2 This is a flowchart illustrating another flight timetable optimization method provided in an embodiment of this application. Figure 2 As shown, the flight timetable optimization method also includes the following steps S201-S205.

[0095] S201: Determine the first target solution based on the first benefit of each first candidate solution.

[0096] Specifically, the first benefits of each first candidate solution are compared, and the first candidate solution with the highest first benefit is selected as the first target solution.

[0097] S202: Determine the incremental demand routes in each first candidate scheme; the incremental demand routes represent routes with candidate flight time pairs.

[0098] Specifically, routes with candidate flight time pairs added to the first candidate scheme will be identified as routes with increased demand.

[0099] Furthermore, if there are no candidate flight time pairs in the route, but there are flight times, then this route can also be identified as a route with increased demand.

[0100] S203: For each first candidate scheme, the revenue reward for each incremental demand route in the first candidate scheme is determined according to the preset rules, and the second revenue is determined; the second revenue is obtained based on the first revenue and the revenue reward; the preset rules represent the relationship between the revenue of the candidate flight time pair and the candidate flight time pair.

[0101] Specifically, the revenue reward refers to adding an extra portion of revenue to routes with increased demand on top of the original revenue. This extra revenue is then added to the first revenue to obtain the second revenue for each of the first candidate routes.

[0102] S204: Determine the second objective solution based on the second benefit of each first candidate solution.

[0103] Specifically, the second benefits of each first candidate scheme are compared, and the first candidate scheme with the highest second benefit is selected as the second target scheme.

[0104] S205: Based on the first benefit of the first objective scheme and the second benefit of the second objective scheme, determine the first optimal scheme.

[0105] Specifically, the scheme with the highest benefit among the first benefit of the first objective scheme and the second benefit of the second objective scheme is determined as the first optimal scheme.

[0106] Based on this, the flight schedule optimization method provided in this application determines the first optimization scheme by separately determining the first benefit of the first objective scheme and the second benefit of the second objective scheme, thereby making the optimization accuracy of the flight schedule higher and maximizing the benefits for the airline.

[0107] See Figure 3 This is a flowchart illustrating another flight timetable optimization method provided in this application. Figure 3 As shown, the flight timetable optimization method also includes the following steps S301-S305.

[0108] S301: Determine the third objective solution based on the first benefit of each second candidate solution.

[0109] S302: Determine the incremental demand routes in each of the second candidate options.

[0110] S303: For each second candidate scheme, the revenue reward for each incremental demand route in the second candidate scheme is determined according to the preset rules to determine the third revenue; the third revenue is obtained based on the first revenue and the revenue reward.

[0111] S304: Determine the fourth objective solution based on the third benefit of each second candidate solution.

[0112] S305: Based on the first benefit of the third objective scheme and the third benefit of the fourth objective scheme, determine the second optimal scheme.

[0113] The specific implementation methods and technical effects of S301-S305 can be referred to the above embodiments, and will not be repeated here.

[0114] In some embodiments, the benefits of the first optimization scheme and the benefits of the second optimization scheme are compared, and the optimization scheme with the highest benefit is taken as the target optimization scheme.

[0115] Based on this, it can solve the problems of unpredictable passenger demand on popular routes, difficulty in adding new flights on popular routes, and poor revenue on routes. By optimizing flight schedules, optimal solutions can be obtained under various conditions, and each optimal solution is determined based on maximizing airline revenue. By selecting the target solution from the optimal solutions under various conditions, the airline's revenue can be maximized.

[0116] In one possible implementation, the flight route needs to meet the flight frequency constraint; the flight frequency constraint indicates that the flight frequency of the route is less than or equal to the maximum flight frequency of the route.

[0117] Specifically, the flight frequency for each route must meet the airline's regulations. This frequency includes both the historical flight schedule pairs and candidate flight schedule pairs for that route.

[0118] The specific flight frequency constraints are shown in Formula Six:

[0119]

[0120] Among them, F i This represents the maximum flight frequency for route i.

[0121] In some embodiments, if a route in the candidate scheme does not meet the flight frequency constraint, the first flight time constraint, and the second flight time constraint, the revenue of that route needs to be determined by reading the revenue of the flight time itself in that route.

[0122] As can be seen, the above mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, the embodiments of this application provide corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the modules and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.

[0123] This application embodiment can divide the flight timetable optimization device into functional modules according to the above method example. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0124] In some embodiments, this application also provides a flight schedule optimization apparatus. The flight schedule optimization apparatus may include one or more functional modules for implementing the flight schedule optimization method of the above method embodiments.

[0125] For example, Figure 4 This is a schematic diagram illustrating the composition of a flight timetable optimization device provided in an embodiment of this application. Figure 4As shown, the flight timetable optimization device 400 includes: an acquisition unit 401, a determination unit 402, and a calculation unit 403.

[0126] The acquisition unit 401 is used to acquire candidate flight time pairs for each route; wherein, the flight time pair includes the departure time and arrival time of the flight; the candidate flight time pairs are determined based on the flight time pair increments for each route; the flight time pair increments for each route are predicted based on a first model, which is used to predict the flight time pair increments for each route based on at least one of the historical passenger volume, flight frequency, and aircraft type; the determination unit 402 is used to determine candidate schemes based on the candidate flight time pairs; the candidate schemes include flight time pairs configured for each route in the historical flight timetable and candidate flight time pairs; the calculation unit 403 is used to calculate a first benefit for each candidate scheme based on the benefit of each route in the candidate scheme; wherein, the benefit of each route is predicted based on the first model, which is also used to predict the benefit of the route based on at least the flight time pairs and candidate flight time pairs; the determination unit 402 is also used to determine a target scheme based on the first benefit of each candidate scheme.

[0127] In some embodiments, the calculation unit 403 is specifically configured to calculate a first benefit for each candidate solution according to a pre-defined objective function; wherein the objective function is as follows:

[0128]

[0129] Where I represents the set of routes; J represents the set of flight time pairs; j represents a flight time pair; K represents the set of flight time pairs; R ij X represents the benefit of configuring flight times for route i to route j; ij =1 indicates that flight schedule pair j has been configured for route i; otherwise, X ij =0; y k =0 indicates that flight time k has been reassigned; otherwise, y k =1; R k,r Let r represent the revenue of flight time k itself; L represent the historical flight timetable; R′ represent the revenue of flight time k itself. ij This represents the benefit of configuring flight times for route i on route j in the historical flight timetable; X′ ij =1 indicates that route i in the historical flight timetable has been configured with flight time pair j; otherwise, X′ ij =0.

[0130] In other embodiments, flight schedules satisfy a first flight time constraint or a second flight time constraint; the first flight time constraint indicates that the sum of the flight's departure time and flight time is less than or equal to the flight's arrival time; the second flight time constraint indicates that the sum of the flight's departure time and flight time is less than or equal to the sum of the flight's arrival time and a preset flexible time.

[0131] In other embodiments, the candidate scheme includes a first candidate scheme and a second candidate scheme; the first candidate scheme is the candidate scheme under the condition that the flight time constraint meets the first flight time constraint; the second candidate scheme is the candidate scheme under the condition that the flight time constraint meets the second flight time constraint.

[0132] In other embodiments, the determining unit 402 is specifically configured to: determine a first target scheme based on the first benefit of each first candidate scheme; determine the incremental demand routes in each first candidate scheme; the incremental demand routes represent routes with candidate flight time pairs; for each first candidate scheme, reward each incremental demand route in the first candidate scheme according to a preset rule to determine a second benefit; the second benefit is obtained based on the first benefit and the benefit reward; the preset rule represents the relationship between the benefits of candidate flight time pairs and candidate flight time pairs; determine a second target scheme based on the second benefit of each first candidate scheme; and determine a first optimization scheme based on the first benefit of the first target scheme and the second benefit of the second target scheme.

[0133] In some other embodiments, the determining unit 402 is further specifically configured to: determine a third target scheme based on the first benefit of each second candidate scheme; determine the incremental demand routes in each second candidate scheme; for each second candidate scheme, award a benefit to each incremental demand route in the second candidate scheme according to a preset rule, and determine a third benefit; the third benefit is obtained based on the first benefit and the benefit award; determine a fourth target scheme based on the third benefit of each second candidate scheme; and determine a second optimization scheme based on the first benefit of the third target scheme and the third benefit of the fourth target scheme.

[0134] In other embodiments, the flight route needs to meet a flight frequency constraint; the flight frequency constraint indicates that the flight frequency of the route is less than or equal to the maximum flight frequency of the route.

[0135] In the case of implementing the functions of the integrated modules described above in hardware, this embodiment of the invention provides a possible structural schematic diagram of the electronic device involved in the above embodiments. For example... Figure 5 As shown, the electronic device 500 includes: a processor 502, a communication interface 503, and a bus 504. Optionally, the electronic device 500 may also include a memory 501.

[0136] Processor 502 may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 502 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 502 may also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0137] Communication interface 503 is used to connect to other devices via a communication network. This communication network can be Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0138] The memory 501 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0139] In one possible implementation, the memory 501 can exist independently of the processor 502. The memory 501 can be connected to the processor 502 via a bus 504 and is used to store instructions or program code. When the processor 502 calls and executes the instructions or program code stored in the memory 501, it can implement the flight timetable optimization method provided in this embodiment of the invention.

[0140] In another possible implementation, the memory 501 can also be integrated with the processor 502.

[0141] Bus 504 can be an extended industry standard architecture (EISA) bus, etc. Bus 504 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0142] Through the above description of the implementation methods, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the service calling device can be divided into different functional modules to complete all or part of the functions described above.

[0143] This application also provides a computer-readable storage medium. All or part of the processes in the above method embodiments can be executed by computer instructions instructing related hardware. The program can be stored in the aforementioned computer-readable storage medium, and when executed, it can include the processes of the above method embodiments. The computer-readable storage medium can be any of the foregoing embodiments or memory. The aforementioned computer-readable storage medium can also be an external storage device of the aforementioned service invocation device, such as a pluggable hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the aforementioned service invocation device. Further, the aforementioned computer-readable storage medium can include both internal storage units of the aforementioned service invocation device and external storage devices. The aforementioned computer-readable storage medium is used to store the aforementioned computer program and other programs and data required by the aforementioned service invocation device. The aforementioned computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0144] This application also provides a computer program product comprising a computer program that, when run on a computer, causes the computer to execute any of the flight schedule optimization methods provided in the above embodiments.

[0145] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for optimizing flight schedules, characterized in that, The method includes: Obtain candidate flight time pairs for each route; wherein, the flight time pair includes the departure time and arrival time of the flight; the candidate flight time pairs are determined based on the flight time pair increments for each route; the flight time pair increments for each route are predicted based on a first model, the first model being used to predict the flight time pair increments for each route based on at least one of the following: historical passenger numbers, flight frequency, and aircraft type. Based on the candidate flight time pairs, candidate schemes are determined; the candidate schemes include flight time pairs configured for each of the routes in the historical flight timetable and the candidate flight time pairs. For each of the candidate schemes, a first revenue is calculated based on the revenue of each of the routes in the candidate schemes; wherein, the revenue of each route is predicted based on the first model, and the first model is further used to predict the revenue of the route based at least on the flight time pair and the candidate flight time pair; The target solution is determined based on the first benefit of each of the candidate solutions.

2. The method according to claim 1, characterized in that, The step of calculating the first revenue based on the revenue of each of the candidate routes in each candidate scheme includes: For each of the candidate solutions, the first benefit is calculated according to a pre-defined objective function; The objective function is as follows: Where I represents the set of routes; J represents the set of flight time pairs; j represents the flight time pair; K represents the set of flight times; R ij X represents the benefit of configuring flight times for route i to route j; ij =1 indicates that route i has already been configured with the flight time pair j; otherwise, X ij =0; y k =0 indicates that flight time k has been reassigned; otherwise, y k =1; R k,r The revenue of flight time k itself is r; L represents the historical flight timetable; R′ ij This represents the benefit of configuring flight time pair j with route i in the historical flight timetable; X′ ij =1 indicates that route i in the historical flight timetable has been configured with flight time pair j; otherwise, X′ ij =0.

3. The method according to claim 1, characterized in that, The flight schedule satisfies either a first flight time constraint or a second flight time constraint; the first flight time constraint indicates that the sum of the flight's departure time and flight time is less than or equal to the flight's arrival time; the second flight time constraint indicates that the sum of the flight's departure time and flight time is less than or equal to the sum of the flight's arrival time and a preset flexible time.

4. The method according to claim 3, characterized in that, The candidate schemes include a first candidate scheme and a second candidate scheme; the first candidate scheme is the candidate scheme under the condition that the flight time constraint meets the first flight time constraint; the second candidate scheme is the candidate scheme under the condition that the flight time constraint meets the second flight time constraint.

5. The method according to claim 4, characterized in that, The method further includes: Based on the first benefit of each of the first candidate solutions, the first target solution is determined; Determine the incremental demand routes in each of the first candidate schemes; the incremental demand routes represent the routes for which the candidate flight time pairs exist; For each of the first candidate schemes, a revenue reward is given to each incremental demand route in the first candidate scheme according to a preset rule to determine the second revenue; the second revenue is obtained based on the first revenue and the revenue reward; the preset rule represents the relationship between the revenue of the candidate flight time pair and the candidate flight time pair. Based on the second benefit of each of the first candidate solutions, a second target solution is determined; Based on the first benefit of the first objective scheme and the second benefit of the second objective scheme, a first optimization scheme is determined.

6. The method according to claim 5, characterized in that, The method further includes: Based on the first benefit of each of the second candidate solutions, a third target solution is determined; Determine the incremental demand routes in each of the second candidate schemes; For each of the second candidate schemes, the incremental demand routes in each of the second candidate schemes are rewarded according to preset rules to determine the third revenue; the third revenue is obtained based on the first revenue and the revenue reward. Based on the third benefit of each of the second candidate schemes, a fourth target scheme is determined; Based on the first benefit of the third objective scheme and the third benefit of the fourth objective scheme, a second optimal scheme is determined.

7. The method according to any one of claims 1-6, characterized in that, The flight route needs to meet the flight frequency constraint; the flight frequency constraint indicates that the flight frequency of the flight route is less than or equal to the maximum flight frequency of the flight route.

8. A flight schedule optimization device, characterized in that, include: An acquisition unit is used to acquire candidate flight time pairs for each route; wherein, the flight time pair includes the departure time and arrival time of the flight; the candidate flight time pair is determined based on the flight time pair increment of each route; the flight time pair increment of each route is predicted based on a first model, the first model being used to predict the flight time pair increment of the route based on at least one of the historical passenger volume, flight frequency and aircraft type of the route; A determining unit is configured to determine a candidate scheme based on the candidate flight time pairs; the candidate scheme includes flight time pairs configured for each route in the historical flight timetable and the candidate flight time pairs. A calculation unit is configured to calculate a first revenue for each of the candidate schemes based on the revenue of each of the routes in the candidate schemes; wherein the revenue of each route is predicted based on the first model, and the first model is further configured to predict the revenue of the route based at least on the flight time pair and the candidate flight time pair; The determining unit is further configured to determine the target scheme based on the first benefit of each of the candidate schemes.

9. An electronic device, characterized in that, The device includes a processor and a memory, the processor being coupled to the memory; the memory is used to store computer instructions, which are loaded and executed by the processor to enable the computer device to implement the flight timetable optimization method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes computer-executable instructions that, when executed on a computer, cause the computer to perform the flight schedule optimization method as described in any one of claims 1 to 7.

11. A computer program product, characterized in that, The computer program product includes a computer program that, when run on an electronic device, causes the electronic device to perform the flight schedule optimization method as described in any one of claims 1 to 7.

Images