Intelligent processing method of aircraft communication data based on air-ground integrated network

Abstract

The present invention relates to the field of data processing technology, and in particular to an intelligent processing method for aircraft communication data based on an air-ground-ground integrated network, comprising: respectively acquiring collected data of each aircraft, respectively filtering out abnormal values ​​in the collected data of the corresponding collection terminal based on corresponding preset screening thresholds, respectively compressing the collected data of each collection terminal after filtering out the abnormal values, matching the corresponding decompression code based on the additional identification code of the compressed information, and performing decompression processing; sequentially acquiring label information of the data set after each compressed information is decompressed; classifying and processing each data based on the identified label information; determining whether a large amount of stored data is qualified, and determining a processing method for a server when the data is determined to be abnormal, thereby improving the reliability of the data and further improving the processing efficiency of the data.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an intelligent processing method for aircraft communication data based on an air-ground-integrated network. Background Art

[0002] The integrated air-ground-space information network is composed of a constellation of satellites of different types and performance in different orbits, covering the entire globe. It densely connects users, aircraft and various communication platforms on the ground, at sea, in the air and in deep space through inter-satellite and satellite-to-ground links. It uses IP as the information carrier, adopts intelligent high-speed on-board processing, switching and routing technology, and is oriented towards optical and infrared multi-spectral information. It follows the principle of maximizing the effective comprehensive utilization of information resources, and is an integrated high-speed, broadband and large-capacity information network that accurately acquires, quickly processes and efficiently transmits information. That is, it is an integrated space-based, air-based and land-based network.

[0003] In order to efficiently acquire massive data, it is necessary to effectively identify and classify massive data.

[0004] Chinese Patent Publication No.: CN110892671B, discloses an aircraft, a data processing system and a data processing method for an aircraft, wherein a data acquisition device is used to generate a synchronization pulse signal when target data is acquired, and send the synchronization pulse signal and the target data to the data processing device; the data processing device is used to receive the synchronization pulse signal sent by the data acquisition device, and determine the target time of receiving the synchronization pulse signal; the data processing device is also used to determine the target data sent by the data acquisition device from the data received by the data interface, and use the target time as the receiving time of the target data; it can be seen that the above technical solution has the following problems: it is impossible to process the server storing the data in time when it is determined that the stored data is abnormal, which affects the reliability of the data and further affects the processing efficiency of the data. Summary of the invention

[0005] To this end, the present invention provides an intelligent processing method for aircraft communication data based on an integrated air-ground-space network, so as to overcome the problem in the prior art that when the stored data is determined to be abnormal, the server storing the data cannot be processed in time, which affects the reliability of the data and further affects the efficiency of data processing.

[0006] To achieve the above object, the present invention provides an intelligent processing method for aircraft communication data based on an air-ground integrated network, comprising:

[0007] S1, each collection terminal respectively obtains the collection data of each aircraft, and a number of processors respectively filter out abnormal values ​​in the collection data of the corresponding collection terminal based on the corresponding preset screening threshold value, and the compression module respectively compresses the collection data of each collection terminal after the abnormal values ​​are filtered out, and adds an identification code to the compressed information after compression based on the collection terminal;

[0008] S2, the primary classification module classifies each compressed information obtained based on the additional identification code, and the decompression module matches the corresponding decompression code based on the additional identification code of the compressed information to perform decompression processing;

[0009] S3, the recognition module sequentially obtains label information of each data set after decompression of the compressed information, and the label information includes an address label, a data category label, and a time node label;

[0010] S4, the secondary classification module classifies each data based on the identified label information, and transmits the classified data to the server storing the corresponding data in sequence, and the statistical module counts the data growth of each server in sequence;

[0011] S5, when the operation time of the acquisition module reaches the preset operation cycle, the analysis module determines the data growth parameter of each server one by one based on the data growth amount of each server, and determines whether the data stored in the corresponding server is qualified based on the data growth parameter, including obtaining the data growth parameter, obtaining the data growth amount stored in a single server within the preset operation cycle, and obtaining the storage data amount;

[0012] Calculate the average value of each storage data volume in each preset operation cycle in history to obtain the storage average parameter;

[0013] Solve the ratio of the amount of stored data in the current preset operation cycle to the average storage parameter to obtain the data growth parameter;

[0014] If the data growth parameter is less than or equal to the first preset data growth parameter, the data stored in the single server is determined to be abnormal, and a processing method for the single server is determined based on the abnormal data parameter, wherein the processing method is to increase the number of processors to a corresponding value, adjust each preset screening threshold to a corresponding value, determine the processing method for the server based on the abnormal data parameter, or divide the categories of data stored by the single server in the current preset operating cycle based on the data growth difference, and further determine the processing method for each server based on the proportion of the categories of data stored by each server in the current preset operating cycle;

[0015] If the data growth parameter is less than or equal to the second preset data growth parameter and greater than the first preset data growth parameter, the data stored in the single server is determined to be qualified, and the single server is controlled to continue to run using the current operating parameters and determine whether the data stored in the next server is qualified until the determination of all servers is completed;

[0016] If the data growth parameter is greater than the second preset data growth parameter, the data stored in the single server is determined to be abnormal, and the data stored in the single server during the current preset operating cycle is classified based on the abnormal growth parameter, and the processing method for each server is determined based on the proportion of the data categories stored in each server during the current preset operating cycle.

[0017] Furthermore, the analysis module classifies the data stored in a single server in a current preset operation cycle based on the abnormal growth parameter, including:

[0018] Determine the abnormal growth parameter, obtain the data stored in a single server within a preset operation cycle, determine the abnormal data in each data, calculate the proportion of the number of bytes of the abnormal data to the number of bytes of the total data stored within the preset operation cycle, and obtain the abnormal growth parameter;

[0019] If the abnormal growth parameter is less than or equal to the first preset abnormal growth parameter, the category of data stored by the single server in the current preset operation cycle is classified into a category of data sets;

[0020] If the abnormal growth parameter is less than or equal to the second preset abnormal growth parameter and greater than the first preset abnormal growth parameter, the data stored in the single server in the current preset operation cycle is classified based on the time distribution parameter;

[0021] If the abnormal growth parameter is greater than the second preset abnormal growth parameter, the category of data stored in the single server during the current preset operation cycle is divided into two categories of data sets.

[0022] Furthermore, the analysis module is used to classify the data stored by a single server in the current preset operation cycle based on the time distribution parameter, including:

[0023] Determine the time distribution parameter, determine the time nodes for obtaining each abnormal data within a preset operation cycle for a single server in turn, obtain the time distance between each time node in turn, solve the variance of each time distance, and obtain the time distribution parameter;

[0024] If the time distribution parameter is less than or equal to the preset time distribution parameter, the category of data stored in the single server in the current preset operation cycle is divided into two categories of data sets;

[0025] If the time distribution parameter is greater than the preset time distribution parameter, the category of data stored in the single server in the current preset operation cycle is divided into a category of data sets.

[0026] Furthermore, the analysis module is used to determine a processing method for a single server based on the abnormal data parameters, including:

[0027] Determine the abnormal data parameter, obtain the ratio of the total number of bytes of the abnormal data of each server to the total number of bytes of each collected data output by the cleaning module, and obtain the abnormal data parameter;

[0028] If the abnormal data parameter is less than or equal to the preset abnormal data parameter, the data stored in the single server in the current preset operation cycle is classified based on the data growth difference;

[0029] If the abnormal data parameter is greater than the preset abnormal data parameter, each preset screening threshold is adjusted to a corresponding value based on the abnormal data parameter.

[0030] Furthermore, the analysis module is used to classify the data stored in a single server in a current preset operation cycle based on the data growth difference, including:

[0031] Determine the data growth difference, obtain the data acquisition amount of a single server at each detection time node within a preset operation cycle, solve the variance of each data acquisition amount, and obtain the data growth difference;

[0032] If the data growth difference is less than or equal to the preset data growth difference, the data stored in the single server in the current preset operation cycle is divided into three types of data sets;

[0033] If the data growth difference is greater than the preset data growth difference, the data stored in the single server during the current preset operation cycle is divided into four categories of data sets.

[0034] Furthermore, the analysis module is used to adjust each preset screening threshold to a corresponding value based on the abnormal data parameter, wherein:

[0035] The reduction range of each preset screening threshold determined based on the abnormal data parameter is proportional to the abnormal data parameter.

[0036] Furthermore, the analysis module is used to determine a processing method for each server based on the proportion of the category of data stored in each server in the current preset operation cycle, including:

[0037] Calculate the proportion of the number of servers in one category to the total number of servers to determine the proportion of one category;

[0038] Calculate the ratio of the number of Class II servers to the total number of servers to determine the proportion of Class II.

[0039] Calculate the proportion of the number of the three types of servers to the total number of servers to determine the proportion of the three types;

[0040] Calculate the ratio of the number of four types of servers to the total number of servers to determine the proportion of the four types;

[0041] Get the maximum value of each category proportion;

[0042] If the maximum value is the proportion of one category or three categories, the processing method for each server is based on the proportion ratio of the proportion of one category to the proportion of three categories;

[0043] If the maximum value is the proportion of the second category, the match of the optimized decompression code is determined;

[0044] If the maximum value is the proportion of the four categories, the number of processors is increased to a corresponding value based on the proportion of the four categories.

[0045] Furthermore, the analysis module is used to process each server based on the ratio of the first category proportion to the third category proportion, including:

[0046] If the proportion ratio is within the preset proportion range, it is determined to optimize the secondary classification module;

[0047] If the proportion ratio is outside the preset proportion range, each preset screening threshold is adjusted to a corresponding value based on the abnormal data parameter.

[0048] Further, the analysis module is used to increase the number of processors to a corresponding value based on the four types of proportions, wherein:

[0049] The increase in the number of processors determined based on the proportions of the four categories is proportional to the proportions of the four categories.

[0050] Compared with the prior art, the beneficial effect of the present invention is that it determines whether a large amount of stored data is qualified, and when the data is determined to be abnormal, determines the processing method for the server, thereby improving the reliability of the data and further improving the processing efficiency of the data.

[0051] Furthermore, the massive data are centrally cleaned and classified, and the data growth parameters of each server are calculated one by one to determine whether the data stored in each server is qualified. The data growth parameter represents the data change of each server within a preset time interval. When the data growth parameter is greater than the second preset data growth parameter, the data of a single server increases dramatically. In this case, the newly added data of the server within the period is analyzed to determine the abnormal growth parameter. The abnormal growth parameter represents the proportion of abnormal data in a single server. When the abnormal growth parameter is less than or equal to the first preset abnormal growth parameter, the proportion of abnormal data is low. At this time, since the cleaning of the data does not meet the standards, redundant abnormal data exists due to unqualified cleaning; when the abnormal growth parameter is greater than the second preset abnormal growth parameter, the proportion of abnormal data is large. In this case, too much invalid data appears due to problems with decoding; When the constant growth parameter is less than or equal to the second preset abnormal growth parameter and greater than the first preset abnormal growth parameter, the categories of the stored data are determined in combination with the time distribution parameter; the time distribution parameter characterizes the distribution of abnormal data in the time dimension. When the time distribution parameter is less than or equal to the preset time distribution parameter, the distribution is concentrated. In this case, due to decoding problems, a batch of concentrated abnormal data appears; when the time distribution parameter is greater than the preset time distribution parameter, the distribution is dispersed. In this case, due to abnormal operating parameters of the cleaning module, some abnormal data will appear every once in a while. The stored data is analyzed and the categories of data stored by a single server in the current preset operating cycle are divided to comprehensively consider the proportion of each category of each server, and the overall data processing process is adjusted to improve the reliability of the stored data, further improving the efficiency of classification and processing of massive data.

[0052] Furthermore, when the data growth parameter is less than or equal to the first preset data growth parameter, the data growth amount in a single server is too low, and further determination is made for the abnormal situation. At this time, the abnormal data parameter is calculated to determine the processing method for the single server. The abnormal data parameter represents the ratio of the total amount of abnormal data of each server to the total amount of data obtained by each server. When the abnormal data parameter is less than or equal to the preset abnormal data parameter, the abnormal data is relatively low overall. In this case, the acquired data is relatively low due to problems with the server itself. At this time, the data stored in a single server in the current preset operating cycle is divided into categories according to the data growth difference, so as to comprehensively consider the proportion of each server category and adjust the entire data processing process as a whole; when the abnormal data parameter is greater than the preset abnormal data parameter, in actual circumstances, the corresponding server has low valid data in this cycle, but high abnormal data. At this time, the data cleaning standard is adjusted to ensure the reliability of the data, improve the monitoring accuracy of the data, and further improve the data processing efficiency.

[0053] Furthermore, the categories of data stored in a single server during the current preset operating cycle are divided based on the data growth difference. The data growth difference characterizes the difference in the amount of data increase at each detection node during the preset operating cycle. When the data growth difference is less than or equal to the preset data growth difference, the amount of data received during the preset operating cycle is very small; when the data growth difference is greater than the preset data growth difference, there is fluctuation in data reception in this case; after completing the marking of each server, the processing method for each server is comprehensively determined based on the proportion of the categories of data stored in each server during the current preset operating cycle. When the maximum value is the proportion of the second category, there is a problem in the decoding process in this case, and the matching of the decompression code is optimized; when the maximum value is the proportion of the fourth category, the data processing environment load is too high in this case, and an increase in the processor is required to ensure that the processing method for each server is completed. To ensure stable data processing; when the maximum value is the proportion of one category or the proportion of three categories, the proportion of one category data set and the three category data set is the largest. In this case, a large amount of abnormal data appears in each server, and the proportion ratio is determined at this time; when the proportion ratio is within the preset proportion interval, the proportion ratio is close to 1 in this case. At this time, due to the deviation in the classification of each data by the secondary classification module, there are too many abnormal data, so the data classification process is optimized; when the proportion ratio is outside the preset proportion interval, the proportion ratio is not close to 1 in this case. At this time, due to the abnormality in the data cleaning, there are too many abnormal data, and the data cleaning standard is re-determined at this time; according to the specific abnormal situation of each server, the corresponding processing method is selected for processing, which effectively improves the stability of data processing and further improves the classification processing efficiency of massive data. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a flowchart of the steps of the method for intelligently processing aircraft communication data based on an air-ground integrated network according to an embodiment of the present invention;

[0055] Figure 2 This is a logical decision diagram for an analysis module in an embodiment of the present invention to determine whether data stored in a single server is qualified based on data growth parameters. DETAILED DESCRIPTION

[0056] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0057] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0058] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0059] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0060] See also Figure 1 and Figure 2 As shown, they are respectively a flow chart of the steps of the method for intelligently processing aircraft communication data based on an air-ground-integrated network according to an embodiment of the present invention, and a logic determination diagram of the analysis module determining whether the data stored in a single server is qualified based on the data growth parameter; an intelligent method for intelligently processing aircraft communication data based on an air-ground-integrated network according to an embodiment of the present invention, comprising:

[0061] S1, each collection terminal respectively obtains the collection data of each aircraft, and a number of processors respectively filter out abnormal values ​​in the collection data of the corresponding collection terminal based on the corresponding preset screening threshold value, and the compression module respectively compresses the collection data of each collection terminal after the abnormal values ​​are filtered out, and adds an identification code to the compressed information after compression based on the collection terminal;

[0062] S2, the primary classification module classifies each compressed information obtained based on the additional identification code, and the decompression module matches the corresponding decompression code based on the additional identification code of the compressed information to perform decompression processing;

[0063] S3, the recognition module sequentially obtains label information of each data set after decompression of the compressed information, and the label information includes an address label, a data category label, and a time node label;

[0064] S4, the secondary classification module classifies each data based on the identified label information, and transmits the classified data to the server storing the corresponding data in sequence, and the statistical module counts the data growth of each server in sequence;

[0065] S5, when the running time of the acquisition module reaches the preset running cycle, the analysis module determines the data growth parameter of each server one by one based on the data growth amount of each server, and determines whether the data stored in the corresponding server is qualified based on the data growth parameter, including:

[0066] Determine whether the data stored in a single server is qualified, control the single server to continue to operate using the current operating parameters, and determine whether the data stored in the next server is qualified until all servers are determined;

[0067] Or, determine that the data stored in a single server is abnormal, and determine a processing method for the single server based on the abnormal data parameters, where the processing method is to increase the number of processors to a corresponding value, or adjust each preset screening threshold to a corresponding value.

[0068] Specifically, the collection module includes a number of collection terminals for acquiring the collection data of each aircraft;

[0069] A cleaning module, which is connected to the acquisition module and includes a plurality of processors for respectively filtering out abnormal values ​​in the collected data of the corresponding acquisition terminal based on corresponding preset screening thresholds;

[0070] A compression module, which is connected to the cleaning module, and is used to compress the collected data of each collection terminal after the abnormal values ​​are screened out, and add an identification code to the compressed information after compression based on the collection terminal;

[0071] A primary classification module, connected to the compression module, for classifying each compressed information obtained based on the additional identification code;

[0072] A decompression module, connected to the primary classification module, for matching the corresponding decompression code based on the additional identification code of the compressed information to perform decompression processing;

[0073] An identification module, which is connected to the decompression module and is used to sequentially obtain label information of each data set after decompression of the compressed information, wherein the label information includes an address label, a data category label and a time node label;

[0074] A secondary classification module, which is connected to the identification module, is used to classify each data based on the identified tag information, and sequentially transmit the classified data to the server storing the corresponding data;

[0075] The statistics module is used to count the data growth of each server in turn;

[0076] An analysis module, which is respectively connected to the cleaning module, the compression module, the primary classification module, the decompression module, the secondary classification module and the statistical module, and is used to determine a data growth parameter based on the data growth amount, determine whether the data stored in a single server is qualified based on the data growth parameter, and when it is determined that the data stored in a single server is abnormal, determine a processing method for the single server based on the abnormal data parameter, wherein the processing method is to increase the number of processors to a corresponding value, or adjust each preset screening threshold to a corresponding value.

[0077] Specifically, it is determined whether a large amount of stored data is qualified. When the data is determined to be abnormal, the processing method for the server is determined, which improves the reliability of the data and further improves the efficiency of data processing.

[0078] Specifically, there is no limitation on the determination of the preset screening threshold of the cleaning module. It can be based on the statistical analysis of historical collected data, collect a large amount of normal aircraft collection data, analyze the statistical characteristics of the distribution, fluctuation range, mean, and standard deviation of each collected data, and make a comprehensive determination. It can be understood that abnormal data deviates from the statistical characteristics of a large amount of normal collected data, which will not be elaborated here.

[0079] Specifically, in S5, the analysis module determines whether the data stored in a single server is qualified based on the data growth parameter, including:

[0080] Obtaining a data growth parameter, obtaining the data growth amount stored in a single server within a preset operation cycle, and obtaining the amount of stored data;

[0081] Calculate the average value of each storage data volume in each preset operation cycle in history to obtain the storage average parameter;

[0082] Solve the ratio of the amount of stored data in the current preset operation cycle to the average storage parameter to obtain the data growth parameter;

[0083] If the data growth parameter is less than or equal to the first preset data growth parameter, the data stored in the single server is determined to be abnormal, and a processing method for the single server is determined based on the abnormal data parameter, wherein the processing method is to increase the number of processors to a corresponding value, adjust each preset screening threshold to a corresponding value, determine the processing method for the server based on the abnormal data parameter, or divide the categories of data stored by the single server in the current preset operating cycle based on the data growth difference, and further determine the processing method for each server based on the proportion of the categories of data stored by each server in the current preset operating cycle;

[0084] If the data growth parameter is less than or equal to the second preset data growth parameter and greater than the first preset data growth parameter, the data stored in the single server is determined to be qualified, and the single server is controlled to continue to run using the current operating parameters;

[0085] If the data growth parameter is greater than the second preset data growth parameter, the data stored in the single server is determined to be abnormal, and the data stored in the single server during the current preset operating cycle is classified based on the abnormal growth parameter, and the processing method for each server is determined based on the proportion of the data categories stored in each server during the current preset operating cycle.

[0086] Specifically, the first preset data growth parameter is selected within the interval [0.67, 0.87], and the second preset data growth parameter is selected within the interval [1.25, 1.72].

[0087] Specifically, the analysis module divides the categories of data stored in a single server in the current preset operation cycle based on the abnormal growth parameter, including:

[0088] Determine the abnormal growth parameter, obtain the data stored in a single server within a preset operation cycle, determine the abnormal data in each data, calculate the proportion of the number of bytes of the abnormal data to the number of bytes of the total data stored within the preset operation cycle, and obtain the abnormal growth parameter;

[0089] If the abnormal growth parameter is less than or equal to the first preset abnormal growth parameter, the category of data stored by the single server in the current preset operation cycle is classified into a category of data sets;

[0090] If the abnormal growth parameter is less than or equal to the second preset abnormal growth parameter and greater than the first preset abnormal growth parameter, the data stored in the single server in the current preset operation cycle is classified based on the time distribution parameter;

[0091] If the abnormal growth parameter is greater than the second preset abnormal growth parameter, the category of data stored in the single server during the current preset operation cycle is divided into two categories of data sets.

[0092] Specifically, the first preset abnormal growth parameter is selected within the interval [0.07, 0.22], and the second preset abnormal growth parameter is selected within the interval [0.38, 0.42].

[0093] Specifically, there is no limitation on the specific method of determining abnormal data. A clustering algorithm can be used to group data, and data points far away from the main clusters are determined as abnormal data. It can be understood that the abnormal data can be filtered, which will not be elaborated here.

[0094] Specifically, the analysis module is used to classify the data stored by a single server in the current preset operation cycle based on the time distribution parameter, including:

[0095] Determine the time distribution parameter, determine the time nodes for obtaining each abnormal data within a preset operation cycle for a single server in turn, obtain the time distance between each time node in turn, solve the variance of each time distance, and obtain the time distribution parameter;

[0096] If the time distribution parameter is less than or equal to the preset time distribution parameter, the category of data stored in the single server in the current preset operation cycle is divided into two categories of data sets;

[0097] If the time distribution parameter is greater than the preset time distribution parameter, the category of data stored in the single server in the current preset operation cycle is divided into a category of data sets.

[0098] Specifically, massive data are cleaned and classified in a centralized manner, and the data growth parameters of each server are calculated one by one to determine whether the data stored in each server is qualified. The data growth parameter represents the data change of each server within a preset time interval. When the data growth parameter is greater than the second preset data growth parameter, the data of a single server increases dramatically. In this case, the new data added to the server within the period is analyzed to determine the abnormal growth parameter. The abnormal growth parameter represents the proportion of abnormal data in a single server. When the abnormal growth parameter is less than or equal to the first preset abnormal growth parameter, the proportion of abnormal data is low. At this time, since the data cleaning does not meet the standards, redundant abnormal data exists due to unqualified cleaning; when the abnormal growth parameter is greater than the second preset abnormal growth parameter, the proportion of abnormal data is large. In this case, too much invalid data appears due to problems with decoding; When the constant growth parameter is less than or equal to the second preset abnormal growth parameter and greater than the first preset abnormal growth parameter, the categories of the stored data are determined in combination with the time distribution parameter; the time distribution parameter characterizes the distribution of abnormal data in the time dimension. When the time distribution parameter is less than or equal to the preset time distribution parameter, the distribution is concentrated. In this case, due to decoding problems, a batch of concentrated abnormal data appears; when the time distribution parameter is greater than the preset time distribution parameter, the distribution is dispersed. In this case, due to abnormal operating parameters of the cleaning module, some abnormal data will appear every once in a while. The stored data is analyzed and the categories of data stored by a single server in the current preset operating cycle are divided to comprehensively consider the proportion of each category of each server, and the overall data processing process is adjusted to improve the reliability of the stored data, further improving the efficiency of classification and processing of massive data.

[0099] Specifically, the preset time distribution parameter is selected within the interval [0.04T02, 0.16T02], and T0 is the duration of the preset operation cycle.

[0100] Specifically, the analysis module is used to determine a processing method for a single server based on abnormal data parameters, including:

[0101] Determine the abnormal data parameter, obtain the ratio of the total number of bytes of the abnormal data of each server to the total number of bytes of each collected data output by the cleaning module, and obtain the abnormal data parameter;

[0102] If the abnormal data parameter is less than or equal to the preset abnormal data parameter, the data stored in the single server in the current preset operation cycle is classified based on the data growth difference;

[0103] If the abnormal data parameter is greater than the preset abnormal data parameter, each preset screening threshold is adjusted to a corresponding value based on the abnormal data parameter.

[0104] Specifically, the preset abnormal data parameter S0 is selected within the interval [0.08, 0.17].

[0105] Specifically, when the data growth parameter is less than or equal to the first preset data growth parameter, the data growth amount in a single server is too low, and further determination is made for the abnormal situation. At this time, the abnormal data parameter is calculated to determine the processing method for the single server. The abnormal data parameter represents the ratio of the total amount of abnormal data of each server to the total amount of data obtained by each server. When the abnormal data parameter is less than or equal to the preset abnormal data parameter, the abnormal data is relatively low overall. In this case, the acquired data is relatively low due to problems with the server itself. At this time, the data stored in a single server in the current preset operating cycle is divided into categories according to the data growth difference, so as to comprehensively consider the proportion of each server category and adjust the entire data processing process as a whole; when the abnormal data parameter is greater than the preset abnormal data parameter, in actual situation, the corresponding server has low valid data in this cycle, but high abnormal data. At this time, the data cleaning standard is adjusted to ensure the reliability of the data, improve the monitoring accuracy of the data, and further improve the data processing efficiency.

[0106] Specifically, the analysis module is used to classify the data stored in a single server in the current preset operation cycle based on the data growth difference, including:

[0107] Determine the data growth difference, obtain the data acquisition amount of a single server at each detection time node within a preset operation cycle, solve the variance of each data acquisition amount, and obtain the data growth difference;

[0108] If the data growth difference is less than or equal to the preset data growth difference, the data stored in the single server in the current preset operation cycle is divided into three types of data sets;

[0109] If the data growth difference is greater than the preset data growth difference, the data stored in the single server during the current preset operation cycle is divided into four categories of data sets.

[0110] Specifically, the preset data growth difference is selected within the interval [1.21Q0, 1.56Q0], and Q0 is the average value of each data growth difference obtained by each server in each historical operation cycle.

[0111] Specifically, the analysis module is used to adjust each preset screening threshold to a corresponding value based on the abnormal data parameter, wherein:

[0112] The reduction range of each preset screening threshold determined based on the abnormal data parameter is proportional to the abnormal data parameter.

[0113] In this embodiment, optionally,

[0114] Comparing the abnormal data parameter with a first preset abnormal comparison threshold and a second preset abnormal comparison threshold;

[0115] If the abnormal data parameter is less than or equal to the first preset abnormal comparison threshold, each preset screening threshold is adjusted to 0.93 times the initial preset screening threshold;

[0116] If the abnormal data parameter is less than or equal to the second preset abnormal comparison threshold and greater than the first preset abnormal comparison threshold, each preset screening threshold is adjusted to 0.84 times the initial preset screening threshold;

[0117] If the abnormal data parameter is greater than the second preset abnormal comparison threshold, each preset screening threshold is adjusted to 0.76 times the initial preset screening threshold;

[0118] The first preset abnormality comparison threshold is 1.17S0, and the second preset abnormality comparison threshold is 1.32S0.

[0119] Specifically, the analysis module is used to determine the processing method for each server based on the proportion of the category of data stored in each server in the current preset operation cycle, including:

[0120] Calculate the proportion of the number of servers in one category to the total number of servers to determine the proportion of one category;

[0121] Calculate the ratio of the number of Class II servers to the total number of servers to determine the proportion of Class II.

[0122] Calculate the proportion of the number of the three types of servers to the total number of servers to determine the proportion of the three types;

[0123] Calculate the ratio of the number of four types of servers to the total number of servers to determine the proportion of the four types;

[0124] Get the maximum value of each category proportion;

[0125] If the maximum value is the proportion of one category or three categories, the processing method for each server is based on the proportion ratio of the proportion of one category to the proportion of three categories;

[0126] If the maximum value is the proportion of the second category, the match of the optimized decompression code is determined;

[0127] If the maximum value is the proportion of the four categories, the number of processors is increased to a corresponding value based on the proportion of the four categories.

[0128] Specifically, the categories of data stored in a single server during the current preset operating cycle are divided based on the data growth difference. The data growth difference characterizes the difference in the amount of data increase at each detection node during the preset operating cycle. When the data growth difference is less than or equal to the preset data growth difference, the amount of data received during the preset operating cycle is very small; when the data growth difference is greater than the preset data growth difference, there is fluctuation in data reception in this case; after completing the marking of each server, the processing method for each server is comprehensively determined based on the proportion of the categories of data stored in each server during the current preset operating cycle. When the maximum value is the proportion of the second category, there is a problem in the decoding process in this case, and the matching of the decompression code is optimized; when the maximum value is the proportion of the fourth category, the data processing environment load is too high in this case, and an increase in the processor is required to ensure that the processing method for each server is completed. To ensure stable data processing; when the maximum value is the proportion of one category or the proportion of three categories, the proportion of one category data set and the three category data set is the largest. In this case, a large amount of abnormal data appears in each server, and the proportion ratio is determined at this time; when the proportion ratio is within the preset proportion interval, the proportion ratio is close to 1 in this case. At this time, due to the deviation in the classification of each data by the secondary classification module, there are too many abnormal data, so the data classification process is optimized; when the proportion ratio is outside the preset proportion interval, the proportion ratio is not close to 1 in this case. At this time, due to the abnormality in the data cleaning, there are too many abnormal data, and the data cleaning standard is re-determined at this time; according to the specific abnormal situation of each server, the corresponding processing method is selected for processing, which effectively improves the stability of data processing and further improves the classification processing efficiency of massive data.

[0129] Specifically, the matching of the decompression code is optimized, each of the acquired second-category data sets is determined as a data sample, the data sample is added to the training data set, and the decompression code matching model is retrained to update the matching standard.

[0130] Specifically, the analysis module is used to process each server based on the ratio of the first category proportion to the third category proportion, including:

[0131] If the proportion ratio is within the preset proportion range, it is determined to optimize the secondary classification module;

[0132] If the proportion ratio is outside the preset proportion range, each preset screening threshold is adjusted to a corresponding value based on the abnormal data parameter.

[0133] Specifically, the preset proportion interval is [0.94, 1.16].

[0134] Specifically, the secondary classification module is optimized, the label information of the first-category data set and the second-category data set is re-acquired, and the ambiguous label information and fuzzy label information in each label information are annotated and updated to provide a clearer classification basis.

[0135] Specifically, the analysis module is used to increase the number of processors to corresponding values ​​based on four types of proportions, wherein:

[0136] The increase in the number of processors determined based on the proportions of the four categories is proportional to the proportions of the four categories.

[0137] In this embodiment, optionally,

[0138] Compare the proportions of the four categories with a first preset proportion comparison threshold and a second preset proportion comparison threshold;

[0139] If the proportion of the four categories is less than or equal to the first preset proportion comparison threshold, the number of processors is adjusted to 1.11 times the initial number;

[0140] If the proportion of the four categories is less than or equal to the second preset proportion comparison threshold and greater than the first preset proportion comparison threshold, the number of processors is adjusted to 1.21 times the initial number;

[0141] If the proportion of the four categories is greater than the second preset proportion comparison threshold, the number of processors is adjusted to 1.28 times the initial number;

[0142] The first preset ratio comparison threshold is 1.23Z0, and the second preset ratio comparison threshold is 1.44Z0, where Z0 is the average value of each category ratio.

[0143] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0144] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for intelligently processing aircraft communication data based on an air-ground integrated network, characterized in that: include: S1, each collection terminal respectively obtains the collection data of each aircraft, and a number of processors respectively filter out abnormal values ​​in the collection data of the corresponding collection terminal based on the corresponding preset screening threshold value, and the compression module respectively compresses the collection data of each collection terminal after the abnormal values ​​are filtered out, and adds an identification code to the compressed information after compression based on the collection terminal; S2, the primary classification module classifies each compressed information obtained based on the additional identification code, and the decompression module matches the corresponding decompression code based on the additional identification code of the compressed information to perform decompression processing; S3, the recognition module sequentially obtains label information of each data set after decompression of the compressed information, and the label information includes an address label, a data category label, and a time node label; S4, the secondary classification module classifies each data based on the identified label information, and transmits the classified data to the server storing the corresponding data in sequence, and the statistical module counts the data growth of each server in sequence; S5, when the operation time of the acquisition module reaches the preset operation cycle, the analysis module determines the data growth parameter of each server one by one based on the data growth amount of each server, and determines whether the data stored in the corresponding server is qualified based on the data growth parameter, including obtaining the data growth parameter, obtaining the data growth amount stored in a single server within the preset operation cycle, and obtaining the storage data amount; Calculate the average value of each storage data volume in each preset operation cycle in history to obtain the storage average parameter; Solve the ratio of the amount of stored data in the current preset operation cycle to the average storage parameter to obtain the data growth parameter; If the data growth parameter is less than or equal to the first preset data growth parameter, the data stored in the single server is determined to be abnormal, and a processing method for the single server is determined based on the abnormal data parameter, wherein the processing method is to increase the number of processors to a corresponding value, adjust each preset screening threshold to a corresponding value, determine the processing method for the server based on the abnormal data parameter, or divide the categories of data stored by the single server in the current preset operating cycle based on the data growth difference, and further determine the processing method for each server based on the proportion of the categories of data stored by each server in the current preset operating cycle; If the data growth parameter is less than or equal to the second preset data growth parameter and greater than the first preset data growth parameter, the data stored in the single server is determined to be qualified, and the single server is controlled to continue to run using the current operating parameters and determine whether the data stored in the next server is qualified until the determination of all servers is completed; If the data growth parameter is greater than the second preset data growth parameter, the data stored in the single server is determined to be abnormal, and the data stored in the single server during the current preset operating cycle is classified based on the abnormal growth parameter, and the processing method for each server is determined based on the proportion of the data categories stored in each server during the current preset operating cycle.

2. The method for intelligently processing aircraft communication data based on an air-ground integrated network according to claim 1, characterized in that: The analysis module classifies the data stored in a single server in the current preset operation cycle based on the abnormal growth parameter, including: Determine the abnormal growth parameter, obtain the data stored in a single server within a preset operation cycle, determine the abnormal data in each data, calculate the proportion of the number of bytes of the abnormal data to the number of bytes of the total data stored within the preset operation cycle, and obtain the abnormal growth parameter; If the abnormal growth parameter is less than or equal to the first preset abnormal growth parameter, the category of data stored by the single server in the current preset operation cycle is classified into a category of data sets; If the abnormal growth parameter is less than or equal to the second preset abnormal growth parameter and greater than the first preset abnormal growth parameter, the data stored in the single server in the current preset operation cycle is classified based on the time distribution parameter; If the abnormal growth parameter is greater than the second preset abnormal growth parameter, the category of data stored in the single server during the current preset operation cycle is divided into two categories of data sets.

3. The method for intelligently processing aircraft communication data based on an air-ground integrated network according to claim 2, characterized in that: The analysis module is used to classify the data stored in a single server within the current preset operation cycle based on the time distribution parameter, including: Determine the time distribution parameter, determine the time nodes for obtaining each abnormal data within a preset operation cycle for a single server in turn, obtain the time distance between each time node in turn, solve the variance of each time distance, and obtain the time distribution parameter; If the time distribution parameter is less than or equal to the preset time distribution parameter, the category of data stored in the single server in the current preset operation cycle is divided into two categories of data sets; If the time distribution parameter is greater than the preset time distribution parameter, the category of data stored in the single server in the current preset operation cycle is divided into a category of data sets.

4. The method for intelligently processing aircraft communication data based on an air-ground-integrated network according to claim 3, characterized in that: The analysis module is used to determine a processing method for a single server based on abnormal data parameters, including: Determine the abnormal data parameter, obtain the ratio of the total number of bytes of the abnormal data of each server to the total number of bytes of each collected data output by the cleaning module, and obtain the abnormal data parameter; If the abnormal data parameter is less than or equal to the preset abnormal data parameter, the data stored in the single server in the current preset operation cycle is classified based on the data growth difference; If the abnormal data parameter is greater than the preset abnormal data parameter, each preset screening threshold is adjusted to a corresponding value based on the abnormal data parameter.

5. The method for intelligently processing aircraft communication data based on an air-ground integrated network according to claim 4, characterized in that: The analysis module is used to classify the data stored in a single server in a current preset operation cycle based on the data growth difference, including: Determine the data growth difference, obtain the data acquisition amount of a single server at each detection time node within a preset operation cycle, solve the variance of each data acquisition amount, and obtain the data growth difference; If the data growth difference is less than or equal to the preset data growth difference, the data stored in the single server in the current preset operation cycle is divided into three types of data sets; If the data growth difference is greater than the preset data growth difference, the data stored in the single server during the current preset operation cycle is divided into four categories of data sets.

6. The method for intelligently processing aircraft communication data based on an air-ground integrated network according to claim 5, characterized in that: The analysis module is used to adjust each preset screening threshold to a corresponding value based on the abnormal data parameter, wherein: The reduction range of each preset screening threshold determined based on the abnormal data parameter is proportional to the abnormal data parameter.

7. The method for intelligently processing aircraft communication data based on an air-ground-integrated network according to claim 6, characterized in that: The analysis module is used to determine the processing method for each server based on the proportion of the category of the data stored in each server in the current preset operation cycle, including: Calculate the proportion of the number of servers in one category to the total number of servers to determine the proportion of one category; Calculate the ratio of the number of Class II servers to the total number of servers to determine the proportion of Class II. Calculate the proportion of the number of the three types of servers to the total number of servers to determine the proportion of the three types; Calculate the ratio of the number of four types of servers to the total number of servers to determine the proportion of the four types; Get the maximum value of each category proportion; If the maximum value is the proportion of one category or three categories, the processing method for each server is based on the proportion ratio of the proportion of one category to the proportion of three categories; If the maximum value is the proportion of the second category, the match of the optimized decompression code is determined; If the maximum value is the proportion of the four categories, the number of processors is increased to a corresponding value based on the proportion of the four categories.

8. The method for intelligently processing aircraft communication data based on an air-ground integrated network according to claim 7, characterized in that: The analysis module is used to process each server based on the ratio of the first category proportion to the third category proportion, including: If the proportion ratio is within the preset proportion range, it is determined to optimize the secondary classification module; If the proportion ratio is outside the preset proportion range, each preset screening threshold is adjusted to a corresponding value based on the abnormal data parameter.

9. The method for intelligently processing aircraft communication data based on an air-ground integrated network according to claim 8, characterized in that: The analysis module is used to increase the number of processors to corresponding values ​​based on the four types of proportions, wherein: The increase in the number of processors determined based on the proportions of the four categories is proportional to the proportions of the four categories.

Images