Civil aviation transportation market data intelligent analysis method and system

Abstract

This invention relates to the field of civil aviation transportation market data analysis technology, specifically a method and system for intelligent analysis of civil aviation transportation market data. The method includes acquiring flight operation data, passenger transport data, and initial total passenger volume within a target statistical period; filtering cross-period flights based on actual departure time and planned departure time, determining operational deviations, and calculating disturbance contribution values; stripping disturbance components from the initial total passenger volume to obtain de-disturbed passenger volume, generating a disturbance impact quantification label; calculating the de-disturbed transportation market trend change index, and using the transportation market trend change index and disturbance impact quantification label as the transportation market analysis results. This invention quantifies the disturbance contribution value generated by cross-period flights and strips disturbance components from passenger transport index data, enabling the transportation market analysis results to distinguish the degree of impact between market changes and cross-period statistical disturbances, thus improving the accuracy of transportation market monitoring and trend analysis.

Description

Technical Field

[0001] This invention relates to the field of civil aviation transportation market data analysis technology, specifically a method and system for intelligent analysis of civil aviation transportation market data. Background Technology

[0002] As the civil aviation transportation market continues to expand, airlines, airports, and industry management agencies are conducting multi-time-dimensional statistical analysis of passenger data to plan capacity deployment and improve transportation efficiency. Existing civil aviation transportation market monitoring and analysis platforms, aiming for multi-dimensional data, refined analysis, and forward-looking data mining, have constructed a monitoring and analysis system covering business modules such as passenger transport reports, passenger transport monitoring, passenger transport rankings, and trend analysis. This system supports the collection and aggregation of indicators such as passenger volume, capacity, and load factor on a fixed statistical period basis, and reflects the time-varying characteristics of data through year-on-year and month-on-month comparisons, supporting a closed loop of passenger transport governance encompassing "planning-production-monitoring-optimization."

[0003] However, in actual operation, flight production execution status is continuous in time, and the actual departure time may deviate from the planned departure time under special circumstances such as delays. When the actual departure time and the planned departure time belong to different statistical periods, the flight production execution time may cross the boundary of the statistical period. In traditional statistical analysis, rigid attribution rules are usually used to uniformly assign all operational indicators of a flight to the statistical period containing the planned departure date. Although rigid attribution rules ensure the uniqueness of the attribution and the internal consistency at the macro level, they mask the actual deviation of the flight production execution time on the time axis, resulting in the inclusion of disturbance data caused by cross-period execution in the passenger traffic indicator data aggregated within the same statistical period. When performing month-on-month, year-on-year, and other trend analyses based on such passenger traffic indicator data containing disturbance components, the disturbance components are directly included in the market change results, reducing the accuracy of transportation market monitoring and trend analysis. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for intelligent analysis of civil aviation transportation market data, in order to solve the technical problem that existing rigid attribution rules cause cross-period flight disturbance data to be mixed into passenger transport statistics, interfering with the accuracy of transportation market monitoring and trend analysis.

[0005] To achieve the above objectives, on the one hand, the present invention provides a method for intelligent analysis of civil aviation transportation market data, the method comprising:

[0006] Step S1: Obtain flight operation data, passenger transport data, and initial total passenger volume within the target statistical period. The flight operation data includes the planned departure time, actual departure time, and capacity configuration data for each flight. The passenger transport data includes the boarding completion time and corresponding passenger volume for each flight. Select flights whose actual departure time belongs to a statistical period that is inconsistent with the statistical period of their planned departure time as cross-period flights. Step S2: Based on the boarding completion time and actual departure time of the cross-cycle flight, compare them with the time boundary of the target statistical period to determine the corresponding cross-cycle flight's operational offset. Step S3: Calculate the disturbance contribution value generated by the corresponding cross-cycle flight in the target statistical period based on the operation offset, capacity configuration data and passenger volume; based on the disturbance contribution value of each cross-cycle flight, remove the disturbance component from the initial total passenger volume to obtain the disturbance-free passenger volume for the target statistical period. Step S4: Generate a disturbance impact quantification label based on the initial total passenger volume and the disturbance-free passenger volume; calculate the disturbance-free transportation market trend change index based on the disturbance-free passenger volume and capacity configuration data within the target statistical period and the preset historical statistical period; use the transportation market trend change index and the disturbance impact quantification label as the transportation market analysis results for the target statistical period.

[0007] Furthermore, the method for filtering out flights whose actual departure time falls within a different statistical period than their planned departure time, and classifying them as cross-period flights, includes: The planned departure time and the actual departure time are converted into continuous time values ​​under a unified time base; the continuous time values ​​are periodically mapped according to a preset statistical period division rule to obtain the corresponding planned departure period identifier and actual departure period identifier; flights whose actual departure period identifier and planned departure period identifier are inconsistent are identified as cross-period flights.

[0008] Furthermore, the method for determining the operational offset of the corresponding cross-cycle flight by comparing the boarding completion time and actual departure time of the cross-cycle flight with the time boundary of the target statistical period includes: The time from boarding completion to actual departure time is divided into a pre-departure waiting period; the boarding offset component is determined based on the time difference between the boarding completion time and the target statistical period time boundary; the departure offset component is determined based on the time difference between the actual departure time and the target statistical period time boundary; and the operational offset of cross-period flights is generated based on the boarding offset component and the departure offset component.

[0009] Furthermore, the method also includes: When the time interval between boarding completion time and actual departure time spans at least two statistical period boundaries, the boarding offset component and departure offset component are calculated in segments according to the time interval corresponding to each statistical period, based on the overlap relationship between the time interval and each statistical period boundary, to obtain the boarding offset sub-quantity and departure offset sub-quantity for each statistical period. When the boarding offset sub-quantity and departure offset sub-quantity corresponding to the target statistical period are determined, the boarding offset sub-quantity corresponding to the target statistical period is taken as the boarding offset component, and the departure offset sub-quantity corresponding to the target statistical period is taken as the departure offset component.

[0010] Furthermore, the method for calculating the disturbance contribution value generated by the corresponding cross-cycle flight within the target statistical period based on the operational offset, capacity configuration data, and passenger volume includes: The boarding disturbance contribution component is calculated based on the boarding offset component and the passenger volume of the corresponding flight; the departure disturbance contribution component is calculated based on the departure offset component and the capacity configuration data of the corresponding flight. Based on the sign combination relationship between the boarding disturbance contribution component and the departure disturbance contribution component, the disturbance contribution value of cross-cycle flights within the target statistical period is determined.

[0011] Furthermore, the method for determining the disturbance contribution value of cross-period flights within the target statistical period based on the sign combination relationship between the boarding disturbance contribution component and the departure disturbance contribution component includes: When the boarding disturbance contribution component and the departure disturbance contribution component represent the same cross-cycle offset direction, the boarding disturbance contribution component and the departure disturbance contribution component are superimposed to obtain the disturbance contribution value. When the boarding disturbance contribution component and the departure disturbance contribution component represent cross-cycle offset directions opposite, the absolute difference between the boarding disturbance contribution component and the departure disturbance contribution component is calculated as the disturbance contribution value.

[0012] Furthermore, the method for removing disturbance components from the initial total passenger volume based on the disturbance contribution value of each cross-period flight to obtain the disturbance-free passenger volume for the target statistical period includes: The disturbance contribution values ​​of each cross-period flight are assigned to the positive disturbance set and negative disturbance set of the target statistical period according to their signs; each disturbance contribution value in the positive disturbance set is deducted from the initial total passenger volume, and the absolute value of each disturbance contribution value in the negative disturbance set is added to the initial total passenger volume to obtain the disturbance-free passenger volume.

[0013] Furthermore, the method for calculating the disturbance-free transportation market trend change index based on the disturbance-free passenger volume and capacity allocation data within the target statistical period and the preset historical statistical period includes: Calculate the target undisturbed passenger load factor based on the undisturbed passenger volume and capacity configuration data for the target statistical period; calculate the historical undisturbed passenger load factor based on the undisturbed passenger volume and capacity configuration data for the preset historical statistical period; and determine the undisturbed transportation market trend change index based on the target undisturbed passenger load factor and the historical undisturbed passenger load factor.

[0014] Based on the same inventive concept, this invention also provides a civil aviation transportation market data intelligent analysis system, the system comprising: The cross-period identification module is used to acquire flight operation data, passenger transport data, and initial total passenger volume within the target statistical period. The flight operation data includes the planned departure time, actual departure time, and capacity configuration data of each flight. The passenger transport data includes the boarding completion time and corresponding passenger volume of each flight. Flights whose statistical period of actual departure time is inconsistent with the statistical period of planned departure time are selected as cross-period flights.

[0015] The offset quantization module is used to compare the boarding completion time and actual departure time of cross-cycle flights with the time boundary of the target statistical period to determine the operating offset of the corresponding cross-cycle flights.

[0016] The disturbance stripping module is used to calculate the disturbance contribution value generated by the corresponding cross-cycle flight in the target statistical period based on the operation offset, capacity configuration data and passenger volume; and to strip the disturbance component from the initial total passenger volume based on the disturbance contribution value of each cross-cycle flight to obtain the disturbance-free passenger volume for the target statistical period.

[0017] The trend analysis module is used to generate a quantitative indicator of disturbance impact based on the initial total passenger volume and the disturbance-free passenger volume; calculate the disturbance-free transportation market trend change index based on the disturbance-free passenger volume and capacity configuration data within the target statistical period and the preset historical statistical period; and use the transportation market trend change index and the disturbance impact quantitative indicator as the transportation market analysis result for the target statistical period.

[0018] Compared with the prior art, the beneficial effects of the present invention are: 1. By identifying cross-period flights whose actual departure time and planned departure time do not belong to the same statistical period, the disturbance contribution value generated by cross-period flights within the target statistical period is calculated, and the disturbance component is removed from the initial total passenger volume. This allows the transportation market trend change indicators and disturbance impact quantification indicators to reflect the market changes and disturbance impact degree after removing cross-period disturbances, respectively. This avoids the reduction in the accuracy of transportation market monitoring and trend analysis caused by directly including cross-period operational disturbances in the transportation market trend analysis results.

[0019] 2. When determining the operational offset, the boarding offset component and the departure offset component are calculated independently, so that the passenger flow time anchor point offset of the boarding event and the production execution time anchor point offset of the actual departure event are quantified separately. The generation of the disturbance contribution value is based on the sign combination relationship of the two components to distinguish between unidirectional superposition and reverse cancellation. This enables differentiated disturbance separation of passenger flow misalignment and production execution misalignment at the statistical period boundary for cross-period flights, improving the consistency between the disturbance component separation result and the flight production execution process. Attached Figure Description

[0020] Figure 1 This is a flowchart of a method for intelligent analysis of civil aviation transportation market data according to the present invention; Figure 2 This is a block diagram of a civil aviation transportation market data intelligent analysis system according to the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Before providing examples, it is necessary to explain the application scenarios of this invention. This invention is applicable to scenarios involving multi-time-dimensional trend analysis of civil aviation passenger transport statistics. It is particularly applicable to the month-on-month or year-on-year analysis of short-cycle passenger transport indicators such as daily and weekly data under the normalized operation of cross-day delays. It is necessary to identify and quantify the cross-cycle disturbance component introduced by rigid attribution rules and separate the disturbance component from the passenger transport indicator data, so that the output transportation market trend change indicator is closer to the market change result after removing the cross-cycle operation disturbance, thereby reducing the deviation caused by the coupling of statistical rules and operation disturbances.

[0023] Example 1: As Figure 1 As shown in the figure, this embodiment provides a method for intelligent analysis of civil aviation transportation market data, the method including: The system acquires flight operation data, passenger transport data, and initial total passenger volume for the target statistical period. The flight operation data includes the planned departure time, actual departure time, and capacity configuration data for each flight. The passenger transport data includes the boarding completion time and corresponding passenger volume for each flight. The planned departure time and actual departure time are converted into continuous time values ​​under a unified time base. The continuous time values ​​are then periodically mapped according to a preset statistical period division rule to obtain the corresponding planned departure period identifier and actual departure period identifier. Flights whose actual departure period identifier does not match the planned departure period identifier are identified as cross-period flights.

[0024] In this embodiment, the target statistical period is denoted as Day T, the statistical period is divided by calendar days, the time boundary is from 00:00:00 on Day T to 23:59:59 on Day T, and the unified time base adopts continuous time values ​​in seconds. Flight operation data includes three flights. Flight F1's scheduled departure time is 23:10:00 on Day T-1, and the actual departure time is 00:18:00 on Day T. The capacity configuration data includes 180 available seats. Flight F2's scheduled departure time is 08:45:00 on Day T, and the actual departure time is 08:50:00 on Day T. The capacity configuration data includes 200 available seats. Flight F3's scheduled departure time is 22:55:00 on Day T-1, and the actual departure time is 01:32:00 on Day T. The capacity configuration data includes 160 available seats. Passenger transport data includes three flights. Boarding for Flight F1 was completed at 00:02:00 on Day T, with a passenger volume of 165. Boarding for Flight F2 was completed at 08:35:00 on Day T, with a passenger volume of 188. Boarding for Flight F3 was completed at 23:48:00 on Day T-1, with a passenger volume of 142. The initial total passenger volume was 495, which is the direct summation of passenger volumes from the passenger transport data of Flights F1, F2, and F3 within the target statistical period. The boarding completion time can be either the cabin door closing time or the boarding end time recorded by the boarding system.

[0025] Taking 00:00:00 on day T-1 as the zero point, then 23:10:00 on day T-1 corresponds to a continuous time value of 83400, and 00:00:00 on day T corresponds to a continuous time value of 86400. The planned departure time of flight F1 has a continuous time value of 83400, and the actual departure time has a continuous time value of 86580. The planned departure time of flight F2 has a continuous time value of 117900, and the actual departure time has a continuous time value of 118200. The planned departure time of flight F3 has a continuous time value of 82500, and the actual departure time has a continuous time value of 91920.

[0026] The continuous time value interval for day T-1 is [0, 86399], and the continuous time value interval for day T is [86400, 172799]. Flight F1's scheduled departure time of 83400 falls within the interval of day T-1, and the scheduled departure cycle is identified as D1. Flight F1's actual departure time of 86580 falls within the interval of day T, and the actual departure cycle is identified as D2. Flight F2's scheduled departure time of 117900 falls within the interval of day T, and the scheduled departure cycle is identified as D2. Flight F2's actual departure time of 118200 falls within the interval of day T, and the actual departure cycle is identified as D2. Flight F3's scheduled departure time of 82500 falls within the interval of day T-1, and the scheduled departure cycle is identified as D1. Flight F3's actual departure time of 91920 falls within the interval of day T, and the actual departure cycle is identified as D2.

[0027] Flight F1's actual departure cycle identifier D2 differs from its planned departure cycle identifier D1, therefore it is classified as a cross-cycle flight. Flight F2's actual departure cycle identifier D2 matches its planned departure cycle identifier D2, therefore it is not classified as a cross-cycle flight. Flight F3's actual departure cycle identifier D2 differs from its planned departure cycle identifier D1, therefore it is classified as a cross-cycle flight. Cross-cycle flights include both Flight F1 and Flight F3.

[0028] The time from boarding completion to actual departure time is divided into a pre-departure waiting period; the boarding offset component is determined based on the time difference between the boarding completion time and the target statistical period time boundary; the departure offset component is determined based on the time difference between the actual departure time and the target statistical period time boundary; and the operational offset of cross-period flights is generated based on the boarding offset component and the departure offset component.

[0029] When the time interval between boarding completion time and actual departure time spans at least two statistical period boundaries, the boarding offset component and departure offset component are calculated in segments according to the time interval corresponding to each statistical period, based on the overlap relationship between the time interval and each statistical period boundary, to obtain the boarding offset sub-quantity and departure offset sub-quantity for each statistical period. When the boarding offset sub-quantity and departure offset sub-quantity corresponding to the target statistical period are determined, the boarding offset sub-quantity corresponding to the target statistical period is taken as the boarding offset component, and the departure offset sub-quantity corresponding to the target statistical period is taken as the departure offset component.

[0030] For example, for cross-cycle flight F1, the boarding completion time from 86520 to the actual departure time from 86580 is divided into a pre-departure waiting period with a length of 60 seconds. For cross-cycle flight F3, the boarding completion time from 85680 to the actual departure time from 91920 is divided into a pre-departure waiting period with a length of 6240 seconds.

[0031] The boarding offset component is the difference between the boarding completion time and the target statistical period time boundary. The target statistical period time boundary is taken as the boundary starting from day T, which is 86400. For cross-period flight F1, the boarding completion time is 86520, and the boarding offset component is 86520 - 86400 = +120. For cross-period flight F3, the boarding completion time is 85680, and the boarding offset component is 85680 - 86400 = -720.

[0032] The departure offset component is the difference between the actual departure time and the target statistical period time boundary. For cross-period flight F1, the actual departure time is 86580, and the departure offset component is 86580 - 86400 = +180. For cross-period flight F3, the actual departure time is 91920, and the departure offset component is 91920 - 86400 = +5520. The boarding offset component +120 and the departure offset component +180 for cross-period flight F1 constitute the operational offset of cross-period flight F1. The boarding offset component -720 and the departure offset component +5520 for cross-period flight F3 constitute the operational offset of cross-period flight F3.

[0033] The pre-departure waiting range for cross-cycle flight F1, from 86520 to 86580, is entirely within the range of day T and does not cross any statistical cycle boundaries. The pre-departure waiting range for cross-cycle flight F3, from 85680 to 91920, crosses the boundary 86400 between day T-1 and day T, crossing only one statistical cycle boundary, thus failing to meet the condition that the pre-departure waiting range crosses at least two statistical cycle boundaries. Neither cross-cycle flight F1 nor cross-cycle flight F3 triggers the segmented calculation of the offset component.

[0034] When a cross-cycle flight meets the condition that its pre-departure waiting interval crosses at least two statistical cycle boundaries, taking cross-cycle flight F5 as an example, the boarding completion time for cross-cycle flight F5 is 23:00:00 on day T-1, corresponding to a continuous time value of 82800; the actual departure time is 01:00:00 on day T+1, corresponding to a continuous time value of 176400. The pre-departure waiting interval for cross-cycle flight F5 from the boarding completion time of 82800 to the actual departure time of 176400 is the pre-departure waiting interval, with a length of 93600 seconds. The pre-departure waiting interval crosses the boundary between day T-1 and day T (86400) and the boundary between day T and day T+1 (172800), thus crossing two statistical cycle boundaries.

[0035] Based on the overlap between the pre-departure waiting period and the boundaries of each statistical period, the boarding offset component and the departure offset component are calculated in segments according to the time intervals corresponding to each statistical period. The pre-departure waiting period has a time sub-interval of [82800, 86400] on day T-1, corresponding to a duration of 3600 seconds; a time sub-interval of [86400, 172800] on day T, corresponding to a duration of 86400 seconds; and a time sub-interval of [172800, 176400] on day T+1, corresponding to a duration of 3600 seconds. The boarding offset component is segmented according to the above durations, with a boarding offset sub-value of -3600 on day T-1, +86400 on day T, and +3600 on day T+1. The departure offset component is segmented according to the above time period. The departure offset sub-quantity is 0 on day T-1, 0 on day T, and +3600 on day T+1. When the target statistical period is day T, the boarding offset sub-quantity +86400 corresponding to day T is taken as the boarding offset component, and the departure offset sub-quantity 0 corresponding to day T is taken as the departure offset component.

[0036] The boarding disturbance contribution component is calculated based on the boarding offset component and the passenger volume of the corresponding flight; the departure disturbance contribution component is calculated based on the departure offset component and the capacity configuration data of the corresponding flight. When the boarding disturbance contribution component and the departure disturbance contribution component represent the same cross-cycle offset direction, the boarding disturbance contribution component and the departure disturbance contribution component are superimposed to obtain the disturbance contribution value. When the boarding disturbance contribution component and the departure disturbance contribution component represent cross-cycle offset directions opposite, the absolute difference between the boarding disturbance contribution component and the departure disturbance contribution component is calculated as the disturbance contribution value. The disturbance contribution values ​​of each cross-cycle flight are assigned to the positive disturbance set and negative disturbance set of the target statistical period according to their signs. Each disturbance contribution value in the positive disturbance set is deducted from the initial total passenger volume, and the absolute values ​​of each disturbance contribution value in the negative disturbance set are added to the initial total passenger volume to obtain the de-disturbed passenger volume. A disturbance impact quantification label is generated based on the initial total passenger volume and the de-disturbed passenger volume.

[0037] When the pre-departure waiting period of a cross-cycle flight is completely within the target statistical period, it means that both the boarding completion time and the actual departure time fall within the target statistical period. Although there may be a situation where the planned departure period and the actual departure period are inconsistent, there is no passenger volume misalignment that needs to be separated within the target statistical period. In this case, both the boarding disturbance contribution component and the departure disturbance contribution component are determined to be 0.

[0038] When the pre-departure waiting interval of a cross-cycle flight crosses the boundary of the target statistical period, the passenger volume of the corresponding flight is divided according to the proportion of the time sub-intervals of the pre-departure waiting interval on both sides of the boundary of the target statistical period. The passenger volume portion outside the target statistical period forms the disturbance contribution value, while the passenger volume portion within the target statistical period is retained within the target statistical period.

[0039] The boarding completion time for Flight F1 is 00:02:00 on Day T, corresponding to a continuous time value of 86520; the actual departure time is 00:18:00 on Day T, corresponding to a continuous time value of 86580. Both the boarding completion time (86520) and the actual departure time (86580) for Flight F1 are after the time boundary 86400 on Day T, and the entire pre-departure waiting interval [86520, 86580] falls within Day T. Flight F1 does not generate any disturbance contribution value that needs to be separated from the target statistical period; the boarding disturbance contribution component is 0 people, the departure disturbance contribution component is 0 people, and the total disturbance contribution value is 0 people.

[0040] The boarding completion time for Flight F3 is 23:48:00 on day T-1, corresponding to a continuous time value of 85680; the actual departure time is 01:32:00 on day T, corresponding to a continuous time value of 91920. The boarding completion time 85680 for Flight F3 falls before the time boundary 86400 on day T, while the actual departure time 91920 falls after the time boundary 86400 on day T. The pre-departure waiting interval [85680, 91920] spans the boundary 86400 between day T-1 and day T, with a total waiting interval duration of 91920 - 85680 = 6240 seconds. The pre-departure waiting interval has a time sub-interval of [85680, 86400] on day T-1, with a duration of 720 seconds; and a time sub-interval of [86400, 91920] on day T, with a duration of 5520 seconds. The boarding offset component = 85680 - 86400 = -720, and the departure offset component = 91920 - 86400 = +5520. The boarding offset component of -720 indicates that the boarding completion time offset direction points to day T-1, and the departure offset component of +5520 indicates that the actual departure time offset direction points to day T. The two components have opposite signs.

[0041] In this embodiment, the number of available seats in the capacity configuration data is used to define the carrying capacity benchmark for the departure-side disturbance contribution component. Flight F3 has 160 available seats, and its passenger volume of 142 does not exceed the available seat count of 160. Therefore, the passenger volume of 142 for Flight F3 is used as the basis for calculating the departure-side disturbance contribution component. The passenger volume of 142 for Flight F3 is divided according to the time intervals of the pre-departure waiting period on both sides of the boundary: Passenger volume corresponding to day T-1 = 142 × 720 ÷ 6240 ≈ 16 people; Passenger volume corresponding to day T = 142 × 5520 ÷ 6240 ≈ 126 people. Since the 16 passengers corresponding to day T-1 are already included in the initial total passenger volume of day T in the target statistical period, but the boarding completion time corresponding to this part is before day T, these 16 people are determined as the positive disturbance contribution value generated by Flight F3 within the target statistical period.

[0042] Boarding for Flight F2 was completed at 08:35:00 on Day T, and the actual departure time was 08:50:00 on Day T. Since both the actual and planned departure times fall on Day T, Flight F2 is not a cross-cycle flight. The passenger volume of 188 passengers for Flight F2 is entirely included in the passenger volume that should belong to Day T itself, and does not generate any disturbance contribution.

[0043] The disturbance contribution value of cross-period flight F1 is 0 people, and the disturbance contribution value of cross-period flight F3 is +16 people. The +16 people disturbance contribution value of cross-period flight F3 is added to the positive disturbance set on day T of the target statistical period, while the negative disturbance set is empty. The initial total passenger volume on day T of the target statistical period is 495 people, which is the direct sum of the passenger volumes of flights F1, F2, and F3. The disturbance contribution value of 16 people in the positive disturbance set is subtracted from the initial total passenger volume of 495 people, resulting in a disturbance-free passenger volume of 479 people. The disturbance impact quantification indicator = |initial total passenger volume - disturbance-free passenger volume| = |495 - 479| = 16 people.

[0044] Based on the disturbance-free passenger volume and capacity allocation data for the target statistical period, calculate the target disturbance-free load factor; based on the disturbance-free passenger volume and capacity allocation data for a preset historical statistical period, calculate the historical disturbance-free load factor; based on the target disturbance-free load factor and the historical disturbance-free load factor, determine the disturbance-free transportation market trend change index. Use the transportation market trend change index and the disturbance impact quantification indicator as the transportation market analysis results for the target statistical period.

[0045] The disturbance-free passenger volume on day T of the target statistical period is 479 people. Within the target statistical period, the available seats for flights F1, F2, and F3 are 180, 200, and 160 respectively, totaling 540 seats. The target disturbance-free load factor = 479 ÷ 540 × 100% ≈ 88.7%. The preset historical statistical period is day T-7, which has undergone the same disturbance component stripping process as day T of the target statistical period. The disturbance-free passenger volume on day T-7 is 450 people, and the capacity configuration data includes a total of 500 available seats. The historical disturbance-free load factor = 450 ÷ 500 × 100% = 90.0%. The transportation market analysis results for day T of the target statistical period include indicators of transportation market trend changes and quantitative indicators of disturbance impact. The transportation market trend change indicator is the year-on-year change in load factor after removing disturbances, i.e., the difference between the target removed load factor and the historical removed load factor = 88.7% - 90.0% = -1.3 percentage points. The disturbance impact quantification indicator is 16 people. The transportation market trend change indicator is used to characterize the direction and magnitude of load factor changes after removing cross-cycle disturbances, and the disturbance impact quantification indicator is used to characterize the degree of impact of cross-cycle operational disturbances on the passenger transport statistics results of the target statistical period.

[0046] Example 2: Based on the same inventive concept, such as Figure 2 As shown in the figure, this embodiment also provides a civil aviation transportation market data intelligent analysis system, the system comprising: The cross-period identification module is used to acquire flight operation data, passenger transport data, and initial total passenger volume within the target statistical period. The flight operation data includes the planned departure time, actual departure time, and capacity configuration data of each flight. The passenger transport data includes the boarding completion time and corresponding passenger volume of each flight. Flights whose statistical period of actual departure time is inconsistent with the statistical period of planned departure time are selected as cross-period flights.

[0047] The offset quantization module is used to compare the boarding completion time and actual departure time of cross-cycle flights with the time boundary of the target statistical period to determine the operating offset of the corresponding cross-cycle flights.

[0048] The disturbance stripping module is used to calculate the disturbance contribution value generated by the corresponding cross-cycle flight in the target statistical period based on the operation offset, capacity configuration data and passenger volume; and to strip the disturbance component from the initial total passenger volume based on the disturbance contribution value of each cross-cycle flight to obtain the disturbance-free passenger volume for the target statistical period.

[0049] The trend analysis module is used to generate a quantitative indicator of disturbance impact based on the initial total passenger volume and the disturbance-free passenger volume; calculate the disturbance-free transportation market trend change index based on the disturbance-free passenger volume and capacity configuration data within the target statistical period and the preset historical statistical period; and use the transportation market trend change index and the disturbance impact quantitative indicator as the transportation market analysis result for the target statistical period.

[0050] It should be noted that the specific methods by which each module performs operations in the system described in the above embodiments have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0051] Finally, it should be noted that although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent analysis of civil aviation transportation market data, characterized in that, The method includes: Obtain flight operation data, passenger transport data, and initial total passenger volume within the target statistical period. The flight operation data includes the planned departure time, actual departure time, and capacity configuration data for each flight. The passenger transport data includes the boarding completion time and corresponding passenger volume for each flight. Select flights whose actual departure time belongs to a statistical period that is inconsistent with the statistical period of their planned departure time as cross-period flights. Based on the boarding completion time and actual departure time of cross-cycle flights, the time boundary of the target statistical period is compared to determine the corresponding cross-cycle flight's operational offset. Based on the operational offset, capacity configuration data, and passenger volume, calculate the disturbance contribution value generated by the corresponding cross-cycle flight within the target statistical period; based on the disturbance contribution value of each cross-cycle flight, remove the disturbance component from the initial total passenger volume to obtain the disturbance-free passenger volume for the target statistical period. Based on the initial total passenger volume and the disturbance-free passenger volume, a disturbance impact quantification label is generated; based on the disturbance-free passenger volume and capacity allocation data within the target statistical period and the preset historical statistical period, a disturbance-free transportation market trend change index is calculated; the transportation market trend change index and the disturbance impact quantification label are used as the transportation market analysis results for the target statistical period.

2. The intelligent analysis method for civil aviation transportation market data according to claim 1, characterized in that, The method for identifying flights whose actual departure time does not fall within the same statistical period as their planned departure time as cross-period flights includes: The planned departure time and the actual departure time are converted into continuous time values ​​under a unified time base; the continuous time values ​​are periodically mapped according to a preset statistical period division rule to obtain the corresponding planned departure period identifier and actual departure period identifier; flights whose actual departure period identifier and planned departure period identifier are inconsistent are identified as cross-period flights.

3. The intelligent analysis method for civil aviation transportation market data according to claim 2, characterized in that, The method for determining the operational offset of a cross-cycle flight by comparing the boarding completion time and actual departure time of the cross-cycle flight with the time boundary of the target statistical period includes: The time from boarding completion to actual departure time is divided into a pre-departure waiting period; the boarding offset component is determined based on the time difference between the boarding completion time and the target statistical period time boundary; the departure offset component is determined based on the time difference between the actual departure time and the target statistical period time boundary; and the operational offset of cross-period flights is generated based on the boarding offset component and the departure offset component.

4. The intelligent analysis method for civil aviation transportation market data according to claim 3, characterized in that, The method further includes: When the time interval between boarding completion time and actual departure time spans at least two statistical period boundaries, the boarding offset component and departure offset component are calculated in segments according to the time interval corresponding to each statistical period, based on the overlap relationship between the time interval and each statistical period boundary, to obtain the boarding offset sub-quantity and departure offset sub-quantity for each statistical period. When the boarding offset sub-quantity and departure offset sub-quantity corresponding to the target statistical period are determined, the boarding offset sub-quantity corresponding to the target statistical period is taken as the boarding offset component, and the departure offset sub-quantity corresponding to the target statistical period is taken as the departure offset component.

5. The intelligent analysis method for civil aviation transportation market data according to claim 3, characterized in that, The method for calculating the disturbance contribution value generated by the corresponding cross-cycle flight within the target statistical period based on the operational offset, capacity configuration data, and passenger volume includes: The boarding disturbance contribution component is calculated based on the boarding offset component and the passenger volume of the corresponding flight; the departure disturbance contribution component is calculated based on the departure offset component and the capacity configuration data of the corresponding flight. Based on the sign combination relationship between the boarding disturbance contribution component and the departure disturbance contribution component, the disturbance contribution value of cross-cycle flights within the target statistical period is determined.

6. The intelligent analysis method for civil aviation transportation market data according to claim 5, characterized in that, The method for determining the disturbance contribution value of cross-cycle flights within the target statistical period based on the sign combination relationship between the boarding disturbance contribution component and the departure disturbance contribution component includes: When the boarding disturbance contribution component and the departure disturbance contribution component represent the same cross-cycle offset direction, the boarding disturbance contribution component and the departure disturbance contribution component are superimposed to obtain the disturbance contribution value. When the boarding disturbance contribution component and the departure disturbance contribution component represent cross-cycle offset directions opposite, the absolute difference between the boarding disturbance contribution component and the departure disturbance contribution component is calculated as the disturbance contribution value.

7. The intelligent analysis method for civil aviation transportation market data according to claim 6, characterized in that, The method for removing disturbance components from the initial total passenger volume based on the disturbance contribution value of each cross-period flight to obtain the disturbance-free passenger volume for the target statistical period includes: The disturbance contribution values ​​of each cross-period flight are assigned to the positive disturbance set and negative disturbance set of the target statistical period according to their signs; each disturbance contribution value in the positive disturbance set is deducted from the initial total passenger volume, and the absolute value of each disturbance contribution value in the negative disturbance set is added to the initial total passenger volume to obtain the disturbance-free passenger volume.

8. The intelligent analysis method for civil aviation transportation market data according to claim 1, characterized in that, The method for calculating the disturbance-free transportation market trend change index based on the disturbance-free passenger volume and capacity allocation data within the target statistical period and the preset historical statistical period includes: Calculate the target undisturbed passenger load factor based on the undisturbed passenger volume and capacity configuration data for the target statistical period; calculate the historical undisturbed passenger load factor based on the undisturbed passenger volume and capacity configuration data for the preset historical statistical period; and determine the undisturbed transportation market trend change index based on the target undisturbed passenger load factor and the historical undisturbed passenger load factor.

9. A civil aviation transportation market data intelligent analysis system, characterized in that, The system includes: The cross-period identification module is used to acquire flight operation data, passenger transport data, and initial total passenger volume within the target statistical period. The flight operation data includes the planned departure time, actual departure time, and capacity configuration data of each flight. The passenger transport data includes the boarding completion time and corresponding passenger volume of each flight. Flights whose statistical period of actual departure time is inconsistent with the statistical period of planned departure time are selected as cross-period flights. The offset quantization module is used to compare the boarding completion time and actual departure time of cross-cycle flights with the time boundary of the target statistical period to determine the operating offset of the corresponding cross-cycle flights. The disturbance stripping module is used to calculate the disturbance contribution value generated by the corresponding cross-period flight in the target statistical period based on the operation offset, capacity configuration data and passenger volume; and to strip the disturbance component from the initial total passenger volume based on the disturbance contribution value of each cross-period flight to obtain the disturbance-free passenger volume for the target statistical period. The trend analysis module is used to generate a quantitative indicator of disturbance impact based on the initial total passenger volume and the disturbance-free passenger volume; calculate the disturbance-free transportation market trend change index based on the disturbance-free passenger volume and capacity configuration data within the target statistical period and the preset historical statistical period; and use the transportation market trend change index and the disturbance impact quantitative indicator as the transportation market analysis result for the target statistical period.

Images