Prompting method and device for adjusting flight sales information

Abstract

The invention provides a prompting method and device for adjusting flight sales information, relates to the field of aviation information processing, and is used for reducing the number of monitoring time points and the workload of managers. The method comprises the steps that accumulated ticket selling data recorded by historical flights in a flight selling period according to a time sequence is acquired, a historical selling progress sequence of the historical flights is generated, and the accumulated ticket selling data is ticket selling data accumulated before a time node; based on the change characteristics between the accumulated ticketing data in the historical sales progress sequence, a plurality of key time nodes are determined, and the key time nodes are time nodes of which the change amplitude of the accumulated ticketing data is greater than a preset change threshold value. Based on the multiple key time nodes, regulation and control reminding information is sent out, and the regulation and control reminding information is used for indicating the sales information of the current operation flight to be adjusted at the key time nodes.

Description

Technical Field

[0001] This application relates to the field of aviation information processing, and in particular to a method and apparatus for providing prompts on adjusting flight sales information. Background Technology

[0002] During the flight sales process, the entire sales cycle, from the release of the flight schedule to the day of departure, can last for several months, and passenger ticketing behavior exhibits distinct phased characteristics. The sales pace at different times is influenced by various factors such as holidays, business travel patterns, market competition, and fare strategies, resulting in significant differences in the speed of ticket sales and seat accumulation patterns. For example, sales progress is slow in the early stages of pre-sales, a peak in ticket sales may occur in the middle stages, and fluctuations may occur closer to departure due to promotions on remaining seats or changes in refunds and changes.

[0003] To ensure stable flight sales, route managers need to adjust flight sales strategies promptly based on actual sales dynamics. However, current management methods generally rely on manual daily monitoring of sales data for a large number of flights, which is not only time-consuming and labor-intensive but also prone to missing key changes. Therefore, how to reduce the number of monitoring points and decrease the workload of managers has become an urgent technical problem to be solved. Summary of the Invention

[0004] This application provides a method and apparatus for adjusting flight sales information, which addresses the problem of a large number of monitored time points leading to a heavy workload for management personnel.

[0005] To achieve the above objectives, this application adopts the following technical solution: Firstly, this application provides a method for prompting adjustments to flight sales information. This method involves acquiring cumulative ticket sales data for historical flights recorded chronologically during the flight sales period, and generating a historical sales progress sequence for the historical flights. The cumulative ticket sales data refers to the ticket sales data accumulated up to a certain time point. Based on the change characteristics between the cumulative ticket sales data in the historical sales progress sequence, multiple key time points are determined. These key time points are those where the change in cumulative ticket sales data exceeds a preset change threshold. Based on these multiple key time points, adjustment reminder information is issued, instructing adjustments to the sales information of currently operating flights at these key time points.

[0006] Based on the aforementioned technical solution, by acquiring the cumulative ticket sales data of historical flights recorded chronologically during the sales period and generating a historical sales progress sequence reflecting sales dynamics, the pattern of passenger seat accumulation during the flight sales process can be accurately reconstructed. Based on the changing characteristics between the cumulative ticket sales data in this sequence, key time points where the fluctuation exceeds a preset threshold are identified, effectively capturing moments of significant fluctuations in sales trends, such as peak ticket sales, peak refund periods, or sudden increases in market demand—key business turning points. Furthermore, adjustment reminders are automatically issued at these key time points, prompting route management personnel to adjust the sales information of currently operating flights in a timely manner. This not only significantly reduces the workload of route management and avoids revenue loss due to monitoring blind spots, but also improves the accuracy of adjustment timing.

[0007] In one possible implementation, the flight sales period is divided into multiple sales time periods based on multiple preset time nodes, with each sales time period defined by two adjacent preset time nodes. The sales variation cost within each sales time period is determined; this cost measures the fluctuation range of historical flight ticket sales data within that time period. The total sales monitoring cost is determined based on the sales variation cost within each sales time period and a monitoring frequency penalty coefficient. This total sales monitoring cost is then optimized using a target optimization algorithm, with the preset time nodes corresponding to the minimum total sales monitoring cost being selected as multiple target time nodes. The monitoring frequency penalty coefficient is positively correlated with the number of preset time nodes. Multiple key time nodes are then identified from these target time nodes.

[0008] In one possible implementation, a solution method combining dynamic programming and pruning strategies is used to optimize the total cost of sales monitoring. Dynamic programming is used to determine the minimum total cost of sales monitoring as the number of preset key nodes increases layer by layer. Pruning strategies are used to remove time nodes that cannot participate in subsequent optimization processes as the number of preset key nodes increases layer by layer.

[0009] In one possible implementation, the minimum total cost of sales monitoring satisfies the following formula:

[0010] Where P(λ) represents the total cost of sales monitoring, and m represents the number of preset time points. This is used to represent the sales variation cost corresponding to the sales period defined by the (j-1)th preset time point and the jth preset time point. Used to represent ticket sales data between the (j-1)th preset time point and the jth preset time point. Used to represent the j-th preset time point Used to represent the penalty coefficient for monitoring frequency.

[0011] In one possible implementation, for each sales period, the sales variation cost within the sales period is determined based on the cumulative ticket sales data corresponding to the first time node, the cumulative ticket sales data corresponding to the second time node, and the target ticket sales data; wherein the first time node and the second time node are the start and end times of the sales period, respectively; and the target ticket sales data is determined based on the cumulative ticket sales data corresponding to the first time node and the cumulative ticket sales data corresponding to the second time node.

[0012] In one possible implementation, the constraints of the objective optimization algorithm include at least one of the following: complete coverage of the sales period, time sequence of segment points, and non-empty segment constraints; wherein, the complete coverage of the sales period constraint is used to ensure that all sales time periods are consistent with the data within the flight sales period, the time sequence of segment points constraint is used to ensure that the preset time points are arranged according to the number of days from the flight departure date, and the non-empty segment constraints are used to ensure that the preset time points are unit time points, and the unit time point is the time point with cumulative ticket sales data in the flight sales period.

[0013] In one possible implementation, ticket sales data changes for at least one key time period are acquired, and based on these changes, a control alert message corresponding to each key time period is generated. Each key time period is defined by two adjacent key time nodes. Multiple key time nodes are matched with the sales timeline of the currently operating flights to generate at least one actual alert date. The key time nodes are the time points prior to flight departure, and the actual alert date is the earliest of the two key time nodes within each key time period. Based on at least one actual alert date, at least one control alert message corresponding to each key time period is issued, with one actual alert date corresponding to one control alert message.

[0014] Secondly, this application provides a notification device for adjusting flight sales information, the device including an acquisition module, a processing module, and a sending module.

[0015] The acquisition module retrieves the cumulative ticket sales data of historical flights recorded chronologically during the flight sales period and generates a historical sales progress sequence for these flights. The cumulative ticket sales data represents the total ticket sales accumulated up to a given time point. The processing module identifies multiple key time points based on the changing characteristics of the cumulative ticket sales data within the historical sales progress sequence. Key time points are those where the change in cumulative ticket sales data exceeds a preset threshold. The sending module issues adjustment reminders based on these key time points, instructing adjustments to the sales information of currently operating flights at these critical time points.

[0016] In one possible implementation, the processing module is further configured to divide the flight sales period into multiple sales time periods based on multiple preset time nodes, with each sales time period defined by two adjacent preset time nodes. The processing module is also configured to determine the sales variation cost within each sales time period, whereby the sales variation cost measures the magnitude of change in the cumulative ticket sales data of historical flights within that sales time period. The processing module is further configured to determine the total sales monitoring cost based on the sales variation cost within each sales time period and the monitoring frequency penalty coefficient, and to optimize the total sales monitoring cost using a target optimization algorithm, selecting the multiple preset time nodes corresponding to the minimum total sales monitoring cost as multiple target time nodes; the monitoring frequency penalty coefficient is positively correlated with the number of preset time nodes. The processing module is also configured to determine multiple key time nodes from the multiple target time nodes.

[0017] In one possible implementation, the processing module is also used to optimize the total cost of sales monitoring by using a solution method that combines dynamic programming with pruning strategies. Dynamic programming is used to determine the minimum total cost of sales monitoring as the number of preset key nodes increases layer by layer. Pruning strategies are used to remove time nodes that cannot participate in the subsequent optimization process as the number of preset key nodes increases layer by layer.

[0018] In one possible implementation, the minimum total cost of sales monitoring satisfies the following formula:

[0019] Where P(λ) represents the total cost of sales monitoring, and m represents the number of preset time points. This is used to represent the sales variation cost corresponding to the sales period defined by the (j-1)th preset time point and the jth preset time point. Used to represent ticket sales data between the (j-1)th preset time point and the jth preset time point. Used to represent the j-th preset time point Used to represent the penalty coefficient for monitoring frequency.

[0020] In one possible implementation, the processing module is further configured to determine the sales variation cost within each sales period based on the cumulative ticket sales data corresponding to the first time node, the cumulative ticket sales data corresponding to the second time node, and the target ticket sales data; wherein the first time node and the second time node are the start and end times of the sales period, respectively; and the target ticket sales data are determined based on the cumulative ticket sales data corresponding to the first time node and the cumulative ticket sales data corresponding to the second time node.

[0021] In one possible implementation, the constraints of the objective optimization algorithm include at least one of the following: complete coverage of the sales period, time sequence of segment points, and non-empty segment constraints; wherein, the complete coverage of the sales period constraint is used to ensure that all sales time periods are consistent with the data within the flight sales period, the time sequence of segment points constraint is used to ensure that the preset time points are arranged according to the number of days from the flight departure date, and the non-empty segment constraints are used to ensure that the preset time points are unit time points, and the unit time point is the time point with cumulative ticket sales data in the flight sales period.

[0022] In one possible implementation, the acquisition module is further configured to acquire ticket sales data change information for at least one key time period, and generate control reminder information corresponding to each key time period based on the ticket sales data change information for each key time period; the key time period is defined by two adjacent key time nodes. The processing module is further configured to match multiple key time nodes with the sales timeline of the currently operating flights to generate at least one actual reminder date, where the key time nodes are the time nodes before the flight departure, and the actual reminder date is the earliest of the two key time nodes of the key time period. The sending module is further configured to send control reminder information corresponding to at least one key time period based on at least one actual reminder date, with one control reminder message corresponding to one actual reminder date.

[0023] Thirdly, this application provides a notification device for adjusting flight sales information, the device comprising: a processor and a memory; the processor and the memory being coupled; the memory being used to store one or more programs, the one or more programs including computer device execution instructions, wherein when the notification device for adjusting flight sales information is running, the processor executes the computer device execution instructions stored in the memory to implement the method as described in the first aspect and any possible implementation thereof.

[0024] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause a computer device to perform the methods described in the first aspect and any possible implementation thereof.

[0025] Fifthly, this application provides a chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run computer programs or instructions to implement the methods described in the first aspect and any possible implementation thereof.

[0026] Sixthly, this application provides a computer program product containing instructions that, when executed by a computer, cause the computer device to perform the methods described in the first aspect and any possible implementation thereof.

[0027] The technical problems and effects that the above-mentioned solution can solve by the flight sales information prompting device, computer equipment, computer storage medium, chip or computer program product can solve are the same as those solved by the first aspect above, and will not be repeated here. Attached Figure Description

[0028] Figure 1 A flowchart illustrating a method for providing prompts to adjust flight sales information, as provided in an embodiment of this application; Figure 2 A flowchart illustrating another method for adjusting flight sales information provided in this application embodiment; Figure 3 A flowchart illustrating another method for adjusting flight sales information provided in this application embodiment; Figure 4 A schematic diagram of a prompting device for adjusting flight sales information provided in an embodiment of this application; Figure 5 A schematic diagram of another prompting device for adjusting flight sales information provided in an embodiment of this application; Figure 6 A conceptual partial view of a computer program product provided for an embodiment of this application. Detailed Implementation

[0029] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0030] The terms “first” and “second” in the specification and claims of this application are used to distinguish different objects, rather than to describe a specific order of objects.

[0031] 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 device that includes a series of steps or modules is not limited to the steps or modules listed, but may optionally include other steps or modules not listed, or may optionally include other steps or modules inherent to such process, method, product, or device.

[0032] Furthermore, in the embodiments of this application, the words "exemplary" or "for example" are used to indicate that they are examples, illustrations, or descriptions. Any embodiment or design that is described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design options. Specifically, the use of the words "exemplary" or "for example" is intended to present concepts in a concrete manner.

[0033] During the flight sales process, the entire sales cycle, from the release of the flight schedule to the day of departure, can last for several months, and passenger ticketing behavior exhibits distinct phased characteristics. The sales pace at different times is influenced by various factors such as holidays, business travel patterns, market competition, and fare strategies, resulting in significant differences in the speed of ticket sales and seat accumulation patterns. For example, sales progress is slow in the early stages of pre-sales, a peak in ticket sales may occur in the middle stages, and fluctuations may occur closer to departure due to promotions on remaining seats or changes in refunds and changes.

[0034] To ensure flight stability, route managers need to adjust cabin availability strategies, fare classes, and sales channel configurations in a timely manner based on actual sales dynamics. However, current management methods generally rely on manual daily monitoring of sales data for a large number of flights, which is not only time-consuming and labor-intensive but also prone to missing key changes. Due to the lack of systematic analysis of historical sales patterns, managers often struggle to accurately determine which time periods truly require intervention, leading to either excessive monitoring resulting in wasted resources or missing the optimal adjustment opportunity, impacting revenue. Therefore, the existing flight sales management model suffers from both a large workload for adjustment and insufficient decision-making accuracy.

[0035] To address the aforementioned technical problems, this application provides a method for prompting adjustments to flight sales information. This method involves acquiring cumulative ticket sales data for historical flights recorded chronologically during the flight sales period, and generating a historical sales progress sequence for these flights. The cumulative ticket sales data represents the ticket sales accumulated up to a specific time point. Based on the variation characteristics between the cumulative ticket sales data in the historical sales progress sequence, multiple key time points are determined. These key time points are those where the change in cumulative ticket sales data exceeds a preset change threshold. Based on these key time points, adjustment reminder information is issued, instructing adjustments to the sales information of currently operating flights at these key time points.

[0036] This approach, by acquiring historical flight ticket sales data recorded chronologically during the sales period and generating a historical sales progress sequence reflecting sales dynamics, allows for a true reconstruction of passenger seat accumulation patterns during the flight sales process. Based on the changing characteristics between the cumulative ticket sales data in this sequence, key time points where fluctuations exceed preset thresholds are identified, effectively capturing moments of significant sales trend fluctuations, such as peak ticket sales, peak refund periods, or sudden increases in market demand—critical business turning points. Subsequently, automatic adjustment reminders are issued at these key time points, prompting route management personnel to adjust the sales information for currently operating flights in a timely manner. This not only significantly reduces the workload of route management and avoids revenue loss due to monitoring blind spots but also improves the accuracy of adjustment timing.

[0037] The embodiments of this application will now be described in conjunction with the accompanying drawings.

[0038] like Figure 1 The image shows a method for prompting adjustments to flight sales information provided in an embodiment of this application. The method includes: S101. Obtain the cumulative ticket sales data of historical flights recorded in chronological order during the flight sales period, and generate the historical sales progress sequence of historical flights.

[0039] The cumulative ticket sales data refers to the cumulative ticket sales data up to a certain point in time.

[0040] It should be understood that the ticketing data in this application is not limited. For example, the ticketing data can be seat sales data or sales amount.

[0041] In this embodiment of the application, the flight sales period includes multiple unit time points, and each unit time point corresponds to a cumulative ticket sales data.

[0042] For example, the unit of time can be based on days or weeks, and this application embodiment does not limit this. For instance, if the unit of time is based on days, and the flight sales period is 3 days before the flight's departure, then the cumulative ticket sales data includes: cumulative ticket sales data up to the 3rd day before departure, cumulative ticket sales data up to the 2nd day before departure, cumulative ticket sales data up to the 1st day before departure, and cumulative ticket sales data up to the day of departure.

[0043] For example, if the cumulative ticket sales data up to 3 days before departure is 10, the cumulative ticket sales data up to 3 days before departure is 30, the cumulative ticket sales data up to 1 day before departure is 50, and the cumulative ticket sales data up to departure is 65, then it means that the ticket sales data up to 3 days before departure is 10, and the ticket sales data up to 2 days before departure is 20. The historical sales progress sequence is (10, 30, 50, 65).

[0044] S102. Based on the changing characteristics of cumulative ticket sales data in the historical sales progress sequence, determine several key time nodes.

[0045] The key time point is the time point when the change in cumulative ticket sales data exceeds the preset change threshold.

[0046] It should be understood that the change range of cumulative ticket sales data refers to the change range of cumulative ticket sales data corresponding to each unit time point within the sales period. The preset change threshold can be 10, 20, 50, etc., and this application embodiment does not limit it.

[0047] In this embodiment of the application, the sales period is defined by two adjacent preset time nodes.

[0048] For example, if the two preset time points are 180 days before departure and 151 days before departure, the sales period is 30 days from 180 days before departure to 151 days before departure, including 30 cumulative ticket sales data.

[0049] In one possible implementation, the flight sales period can be divided into multiple sales time slots, each including at least one cumulative ticket sales data slot. Then, the variation range between the cumulative ticket sales data slots within each sales time slot is determined, with each variation range corresponding to one sales time slot. Next, time slots with variation ranges exceeding a preset threshold are designated as critical time slots, and the start and end times of these critical time slots are designated as critical time nodes.

[0050] S103. Issue control and regulation reminders based on multiple key time points.

[0051] Among them, the control reminder information is used to indicate adjustments to the sales information of currently operating flights at key time points.

[0052] For example, sales information may include cabin configurations and fare strategies for currently operating flights.

[0053] In one possible implementation, multiple key time points are matched with the sales timeline of currently operating flights to generate at least one actual reminder date. This actual reminder date is the earliest of two key time points within a key time period. Then, a control reminder message is issued on the actual reminder date.

[0054] For example, if the key time points are 6 days and 3 days before departure, the actual reminder date will be 6 days before departure.

[0055] Based on the aforementioned technical solution, by acquiring the cumulative ticket sales data of historical flights recorded chronologically during the sales period and generating a historical sales progress sequence reflecting sales dynamics, the pattern of passenger seat accumulation during the flight sales process can be accurately reconstructed. Based on the changing characteristics between the cumulative ticket sales data in this sequence, key time points where the fluctuation exceeds a preset threshold are identified, effectively capturing moments of significant fluctuations in sales trends, such as peak ticket sales, peak refund periods, or sudden increases in market demand—key business turning points. Furthermore, adjustment reminders are automatically issued at these key time points, prompting route management personnel to adjust the sales information of currently operating flights in a timely manner. This not only significantly reduces the workload of route management and avoids revenue loss due to monitoring blind spots, but also improves the accuracy of adjustment timing.

[0056] like Figure 2 As shown, this is another method for prompting adjustments to flight sales information provided in an embodiment of this application. In this method, S102 includes: S201. Based on multiple preset time nodes, the flight sales period is divided into multiple sales time periods.

[0057] The sales period is defined by two adjacent preset time nodes.

[0058] In this embodiment of the application, the preset time node is any unit time node in the flight sales period.

[0059] For example, suppose the departure time of a historical flight is January 10th, and the flight sales period is 10 days, from 00:00 on January 1st to January 10th. The flight sales period includes 11 time nodes, such as 00:00 on January 1st, 00:00 on January 2nd, 00:00 on January 3rd, 00:00 on January 4th, 00:00 on January 5th, 00:00 on January 6th, 00:00 on January 7th, 00:00 on January 8th, 00:00 on January 9th, 00:00 on January 10th, and the ticket sales deadline. If the preset time nodes are 00:00 on January 4th and 00:00 on January 7th, then multiple sales time periods are 00:00 on January 1st to 00:00 on January 4th, 00:00 on January 4th to 00:00 on January 7th, and 00:00 on January 7th to the ticket sales deadline.

[0060] S202. Determine the sales variation costs for each sales period.

[0061] Among them, sales variation costs are used to measure the magnitude of change in the cumulative ticket sales data of historical flights within a sales period.

[0062] In one possible implementation, for each sales period, the sales variation cost within the sales period is determined based on the cumulative ticket sales data corresponding to the first time node, the cumulative ticket sales data corresponding to the second time node, and the target ticket sales data. Here, the first and second time nodes are the start and end times of the sales period, respectively; the target ticket sales data is determined based on the cumulative ticket sales data corresponding to the first and second time nodes.

[0063] In this embodiment of the application, the target sales data can be any of the following: the median of the cumulative ticket sales data in the sales period, the arithmetic mean of the cumulative ticket sales data in the sales period, or the sample covariance matrix of the cumulative ticket sales data in the sales period.

[0064] In one possible implementation, where the target sales data is the median of the cumulative ticket sales data within the sales period, the sales variation cost within the sales period satisfies the following formula.

[0065] Formula 1.

[0066] in, This is used to represent the sales change cost within the sales period defined by the first and second time nodes. 'a' represents the first time node, and 'b' represents the second time node. Used to represent the cumulative ticket sales data at the i-th unit time point. This is used to represent the median of cumulative ticket sales data for each sales period.

[0067] In another possible implementation, where the target sales data is the arithmetic mean of the cumulative ticket sales data within the sales period, the sales variation cost within the sales period satisfies the following formula two.

[0068] Formula 2.

[0069] in, This is used to represent the arithmetic mean of cumulative ticket sales data within a sales period.

[0070] In another possible implementation, where the target sales data is a sample covariance matrix of cumulative ticket sales data within a sales period, the sales variation cost within the sales period satisfies the following formula three.

[0071] Formula 3.

[0072] in, This is used to represent the sample covariance matrix of cumulative ticket sales data for each sales period.

[0073] S203. Determine the total cost of sales monitoring based on the sales change cost and monitoring frequency penalty coefficient within each sales period, and optimize the total cost of sales monitoring according to the target optimization algorithm, so as to take the multiple preset time nodes corresponding to the minimum total cost of sales monitoring as multiple target time nodes.

[0074] Among them, the monitoring frequency penalty coefficient is positively correlated with the number of preset time nodes.

[0075] In one possible implementation, the minimum total cost of sales monitoring satisfies the following formula: Formula 4.

[0076] Where P(λ) represents the total cost of sales monitoring, and m represents the number of preset time points. This is used to represent the sales variation cost corresponding to the sales period defined by the (j-1)th preset time point and the jth preset time point. Used to represent ticket sales data between the (j-1)th preset time point and the jth preset time point. Used to represent the j-th preset time point Used to represent the penalty coefficient for monitoring frequency.

[0077] In this embodiment, there are multiple historical flights. The determination of the monitoring frequency penalty coefficient is related to the relationship between multiple historical flights, which can be either the historical flights of a single flight or the historical flights of a single route.

[0078] It should be understood that a flight's historical flights refer to flights on different dates with the same flight time, route, and flight number. For example, flight number 001 operates on Mondays, Tuesdays, and Wednesdays. A route's historical flights refer to flights with the same route. For example, flights from region A to region B on Mondays include: Flight A, Flight B, and Flight C.

[0079] In one possible implementation, when the historical flight relationship is a historical flight of a single flight, the monitoring frequency penalty coefficient can be a preset penalty coefficient, or the monitoring frequency penalty coefficient can be related to the number of preset time nodes.

[0080] For example, in the case where the historical flight relationship is a historical flight of a single flight, the monitoring frequency penalty coefficient satisfies the following formula five.

[0081] Formula 5: β=log m

[0082] In another possible implementation, when the historical flight relationship is that of historical flights on the same route, the monitoring frequency penalty coefficient can be related to the number of preset time nodes and the number of historical flights, where the number of flights refers to the number of flights with different flight numbers.

[0083] For example, in the case of historical flights that are on the same route, the monitoring frequency penalty coefficient satisfies the following formula six.

[0084] Formula 6: β = d × log m

[0085] Where d represents the number of historical flights.

[0086] Alternatively, in the case where the historical flight relationship is that of a single route, the monitoring frequency penalty coefficient satisfies the following formula seven.

[0087] Formula 7: β=(d+(d×(d+1)) / 2)×log m

[0088] In this embodiment, a solution method combining dynamic programming and pruning strategies can be used to optimize the total cost of sales monitoring. Dynamic programming is used to determine the minimum total cost of sales monitoring as the number of preset key nodes increases layer by layer. Pruning strategies are used to remove time nodes that cannot participate in subsequent optimization processes as the number of preset key nodes increases layer by layer.

[0089] The embodiments of this application are described below with reference to specific examples.

[0090] For example, the objective optimization algorithm (also called the objective function, such as Equation 4) and constraints form a model, which can be solved from the perspective of dynamic programming. Regarding the objective function, from the perspective of dynamic programming, given the existing... In the case of a number of segment points, add a new segment point. The total cost of sales monitoring satisfies Formula 8.

[0091] Formula 8.

[0092] The point may be to Let n be any one of the values ​​in the equation, where n is the number of time points within the flight sales period. Therefore, it is necessary to calculate all possible value points and select the point with the lowest cost as the new split point. .

[0093] The computational complexity of this method is To improve computational efficiency, an exact pruning linear algorithm is used to limit... The possible range of values ​​for a point (using a set) (Representation). Assuming for the segmentation point... ,inequality Found. In calculation At that time, for ( In terms of ), if The positions of subsequent segmentation points will be... After that, at this time you can From the range of possible values Remove from the middle. In the calculation... When, for the set of possible value ranges ,if , then from Remove it from the middle, and the computational complexity will become .

[0094] Understandably, by systematically traversing all possible segment combinations through dynamic programming, the system ensures that, as the number of key monitoring nodes increases layer by layer, it can globally find the optimal or near-optimal set of key time points that minimizes the total cost of sales monitoring, thus guaranteeing the global optimality of the monitoring cycle division results. Simultaneously, the pruning strategy dynamically removes intermediate nodes that have been proven unable to form a better solution during the iteration process, thereby reducing the computational complexity of the algorithm. In this way, the system can automatically and accurately output key monitoring days in a short period of time, providing real-time and reliable decision support for route administrators.

[0095] In this embodiment of the application, the constraints of the target optimization algorithm include at least one of the following: complete coverage of the sales period, time sequence of segment points, and non-empty segment constraints; wherein, the complete coverage of the sales period constraint is used to ensure that all sales time periods are consistent with the data within the flight sales period, the time sequence of segment points constraint is used to ensure that the preset time points are arranged according to the number of days from the flight departure date, and the non-empty segment constraints are used to ensure that the preset time points are unit time points, and the unit time point is the time point with cumulative ticket sales data in the flight sales period.

[0096] In this way, by implementing constraints on complete coverage of the sales period, time sequence of segment points, and non-empty segments, this method can systematically determine the key time nodes in the flight sales monitoring cycle. It ensures that the monitoring cycle fully covers the entire sales period, that the segment points are arranged in chronological order, and that each segment is based on actual sales data. Thus, while ensuring the comprehensiveness of monitoring and the rationality of the timing, it significantly reduces the number of flights that route managers need to monitor daily, allowing them to focus on in-depth analysis and precise control on key sales days. This improves monitoring efficiency and ensures the effectiveness of flight management.

[0097] S204. Identify multiple key time nodes from multiple target time nodes.

[0098] In one possible implementation, multiple target time periods can be determined based on multiple target time nodes, with each target time period defined by two adjacent target time nodes. Then, the sales variation cost for each target time period is determined. Target time periods where the sales variation cost exceeds a preset cost threshold are designated as critical time periods, and the preset nodes corresponding to these critical time periods are designated as critical time nodes.

[0099] It should be understood that the embodiments of this application do not limit the preset cost threshold. For example, the preset cost threshold can be 10, 40, 33, etc.

[0100] For example, if multiple target time points are day 180, day 150, day 121, day 90, day 40, day 20, day 10, and day 1, then multiple target time periods include: day 180-day 150, day 150-day 121, day 121-day 90, day 90-day 40, day 40-day 20, day 20-day 10, and day 10-day 1. If the key time periods are day 40-day 20, day 20-day 10, and day 10-day 1, then multiple key time points are day 40, day 20, and day 1.

[0101] Based on the above technical solution, by dividing the flight sales period into multiple sales time periods based on preset time nodes and quantifying the historical sales data fluctuation range within each time period as the sales change cost, the system can accurately depict the stable and abrupt intervals of sales progress. By combining the monitoring frequency penalty coefficient which is positively correlated with the number of nodes to construct a total sales monitoring cost model, and using an optimization algorithm to minimize it, the system can automatically suppress unnecessary monitoring frequency while ensuring monitoring coverage of sales abrupt change points, thereby achieving an optimal balance between the monitoring needs represented by data and the control costs of manual input.

[0102] like Figure 3 The image shows another method for prompting adjustments to flight sales information provided in this application embodiment. In this method, S103 includes: S301. Obtain ticket sales data change information for at least one key time period, and generate control reminder information corresponding to each key time period based on the ticket sales data change information for each key time period.

[0103] The critical time period is defined by two adjacent critical time nodes.

[0104] In this embodiment of the application, the ticket sales data change information may include: the number of tickets purchased is greater than a preset change threshold, and the number of refunds is greater than a preset change threshold.

[0105] In one possible implementation, when the ticket sales data shows that the number of tickets purchased exceeds a preset threshold, a regulatory alert is generated indicating that cabin availability is tight or that cabin prices need to be increased.

[0106] If the ticket sales data shows that the number of refunds exceeds a preset threshold, a control reminder message will be generated indicating that there is redundancy in cabin class or that cabin class prices need to be lowered or promotions need to be launched.

[0107] S302. Match multiple key time points with the sales timeline of currently operating flights to generate at least one actual reminder date.

[0108] Among them, the key time node is the time node before the flight takes off, and the actual reminder date is the earliest of the two key time nodes in the key time period.

[0109] For example, if the key time points are the 7th and 5th days before the flight departure, and the current flight departure date is January 8th, then the actual reminder date is January 1st.

[0110] S303. Based on at least one actual reminder date, issue control reminder information corresponding to at least one key time period.

[0111] One actual reminder date corresponds to one regulatory reminder message.

[0112] Understandably, by dynamically matching key time points with the actual sales timeline of currently operating flights, and converting them into specific actual reminder dates, theoretical monitoring nodes are transformed into actionable schedules. Furthermore, by automatically triggering and issuing adjustment reminders based on the actual reminder dates at the beginning of each key time period, targeted sales change characteristics for that period are generated, achieving precise time alignment between monitoring and decision support.

[0113] The foregoing mainly describes the solutions provided by the embodiments of this application from a methodological perspective. It is understood that the device for adjusting flight sales information includes hardware structures and / or software modules corresponding to the execution of each function in order to achieve the aforementioned functions. Those skilled in the art should readily recognize that, based on the steps of the methods for adjusting flight sales information described in conjunction with the embodiments disclosed in this application, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in 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 application.

[0114] This application also provides a device for prompting adjustments to flight sales information. This device can be a server, the CPU of the server, a prompting module within the server for prompting adjustments to flight sales information, or a client in the mobile terminal for prompting adjustments to flight sales information.

[0115] This application embodiment can divide the flight sales information adjustment prompt device into functional modules or functional units according to the above method example. For example, each function can be divided into a separate functional module or functional unit, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or in software functional modules or functional units. The module or unit division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0116] This application provides a notification device for adjusting flight sales information. For example... Figure 4 As shown, the device for prompting adjustments to flight sales information may include: an acquisition module 401, a processing module 402, and a sending module 403.

[0117] The acquisition module 401 is used to acquire the cumulative ticket sales data of historical flights recorded in chronological order during the flight sales period, and generate a historical sales progress sequence for historical flights. The cumulative ticket sales data refers to the ticket sales data accumulated up to a certain time point. The processing module 402 is used to determine multiple key time points based on the change characteristics between the cumulative ticket sales data in the historical sales progress sequence. The key time points are the time points where the change in the cumulative ticket sales data exceeds a preset change threshold. The sending module 403 is used to issue adjustment reminder information based on the multiple key time points. The adjustment reminder information is used to instruct adjustments to the sales information of currently operating flights at the key time points.

[0118] In one possible implementation, processing module 402 is further configured to divide the flight sales period into multiple sales time periods based on multiple preset time nodes, with each sales time period defined by two adjacent preset time nodes. Processing module 402 is also configured to determine the sales variation cost within each sales time period, whereby the sales variation cost measures the magnitude of change in the cumulative ticket sales data of historical flights within the sales time period. Processing module 402 is further configured to determine the total sales monitoring cost based on the sales variation cost within each sales time period and the monitoring frequency penalty coefficient, and to optimize the total sales monitoring cost according to a target optimization algorithm, so that the multiple preset time nodes corresponding to the minimum total sales monitoring cost are used as multiple target time nodes; the monitoring frequency penalty coefficient is positively correlated with the number of preset time nodes. Processing module 402 is further configured to determine multiple key time nodes from the multiple target time nodes.

[0119] In one possible implementation, the processing module 402 is further used to optimize the total cost of sales monitoring by using a solution method that combines dynamic programming with pruning strategies. Dynamic programming is used to determine the minimum total cost of sales monitoring as the number of preset key nodes increases layer by layer. Pruning strategies are used to remove time nodes that cannot participate in the subsequent optimization process as the number of preset key nodes increases layer by layer.

[0120] In one possible implementation, the minimum total cost of sales monitoring satisfies the following formula:

[0121] Where P(λ) represents the total cost of sales monitoring, and m represents the number of preset time points. This is used to represent the sales variation cost corresponding to the sales period defined by the (j-1)th preset time point and the jth preset time point. Used to represent ticket sales data between the (j-1)th preset time point and the jth preset time point. Used to represent the j-th preset time point Used to represent the penalty coefficient for monitoring frequency.

[0122] In one possible implementation, the processing module 402 is further configured to determine the sales variation cost within each sales period based on the cumulative ticket sales data corresponding to the first time node, the cumulative ticket sales data corresponding to the second time node, and the target ticket sales data; wherein the first time node and the second time node are the start and end times of the sales period, respectively; and the target ticket sales data are determined based on the cumulative ticket sales data corresponding to the first time node and the cumulative ticket sales data corresponding to the second time node.

[0123] In one possible implementation, the constraints of the objective optimization algorithm include at least one of the following: complete coverage of the sales period, time sequence of segment points, and non-empty segment constraints; wherein, the complete coverage of the sales period constraint is used to ensure that all sales time periods are consistent with the data within the flight sales period, the time sequence of segment points constraint is used to ensure that the preset time points are arranged according to the number of days from the flight departure date, and the non-empty segment constraints are used to ensure that the preset time points are unit time points, and the unit time point is the time point with cumulative ticket sales data in the flight sales period.

[0124] In one possible implementation, the acquisition module 401 is further configured to acquire ticket sales data change information for at least one key time period, and generate control reminder information corresponding to each key time period based on the ticket sales data change information for each key time period; the key time period is defined by two adjacent key time nodes. The processing module 402 is further configured to match multiple key time nodes with the sales timeline of the currently operating flights to generate at least one actual reminder date, where the key time nodes are the time nodes before the flight departure, and the actual reminder date is the earliest of the two key time nodes in the key time period. The sending module 403 is further configured to send control reminder information corresponding to at least one key time period based on at least one actual reminder date, where one actual reminder date corresponds to one control reminder message.

[0125] Figure 5 This is a schematic diagram illustrating the structure of another device for prompting adjustments to flight sales information according to an exemplary embodiment. The device may include a processor 502, which executes application code to implement the method for prompting adjustments to flight sales information as described in this application.

[0126] The processor 502 may be a central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present application.

[0127] like Figure 5 As shown, the device for adjusting flight sales information may further include a memory 503. The memory 503 stores the application code that executes the solution of this application, and its execution is controlled by the processor 502.

[0128] Memory 503 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), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, 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 not limited thereto. Memory 503 may exist independently and be connected to processor 502 via bus 504. Memory 503 may also be integrated with processor 502.

[0129] like Figure 5 As shown, the device for adjusting flight sales information may further include a communication interface 501, wherein the communication interface 501, processor 502, and memory 503 may be coupled to each other, for example, via a bus 504. The communication interface 501 is used for information exchange with other devices, for example, supporting information exchange between the device for adjusting flight sales information and other devices.

[0130] It should be pointed out that, Figure 5 The device structure shown does not constitute a limitation on the notification device for adjusting flight sales information, except... Figure 5 In addition to the components shown, the device for adjusting flight sales information may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0131] In actual implementation, the functions implemented by the processing unit can be derived from... Figure 5 The processor 502 shown calls the program code in memory 503 to implement this.

[0132] This application also provides a computer-readable storage medium storing instructions that, when executed by a processor of a computer device, enable the computer to perform the method for adjusting flight sales information provided in the embodiments described above. For example, the computer-readable storage medium may be a memory 503 including instructions, which may be executed by a processor 502 of a computer device to complete the method. Optionally, the computer-readable storage medium may be a non-transitory computer-readable storage medium, such as a ROM, RAM, CD-ROM, magnetic tape, floppy disk, or optical data storage device.

[0133] Figure 6 A conceptual partial view of a computer program product provided in an embodiment of this application is shown schematically. The computer program product includes a computer program for executing computer processes on a computing device.

[0134] In one embodiment, the computer program product is provided using a signal bearer medium 600. The signal bearer medium 600 may include one or more program instructions that, when executed by one or more processors, can provide the functions or parts thereof described above with respect to the embodiments.

[0135] In some examples, the signal carrying medium 600 may include a computer-readable medium 601, such as, but not limited to, a hard disk drive, a compact disc (CD), a digital video optical disc (DVD), a digital magnetic tape, a memory, a read-only memory (ROM), or a random access memory (RAM), and so on.

[0136] In some implementations, the signal carrying medium 600 may include a computer recordable medium 602, such as, but not limited to, a memory, a read / write (R / W) CD, an R / W DVD, and so on.

[0137] In some implementations, the signal carrying medium 600 may include a communication medium 603, such as, but not limited to, digital and / or analog communication media (e.g., fiber optic cables, waveguides, wired communication links, wireless communication links, etc.).

[0138] The signal-bearing medium 600 can be transmitted by a wireless communication medium 603. One or more program instructions may be, for example, computer-executable instructions or logical implementation instructions.

[0139] In some examples, the device for adjusting flight sales information can be configured to provide various operations, functions, or actions in response to one or more program instructions via a computer-readable medium 601, a computer-recordable medium 602, and / or a communication medium 603.

[0140] Through the above description of the embodiments, 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 device can be divided into different functional modules to complete all or part of the functions described above.

[0141] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0142] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0143] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0144] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, essentially, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0145] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes 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 prompting adjustments to flight sales information, characterized in that, The method includes: Obtain the cumulative ticket sales data of historical flights recorded in chronological order during the flight sales period, and generate the historical sales progress sequence of the historical flights, wherein the cumulative ticket sales data is the ticket sales data accumulated before a certain time point; Based on the change characteristics between the cumulative ticket sales data in the historical sales progress sequence, multiple key time nodes are determined. The key time nodes are the time nodes when the change in the cumulative ticket sales data is greater than a preset change threshold. Based on the aforementioned multiple key time points, adjustment reminder information is issued, which is used to instruct adjustments to the sales information of currently operating flights at the key time points.

2. The method according to claim 1, characterized in that, Based on the changing characteristics between the cumulative ticket sales data in the historical sales progress sequence, several key time nodes are determined, including: Based on multiple preset time nodes, the flight sales period is divided into multiple sales time periods, and the sales time period is defined by two adjacent preset time nodes; Determine the cost of sales variation for each of the sales periods, wherein the cost of sales variation is used to measure the magnitude of change in the cumulative ticket sales data of the historical flights within the sales period; The total cost of sales monitoring is determined based on the sales change cost and monitoring frequency penalty coefficient within each sales period, and the total cost of sales monitoring is optimized according to the target optimization algorithm, so that multiple preset time nodes corresponding to the minimum total cost of sales monitoring are used as multiple target time nodes; the monitoring frequency penalty coefficient is positively correlated with the number of preset time nodes; The multiple key time nodes are determined from the multiple target time nodes.

3. The method according to claim 2, characterized in that, Optimize the total cost of sales monitoring according to the target optimization algorithm, including: The total cost of sales monitoring is optimized by using dynamic programming combined with pruning strategies. The dynamic programming is used to determine the minimum total cost of sales monitoring as the number of preset key nodes increases layer by layer. The pruning strategy is used to remove time nodes that cannot participate in the subsequent optimization process as the number of preset key nodes increases layer by layer.

4. The method according to claim 2, characterized in that, The minimum total cost of sales monitoring satisfies the following formula: Where P(λ) represents the total cost of sales monitoring, and m represents the number of preset time points. This is used to represent the sales variation cost corresponding to the sales period defined by the (j-1)th preset time point and the jth preset time point. Used to represent ticket sales data between the (j-1)th preset time point and the jth preset time point. Used to represent the j-th preset time point Used to represent the penalty coefficient for monitoring frequency.

5. The method according to any one of claims 2-4, characterized in that, The calculation of sales variation costs within each of the aforementioned sales periods includes: For each sales period, the sales variation cost within the sales period is determined based on the cumulative ticket sales data corresponding to the first time node, the cumulative ticket sales data corresponding to the second time node, and the target ticket sales data; wherein the first time node and the second time node are the start and end times of the sales period, respectively; and the target ticket sales data is determined based on the cumulative ticket sales data corresponding to the first time node and the cumulative ticket sales data corresponding to the second time node.

6. The method according to any one of claims 2-4, characterized in that, The constraints for the objective optimization algorithm include at least one of the following: complete sales period coverage constraint, segment point time sequence constraint, and segment non-empty constraint; wherein, the complete sales period coverage constraint is used to ensure that all sales time periods are consistent with the data within the flight sales period, the segment point time sequence constraint is used to ensure that the preset time points are arranged according to the number of days from the flight departure date, and the segment non-empty constraint is used to ensure that the preset time points are unit time points, and the unit time point is the time point within the flight sales period that has cumulative ticket sales data.

7. The method according to claim 1, characterized in that, The issuance of control reminder information based on the multiple key time nodes includes: Acquire ticket sales data change information for at least one key time period, and generate control reminder information corresponding to each key time period based on the ticket sales data change information for each key time period; the key time period is defined by two adjacent key time nodes. The multiple key time nodes are matched with the sales timeline of the currently operating flights to generate at least one actual reminder date. The key time nodes are the time nodes before the flight takes off, and the actual reminder date is the earliest key time node among the two key time nodes in the key time period. Based on the at least one actual reminder date, issue at least one control reminder message corresponding to the key time period, with one actual reminder date corresponding to one control reminder message.

8. A device for adjusting flight sales information, characterized in that, The device includes: The acquisition module is used to acquire the cumulative ticket sales data of historical flights recorded in chronological order during the flight sales period, and generate the historical sales progress sequence of the historical flights, wherein the cumulative ticket sales data is the ticket sales data accumulated before a certain time point; The processing module is used to determine multiple key time nodes based on the change characteristics between the cumulative ticket sales data in the historical sales progress sequence. The key time nodes are the time nodes when the change in the cumulative ticket sales data is greater than a preset change threshold. The sending module is used to send control reminder information based on the multiple key time nodes. The control reminder information is used to instruct the sales information of the currently operating flights to be adjusted at the key time nodes.

9. A device for adjusting flight sales information, characterized in that, include: Processor and memory; The processor and the memory are coupled; The memory is used to store one or more programs, the one or more programs including computer device execution instructions. When the flight sales information adjustment prompting device is running, the processor executes the computer device execution instructions stored in the memory to cause the flight sales information adjustment prompting device to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium storing instructions, characterized in that, When the computer device executes the instruction, the computer device performs the method as described in any one of claims 1-7.

Images