Airborne detection data analysis method and system for intelligent meteorology

Abstract

The present application relates to the technical field of meteorological data analysis, and in particular, provides an airborne detection data analysis method and system for intelligent meteorology, which utilizes the data scanning of the first dimension to disassemble the airborne detection data, and generates an aviation meteorological embedded state vector by analyzing the meteorological feature correlation between data units, which can more comprehensively capture the inherent laws and changing trends of meteorological data and improve the accuracy and reliability of predictions. By adjusting the step size of the data scanning kernel and introducing data disassembly in different dimensions, a multi-level and multi-angle analysis of meteorological data is achieved, which helps to more comprehensively understand the complexity and dynamics of meteorological data, and provides strong support for subsequent predictions and decision support. It also optimizes data transmission efficiency and ensures the real-time and accuracy of information. This is crucial for real-time monitoring and early warning during flight, and can provide pilots with accurate meteorological information in a timely manner to help them make scientific flight decisions.

Description

Technical Field

[0001] The present application relates to the technical field of meteorological data analysis, and in particular to an airborne detection data analysis method and system for intelligent meteorology. Background Art

[0002] In existing aviation meteorological services, predicting and monitoring weather patterns is a crucial component of ensuring flight safety. However, traditional weather forecasting methods often rely on limited weather data and simple analytical models, making it difficult to accurately capture the inherent patterns and complex variations in weather data. Real-time and accurate weather information acquisition is particularly crucial during flight. Therefore, accurately identifying and predicting complex weather patterns has become a pressing challenge in aviation meteorological services. Summary of the Invention

[0003] In order to improve the above problems, the present application provides an airborne detection data analysis method and system for intelligent meteorology.

[0004] The embodiment of the present application provides an airborne detection data analysis method for intelligent meteorology, which is applied to a big data system. The method includes: acquiring airborne detection data, wherein the airborne detection data is meteorological detection data of a weather pattern to be predicted, wherein the weather pattern is used to characterize the meteorological state change of multidimensional meteorological data in the airborne detection data; the airborne detection data is disassembled into a plurality of first data scan sets by a data scan core of a first dimension; the airborne detection data is disassembled into a plurality of data units in a second dimension, wherein the first dimension is larger than the second dimension; and determining, based on the meteorological feature correlation between the data units in the plurality of first data scan sets, the first airborne detection data corresponding to the plurality of data units. The invention provides an air meteorological embedding state vector; adjusting the data scanning kernel of the first dimension in the airborne detection data by a set step size, and re-disassembling the airborne detection data into a plurality of second data scan sets; determining the second aviation meteorological embedding state vectors corresponding to the plurality of data units respectively based on the meteorological feature correlation between the first aviation meteorological embedding state vectors in the plurality of second data scan sets; predicting the weather pattern in the airborne detection data based on the second aviation meteorological embedding state vector, and obtaining a weather pattern prediction label corresponding to the airborne detection data, wherein the weather pattern prediction label is used to characterize the prediction result of the airborne detection data relative to the flight safety weather status.

[0005] An embodiment of the present application provides a big data system, comprising at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the above-mentioned method.

[0006] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the above method when executed.

[0007] The present invention uses a deep dive into and analysis of large amounts of meteorological data collected by airborne detection equipment, leveraging the inherent patterns and correlations of multidimensional meteorological data to accurately identify and predict complex weather patterns. Compared to traditional meteorological forecasting methods, the present invention offers the following significant advantages:

[0008] First, the airborne detection data is broken down using a first-dimensional data scan and verification. By analyzing the correlation between meteorological characteristics between data units, an aviation meteorological embedded state vector is generated. This approach can more comprehensively capture the inherent patterns and changing trends of meteorological data, improving the accuracy and reliability of forecasts.

[0009] Secondly, by adjusting the step size of the data scanning kernel and introducing data decomposition in different dimensions, we achieve multi-level and multi-angle analysis of meteorological data. This helps to more fully understand the complexity and dynamics of meteorological data, providing strong support for subsequent forecasting and decision-making.

[0010] Furthermore, data transmission efficiency has been optimized to ensure real-time and accurate information. This is crucial for real-time monitoring and early warning during flight, providing pilots with timely and accurate weather information to help them make informed flight decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 This is a flowchart of a method for analyzing airborne detection data for intelligent meteorology provided in an embodiment of the present application.

[0012] Figure 2 A schematic diagram of the structure of a big data system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0013] In order to better understand the above technical solution, the technical solution of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0014] Figure 1 A method for analyzing airborne detection data for intelligent meteorology is shown, which is applied to a big data system. The method includes the following steps 110 to 150.

[0015] In one application scenario, a big data system is used to process and analyze real-time meteorological data from airborne detection equipment to predict weather patterns and generate corresponding flight safety prediction labels. First, the big data system receives real-time detection data from airborne detection equipment. This airborne detection data contains a wealth of meteorological information, such as temperature, humidity, wind speed, wind direction, and air pressure, which are crucial for predicting weather patterns. The system identifies this data as meteorological detection data for the weather pattern to be predicted. Next, the big data system decomposes the airborne detection data using a pre-defined first-dimensional data scan. This data scan is a specific algorithm or tool that divides data according to a specific dimension. In this step, the airborne detection data is decomposed into several first data scan sets. Each first data scan set contains a portion of meteorological data, but with a reduced dimensionality compared to the original airborne detection data. The big data system then performs meteorological feature correlation analysis on the data units within each first data scan set. This analysis involves comparing meteorological features between different data units, such as the correlation between temperature and humidity or between wind speed and wind direction. By analyzing these correlations, the big data system determines a first aviation meteorological embedded state vector for each data unit. The first aviation meteorological embedded state vector is a mathematical representation that describes the position and state of the data unit in the meteorological feature space. After determining the first aviation meteorological embedded state vector, the big data system adjusts the step size of the data scan kernel in the first dimension and performs another decomposition on the airborne detection data. This decomposition results in several second data scan sets. Compared to the first data scan set, the second data scan set may have a different data distribution and feature combination. Next, the big data system again uses meteorological feature correlation analysis to determine the correlation between each first aviation meteorological embedded state vector in the second data scan set. This analysis process is similar to the previous step, but is based on different data scan sets and embedding state vectors. By analyzing these correlations, the big data system determines a second aviation meteorological embedded state vector for each data unit. This vector may differ from the first aviation meteorological embedded state vector because it is based on more granular or different perspectives of data analysis. Finally, the big data system uses the second aviation meteorological embedded state vector to predict weather patterns in the airborne detection data. This process can involve complex machine learning algorithms or models such as neural networks and decision trees. By comparing and analyzing the relationship between the embedded state vector and known weather patterns, the big data system generates a weather pattern prediction label. This label is an indicator that represents the predicted results of the onboard detection data relative to the flight-safe weather conditions. For example, if the prediction label indicates that the current weather pattern may pose a threat to flight safety, the airline or pilot can take appropriate measures to ensure flight safety.Throughout the entire process, the big data system continuously deconstructs, analyzes, and predicts data, achieving a deep understanding and utilization of airborne detection data. This not only improves the accuracy and reliability of weather forecasts, but also provides strong support for flight safety.

[0016] Step 110: Acquire airborne detection data, where the airborne detection data is meteorological detection data for which a weather pattern is to be predicted. The weather pattern is used to characterize meteorological state changes of multidimensional meteorological data in the airborne detection data. The airborne detection data is decomposed into a plurality of first data scan sets by a data scan core of a first dimension. The airborne detection data is decomposed into a plurality of data units by a second dimension, where the first dimension is larger than the second dimension.

[0017] In step 110, airborne detection data refers to real-time weather information collected by various meteorological detection devices installed on the aircraft. This data includes, but is not limited to, various meteorological parameters such as temperature, humidity, wind speed, wind direction, and air pressure. After being acquired and processed by sensors, it becomes an important basis for flight safety assessments and weather pattern forecasts. For example, during flight, an onboard radar can detect precipitation clouds ahead in real time; this data is part of the airborne detection data.

[0018] Weather patterns refer to the combination and variation of various atmospheric meteorological elements (such as temperature, humidity, air pressure, and wind speed) within specific time and space. Weather patterns characterize the state and evolution of weather systems and are key elements in weather forecasting and flight safety assessments. For example, a tropical cyclone (typhoon) is a typical weather pattern, characterized by specific meteorological characteristics and movement patterns.

[0019] Meteorological changes refer to the temporal and spatial variations of various atmospheric elements. These variations can range from subtle fluctuations to significant mutations, collectively constituting complex and ever-changing weather phenomena. During flight, meteorological changes directly impact flight safety and comfort. For example, sudden strong wind shear during flight can cause turbulence or even a crash.

[0020] A data scanning kernel is a specific algorithm or tool used in big data systems for data decomposition and analysis. It can break down complex airborne detection data into multiple data subsets (i.e., data scans) based on pre-defined dimensions and rules, enabling deeper analysis and prediction. The design and selection of a data scanning kernel is crucial for the accuracy and efficiency of data analysis. For example, in meteorological data analysis, a data scanning kernel can break down data into different subsets for temperature, humidity, wind speed, and other factors based on the correlation of meteorological elements.

[0021] The first data scan sets are subsets of the airborne detection data obtained by the big data system through the first-dimensional data scan. These subsets contain some meteorological data, but their dimensionality is reduced compared to the original airborne detection data, making them more convenient for subsequent analysis and prediction. The number and specific content of the first data scan sets depend on the data scan core settings and the characteristics of the airborne detection data.

[0022] A data unit is the smallest unit of data in airborne detection data. It contains the numerical information of a single meteorological element at a specific moment. In big data systems, data units are the basis for analyzing meteorological feature correlations and constructing embedded state vectors. By comparing meteorological feature correlations between different data units, big data systems can reveal the inherent connections and changing patterns among meteorological elements.

[0023] Specifically, the big data system receives real-time detection data from airborne detection equipment based on step 110. This data is meteorological detection data for the weather pattern to be predicted, and contains information on meteorological state changes in multi-dimensional meteorological data. To better facilitate subsequent analysis and prediction, the big data system uses data scans along the first dimension to break down the airborne detection data, dividing it into several first data scan sets. Simultaneously, the airborne detection data is also broken down into several data units along the second dimension, where the first dimension is larger than the second dimension, facilitating data analysis and processing at different levels.

[0024] Step 120: Determine first aviation meteorological embedded state vectors corresponding to the plurality of data units respectively based on meteorological feature correlations between the plurality of data units in the first data scan sets.

[0025] In step 120, meteorological feature correlation refers to the degree of association between different meteorological features (such as temperature, humidity, and wind speed) in the airborne detection data. This correlation can be measured using statistical analysis methods (such as correlation coefficients and covariance). For example, in airborne detection data, there may be a high correlation between temperature and humidity because, in some cases, when temperature increases, humidity also increases accordingly. This correlation is crucial for understanding the inherent patterns in meteorological data and predicting weather patterns. For example, if airborne detection data contains temperature and humidity data, the correlation between them can be measured by calculating the correlation coefficient between the two. A correlation coefficient close to 1 (or -1) indicates a high positive correlation (or negative correlation); a correlation coefficient close to 0 indicates a weak correlation.

[0026] The first aviation meteorological embedded state vector is a mathematical representation that describes the position and state of each data unit in the airborne detection data within the meteorological feature space. This vector can be composed of multiple numerical values, each representing the performance of the data unit with respect to a specific meteorological characteristic. These numerical values ​​can be extracted from the raw meteorological data using various algorithms (such as principal component analysis and neural networks). For example, each data unit in the airborne detection data is composed of three meteorological characteristics: temperature, humidity, and wind speed. Using an algorithm (such as a deep learning model), a three-dimensional embedded state vector can be generated for each data unit, such as [0.5, 0.8, 0.3]. The three numerical values ​​in this vector represent the performance of the data unit with respect to the three characteristics of temperature, humidity, and wind speed, respectively.

[0027] Based on step 120, the big data system first analyzes the meteorological characteristic correlations between data units within each first data scan set. This involves calculating statistics such as correlation coefficients and covariances between different meteorological characteristics to reveal the degree of association between them. The big data system then uses this correlation information, combined with specific algorithms (such as deep learning models and principal component analysis), to generate a first aviation meteorological embedded state vector for each data unit. This vector is a multidimensional numerical representation that integrates the data unit's performance across various meteorological characteristics and accurately locates the data unit's position and state within the meteorological feature space. Specifically, the big data system may first perform preprocessing on the raw meteorological data, such as data cleaning and normalization, to ensure data quality and consistency. It then selects an appropriate algorithm (such as a deep learning model) and sets the appropriate parameters and training strategy. Through model training, the big data system learns the meteorological characteristic correlations between data units and generates a corresponding embedded state vector. This embedded state vector not only contains the numerical information of the data unit across various meteorological characteristics, but also contains the relative relationships and spatial structure between the data units. Therefore, it can provide strong support for subsequent weather pattern forecasts. In this way, the big data system can generate an accurate and comprehensive first aviation meteorological embedded state vector for each data unit, laying a solid foundation for subsequent weather pattern prediction.

[0028] Step 130: Adjust the set step length of the data scan core of the first dimension in the airborne detection data, and re-decompose the airborne detection data into a plurality of second data scan sets.

[0029] In meteorological data analysis and weather pattern forecasting applications, the second data scan set refers to the data set obtained by re-decomposing the airborne detection data after adjusting the set step size of the first-dimensional data scan kernel. The "first dimension" here can refer to the initial dimension or granularity of the data scan kernel applied to the raw data, while "setting the step size adjustment" refers to adjusting the movement or change step size of the data scan kernel on the data according to specific rules or algorithms to observe and analyze the data at a finer granularity or from different angles.

[0030] In the second data scan set, the data is broken down in a similar way to the first data scan set. However, due to a change in the step size of the data scan kernel, each second data scan set can contain a different data distribution and feature combination. This variation helps the big data system extract and analyze the inherent patterns and correlations of meteorological data from multiple perspectives and levels, thereby more accurately predicting weather patterns.

[0031] For example, airborne detection data contains meteorological data such as temperature, humidity, and wind speed for a region, and this data is arranged in chronological order. In the first round of data scanning, the data scanning kernel decomposes the data with a larger step size (e.g., every hour), generating several first data scan sets, each containing meteorological data from adjacent time points. Then, in the second round of data scanning, the step size of the data scanning kernel is adjusted to a smaller value (e.g., every 15 minutes), and the airborne detection data is re-decomposed to generate several second data scan sets. Due to the reduced step size, these second data scan sets contain more fine-grained meteorological data, enabling the big data system to more precisely observe and analyze changes and correlations in meteorological characteristics.

[0032] As can be understood, step 130 is a critical step in the process of meteorological data analysis and weather pattern prediction. It involves adjusting the step size of the data scan kernel and re-fragmenting the airborne detection data accordingly. In this step, the big data system first determines the specific value and direction for adjusting the step size of the data scan kernel based on certain rules or algorithms. This step size adjustment is based on the results of the first round of data scanning (generating the first data scan set) and a deeper understanding of the inherent patterns and correlations of meteorological data. By adjusting the step size, the big data system can observe and analyze meteorological data at a finer granularity or from different perspectives, thereby extracting more useful information. Next, the big data system uses the adjusted data scan kernel to re-fragment the airborne detection data. This process is similar to the first round of data scanning, but due to the change in step size, each second data scan set will contain a different data distribution and feature combination. These second data scan sets will serve as the basis for subsequent meteorological feature correlation analysis and weather pattern prediction. During the re-fragmentation process, the big data system must ensure data integrity and accuracy, while also carefully handling potential outliers and noisy data. Furthermore, because adjusting the step size can increase or decrease the amount of data, the big data system also needs to adjust and optimize its data processing and storage capabilities accordingly. This allows the big data system to obtain a more detailed and comprehensive set of meteorological data (the second data scan), providing strong support for subsequent weather pattern forecasts.

[0033] Step 140: Determine second aviation meteorological embedded state vectors corresponding to the plurality of data units, respectively, based on meteorological feature correlations between the first aviation meteorological embedded state vectors in the plurality of second data scan sets.

[0034] In the application scenarios of meteorological data analysis and flight safety prediction, the second aviation meteorological embedded state vector is a new meteorological characteristic state representation generated by the big data system for each data unit based on more fine-grained or different-angle data analysis. It differs from the first aviation meteorological embedded state vector in that it is determined based on the meteorological characteristic correlation between the first aviation meteorological embedded state vectors within the second data scan set after adjusting the step size of the data scan kernel.

[0035] Specifically, after the big data system re-disassembles the airborne detection data into several second data scan sets by adjusting the set step size, it will further analyze the meteorological feature correlations between the original data units (or data points) in these newly generated data sets. These correlations can include the interactions and associations between various meteorological features such as temperature and humidity, wind speed and wind direction. Based on these new correlation analyses, the big data system recalculates and generates a second aviation meteorological embedded state vector for each data unit. This new embedded state vector not only contains the meteorological feature information of the data unit at a finer granularity or at different angles, but also reflects the new position and state of the data unit in the meteorological feature space. It is a more in-depth description and representation of the meteorological feature state of the data unit, which helps the big data system to more accurately understand and predict weather patterns, thereby providing more reliable prediction results for flight safety.

[0036] It can be understood that step 140 is a critical step in the meteorological data analysis and flight safety prediction process. It involves determining a second aviation meteorological embedded state vector for each data unit based on a more granular or different-angle data analysis. In this step, the big data system first obtains and analyzes the first aviation meteorological embedded state vectors within the second data scan set. These embedded state vectors are generated based on the first round of data scanning and meteorological feature correlation analysis. They provide a preliminary description of the position and status of the data unit in the meteorological feature space. Next, the big data system further analyzes the meteorological feature correlations between these first aviation meteorological embedded state vectors. This analysis process may include calculating similarity, distance, or other correlation metrics between vectors to reveal the relationships and changing trends in meteorological features between different data units. Based on these new correlation analyses, the big data system recalculates and generates a second aviation meteorological embedded state vector for each data unit. This new embedded state vector will contain meteorological feature information at a more granular or different angle, more accurately reflecting the position and status of the data unit in the meteorological feature space. In calculating the second aviation meteorological embedded state vector, the big data system can utilize various advanced algorithms and technologies, such as neural networks and deep learning. These algorithms and techniques can effectively process and analyze large amounts of meteorological data, extracting useful information and features to provide strong support for subsequent weather pattern forecasts. Through this process, the big data system can generate a more accurate and comprehensive second aviation meteorological embedded state vector for each data unit, providing a more reliable basis for subsequent flight safety predictions. This will help improve the accuracy and reliability of flight safety predictions and provide more valuable decision support for airlines and pilots.

[0037] Step 150: Predict the weather pattern in the airborne detection data based on the second aviation meteorological embedded state vector to obtain a weather pattern prediction label corresponding to the airborne detection data, where the weather pattern prediction label is used to characterize the prediction result of the airborne detection data relative to the flight safety weather state.

[0038] In step 150, weather pattern prediction labels are identifiers or labels for the likelihood of future weather patterns, derived from analysis of airborne sensor data using big data and machine learning algorithms. These labels, based on complex algorithms and models, can predict future weather patterns (e.g., sunny, cloudy, rainy, stormy, etc.) by comprehensively analyzing multiple meteorological data features such as temperature, humidity, wind speed, and direction. These labels not only contain basic information about the weather pattern but also reflect the potential impact of that weather pattern on flight safety.

[0039] The prediction of flight safety weather conditions based on airborne sensor data refers to an assessment of the potential impact of current or future weather conditions on flight safety, derived through a series of analysis and prediction algorithms based on airborne sensor data. This prediction is based on weather pattern prediction tags and combines multiple factors, such as aircraft performance parameters, flight path, and altitude, to comprehensively assess the impact of weather on flight safety. For example, if a severe storm is predicted, this prediction may prompt the pilot to change the flight path or lower the altitude to ensure flight safety.

[0040] In the meteorological data analysis and flight safety prediction process, step 150 is a key step. It involves using the second aviation meteorological embedded state vector to predict the weather pattern in the airborne probe data and generating a weather pattern prediction label based on this prediction. First, the big data system uses the calculated second aviation meteorological embedded state vectors. These vectors contain meteorological feature information at a finer granularity or from different angles, and can more accurately reflect the position and state of data units in the meteorological feature space. Next, the big data system inputs these second aviation meteorological embedded state vectors into a pre-trained weather pattern prediction model. This model may be built based on deep learning, neural networks, or other machine learning algorithms. It can automatically identify and predict different weather patterns by analyzing and learning from meteorological data. During the model's operation, it calculates the most likely weather pattern prediction based on the input second aviation meteorological embedded state vector and combines the model's internal parameters and algorithms. This prediction can be represented as a label, such as "sunny," "cloudy," or "rainy." Finally, this weather pattern prediction label is used to represent the prediction of the airborne probe data relative to the flight safety weather conditions. In other words, this tag not only contains basic information about weather patterns but also reflects the potential impact of these patterns on flight safety. Pilots and airlines can use this tag to assess current flight conditions and make appropriate decisions and adjustments to ensure flight safety. Through this process, the big data system can provide pilots and airlines with timely and accurate weather forecast information, helping them better understand current flight conditions and take appropriate measures to ensure flight safety.

[0041] The embodiment of the present application uses a series of advanced data processing technologies and intelligent algorithms to conduct in-depth mining and analysis of a large amount of meteorological data collected by airborne detection equipment, thereby achieving accurate identification and prediction of complex weather patterns. Specifically, the embodiment of the present application uses the first dimension of data scanning to disassemble the airborne detection data, and generates a first aviation meteorological embedded state vector by analyzing the meteorological feature correlation between data units. Subsequently, by adjusting the step size of the data scanning kernel, the airborne detection data is re-disassembled, and based on the meteorological feature correlation within the second data scan set, a more accurate second aviation meteorological embedded state vector is generated. Finally, based on these embedded state vectors, the embodiment of the present application can predict the weather pattern corresponding to the airborne detection data, and output the prediction results in the form of weather pattern prediction labels.

[0042] First, through the in-depth mining of multi-dimensional meteorological data and the application of intelligent algorithms, the accuracy and reliability of weather pattern forecasts have been significantly improved. This is of great significance to aviation meteorological support and can effectively enhance flight safety. Second, by adjusting the step size of the data scanning kernel and introducing data decomposition in different dimensions, multi-level and multi-angle analysis of meteorological data is achieved, thereby more comprehensively capturing the inherent patterns and changing trends of meteorological data. This not only improves the efficiency and accuracy of data analysis but also provides strong support for subsequent meteorological forecasts and decision support. Furthermore, data transmission efficiency is optimized to ensure the real-time and accurate information. This is crucial for real-time monitoring and early warning during flight, providing pilots with timely and accurate weather information to help them make informed flight decisions.

[0043] In summary, the application of advanced data processing technologies and intelligent algorithms has enabled the precise identification and prediction of complex weather patterns, significantly improving the reliability and safety of aviation meteorological services. This is of great significance for enhancing flight safety and optimizing meteorological services.

[0044] It should be noted that the adjustment of the set step size in the airborne detection data for the data scanning core of the first dimension is one of the core inventions of the present invention, which is described in detail below.

[0045] 1. The Importance of Setting Step Size Adjustments

[0046] In aviation weather monitoring and forecasting, the step size of the data scanning kernel plays a crucial role in accurately extracting and analyzing meteorological data. The step size determines the accuracy and efficiency of data scanning, which in turn influences the accuracy of weather pattern forecasts. Therefore, adjusting the step size of the data scanning kernel in the first dimension is a key step in optimizing data processing and forecasting.

[0047] 2. Specific operations for setting step length adjustment

[0048] Initial step size setting: Before starting data scanning, first set an initial data scanning kernel step size based on the characteristics of the airborne detection data and forecast requirements. This step size can be determined based on historical data and empirical values ​​to ensure that the main characteristics and changes of the meteorological data are covered.

[0049] Dynamic Adjustment Mechanism: During the data scanning process, the step size of the data scanning kernel is dynamically adjusted based on the scan results and real-time weather conditions. This dynamic adjustment can be automatic based on machine learning algorithms or manual with human intervention.

[0050] Automatic adjustment based on machine learning algorithms: By training a machine learning model, the model can automatically adjust the step size based on the quality and complexity of real-time data. When the data changes are complex and the weather patterns are volatile, the model will automatically reduce the step size to improve scanning accuracy; when the data changes are stable and the weather patterns are stable, the model will increase the step size appropriately to improve scanning efficiency.

[0051] Manual Adjustment with Human Intervention: In certain circumstances, such as during special weather events or flight mission requirements, the operator can manually adjust the step size based on actual conditions. This adjustment requires the operator to have extensive meteorological knowledge and experience to ensure that the adjusted step size more accurately reflects the actual meteorological data.

[0052] Multi-step combined scanning: To more comprehensively extract information from meteorological data, a multi-step combined scanning approach can be used. This involves performing multiple scans with varying step sizes within the same data set, and then fusing and analyzing the results. This approach can cover a wider range of data and feature variations, improving forecast accuracy.

[0053] 3. Setting the effect of step size adjustment

[0054] By adjusting the step size of the data scanning kernel in the first dimension, the following effects can be achieved:

[0055] Improve the accuracy of data scanning: By dynamically adjusting the step size, key information and characteristic changes in meteorological data can be extracted more accurately, reducing information loss and errors.

[0056] Improve data processing efficiency: Under the premise of ensuring scanning accuracy, appropriately increasing the step size can improve the speed and efficiency of data scanning and reduce computing resources and time costs.

[0057] Improve the accuracy of weather pattern predictions: By more accurately extracting and analyzing meteorological data, more precise predictions and identification of complex weather patterns can be achieved, improving the reliability and safety of aviation meteorological services.

[0058] To sum up, adjusting the step size of the data scanning kernel of the first dimension is one of the core invention points of the embodiment of this application. It realizes more efficient and accurate extraction and analysis of meteorological data by dynamically adjusting the scanning step size and optimizing the data processing method, providing strong support for aviation meteorological monitoring and forecasting.

[0059] In some optional embodiments, the first aviation meteorological embedded state vectors corresponding to the several data units are determined based on the meteorological feature correlation between the data units in the several first data scan sets, including: determining the first aviation meteorological focus features corresponding to the data units in the first data scan set based on the linkage feature focusing strategy; performing interval numerical mapping on the first aviation meteorological focus features corresponding to the several data units to obtain first aviation meteorological interval quantitative features; performing residual connection processing on the first aviation meteorological interval quantitative features through a deep residual network to obtain the first aviation meteorological embedded state vector.

[0060] In this embodiment, the big data system first acquires airborne detection data. This data is the meteorological detection data for the weather pattern to be predicted, which is used to characterize the meteorological state changes of multi-dimensional meteorological data. Next, the big data system processes this airborne detection data to extract and express its inherent meteorological characteristics.

[0061] In the first step of processing, the big data system uses specific data scans to break down the airborne detection data into several first data scan sets. Each data scan set contains a portion of data units in the airborne detection data, and these data units represent different meteorological characteristics or conditions.

[0062] Subsequently, the big data system determines the first aviation meteorological focal feature corresponding to each data unit in the first data scan set based on the linked feature focusing strategy. The linked feature focusing strategy is a feature selection method that analyzes the correlation of meteorological features between data units to identify key features, namely focal features, that have a significant impact on weather pattern predictions. These focal features can accurately reflect the main changes in meteorological conditions and are the basis for subsequent forecast analysis. After obtaining the first aviation meteorological focal features, the big data system will perform interval numerical mapping on these features. Interval numerical mapping is a feature conversion technology that maps the original feature value to a specific numerical interval for subsequent quantitative analysis and processing. Through interval numerical mapping, the big data system obtains the first aviation meteorological interval quantitative features, which have better numerical expression capabilities and computability.

[0063] Next, the big data system uses a deep residual network (DRN) to perform residual connection processing on the first aviation meteorological interval quantization features. A DRN is a deep learning model that uses shortcut connections to optimize the network structure, improving training effectiveness and generalization. During this residual connection process, the big data system inputs the interval quantization features into the DRN. Through network learning and calculation, the system obtains the first aviation meteorological embedded state vector corresponding to each data unit. These embedded state vectors contain rich meteorological information and can fully reflect the position and status of the data unit in the meteorological feature space.

[0064] After obtaining the first aviation weather embedded state vector, the big data system performs further adjustments and optimizations. First, it adjusts the first-dimensional data scan kernel within the airborne detection data with a set step size to more accurately capture changes in the weather data. Then, based on the adjusted data scan kernel, the big data system re-decomposes the airborne detection data into several second data scan sets.

[0065] Based on the second data scan, the big data system again utilizes a linked feature focussing strategy and a deep residual network to determine the second aviation weather embedding state vector for each data unit. These second aviation weather embedding state vectors more accurately represent the weather state of each data unit by taking into account more dimensional meteorological features.

[0066] Finally, the big data system predicts the weather patterns in the airborne probe data based on the second aviation meteorological embedded state vector and generates corresponding weather pattern prediction labels. These prediction labels are used to characterize the prediction results of the airborne probe data relative to the flight safety weather conditions, providing strong support for aviation meteorological support.

[0067] In this way, the big data system can achieve deep mining and efficient processing of airborne detection data, enabling accurate identification and prediction of complex weather patterns. Furthermore, by optimizing data transmission efficiency and improving prediction accuracy, the embodiments of this application provide more reliable and secure aviation meteorological services. This not only improves the efficiency and quality of aviation meteorological services, but also provides important technical support for flight safety.

[0068] In the next step, the first aviation meteorological focus feature corresponding to the data unit in the first data scan set is determined based on the linkage feature focusing strategy, including: extracting the local aviation meteorological embedded state vectors corresponding to the several data units in the airborne detection data; determining the local aviation meteorological state correlation between the u-th local aviation meteorological embedded state vector corresponding to the u-th data unit in the first data scan set and the v-th local aviation meteorological embedded state vector corresponding to the v-th data unit, where u and v are positive integers; for the u-th data unit in the first data scan set, the local aviation meteorological state correlation corresponding to the u-th data unit in the first data scan set is used as an enhancement coefficient, and the local aviation meteorological embedded state vector of the data unit in the first data scan set is feature enhanced to obtain the first aviation meteorological focus feature corresponding to the u-th data unit.

[0069] Based on this embodiment, after acquiring the airborne detection data, the big data system will first use a specific data scan to verify the data and break it down into several first data scan sets. Each data scan set contains a portion of data units in the airborne detection data, and these data units represent different meteorological characteristics or conditions.

[0070] Next, the big data system implements a linked feature focusing strategy. The core of this strategy is to identify key features, or focal features, by analyzing the correlations between meteorological features between data units. During this step, the big data system first extracts the local aviation meteorological embedded state vector corresponding to each data unit. This local aviation meteorological embedded state vector is obtained by encoding and embedding the meteorological features of the data unit and reflects the local state of the data unit in the meteorological feature space.

[0071] The big data system then determines the correlation between the local aviation meteorological states of different data units within the first data scan set. Specifically, the system calculates the correlation between the u-th local aviation meteorological embedded state vector corresponding to the u-th data unit and the v-th local aviation meteorological embedded state vector corresponding to the v-th data unit. This correlation can be obtained by calculating the similarity, distance, or other metric between the two vectors. u and v are positive integers, representing different data units within the first data scan set.

[0072] After determining the correlation of local aviation meteorological states, the big data system will perform feature enhancement on the local aviation meteorological embedded state vector of each data unit. The purpose of this step is to enhance the expression of key features based on the correlation between data units, making them more prominent. Specifically, for the u-th data unit in the first data scan set, the big data system will use the local aviation meteorological state correlation between it and other data units as the enhancement coefficient and perform weighted processing on the local aviation meteorological embedded state vector corresponding to the u-th data unit. In this way, features that are strongly correlated with the u-th data unit will receive greater weights, thereby playing a more important role in subsequent analysis.

[0073] After feature enhancement, the big data system obtains the primary aviation meteorological focus features for each data unit. These focus features not only contain the meteorological information of the data unit itself, but also incorporate information about its relationships with other data units, thus more accurately reflecting the position and role of the data unit in the meteorological system.

[0074] In this way, the big data system can achieve deep mining and efficient processing of airborne detection data, thereby more accurately identifying and predicting complex weather patterns. Specifically, by extracting local aviation meteorological embedded state vectors, calculating local aviation meteorological state correlations, and performing feature enhancement processing, the big data system can identify key features that have a significant impact on weather pattern prediction, providing strong support for subsequent forecast analysis. This not only improves the accuracy and reliability of aviation meteorological services, but also provides important technical support for flight safety.

[0075] In some preferred technical solutions, the second aviation meteorological embedded state vectors corresponding to the several data units are determined based on the meteorological feature correlation between the first aviation meteorological embedded state vectors in the several second data scan sets, including: determining the second aviation meteorological focus features corresponding to the first aviation meteorological embedded state vector in the second data scan set based on the linkage feature focusing strategy; performing interval numerical mapping on the second aviation meteorological focus features corresponding to the several data units to obtain second aviation meteorological interval quantitative features; performing residual connection processing on the second aviation meteorological interval quantitative features through a deep residual network to obtain the second aviation meteorological embedded state vector.

[0076] In the above technical solutions, the linked feature focus strategy is a strategy used to identify key features or focal points in data analysis. It analyzes correlations between data to identify the features that have the greatest impact on the results. Interval-value mapping is a method that maps raw data to specific numerical intervals for quantitative analysis and comparison. A deep residual network is a deep learning network architecture that introduces residual connections to address the vanishing gradient problem in deep network training, improving network performance.

[0077] Now, taking a specific application scenario as an example, we will explain in detail how the big data system determines the second aviation meteorological embedded state vectors corresponding to several data units based on the meteorological feature correlation between the first aviation meteorological embedded state vectors in several second data scan sets.

[0078] During flight, an aircraft's onboard detection equipment collects a large amount of meteorological data in real time, including temperature, humidity, wind speed, and other meteorological characteristics. The big data system first decomposes this onboard detection data using first-dimensional data scanning and verification, generating several first data scan sets. The system then analyzes the meteorological feature correlations between data units within each first data scan set, generating a first aviation meteorological embedded state vector for each data unit.

[0079] The big data system then adjusts the step size of the data scan core in the first dimension based on the flight mission requirements and the accuracy of the data analysis. This adjustment may include reducing the step size to obtain finer-grained data or changing the direction of the step size to observe data changes at different angles. The adjusted data scan core then re-decomposes the airborne detection data to generate several second data scan sets.

[0080] After obtaining the second data scan set, the big data system begins implementing a linked feature focussing strategy. This strategy determines the second aviation meteorological focus features for each data unit by analyzing the meteorological feature correlations between the first aviation meteorological embedded state vectors within the second data scan set. These focus features are key meteorological features that influence weather pattern predictions and may be a combination of one or more of temperature, humidity, and wind speed.

[0081] Next, the big data system performs interval-value mapping on the second aviation meteorological focus features corresponding to each data unit. This process converts the raw meteorological data into quantitative features with uniform numerical intervals, facilitating subsequent mathematical analysis and calculations. Through interval-value mapping, the big data system obtains a set of second aviation meteorological interval-valued features.

[0082] Finally, the big data system uses a deep residual network to perform residual connection processing on the quantitative features of the second aviation weather interval. By introducing residual connections, the deep residual network effectively solves the vanishing gradient problem that can occur during deep network training, improving network performance. During this residual connection process, the network can learn more complex meteorological feature relationships between data units and generate a more accurate second aviation weather embedding state vector based on this.

[0083] Through this series of data processing and analysis steps, the big data system generates a second aviation weather embedded state vector for each data unit. These embedded state vectors not only contain the data unit's position and state information in the meteorological feature space, but also imply the relative relationships and spatial structure between data units. Based on these embedded state vectors, the big data system can more accurately predict weather patterns and provide more reliable forecasts for flight safety.

[0084] In this way, through multiple steps, including decomposing data scanning kernels, analyzing meteorological feature correlations, applying a linkage feature focusing strategy, interval-value mapping, and residual connection processing using a deep residual network, this method achieves in-depth analysis and processing of meteorological data from airborne detection data. This technical solution improves the accuracy and reliability of weather pattern forecasts, providing a strong guarantee for flight safety. It also demonstrates the potential and value of big data and machine learning technologies in meteorological data analysis.

[0085] In some other preferred technical solutions, the airborne detection data is decomposed into x first data scan sets by the data scanning core of the first dimension, where x is a positive integer; the second aviation meteorological focus feature corresponding to the first aviation meteorological embedded state vector in the second data scan set is determined based on the linkage feature focusing strategy, including: determining that the number of the second data scan sets obtained by decomposing the airborne detection data after the data scanning core of the first dimension wanders is y, where y is a positive integer and y>x; cross-matching the data units in the second data scan set based on time series features to obtain x third data scan sets; and determining the second aviation meteorological focus feature corresponding to the first aviation meteorological embedded state vector in the third data scan set based on the linkage feature focusing strategy.

[0086] When explaining the implementation of this technical solution in detail, a specific application scenario will be used to illustrate how the big data system determines the second aviation meteorological focus feature based on the linkage feature focusing strategy.

[0087] For example, when an aircraft performs a long-distance flight, its onboard detection equipment continuously collects meteorological data, including temperature, humidity, wind speed, and other weather characteristics. This data changes in real time and is crucial for flight safety. The big data system first uses the first-dimensional data scan to break down the onboard detection data and generate x first-dimensional data scan sets. Each data scan set contains a series of meteorological data units within a specific time period.

[0088] However, to further refine the analysis and capture subtle changes in meteorological data, the big data system decided to adjust the step size of the data scan kernel and re-decompose the airborne detection data. The adjusted data scan kernel performs a roving decomposition of the airborne detection data, resulting in y second data scan sets, where y is a positive integer and y>x. This means that the new decomposition method provides more data subsets, each of which reflects changes in meteorological data at a finer granularity or from different angles.

[0089] After obtaining the second data scan set, the big data system did not directly analyze these new data subsets. Instead, it adopted a cross-matching method based on time series characteristics. Because meteorological data has a distinct time series nature, meaning that the data changes over time, the big data system believes that cross-matching data units at different time points can better reveal the inherent connections and changing patterns between meteorological characteristics.

[0090] The big data system then cross-matched the data units in the second data scan set based on their temporal characteristics. Specifically, the system matched each data unit with similar data units at other points in time based on their timestamps, forming a new set of data subsets, or x third data scan sets. These third data scan sets not only contained the meteorological characteristics of the original data but also introduced temporal correlation information through cross-matching.

[0091] Next, the big data system uses the linked feature focusing strategy to determine the second aviation meteorological focus feature corresponding to the first aviation meteorological embedded state vector in the third data scan set. Linked feature focusing is a data analysis method that analyzes the correlations between different features in a dataset to identify the key features that have the greatest impact on the results. In this scenario, the big data system analyzes the correlations between meteorological features in the third data scan set to identify the feature combination that has the greatest impact on the weather pattern forecast, namely the second aviation meteorological focus feature.

[0092] Through this process, the big data system not only obtains a more granular subset of meteorological data but also identifies key meteorological features that influence weather pattern predictions through cross-matching of time series features and focusing on linked features. These key features will provide strong support for subsequent weather pattern predictions, making them more accurate and reliable.

[0093] As can be seen, by adjusting the step size of the data scanning kernel, cross-matching based on time series features, and applying a linkage feature focusing strategy, in-depth analysis and processing of airborne detection data is achieved. This technical solution not only improves the accuracy and efficiency of meteorological data analysis, but also provides more accurate key feature information for weather pattern prediction. This is of great significance for ensuring flight safety and improving the accuracy of weather forecasts. At the same time, this technical solution also demonstrates the powerful potential and application value of big data and machine learning technologies in the field of meteorological data analysis.

[0094] Under other possible design ideas, the second aviation meteorological focus feature corresponding to the first aviation meteorological embedded state vector in the third data scan set is determined based on the linkage feature focusing strategy, including: obtaining the time series cross-matching information corresponding to the p-th third data scan set, the time series cross-matching information is used to characterize the time series continuity of the second data scan set after cross-matching, p is a positive integer, p≤x; obtaining the aviation state labeling information corresponding to the p-th third data scan set based on the time series cross-matching information; determining the embedding vector commonality value between the first aviation meteorological embedded state vectors in the third data scan set based on the linkage feature focusing strategy; weighting the embedding vector commonality value and the aviation state labeling information to obtain the aviation state weighted commonality value; and performing feature enhancement on the first aviation meteorological embedded state vector of the data unit in the third data scan set based on the aviation state weighted commonality value to obtain the second aviation meteorological focus feature.

[0095] When further explaining in detail how the big data system determines the second aviation meteorological focus feature corresponding to the first aviation meteorological embedded state vector in the third data scan set based on the linkage feature focusing strategy, a specific application scenario will be used to illustrate.

[0096] For example, when an aircraft flies over a complex weather area, its onboard detection equipment continuously collects meteorological data. The big data system adjusts the data scan kernel and cross-matches the time series features to generate x third-order data scan sets. Each third-order data scan set contains cross-matched meteorological data units, which maintain a certain degree of temporal continuity.

[0097] First, the big data system begins processing the pth third data scan set, where p is a positive integer and p≤x. The system obtains the time series cross-matching information corresponding to this data scan set. Time series cross-matching information refers to the information recorded by the system during the cross-matching process regarding the temporal continuity and correlation of data units. This information is crucial for understanding the changing trends and inherent patterns of meteorological data.

[0098] Next, the big data system uses the time-series cross-matching information to obtain the aviation status annotation information corresponding to the pth third data scan set. Aviation status annotation information refers to the information that labels the impact of meteorological data on flight safety based on the time-series cross-matching results. For example, the system may label certain meteorological data as "potentially dangerous areas" to alert pilots.

[0099] Then, the big data system uses a linked feature focusing strategy to determine the embedding vector commonality between the first aviation weather embedded state vectors in the third data scan set. Embedding vector commonality refers to the similarity or shared characteristics between different embedded state vectors in the meteorological feature space. By calculating this embedding vector commonality, the system can identify the embedding state vector combinations that have the greatest impact on weather pattern forecasts.

[0100] Next, the big data system performs a weighted process on the embedding vector commonality values ​​and the aviation status annotation information. Weighted processing involves adjusting the embedding vector commonality values ​​based on the importance of the aviation status annotation information. This step further highlights the role of key meteorological features in weather pattern prediction.

[0101] Finally, the big data system performs feature enhancement on the first aviation meteorological embedded state vectors of the data units in the third data scan set based on the weighted commonality of the aviation states. Feature enhancement involves increasing the weights of key meteorological features or adjusting their values ​​to make them more effective in subsequent weather pattern forecasts. The resulting embedded state vector, known as the second aviation meteorological focal feature, serves as an important input for weather pattern forecasts.

[0102] This implementation not only considers the temporal continuity and correlation of meteorological data but also enhances key meteorological features by combining aviation status annotation information and embedded vector commonality values. This enables the system to more accurately identify the meteorological feature combinations that have the greatest impact on flight safety, thereby improving the accuracy and reliability of weather pattern forecasts. This technical solution is of great significance in ensuring flight safety and enhancing the quality of weather forecasts.

[0103] In some other embodiments, the step size of the data scanning core of the first dimension is adjusted in the airborne detection data to re-disassemble the airborne detection data into a plurality of second data scanning sets, including: wandering the data scanning core of the first dimension at intervals of w data units on a first wandering path corresponding to the airborne detection data; wandering the data scanning core of the first dimension at intervals of r data units on a second wandering path corresponding to the airborne detection data to determine the plurality of second data scanning sets; wherein w and r are positive integers.

[0104] For example, when an aircraft flies through a highly variable weather region, its onboard detection equipment collects a large amount of meteorological data in real time. This data covers multiple dimensions, such as temperature, humidity, wind speed, and wind direction, and is crucial for flight safety. The big data system has already performed a preliminary analysis of this airborne detection data using a first-dimensional data scan core, generating several first-dimensional data scan sets. However, to more comprehensively capture the subtle changes and inherent patterns in the meteorological data, the system decided to adjust the step size of the first-dimensional data scan core and re-analyze the data.

[0105] In this embodiment, the big data system uses two different walk paths to adjust the step size of the data scanning kernel. First, on the first walk path corresponding to the airborne detection data, the system walks the data scanning kernel in the first dimension at intervals of w data units. This means that each time the data is disassembled, the data scanning kernel skips w data units, resulting in a new data subset. By adjusting the size of w, the system can observe changing trends in meteorological data at different data granularities.

[0106] Next, on the second roaming path corresponding to the airborne detection data, the system roams the data scan core of the first dimension at intervals of r data units. The r here differs from the w in the first roaming path and represents another granularity of data decomposition. By varying the value of r, the system can capture the characteristics of meteorological data from a different perspective. It is worth noting that the first and second roaming paths may be based on different data features or time series, allowing for analysis of meteorological data from multiple dimensions.

[0107] During the walk, the big data system records each data subset and combines them into several secondary data scans. These secondary data scans, using different walk paths and step sizes, contain meteorological data at varying granularities and angles. These provide a rich data foundation for subsequent linked feature focusing strategies, embedding vector commonality calculations, and feature enhancement processing.

[0108] This implementation enables the big data system to flexibly adjust the step size of the data scanning kernel and analyze airborne detection data from multiple angles and granularities. This not only helps comprehensively capture subtle changes and inherent patterns in meteorological data, but also improves the accuracy and reliability of weather pattern forecasts. This technical solution has important application value in fields such as flight safety prediction and meteorological data analysis.

[0109] By adjusting the step size of the data scanning kernel and employing a multi-path approach to decompose airborne detection data, the big data system can acquire richer, multi-dimensional meteorological data. This information provides strong support for subsequent feature analysis, pattern recognition, and forecasting, making weather pattern predictions more accurate and reliable.

[0110] In an optional embodiment, predicting the weather pattern in the airborne detection data based on the second aviation meteorological embedded state vector to obtain a weather pattern prediction label corresponding to the airborne detection data includes: obtaining an aviation mission description feature, the aviation mission description feature is used to assist in predicting the weather pattern corresponding to the airborne detection data; inputting the aviation mission description feature and the second aviation meteorological embedded state vector into a pre-debugged aviation meteorological prediction network to obtain the weather pattern prediction label.

[0111] In a more refined embodiment, when predicting weather patterns in airborne probe data based on the second aviation weather embedded state vector, the big data system not only considers the weather data itself but also incorporates aviation mission description features as auxiliary information to further improve prediction accuracy. The specific steps and beneficial effects of this embodiment are explained in detail below.

[0112] For example, an aircraft carrying out a long-distance cargo mission may have a route that traverses multiple regions with complex weather conditions. To ensure flight safety, a big data system must accurately predict weather patterns along the flight path. First, the system acquires airborne sensor data through the previous steps. By decomposing the data scanning core and applying a linkage feature focusing strategy, it generates a second aviation weather embedding state vector for each data unit.

[0113] However, relying solely on meteorological data for predictions may not be comprehensive enough. This is because different aviation missions have different requirements for weather conditions. For example, cargo missions may be more concerned with wind speed and direction, while passenger missions may be more concerned with precipitation and visibility. Therefore, in this embodiment, the big data system incorporates aviation mission description features as auxiliary prediction information.

[0114] Aviation mission description features can include multiple dimensions, such as mission type (e.g., cargo, passenger, military), flight route, estimated flight time, flight altitude, and aircraft model. These features can be obtained through channels such as the airline's mission plan and flight management system. The big data system correlates these features with the second aviation meteorological embedded state vector to more comprehensively understand the weather requirements and constraints of the current flight mission.

[0115] Next, the big data system feeds the mission description features and the second aviation weather embedded state vector into a pre-tuned aviation weather prediction network. This prediction network is a deep learning model trained and optimized with extensive historical data. Based on the input meteorological data and mission characteristics, it automatically learns and identifies the relationships and patterns between different weather patterns and flight missions.

[0116] Through calculations within the aviation weather forecast network, the big data system ultimately generates a weather pattern prediction label. This label not only includes information about current or future weather patterns (such as sunny, cloudy, rainy, and stormy), but also incorporates mission descriptors to comprehensively assess the impact of weather patterns on flight missions. For example, if a severe storm is predicted for a certain period of time in the future, and this storm could seriously impact the safety of a cargo mission, the prediction label could specifically indicate this fact, alerting pilots and airlines to take appropriate action.

[0117] Through this implementation, the big data system not only leverages the inherent information in meteorological data but also incorporates the characteristics of aviation mission descriptions to achieve more comprehensive and accurate forecasts of weather patterns. This forecasting method not only helps improve flight safety but also provides airlines with more scientific decision-making support, optimizing flight plans and resource allocation. Furthermore, this technical solution demonstrates the broad application prospects of big data and deep learning technologies in weather forecasting and aviation safety.

[0118] In the next step, the aviation mission description feature and the second aviation meteorological embedded state vector are input into the pre-debugged aviation meteorological forecast network to obtain the weather pattern prediction label, including: inputting the aviation mission description feature and the second aviation meteorological embedded state vector into the pre-debugged aviation meteorological forecast network to obtain the meteorological state bias prediction information of the aviation meteorological forecast network; obtaining a set label index indication, the label index indication is used to match and output prediction keywords that meet the target aviation weather requirements; and updating the meteorological state bias prediction information through the label index indication to obtain the weather pattern prediction label.

[0119] When further explaining how the big data system uses aviation mission description features and the second aviation weather embedding state vector to predict weather patterns, it will be elaborated on how to generate weather pattern prediction labels through the pre-debugged aviation weather prediction network and how to more accurately meet specific aviation weather needs through label index indication.

[0120] For example, consider an aircraft carrying out an important passenger mission, whose route traverses multiple regions with varying climates. To ensure the safety and comfort of passengers, a big data system needs to accurately predict weather patterns along the flight path, paying particular attention to weather conditions that could adversely affect the flight.

[0121] First, the big data system has already acquired the airborne detection data through the previous steps and generated the second aviation weather embedding state vector. At the same time, the system also obtains descriptive features related to the current aviation mission, such as the flight type (passenger transport), flight route, and estimated flight time.

[0122] Next, the big data system inputs the mission description features and the second aviation weather embedded state vector into a pre-tuned aviation weather forecasting network. This network is a deep learning model that has been trained and optimized using a large amount of historical weather data and flight mission data. Based on the input feature vectors, it automatically learns and identifies the relationships and patterns between different weather patterns and flight missions.

[0123] When the input feature vector enters the aviation weather forecast network, it performs a series of complex calculations and processing, ultimately outputting a biased forecast of the weather state. This information is a quantitative description of weather patterns over a period of time, encompassing the changing trends and possible ranges of multiple meteorological elements such as temperature, humidity, wind speed, and wind direction.

[0124] However, relying solely on biased meteorological forecast information may not be sufficient to meet specific aviation weather requirements. For example, in passenger transport missions, passengers may have high comfort requirements, so special attention needs to be paid to weather conditions that may cause turbulence or discomfort. To more accurately meet these requirements, big data systems introduce a tool called label indexing.

[0125] Label indexing is a set of pre-set rules or mappings used to match forecast keywords to target aviation weather requirements. For example, a label indexing might specify that when wind speeds exceed a certain threshold, the label "strong winds" should be output; when visibility falls below a certain threshold, the label "low visibility" should be output, and so on. These labels not only describe basic weather patterns but also incorporate the specific requirements of aviation missions, providing more intuitive and targeted guidance for pilots and airlines.

[0126] The big data system updates the biased weather forecast information using tag indexes. Specifically, the system first filters and matches the forecast information according to the rules indicated by the tag indexes, identifying keywords or tags that meet specific weather requirements. The system then combines these keywords or tags with the original biased weather forecast information to generate the final weather pattern forecast tag.

[0127] Through this implementation, the big data system not only leverages the mission description features and the second aviation weather embedded state vector to predict weather patterns, but also performs more refined processing of the prediction results through label index indication. This processing approach not only improves prediction accuracy but also makes the predictions more tailored to the specific requirements of the aviation mission. This is of great significance for ensuring flight safety and improving flight comfort. Furthermore, this technical solution demonstrates the powerful potential and application value of big data and deep learning technologies in the fields of weather forecasting and aviation safety.

[0128] In some further preferred embodiments, the weather pattern prediction label includes the meteorological state jump type, meteorological state distribution characteristics and meteorological state risk characteristics of the weather pattern. After predicting the weather pattern in the airborne detection data based on the second aviation meteorological embedded state vector and obtaining the weather pattern prediction label corresponding to the airborne detection data, it also includes: based on the meteorological state distribution characteristics indicated by the weather pattern prediction label, decomposing the airborne detection data into local airborne detection results corresponding to several weather patterns; predicting the state jump characteristics within the local airborne detection results based on the meteorological state jump type indicated by the weather pattern prediction label, and generating state jump mapping data corresponding to the local airborne detection results; judging the state jump mapping data corresponding to the several weather patterns based on the meteorological state risk characteristics indicated by the weather pattern prediction label, and generating an aviation risk judgment opinion.

[0129] Further exploring how big data systems can implement weather pattern predictions and conduct in-depth analysis based on these predictions, consider an aircraft conducting a cross-country flight, where its flight path traverses multiple climate zones. To ensure flight safety, big data systems must accurately predict weather patterns from onboard sensor data and generate detailed local weather analysis and risk assessments based on these predictions.

[0130] First, the big data system uses the second aviation meteorological embedded state vector, following the previous steps, to predict the weather pattern in the airborne detection data and generate a corresponding weather pattern prediction label. In this embodiment, the weather pattern prediction label not only contains basic information about the weather pattern but is also further divided into three components: weather state transition type, weather state distribution characteristics, and weather state risk characteristics. The weather state transition type describes the types of changes that may occur in various meteorological elements (such as temperature and wind speed) within the weather pattern; the weather state distribution characteristics reflect the temporal and spatial distribution of different weather patterns; and the weather state risk characteristics assess the potential risk each weather pattern poses to flight safety.

[0131] After receiving the weather pattern prediction labels, the big data system begins to analyze the airborne detection data based on the meteorological distribution characteristics in the labels. Specifically, the system divides the airborne detection data into several localized areas based on the distribution of different weather patterns indicated by the labels. Each area corresponds to one or more weather patterns. This analysis helps the system more accurately analyze the specific impact of different weather patterns on flight safety.

[0132] Next, the big data system predicts the state transition characteristics within each local airborne detection result based on the types of meteorological state transitions in the weather pattern prediction tag. State transition characteristics describe the potential change trends and speeds of various meteorological elements under specific weather patterns. By generating state transition mapping data, the system can more intuitively display these changes and provide timely warnings and guidance to pilots.

[0133] Finally, the big data system identifies the state transition mapping data corresponding to each local airborne detection result based on the meteorological state risk characteristics in the weather pattern forecast label. This step aims to assess the potential risks of different weather patterns to flight safety and generate corresponding aviation risk assessment opinions. These opinions not only include an assessment of the risk level but also may include the specific risk source, impact scope, and recommended response measures, providing comprehensive decision support for pilots and airlines.

[0134] Through this embodiment, the big data system not only achieves accurate prediction of weather patterns in airborne detection data, but also conducts in-depth analysis and judgment based on the prediction results. This comprehensive analysis method not only improves the level of flight safety, but also provides airlines with a more scientific and comprehensive basis for decision-making. Specifically, the system comprehensively reveals the impact mechanism of different weather patterns on flight safety through multiple steps such as disassembling airborne detection data, predicting state jump characteristics, and judging aviation risks, providing pilots with more accurate and timely guidance information. At the same time, this comprehensive analysis method can also provide strong support for airlines to optimize flight plans, improve service quality, and further promote the safe and efficient development of the aviation industry.

[0135] In an optional embodiment, the method is implemented by a pre-debugged weather pattern prediction algorithm, which is debugged by the prediction algorithm to be debugged, and the debugging process of the prediction algorithm to be debugged includes: obtaining airborne detection data samples and a weather pattern authentication sample set corresponding to the airborne detection data samples, the weather pattern authentication sample set is used to characterize the weather pattern training annotation chain corresponding to the airborne detection data samples; inputting the airborne detection data samples into the prediction algorithm to be debugged to generate a weather pattern prediction training result; and based on the difference between the weather pattern prediction training result and the weather pattern authentication sample set, cyclically debugging the prediction algorithm to be debugged to obtain the weather pattern prediction algorithm.

[0136] In a more refined and systematic embodiment, the big data system uses a pre-debugged weather pattern prediction algorithm to predict weather patterns from airborne sensor data. This pre-debugged weather pattern prediction algorithm is not directly applied to actual forecasting tasks, but rather has been carefully debugged and optimized to ensure its accuracy and reliability. The following details the debugging process for the prediction algorithm to be debugged and how this process results in the pre-debugged weather pattern prediction algorithm.

[0137] First, to debug and optimize the prediction algorithm to be debugged, the big data system needs to obtain two sets of key data: airborne detection data samples and a set of certified weather pattern samples corresponding to the airborne detection data samples. The airborne detection data samples are a series of representative meteorological detection data from actual flights, which contain meteorological data characteristics under various weather patterns. The certified weather pattern sample set, on the other hand, contains the weather pattern annotation information corresponding to these airborne detection data samples, which has been verified by experts or historical data. This certified sample set effectively constitutes a weather pattern training annotation chain, providing clear learning objectives and evaluation criteria for the prediction algorithm to be debugged.

[0138] After acquiring these two sets of data, the big data system feeds the airborne detection data samples into the prediction algorithm to be debugged, allowing the algorithm to generate weather pattern prediction training results based on the input data. This process simulates the scenarios encountered in actual forecasting tasks, allowing the prediction algorithm to initially demonstrate its predictive capabilities.

[0139] However, simply generating forecasts isn't enough; big data systems also need to evaluate their accuracy. To this end, the big data system compares the forecast training results with a validated set of weather pattern examples to identify differences and discrepancies between the two. These differences may manifest in various aspects, such as the type of weather pattern predicted, the changing trends of meteorological elements, and the assessment of risk levels.

[0140] Based on these comparison results, the big data system begins a cycle of debugging the prediction algorithm. This debugging process can include modifying the algorithm's internal parameters, adjusting the model structure, adding new learning features, and other methods. Through continuous trial and error, the big data system gradually optimizes the performance of the prediction algorithm, enabling it to better fit the characteristics of actual meteorological data and improve prediction accuracy.

[0141] After multiple rounds of debugging and optimization, the performance of the prediction algorithm under debugging was significantly improved, and the big data system designated it as the pre-debugged weather pattern prediction algorithm. This pre-debugged algorithm not only achieved high prediction accuracy but also maintained stable performance across various weather patterns. Therefore, when the big data system was presented with actual airborne detection data, it was able to quickly and accurately generate corresponding weather pattern prediction labels, providing a strong guarantee for flight safety.

[0142] This implementation demonstrates a systematic and refined debugging process for a weather pattern prediction algorithm. This process not only improves the accuracy and reliability of the prediction algorithm but also ensures its stability and usability in practical applications. This data-driven, iterative debugging optimization approach is not only applicable to weather pattern prediction but can also be extended to other scenarios requiring high-precision predictions, possessing broad application prospects and significant practical value.

[0143] In an independent embodiment, obtaining a weather pattern authentication sample set corresponding to the airborne detection data sample includes:

[0144] (1) obtaining meteorological environment information of the airborne detection data sample, wherein the meteorological environment information includes a training learning annotation of the weather pattern in the airborne detection data sample;

[0145] (2) adjusting the airborne detection data samples into a meteorological monitoring relationship network, wherein the meteorological monitoring relationship network includes a meteorological status relationship subnet and an abnormal warning relationship subnet;

[0146] (3) performing entity updates based on weather patterns on the meteorological monitoring relationship network, disassembling the meteorological monitoring relationship network according to the connection relationships between the entity update information based on weather patterns, and obtaining a plurality of first knowledge relationship spectra, wherein the knowledge relationship feature sets corresponding to the first knowledge relationship spectra include pre-order meteorological knowledge derivation information and reverse-order meteorological state tracing information;

[0147] (4) performing entity updates based on spatiotemporal modalities on the plurality of first knowledge relationship spectra, respectively, and disassembling the first knowledge relationship spectra according to the connection relationships between entity update information based on spatiotemporal modalities to obtain a plurality of second knowledge relationship spectra, wherein the knowledge relationship feature sets corresponding to the second knowledge relationship spectra include time-domain meteorological knowledge features and space-domain meteorological knowledge features;

[0148] (5) determining at least one meteorological knowledge coverage area based on the preceding meteorological knowledge derivation information and the reverse meteorological state tracing information corresponding to the first knowledge relationship spectrum, and the time-domain meteorological knowledge features and the space-domain meteorological knowledge features corresponding to the second knowledge relationship spectrum;

[0149] (6) performing iterative decomposition based on the entity update information based on the weather pattern and the entity update information based on the spatiotemporal modality within the meteorological knowledge coverage area;

[0150] (7) On the basis that there is no new knowledge relationship spectrum under the entity update information based on the weather pattern, or the number of knowledge relationship spectra under the entity update information based on the spatiotemporal modality is not greater than a set number, the weather pattern in the meteorological environment information is judged based on the decomposition order of the knowledge relationship spectrum to obtain the weather pattern authentication sample set.

[0151] When explaining this standalone implementation in detail, we'll use a specific scenario to illustrate how the big data system obtains a set of certified weather pattern samples corresponding to airborne detection data samples. This process not only involves in-depth analysis of airborne detection data, but also integrates multi-dimensional correlation and iterative decomposition of meteorological knowledge to ensure the accuracy and comprehensiveness of the certified weather pattern sample set.

[0152] First, the big data system extracts meteorological environmental information from airborne detection data. This information includes a wealth of meteorological data, such as temperature, humidity, wind speed, and direction, as well as training annotations corresponding to weather patterns. These annotations, generated by meteorological experts based on historical data and professional knowledge, provide a crucial reference for subsequent weather pattern forecasts.

[0153] Next, the big data system transforms the airborne detection data samples into a meteorological monitoring network. This network is a complex network of meteorological data associations, consisting of a meteorological status subnetwork and an anomaly warning subnetwork. The meteorological status subnetwork primarily describes the interrelationships and mechanisms between different meteorological elements, while the anomaly warning subnetwork focuses on identifying possible meteorological anomalies and potential risks.

[0154] The big data system then updates the entities in the meteorological monitoring network based on weather patterns. This process essentially updates the entities in the network based on the latest meteorological data to reflect current weather pattern trends. New connections are formed between the updated entity information. Based on these connections, the big data system disassembles the meteorological monitoring network to obtain several first-order knowledge relationship spectra. Each first-order knowledge relationship spectra corresponds to a knowledge relationship feature set, which contains pre-order meteorological knowledge derivation information and reverse-order meteorological state tracing information. Pre-order meteorological knowledge derivation information refers to the causes and processes that led to the current meteorological state, while reverse-order meteorological state tracing information describes the future meteorological state that may evolve from the current state.

[0155] Subsequently, the big data system updates each first knowledge relationship spectrum based on the spatiotemporal modality. Spatiotemporal modality refers to the distribution and change characteristics of meteorological data in time and space. By updating entities based on the spatiotemporal modality, the big data system can more accurately capture the dynamic changes of meteorological data in time and space. The updated entity information is once again connected, and the big data system disassembles the first knowledge relationship spectrum based on these connection relationships to obtain several second knowledge relationship spectra. The knowledge relationship feature set corresponding to each second knowledge relationship spectrum includes time-domain meteorological knowledge features and space-domain meteorological knowledge features. The time-domain meteorological knowledge features describe the change patterns of meteorological data in the time dimension, while the space-domain meteorological knowledge features reflect the characteristics of meteorological data in spatial distribution.

[0156] After obtaining the first and second knowledge relationship spectra, the big data system determines at least one meteorological knowledge coverage area based on their corresponding knowledge relationship feature sets. These coverage areas represent the impact of the current weather pattern within the meteorological knowledge space. The big data system iteratively decomposes the meteorological knowledge coverage area, gradually refining the knowledge relationship spectra based on weather pattern entity update information and spatiotemporal modal entity update information. This process continues until no new knowledge relationship spectra are generated under weather pattern entity update information, or until the number of knowledge relationship spectra under spatiotemporal modal entity update information does not exceed a set number.

[0157] Finally, after the decomposition is complete, the big data system identifies the weather patterns within the meteorological environmental information based on the order in which the knowledge relationship spectrum was decomposed. This process comprehensively considers multiple dimensions, including information derived from pre-sequential meteorological knowledge, information traced back to previous meteorological states, and features of temporal and spatial meteorological knowledge, ensuring the accuracy and comprehensiveness of weather pattern authentication. After authentication, the big data system generates a set of authenticated weather pattern examples, which provide important training data and evaluation criteria for subsequent weather pattern prediction algorithms.

[0158] This implementation not only enables in-depth analysis and processing of airborne detection data, but also ensures the accuracy and comprehensiveness of the weather pattern certification sample set through multi-dimensional meteorological knowledge association and iterative decomposition. This technical solution not only improves the accuracy and reliability of weather pattern forecasts but also provides a new approach and method for meteorological data analysis, with significant application value and promotional significance.

[0159] In other independent embodiments, the meteorological monitoring relationship network is updated based on the weather pattern to obtain entity update information based on the weather pattern, including: obtaining past airborne detection data, the past airborne detection data including the meteorological parameters and status information of the current flight area; matching the past airborne detection data with entities in the meteorological monitoring relationship network to determine key entities directly related to the current weather pattern; dynamically updating the status of key entities based on the past airborne detection data and a preset weather pattern model to reflect the meteorological characteristics of the current weather pattern; during the entity update process, recording meteorological parameters and status information related to the key entity status changes to form entity update information based on the weather pattern; the weather pattern-based entity update information includes the update status of the key entity, update time, associated meteorological parameter changes, and weather pattern feature description, which are used for subsequent meteorological knowledge relationship decomposition and weather pattern discrimination.

[0160] In this embodiment, the big data system first acquires past airborne detection data, which contains meteorological parameters and status information for the current flight area. These meteorological parameters may include temperature, humidity, wind speed, and wind direction, while the status information reflects the state of different meteorological elements at a specific point in time. Next, the big data system matches the past airborne detection data with entities in the meteorological monitoring network. The meteorological monitoring network is a complex network of meteorological data associations that includes multiple meteorological entities, such as pressure systems, wind fields, and precipitation clouds. Through this matching process, the system identifies key entities directly related to the current weather pattern. After identifying these key entities, the big data system dynamically updates the status of these key entities based on past airborne detection data and a pre-set weather pattern model. The weather pattern model is a trained and optimized mathematical model that predicts changing weather patterns based on meteorological data. By applying this model, the system updates the status of key entities based on past airborne detection data to reflect the meteorological characteristics of the current weather pattern. During the entity update process, the big data system records the meteorological parameters and status information related to the key entity status changes. This information includes the update status of key entities, update time, associated meteorological parameter changes, and weather pattern characteristics. This information is crucial for the subsequent decomposition of meteorological knowledge relationships and weather pattern identification, as it provides important clues about the formation and evolution of weather patterns.

[0161] In this way, the big data system updates entities in the meteorological monitoring network based on weather patterns and spatiotemporal modalities and generates corresponding entity update information. This entity update information not only provides detailed information about current weather patterns and historical meteorological data, but also provides strong data support for subsequent meteorological knowledge relationship decomposition and weather pattern forecasting. Specifically, by updating the entity states in the meteorological monitoring network in real time, the system can more accurately reflect the changing trends of current weather patterns and meteorological conditions, thereby improving the accuracy of weather pattern forecasts. Entity update information based on weather patterns and spatiotemporal modalities provides pilots and airlines with rich meteorological data support, helping them make more informed flight decisions. By deeply exploring the knowledge relationships and weather pattern characteristics in meteorological data, the system can provide more comprehensive and accurate information support for meteorological services, optimizing the quality and efficiency of meteorological services.

[0162] Further, Figure 2 This is a schematic diagram of the structure of a big data system 200 provided in an embodiment of the present application. Figure 2 The big data system 200 shown includes a processor 210, which can call and run a computer program from a memory to implement the method in the embodiment of the present application. Figure 2As shown, the big data system 200 may further include a memory 230. The processor 210 may call and run a computer program from the memory 230 to implement the method in the embodiment of the present application. The memory 230 may be a separate device independent of the processor 210 or may be integrated into the processor 210. Optionally, as Figure 2 As shown, big data system 200 may also include a transceiver 220. Processor 210 may control transceiver 220 to interact with other devices. Specifically, it may send information or data to other devices or receive information or data sent by other devices. Optionally, big data system 200 may implement the corresponding processes corresponding to the storage engine, components within the storage engine (such as processing modules), or devices deployed with the storage engine in the various methods of the embodiments of this application. For the sake of brevity, these processes are not further described here.

[0163] Based on the above, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program implements the above method when running.

[0164] The above are merely examples of the present application and are not intended to limit the present application. For those skilled in the art, the present application may be subject to various modifications and variations.

Claims

1. A method for analyzing airborne detection data for intelligent meteorology, characterized in that: Applied to a big data system, the method comprises: Acquire airborne detection data, the airborne detection data being meteorological detection data whose weather pattern is to be predicted, the weather pattern being used to characterize meteorological state changes of multidimensional meteorological data in the airborne detection data, the airborne detection data being decomposed into a plurality of first data scan sets by a data scan core of a first dimension, the airborne detection data being decomposed into a plurality of data units by a second dimension, the first dimension being greater than the second dimension; Determining first aviation meteorological embedded state vectors corresponding to the plurality of data units respectively according to meteorological characteristic correlations between the plurality of data units in the plurality of first data scan sets; The data scanning core of the first dimension is adjusted by setting a step length in the airborne detection data, and the airborne detection data is re-disassembled into a plurality of second data scanning sets; Determining second aviation meteorological embedded state vectors corresponding to the plurality of data units respectively according to meteorological feature correlations between the first aviation meteorological embedded state vectors in the plurality of second data scan sets; Predicting the weather pattern in the airborne detection data according to the second aviation meteorological embedded state vector to obtain a weather pattern prediction label corresponding to the airborne detection data, wherein the weather pattern prediction label is used to characterize a prediction result of the airborne detection data relative to a flight safety weather state; The method of determining the first aviation meteorological embedded state vectors corresponding to the data units in the first data scan set respectively based on the meteorological feature correlations between the data units in the first data scan set includes: determining the first aviation meteorological focus features corresponding to the data units in the first data scan set according to the linkage feature focusing strategy; performing interval numerical mapping on the first aviation meteorological focus features corresponding to the data units respectively to obtain first aviation meteorological interval quantitative features; performing residual connection processing on the first aviation meteorological interval quantitative features through a deep residual network to obtain the first aviation meteorological embedded state vector; The method of determining the second aviation meteorological embedded state vectors corresponding to the plurality of data units respectively based on the meteorological feature correlation between the first aviation meteorological embedded state vectors in the plurality of second data scan sets includes: determining the second aviation meteorological focus features corresponding to the first aviation meteorological embedded state vectors in the second data scan set according to the linkage feature focusing strategy; performing interval numerical mapping on the second aviation meteorological focus features corresponding to the plurality of data units respectively to obtain second aviation meteorological interval quantitative features; and performing residual connection processing on the second aviation meteorological interval quantitative features through a deep residual network to obtain the second aviation meteorological embedded state vector.

2. The method according to claim 1, characterized in that: The determining, according to the linkage feature focusing strategy, the first aviation meteorological focus feature corresponding to the data unit in the first data scan set includes: Extracting local aviation meteorological embedded state vectors corresponding to the plurality of data units in the airborne detection data; Determine the local aviation meteorological state correlation between the u-th local aviation meteorological embedded state vector corresponding to the u-th data unit in the first data scan set and the v-th local aviation meteorological embedded state vector corresponding to the v-th data unit, where u and v are positive integers; For the u-th data unit in the first data scan set, the correlation between the local aviation meteorological state corresponding to the u-th data unit in the first data scan set is used as the reinforcement coefficient, and the local aviation meteorological embedded state vector of the data unit in the first data scan set is feature enhanced to obtain the first aviation meteorological focus feature corresponding to the u-th data unit.

3. The method according to claim 1, characterized in that The airborne detection data is decomposed into x first data scan sets by the data scan core of the first dimension, where x is a positive integer; The determining, according to the linkage feature focusing strategy, the second aviation meteorological focus feature corresponding to the first aviation meteorological embedded state vector in the second data scan set includes: Determine that the number of the second data scan sets obtained by disassembling the airborne detection data after the data scan core of the first dimension wanders is y, where y is a positive integer and y>x; Performing cross-matching based on time series features on the data units in the second data scan set to obtain x third data scan sets; Determining the second aviation meteorological focus feature corresponding to the first aviation meteorological embedded state vector in the third data scan set according to the linkage feature focusing strategy; The determining, according to the linkage feature focusing strategy, the second aviation meteorological focus feature corresponding to the first aviation meteorological embedded state vector in the third data scan set includes: Acquire the timing cross-matching information corresponding to the p-th third data scan set, where the timing cross-matching information is used to characterize the timing continuity of the second data scan set after cross-matching, where p is a positive integer, p≤x; Acquire aviation status labeling information corresponding to the p-th third data scan set according to the time series cross-matching information; Determining the embedding vector commonality value between the first aviation meteorological embedded state vectors in the third data scan set according to the linkage feature focusing strategy; Weighting the embedding vector commonality value and the aviation state annotation information to obtain an aviation state weighted commonality value; Based on the aviation state weighted commonality value, feature enhancement is performed on the first aviation meteorological embedded state vector of the data unit in the third data scan set to obtain a second aviation meteorological focus feature.

4. The method according to any one of claims 1 to 2, characterized in that: The step size of the data scanning core of the first dimension is adjusted in the airborne detection data, and the airborne detection data is re-disassembled into a plurality of second data scanning sets, including: Walking the data scanning core of the first dimension at intervals of w data units on a first walking path corresponding to the airborne detection data; Walk the data scanning core of the first dimension at intervals of r data units on the second walking path corresponding to the airborne detection data to determine the plurality of second data scanning sets; Wherein, w and r are positive integers.

5. The method according to any one of claims 1 to 2, characterized in that: The step of predicting the weather pattern in the airborne detection data according to the second aviation meteorological embedded state vector to obtain a weather pattern prediction label corresponding to the airborne detection data includes: Acquire an aviation mission description feature, where the aviation mission description feature is used to assist in predicting a weather pattern corresponding to the airborne detection data; Inputting the aviation mission description feature and the second aviation weather embedded state vector into a pre-debugged aviation weather forecast network to obtain the weather pattern forecast label; The step of inputting the aviation mission description feature and the second aviation meteorological embedded state vector into a pre-debugged aviation meteorological forecast network to obtain the weather pattern forecast label comprises: Inputting the aviation mission description feature and the second aviation meteorological embedded state vector into a pre-debugged aviation meteorological prediction network to obtain meteorological state bias prediction information of the aviation meteorological prediction network; Obtaining a set label index indication, where the label index indication is used to match and output forecast keywords that meet target aviation weather requirements; The meteorological state bias prediction information is updated according to the label index indication to obtain the weather pattern prediction label.

6. The method according to any one of claims 1 to 2, characterized in that: The weather mode prediction label includes the meteorological state jump type, meteorological state distribution characteristics and meteorological state risk characteristics of the weather mode. After predicting the weather mode in the airborne detection data according to the second aviation meteorological embedded state vector and obtaining the weather mode prediction label corresponding to the airborne detection data, the method further includes: Based on the meteorological state distribution characteristics indicated by the weather pattern prediction tag, the airborne detection data is disassembled into local airborne detection results corresponding to a plurality of weather patterns respectively; According to the meteorological state jump type indicated by the weather pattern prediction tag, predict the state jump characteristics in the local airborne detection result, and generate state jump mapping data corresponding to the local airborne detection result; According to the meteorological state risk characteristics indicated by the weather mode forecast label, the state jump mapping data corresponding to the several weather modes are judged to generate an aviation risk judgment viewpoint.

7. The method according to any one of claims 1 to 2, characterized in that: The method is implemented by a pre-debugged weather pattern prediction algorithm, which is debugged by a prediction algorithm to be debugged, and the debugging process of the prediction algorithm to be debugged includes: Acquire an airborne detection data sample and a weather pattern certification sample set corresponding to the airborne detection data sample, wherein the weather pattern certification sample set is used to characterize a weather pattern training annotation chain corresponding to the airborne detection data sample; Inputting the airborne detection data samples into the prediction algorithm to be debugged to generate weather pattern prediction training results; According to the difference between the weather pattern prediction training result and the weather pattern authentication sample set, the prediction algorithm to be debugged is debugged in a loop to obtain the weather pattern prediction algorithm.

8. A big data system, characterized in that: The method comprises at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method according to any one of claims 1 to 7.

Images