A method, system, storage medium and device for discovering hot flights in real time

Abstract

The application discloses a kind of methods, systems, storage medium and equipment that can discover hot spot flight in real time, comprising: the access and attention data of each flight are sliced according to time dimension Statistics, and analysis is carried out to obtain real-time heat parameter;Obtain the flight status of each flight;Wherein, flight status includes normal state and abnormal state;The flight in abnormal state is adjusted parameter, and the abnormal parameter of the flight in abnormal state is obtained;According to the real-time heat parameter and abnormal parameter of each flight, the final heat parameter of each flight is obtained;According to the final heat parameter of each flight, each flight is sorted, and real-time heat ranking is obtained.The application can better discover special flight with particularity or abnormality according to real-time heat ranking, so as to be used to show or early warning.

Description

Technical Field

[0001] This invention relates to the field of flight early warning technology, and in particular to a method, system, storage medium, and device for real-time detection of hot flights. Background Technology

[0002] "Hot flights" primarily refer to flights that have experienced special circumstances or abnormal conditions, resulting in high levels of attention and thus possessing certain display and early warning value. Currently, algorithms for identifying hot flights primarily rely on simple ranking based on the number of followers. However, such algorithms have significant limitations. For example, popular business flights and large aircraft with high load factors, due to a high proportion of frequent flyers and a large number of passengers, are easily ranked high in the attention lists. However, these flights may not inherently possess any significant special or abnormal characteristics. Summary of the Invention

[0003] To address the technical problems existing in the background art, the present invention proposes a method, system, storage medium, and device for real-time detection of popular flights.

[0004] This invention proposes a method for real-time detection of popular flights, comprising:

[0005] Access and attention data for each flight are sliced ​​and statistically analyzed according to the time dimension to obtain real-time popularity parameters;

[0006] Obtain the flight status of each flight; the flight status includes normal status and abnormal status.

[0007] Adjust the parameters of flights in abnormal status to obtain the abnormal parameters of the flights in abnormal status;

[0008] Based on the real-time popularity parameters and abnormal parameters of each flight, the final popularity parameters of each flight are obtained.

[0009] The flights are sorted according to their final popularity parameters to obtain a real-time popularity ranking.

[0010] Preferably, the final heat parameter is the sum of the real-time heat parameter and the abnormal parameter.

[0011] Preferably, the abnormal states include: flight abnormal states such as circling, circling, diverting, diverting and then canceling, diverting and then arriving, returning, returning and then canceling, returning and then arriving, losing contact, crash, delay warning, and delays exceeding a second preset time. Each flight abnormal state has corresponding abnormal parameters.

[0012] Preferably, the access and attention data for each flight are sliced ​​and statistically analyzed according to the time dimension to obtain real-time popularity parameters, specifically including:

[0013] Divide the current time period evenly into multiple time segments;

[0014] Retrieve access and attention data for each flight within the current time segment and all time segments preceding the current time segment, as well as the access and attention counts for each time segment corresponding to the current time segment and all time segments preceding the current time segment within n historical time periods; where n is an integer greater than or equal to 1;

[0015] Based on the flight access and attention data of each flight in the current time segment and all time segments before the current time segment, as well as the access and attention data of each time segment in the corresponding n historical time periods, calculate the first coefficient of each flight in the current time period and each time segment in the previous n-1 historical time periods, and the second coefficient of each flight in the current time period and each time segment in the previous n-1 historical time periods.

[0016] The first coefficient is the ratio of the access and attention data of a certain time segment to the access and attention data of the previous time segment within the same time period.

[0017] The second coefficient is the ratio of the access and attention data of a certain time segment to the access and attention data of the corresponding time segment in the previous historical time segment before the time segment.

[0018] The real-time popularity parameters of each flight are obtained by weighting the first coefficient of each time segment in the current time period and the previous n-1 historical time periods and the second coefficient of each time segment in the current time period and the previous n-1 historical time periods.

[0019] Preferably, the first coefficient is q j -i =m j -i / m j -(i+1) The second coefficient is p. j -i =m j -i / m j+1 -i :

[0020] Where q represents the first coefficient, p represents the second coefficient, and m represents access and attention data;

[0021] j = 0, 1, 2, ..., n. When j = 0, it means that the time period is the current time period. When j = 1, 2, ..., n, it means that the time period is the j-th historical time period before the current time period.

[0022] i = 0, 1, 2, ..., k, where k is a positive integer greater than 2; when i = 0, it means that the time segment is the current time segment or the time segment corresponding to the current time segment; when i = 1, 2, ..., k, it means that the time segment is the i-th time segment before the current time segment or the time segment corresponding to the i-th time segment before the current time segment.

[0023] Preferably, before weighting and calculating the first coefficient of each flight in the current time period and the first coefficient of each time segment in the previous n-1 historical time periods, and the second coefficient of each flight in the current time period and the previous n-1 historical time periods to obtain the real-time popularity parameters of each flight, the method further includes:

[0024] Weights are assigned to each of the first and second coefficients using a time-weighted method.

[0025] Preferably, after sorting each flight according to its final popularity parameters to obtain a real-time popularity ranking, the method further includes:

[0026] Generate visual information based on real-time popularity rankings;

[0027] The information will be displayed visually.

[0028] Preferably, during the process of displaying the visualized information, if the access and attention data of a time segment within the current time period exceeds a preset threshold, the time segment is marked as "hot" and the "hot" mark is displayed.

[0029] Preferably, during the process of displaying the visual information, if the time between a flight's first entry into the top ten rankings and the flight's first entry into the top ten rankings is no more than a first preset time, then the time segment in which the flight first entered the top ten rankings is marked as "new" and the "new" mark is displayed.

[0030] This invention also proposes a system for real-time detection of popular flights, characterized by comprising:

[0031] The slice statistics module is used to slice and analyze the access and attention data of each flight according to the time dimension to obtain real-time popularity parameters.

[0032] The flight status parameter tuning module is used to obtain the flight status of each flight, which includes normal status and abnormal status; and to tune the parameters of flights in abnormal status to obtain the abnormal parameters of the flights in abnormal status.

[0033] The final popularity parameter calculation module is used to calculate the final popularity parameter of each flight based on the real-time popularity parameters and abnormal parameters of each flight.

[0034] The sorting module is used to sort each flight according to its final popularity parameters to obtain a real-time popularity ranking.

[0035] Preferably, the slice statistics module includes:

[0036] The slicing submodule is used to evenly divide the current time period into multiple time segments;

[0037] The data acquisition submodule is used to acquire access and attention data for each flight within the current time segment and all time segments before the current time segment, as well as the access and attention counts for each time segment corresponding to the current time segment and all time segments before the current time segment within n historical time periods; where n is an integer greater than or equal to 1.

[0038] The statistics submodule is used to calculate the first coefficient and the second coefficient of each flight in the current time period and in each time segment of the previous n-1 historical time periods, based on the flight access and attention data of each flight in the current time period and in all time segments before the current time segment, as well as the access and attention data of each time segment in the corresponding n historical time periods.

[0039] The first coefficient is the ratio of the access and attention data of a certain time segment to the access and attention data of the previous time segment within the same time period.

[0040] The second coefficient is the ratio of the access and attention data of a certain time segment to the access and attention data of the corresponding time segment in the previous historical time segment before the time segment.

[0041] It is used to perform weighted calculations on the first coefficient of each flight in the current time period and the first n-1 historical time periods, and the second coefficient of each flight in the current time period and the first n-1 historical time periods, to obtain the real-time popularity parameters of each flight.

[0042] The present invention also proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for real-time detection of hotspot flights as described in any of the preceding claims.

[0043] The present invention also proposes a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for real-time detection of hot-spot flights as described in any of the above.

[0044] This invention proposes a method, system, storage medium, and device for real-time detection of popular flights. It obtains real-time popularity parameters by slicing and analyzing access and attention data for each flight along a time dimension. Then, it adjusts parameters based on the flight status of each flight to obtain abnormal parameters for flights in an abnormal state. Finally, it calculates the final popularity parameters for each flight based on the real-time popularity parameters and abnormal parameters. The flights are then ranked according to their final popularity parameters to obtain a real-time popularity ranking. This invention can better identify special flights with unique or abnormal characteristics based on the real-time popularity ranking, for display or early warning purposes. Attached Figure Description

[0045] Figure 1 This is a flowchart illustrating a method for real-time detection of popular flights proposed in this invention. Detailed Implementation

[0046] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0047] Reference Figure 1 The present invention proposes a method for real-time detection of popular flights, comprising:

[0048] Access and attention data for each flight are sliced ​​and statistically analyzed according to the time dimension to obtain real-time popularity parameters;

[0049] Obtain the flight status of each flight; the flight status includes normal status and abnormal status.

[0050] Adjust the parameters of flights in abnormal status to obtain the abnormal parameters of the flights in abnormal status;

[0051] Based on the real-time popularity parameters and abnormal parameters of each flight, the final popularity parameters of each flight are calculated.

[0052] The flights are sorted according to their final popularity parameters to obtain a real-time popularity ranking.

[0053] This invention slices and analyzes access and attention data for each flight along a time dimension to obtain real-time popularity parameters. It then adjusts parameters based on the flight status of each flight to obtain abnormal parameters for flights in an abnormal state. Finally, based on the real-time popularity parameters and abnormal parameters, it calculates the final popularity parameters for each flight. Finally, it sorts the flights according to their final popularity parameters to obtain a real-time popularity ranking. This invention can better identify special or abnormal flights based on real-time popularity rankings, allowing for display or early warning purposes.

[0054] In this embodiment, abnormal states include: flight abnormal states such as circling, circling, diverting, diverting and then canceling, diverting and then arriving, returning, returning and then canceling, returning and then arriving, losing contact, crash, delay warning, and delays exceeding a second preset time. Each flight abnormal state has a corresponding abnormal parameter Q.

[0055] Specifically, the second preset time is 120 minutes.

[0056] It's important to know that the flight status of each flight is obtained from existing systems, such as FlightAware.

[0057] In this embodiment, the final heat parameter is the sum of the real-time heat parameter R and the anomaly parameter Q.

[0058] In this embodiment, the access and attention data for each flight are sliced ​​and statistically analyzed according to the time dimension, specifically including:

[0059] Divide the current time period evenly into multiple time segments;

[0060] Retrieve access and attention data for each flight within the current time segment and all time segments preceding the current time segment;

[0061] Get the number of visits and follows for each flight within n historical time periods, corresponding to the current time segment and all time segments before the current time segment; where n is an integer greater than or equal to 1.

[0062] It should be noted that "several" in this embodiment includes one or more.

[0063] In this embodiment, the real-time heat parameter R is obtained through analysis, specifically including:

[0064] Based on the flight access and attention data of each flight in the current time segment and all time segments before the current time segment, as well as the access and attention data of each time segment in the corresponding n historical time periods, calculate the first coefficient of each flight in the current time period and each time segment in the previous n-1 historical time periods, and the second coefficient of each flight in the current time period and each time segment in the previous n-1 historical time periods.

[0065] The first coefficient is the ratio of the access and attention data of a certain time segment to the access and attention data of the previous time segment within the same time period.

[0066] The second coefficient is the ratio of the access and attention data of a certain time segment to the access and attention data of the corresponding time segment in the previous historical time segment before the time segment.

[0067] The real-time popularity parameter R of each flight is obtained by weighting the first coefficient of each time segment in the current time period and the previous n-1 historical time periods and the second coefficient of each time segment in the current time period and the previous n-1 historical time periods.

[0068] In this embodiment, data from various time segments within the current time period can be linked with data from historical time periods to exclude high access and attention data caused by factors such as high passenger occupancy rates and a large number of passengers. This allows for better identification of special flights with unique or abnormal characteristics, i.e., popular flights, which can then be displayed or used for early warning.

[0069] In this embodiment, the first coefficient is q. j -i =m j -i / m j -(i+1) The second coefficient is P. j -i =m j -i / m j+1 -i ;

[0070] Where q represents the first coefficient, p represents the second coefficient, and m represents access and attention data;

[0071] j = 0, 1, 2, ..., n. When j = 0, it means that the time period is the current time period. When j = 1, 2, ..., n, it means that the time period is the j-th historical time period before the current time period.

[0072] i = 0, 1, 2, ..., k, where k is a positive integer greater than 2; when i = 0, it means that the time segment is the current time segment or the time segment corresponding to the current time segment; when i = 1, 2, ..., k, it means that the time segment is the i-th time segment before the current time segment or the time segment corresponding to the i-th time segment before the current time segment.

[0073] In a further embodiment, before weighting and calculating the first coefficient of each time segment in the current time period and the previous n-1 historical time periods for each flight, and the second coefficient of each time segment in the current time period and the previous n-1 historical time periods to obtain the real-time popularity parameter R of each flight, the method further includes:

[0074] Weights are assigned to each of the first and second coefficients using a time-weighted method.

[0075] This example uses time weighting to link the first and second coefficients to time, making the calculation results closer to reality.

[0076] It should be noted that in this embodiment, when performing weighted calculations on the first and second coefficients, the weights generally follow the principle that the closer to the current time, the higher the weight, and the greater the percentage change in value, the higher the weight, highlighting the focus on trend changes.

[0077] In one specific embodiment, if the current time period is the current day and the historical time period is the previous day, the current day is divided into 24 time segments according to hours, and the current time segment is the 24th hour.

[0078] Retrieve flight access and attention data for each flight within the current time period, for example, if the time segment within the current time period is m0. 0 m0 -1 m0 -2 m0 -3 ... m0 -23 ;

[0079] Retrieve access and engagement data for each flight within a previous historical time period, such as m1. 0 m1 -1 m1 -2 m1 -3 ... m1 -23 ;

[0080] Based on the flight access and attention data of each flight in the current time segment and all time segments before the current time segment, as well as the access and attention data of each time segment in the corresponding n historical time periods, calculate the first coefficient of each flight in the current time period and each time segment in the previous n-1 historical time periods, and the second coefficient of each flight in the current time period and each time segment in the previous n-1 historical time periods.

[0081] Specifically:

[0082] First coefficient, q0 0 =m0 0 / m0 -1 ,q0 -1 =m0 -1 / m0 -2 , ..., q0 -22 =m0 -22 / m0 -23 ;

[0083] q1 0 =m1 0 / m1 -1 , q1 -1 =m1 -1 / m1 -2 , ..., q1 -22 =m1 -22 / m1 -23 ;

[0084] The second coefficient, p0 0 =m0 0 / m1 0 p0 -1 =m0 -1 / m1 -1 p0 -2 =m0 -2 / m1 -2 ..., p0 -22 =m0 -22 / m1 -23 ;

[0085] p1 0 =m1 0 / m2 0 p1 -1 =m1 -1 / m2 -1 p1 -2 =m1 -2 / m2 -2 ..., p1 -22 =m1 -22 / m2 -23 ;

[0086] Next, regarding q0 0 , q0 -1 , ..., q0 -22 q1 0 q1 -1 , ..., q1 -22 and p0 0 p0 -1 p0 -2 ... p0 -22 and p1 0 p1 -1 p1 -2 ... p1 -22 Weighted calculations are performed to obtain the real-time popularity parameter R for each flight.

[0087] In this embodiment, after sorting each flight according to its final popularity parameters to obtain a real-time popularity ranking, the process further includes:

[0088] Generate visual information based on real-time popularity rankings;

[0089] The information will be displayed visually.

[0090] This is to provide information to enthusiasts on the consumer side, allowing them to discover interesting flights such as those that circle or make emergency landings. Moreover, in terms of early warning, these flights can be connected to the early warning systems of airports and platforms to provide timely warnings of potential hot topics.

[0091] In a further embodiment, during the process of displaying the visual information, if the access and attention data of a time segment within the current time period exceeds a preset threshold, the time segment is marked as "hot" and the "hot" mark is displayed.

[0092] In a further embodiment, during the process of displaying the visual information, if the time between a flight's first entry into the top ten rankings and the flight's first entry into the top ten rankings does not exceed a first preset time, then the time segment in which the flight first entered the top ten rankings is marked as "new" and the "new" mark is displayed.

[0093] Specifically, the first preset time is 120 minutes.

[0094] It's important to know that the visualization display supports manual backend intervention, allowing for manual operations such as fixing rankings, deleting rankings, and adding tags.

[0095] This invention also proposes a system for real-time detection of popular flights, comprising:

[0096] The slice statistics module is used to slice and analyze the access and attention data of each flight according to the time dimension to obtain real-time popularity parameters.

[0097] The flight status parameter tuning module is used to obtain the flight status of each flight, which includes normal status and abnormal status; and to tune the parameters of flights in abnormal status to obtain the abnormal parameters of the flights in abnormal status.

[0098] The final popularity parameter calculation module is used to calculate the final popularity parameter of each flight based on the real-time popularity parameters and abnormal parameters of each flight.

[0099] The sorting module is used to sort each flight according to its final popularity parameters to obtain a real-time popularity ranking.

[0100] In this embodiment, the slice statistics module includes:

[0101] The slicing submodule is used to evenly divide the current time period into multiple time segments;

[0102] The data acquisition submodule is used to acquire access and attention data for each flight within the current time segment and all time segments before the current time segment, as well as the access and attention counts for each time segment corresponding to the current time segment and all time segments before the current time segment within n historical time periods; where n is an integer greater than or equal to 1.

[0103] The statistics submodule is used to calculate the first coefficient and the second coefficient of each flight in the current time period and in each time segment of the previous n-1 historical time periods, based on the flight access and attention data of each flight in the current time period and in all time segments before the current time segment, as well as the access and attention data of each time segment in the corresponding n historical time periods.

[0104] The first coefficient is the ratio of the access and attention data of a certain time segment to the access and attention data of the previous time segment within the same time period.

[0105] The second coefficient is the ratio of the access and attention data of a certain time segment to the access and attention data of the corresponding time segment in the previous historical time segment before the time segment.

[0106] It is used to perform weighted calculations on the first coefficient of each flight in the current time period and the first n-1 historical time periods, and the second coefficient of each flight in the current time period and the first n-1 historical time periods, to obtain the real-time popularity parameter R of each flight.

[0107] The present invention also proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for real-time detection of hot flights as described in any of the above.

[0108] The present invention also proposes a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for real-time detection of hot-spot flights as described in any of the above.

[0109] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for real-time detection of popular flights, characterized in that, include: Divide the current time period evenly into multiple time segments; Retrieve access and attention data for each flight within the current time segment and all time segments preceding the current time segment, as well as the access and attention counts for each time segment corresponding to the current time segment and all time segments preceding the current time segment within n historical time periods; where n is an integer greater than or equal to 1; Based on the flight access and attention data for each flight within the current time segment and all time segments preceding it, as well as the access and attention data for each corresponding time segment within n historical time periods, calculate the first coefficient and the second coefficient for each time segment within the current time period and the preceding n-1 historical time periods for each flight. The first coefficient is the ratio of the access and attention data for a given time segment to the access and attention data for the previous time segment within the same time period. The second coefficient is the ratio of the access and attention data for a given time segment to the access and attention data for the corresponding time segment within the preceding historical time period before the time segment in which the given time segment is located. The first coefficient is q. j -i =m j -i / m j -(i+1) The second coefficient is p. j -i = m j -i / m j+1 -i : Where q represents the first coefficient, p represents the second coefficient, and m represents access and attention data; j = 0, 1, 2, ..., n, when j = 0, it means that the time period is the current time period, and when j = 1, 2, ..., n, it means that the time period is the j-th historical time period before the current time period; i = 0, 1, 2, ..., k, k is a positive integer greater than 2; when i = 0, it means that the time segment is the current time segment or the time segment corresponding to the current time segment; when i = 1, 2, ..., k, it means that the time segment is the i-th time segment before the current time segment or the time segment corresponding to the i-th time segment before the current time segment. The real-time popularity parameters of each flight are obtained by weighting the first coefficient of each time segment in the current time period and the previous n-1 historical time periods and the second coefficient of each time segment in the current time period and the previous n-1 historical time periods. Obtain the flight status of each flight; the flight status includes normal status and abnormal status; the abnormal status includes: flight abnormal status such as circling, circling, diverting, diverting and then canceling, diverting and then arriving, returning, returning and then canceling, returning and then arriving, lost contact, accident, delay warning, and delay exceeding the second preset time. Each flight abnormal status has corresponding abnormal parameters. Adjust the parameters of flights in abnormal status to obtain the abnormal parameters of the flights in abnormal status; The real-time popularity parameters and abnormal parameters of each flight are summed to obtain the final popularity parameters of each flight; the flights are sorted according to the final popularity parameters to obtain the real-time popularity ranking; a visual display is generated based on the real-time popularity ranking; and the visual display is then displayed. During the process of displaying visualized information, if the access and attention data of a time segment within the current time period exceeds a preset threshold, the time segment will be marked as "hot" and the "hot" mark will be displayed. If the time since a flight first entered the top ten of the ranking does not exceed a first preset time, the time segment in which the flight first entered the top ten of the ranking will be marked as "new" and the "new" mark will be displayed.

2. The method for real-time detection of popular flights according to claim 1, characterized in that, Before calculating the real-time popularity parameters of each flight by weighting the first coefficient of each time segment in the current time period and the previous n-1 historical time periods and the second coefficient of each time segment in the current time period and the previous n-1 historical time periods, the following steps are also included: Weights are assigned to each of the first and second coefficients using a time-weighted method.

3. A system for real-time detection of popular flights, used to implement the method for real-time detection of popular flights as described in claim 1 or 2, characterized in that, include: The slice statistics module is used to slice and analyze the access and attention data of each flight according to the time dimension to obtain real-time popularity parameters. The flight status parameter tuning module is used to obtain the flight status of each flight, which includes normal status and abnormal status; and to tune the parameters of flights in abnormal status to obtain the abnormal parameters of the flights in abnormal status. The final popularity parameter calculation module is used to calculate the final popularity parameter of each flight based on the real-time popularity parameters and abnormal parameters of each flight. The sorting module is used to sort each flight according to its final popularity parameters to obtain a real-time popularity ranking.

4. The system for real-time detection of popular flights according to claim 3, characterized in that, The slice statistics module includes: The slicing submodule is used to evenly divide the current time period into multiple time segments; The data acquisition submodule is used to acquire access and attention data for each flight within the current time segment and all time segments before the current time segment, as well as the access and attention counts for each time segment corresponding to the current time segment and all time segments before the current time segment within n historical time periods; where n is an integer greater than or equal to 1. The statistics submodule is used to calculate the first coefficient and the second coefficient of each flight in the current time period and in each time segment of the previous n-1 historical time periods, based on the flight access and attention data of each flight in the current time period and in all time segments before the current time segment, as well as the access and attention data of each time segment in the corresponding n historical time periods. The first coefficient is the ratio of the access and attention data of a certain time segment to the access and attention data of the previous time segment within the same time period; the second coefficient is the ratio of the access and attention data of a certain time segment to the access and attention data of the corresponding time segment in the previous historical time period before the time segment. It is used to perform weighted calculations on the first coefficient of each flight in the current time period and the first n-1 historical time periods, and the second coefficient of each flight in the current time period and the first n-1 historical time periods, to obtain the real-time popularity parameters of each flight.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the program to implement the method for real-time detection of hotspot flights as described in any one of claims 1 to 2.

6. A readable storage medium having a computer program stored thereon, characterized in that, When a computer program is executed by a processor, it implements the method for real-time detection of hotspot flights as described in any one of claims 1 to 2.

Images