WO2022252847A1 - 航班季节性归类的预测方法、装置及机器可读介质 - Google Patents

航班季节性归类的预测方法、装置及机器可读介质 Download PDF

Info

Publication number
WO2022252847A1
WO2022252847A1 PCT/CN2022/087049 CN2022087049W WO2022252847A1 WO 2022252847 A1 WO2022252847 A1 WO 2022252847A1 CN 2022087049 W CN2022087049 W CN 2022087049W WO 2022252847 A1 WO2022252847 A1 WO 2022252847A1
Authority
WO
WIPO (PCT)
Prior art keywords
flight
data
historical
target
date
Prior art date
Application number
PCT/CN2022/087049
Other languages
English (en)
French (fr)
Inventor
张毅
周榕
梁巍
陈思
Original Assignee
中国民航信息网络股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中国民航信息网络股份有限公司 filed Critical 中国民航信息网络股份有限公司
Priority to KR1020237036733A priority Critical patent/KR20230159604A/ko
Publication of WO2022252847A1 publication Critical patent/WO2022252847A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28—Databases characterised by their database models, e.g. relational or object models
    • G06F16/284—Relational databases
    • G06F16/285—Clustering or classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2462—Approximate or statistical queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465—Query processing support for facilitating data mining operations in structured databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Definitions

  • the present application relates to the field of aviation, and in particular to a method, device and machine-readable medium for predicting seasonal classification of flights.
  • the seasonal classification of aviation flights is mainly carried out quantitatively or qualitatively.
  • artificially judging the seasonal classification of aviation flights will inevitably lead to biased results, which will lead to the accuracy of seasonal classification of aviation flights. not tall.
  • the present application provides a prediction method, device and machine-readable medium for seasonal classification of flights, which can improve the accuracy of seasonal classification and avoid bias caused by artificial seasonal classification of flights.
  • the first aspect of the embodiment of the present application provides a method for predicting the seasonal classification of flights, including:
  • the target departure date corresponding to the target flight from the local database, and the target flight is an undeparted flight in the target airline company to be predicted by seasonal classification;
  • N is a positive integer greater than or equal to 2;
  • the seasonal classification of the target flight is determined according to the weighted value of each first historical flight and the number of days away from port of each first historical flight.
  • the second aspect of the present application provides a device for predicting seasonal classification of flights, including:
  • the obtaining unit is used to obtain the target departure date corresponding to the target flight from the local database, and the target flight is an undeparted flight to be predicted in the target airline company for seasonal classification;
  • a construction unit configured to construct N data pools corresponding to the target flight, wherein the N is a positive integer greater than or equal to 2;
  • a first determination unit configured to determine a first historical flight set corresponding to the target flight according to the target departure date, each first historical flight in the first historical flight set is not classified seasonally flight;
  • the acquiring unit is further configured to acquire flight data of each first historical flight in the first historical flight set;
  • a second determining unit configured to determine the weighted value of each first historical flight according to the N data pools and the flight data of each first historical flight;
  • the third determining unit is configured to determine the seasonal classification of the target flight according to the weighted value of each first historical flight and the number of days away from port of each first historical flight.
  • the third determining unit is specifically configured to:
  • a seasonal classification of the target flight is determined according to the weighted sum and the total number of days.
  • the third determining unit determining the seasonal classification of the target flight according to the weighted sum and the total number of days includes:
  • a seasonal classification of the target flight is determined based on the comparison result.
  • the second determining unit is specifically configured to:
  • the first revenue data is the revenue data corresponding to any flight in each of the first historical flights
  • the first data pool is the N data pools the data pool with the smallest distance between the central data and the first income data;
  • the preset weighted value of the first data pool is determined as the weighted value of the flight corresponding to the first revenue data.
  • the first determining unit is specifically configured to:
  • the first date the target departure date-52 ⁇ 7 ⁇ i-1;
  • the second date the target departure date-52 ⁇ 7 ⁇ i+1;
  • the third date the target departure date-51 ⁇ 7 ⁇ i
  • the fourth date the target departure date - 53 ⁇ 7 ⁇ i;
  • i (1,2,3...,n), said i is the year before the current year;
  • the first determining unit is further specifically configured to:
  • the target historical reference date is calculated by the following formula:
  • the first date, the second date, the third date and the fourth date are determined according to the target historical reference date, the first date is the day before the target historical reference date, and the second date is the target historical reference date.
  • the flight corresponding to the target flight in the first date, the second date, the third date and the fourth date is determined as the first historical flight set.
  • the building unit is specifically used for:
  • Step 1 Obtain the flight data of each second historical flight in the second historical flight set corresponding to the target flight;
  • Step 2 Calculate the revenue data of each second historical flight according to the flight data of each second historical flight;
  • Step 3 Determine the second income data as the central data of the second data pool, the second income data is the income data corresponding to the first flight, and the first flight is any flight in the second historical flight set , the second data pool is any one of the N data pools;
  • Step 4 Calculate the distance between the third income data and the second income data, the third income data is the income data corresponding to any flight in the flight subset, and the flight subset is the second history a set of flights in the set of flights other than said first flight;
  • Step 5 Divide the fourth income data into the second data pool, the fourth income data is the income data corresponding to the second flight, and the second flight is the second flight in the subset of flights. The flight corresponding to the nearest revenue data in the revenue data;
  • Step 6 calculating the center data of the second data pool after division
  • the third aspect of the present application provides a computer device, including: a memory, a processor, and a bus system; wherein, the memory is used to store programs, and the bus system is used to connect the memory and the processor so that the memory and the processor communicate;
  • the device is used to execute the program in the memory, and execute the method for predicting the seasonal classification of flights according to the above-mentioned first aspect according to the instructions in the program code.
  • the fourth aspect of the embodiments of the present application provides a machine-readable medium, which includes instructions, which, when run on a machine, cause the machine to execute the steps of the method for predicting the seasonal classification of flights described in the above aspects.
  • the flight seasonal classification prediction device determines the seasonal classification of the target flight, it can obtain the target departure date of the target flight, and construct the method for changing the target flight.
  • the corresponding N data pools determine the first historical flight set according to the target departure date, and determine the weighted value of each first historical flight according to the flight data of each first historical flight in the first historical flight set, and finally according to The weighted value of each first historical flight and the number of days away from each first historical flight determine the seasonal classification of the target flight.
  • the seasonality can be improved.
  • the accuracy of classification avoids the bias caused by the artificial seasonal classification of flights.
  • Fig. 1 is the schematic flow chart of the prediction method of flight season classification that the embodiment of the present application provides;
  • Fig. 2 is the virtual structure schematic diagram of the flight season classification prediction device that the embodiment of the present application provides;
  • FIG. 3 is a schematic structural diagram of a machine-readable medium provided by an embodiment of the present application.
  • FIG. 4 is a schematic diagram of a hardware structure of a server provided by an embodiment of the present application.
  • Yield management system refers to a system that uses flight plan, inventory, departure and freight rate data to automatically manage the inventory of non-departure flights based on forecasting and optimization models;
  • the market demand value refers to the demand that passengers have the ability to purchase and has actual purchase needs, and actual orders may or may not be generated, as the output value in the revenue management system;
  • Ndo Number of department days (Ndo), the number of days between the system date (that is, the current date) and the departure date of the flight segment, for example, the current date is April 26, 2021, and the departure date is May 1, 2021 day, the Ndo is 5 days;
  • Data collection points are determined by the number of days away from the port, and have a one-to-one correspondence with the number of days away from the port.
  • the data collection points can be set to 24 (Dcp1, Dcp2, ..., Dcp24), and the distance
  • the number of days from Hong Kong can be set to 365 days, wherein the data collection point corresponds to the number of days away from Hong Kong one by one, the data collection point Dcp1 corresponds to the number of days away from Hong Kong for 365 days, and Dcp24 corresponds to the number of days away from Hong Kong for 1 day. It can be understood that the above data collection point
  • the number of days, the number of days away from the port, and the corresponding relationship between the data collection point and the number of days away from the port are examples only, and are not specifically limited.
  • the device for predicting the seasonal classification of flights can obtain the target departure date corresponding to the target flight from the local database, wherein the target flight is a non-departing flight of the target airline company whose seasonal classification is to be predicted.
  • the flight data of the designated airline that is, the target airline
  • the flight control system contains the full or incremental flight data of the designated airline, which can be set as Obtain the full or incremental flight data of the specified airline from the flight control system at predetermined intervals, for example, at intervals of 24 hours.
  • the flight data includes but is not limited to the following data: flight number, flight departure date, DCP and its corresponding number of days before flight departure, booking value of each class and its corresponding transportation value. Therefore, the device for predicting seasonal classification of flights can directly obtain the target departure date corresponding to the target flight directly from the local database.
  • the target flight is used as an example for the above description, and of course, it can also be described directly by taking a flight segment as an example.
  • the target flight includes at least one flight segment, and a flight segment refers to a flight segment that can constitute a passenger flight, for example
  • the target flight is the flight corresponding to Beijing-Shanghai-San Francisco, and there are three possible passenger routes: Beijing-Shanghai, Shanghai-San Francisco and Beijing-San Francisco, that is, the target flight includes the Beijing-Shanghai segment and the Shanghai-San Francisco segment and the Beijing-San Francisco flight segment, a total of 3 flight segments.
  • the device for predicting seasonal classification of flights may construct N data pools corresponding to target flights, where N is a positive integer greater than or equal to 2.
  • N is a positive integer greater than or equal to 2.
  • the number of N is set to 7, and the 7 data pools are marked as peak season 1 (denoted as peak), peak season 2 (denoted as peak1), flat season 1 (denoted as peak2), and flat season 2 (denoted as offpeak2), off-season 1 (denoted as offpeak1), off-season 2 (denoted as offpeak) and the uncategorized data pool default
  • the number of data pools and the classification of the data pools are just examples and are not specifically limited.
  • the N data pools corresponding to the target flight constructed by the flight seasonal classification prediction device include:
  • Step 1 Obtain the flight data of each second historical flight in the second historical flight set corresponding to the target flight.
  • the flight season classification prediction device may first obtain the flight data of each second historical flight in the second historical flight set corresponding to the target flight from the local database.
  • the second historical flight data corresponding to the target flight The set of flights is the departing flights associated with the current date in the three years before the current date (of course, it can also be other time periods, such as 4 years, not limited), for example, the target flight is a certain date on April 25, 2021 For a flight, April 25 is Sunday, then the second historical flight set is a set of flights corresponding to the target flight on all Sundays in the past 3 years.
  • Step 2 Calculate the revenue data of each second historical flight according to the flight data of each second historical flight.
  • the flight seasonal classification prediction device can be calculated by the following formula:
  • Revenue Dcp(x) is the revenue data of the x-th flight in each second historical flight
  • i represents the cabin
  • k is the total number of cabins
  • BKG(i) is the seat reservation of the i-th cabin
  • Fare(i) is the fare of the i-th cabin.
  • Step 3 Determine the second income data as the central data of the second data pool, the second income data is the income data corresponding to the first flight, the first flight is any flight in the second historical flight collection, and the second data pool is Any one of the N data pools.
  • the flight season classification prediction device may determine the second revenue data as the central data of the second data pool, the second revenue data is the revenue data of the first flight, and the first flight is the second historical flight collection
  • the second data pool is any one of the N data pools, that is to say, the revenue data corresponding to the N historical flights can be randomly selected here as the central data of the N data pools.
  • Step 4 Calculate the first distance between the third income data and the second income data.
  • the third income data is the income data corresponding to any flight in the flight subset, and the flight subset is the first distance in the second historical flight collection. A collection of flights other than flights.
  • the flight season classification prediction device can calculate the distance between the third income data and the center data of the N data pools by the following formula:
  • D(i, j) is the distance between the second income data i and the third income data j
  • the third income data j is the income data corresponding to any flight in the flight subset
  • W(t) is the first The weight of the third income data
  • X it is the market demand value of the second income data
  • Y jt is the market demand value corresponding to the third income data.
  • Step 5 Divide the fourth income data into the second data pool, the fourth income data is the income data corresponding to the second flight, and the second flight is corresponding to the income data closest to the second income data in the flight subset flight.
  • the flight season classification prediction device can divide the fourth income data into the first data pool, the fourth income data is the income data corresponding to the second flight, and the second flight is the income data corresponding to the first flight in the subset of flights.
  • the flight corresponding to the nearest income data of the second income data that is to say, each flight in the flight subset can be divided into the data pool closest to each flight.
  • Step 6 calculating the center data of the second data pool after division
  • the flight season classification prediction device can calculate the central data of the second data pool through the following formula:
  • New_mean(t) is the central data of the target data pool after dividing the fourth income data into the second data pool
  • Old_mean(t) is the central data of the target data before dividing the fourth income data into the second data pool
  • m is The amount of central data in the target data pool before the fourth income input is divided into the second data pool
  • X(t) is the market demand value corresponding to any income data in the second data pool.
  • step 3 to step 6 are repeatedly executed until the revenue data corresponding to each second historical flight in the second historical flight set is divided into N data pools.
  • the market demand value refers to the demand that passengers have the ability to purchase and have actual purchase needs. Actual orders may or may not be generated.
  • the market demand value is output by applying the restriction algorithm calculation model in the revenue management system.
  • the market demand value is widely used in judging market trends and dividing market seasons, and is an important input value applied to the optimization module of the core algorithm subsystem of the revenue management system.
  • An automated management system that automatically manages the inventory of non-departing flights based on freight data.
  • the method of obtaining the market demand value of the flight is not specifically limited here. For example, obtain the flight information of the specified flight of the target airline company, and obtain inventory data based on the flight information.
  • the inventory data specifically includes the inventory information of departing flights and non-departing flights Inventory information, where the inventory data of departed flights is the flight inventory data of the departing flights of the specified flight in the past three years based on the current date, and the inventory data of non-departing flights is the future of the specified flight based on the current date One year's flight inventory data; judge the sales status of the specified flight class based on the inventory data.
  • the flight information of the designated airline, the inventory data of the designated flight, etc. to identify the sales status of the designated cabin of the designated flight.
  • the sales status includes locked cabin, open cabin, etc., and finally based on the preset algorithm Process the sales status to obtain the market demand value of the specified flight.
  • the available status when the number of available seats in a designated cabin is less than or equal to zero, and the available status is open or closed, it means that the designated cabin is in a non-saleable state, that is, the cabin is locked; the number of available seats in a designated cabin is greater than zero, and the available If the status is closed, it means that the specified cabin is not available for sale; it is locked; if the number of available seats in the specified cabin is greater than zero, the available status is open, indicating that the specified cabin is available for sale; that is, the cabin is opened;
  • the market demand value of the data collection point DCP(n+1) is calculated by the following formula:
  • the device for predicting seasonal classification of flights may determine the first set of historical flights corresponding to the target flight according to the target departure date. Specifically, it can be determined in the following two ways:
  • First date said target departure date - 52 ⁇ 7 ⁇ i-1;
  • Second date said target departure date - 52 ⁇ 7 ⁇ i+1;
  • the third date said target departure date - 51 ⁇ 7 ⁇ i;
  • Fourth date said target departure date - 53 ⁇ 7 ⁇ i;
  • i (1, 2, 3..., n)
  • i is the year before the current year, for example, the current year is 2021, then i can be multiple years before 2021, 2020, 2019, 2018 year etc;
  • the flights corresponding to the target flight among the first date, the second date, the third date and the fourth date are determined as the first historical flight set.
  • An example is given below:
  • the first historical flight set is a set of flights corresponding to the target flight on December 31, 2019, January 2, 2020, December 25, 2019, and January 8, 2020.
  • the target historical reference date is calculated by the following formula:
  • the first date is the previous day of the target historical reference date
  • the second date is the next day of the target historical reference date
  • the third The date is the week before the target historical reference date
  • the fourth date is the week after the target historical reference date
  • the flights corresponding to the target flight among the first date, the second date, the third date and the fourth date are determined as the first historical flight set.
  • An example is given below:
  • the target departure date is December 30, 2020
  • the corresponding DOW is Wednesday
  • the date of the previous day of the target historical reference date December 31, 2019 that is, the first date is December 31, 2019
  • the date one day after the target historical reference date is January 2, 2020 (that is, the second date is January 2, 2020 )
  • the date of the same DOW one week before the reference date is December 25, 2019 (that is, the third date is December 25, 2019)
  • the date of the same DOW one week after the reference date is January 8, 2020 (that is, the fourth date date is January 8, 2020)
  • the first historical flight set is December 31, 2019, January 2, 2020, December 25, 2019, and January 8, 2020 that correspond to the target flight The collection of corresponding flights.
  • the device for predicting the seasonal classification of flights may acquire flight data of each first historical flight in the first historical flight set from the local database.
  • the target departure date can be obtained through step 101
  • N data pools can be constructed through step 102
  • the flight data of each first historical flight in the first historical flight collection can be obtained through steps 103 to 104, however , step 101, step 102, step 103 to step 104 are not restricted in order of execution, step 101 can be executed first, step 102 can be executed first, step 103 to step 104 can also be executed first, or executed simultaneously, specifically No limit.
  • the flight season classification prediction device can determine the weighted value of each first historical flight according to the N data pools and the flight data of each first historical flight.
  • the flight data of the flight determines the income data of each first historical flight (the calculation of the income data has been described in detail in the above-mentioned step 102, and the details are not repeated here), and then the first income data is divided into the first data pool, wherein , the first income data is the income data corresponding to any flight in each first historical flight, the first data pool is the data pool with the smallest distance between the central data and the first income data among the N data pools, and A preset weighted value of the first data pool is determined, and the preset weighted value of the first data pool is determined as the weighted value of the flight corresponding to the first income data. That is to say, the revenue data corresponding to each first historical flight may be divided into the data pool closest to it, and the preset weighted value of the corresponding data pool is determined as the weighted value of each first historical flight.
  • the default weighted value of each of the N data pools is stored in the local database by default.
  • N is set to 7 (of course, it can also be other values, which are not specifically limited).
  • the flight season classification prediction device can determine the weighted sum of the first historical flight set according to the weighted value of each first historical flight, and determine the first historical flight according to the number of days away from the port of each first historical flight. The total number of days of the flight set, and finally determine the seasonal classification of the target flight based on the weighted sum and the total number of days.
  • the flight seasonal classification predicting device determines the seasonal classification of the target flight according to the weighted sum and the total number of days, including: comparing the weighted sum with the total number of days to obtain a comparison result, and the comparison result is used to indicate the weighted sum and the total number of days The size relationship of the number of days; the seasonal classification of the target flight is determined according to the comparison result.
  • the weighted sum of the first historical flight collection is defined as field Xi
  • the total number of days of the first historical flight collection is defined as Y i ; then compare the size relationship between Xi and Y i , and determine according to the size relationship
  • the seasonal classification of the target flight, the comparison of the size relationship between Xi and Yi and the specific seasonal classification are described below:
  • the flight seasonal classification prediction device determines the seasonal classification of the target flight, it can obtain the target departure date of the target flight, and construct the method for changing the target flight.
  • the corresponding N data pools determine the first historical flight set according to the target departure date, and determine the weighted value of each first historical flight according to the flight data of each first historical flight in the first historical flight set, and finally according to The weighted value of each first historical flight and the number of days away from each first historical flight determine the seasonal classification of the target flight.
  • the seasonality can be improved.
  • the accuracy of classification avoids the bias caused by the artificial seasonal classification of flights.
  • each block in a flowchart or block diagram may represent a module, program segment, or portion of code that contains one or more logical functions for implementing specified executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.
  • the present application can also write computer program codes for performing the operations of the present application in one or more programming languages or combinations thereof, and the above-mentioned programming languages include but are not limited to object-oriented programming languages—such as Java, Smalltalk, C++, and also conventional procedural programming languages—such as "C" or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through an Internet service provider). Internet connection).
  • LAN local area network
  • WAN wide area network
  • Internet connection any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through an Internet service provider). Internet connection).
  • the embodiment of the present application is described above from the perspective of the method for predicting the seasonal classification of flights, and the embodiment of the present application is described below from the perspective of the device for predicting the seasonal classification of flights.
  • Fig. 2 is the imaginary structural representation of the flight seasonal classification prediction device provided by the embodiment of the present application, the flight seasonal classification prediction device 200 includes:
  • the obtaining unit 201 is used to obtain the target departure date corresponding to the target flight from the local database, and the target flight is an undeparted flight to be predicted in the target airline company for seasonal classification;
  • a construction unit 202 configured to construct N data pools corresponding to the target flight, wherein the N is a positive integer greater than or equal to 2;
  • the first determining unit 203 is configured to determine the first historical flight set corresponding to the target flight according to the target departure date, and each first historical flight in the first historical flight set is not seasonally normalized. class of flights;
  • the acquiring unit 201 is further configured to acquire flight data of each first historical flight in the first historical flight set;
  • the second determining unit 204 is configured to determine the weighted value of each first historical flight according to the N data pools and the flight data of each first historical flight;
  • the third determining unit 205 is configured to determine the seasonal classification of the target flight according to the weighted value of each first historical flight and the number of days away from the port of each first historical flight.
  • the third determining unit 205 is specifically configured to:
  • a seasonal classification of the target flight is determined according to the weighted sum and the total number of days.
  • the third determining unit 205 determining the seasonal classification of the target flight according to the weighted sum and the total number of days includes:
  • a seasonal classification of the target flight is determined based on the comparison result.
  • the second determining unit 204 is specifically configured to:
  • the first revenue data is the revenue data corresponding to any flight in each of the first historical flights
  • the first data pool is the N data pools the data pool with the smallest distance between the central data and the first income data;
  • the preset weighted value of the first data pool is determined as the weighted value of the flight corresponding to the first revenue data.
  • the first determining unit 203 is specifically configured to:
  • the first date the target departure date-52 ⁇ 7 ⁇ i-1;
  • the second date the target departure date-52 ⁇ 7 ⁇ i+1;
  • the third date the target departure date-51 ⁇ 7 ⁇ i
  • the fourth date the target departure date - 53 ⁇ 7 ⁇ i;
  • i (1,2,3...,n), said i is the year before the current year;
  • the first determining unit 203 is further specifically configured to:
  • the target historical reference date is calculated by the following formula:
  • the first date, the second date, the third date and the fourth date are determined according to the target historical reference date, the first date is the day before the target historical reference date, and the second date is the target historical reference date.
  • the construction unit 202 is specifically used for:
  • Step 1 Obtain the flight data of each second historical flight in the second historical flight set corresponding to the target flight;
  • Step 2 Calculate the revenue data of each second historical flight according to the flight data of each second historical flight;
  • Step 3 Determine the second income data as the central data of the second data pool, the second income data is the income data corresponding to the first flight, and the first flight is any flight in the second historical flight set , the second data pool is any one of the N data pools;
  • Step 4 Calculate the distance between the third income data and the second income data, the third income data is the income data corresponding to any flight in the flight subset, and the flight subset is the second history a set of flights in the set of flights other than said first flight;
  • Step 5 Divide the fourth income data into the second data pool, the fourth income data is the income data corresponding to the second flight, and the second flight is the second flight in the subset of flights. The flight corresponding to the nearest revenue data in the revenue data;
  • Step 6 calculating the center data of the second data pool after division
  • the flight seasonal classification prediction device determines the seasonal classification of the target flight, it can obtain the target departure date of the target flight, and construct the method for changing the target flight.
  • the corresponding N data pools determine the first historical flight set according to the target departure date, and determine the weighted value of each first historical flight according to the flight data of each first historical flight in the first historical flight set, and finally according to The weighted value of each first historical flight and the number of days away from each first historical flight determine the seasonal classification of the target flight.
  • the seasonality can be improved.
  • the accuracy of classification avoids the bias caused by the artificial seasonal classification of flights.
  • the units involved in the embodiments described in the present application may be implemented by means of software or by means of hardware.
  • the name of the unit does not constitute a limitation on the unit itself under certain circumstances, for example, the acquisition unit may also be described as "a unit that acquires the credential information of the target user".
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSPs Application Specific Standard Products
  • SOCs System on Chips
  • CPLD Complex Programmable Logical device
  • FIG. 3 is a schematic diagram of an embodiment of a machine-readable medium provided in an embodiment of the present application.
  • the present embodiment provides a machine-readable medium 300 on which a computer program 311 is stored, and when the computer program 311 is executed by a processor, the prediction of the seasonal classification of flights described in FIG. 1 is realized. method steps.
  • a machine-readable medium may be a tangible medium, which may contain or store a program for use by an instruction execution system, device, or device or in combination with an instruction execution system, device, or device.
  • a machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • a machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM compact disk read only memory
  • magnetic storage or any suitable combination of the foregoing.
  • machine-readable medium mentioned above in this application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two.
  • a computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can transmit, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device .
  • Program code embodied on a computer readable medium may be transmitted by any appropriate medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device, or may exist independently without being incorporated into the electronic device.
  • FIG. 4 is a schematic diagram of the hardware structure of a server provided by the embodiment of the present application.
  • the server 400 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (central processing units, CPU) 422 (eg, one or more processors) and memory 432, and one or more storage media 430 (eg, one or more mass storage devices) for storing application programs 442 or data 444.
  • the memory 432 and the storage medium 430 may be temporary storage or persistent storage.
  • the program stored in the storage medium 430 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the server.
  • the central processing unit 422 may be configured to communicate with the storage medium 430 , and execute a series of instruction operations in the storage medium 430 on the server 400 .
  • the server 400 can also include one or more power supplies 426, one or more wired or wireless network interfaces 450, one or more input and output interfaces 458, and/or, one or more operating systems 441, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
  • the steps performed by the device for predicting seasonal classification of flights in the above embodiments may be based on the server structure shown in FIG. 4 .
  • the process of the method for predicting the seasonal classification of flights described in the schematic flowchart of FIG. 1 may be implemented as a computer software program.
  • the embodiments of the present application include a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, the computer program including a program for performing the method shown in the flowchart schematic diagram of FIG. 1 above code.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Tourism & Hospitality (AREA)
  • Mathematical Physics (AREA)
  • Fuzzy Systems (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本申请提供了一种航班季节性归类的预测方法及相关设备，可以提高季节性归类的准确性，避免因为人为对航班的季节性归类而造成的偏颇现象。该方法包括：从本地数据库中获取目标航班所对应的目标离港日期；构建所述目标航班所对应的N个数据池；根据所述目标离港日期确定所述目标航班所对应的第一历史航班集合，所述第一历史航班集合中的每个第一历史航班均为未季节性归类的航班；获取所述第一历史航班集合中每个第一历史航班的航班数据；根据所述N个数据池以及所述每个第一历史航班的航班数据确定所述每个第一历史航班的加权值；根据所述每个第一历史航班的加权值以及所述每个第一历史航班的距离港天数确定所述目标航班的季节性归类。

Description

航班季节性归类的预测方法、装置及机器可读介质
本申请要求于2021年5月31日提交中国专利局、申请号为202110604811.2、发明名称为“航班季节性归类的预测方法、装置及机器可读介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及本申请涉及航空领域，尤其涉及一种航班季节性归类的预测方法、装置及机器可读介质。
背景技术
受气候条件、突发事件、工农业生产生活、居民节假日等风俗习惯以及国民经济发展等因素的周期性影响，民航运输业客货运量呈季节性波动。在航空运输领域。通过将已离港历史航班进行淡旺季归类，也称之为季节性归类。
目前来说，主要是通过人为定量或定性的对航空航班进行的季节性归类，然而人为判断航空航班的季节性归类难免出现偏颇的结果，进而导致对航空航班的季节性归类精确度不高。
发明内容
本申请提供了一种航班季节性归类的预测方法、装置及机器可读介质，可以提高季节性归类的准确性，避免因为人为对航班的季节性归类而造成的偏颇现象。
本申请实施例第一方面提供了一种航班季节性归类的预测方法，包括：
从本地数据库中获取目标航班所对应的目标离港日期，所述目标航班为目标航司中待预测季节性归类的未离港航班；
构建所述目标航班所对应的N个数据池，其中，所述N为大于或等于2的正整数；
根据所述目标离港日期确定所述目标航班所对应的第一历史航班集合，所述第一历史航班集合中的每个第一历史航班均为未季节性归类的航班；
获取所述第一历史航班集合中每个第一历史航班的航班数据；
根据所述N个数据池以及所述每个第一历史航班的航班数据确定所述每个第一历史航班的加权值；
根据所述每个第一历史航班的加权值以及所述每个第一历史航班的距离港天数确定所述目标航班的季节性归类。
本申请第二方面提供了一种航班季节性归类预测装置，包括：
获取单元，用于从本地数据库中获取目标航班所对应的目标离港日期，所述目标航班为目标航司中待预测季节性归类的未离港航班；
构建单元，用于构建所述目标航班所对应的N个数据池，其中，所述N为大于或等于2的正整数；
第一确定单元，用于根据所述目标离港日期确定所述目标航班所对应的第一历史航班集合，所述第一历史航班集合中的每个第一历史航班均为未季节性归类的航班；
所述获取单元，还用于获取所述第一历史航班集合中每个第一历史航班的航班数据；
第二确定单元，用于根据所述N个数据池以及所述每个第一历史航班的航班数据确定 所述每个第一历史航班的加权值；
第三确定单元，用于根据所述每个第一历史航班的加权值以及所述每个第一历史航班的距离港天数确定所述目标航班的季节性归类。
一种可能的设计中，所述第三确定单元具体用于：
根据所述每个第一历史航班的加权值确定所述第一历史航班集合的加权值总和；
根据所述每个第一历史航班的距离港天数确定所述第一历史航班集合的总天数；
根据所述加权总和以及所述总天数确定所述目标航班的季节性归类。
一种可能的设计中，所述第三确定单元根据所述加权总和以及所述总天数确定所述目标航班的季节性归类包括：
将所述加权总和与所述总天数进行比较，得到比较结果，所述比较结果用于指示所述加权总和与所述总天数的大小关系；
根据所述比较结果确定所述目标航班的季节性归类。
一种可能的设计中，所述第二确定单元具体用于：
根据所述每个第一历史航班的航班数据确定所述每个第一历史航班的收入数据；
将第一收入数据划分至第一数据池，所述第一收入数据为所述每个第一历史航班中任意一个航班所对应的收入数据，所述第一数据池为所述N个数据池中中心数据与所述第一收入数据之间距离最小的数据池；
确定所述第一数据池的预设加权值；
将所述第一数据池的预设加权值确定为所述第一收入数据所对应的航班的加权值。
一种可能的设计中，所述第一确定单元具体用于：
通过如下公式计算第一日期、第二日期、第三日期以及第四日期：
所述第一日期＝所述目标离港日-52×7×i-1；
所述第二日期＝所述目标离港日-52×7×i+1；
所述第三日期＝所述目标离港日-51×7×i；
所述第四日期＝所述目标离港日-53×7×i；
其中，i＝(1，2，3……，n)，所述i为当前年份之前的年份；
将所述第一日期、所述第二日期、所述第三日期以及所述第四日期中与所述目标航班相对应的航班确定为所述第一历史航班集合。
一种可能的设计中，所述第一确定单元还具体用于：
通过如下公式计算所述目标历史参考日期：
所述目标历史参考日期＝所述目标离港日期-52×7×i，其中，i＝(1，2，3……，n)，所述i为当前年份之前的年份；
根据所述目标历史参考日确定第一日期、第二日期、第三日期以及第四日期，所述第一日期为所述目标历史参考日的前一天，所述第二日期为所述目标历史参考日的后一天，所述第三日期为所述目标历史参考日的前一个星期，所述第四日期为所述目标历史参考日的后一个星期；
将所述第一日期、所述第二日期、所述第三日期以及所述第四日期中与所述目标航班 相对应的航班确定为所述第一历史航班集合。
一种可能的设计中，所述构建单元具体用于：
步骤1、获取所述目标航班所对应的第二历史航班集合中每个第二历史航班的航班数据；
步骤2、根据所述每个第二历史航班的航班数据计算所述每个第二历史航班的收入数据；
步骤3、将第二收入数据确定为第二数据池的中心数据，所述第二收入数据为第一航班对应的收入数据，所述第一航班为所述第二历史航班集合中任意一个航班，所述第二数据池为所述N个数据池中的任意一个；
步骤4、计算第三收入数据与所述第二收入数据的距离，所述第三收入数据为航班子集合中的任意一个航班所对应的收入数据，所述航班子集合为所述第二历史航班集合中除所述第一航班之外的航班集合；
步骤5、将第四收入数据划分至所述第二数据池，所述第四收入数据为第二航班所对应的收入数据，所述第二航班为所述航班子集合中与所述第二收入数据的距离最近的收入数据所对应的航班；
步骤6、计算划分后所述第二数据池的中心数据；
重复执行步骤3至步骤6，直至所述第二历史航班集合中每个第二历史航班所对应的收入数据均划分至所述N个数据池为止。
本申请第三方面提供了一种计算机设备，包括：存储器、处理器以及总线系统；其中，存储器用于存储程序，总线系统用于连接存储器以及处理器，以使存储器以及处理器进行通信；处理器用于执行所述存储器中的程序，并根据程序代码中的指令执行上述第一方面所述航班季节性归类的预测方法。
本申请实施例第四方面提供了一种机器可读介质，其包括指令，当其在机器上运行时，使得机器执行上述各方面所述的航班季节性归类的预测方法的步骤。
综上所述，可以看出，本申请提供的实施例中，航班季节性归类预测装置在确定目标航班的季节性分类时，可以获取目标航班的目标离港日期，并构建更改目标航班所对应的N个数据池，根据目标离港日期确定第一历史航班集合，并根据该第一历史航班集合中每个第一历史航班的航班数据确定每个第一历史航班的加权值，最后根据每个第一历史航班的加权值以及每个第一历史航班的距离港天数确定目标航班的季节性归类，相对于现有的通过人为对航班进行季节性归类来说，可以提高季节性归类的准确性，避免因为人为对航班的季节性归类而造成的偏颇现象。
附图说明
结合附图并参考以下具体实施方式，本申请各实施例的上述和其他特征、优点及方面将变得更加明显。贯穿附图中，相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的，原件和元素不一定按照比例绘制。
图1为本申请实施例提供的航班季节性归类的预测方法的流程示意图；
图2为本申请实施例提供的航班季节性归类预测装置的虚拟结构示意图；
图3为本申请实施例提供的机器可读介质的结构示意图；
图4为本申请实施例提供的服务器的硬件结构示意图。
具体实施方式
下面将参照附图更详细地描述本申请的实施例。虽然附图中显示了本申请的某些实施例，然而应当理解的是，本申请可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例，相反提供这些实施例是为了更加透彻和完整地理解本申请。应当理解的是，本申请的附图及实施例仅用于示例性作用，并非用于限制本申请的保护范围。
本申请中使用的术语“包括”及其变形是开放性包括，即“包括但不限于”。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。其他术语的相关定义将在下文描述中给出。
需要注意，本申请中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意，本申请中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。
首先对本申请实施例涉及的专用名词进行说明：
收益管理系统是指利用航班计划、库存、离港与运价数据，基于预测与优化模型，对未离港航班的库存进行自动管理的系统；
市场需求值是指旅客具有能力购买且具有实际购买需求的需求，可以产生实际的订单，可以不产生实际的订单，作为收益管理系统中的输出值；
距离港天数(Number of department days，Ndo)，系统日期(也即当前日期)距航班航段离港日期的天数，例如当前日期为2021年4月26日，离港日期为2021年5月1日，该Ndo即为5天；
数据采集点(Data collection points，Dcp)，由距离港天数而决定，与距离港天数为一一对应关系，例如该数据采集点可以设置为24个(Dcp1，Dcp2，……，Dcp24)，距离港天数可以设置为365天，其中该数据采集点与距离港天数一一对应，数据采集点Dcp1对应距离港天数365天，Dcp24对应距离港天数1天，可以理解的是，上述数据采集点的数量、距离港天数的天数以及数据采集点与距离港天数的天数之间的对应关系仅为举例说明，具体不做限定。
DOW：Day Of Week，广义的星期
下面从航班季节性归类预测装置的角度本申请提供的航班季节性归类的预测方法进行说明，请参阅图1，图1为本申请实施例提供的航班季节性归类的预测方法的一个流程示意图，包括：
101、从本地数据库中获取目标航班所对应的目标离港日期。
本实施例中，航班季节性归类预测装置可以从本地数据库中获取目标航班所对应的目标离港日期，其中，该目标航班为目标航司中待预测季节性归类的未离港航班。可以理解的是，对于指定航空公司(也即目标航司)的航班数据在本地数据库是有存储的，在航班控制系统中含有指定航空公司全量或是增量的航班数据，可以设定为每隔预定时间从航班 控制系统中获取指定航空公司全量或是增量的航班数据，例如，可以每间隔24小时的获取一次。该航班数据包括但不限于如下数据：航班号、航班离港日期、DCP与其对应的距航班离港天数、各舱位订座值与其对应的运价值。因此，该航班季节性归类预测装置可以直接从本地数据库中直接获取该目标航班所对应的目标离港日期。
需要说明的是，上述以目标航班为例进行说明，当然也还可以直接以航段为例进行说明，该目标航班中包括至少一个航段，航段是指能够构成旅客航程的航段，例如该目标航班为北京-上海-旧金山所对应的航班，旅客航程有3种可能：北京-上海、上海-旧金山和北京-旧金山，也即该目标航班包括北京-上海航段、上海-旧金山航段和北京-旧金山航段，共3个航段。
102、构建目标航班所对应的N个数据池。
本实施例中，航班季节性归类预测装置可以构建目标航班所对应的N个数据池，其中，N为大于或等于2的正整数。本申请中，将N的数量设置为7，将7个数据池标记为旺季1(记作peak)、旺季2(记作peak1)、平季1(记作peak2)、平季2(记作offpeak2)、淡季1(记作offpeak1)、淡季2(记作offpeak)以及无归类数据池default，此处的数据池的数量以及数据池的分类仅为举例说明，具体不做限定。
一个实施例中，航班季节性归类预测装置构建目标航班所对应的N个数据池包括：
步骤1、获取目标航班所对应的第二历史航班集合中每个第二历史航班的航班数据。
本步骤中，航班季节性归类预测装置可以首先从本地数据库中获取目标航班所对应的第二历史航班集合中每个第二历史航班的航班数据，另外，该目标航班所对应的第二历史航班集合为当前日期之前三年(当然也还可以是其他时长，例如4年，具体不限定)中与当前日期相关联的已离港航班，例如目标航班为2021年4月25日中的某一个航班，4月25日为星期天，那么该第二历史航班集合中为过去3年中所有星期天中与该目标航班相对应的航班的集合。
步骤2、根据每个第二历史航班的航班数据计算每个第二历史航班的收入数据。
本步骤中，航班季节性归类预测装置可以通过如下公式进行计算：
Figure PCTCN2022087049-appb-000001
其中，Revenue Dcp(x)为每个第二历史航班中第x个航班的收入数据，i表示舱位，k为舱位的总数，BKG(i)为第i个舱位的订座，Fare(i)为第i个舱位的票价。
步骤3、将第二收入数据确定为第二数据池的中心数据，第二收入数据为第一航班对应的收入数据，第一航班为第二历史航班集合中任意一个航班，第二数据池为N个数据池中的任意一个。
本步骤中，航班季节性归类预测装置可以将第二收入数据确定为第二数据池的中心数据，该第二收入数据为第一航班的收入数据，该第一航班为第二历史航班集合中的任意一个航班，该第二数据池为N个数据池中的任意一个，也就是说，此处可以随机选择N个历史航班所对应的收入数据作为N个数据池的中心数据。
步骤4、计算第三收入数据与第二收入数据的第一距离，第三收入数据为航班子集合中的任意一个航班所对应的收入数据，航班子集合为第二历史航班集合中除第一航班之外的航班集合。
本步骤中，航班季节性归类预测装置可以通过如下公式计算第三收入数据与N个数据池的中心数据之间的距离：
D(i,j)＝W(t)×|X it-Y jt|；
其中，D(i,j)为第二收入数据i与第三收入数据j之间的距离，第三收入数据j为航班子集合中任意一个航班所对应的收入数据，W(t)为第三收入数据的权重，X it为第二收入数据的市场需求值，Y jt为第三收入数据所对应的市场需求值。
步骤5、将第四收入数据划分至第二数据池，第四收入数据为第二航班所对应的收入数据，第二航班为航班子集合中与第二收入数据的距离最近的收入数据所对应的航班。
本步骤中，航班季节性归类预测装置可以将第四收入数据划分至第一数据池，该第四收入数据为第二航班所对应的收入数据，该第二航班为航班子集合中与第二收入数据的距离最近的收入数据所对应的航班，也就是说，可以将航班子集合中的每个航班分别划分至与每个航班距离最近的数据池中。
步骤6、计算划分后第二数据池的中心数据；
本步骤中，航班季节性归类预测装置可以通过如下公式计算第二数据池的中心数据：
Figure PCTCN2022087049-appb-000002
其中，New_mean(t)为将第四收入数据划分至第二数据池后目标数据池的中心数据，Old_mean(t)为将第四收入划分至第二数据池前目标数据的中心数据，m为将第四收入输入划分至第二数据池之前目标数据池的中心数据的数量，X(t)为第二数据池中任意一个收入数据所对应的市场需求值。
之后，重复执行步骤3至步骤6，直至第二历史航班集合中每个第二历史航班所对应的收入数据均划分至N个数据池为止。
需要说明的是，市场需求值指的旅客具有能力购买且具有实际购买需求的需求，可以产生实际的订单，可以不产生实际的订单，在收益管理系统中应用限制算法计算模型输出市场需求值，该市场需求值被广泛应用与市场走势判断、市场淡旺季划分，并且是应用于收益管理系统核心算法子系统优化模块的重要输入值，是收益管理系统是航司利用航班计划、库存、离港与运价数据，对未离港航班的库存进行自动管理的自动化管理系统。此处具体不限定获取航班的市场需求值的方式，例如，获取目标航司的指定航班的航班信息，基于航班信息获取库存数据，该库存数据具体包括已离港航班库存信息和未离港航班库存信息，其中，已离港航班库存数据为指定航班以当前日期为基准的过往三年的已离港航班的航班库存数据，未离港航班的库存数据为指定航班在当前日期为基准的未来一年的航班 库存数据；根据库存数据判断指定航班的指定舱位的销售状态。根据目标航司所对应的数据采集点，指定航空公司的航班信息、指定航班的库存数据等来识别指定航班的指定舱位的销售状态，销售状态包括锁舱、开舱等，最后基于预设算法对销售状态进行处理，得到指定航班的市场需求值。
需要说明的是，当指定舱位的可利用座位数小于等于零，可利用状态为开放、关闭，说明指定舱位处于非可销售状态，即为锁舱；指定舱位的可利用座位数大于零，可利用状态为关闭，说明指定舱位处于非可销售状态；即为锁舱；指定舱位的可利用座位数大于零，可利用状态为开放，说明指定舱位处于可销售状态；即为开舱；
下面对如何基于预设算法对销售状态进行处理，得到指定航班的时长需求值进行说明：
如果数据采集点DCP(n+1)的销售状态为开舱，且数据采集点DCP(n)的销售状态为开舱：
若数据采集点(n)较数据采集点(n+1)订座数是增加的，则使用如下公式计算数据采集点DCP(n+1)的市场需求值计算：
市场需求值DCP(n+1)＝市场需求值DCP(n)+订座值增加变动值DCP(n)，其中，订座增加变动值＝实际订座值DCP(n+1)-实际订座值DCP(n)。
若数据采集点(n)较数据采集点(n+1)订座数是减少的，则通过如下公式计算数据采集点DCP(n+1)的市场需求值：
市场需求值DCP(n+1)＝市场需求值DCP(n)+订座减少变动值DCP(n)，其中，订座减少变动值＝(实际订座值DCP(n+1)x市场需求值(n))/实际订座值DCP(n)-市场需求值(n)。
若数据采集点DCP(n+1)的销售状态为锁舱，且数据采集点DCP(n)的销售状态为开舱：
当数据采集点(n)较数据采集点(n+1)订座数是减少时，则通过如下公式计算：
市场需求值DCP(n+1)＝市场需求值DCP(n)+订座减少变动值DCP(n)，其中，订座减少变动值＝(实际订座值DCP(n+1)x市场需求值(n))/实际订座值DCP(n)-市场需求值(n)。可以理解的是，上述市场需求值的计算是一个迭代的过程，即为DCP(1)的市场需求值等于实际订座值，迭代计算DCP+＝1的市场需求值。
103、根据目标离港日期确定目标航班所对应的第一历史航班集合。
本实施例中，航班季节性归类预测装置可以根据目标离港日期确定目标航班所对应的第一历史航班集合。具体的可以通过如下两种方式确定：
1、通过如下公式计算第一日期、第二日期、第三日期以及第四日期：
第一日期＝所述目标离港日-52×7×i-1；
第二日期＝所述目标离港日-52×7×i+1；
第三日期＝所述目标离港日-51×7×i；
第四日期＝所述目标离港日-53×7×i；
其中，i＝(1，2，3……，n)，i为当前年份之前的年份，例如当前年份为2021年，则i可以为2021年之前的多个年份，2020年，2019年，2018年等等；
将第一日期、第二日期、第三日期以及第四日期中与目标航班相对应的航班确定为第一历史航班集合。下面进行举例说明：
例如目标离港日期为2020年12月30日，那么第一日期即为2019年12月31日，第 二日期为2020年1月2日，第三日期以及第四日期为与目标离港日期同DOW的日期，第三日期为2019年12月25日，第四日期为2020年1月8日。该第一历史航班集合为2019年12月31日、2020年1月2日、2019年12月25日以及2020年1月8日中与该目标航班相对应的航班的集合。
2、通过目标历史参考日期的防火确定目标航班所对应的第一历史航班集合：
通过如下公式计算目标历史参考日期：
目标历史参考日期＝目标离港日期-52×7×i，其中，i＝(1，2，3……，n)，i为当前年份之前的年份；
根据目标历史参考日确定第一日期、第二日期、第三日期以及第四日期，所述第一日期为目标历史参考日的前一天，第二日期为目标历史参考日的后一天，第三日期为目标历史参考日的前一个星期，第四日期为目标历史参考日的后一个星期；
将第一日期、第二日期、第三日期以及第四日期中与目标航班相对应的航班确定为第一历史航班集合。下面进行举例说明：
例如该目标离港日为2020年12月30日，目标历史参考日期＝2020/12/30-52×7×1＝2020/1/1，对应DOW为星期三，目标历史参考日期前一天的日期为2019年12月31日(也即第一日期为2019年12月31日)；目标历史参考日期后一天的日期为2020年1月2日(也即第二日期为2020年1月2日)；参考日前一周同DOW的日期为2019年12月25日(也即第三日期为2019年12月25日)；参考日后一周同DOW的日期为2020年1月8日(也即第四日期为2020年1月8日)；该第一历史航班集合为2019年12月31日、2020年1月2日、2019年12月25日以及2020年1月8日中与该目标航班相对应的航班的集合。
104、获取第一历史航班集合中每个第一历史航班的航班数据。
本实施例中，航班季节性归类预测装置在确定第一历史航班集合之后，可以从本地数据库中获取该第一历史航班集合中每个第一历史航班的航班数据。需要说明的是，通过步骤101可以获取目标离港日期，通过步骤102可以构建N个数据池，通过步骤103至步骤104可以获取第一历史航班集合中每个第一历史航班的航班数据，然而，步骤101、步骤102、步骤103至步骤104之间并没有先后执行顺序的限制，可以先执行步骤101，也可以先执行步骤102，也可以先执行步骤103至步骤104，或者同时执行，具体不做限定。
105、根据N个数据池以及每个第一历史航班的航班数据确定每个第一历史航班的加权值。
本实施例中，航班季节性归类预测装置可以根据N个数据池以及每个第一历史航班的航班数据确定每个第一历史航班的加权值，具体的，可以首先根据每个第一历史航班的航班数据确定每个第一历史航班的收入数据(上述步骤102中已经对计算收入数据进行详细说明，具体此处不再赘述)，之后将第一收入数据划分至第一数据池，其中，该第一收入数据为每个第一历史航班中任意一个航班所对应的收入数据，第一数据池为N个数据池中中心数据与第一收入数据之间的距离最小的数据池，并确定该第一数据池的预设加权值，将该第一数据池的预设加权值确定为第一收入数据所对应航班的加权值。也就是说，可以将 每个第一历史航班所对应的收入数据划分至与其距离最近的数据池，并将对应的数据池的预设加权值确定为该每个第一历史航班的加权值。
需要说明的是，本地数据库中默认存储有N个数据池中每个数据池的预设加权值，本申请中将N设置为7(当然也还可以是其他的数值，具体不限定)，该7个数据池的预设加权值分别设置为：peak＝3，peak1＝2，peak2＝1，default＝0，off-peak2＝-1，off-peak1＝-2，off-peak＝-3，在将每个第一历史航班所对应的收入数据划分至7个数值之后，可以将数据池的预设加权值确定为划分至该数据池的第一历史航班的加权值，可以理解的是，若该第一历史航班集合中存在已经季节性归类的航班时，则将该航班的加权值确定为0。
106、根据每个第一历史航班的加权值以及每个第一历史航班的距离港天数确定目标航班的季节性归类。
本实施例中，航班季节性归类预测装置可以根据每个第一历史航班的加权值确定第一历史航班集合的加权总和，并根据该每个第一历史航班的距离港天数确定第一历史航班集合的总天数，最后根据加权总和以及总天数确定目标航班的季节性归类。一个实施例中，航班季节性归类预测装置根据加权总和以及总天数确定目标航班的季节性归类包括：将加权总和与总天数进行比较，得到比较结果，比较结果用于指示加权总和与总天数的大小关系；根据比较结果确定目标航班的季节性归类。
本实施例中，将第一历史航班集合的加权总和定义为字段X i，将第一历史航班集合的总天数定义为Y i；之后比较X i和Y i的大小关系，根据该大小关系确定目标航班的季节性归类，下面对比较X i和Y i的大小关系及具体的季节性归类进行说明：
若X i＞Y i，则将目标航班指派至peak，也即该目标航班的季节性归类为旺季1；
若
Figure PCTCN2022087049-appb-000003
则将目标航班指派至peak1，也即该目标航班的季节性归类为旺季2；
若
Figure PCTCN2022087049-appb-000004
则将目标航班指派至peak2，也即该目标航班的季节性归类为平季1；
若
Figure PCTCN2022087049-appb-000005
则将目标航班指派至off-peak，也即该目标航班的季节性归类为淡季2；
若
Figure PCTCN2022087049-appb-000006
则将目标航班指派至off-peak1，也即该目标航班的季节性归类为淡季1；
若
Figure PCTCN2022087049-appb-000007
则将目标航班指派至off-peak2，也即该目标航班的季节性归类为平季2。
综上所述，可以看出，本申请提供的实施例中，航班季节性归类预测装置在确定目标航班的季节性分类时，可以获取目标航班的目标离港日期，并构建更改目标航班所对应的N个数据池，根据目标离港日期确定第一历史航班集合，并根据该第一历史航班集合中每个第一历史航班的航班数据确定每个第一历史航班的加权值，最后根据每个第一历史航班的加权值以及每个第一历史航班的距离港天数确定目标航班的季节性归类，相对于现有的通过人为对航班进行季节性归类来说，可以提高季节性归类的准确性，避免因为人为对航 班的季节性归类而造成的偏颇现象。
可以理解的是，附图中的流程图和框图，图示了按照本申请各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
本申请实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
虽然采用特定次序描绘了各操作，但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下，多任务和并行处理可能是有利的。
应当理解，本申请的方法实施方式中记载的各个步骤可以按照不同的顺序执行，和/或并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。本申请的范围在此方面不受限制。
另外，本申请还可以以一种或多种程序设计语言或其组合来编写用于执行本申请的操作的计算机程序代码，上述程序设计语言包括但不限于面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
上面从航班季节性归类的预测方法的角度对本申请实施例进行说明，下面从航班季节性归类预测装置的角度对本申请实施例进行说明。
请参阅图2，图2为本申请实施例提供的航班季节性归类预测装置的虚拟结构意图，该航班季节性归类预测装置200包括：
获取单元201，用于从本地数据库中获取目标航班所对应的目标离港日期，所述目标航班为目标航司中待预测季节性归类的未离港航班；
构建单元202，用于构建所述目标航班所对应的N个数据池，其中，所述N为大于或等于2的正整数；
第一确定单元203，用于根据所述目标离港日期确定所述目标航班所对应的第一历史航班集合，所述第一历史航班集合中的每个第一历史航班均为未季节性归类的航班；
所述获取单元201，还用于获取所述第一历史航班集合中每个第一历史航班的航班数据；
第二确定单元204，用于根据所述N个数据池以及所述每个第一历史航班的航班数据确定所述每个第一历史航班的加权值；
第三确定单元205，用于根据所述每个第一历史航班的加权值以及所述每个第一历史航班的距离港天数确定所述目标航班的季节性归类。
一种可能的设计中，所述第三确定单元205具体用于：
根据所述每个第一历史航班的加权值确定所述第一历史航班集合的加权值总和；
根据所述每个第一历史航班的距离港天数确定所述第一历史航班集合的总天数；
根据所述加权总和以及所述总天数确定所述目标航班的季节性归类。
一种可能的设计中，所述第三确定单元205根据所述加权总和以及所述总天数确定所述目标航班的季节性归类包括：
将所述加权总和与所述总天数进行比较，得到比较结果，所述比较结果用于指示所述加权总和与所述总天数的大小关系；
根据所述比较结果确定所述目标航班的季节性归类。
一种可能的设计中，所述第二确定单元204具体用于：
根据所述每个第一历史航班的航班数据确定所述每个第一历史航班的收入数据；
将第一收入数据划分至第一数据池，所述第一收入数据为所述每个第一历史航班中任意一个航班所对应的收入数据，所述第一数据池为所述N个数据池中中心数据与所述第一收入数据之间距离最小的数据池；
确定所述第一数据池的预设加权值；
将所述第一数据池的预设加权值确定为所述第一收入数据所对应的航班的加权值。
一种可能的设计中，所述第一确定单元203具体用于：
通过如下公式计算第一日期、第二日期、第三日期以及第四日期：
所述第一日期＝所述目标离港日-52×7×i-1；
所述第二日期＝所述目标离港日-52×7×i+1；
所述第三日期＝所述目标离港日-51×7×i；
所述第四日期＝所述目标离港日-53×7×i；
其中，i＝(1，2，3……，n)，所述i为当前年份之前的年份；
将所述第一日期、所述第二日期、所述第三日期以及所述第四日期中与所述目标航班相对应的航班确定为所述第一历史航班集合。
一种可能的设计中，所述第一确定单元203还具体用于：
通过如下公式计算所述目标历史参考日期：
所述目标历史参考日期＝所述目标离港日期-52×7×i，其中，i＝(1，2，3……，n)，所述i为当前年份之前的年份；
根据所述目标历史参考日确定第一日期、第二日期、第三日期以及第四日期，所述第一日期为所述目标历史参考日的前一天，所述第二日期为所述目标历史参考日的后一天，所述第三日期为所述目标历史参考日的前一个星期，所述第四日期为所述目标历史参考日的后一个星期；
将所述第一日期、所述第二日期、所述第三日期以及所述第四日期中与所述目标航班相对应的航班确定为所述第一历史航班集合。
一种可能的设计中，所述构建单元202具体用于：
步骤1、获取所述目标航班所对应的第二历史航班集合中每个第二历史航班的航班数据；
步骤2、根据所述每个第二历史航班的航班数据计算所述每个第二历史航班的收入数据；
步骤3、将第二收入数据确定为第二数据池的中心数据，所述第二收入数据为第一航班对应的收入数据，所述第一航班为所述第二历史航班集合中任意一个航班，所述第二数据池为所述N个数据池中的任意一个；
步骤4、计算第三收入数据与所述第二收入数据的距离，所述第三收入数据为航班子集合中的任意一个航班所对应的收入数据，所述航班子集合为所述第二历史航班集合中除所述第一航班之外的航班集合；
步骤5、将第四收入数据划分至所述第二数据池，所述第四收入数据为第二航班所对应的收入数据，所述第二航班为所述航班子集合中与所述第二收入数据的距离最近的收入数据所对应的航班；
步骤6、计算划分后所述第二数据池的中心数据；
重复执行步骤3至步骤6，直至所述第二历史航班集合中每个第二历史航班所对应的收入数据均划分至所述N个数据池为止。
综上所述，可以看出，本申请提供的实施例中，航班季节性归类预测装置在确定目标航班的季节性分类时，可以获取目标航班的目标离港日期，并构建更改目标航班所对应的N个数据池，根据目标离港日期确定第一历史航班集合，并根据该第一历史航班集合中每个第一历史航班的航班数据确定每个第一历史航班的加权值，最后根据每个第一历史航班的加权值以及每个第一历史航班的距离港天数确定目标航班的季节性归类，相对于现有的通过人为对航班进行季节性归类来说，可以提高季节性归类的准确性，避免因为人为对航班的季节性归类而造成的偏颇现象。
需要说明的是，描述于本申请实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，单元的名称在某种情况下并不构成对该单元本身的限定，例如，获取单元还可以被描述为“获取目标用户的证件信息的单元”。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
请参阅图3，图3为本申请实施例提供的一种机器可读介质的实施例示意图。
如图3所示，本实施例提供了一种机器可读介质300，其上存储有计算机程序311，该计算机程序311被处理器执行时实现上述图1中所述航班季节性归类的预测方法的步骤。
需要说明的是，本申请的上下文中，机器可读介质可以是有形的介质，其可以包含或 存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
需要说明的是，本申请上述的机器可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本申请中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本申请中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
请参阅图4，图4是本申请实施例提供的一种服务器的硬件结构示意图，该服务器400可因配置或性能不同而产生比较大的差异，可以包括一个或一个以上中央处理器(central processing units，CPU)422(例如，一个或一个以上处理器)和存储器432，一个或一个以上存储应用程序442或数据444的存储介质430(例如一个或一个以上海量存储设备)。其中，存储器432和存储介质430可以是短暂存储或持久存储。存储在存储介质430的程序可以包括一个或一个以上模块(图示没标出)，每个模块可以包括对服务器中的一系列指令操作。更进一步地，中央处理器422可以设置为与存储介质430通信，在服务器400上执行存储介质430中的一系列指令操作。
服务器400还可以包括一个或一个以上电源426，一个或一个以上有线或无线网络接口450，一个或一个以上输入输出接口458，和/或，一个或一个以上操作系统441，例如Windows ServerTM，Mac OS XTM，UnixTM，LinuxTM，FreeBSDTM等等。
上述实施例中由航班季节性归类预测装置所执行的步骤可以基于该图4所示的服务器结构。
还需要说明的，根据本申请的实施例，上述图1的流程示意图描述的所述航班季节性归类的预测方法的过程可以被实现为计算机软件程序。例如，本申请的实施例包括一种计算机程序产品，其包括承载在非暂态计算机可读介质上的计算机程序，该计算机程序包含用于执行上述图1的流程示意图中所示的方法的程序代码。
尽管已经采用特定于结构特征和/或方法逻辑动作的语言描述了本主题，但是应当理解所附权利要求书中所限定的主题未必局限于上面描述的特定特征或动作。相反，上面所描述的特定特征和动作仅仅是实现权利要求书的示例形式。
虽然在上面论述中包含了若干具体实现细节，但是这些不应当被解释为对本申请的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地，在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
以上描述仅为本申请的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本申请中所涉及的公开范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述公开构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本申请中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。

Claims (10)

  1. 一种航班季节性归类的预测方法，其特征在于，包括：
    从本地数据库中获取目标航班所对应的目标离港日期，所述目标航班为目标航司中待预测季节性归类的未离港航班；
    构建所述目标航班所对应的N个数据池，其中，所述N为大于或等于2的正整数；
    根据所述目标离港日期确定所述目标航班所对应的第一历史航班集合，所述第一历史航班集合中的每个第一历史航班均为未季节性归类的航班；
    获取所述第一历史航班集合中每个第一历史航班的航班数据；
    根据所述N个数据池以及所述每个第一历史航班的航班数据确定所述每个第一历史航班的加权值；
    根据所述每个第一历史航班的加权值以及所述每个第一历史航班的距离港天数确定所述目标航班的季节性归类。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述每个第一历史航班的加权值以及所述每个第一历史航班的距离港天数确定所述目标航班的季节性归类包括：
    根据所述每个第一历史航班的加权值确定所述第一历史航班集合的加权值总和；
    根据所述每个第一历史航班的距离港天数确定所述第一历史航班集合的总天数；
    根据所述加权总和以及所述总天数确定所述目标航班的季节性归类。
  3. 根据权利要求2所述的方法，其特征在于，所述根据所述加权总和以及所述总天数确定所述目标航班的季节性归类包括：
    将所述加权总和与所述总天数进行比较，得到比较结果，所述比较结果用于指示所述加权总和与所述总天数的大小关系；
    根据所述比较结果确定所述目标航班的季节性归类。
  4. 根据权利要求1所述的方法，其特征在于，所述根据所述N个数据池以及所述每个第一历史航班的航班数据确定所述历史航班集合中的每个第一历史航班的加权值包括：
    根据所述每个第一历史航班的航班数据确定所述每个第一历史航班的收入数据；
    将第一收入数据划分至第一数据池，所述第一收入数据为所述每个第一历史航班中任意一个航班所对应的收入数据，所述第一数据池为所述N个数据池中中心数据与所述第一收入数据之间距离最小的数据池；
    确定所述第一数据池的预设加权值；
    将所述第一数据池的预设加权值确定为所述第一收入数据所对应的航班的加权值。
  5. 根据权利要求1至4中任一项所述的方法，其特征在于，所述根据所述目标离港日期确定所述目标航班所对应的第一历史航班集合包括：
    通过如下公式计算第一日期、第二日期、第三日期以及第四日期：
    所述第一日期＝所述目标离港日-52×7×i-1；
    所述第二日期＝所述目标离港日-52×7×i+1；
    所述第三日期＝所述目标离港日-51×7×i；
    所述第四日期＝所述目标离港日-53×7×i；
    其中，i＝(1，2，3……，n)，所述i为当前年份之前的年份；
    将所述第一日期、所述第二日期、所述第三日期以及所述第四日期中与所述目标航班相对应的航班确定为所述第一历史航班集合。
  6. 根据权利要求1至4中任一项所述的方法，其特征在于，所述根据所述目标离港日期确定所述目标航班所对应的第一历史航班集合包括：
    通过如下公式计算所述目标历史参考日期：
    所述目标历史参考日期＝所述目标离港日期-52×7×i，其中，i＝(1，2，3……，n)，所述i为当前年份之前的年份；
    根据所述目标历史参考日确定第一日期、第二日期、第三日期以及第四日期，所述第一日期为所述目标历史参考日的前一天，所述第二日期为所述目标历史参考日的后一天，所述第三日期为所述目标历史参考日的前一个星期，所述第四日期为所述目标历史参考日的后一个星期；
    将所述第一日期、所述第二日期、所述第三日期以及所述第四日期中与所述目标航班相对应的航班确定为所述第一历史航班集合。
  7. 根据权利要求1至4中任一项所述的方法，其特征在于，所述构建所述目标航班所对应的N个数据池包括：
    步骤1、获取所述目标航班所对应的第二历史航班集合中每个第二历史航班的航班数据；
    步骤2、根据所述每个第二历史航班的航班数据计算所述每个第二历史航班的收入数据；
    步骤3、将第二收入数据确定为第二数据池的中心数据，所述第二收入数据为第一航班对应的收入数据，所述第一航班为所述第二历史航班集合中任意一个航班，所述第二数据池为所述N个数据池中的任意一个；
    步骤4、计算第三收入数据与所述第二收入数据的距离，所述第三收入数据为航班子集合中的任意一个航班所对应的收入数据，所述航班子集合为所述第二历史航班集合中除所述第一航班之外的航班集合；
    步骤5、将第四收入数据划分至所述第二数据池，所述第四收入数据为第二航班所对应的收入数据，所述第二航班为所述航班子集合中与所述第二收入数据的距离最近的收入数据所对应的航班；
    步骤6、计算划分后所述第二数据池的中心数据；
    重复执行步骤3至步骤6，直至所述第二历史航班集合中每个第二历史航班所对应的收入数据均划分至所述N个数据池为止。
  8. 一种航班季节性归类预测装置，其特征在于，包括：
    获取单元，用于从本地数据库中获取目标航班所对应的目标离港日期，所述目标航班为目标航司中待预测季节性归类的未离港航班；
    构建单元，用于构建所述目标航班所对应的N个数据池，其中，所述N为大于或等于2的正整数；
    第一确定单元，用于根据所述目标离港日期确定所述目标航班所对应的第一历史航班集合，所述第一历史航班集合中的每个第一历史航班均为未季节性归类的航班；
    所述获取单元，还用于获取所述第一历史航班集合中每个第一历史航班的航班数据；
    第二确定单元，用于根据所述N个数据池以及所述每个第一历史航班的航班数据确定所述每个第一历史航班的加权值；
    第三确定单元，用于根据所述每个第一历史航班的加权值以及所述每个第一历史航班的距离港天数确定所述目标航班的季节性归类。
  9. 一种计算机设备，其特征在于，包括：存储器、处理器以及总线系统；
    其中，所述存储器用于存储程序；
    所述总线系统用于连接所述存储器以及所述处理器，以使所述存储器以及所述处理器进行通信；
    所述处理器用于执行所述存储器中的程序，并根据程序代码中的指令执行权利要求1至7中任一项所述的航班季节性归类的预测方法。
  10. 一种机器可读介质，其特征在于，包括指令，当所述指令在机器上运行时，使得机器执行上述权利要求1至7中任一项所述的航班季节性归类的预测方法。
PCT/CN2022/087049 2021-05-31 2022-04-15 航班季节性归类的预测方法、装置及机器可读介质 WO2022252847A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020237036733A KR20230159604A (ko) 2021-05-31 2022-04-15 항공편의 시즌별 분류 예측 방법 및 기구, 및 기계 판독가능 매체

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110604811.2A CN113282684B (zh) 2021-05-31 2021-05-31 航班季节性归类的预测方法、装置及机器可读介质
CN202110604811.2 2021-05-31

Publications (1)

Publication Number Publication Date
WO2022252847A1 true WO2022252847A1 (zh) 2022-12-08

Family

ID=77282866

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/087049 WO2022252847A1 (zh) 2021-05-31 2022-04-15 航班季节性归类的预测方法、装置及机器可读介质

Country Status (3)

Country Link
KR (1) KR20230159604A (zh)
CN (1) CN113282684B (zh)
WO (1) WO2022252847A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116503568A (zh) * 2023-06-27 2023-07-28 科大乾延科技有限公司 一种基于全息投影的三维场景显示方法
CN116757731A (zh) * 2023-08-16 2023-09-15 中国民航信息网络股份有限公司 航班季节因子的预测方法、装置、电子设备和存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113282684B (zh) * 2021-05-31 2023-08-29 中国民航信息网络股份有限公司 航班季节性归类的预测方法、装置及机器可读介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180012499A1 (en) * 2016-07-07 2018-01-11 Passur Aerospace, Inc. System and Method for Predicting Aircraft Taxi Time
CN109492334A (zh) * 2018-12-11 2019-03-19 青岛心中有数科技有限公司 航班延误的模型建立方法、预测方法及装置
CN109978211A (zh) * 2017-12-28 2019-07-05 北京航空航天大学 航班进离港率的预测方法和装置
CN111652427A (zh) * 2020-05-29 2020-09-11 航科院中宇（北京）新技术发展有限公司 一种基于数据挖掘分析的航班到达时刻预测方法及系统
CN113282684A (zh) * 2021-05-31 2021-08-20 中国民航信息网络股份有限公司 航班季节性归类的预测方法、装置及机器可读介质

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111784398A (zh) * 2020-06-30 2020-10-16 中国民航信息网络股份有限公司 一种航班数据的划分方法及相关装置
CN111784047B (zh) * 2020-06-30 2023-10-17 中国民航信息网络股份有限公司 一种季节因子的计算方法及相关装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180012499A1 (en) * 2016-07-07 2018-01-11 Passur Aerospace, Inc. System and Method for Predicting Aircraft Taxi Time
CN109978211A (zh) * 2017-12-28 2019-07-05 北京航空航天大学 航班进离港率的预测方法和装置
CN109492334A (zh) * 2018-12-11 2019-03-19 青岛心中有数科技有限公司 航班延误的模型建立方法、预测方法及装置
CN111652427A (zh) * 2020-05-29 2020-09-11 航科院中宇（北京）新技术发展有限公司 一种基于数据挖掘分析的航班到达时刻预测方法及系统
CN113282684A (zh) * 2021-05-31 2021-08-20 中国民航信息网络股份有限公司 航班季节性归类的预测方法、装置及机器可读介质

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116503568A (zh) * 2023-06-27 2023-07-28 科大乾延科技有限公司 一种基于全息投影的三维场景显示方法
CN116503568B (zh) * 2023-06-27 2023-11-07 科大乾延科技有限公司 一种基于全息投影的三维场景显示方法
CN116757731A (zh) * 2023-08-16 2023-09-15 中国民航信息网络股份有限公司 航班季节因子的预测方法、装置、电子设备和存储介质
CN116757731B (zh) * 2023-08-16 2023-11-17 中国民航信息网络股份有限公司 航班季节因子的预测方法、装置、电子设备和存储介质

Also Published As

Publication number Publication date
CN113282684B (zh) 2023-08-29
KR20230159604A (ko) 2023-11-21
CN113282684A (zh) 2021-08-20

Similar Documents

Publication Publication Date Title
WO2022252847A1 (zh) 航班季节性归类的预测方法、装置及机器可读介质
JP6742894B2 (ja) データ予測システムおよびデータ予測方法
EP3499451A1 (en) Prediction system and prediction method
WO2016119749A1 (zh) 一种订单分配系统及方法
CN108053242B (zh) 景点门票票量预测方法、系统、设备及存储介质
US20140281712A1 (en) System and method for estimating maintenance task durations
WO2022252846A1 (zh) 航段市场需求值的预测方法、装置及机器可读介质
US10332038B2 (en) Travel inventory demand modeling
Yang et al. Airport arrival flow prediction considering meteorological factors based on deep-learning methods
Grabbe et al. Clustering days with similar airport weather conditions
CN111325380A (zh) 基于多粒度时间注意力机制确定航班客座率的方法和系统
CN111027837B (zh) 预新增国际航线的参考航线确定方法、系统、设备及介质
WO2022252850A1 (zh) 航班的季节性归类方法、装置及机器可读介质
Tang et al. A gate reassignment framework for real time flight delays
Setiawan et al. Analysis of Demand Potential and Need for Passenger Terminal Facilities at Cikembar Sukabumi Airport
CN109727073B (zh) 访问流量控制方法、系统、电子设备和存储介质
CN112926809B (zh) 一种基于聚类和改进的xgboost的航班流量预测方法及系统
CN114239325B (zh) 机场值机托运柜台配置规划方法、装置、设备和存储介质
WO2023130617A1 (zh) 一种航班锁舱时机的评价方法及装置
Zhang et al. Learning-to-dispatch: Reinforcement learning based flight planning under emergency
Wang et al. A data-driven prediction model for aircraft taxi time by considering time series about gate and real-time factors
CN110414875B (zh) 产能数据处理方法、装置、电子设备及计算机可读介质
CN112308344A (zh) 一种未离港航班订座值预测方法、装置及电子设备
Sun et al. Evolution mechanism and optimisation of traffic congestion
CN117591919B (zh) 客流预测方法、装置、电子设备和存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22814894

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 20237036733

Country of ref document: KR

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 1020237036733

Country of ref document: KR

WWE Wipo information: entry into national phase

Ref document number: 2023574204

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22814894

Country of ref document: EP

Kind code of ref document: A1