CN115169758B

CN115169758B - Reservation data prediction method and device, storage medium and electronic equipment

Info

Publication number: CN115169758B
Application number: CN202211087854.9A
Authority: CN
Inventors: 王忠韬; 孙琼巍; 杨玲; 王东升
Original assignee: China Travelsky Technology Co Ltd
Current assignee: China Travelsky Technology Co Ltd
Priority date: 2022-09-07
Filing date: 2022-09-07
Publication date: 2022-11-25
Anticipated expiration: 2042-09-07
Also published as: CN115169758A

Abstract

The application provides a reservation data prediction method and device, a storage medium and an electronic device, which can be applied to the technical field of data processing, and the method comprises the following steps: the method comprises the steps of predicting target limit booking data of a future flight at the last acquisition time point through a historical limit booking data change curve, obtaining the target limit booking data of each acquisition time point between the current acquisition time point and the last acquisition time point based on the booking data generated by the future flight, the historical limit booking data change curve and the target limit booking data of the future flight at the last acquisition time point, obtaining reachable booking data of each acquisition time point between the next acquisition time point and the last acquisition time point of the current acquisition time point based on each target limit booking data, and further drawing a reachable booking data change curve of the future flight. Therefore, the technical scheme realizes the prediction of the booking data of the future flight, thereby improving the flight profit.

Description

Reservation data prediction method and device, storage medium and electronic equipment

Technical Field

The present application relates to the field of data processing technologies, and in particular, to a seat reservation data prediction method and apparatus, a storage medium, and an electronic device.

Background

The seat booking data prediction is the basis of the flight seat allocation decision, and the seat number can be reasonably allocated to the cabin of each level only by mastering the requirements of the cabin of each level in the future, so that the benefit of the flight cannot be influenced by excessive low-price seats, the flight seat cannot be sold due to excessive high price, and the maximization of the benefit of the whole flight is achieved.

Therefore, how to provide a technical solution capable of predicting reservation data of future flights is a problem that needs to be solved urgently by those skilled in the art.

Disclosure of Invention

The application provides a reservation data prediction method and device, a storage medium and electronic equipment, and aims to realize prediction of reservation data of future flights.

In order to achieve the above object, the present application provides the following technical solutions:

a first aspect of the present application discloses a reservation data prediction method, including:

acquiring the history of historical flights to limit the change curve of the reservation data and the reservation data generated by future flights; the historical unrestricted booking data change curve comprises historical unrestricted booking data of a plurality of acquisition time points;

predicting target order-limitation-free data of the future flight at the last acquisition time point based on the historical order-limitation-free data change curve;

determining a current acquisition time point from all acquisition time points based on reservation data generated by the future flight, and acquiring target reservation limiting data of the current acquisition time point;

acquiring target unrestricted booking data of each first acquisition time point based on the target unrestricted booking data of the current acquisition time point, the target unrestricted booking data of the last acquisition time point and the historical restricted booking data change curve; wherein the first acquisition time point is an acquisition time point between the current acquisition time point and the last acquisition time point;

based on the target limitation data of each second acquisition time point, acquiring reachable booking data of each second acquisition time point; wherein the second acquisition time point is an acquisition time point between the current acquisition time point and the last acquisition time point;

and drawing a reachable seat data change curve of the future flight based on reachable seat data of each acquisition time point.

A second aspect of the present application discloses a reservation data prediction apparatus, comprising:

the first acquisition unit is used for acquiring the history of historical flights to limit the change curve of the reservation data and the reservation data generated by future flights; the historical unrestricted booking data change curve comprises historical unrestricted booking data of a plurality of acquisition time points;

the prediction unit is used for predicting target reservation-removing data of the future flight at the last acquisition time point based on the historical reservation-removing data change curve;

a second obtaining unit, configured to determine a current collection time point from each collection time point based on seat reservation data generated by the future flight, and obtain target limitation seat reservation data of the current collection time point;

a third obtaining unit, configured to obtain target unrestricted seat booking data of each first collection time point based on the target unrestricted seat booking data of the current collection time point, the target unrestricted seat booking data of the last collection time point, and the historical unrestricted seat booking data change curve; wherein the first acquisition time point is an acquisition time point between the current acquisition time point and the last acquisition time point;

the fourth acquisition unit is used for acquiring reachable order data of each second acquisition time point based on the target limitation data of each second acquisition time point; wherein the second acquisition time point is an acquisition time point between the current acquisition time point and the last acquisition time point;

and the drawing unit is used for drawing the reachable seat data change curve of the future flight based on the reachable seat data of each acquisition time point.

A third aspect of the present application discloses a storage medium storing a set of instructions, wherein the set of instructions, when executed by a processor, implements a reservation data prediction method as described above.

The fourth aspect of the present application discloses an electronic device, comprising:

a memory for storing at least one set of instructions;

a processor for executing a set of instructions stored in said memory, said set of instructions being executable to implement a method for subscription data prediction as described above.

Compared with the prior art, the method has the following advantages:

the application provides a reservation data prediction method and device, a storage medium and an electronic device, wherein the method comprises the following steps: the method comprises the steps of predicting target unlimited booking data of a future flight at the last acquisition time point through a historical unlimited booking data change curve, obtaining the target unlimited booking data of each acquisition time point between the current acquisition time point and the last acquisition time point based on the booking data generated by the future flight, the historical unlimited booking data change curve and the target unlimited booking data of the future flight at the last acquisition time point, and obtaining reachable booking data of each acquisition time point between the next acquisition time point and the last acquisition time point of the current acquisition time point based on the target unlimited booking data, so that the reachable booking data change curve of the future flight can be drawn. Therefore, the technical scheme realizes the prediction of the booking data of the future flight, thereby improving the flight profit.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

FIG. 1 is a flow chart of a method for predicting seat booking data provided by the present application;

FIG. 2 is a flowchart of another method for predicting reservation data according to the present application;

FIG. 3 is a flowchart of another method of the present application for predicting seat booking data;

FIG. 4 is a flowchart of another method of predicting seat reservation data according to the present application;

FIG. 5 is a flowchart of another method of the present application for predicting seat booking data;

fig. 6 is a schematic structural diagram of a reservation data prediction apparatus provided in the present application;

fig. 7 is a schematic structural diagram of an electronic device provided in the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.

It should be noted that the terms "first", "second", and the like in the disclosure of the present application are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in the disclosure herein are exemplary rather than limiting, and those skilled in the art will understand that "one or more" will be understood unless the context clearly dictates otherwise.

The application is operational with numerous general purpose or special purpose computing device environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multi-processor appliances, distributed computing environments that include any of the above devices or equipment, and the like.

The embodiment of the present application provides a seat booking data prediction method, which may be applied to a plurality of system platforms, an execution subject of the method may be a computer terminal or a processor of various mobile devices, and a flowchart of the method is shown in fig. 1, and specifically includes:

s101, obtaining the history of the historical flights to limit the change curve of the reservation data and the reservation data generated by future flights.

In this embodiment, historical booking data of the historical flights at each collection time point is acquired, the historical booking data is subjected to limitation removal processing, an average historical booking value of each collection time point is calculated, invalidity judgment is performed on each historical average value, data correction is performed on the invalid average historical booking value, a sales data change initial curve of the historical flights is drawn based on the average historical booking value after data correction and the average historical booking value judged to be an effective value, and curve smoothing processing is performed on the sales data change initial curve to obtain a historical limitation-removal booking data change curve.

The historical unlimited booking data change curve comprises historical unlimited booking data of a plurality of collection time points.

In this embodiment, the generated reservation data of the future flight is obtained, and it should be noted that the generated reservation data of the future flight is the original reservation data.

S102, predicting target reservation-limiting data of the future flight at the last acquisition time point based on the historical reservation-limiting data change curve.

In this embodiment, the target reservation data of the future flight at the last collection time point is predicted based on the historical reservation data change curve. And the last acquisition time point is the time point which is closest to the departure of the historical flights in all the acquisition time points.

Specifically, based on the historical unrestricted booking data of each acquisition time point included in the historical unrestricted booking data change curve, the historical unrestricted booking data of each acquisition time point is processed by using a pre-constructed prediction model, and the target unrestricted booking data of the future flight at the last acquisition time point is obtained.

The prediction model is obtained by training a regression model in advance.

S103, determining the current acquisition time point from all the acquisition time points based on the reservation data generated by the future flight, and acquiring the target of the current acquisition time point to limit the reservation data.

In this embodiment, based on the seat data generated by the future flight, the closest time point before the departure of the future flight in the generated seat data is determined, for example, the future flight is the departure No. 5/month 1 in 2022, the obtained seat data generated by the future flight is the seat data before the departure No. 3/month 1 in 2022 and the seat data before the departure No. 3/month 1 in 2022, and the closest time point before the departure of the future flight is determined to be the departure No. 3/month 1 in 2022.

In this embodiment, the current collection time point is determined from the collection time points based on the determined time point closest to the departure of the future flight, where the current collection time is the determined time point closest to the departure of the future flight or is before and closest to the determined time point closest to the departure of the future flight. For example, if the determined time point closest to the departure of the future flight is 3/1 in 2022, and the respective collection time points are Dcp1 (120 days before the departure of the flight), dcp2 (80 days before the departure of the flight), dcp3 (50 days before the departure of the flight), dcp4 (30 days before the departure of the flight), dcp5 (15 days before the departure of the flight), dcp6 (7 days before the departure of the flight), dcp7 (3 days before the departure of the flight), dcp8 (2 days before the departure of the flight), dcp9 (1 day before the departure of the flight), dcp10 (0 day before the departure of the flight, that is, the day on which the flight takes off), the determined time point closest to the departure of the future flight is 2022 years, namely, 1/3/2022 years, the current time point is Dcp2.

In this embodiment, after the current time point is determined, the target unrestricted seat data at the current acquisition time point is obtained based on the seat data generated by the future flight, specifically, the seat data generated by the future flight is subjected to restriction removal processing to obtain the unrestricted seat data, the unrestricted seat data corresponding to the current acquisition time point is determined from each unrestricted seat data, and the restricted seat data corresponding to the current acquisition time point is determined as the target unrestricted seat data at the current acquisition time point.

In this embodiment, the process of performing the limitation removal processing on the reservation data generated by the future flight is to perform the limitation removal processing on the reservation data generated by the future flight by using a limitation removal algorithm. Illustratively, the de-restriction algorithm may be a Baseline algorithm or an EM algorithm.

S104, acquiring the target unrestricted booking data of each first acquisition time point based on the target unrestricted booking data of the current acquisition time point, the target unrestricted booking data of the last acquisition time point and a historical unrestricted booking data change curve.

In this embodiment, the target unrestricted booking data of each first acquisition time point is obtained based on the target unrestricted booking data of the current acquisition time point, the target unrestricted booking data of the last acquisition time point, and the history unrestricted booking data change curve, wherein the first acquisition time point is an acquisition time point between the current acquisition time point and the last acquisition time point, that is, the first acquisition time point is an acquisition time point of each acquisition time point except an acquisition time point before the current acquisition time point, and the last acquisition time point; for example, if the respective acquisition time points are Dcp1, dcp2, dcp3, dcp4, dcp5, dcp6, dcp7, dcp8, dcp9, and Dcp10, the current acquisition time point is Dcp2, and the last acquisition time point is Dcp10, dcp3, dcp4, dcp5, dcp6, dcp7, dcp8, and Dcp9 are all used as the first acquisition time points.

Referring to fig. 2, the process of obtaining the target unlimited seat data at each first collection time point based on the target unlimited seat data at the current collection time point, the target unlimited seat data at the last collection time point, and the historical unlimited seat data change curve specifically includes the following steps:

s201, based on the historical restriction booking data change curve, obtaining historical restriction booking data of the current collection time point and historical restriction booking data of the last collection time point.

In this embodiment, the historical unlimited booking data at the current collection time point and the historical unlimited booking data at the last collection time point are obtained through the historical unlimited booking data change curve.

S202, based on the historical unlimited booking data of the current collection time point and the historical unlimited booking data of the last collection time point, calculating a historical booking difference value.

In this embodiment, a historical reservation difference is calculated based on the historical unlimited reservation data at the current collection time point and the historical unlimited reservation data at the last collection time point, and specifically, a historical reservation difference is obtained by calculating a difference between the historical unlimited reservation data at the last collection time point and the historical unlimited reservation data at the current collection time point.

Alternatively, the historical debounce seat data for the current acquisition time point may be represented by presenthssbk, and the historical debounce seat data for the last acquisition time point may be represented by finalhesbk, then the historical seat difference hisDif = finalhesbk-presenthbsbk.

S203, calculating a target reservation difference value based on the target reservation removal data of the current collection time point and the target reservation removal data of the last collection time point.

In this embodiment, a target reservation data difference is calculated based on the target unrestricted reservation data at the current collection time point and the target unrestricted reservation data at the last collection time point, and specifically, the target unrestricted reservation data at the last collection time point and the target unrestricted reservation data at the current collection time point are calculated to obtain the target reservation difference.

Alternatively, the target unrestricted seat data for the current acquisition time point may be represented by presentBk, and the target unrestricted seat data for the last acquisition time point may be represented by finalBk, then the target seat difference value, dif = finalBk-presentBk.

S204, calculating a difference ratio based on the target seat difference and the historical seat difference.

In this embodiment, the difference ratio is calculated based on the target seat booking difference and the historical seat booking difference.

Referring to fig. 3, a process for calculating a difference ratio based on a target seat difference and a historical seat difference includes the steps of:

s301, judging whether the historical booking difference value is zero, if so, executing S302, otherwise, executing S303.

S302, assigning a zero value to the difference ratio.

In this embodiment, if the historical booking difference is zero, a zero value is assigned to the difference ratio diffatio, that is, diffatio =0.

S303, calculating a difference ratio based on the target seat difference and the historical seat difference.

In this embodiment, the difference ratio is calculated based on the target seat difference and the historical seat difference, and specifically, the difference ratio is obtained by dividing the target seat difference by the historical seat difference. I.e. the difference ratio diffatio = Dif/hisDif.

S205, judging whether the difference ratio is within a preset interval, if so, executing S206, and if not, executing S207.

In this embodiment, it is determined whether the difference ratio is within a preset interval, where the preset interval is an artificially set interval and can be adjusted according to a requirement, and the preferred preset interval is (0, 2).

S206, aiming at each first collection time point, calculating target restriction-free reservation data of the first collection time point based on the target reservation difference value, the historical restriction-free reservation data of the first collection time point, the target restriction-free reservation data of the previous collection time point of the first collection time point and the historical restriction-free reservation data.

In this embodiment, if the difference is within the preset interval, for each first collection time point, the target unrestricted booking data at the first collection time point is calculated through a preset formula based on the target booking difference, the historical unrestricted booking data at the first collection time point, the target unrestricted booking data at the previous collection time point at the first collection time point, and the historical unrestricted booking data.

Wherein, the preset formula is as follows:

uncBk[Dcp]=leftBk+min(2,(hisBk-leftHisBk)/hisDif)*Dif

wherein uncBk [ Dcp ] represents target unrestricted seat data at a first acquisition time point, leftBk represents target unrestricted seat data at a previous acquisition time point to the first acquisition time point, hisBk represents historical unrestricted seat data at the first acquisition time point, leftHisBk represents historical unrestricted seat data at a previous acquisition time point to the first acquisition time point, hisDif represents a historical seat difference value, and Dif represents a target seat difference value.

In this embodiment, the historical unrestricted seat reservation data at the previous collection time point from the first collection time point is determined based on the historical unrestricted seat reservation data change curve.

It should be noted that, the target order restriction data at the first acquisition time points are sequentially calculated according to the sequence of the days in advance from large to small corresponding to each first acquisition time point.

S207, aiming at each first acquisition time point, calculating the target restriction-free subscriber data of the first acquisition time point based on the advance days corresponding to the first acquisition time point, the advance days corresponding to the previous acquisition time point of the first acquisition time point, the advance days corresponding to the last acquisition time point, the target subscriber difference value, the historical restriction-free subscriber data of the first acquisition time point, the target restriction-free subscriber data and the historical restriction-free subscriber data of the previous acquisition time point of the first acquisition time point.

In this embodiment, if the difference is not within the preset interval, for each first acquisition time point, the target unrestricted seat data of the first acquisition time point is calculated based on the number of days ahead of the first acquisition time point, the number of days ahead of the last acquisition time point, the target seat difference, the historical unrestricted seat data of the first acquisition time point, the target unrestricted seat data and the historical unrestricted seat data of the previous acquisition time point of the first acquisition time point.

In this embodiment, referring to fig. 4, a specific implementation process of step S207 includes the following steps:

s401, calculating the day deviation based on the number of days in advance corresponding to the first acquisition time point, the number of days in advance corresponding to the acquisition time point before the first acquisition time point and the number of days in advance corresponding to the last acquisition time point.

In this embodiment, the number-of-days deviation is calculated based on the number of days in advance corresponding to the first acquisition time point, the number of days in advance corresponding to the previous acquisition time point of the first acquisition time point, and the number of days in advance corresponding to the last acquisition time point, and the number-of-days deviation is calculated by a preset number-of-days deviation calculation formula.

The preset day deviation calculation formula is as follows:

dDifRatio=(leftDPrior-dPrior)/(leftDPrior-finalDPrior)

wherein, dDifRatio represents the day deviation, leftDPrior represents the number of days in advance corresponding to the previous acquisition time point of the first acquisition time point, dPrior represents the number of days in advance corresponding to the first acquisition time point, and finalDPrior represents the number of days in advance corresponding to the last acquisition time point.

S402, limiting seat data, day deviation and historical seat difference values based on the history of the previous acquisition time point of the first acquisition time point, and calculating a historical value.

In this embodiment, the seat data, the day deviation, and the historical seat difference are limited based on the history of the previous collection time point of the first collection time point, and the historical value is calculated by a historical value calculation formula.

Wherein, the historical value calculation formula is as follows:

hisV=leftHisBk+dDifRatio*hisDif

where hisV represents a historical value, leftHisBk represents a historical order-limiting data set based on a previous acquisition time point to the first acquisition time point, dysdifratio represents a day deviation, and hisDif represents a historical order difference.

S403, based on the target reservation data, the day deviation and the target reservation difference value of the previous acquisition time point of the first acquisition time point, calculating a current value.

In this embodiment, the current value is calculated by a current value calculation formula based on the target restriction seat data, the day deviation, and the target seat difference at the previous acquisition time point to the first acquisition time point.

Wherein, the current value calculation formula is as follows:

newV=leftBk+dDifRatio*Dif

wherein newV represents the current value, leftBk represents the target out-of-order data for the previous acquisition time point to the first acquisition time point, dsiratio represents the day deviation, and Dif represents the target out-of-order difference.

S404, judging whether the current value is smaller than the historical value, if not, executing S405, and if so, executing S406.

S405, based on the historical value, the current value and the historical seat-booking-removal data of the first collection time point, calculating target seat-booking-removal data of the first collection time point through a preset first formula.

In this embodiment, if the current value is not less than the historical value, the target unlimited booking data at the first collection time point is calculated by presetting a first formula based on the historical value, the current value, and the historical unlimited booking data at the first collection time point.

Wherein, the preset first formula is as follows:

uncBk[Dcp]=newV+hisBk–hisV

wherein uncBk [ Dcp ] represents target unrestricted seat data at the first acquisition time point, newV represents the current value, hisBk represents historical unrestricted seat data at the first acquisition time point, and hisV represents the historical value.

And S406, judging whether the historical value is larger than a preset threshold value, if so, executing S407, and if not, executing S408.

In this embodiment, if the current value is smaller than the history value, it is further determined whether the history value is larger than a preset threshold, and preferably, the preset threshold may be a zero value.

S407, based on the historical value, the current value and the historical limitation-free booking data of the first collection time point, calculating target limitation-free booking data of the first collection time point through a preset second formula.

And if the current value is smaller than the historical value and the historical value is larger than the preset threshold value, calculating target seat-booking-removal data at the first acquisition time point through a preset second formula based on the historical value, the current value and the historical seat-booking-removal data at the first acquisition time point.

Wherein, the preset second formula is:

uncBk[Dcp]=newV*hisBk/hisV

and S408, determining the current value as the target reservation limiting data of the first acquisition time point.

In this embodiment, if the current value is smaller than the historical value and the current value is not larger than the preset threshold, the current value is determined as the target unrestricted seat booking data at the first collection time point.

And S105, acquiring reachable order data of each second acquisition time point based on the target limitation data of each second acquisition time point.

In this embodiment, reachable reservation data at each second acquisition time point is obtained based on the target limitation data at each second acquisition time point.

The second acquisition time point is an acquisition time point between the current acquisition time point and the last acquisition time point, that is, each of the first acquisition time point, the current acquisition time point and the last acquisition time point is determined as the second acquisition time point.

Referring to fig. 5, the process of obtaining reachable reservation data at each second acquisition time point based on the target limitation removal data at each second acquisition time point specifically includes the following steps:

s501, determining reachable booking data and target limitation booking data of a floating acquisition time point based on the booking data generated by the future flight.

In this embodiment, from seat data generated from the previous flight, seat data corresponding to the floating acquisition time point is determined, and the seat data corresponding to the floating acquisition time point is determined as reachable seat data with the floating acquisition time. And the floating acquisition time point is the time point which is closest to the take-off of the future flight in the time points corresponding to the reservation data. For example, if the future flight is the takeoff of 5 month 1 in 2022, the acquired future flight has generated the reservation data of 3 month 1 in 2022 and the reservation data before 3 month 1, the floating time point is 3 month 1 in 2022, that is, 61 days before the departure of the future flight.

In this embodiment, the unrestricted booking data generated by the future flight is processed to obtain the unrestricted booking data, the unrestricted booking data corresponding to the floating acquisition time point is determined from each unrestricted booking data, and the unrestricted booking data corresponding to the floating acquisition time point is determined as the target unrestricted booking data of the floating acquisition time point.

And S502, determining the reachable order data of the floating acquisition time point as a reachable value.

S503, determining the target destrained booking data of the floating acquisition time point as a destrained value.

S504, according to the time sequence of the acquisition time points, the second acquisition time points form a time point sequence, and a first second acquisition time point in the time point sequence is used as a target acquisition time point.

And S505, judging whether the target limitation removing and booking data of the target acquisition time point is smaller than a limitation removing value, wherein the limitation removing value is not a zero value, if not, executing S506, and if so, executing S507.

S506, based on the target restriction-free seat data, the reachable value and the restriction-free value of the target acquisition time point, the reachable seat data of the target acquisition time point is calculated through a preset third formula.

In this embodiment, if the target unrestricted seat data at the target collection time point is not less than the unrestricted value, or the unrestricted value is zero, the reachable seat data at the target collection time point is calculated by presetting a third formula based on the target unrestricted seat data, the reachable value, and the unrestricted value at the target collection time point.

Wherein, the preset third formula is:

aimBk[Dcp]=aim+uncBk[Dcp]–uncBkP

wherein aimBk [ Dcp ] represents reachable seat data at a target acquisition time point, aim represents a reachable value, uncBk [ Dcp ] represents target unrestricted seat data at the target acquisition time point, and uncBkP represents a unrestricted value.

And S507, calculating the reachable seat data of the target acquisition time point through a preset fourth formula based on the target unlimited seat data, the reachable value and the unlimited value of the target acquisition time point.

In this embodiment, if the target unrestricted seat booking data of the target collection time point is smaller than the unrestricted value and the unrestricted value is not a zero value, the reachable seat booking data of the target collection time point is calculated by presetting a fourth formula based on the target unrestricted seat booking data, the reachable value and the unrestricted value of the target collection time point.

Wherein, the preset fourth formula is:

aimBk[Dcp]=aim*uncBk[Dcp]/uncBkP

and S508, judging whether the target acquisition time point is the last second acquisition time point in the time point sequence, if so, executing S509, and if not, directly ending.

In this embodiment, it is determined whether the target collection time point is the last second collection time point in the time point sequence, if the target collection time point is not the last second collection time point in the time point sequence, it indicates that reachable seat data of the second collection time point is not obtained, and step S509 is executed, and if the target collection time point is the last collection time point in the time point sequence, it indicates that reachable seat data of all the second collection time points are obtained, and the current cycle is ended.

S509, determining the reachable seat data of the target acquisition time point as a new reachable value, determining the target derstriction seat data of the target acquisition time point as a new derstriction value, determining a second acquisition time point next to the target acquisition time point in the time point sequence as a new target acquisition time point, and returning to execute S505 based on the new target acquisition time point, the new reachable value and the new derstriction value.

In this embodiment, if the target collection time point is not the last second collection time point in the time point sequence, the reachable subscription data of the target collection time point is determined as a new reachable value, the target unrestricted subscription data of the target collection time point is determined as a new unrestricted value, the next second collection time point of the target collection time point in the time point sequence is determined as a new target collection time point, and the step S505 is executed in a return manner based on the new target collection time point, the new reachable value, and the new unrestricted value.

And S106, drawing a reachable seat data change curve of the future flight based on the reachable seat data of each acquisition time point.

In this embodiment, the reachable reservation data change curve of the future flight is drawn based on the reachable reservation data at each collection time point. The reachable order data of each collection time point before the floating collection time point is determined based on the order data generated by the future flight, that is, for each collection time point before the floating collection time point, the order data corresponding to the collection time point in the order data generated by the future flight is the reachable order data of the collection time point.

The method for predicting seat booking data provided by the embodiment of the application predicts the target limit seat booking data of the future flight at the last acquisition time point through the historical limit seat booking data change curve, and obtains the target limit seat booking data of each acquisition time point between the current acquisition time point and the last acquisition time point based on the seat booking data generated by the future flight, the historical limit seat booking data change curve and the target limit seat booking data of the future flight at the last acquisition time point, so that the reachable seat booking data of each acquisition time point between the next acquisition time point and the last acquisition time point of the current acquisition time point is obtained based on each target limit seat booking data, and the reachable seat data change curve of the future flight can be drawn. Therefore, the technical scheme realizes the prediction of the booking data of the future flight, thereby improving the flight profit.

The implementation process of the above-mentioned reservation data prediction method is exemplified as follows:

the original historical flight data is subjected to limitation removal processing, and the obtained historical flight data is shown in table 1:

TABLE 1 historical flight data sheet

The historical debottlenecking of historical flights for each collection time point included in the historical debottlenecking data variation curve is shown in table 2:

TABLE 2 History unrestricted booking data sheet

(1) Performing curve backfill calculation on the 11/15/2020 and the 11/22/2020 flights; the resulting target unrestricted booking data for each collection point is shown in table 3:

TABLE 3 destination unrestricted booking data sheet

The curve backfill is calculated as follows:

1) Set Dif = finalBk-presentBk, hisDif = finalHisBk-presenthhisbk (full line segment increment);

2) If hisDif ≠ 0, difRatio = Dif/hisDif; otherwise diffatio =0;

3) For each Dcp between presentDcp and finalDcp, take hisBk = uncHistory [ Dcp ], and dPrior is the number of days ahead of Dcp. The following steps are completed:

4) If 0 is not more than DifRatio 2, uncBk [ 2], [ Dcp ] = leftBk + min (2, (hisBk-leftHisBk)/hisDif) (the ratio of the partial segment increment and the full segment increment for the future and the history two curves is equal);

5) Otherwise (instead of 0-straw DifRatio ≦ 2),

a.dDifRatio=(leftDPrior-dPrior)/(leftDPrior-finalDPrior)；

b.hisV=leftHisBk+dDifRatio*hisDif；

c.newV=leftBk+dDifRatio*Dif；

d. if newV is larger than or equal to hisV, uncBk [ Dcp ] = newV + hisBk-hisV (same amount increase);

e. otherwise, if newV < hisV and hisV >0, uncBk [ Dcp ] = newV = hisBk/hisV (same scale down);

f. otherwise, if newV < hisV and hisV =0, uncBk [ Dcp ] = newV.

(2) Curve simulation calculations were performed on 11/15/2020, 11/22/2020 flights, resulting in reachable reservation data for each pick-up point as shown in Table 4:

TABLE 4 reachable reservation data sheet

Wherein, the curve simulation calculation process comprises:

1) Let aimvable = aimdbk [ presentDcp ], uncBkP = uncBk [ presentDcp ];

2) For each Dcp from startDcp to finalDcp:

a. let uncBkC = uncBk [ Dcp ];

b. if uncBkC is greater than or equal to uncBkP or uncBkP =0, aimBk [ Dcp ] = aim + uncBkC-uncBkP;

c. otherwise, aimBk [ Dcp ] = aim. UncBkC/uncBkP;

d.aim=aimBk[Dcp]，uncBkP=uncBkC。

it should be noted that while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous.

It should be understood that the various steps recited in the method embodiments disclosed herein may be performed in a different order and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the disclosure is not limited in this respect.

Corresponding to the method described in fig. 1, an embodiment of the present application further provides a reservation data prediction apparatus, which is used for specifically implementing the method in fig. 1, and a schematic structural diagram of the reservation data prediction apparatus is shown in fig. 6, and specifically includes:

a first obtaining unit 601, configured to obtain a history of historical flights to limit a seat data change curve and seat data that has been generated by future flights; the historical unrestricted booking data change curve comprises historical unrestricted booking data of a plurality of acquisition time points;

a predicting unit 602, configured to predict target unlimited booking data of the future flight at the last acquisition time point based on the historical unlimited booking data variation curve;

a second obtaining unit 603, configured to determine a current collecting time point from each collecting time point based on the reservation data generated by the future flight, and obtain a target reservation limiting data of the current collecting time point;

a third obtaining unit 604, configured to obtain target unrestricted seat data at each first collection time point based on the target unrestricted seat data at the current collection time point, the target unrestricted seat data at the last collection time point, and the history unrestricted seat data change curve; wherein the first acquisition time point is an acquisition time point between the current acquisition time point and the last acquisition time point;

a fourth obtaining unit 605, configured to obtain reachable reservation data at each second acquisition time point based on the target limitation-removing data at each second acquisition time point; wherein the second acquisition time point is an acquisition time point between the current acquisition time point and the last acquisition time point;

the drawing unit 606 is configured to draw an reachable seat data change curve of the future flight based on reachable seat data at each collection time point.

The reservation data prediction device provided in the embodiment of the application predicts the target reservation data of the future flight at the last acquisition time point through the historical reservation data change limiting curve, and obtains the target reservation data of each acquisition time point between the current acquisition time point and the last acquisition time point based on the reservation data generated by the future flight, the historical reservation data change limiting curve and the target reservation data of the future flight at the last acquisition time point, so as to obtain the reachable reservation data of each acquisition time point between the next acquisition time point and the last acquisition time point of the current acquisition time point based on each target reservation data, and further draw the reachable reservation data change curve of the future flight. Therefore, the technical scheme realizes the prediction of the booking data of future flights, thereby improving the flight income.

In an embodiment of the present application, based on the foregoing solution, the third obtaining unit 604 is specifically configured to:

acquiring historical unlimited booking data of the current acquisition time point and historical unlimited booking data of the last acquisition time point based on the historical unlimited booking data change curve;

calculating a historical booking difference value based on the historical unlimited booking data of the current collection time point and the historical unlimited booking data of the last collection time point;

calculating a target reservation difference value based on the target reservation-removing data at the current collection time point and the target reservation-removing data at the last collection time point;

calculating a difference ratio based on the target seat difference and the historical seat difference;

if the difference ratio is within a preset interval, calculating target unrestricted booking data of each first acquisition time point based on the target booking difference, the historical unrestricted booking data of the first acquisition time point, the target unrestricted booking data of the previous acquisition time point of the first acquisition time point and the historical unrestricted booking data;

if the difference ratio is not within the preset interval, for each first collection time point, calculating the target restriction-free subscriber data of the first collection time point based on the number of days ahead corresponding to the first collection time point, the number of days ahead corresponding to the previous collection time point of the first collection time point, the number of days ahead corresponding to the last collection time point, the target subscriber difference, the historical restriction-free subscriber data of the first collection time point, the target restriction-free subscriber data and the historical restriction-free subscriber data of the previous collection time point of the first collection time point.

In an embodiment of the application, based on the foregoing solution, when calculating the target deregulated subscriber data at the first collection time point based on the number of days in advance corresponding to the first collection time point, the number of days in advance corresponding to the previous collection time point at the first collection time point, the number of days in advance corresponding to the last collection time point, the target subscriber difference, the historical deregulated subscriber data at the first collection time point, the target deregulated subscriber data at the previous collection time point at the first collection time point, and the historical deregulated subscriber data at the first collection time point, the third obtaining unit 604 is specifically configured to:

calculating a day deviation based on the number of days in advance corresponding to the first acquisition time point, the number of days in advance corresponding to the acquisition time point previous to the first acquisition time point, and the number of days in advance corresponding to the last acquisition time point;

calculating a historical value based on historical order-limiting data of a previous acquisition time point of the first acquisition time point, the day deviation and the historical order difference value;

calculating a current value based on the target order limit data, the day deviation and the target order difference value of the previous acquisition time point of the first acquisition time point;

if the current value is not less than the historical value, calculating target unrestricted booking data of the first collection time point through a preset first formula based on the historical value, the current value and the historical unrestricted booking data of the first collection time point;

if the current value is smaller than the historical value and the historical value is larger than a preset threshold value, calculating target unrestricted booking data of the first collection time point through a preset second formula based on the historical value, the current value and the historical unrestricted booking data of the first collection time point;

and if the current value is smaller than the historical value and the historical value is not larger than a preset threshold value, determining the current value as the target destina-tion seat booking data of the first acquisition time point.

In an embodiment of the application, based on the foregoing solution, when calculating the difference ratio based on the target seat booking difference and the historical seat booking difference, the third obtaining unit 604 is specifically configured to:

judging whether the historical booking difference value is a zero value or not;

and if the historical booking difference value is not a zero value, calculating a difference value ratio based on the target booking difference value and the historical booking difference value.

In an embodiment of the present application, based on the foregoing scheme, the fourth obtaining unit 605 is specifically configured to:

determining reachable booking data and target limitation booking data of a floating acquisition time point based on the booking data generated by the future flight; the floating acquisition time point is the time point which is closest to the take-off of the future flight in the time points corresponding to the reservation data;

determining reachable order data of the floating acquisition time point as a reachable value;

determining the target limitation-removing booking data of the floating acquisition time point as a limitation-removing value;

according to the time sequence of the acquisition time points, forming a time point sequence by all the second acquisition time points, and taking a first second acquisition time point in the time point sequence as a target acquisition time point;

judging whether the target limitation removing booking data of the target acquisition time point is smaller than the limitation removing value, wherein the limitation removing value is not a zero value;

if the target unrestricted booking data of the target collection time point is not smaller than the unrestricted value or the unrestricted value is zero, calculating the reachable booking data of the target collection time point through a preset third formula based on the target unrestricted booking data, the reachable value and the unrestricted value of the target collection time point;

if the target unrestricted seat reservation data of the target collection time point is smaller than the unrestricted value and the unrestricted value is not a zero value, calculating reachable seat reservation data of the target collection time point through a preset fourth formula based on the target unrestricted seat reservation data of the target collection time point, the reachable value and the unrestricted value;

if the target acquisition time point is not the last second acquisition time point in the time point sequence, determining the reachable seat data of the target acquisition time point as a new reachable value, and determining the target unrestricted seat data of the target acquisition time point as a new unrestricted value;

determining a second acquisition time point next to the target acquisition time point in the time point sequence as a new target acquisition time point;

and returning to execute the step of judging whether the target unrestricted booking data of the target acquisition time point is smaller than the unrestricted value or not and the unrestricted value is not a zero value on the basis of the new target acquisition time point, the new reachable value and the new unrestricted value.

The embodiment of the present application further provides a storage medium, where an instruction set is stored in the storage medium, and when the instruction set runs, the reservation data prediction method disclosed in any of the above embodiments is executed.

An electronic device is further provided in an embodiment of the present application, and a schematic structural diagram of the electronic device is shown in fig. 7, which specifically includes a memory 701 configured to store at least one set of instruction sets; a processor 702 configured to execute a set of instructions stored in the memory, the set of instructions being executable to implement a method for subscription data prediction as disclosed in any of the above embodiments.

In the detailed description section, this application will repeat all of the protected material in the form of the claims, in the following detailed description:

fig. 1 provides a reservation data prediction method according to one or more embodiments disclosed herein, including: acquiring the history of historical flights to limit the change curve of the reservation data and the reservation data generated by future flights; the historical unrestricted booking data change curve comprises historical unrestricted booking data of a plurality of acquisition time points; predicting target order-limitation-free data of the future flight at the last acquisition time point based on the historical order-limitation-free data change curve; determining a current acquisition time point from all acquisition time points based on the reservation data generated by the future flight, and acquiring target reservation limiting data of the current acquisition time point; acquiring target unrestricted booking data of each first acquisition time point based on the target unrestricted booking data of the current acquisition time point, the target unrestricted booking data of the last acquisition time point and the historical restricted booking data change curve; wherein the first acquisition time point is an acquisition time point between the current acquisition time point and the last acquisition time point; based on the target limitation data of each second acquisition time point, acquiring reachable order data of each second acquisition time point; wherein the second acquisition time point is an acquisition time point between the current acquisition time point and the last acquisition time point; and drawing an reachable seat data change curve of the future flight based on reachable seat data of each acquisition time point.

Fig. 2 provides another seat data prediction method according to one or more embodiments disclosed herein, including: acquiring historical unrestricted booking data of the current acquisition time point and historical unrestricted booking data of the last acquisition time point based on the historical unrestricted booking data change curve; calculating a historical booking difference value based on the historical unlimited booking data of the current collection time point and the historical unlimited booking data of the last collection time point; calculating a target reservation difference value based on the target reservation removal data at the current acquisition time point and the target reservation removal data at the last acquisition time point; calculating a difference ratio based on the target seat difference and the historical seat difference; if the difference ratio is within a preset interval, calculating target unrestricted booking data of each first acquisition time point based on the target booking difference, the historical unrestricted booking data of the first acquisition time point, the target unrestricted booking data of the previous acquisition time point of the first acquisition time point and the historical unrestricted booking data; if the difference ratio is not within the preset interval, for each first collection time point, calculating the target restriction-free subscriber data of the first collection time point based on the number of days ahead corresponding to the first collection time point, the number of days ahead corresponding to the previous collection time point of the first collection time point, the number of days ahead corresponding to the last collection time point, the target subscriber difference, the historical restriction-free subscriber data of the first collection time point, the target restriction-free subscriber data and the historical restriction-free subscriber data of the previous collection time point of the first collection time point.

In accordance with one or more embodiments disclosed herein, fig. 3 provides another seat reservation data prediction method, including: judging whether the historical booking difference value is zero or not; and if the historical booking difference value is not a zero value, calculating a difference value ratio based on the target booking difference value and the historical booking difference value.

Fig. 4 provides another seat reservation data prediction method according to one or more embodiments disclosed herein, including: calculating a day deviation based on the number of days in advance corresponding to the first acquisition time point, the number of days in advance corresponding to the acquisition time point previous to the first acquisition time point, and the number of days in advance corresponding to the last acquisition time point; calculating a historical value based on historical order-limiting data of a previous acquisition time point of the first acquisition time point, the day deviation and the historical order difference value; calculating a current value based on the target order limit data, the day deviation and the target order difference value of the previous acquisition time point of the first acquisition time point; if the current value is not less than the historical value, calculating target unrestricted booking data of the first collection time point through a preset first formula based on the historical value, the current value and the historical unrestricted booking data of the first collection time point; if the current value is smaller than the historical value and the historical value is larger than a preset threshold value, calculating target unrestricted booking data of the first collection time point through a preset second formula based on the historical value, the current value and the historical unrestricted booking data of the first collection time point; and if the current value is smaller than the historical value and the historical value is not larger than a preset threshold value, determining the current value as the target destrained seat booking data of the first acquisition time point.

Fig. 5 provides another seat data prediction method according to one or more embodiments disclosed herein, including: determining reachable booking data and target limitation booking data of a floating acquisition time point based on the booking data generated by the future flight; the floating acquisition time point is the time point which is closest to the take-off of the future flight in the time points corresponding to the reservation data; determining reachable order data of the floating acquisition time point as a reachable value; determining the target limitation-free booking data of the floating acquisition time point as a limitation-free value; according to the time sequence of the acquisition time points, forming a time point sequence by all the second acquisition time points, and taking the first second acquisition time point in the time point sequence as a target acquisition time point; judging whether the target limitation removing booking data of the target acquisition time point is smaller than the limitation removing value, wherein the limitation removing value is not a zero value; if the target unrestricted seat reservation data of the target collection time point is not smaller than the unrestricted value or the unrestricted value is zero, calculating the reachable seat reservation data of the target collection time point through a preset third formula based on the target unrestricted seat reservation data, the reachable value and the unrestricted value of the target collection time point; if the target unrestricted seat reservation data of the target collection time point is smaller than the unrestricted value and the unrestricted value is not a zero value, calculating reachable seat reservation data of the target collection time point through a preset fourth formula based on the target unrestricted seat reservation data of the target collection time point, the reachable value and the unrestricted value; if the target acquisition time point is not the last second acquisition time point in the time point sequence, determining reachable reservation data of the target acquisition time point as a new reachable value, and determining target unrestricted reservation data of the target acquisition time point as a new unrestricted value; determining a second acquisition time point next to the target acquisition time point in the time point sequence as a new target acquisition time point; and returning to execute the step of judging whether the target limitation removing seat booking data of the target acquisition time point is smaller than the limitation removing value or not and the limitation removing value is not equal to a zero value based on the new target acquisition time point, the new reachable value and the new limitation removing value.

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

While several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.

The foregoing description is only exemplary of the preferred embodiments disclosed herein and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the disclosure. For example, the above features and (but not limited to) technical features having similar functions disclosed in the present disclosure are mutually replaced to form the technical solution.

Claims

1. A reservation data prediction method, comprising:

predicting target order-limitation-free data of the future flight at the last acquisition time point based on the historical order-limitation-free data change curve, wherein the last acquisition time point is the time point which is closest to the departure of the historical flight in each acquisition time point;

determining a current acquisition time point from all acquisition time points based on the reservation data generated by the future flight, and acquiring a target of the current acquisition time point to limit the reservation data, wherein the current acquisition time is the determined time point closest to the future flight before takeoff;

calculating a target reservation difference value based on the target reservation removal data at the current acquisition time point and the target reservation removal data at the last acquisition time point;

if the difference ratio is not within a preset interval, calculating target restriction-free subscriber data of each first acquisition time point based on the number of days in advance corresponding to the first acquisition time point, the number of days in advance corresponding to the previous acquisition time point of the first acquisition time point, the number of days in advance corresponding to the last acquisition time point, the target subscriber difference, the historical restriction-free subscriber data of the first acquisition time point, the target restriction-free subscriber data and the historical restriction-free subscriber data of the previous acquisition time point of the first acquisition time point; wherein the first acquisition time point is an acquisition time point between the current acquisition time point and the last acquisition time point;

determining the reachable booking data of the floating acquisition time point as a reachable value;

according to the time sequence of the acquisition time points, forming a time point sequence by all the second acquisition time points, and taking the first second acquisition time point in the time point sequence as a target acquisition time point;

if the target unrestricted seat reservation data of the target collection time point is not smaller than the unrestricted value or the unrestricted value is zero, calculating the reachable seat reservation data of the target collection time point through a preset third formula based on the target unrestricted seat reservation data, the reachable value and the unrestricted value of the target collection time point;

if the target unrestricted booking data of the target collection time point is smaller than the unrestricted value and the unrestricted value is not a zero value, calculating the reachable booking data of the target collection time point through a preset fourth formula based on the target unrestricted booking data, the reachable value and the unrestricted value of the target collection time point;

if the target acquisition time point is not the last second acquisition time point in the time point sequence, determining reachable reservation data of the target acquisition time point as a new reachable value, and determining target unrestricted reservation data of the target acquisition time point as a new unrestricted value;

returning to the step of judging whether the target limitation-free booking data of the target acquisition time point is smaller than the limitation-free value or not and the limitation-free value is not equal to zero value based on the new target acquisition time point, the new reachable value and the new limitation-free value; wherein the second acquisition time point is an acquisition time point between the current acquisition time point and the last acquisition time point;

and drawing an reachable seat data change curve of the future flight based on reachable seat data of each acquisition time point.

2. The method of claim 1, wherein calculating the target unrestricted seat data for the first acquisition time point based on the number of days in advance corresponding to the first acquisition time point, the number of days in advance corresponding to a previous acquisition time point for the first acquisition time point, the number of days in advance corresponding to the last acquisition time point, the target seat difference, the historical unrestricted seat data for the first acquisition time point, the target unrestricted seat data for a previous acquisition time point for the first acquisition time point, and the historical unrestricted seat data comprises:

based on the historical booking data of the previous acquisition time point of the first acquisition time point, limiting booking data, the day deviation and the historical booking difference value, calculating a historical value;

3. The method of claim 1, wherein calculating a difference ratio based on the target seat difference and the historical seat difference comprises:

judging whether the historical booking difference value is zero or not;

4. A reservation data prediction apparatus, comprising:

the prediction unit is used for predicting target reservation-restricted data of the future flight at the last acquisition time point based on the historical reservation-restricted data change curve, wherein the last acquisition time point is the time point which is the closest to the departure of the historical flight in each acquisition time point;

a second obtaining unit, configured to determine a current collection time point from each collection time point based on the reservation data generated by the future flight, and obtain a target of the current collection time point to limit the reservation data, where the current collection time is a time point closest to the future flight before takeoff;

a third obtaining unit, configured to obtain target unrestricted seat data at each first collection time point based on the target unrestricted seat data at the current collection time point, the target unrestricted seat data at the last collection time point, and the history unrestricted seat data change curve; wherein the first acquisition time point is an acquisition time point between the current acquisition time point and the last acquisition time point;

the drawing unit is used for drawing a reachable seat data change curve of the future flight based on reachable seat data of each acquisition time point;

the third obtaining unit is specifically configured to:

acquiring historical unrestricted booking data of the current acquisition time point and historical unrestricted booking data of the last acquisition time point based on the historical unrestricted booking data change curve;

if the difference ratio is not within a preset interval, for each first acquisition time point, calculating target unrestricted seat data of the first acquisition time point based on the number of days in advance corresponding to the first acquisition time point, the number of days in advance corresponding to the previous acquisition time point of the first acquisition time point, the number of days in advance corresponding to the last acquisition time point, the target seat difference, the historical unrestricted seat data of the first acquisition time point, the target unrestricted seat data and the historical unrestricted seat data of the previous acquisition time point of the first acquisition time point;

the fourth obtaining unit is specifically configured to:

and returning to execute the step of judging whether the target limitation removing seat booking data of the target acquisition time point is smaller than the limitation removing value or not and the limitation removing value is not equal to a zero value based on the new target acquisition time point, the new reachable value and the new limitation removing value.

5. The apparatus according to claim 4, wherein the third acquiring unit is configured to, when calculating the target out-of-limit subscriber data at the first collection time point based on the number of days-in-advance corresponding to the first collection time point, the number of days-in-advance corresponding to a previous collection time point at the first collection time point, the number of days-in-advance corresponding to the last collection time point, the target out-of-limit subscriber difference, the historical out-of-limit subscriber data at the first collection time point, the target out-of-limit subscriber data and the historical out-of-limit subscriber data at a previous collection time point at the first collection time point, specifically:

if the current value is not smaller than the historical value, calculating target unrestricted booking data of the first collection time point through a preset first formula based on the historical value, the current value and the historical unrestricted booking data of the first collection time point;

if the current value is smaller than the historical value and the historical value is larger than a preset threshold value, calculating target unrestricted booking data of the first acquisition time point through a preset second formula based on the historical value, the current value and the historical unrestricted booking data of the first acquisition time point;

and if the current value is smaller than the historical value and the historical value is not larger than a preset threshold value, determining the current value as the target destrained seat booking data of the first acquisition time point.

6. A storage medium storing a set of instructions, wherein the set of instructions when executed by a processor implement the seat data prediction method according to any one of claims 1-3.

7. An electronic device, comprising:

a memory for storing at least one set of instructions;

a processor for executing a set of instructions stored in the memory, the set of instructions being executable to implement the method of subscription data prediction as claimed in any one of claims 1 to 3.