A method and system for storing meteorological data of various structures

Abstract

This application relates to the field of data processing technology, and in particular provides a method and system for storing multi-type structured meteorological data. By conducting in-depth analysis of the target multi-mode meteorological monitoring data to be stored, and using meteorological type tags to accurately identify key information, unified storage according to preset storage standards is achieved. This not only solves the problem of inconsistent data attributes, but also significantly improves the flexibility and uniformity of data storage through a series of technical means, such as data splitting, enhanced processing, and structured attribute vector recognition. The embodiments of this application aim to provide a more efficient and convenient solution for the integration, management, and application of meteorological data, thereby promoting the continuous development of meteorological research and related applications.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method and system for storing meteorological data of various structures. Background Technology

[0002] In the field of meteorological monitoring, with the continuous advancement of technology, it is possible to acquire meteorological data of various structural types. However, these data are often difficult to store and manage uniformly due to their inconsistent attributes, causing great inconvenience to subsequent data analysis and applications. Traditional data storage methods often fall short when faced with such multimodal and multi-attribute meteorological data, failing to meet the high requirements of modern meteorological research for data flexibility and uniformity. Summary of the Invention

[0003] To address the aforementioned issues, this application provides a method and system for storing meteorological data in various structural formats.

[0004] This application provides a method for storing meteorological data with multiple structural types, applied to a data storage system. The method includes:

[0005] Obtain the target multi-mode meteorological monitoring data to be stored, and the meteorological type label corresponding to the target multi-mode meteorological monitoring data. The meteorological type label is used to describe the structured meteorological attribute feature set of the target multi-mode meteorological monitoring data.

[0006] The target multi-mode meteorological monitoring data is split into data to obtain the meteorological monitoring dataset of the target multi-mode meteorological monitoring data, and the meteorological monitoring dataset is enhanced to obtain the enhanced meteorological monitoring dataset.

[0007] Based on the meteorological type labels, the enhanced meteorological monitoring dataset is subjected to X rounds of structured attribute vector recognition using a structured storage analysis algorithm to obtain the target structured meteorological attribute feature set of the target multi-mode meteorological monitoring data;

[0008] Specifically, during the Y-round structured attribute vector identification in the X-round structured attribute vector identification, the transitional meteorological state one-hot encoding of the structured storage analysis algorithm is mapped to the meteorological state transmission network obtained in the target multi-mode meteorological monitoring data. After vector integration of the meteorological state one-hot encodings of at least Z network units in the meteorological state transmission network with the meteorological state one-hot encodings of their corresponding neighboring network units, these are used as the objects to be processed in the next algorithm branch of the structured storage analysis algorithm. The Z network units include the network units corresponding to the modality identifiers when the target multi-mode meteorological monitoring data is split. X and Z are both positive integers, and Y is a positive integer not greater than X.

[0009] Preferably, based on the meteorological type label, the enhanced meteorological monitoring dataset is subjected to X rounds of structured attribute vector recognition using a structured storage analysis algorithm to obtain the target structured meteorological attribute feature set of the target multi-mode meteorological monitoring data, including:

[0010] In the u-th round of structured attribute vector recognition, the first transitional meteorological state unique thermal code generated by the v-th algorithm branch of the structured storage analysis algorithm is obtained. The first transitional meteorological state unique thermal code is obtained based on the enhanced meteorological monitoring dataset and the meteorological type label, where v is a positive integer and u is a positive integer not greater than X.

[0011] When the u-th round of structured attribute vector identification belongs to the Y-th round of structured attribute vector identification, the first transitional meteorological state unique thermal code is mapped to the target multi-mode meteorological monitoring data to obtain the meteorological state transmission network, and the meteorological state unique thermal codes of Z network units in the meteorological state transmission network are weighted with the meteorological state unique thermal codes of the corresponding neighboring network units to obtain the first meteorological state weighted unique thermal code;

[0012] Based on the weighted one-hot encoding of the first meteorological state, the one-hot encoding to be processed in the (v+1)th branch of the structured storage analysis algorithm is determined, and further identification processing is performed to obtain the uth intermediate structured meteorological attribute feature set of the target multi-mode meteorological monitoring data.

[0013] Based on the meteorological type label, the structured attribute vector of the intermediate structured meteorological attribute feature set of the uth round is identified in the (u+1)th round using the structured storage analysis algorithm to obtain the target structured meteorological attribute feature set.

[0014] Preferably, obtaining the unique thermal code of the first transitional meteorological state generated by the v-th algorithm branch of the structured storage analysis algorithm includes:

[0015] Obtain the (u-1)th round intermediate structured meteorological attribute feature set of the target multi-mode meteorological monitoring data;

[0016] Based on the meteorological type label and the intermediate structured meteorological attribute feature set of the (u-1)th round, the unique thermal code of the first transitional meteorological state generated by the vth algorithm branch is obtained.

[0017] Preferably, the step of acquiring the (u-1)th round intermediate structured meteorological attribute feature set of the target multi-mode meteorological monitoring data includes:

[0018] In response to u equaling 1, the enhanced meteorological monitoring dataset is determined as the intermediate structured meteorological attribute feature set of the (u-1)th round;

[0019] In response to u being greater than 1, the structured attribute vector identification of the enhanced meteorological monitoring dataset is performed in the (u-1)th round using the structured storage analysis algorithm based on the meteorological type label, thereby obtaining the intermediate structured meteorological attribute feature set in the (u-1)th round.

[0020] Preferably, the step of obtaining the unique thermal encoding of the first transitional meteorological state generated by the v-th algorithm branch based on the meteorological type label and the intermediate structured meteorological attribute feature set of the (u-1)th round includes:

[0021] When the v-th algorithm branch is the first algorithm branch of the structured storage analysis algorithm, the meteorological type label and the intermediate structured meteorological attribute feature set of the u-1th round are processed through the v-th algorithm branch to obtain the unique thermal encoding of the first transitional meteorological state.

[0022] When the v-th algorithm branch is a transitional algorithm branch of the structured storage analysis algorithm, the second transitional meteorological state unique thermal code generated by the (v-1)-th algorithm branch of the structured storage analysis algorithm is obtained, and the unique thermal code to be processed of the v-th algorithm branch is determined based on the second transitional meteorological state unique thermal code. The unique thermal code to be processed of the v-th algorithm branch is processed by the v-th algorithm branch to obtain the first transitional meteorological state unique thermal code.

[0023] Preferably, the step of processing the meteorological type label and the intermediate structured meteorological attribute feature set of the (u-1)th round through the v-th algorithm branch to obtain the unique thermal encoding of the first transitional meteorological state includes:

[0024] Mine the unique thermal code of the meteorological type label;

[0025] Mining the linear meteorological state one-heat encoding of the intermediate structured meteorological attribute feature set in the (u-1)th round;

[0026] The first transitional meteorological state unique code is obtained by processing the meteorological type one-hot encoding of the meteorological type label and the linear meteorological state one-hot encoding of the intermediate structured meteorological attribute feature set in the (u-1)th round through the v-th algorithm branch.

[0027] Preferably, determining the one-hot code to be processed for the vth algorithm branch based on the one-hot code of the second transitional meteorological state includes:

[0028] The unique thermal code of the second transitional meteorological state is determined as the unique thermal code to be processed in the v-th algorithm branch;

[0029] Alternatively, the second transitional meteorological state one-hot encoding is mapped to the target multi-mode meteorological monitoring data to obtain the meteorological state transmission network. The meteorological state one-hot encodings of the Z network units in the meteorological state transmission network are weighted with the meteorological state one-hot encodings of their corresponding neighboring network units to obtain the second meteorological state weighted one-hot encoding. Based on the second meteorological state weighted one-hot encoding, the one-hot encoding to be processed for the vth algorithm branch is determined.

[0030] Preferably, the one-hot encoding of the meteorological state of Z network units in the meteorological state transmission network is weighted with the one-hot encoding of the meteorological state of their corresponding neighboring network units to obtain the weighted one-hot encoding of the target meteorological state, including:

[0031] For each of the Z network units, the meteorological state one-hot code of the network unit is weighted with the meteorological state one-hot code of the neighboring network units to obtain the current meteorological state one-hot code of the network unit, thus obtaining the meteorological state transmission network after vector integration.

[0032] Based on the meteorological state transmission network after vector integration, the target meteorological state weighted monothermal code is obtained, which is either a first meteorological state weighted monothermal code or a second meteorological state weighted monothermal code.

[0033] Preferably, obtaining the weighted one-heat code of the target meteorological state based on the vector-integrated meteorological state transmission network includes: performing feature encoding on the vector-integrated meteorological state transmission network based on the meteorological monitoring dataset to obtain the weighted one-heat code of the target meteorological state.

[0034] Preferably, the step of performing feature encoding on the vector-integrated meteorological state transmission network based on the meteorological monitoring dataset to obtain the weighted one-heat encoding of the target meteorological state includes:

[0035] Based on the feature encoding rules between the meteorological monitoring dataset and the target multi-mode meteorological monitoring data, the meteorological state transmission network after vector integration is mapped to the meteorological monitoring dataset to obtain the third meteorological state weighted one-heat encoding.

[0036] The weighted unique thermal code of the target meteorological state is obtained based on the weighted unique thermal code of the third meteorological state.

[0037] Preferably, obtaining the target meteorological state weighted unique thermal code based on the third meteorological state weighted unique thermal code includes: adjusting the dimensions of the third meteorological state weighted unique thermal code based on the dimension information of the target transition meteorological state unique thermal code to obtain the target meteorological state weighted unique thermal code;

[0038] Wherein, the dimension of the target meteorological state weighted unique thermal code is consistent with the dimension of the target transition meteorological state unique thermal code. When the target transition meteorological state unique thermal code is the first transition meteorological state unique thermal code, then the target meteorological state weighted unique thermal code is the first meteorological state weighted unique thermal code. When the target transition meteorological state unique thermal code is the second transition meteorological state unique thermal code, then the target meteorological state weighted unique thermal code is the second meteorological state weighted unique thermal code.

[0039] Preferably, based on the weighted one-hot encoding of the target meteorological state, the one-hot encoding to be processed in the target algorithm branch is determined, including:

[0040] The weighted one-hot code of the target meteorological state is used as the one-hot code to be processed in the target algorithm branch; or, the one-hot code of the target transition meteorological state and the weighted one-hot code of the target meteorological state are weighted to obtain the one-hot code to be processed in the target algorithm branch.

[0041] Specifically, when the target algorithm branch is the (v+1)th algorithm branch, the target meteorological state weighted unique thermal encoding is the first meteorological state weighted unique thermal encoding, and the target transition meteorological state unique thermal encoding is the first transition meteorological state unique thermal encoding. When the target algorithm branch is the vth algorithm branch, the target meteorological state weighted unique thermal encoding is the second meteorological state weighted unique thermal encoding, and the target transition meteorological state unique thermal encoding is the second transition meteorological state unique thermal encoding.

[0042] Preferably, the step of weighting the one-hot encoding of the target transitional meteorological state and the weighted one-hot encoding of the target meteorological state to obtain the one-hot encoding to be processed for the target algorithm branch includes:

[0043] Determine the confidence coefficients corresponding to the one-thermal code of the target transitional meteorological state and the weighted one-thermal code of the target meteorological state, respectively;

[0044] Based on the confidence coefficients corresponding to the target transitional meteorological state one-hot encoding and the target meteorological state weighted one-hot encoding, the target transitional meteorological state one-hot encoding and the target meteorological state weighted one-hot encoding are weighted to obtain the object to be processed in the target algorithm branch.

[0045] Preferably, determining the confidence coefficients corresponding to the one-thermal code of the target transitional meteorological state and the weighted one-thermal code of the target meteorological state includes:

[0046] By employing a feature-focusing strategy, the one-hot encoding and weighted one-hot encoding of the target transitional meteorological state are processed to obtain the confidence coefficients corresponding to the one-hot encoding and weighted one-hot encoding of the target transitional meteorological state, respectively.

[0047] Preferably, the method further includes:

[0048] When the u-th round of structured attribute vector identification does not belong to the Y-th round of structured attribute vector identification, the first transitional meteorological state unique thermal code is determined as the unprocessed unique thermal code of the v+1-th algorithm branch of the structured storage analysis algorithm.

[0049] This application provides a data storage system, including at least one processor and a memory; the memory stores computer execution instructions; the at least one processor executes the computer execution instructions stored in the memory, causing the at least one processor to perform the above-described method.

[0050] This application provides a computer-readable storage medium having a computer program stored thereon, which implements the above-described method when run.

[0051] In this embodiment, by conducting in-depth analysis of the target multi-mode meteorological monitoring data to be stored and accurately identifying key information using meteorological type tags, unified storage according to preset storage standards is achieved. This not only solves the problem of inconsistent data attributes but also significantly improves the flexibility and uniformity of data storage through a series of technical means, such as data splitting, enhanced processing, and structured attribute vector recognition. This embodiment aims to provide a more efficient and convenient solution for the integration, management, and application of meteorological data, thereby promoting the continuous development of meteorological research and related applications. Attached Figure Description

[0052] Figure 1 This is a flowchart illustrating a meteorological multi-type structure data storage method provided in an embodiment of this application.

[0053] Figure 2 This is a schematic diagram of the structure of a data storage system provided in an embodiment of this application. Detailed Implementation

[0054] To better understand the above technical solutions, the technical solutions of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this application and the specific features in the embodiments are detailed descriptions of the technical solutions of this application, rather than limitations on the technical solutions of this application. In the absence of conflict, the embodiments of this application and the technical features in the embodiments can be combined with each other.

[0055] Figure 1 A method for storing meteorological data of various structures is presented and applied to a data storage system. The method includes the following steps 110-130.

[0056] In an exemplary meteorological monitoring application scenario, the data storage system is responsible for acquiring, processing, and structuring multi-mode meteorological monitoring data.

[0057] Step 110: Obtain the target multi-mode meteorological monitoring data to be stored, and the meteorological type label corresponding to the target multi-mode meteorological monitoring data. The meteorological type label is used to describe the structured meteorological attribute feature set of the target multi-mode meteorological monitoring data.

[0058] First, in step 110, the data storage system acquires the target multi-mode meteorological monitoring data to be stored from various meteorological monitoring devices. The target multi-mode meteorological monitoring data may include meteorological information in multiple modes, such as temperature, humidity, wind speed, wind direction, and air pressure. Simultaneously, the data storage system also acquires meteorological type labels corresponding to the target multi-mode meteorological monitoring data. These meteorological type labels describe the structured meteorological attribute feature set of the target multi-mode meteorological monitoring data, such as "high temperature and high humidity" or "low wind speed," which is helpful for subsequent data processing and analysis.

[0059] In detail, the target multi-mode meteorological monitoring data to be stored refers to the raw data collected from various meteorological monitoring devices. This data contains meteorological information in multiple modes. For example, temperature data reflects the heat of the environment, humidity data reflects the moisture content in the air, wind speed and direction data reveals the intensity and direction of the wind, and air pressure data shows changes in atmospheric pressure. These data modes are independent yet interconnected, collectively constituting complex and ever-changing meteorological conditions. Because this data originates from different monitoring devices and sensors, it is called "multi-mode" data, that is, a collection of data of multiple modes and types. This data is crucial for applications such as meteorological analysis, forecasting, and disaster early warning.

[0060] Meteorological type labels are keywords or phrases used to classify and describe multi-mode meteorological monitoring data. They are defined based on specific characteristics and attributes of the data, and are used to summarize and identify the overall meteorological conditions. For example, a label like "high temperature and high humidity" might indicate that both temperature and humidity reached high levels within a certain time period, while a label like "low wind speed" indicates low wind speed conditions. These labels not only help to quickly understand the core characteristics of the data but also provide important reference for subsequent data processing and analysis. Through meteorological type labels, researchers can more efficiently screen, compare, and analyze different types of meteorological data.

[0061] Structured meteorological attribute feature sets are a set of key features extracted after in-depth analysis and processing of multi-mode meteorological monitoring data. These features are presented in a structured form, meaning they are organized into a set of attributes with clear meanings and interrelationships. For example, temperature, humidity, and wind speed can all be part of structured meteorological attributes. These attributes not only reflect the core information of meteorological data but also facilitate quantitative analysis and comparison. By extracting and integrating these structured features, researchers can gain a deeper understanding of the inherent patterns and trends in meteorological data, providing strong data support for applications such as weather forecasting and disaster early warning.

[0062] Step 110 is understandably the primary step in the meteorological data processing of the data storage system. Its core task is to acquire the target multi-mode meteorological monitoring data to be stored, and simultaneously obtain the corresponding meteorological type labels for this data. In this step, the data storage system first receives or periodically collects multi-mode meteorological monitoring data from meteorological monitoring equipment located in various locations through various interfaces and protocols. This data covers a variety of key meteorological parameters such as temperature, humidity, wind speed, wind direction, and air pressure, forming the basis for subsequent analysis and forecasting. Simultaneously, the data storage system also acquires the meteorological type labels corresponding to this data. These labels are typically generated by meteorological experts or automated algorithms based on the characteristics of the data, and are used to concisely describe the overall meteorological conditions of the data. For example, if the data for a certain period shows characteristics of high temperature and high humidity, then the data for that period might be labeled as "high temperature and high humidity." The acquired meteorological type labels not only help researchers quickly understand the overall characteristics of the data but also provide important classification criteria for subsequent data processing and analysis. Through these labels, the data storage system can more efficiently organize and manage massive amounts of meteorological data, providing accurate and targeted data support for subsequent applications such as weather forecasting and disaster early warning. Therefore, step 110 is a crucial step in ensuring that the data storage system can comprehensively and accurately acquire and understand multi-mode meteorological monitoring data, laying a solid foundation for subsequent data processing and analysis.

[0063] Step 120: Split the target multi-mode meteorological monitoring data to obtain the meteorological monitoring dataset of the target multi-mode meteorological monitoring data, and perform enhancement processing on the meteorological monitoring dataset to obtain the enhanced meteorological monitoring dataset.

[0064] Next, in step 120, the data storage system splits the acquired target multimodal meteorological monitoring data. The purpose of this step is to decompose the complex multimodal data into meteorological monitoring datasets that are easier to process and analyze. For example, wind speed data and wind direction data may be stored and processed separately. After data splitting, the data storage system enhances these meteorological monitoring datasets, such as performing data cleaning, outlier detection and correction, to improve data quality and accuracy, thereby obtaining enhanced meteorological monitoring datasets.

[0065] In detail, a meteorological monitoring dataset refers to a collection and organization of data from various meteorological monitoring devices. This data encompasses a variety of meteorological parameters, such as temperature, humidity, wind speed, wind direction, and air pressure. It is systematically organized and stored for subsequent data analysis and meteorological research. Meteorological monitoring datasets are a crucial foundation for meteorological research, weather forecasting, and climate model building. By analyzing these datasets, scientists can better understand atmospheric dynamics, predict future weather conditions, and even assess the impacts of climate change.

[0066] In the context of data processing, data enhancement refers to a series of optimization and correction operations performed on raw data to improve its quality and usability. This process may include data cleaning (removing invalid or erroneous data points); outlier detection and correction to ensure all values ​​in the dataset are within reasonable ranges; data smoothing to reduce the impact of noise and fluctuations on the analysis results; and possible data transformation or standardization to make the data more suitable for specific analytical needs. Data enhancement is a crucial step before data analysis, ensuring the accuracy and effectiveness of subsequent analyses.

[0067] Enhanced meteorological monitoring datasets refer to collections of meteorological data that have undergone enhancement processing. These datasets have been cleaned, validated, and potentially transformed to ensure their quality, accuracy, and consistency, making them more suitable for advanced data analysis and model building. Enhanced meteorological monitoring datasets are key inputs for applications such as weather forecasting, climate research, and disaster early warning, as they provide a reliable and optimized data foundation that supports more precise scientific analysis and decision-making.

[0068] In step 120, the core task of the data storage system is to process and optimize the raw multi-mode meteorological data collected from meteorological monitoring equipment. First, the system splits the "target multi-mode meteorological monitoring data." Since this data typically contains multiple meteorological parameters, such as temperature, humidity, and wind speed, it needs to be decomposed appropriately for separate processing and analysis. The data splitting process is based on the modal characteristics of the data, ensuring that data from each modality can be extracted and processed individually. After data splitting, the system obtains multiple single-modality "meteorological monitoring datasets." These datasets correspond to different meteorological parameters and have undergone preliminary sorting and formatting, laying the foundation for subsequent data processing. Next, the system performs "enhancement processing" on these meteorological monitoring datasets. This process aims to improve the quality and accuracy of the data, ensuring that the datasets do not contain errors, anomalies, or irrelevant information. Enhancement processing may include data cleaning to remove duplicate, invalid, or obviously erroneous data points; outlier detection to identify and correct values ​​outside the normal range; and data standardization or normalization to enable analysis of data from different modalities on the same scale. After enhancement processing, the system obtains "enhanced meteorological monitoring datasets." These datasets are not only cleaner and more accurate, but also optimized, making them more suitable for complex data analysis and model building. The output of this step provides a high-quality data foundation for subsequent structured storage analysis algorithms, and is a key link in ensuring the effectiveness and accuracy of the entire data storage and processing flow.

[0069] Step 130: Based on the meteorological type label, perform X rounds of structured attribute vector recognition on the enhanced meteorological monitoring dataset using a structured storage analysis algorithm to obtain the target structured meteorological attribute feature set of the target multi-mode meteorological monitoring data.

[0070] Specifically, during the Y-round structured attribute vector identification in the X-round structured attribute vector identification, the transitional meteorological state one-hot encoding of the structured storage analysis algorithm is mapped to the meteorological state transmission network obtained in the target multi-mode meteorological monitoring data. After vector integration of the meteorological state one-hot encodings of at least Z network units in the meteorological state transmission network with the meteorological state one-hot encodings of their corresponding neighboring network units, these are used as the objects to be processed in the next algorithm branch of the structured storage analysis algorithm. The Z network units include the network units corresponding to the modality identifiers when the target multi-mode meteorological monitoring data is split. X and Z are both positive integers, and Y is a positive integer not greater than X.

[0071] In step 130, the data storage system uses a structured storage analysis algorithm to perform multiple rounds of structured attribute vector identification on the enhanced meteorological monitoring dataset based on the previously acquired meteorological type labels. During this process, the structured storage analysis algorithm identifies and extracts key structured features from the data. Notably, in one round of structured attribute vector identification, the algorithm maps the one-heat encoding of transitional meteorological states onto the meteorological state transmission network extracted from the target multi-mode meteorological monitoring data. This meteorological state transmission network (which can be understood as a mapping map) reflects the mutual influence and transmission relationships between different meteorological states.

[0072] Subsequently, the structured storage analysis algorithm selects at least Z network units, corresponding to different modes in the original multi-mode meteorological monitoring data splitting. For these selected network units, the algorithm performs vector integration of their one-hot meteorological state codes with those of adjacent network units. This integration takes into account the spatial relationships between meteorological states, helping to improve the accuracy of data analysis. The integrated vector then becomes the object to be processed in the next branch of the structured storage analysis algorithm.

[0073] The entire process will be repeated X times to ensure comprehensive and in-depth data analysis. In this way, the data storage system can not only effectively store large amounts of multi-mode meteorological monitoring data, but also perform efficient structured processing and analysis of this data, providing accurate data support for subsequent applications such as weather forecasting and disaster early warning.

[0074] In detail, structured attribute vector recognition (SAV) is a data processing technique used to extract key structured features from complex datasets. In meteorological monitoring data processing, it specifically refers to identifying and analyzing meteorological attributes in the data using algorithms, transforming these attributes into vector form to facilitate subsequent data analysis, comparison, and storage. This process helps reveal hidden patterns and correlations in the data, providing support for weather forecasting and decision-making.

[0075] The target structured meteorological attribute feature set refers to the collection of key meteorological features extracted from multi-mode meteorological monitoring data through structured attribute vector recognition technology. These features, after structured processing, are represented in vector form and can comprehensively and accurately reflect the key information of the original data, providing strong data support for meteorological analysis, forecasting, and decision-making applications.

[0076] One-hot encoding of transitional weather states is a data representation method used to convert weather states into a computer-processable format. In structured storage analysis, each unique weather state is assigned a unique binary vector with only one element set to 1 and the rest to 0. This encoding method helps algorithms accurately identify different weather states when processing data, thereby improving the accuracy of the analysis.

[0077] Meteorological state transmission networks are a type of mapping graph used to represent the mutual influence and transmission relationships between different meteorological states. In this network, nodes represent different meteorological states, and edges represent the transmission paths between states. By analyzing this network, we can gain a deeper understanding of the dynamic changes and interaction mechanisms within the meteorological system, providing a scientific basis for applications such as weather forecasting and disaster early warning.

[0078] In meteorological state transmission networks, network units refer to the individual nodes or components that make up the network. Each network unit represents a specific meteorological state or attribute and is connected to other units through edges, collectively forming a complex network structure. By analyzing the connections and attribute characteristics between network units, the internal structure and operational laws of the meteorological system can be revealed.

[0079] Modal identifiers are labels or tags used to distinguish and identify different modal information in multimodal meteorological monitoring data. In multimodal data, each modality (such as temperature, humidity, wind speed, etc.) has unique data characteristics and representations. Modal identifiers help algorithms accurately identify and process these different modal information when processing data, thereby improving the efficiency and accuracy of data processing.

[0080] Step 130 is understandably the core component of the data storage system, aiming to deeply mine key information from the enhanced meteorological monitoring dataset using structured storage analysis algorithms. First, based on previously acquired meteorological type labels, the system performs multiple rounds of structured attribute vector identification on the enhanced meteorological monitoring dataset. During this process, the algorithm meticulously analyzes each meteorological attribute in the dataset, transforming it into a meaningful vector form. These vectors not only contain key information from the original data but also facilitate subsequent data processing and analysis. Of particular note is that in X rounds of structured attribute vector identification, one or more rounds involve one-hot encoding of transitional meteorological states. At this stage, the structured storage analysis algorithm represents the identified meteorological states in one-hot encoding form. This encoding method ensures the uniqueness and accuracy of each meteorological state, laying a solid foundation for subsequent data analysis. Next, the algorithm maps these one-hot encodings of transitional meteorological states onto a meteorological state transmission network. This network is a complex mapping graph that clearly demonstrates the mutual influence and transmission relationships between different meteorological states. Through network analysis, a deeper understanding of the internal structure and dynamic changes of the meteorological system can be achieved. During the mapping process, the algorithm selects at least Z network units for further analysis. These network units correspond to different modal identifiers from the original multi-mode meteorological monitoring data splitting. The algorithm then performs vector integration of the one-hot codes of meteorological states of these selected network units with the one-hot codes of meteorological states of their neighboring network units. This integration method comprehensively considers the spatial relationships and mutual influences between meteorological states, thereby improving the accuracy and comprehensiveness of data analysis. Finally, the vector-integrated data becomes the object to be processed in the next branch of the structured storage analysis algorithm. Through continuous iteration and optimization, the algorithm can gradually reveal the deep information and patterns hidden in the multi-mode meteorological monitoring data. The entire X-round structured attribute vector recognition process ensures comprehensive and in-depth data analysis, providing strong data support for subsequent applications such as meteorological forecasting and disaster early warning.

[0081] This application embodiment achieves accurate identification and efficient storage of key information by conducting in-depth analysis of the target multi-mode meteorological monitoring data to be stored and combining it with its corresponding meteorological type labels. This method not only solves the problem of inconsistent attributes among meteorological data of various structural types, but also significantly improves the flexibility and uniformity of data storage through data splitting, enhancement processing, and multi-round structured attribute vector recognition. In particular, during the structured attribute vector recognition process, by cleverly mapping the one-hot encoding of transitional meteorological states to the meteorological state transmission network and performing vector integration of the one-hot encoding of meteorological states in network units, this application embodiment further enhances the ability to analyze and mine the intrinsic correlation of data.

[0082] Compared to existing technologies, the embodiments of this application not only store various types of meteorological data in a single data file according to a unified standard, but also support a series of data-driven functions such as arbitrary attribute expansion, parallel compression and decompression, and encryption and decryption, thereby greatly improving the overall efficiency of data storage and processing. This not only brings revolutionary convenience to the integration and management of meteorological data, but also lays a solid foundation for subsequent data analysis and applications, and is expected to play an important role in fields such as weather forecasting and disaster prevention.

[0083] In some optional embodiments, the step of performing X rounds of structured attribute vector recognition on the enhanced meteorological monitoring dataset based on the meteorological type label, to obtain the target structured meteorological attribute feature set of the target multi-mode meteorological monitoring data, includes: in the u-th round of structured attribute vector recognition, obtaining the first transitional meteorological state one-hot code generated by the v-th algorithm branch of the structured storage analysis algorithm, wherein the first transitional meteorological state one-hot code is obtained based on the enhanced meteorological monitoring dataset and the meteorological type label, where v is a positive integer and u is a positive integer not greater than X; when the u-th round of structured attribute vector recognition belongs to the Y-th round of structured attribute vector recognition, mapping the first transitional meteorological state one-hot code to the target multi-mode meteorological monitoring data. The meteorological state transmission network is obtained from the target multi-mode meteorological monitoring data. The one-hot codes of the meteorological states of the Z network units in the meteorological state transmission network are weighted with the one-hot codes of the meteorological states of their corresponding neighboring network units to obtain the first weighted one-hot codes of the meteorological states. Based on the first weighted one-hot codes of the meteorological states, the one-hot codes to be processed in the (v+1)th branch of the structured storage analysis algorithm are determined and further identification processing is performed to obtain the u-th round intermediate structured meteorological attribute feature set of the target multi-mode meteorological monitoring data. Based on the meteorological type label, the structured storage analysis algorithm is used to perform the (u+1)th round structured attribute vector identification on the u-th round intermediate structured meteorological attribute feature set to obtain the target structured meteorological attribute feature set.

[0084] Based on the above embodiments, the data storage system performs a series of complex operations to process and analyze multi-mode meteorological monitoring data. One of the key steps in this process is to perform multiple rounds of structured attribute vector identification on the enhanced meteorological monitoring dataset using structured storage analysis algorithms.

[0085] For example, when the data storage system reaches the u-th round of structured attribute vector recognition, it first obtains the one-hot code of the first transitional meteorological state generated by the v-th branch of the structured storage analysis algorithm. This one-hot code is derived based on the enhanced meteorological monitoring dataset and the corresponding meteorological type labels. Here, "one-hot coding" is a method of converting categorical variables into a format that machine learning algorithms can better process; in this scenario, it represents a specific meteorological state.

[0086] If the u-th round of structured attribute vector identification happens to belong to one of the Y rounds requiring special processing, the data storage system will perform additional steps. It will map the one-thermal encoding of the first transitional meteorological state onto the meteorological state propagation network extracted from the target multi-mode meteorological monitoring data. This network reveals the connections and influences between different meteorological states.

[0087] Next, the system selects Z network units from the meteorological state transmission network, which correspond to the modal identifiers used during data splitting. Then, the system weights the one-hot codes of the meteorological states of these selected network units and their neighboring network units to obtain the first weighted one-hot code for the meteorological state. Weighting is a mathematical method that considers the importance of different data points; here, it is used to enhance the influence of key meteorological states.

[0088] With this weighted one-hot encoding, the data storage system can determine the one-hot encoding to be processed for the (v+1)th branch of the structured storage analysis algorithm. Subsequently, the system continues the identification process, generating the u-th intermediate structured meteorological attribute feature set of the target multi-mode meteorological monitoring data. This feature set captures the key attributes of the data in this round of processing.

[0089] Finally, based on the meteorological type labels, the data storage system uses a structured storage analysis algorithm to perform the next round of structured attribute vector identification on this intermediate feature set, namely the (u+1)th round. Through these rounds of processing, the system can ultimately extract the target structured meteorological attribute feature set, which is a dataset that comprehensively and accurately describes the core attributes of multi-mode meteorological monitoring data.

[0090] Through the detailed operation of the above embodiments, the data storage system not only achieves efficient processing of multimodal and multi-attribute meteorological data, but also deeply mines key information in the data through multi-round identification using structured storage analysis algorithms. This processing method significantly improves the flexibility and uniformity of data storage, enabling different types of meteorological data to be integrated and stored according to a unified standard. Furthermore, through weighted processing and the application of meteorological state transmission networks, the system further enhances the depth and accuracy of data analysis, providing more reliable data support for subsequent applications such as weather forecasting and disaster early warning. Overall, this embodiment of the data storage system demonstrates an advanced and efficient method for processing multimodal meteorological monitoring data, with beneficial effects reflected in the accuracy of data processing, the uniformity of storage, and the wide applicability of subsequent applications.

[0091] To understand the above technical solution more intuitively, a specific example of a numerical feature vector can be used for detailed explanation.

[0092] For example, there is an enhanced meteorological monitoring dataset containing various meteorological parameters such as temperature, humidity, and wind speed. This data has been preprocessed and enhanced for subsequent structured attribute vector recognition.

[0093] Example:

[0094] Weather type labels: There are three weather type labels: "Sunny", "Rainy", and "Snowy", which can be represented by unique thermal codes as follows:

[0095] Sunny: [1, 0, 0];

[0096] Rainy day: [0, 1, 0];

[0097] Snowy day: [0, 0, 1].

[0098] Structured storage analysis algorithm: Perform 3 rounds (X=3) of structured attribute vector recognition.

[0099] First round of identification (u=1):

[0100] In the first round, the data for "sunny day" was processed, and the unique thermal code for its weather type label is [1, 0, 0].

[0101] The first branch of the structured storage analysis algorithm (v=1) generates a unique thermal code for the first transitional weather state, such as [0.8, 0.1, 0.1], indicating that the current data is more inclined to "sunny".

[0102] Since the first round does not belong to a special Y round, we proceed directly to the next round of identification.

[0103] Second round of identification (u=2, this round is one of the Y rounds):

[0104] In this round, we will continue to process the data for "sunny days," but now we need to consider the weather condition transmission network.

[0105] The network has 5 network units (Z=5), each unit representing a different meteorological observation point.

[0106] Each network unit has a unique thermal code for its weather state. For example, unit 1 is [0.9, 0.05, 0.05], unit 2 is [0.85, 0.1, 0.05], and so on.

[0107] These one-hot codes are weighted with the one-hot codes of their neighboring cells. For example, the weighted one-hot code of cell 1 might be the average of its own code and the codes of its neighboring cells (such as cells 2 and 3).

[0108] After weighting, a weighted unique thermal code for the first meteorological state is obtained, such as [0.87, 0.08, 0.05].

[0109] This weighted one-hot encoding becomes the input to the next algorithm branch (v+1) and continues the recognition process.

[0110] Third round of identification (u=3):

[0111] In this round, the weighted one-hot code obtained in the previous round is used as input.

[0112] The structured storage analysis algorithm continues to process this weighted one-heat encoding and finally outputs a target structured meteorological attribute feature set.

[0113] This feature set may be a more refined description of meteorological conditions, such as a vector containing multiple attributes such as temperature, humidity, and wind speed.

[0114] This example demonstrates how each round of structured attribute vector identification progressively refines and strengthens the features of meteorological data. Particularly in round Y, by considering the meteorological state transmission network and weighted processing, complex relationships and patterns within the data can be captured more accurately. Ultimately, this technical solution helps obtain a comprehensive and accurate set of target structured meteorological attribute features, providing strong support for subsequent meteorological analysis and forecasting.

[0115] In some preferred embodiments, obtaining the first transitional meteorological state unique thermal code generated by the vth algorithm branch of the structured storage analysis algorithm includes: obtaining the u-1th round intermediate structured meteorological attribute feature set of the target multi-mode meteorological monitoring data; and obtaining the first transitional meteorological state unique thermal code generated by the vth algorithm branch based on the meteorological type label and the u-1th round intermediate structured meteorological attribute feature set.

[0116] Based on this embodiment, when the data storage system executes the structured storage analysis algorithm, it obtains the unique thermal code of the first transitional meteorological state generated by the v-th branch of the algorithm. This process is one of the key steps in the algorithm's processing of multi-mode meteorological monitoring data, helping the system to gradually extract the key features of the data.

[0117] In detail, when the data storage system is preparing to perform the u-th round of structured attribute vector recognition, it first reviews and retrieves the intermediate structured meteorological attribute feature set from the previous round, i.e., the (u-1)-th round. This feature set consists of the key meteorological attributes extracted during the previous round of recognition, reflecting the main characteristics of the data at that stage.

[0118] Next, the data storage system analyzes the data by combining the current weather type label with the intermediate structured weather attribute feature set from round u-1. The weather type label provides the system with the overall context of the data, while the intermediate structured weather attribute feature set provides detailed characteristics of the data from the previous stage. By comprehensively considering these two aspects of information, the system can more accurately grasp the current state of the data.

[0119] Then, based on the comprehensive analysis above, the data storage system will obtain the first transitional meteorological state unique thermal code generated by the v-th algorithm branch. This unique thermal code is a temporary, intermediate meteorological state representation, which will be further refined and optimized in subsequent processing.

[0120] For example, the data storage system is processing a round of data on the "rainy day" weather type. In the previous round of identification, the system has extracted some key meteorological attributes related to rainy days, such as humidity and precipitation. When the system reaches the u-th round of identification, it will combine these key attributes with the "rainy day" weather type label to generate a more accurate unique thermal code for the first transitional weather state. This code may not only contain basic information about rainy days but also reflect specific meteorological characteristics extracted in the previous round of identification.

[0121] In this way, the data storage system can more effectively utilize historical identification results and current weather type labels to generate more accurate unique thermal codes for the first transitional weather state. This not only improves the accuracy of data processing but also provides more reliable basic data for subsequent weather state analysis and forecasting. Overall, this embodiment enhances the intelligence and accuracy of the data storage system in processing multi-mode weather monitoring data, providing strong technical support for applications in the meteorological field.

[0122] In some other preferred embodiments, the step of obtaining the (u-1)th round intermediate structured meteorological attribute feature set of the target multi-mode meteorological monitoring data includes: in response to u equaling 1, determining the enhanced meteorological monitoring dataset as the (u-1)th round intermediate structured meteorological attribute feature set; in response to u being greater than 1, performing the (u-1)th round structured attribute vector recognition on the enhanced meteorological monitoring dataset based on the meteorological type label using the structured storage analysis algorithm to obtain the (u-1)th round intermediate structured meteorological attribute feature set.

[0123] Based on this embodiment, the data storage system will adopt a flexible and efficient method when executing the structured storage analysis algorithm to obtain the u-1th round intermediate structured meteorological attribute feature set of the target multi-mode meteorological monitoring data.

[0124] When the data storage system reaches the first round of structured attribute vector recognition, i.e., when u equals 1, since there are no recognition results from the previous round to refer to, the system will directly use the enhanced meteorological monitoring dataset as the intermediate structured meteorological attribute feature set for round 0 (i.e., round u-1). This is because, in the initial stage, the enhanced meteorological monitoring dataset itself already contains rich meteorological information, which can serve as the starting point for the first round of recognition.

[0125] For example, the data storage system has just started up and is preparing for the first round of identification, at which point u=1. Since there are no identification results from the previous round, the system will directly use the enhanced meteorological monitoring dataset, which may contain multiple meteorological indicators such as temperature, humidity, and wind speed, as the intermediate structured meteorological attribute feature set for round 0, for the first round of structured attribute vector identification.

[0126] When the data storage system reaches the second or later round, i.e., when u is greater than 1, the system will perform the (u-1)th round of structured attribute vector recognition on the enhanced meteorological monitoring dataset based on the current meteorological type label and using a structured storage analysis algorithm. This means that the system will use the recognition results from the previous round and the current meteorological type label to perform more in-depth analysis and processing of the dataset in order to extract more accurate meteorological attribute features.

[0127] Taking the second round of identification as an example, u=2. At this point, the system has completed the first round of identification and obtained the first round of intermediate structured meteorological attribute feature set. Before conducting the second round of identification, the system combines the current meteorological type labels, such as "sunny" and "rainy," and uses a structured storage analysis algorithm to perform the first round of structured attribute vector identification on the enhanced meteorological monitoring dataset, thereby obtaining the first round (i.e., the u-1th round) of intermediate structured meteorological attribute feature set. This feature set will serve as the input for the second round of identification, helping the system to more accurately identify the meteorological attribute features in the second round.

[0128] In this way, the data storage system can flexibly adjust the acquisition method of intermediate structured meteorological attribute feature sets according to actual conditions. In the initial stage, the system can directly utilize the enhanced meteorological monitoring dataset for identification, improving processing efficiency; while in subsequent stages, the system can combine historical identification results with current meteorological type labels for more in-depth analysis, improving identification accuracy. Overall, this embodiment makes the data storage system more flexible and efficient in processing multi-mode meteorological monitoring data, providing stronger technical support for meteorological applications.

[0129] In some preferred embodiments, obtaining the first transitional meteorological state unique hot code generated by the vth algorithm branch based on the meteorological type label and the intermediate structured meteorological attribute feature set of the (u-1)th round includes: when the vth algorithm branch is the first algorithm branch of the structured storage analysis algorithm, processing the meteorological type label and the intermediate structured meteorological attribute feature set of the (u-1)th round through the vth algorithm branch to obtain the first transitional meteorological state unique hot code; when the vth algorithm branch is a transitional algorithm branch of the structured storage analysis algorithm, obtaining the second transitional meteorological state unique hot code generated by the (v-1)th algorithm branch of the structured storage analysis algorithm, determining the unprocessed unique hot code of the vth algorithm branch based on the second transitional meteorological state unique hot code, and processing the unprocessed unique hot code of the vth algorithm branch through the vth algorithm branch to obtain the first transitional meteorological state unique hot code.

[0130] Based on this embodiment, when the data storage system obtains the unique thermal code of the first transitional meteorological state generated by the v-th algorithm branch based on the meteorological type label and the intermediate structured meteorological attribute feature set of the u-1th round, it will adopt different processing strategies according to the type of the algorithm branch.

[0131] When the v-th algorithm branch is the first algorithm branch of the structured storage analysis algorithm, the data storage system will directly use this branch to process the meteorological type labels and the intermediate structured meteorological attribute feature set of the (u-1)-th round. Specifically, the system will process this input data through a series of calculations and transformations in the first algorithm branch, ultimately generating a one-hot code for the first transitional meteorological state. This one-hot code is a preliminary and temporary digital representation of the current meteorological state, which will serve as the basis for subsequent algorithm branch processing.

[0132] To illustrate with a concrete example, the data storage system is currently performing the first round of structured attribute vector recognition, and the data being processed is for the weather type "sunny". The first algorithm branch receives the weather type label "sunny" and the intermediate structured weather attribute feature set of round 0 (i.e., the initial). Through specific algorithmic logic, it converts this information into a one-hot code for the first transitional weather state, such as a one-hot code representing the "sunny" state.

[0133] However, when the v-th algorithm branch is a transitional algorithm branch of the structured storage analysis algorithm, the data processing method will be different. In this case, the data storage system will first obtain the second transitional meteorological state one-hot code generated by the (v-1)-th algorithm branch of the structured storage analysis algorithm. This second transitional meteorological state one-hot code is the result of the previous algorithm branch processing, and it contains richer meteorological state information.

[0134] Next, the data storage system determines the one-hot code to be processed for the v-th algorithm branch based on this second transitional meteorological state one-hot code. This typically involves further analysis or adjustment of the second transitional meteorological state one-hot code. Finally, the v-th algorithm branch processes the one-hot code to be processed, refining and updating the meteorological state information through specific algorithmic logic, ultimately generating the first transitional meteorological state one-hot code.

[0135] For example, the data storage system has completed the processing of the first two algorithm branches and is now entering the processing stage of the third algorithm branch (a transitional algorithm branch). The system first obtains the second transitional meteorological state unique thermal code generated by the second algorithm branch. This code can contain more detailed meteorological feature information. Then, the system determines the unique thermal code to be processed in the third algorithm branch based on this code, possibly optimizing or adjusting it. Finally, the third algorithm branch processes this unique thermal code to generate a new first transitional meteorological state unique thermal code, which more accurately reflects the current meteorological state.

[0136] In this way, the data storage system can flexibly process meteorological type labels and intermediate structured meteorological attribute feature sets according to the characteristics of different algorithm branches, generating accurate one-heat codes for the first transitional meteorological state. This processing method not only improves the efficiency and accuracy of data processing, but also provides a more reliable data foundation for subsequent meteorological state analysis and forecasting. Overall, this embodiment enhances the adaptability and accuracy of the data storage system when processing complex meteorological data, bringing significant technological progress to meteorological research and applications.

[0137] In the following steps, the process of processing the meteorological type label and the intermediate structured meteorological attribute feature set of the (u-1)th round through the v-th algorithm branch to obtain the first transitional meteorological state one-hot code includes: mining the meteorological type one-hot code of the meteorological type label; mining the linear meteorological state one-hot code of the intermediate structured meteorological attribute feature set of the (u-1)th round; and processing the meteorological type one-hot code of the meteorological type label and the linear meteorological state one-hot code of the intermediate structured meteorological attribute feature set of the (u-1)th round through the v-th algorithm branch to obtain the first transitional meteorological state one-hot code.

[0138] Based on this embodiment, the data storage system will perform a series of operations to process the meteorological type label and the intermediate structured meteorological attribute feature set of the u-1th round through the v-th algorithm branch, thereby obtaining the unique thermal encoding of the first transitional meteorological state. This process is an important step in the data storage system's meteorological data analysis, aiming to transform the raw data into a format that is easier to process and understand.

[0139] First, the data storage system mines the one-hot encoding of the weather type label. One-hot encoding is a method for converting categorical variables into a format easily used by machine learning algorithms. In this case, each weather type (such as sunny, rainy, snowy, etc.) is converted into a unique binary vector with only one element being 1 and the rest being 0. For example, if the weather type label is "sunny," the corresponding one-hot encoding might be a vector where the position representing "sunny" is 1 and the rest are 0.

[0140] Secondly, the data storage system mines the linear meteorological state one-hot encoding of the intermediate structured meteorological attribute feature set in the (u-1)th round. Here, "linear meteorological state" likely refers to meteorological state features extracted using a linear model or method; these features are also converted into one-hot encoding format for subsequent processing. The purpose of this step is to extract key information from the structured meteorological attributes of the previous round and represent it in one-hot encoding form.

[0141] Finally, the data storage system processes these two sets of one-hot codes (i.e., the meteorological type one-hot code for the meteorological type label and the linear meteorological state one-hot code for the intermediate structured meteorological attribute feature set in the (u-1)th round) through the v-th algorithm branch. This processing may include weighting, merging, transformation, or other complex calculations, depending on the design of the algorithm branch. Ultimately, this processing step generates the first transitional meteorological state one-hot code, an intermediate representation that integrates meteorological type and structured meteorological attribute features, providing a foundation for subsequent meteorological state identification and prediction.

[0142] For example, a data storage system is processing a dataset containing a weather type label of "sunny" and a series of weather attributes such as temperature and humidity. The system first converts "sunny" into its corresponding one-hot code, then extracts the linear weather state one-hot codes for attributes such as temperature and humidity. Next, through specific computational logic in the v-th algorithm branch, these two sets of one-hot codes are combined to generate a first transitional weather state one-hot code that integrates the weather type and attribute features. This code not only reflects that the current weather is "sunny," but also includes the specific weather attribute states under this weather type.

[0143] In this way, the data storage system can effectively convert meteorological type labels and structured meteorological attribute feature sets into unique thermal codes for the first transitional meteorological state. This conversion not only simplifies the data representation, making it easier for machine learning algorithms to process, but also preserves the key information of the original data. Therefore, this embodiment improves the efficiency and accuracy of the data storage system in processing and analyzing meteorological data, providing strong support for subsequent meteorological state identification and forecasting.

[0144] In the following steps, determining the unprocessed one-hot code of the vth algorithm branch based on the second transitional meteorological state one-hot code includes: determining the second transitional meteorological state one-hot code as the unprocessed one-hot code of the vth algorithm branch; or, mapping the second transitional meteorological state one-hot code to the target multi-mode meteorological monitoring data to obtain the meteorological state transmission network, and weighting the meteorological state one-hot codes of Z network units in the meteorological state transmission network with the meteorological state one-hot codes of their corresponding neighboring network units to obtain the second meteorological state weighted one-hot code, and determining the unprocessed one-hot code of the vth algorithm branch based on the second meteorological state weighted one-hot code.

[0145] Based on this embodiment, the data storage system determines the one-hot encoding to be processed for the v-th algorithm branch according to the one-hot encoding of the second transitional meteorological state. This process is one of the key steps in the data storage system's processing of multi-mode meteorological monitoring data, ensuring smooth data transfer and correct processing between algorithm branches.

[0146] One direct approach is for the data storage system to directly determine the one-hot encoding of the second transitional meteorological state as the one-hot encoding to be processed in the v-th algorithm branch. In this case, the one-hot encoding of the second transitional meteorological state, as the output of the previous algorithm branch, directly becomes the input of the next algorithm branch, maintaining the continuity of data processing.

[0147] For example, the data storage system has already obtained a one-hot code representing the second transitional weather state of "partly cloudy to overcast" through the previous algorithm branch. In this code, the "partly cloudy" and "overcast" state bits may both be activated (set to 1), while the other state bits are 0. When this code is directly determined as the one-hot code to be processed in the v-th algorithm branch, the v-th algorithm branch will perform subsequent processing based on this "partly cloudy to overcast" state.

[0148] Another approach is for the data storage system to map the one-hot encoding of the second transitional meteorological state to the target multi-mode meteorological monitoring data, constructing a meteorological state transmission network. In this network, each network unit represents a specific meteorological state, and the connections between network units represent the transmission relationships between states. The system weights the one-hot encoding of the meteorological state of each network unit with the one-hot encoding of the meteorological state of its neighboring network units to obtain the weighted one-hot encoding of the second meteorological state. This weighting process considers the mutual influence between different meteorological states, making data processing more refined and accurate.

[0149] Continuing with the example of "partly cloudy to overcast," in the meteorological state transmission network, "partly cloudy" and "overcast" may be adjacent network units. During weighted processing, the system considers the impact of "partly cloudy" on "overcast" and vice versa, and weights them according to preset weights. The resulting weighted one-hot code for the second meteorological state not only reflects the current meteorological state but also implies the transition trend between states. Finally, this weighted one-hot code will be determined as the one-hot code to be processed in the v-th algorithm branch.

[0150] In this way, the data storage system can flexibly and accurately determine the one-hot encoding to be processed in the v-th algorithm branch. Whether directly using the one-hot encoding of the second transitional meteorological state or performing weighted processing through the meteorological state transmission network, the continuity and accuracy of data processing can be ensured. This method not only improves the data storage system's ability to process complex meteorological data but also provides a more reliable data foundation for subsequent meteorological analysis and forecasting. Overall, this embodiment enhances the adaptability and accuracy of the data storage system in meteorological data processing.

[0151] In some alternative embodiments, the unique hot codes of the meteorological states of the Z network units in the meteorological state transmission network are weighted with the unique hot codes of the meteorological states of their corresponding neighboring network units to obtain a target meteorological state weighted unique hot code. This includes: for each of the Z network units, weighting the unique hot code of the meteorological state of the network unit with the unique hot codes of the meteorological states of the neighboring network units to obtain the current unique hot code of the meteorological state of the network unit, thus obtaining a vector-integrated meteorological state transmission network; and obtaining the target meteorological state weighted unique hot code based on the vector-integrated meteorological state transmission network, wherein the target meteorological state weighted unique hot code is either a first meteorological state weighted unique hot code or a second meteorological state weighted unique hot code.

[0152] Based on this embodiment, the data storage system performs a series of complex operations to weightedly process the unique thermal encoding of the meteorological states of each network unit in the meteorological state transmission network. The implementation details of this process are described here.

[0153] First, consider the Z network units contained in the meteorological state transmission network. Each network unit has a corresponding one-hot code for the meteorological state. One-hot coding is a method for converting categorical variables into a format that can be used by machine learning algorithms. In one-hot coding, only one element is 1 (representing "hot"), and all other elements are 0. For example, if there are three meteorological states: sunny, rainy, and cloudy, then the one-hot code for sunny might be [1, 0, 0], for rainy it is [0, 1, 0], and for cloudy it is [0, 0, 1].

[0154] Next, the data storage system performs the following steps for each of the Z network units: Identify the neighboring network units of the network unit. In the network structure, a neighbor refers to other units directly connected to the current network unit. Obtain the unique-heat codes of the meteorological state of the network unit and its neighboring network units. Weight these unique-heat codes. The weighting method can be determined based on specific application requirements and network structure. A simple example is that if a network unit has three neighbors, each neighbor's unique-heat code of the meteorological state is assigned a weight, and these weighted codes are then added to the network unit's own unique-heat code of the meteorological state to obtain a new weighted unique-heat code. After the above processing, each network unit obtains a current meteorological state weighted unique-heat code, and these codes together constitute the vector-integrated meteorological state propagation network. Finally, based on this vector-integrated network, the data storage system generates a target meteorological state weighted unique-heat code. This target code can be a first meteorological state weighted unique-heat code, representing a specific meteorological condition or pattern, or a second meteorological state weighted unique-heat code, representing another condition or pattern.

[0155] For example, consider a simple weather state transmission network containing five network units, each capable of being in one of three states: sunny, rainy, or cloudy. The data storage system first obtains one-hot codes for each network unit and its neighbors. For instance, if a network unit and its two neighbors are in the states of rainy, sunny, and cloudy, their one-hot codes might be [0, 1, 0], [1, 0, 0], and [0, 0, 1]. Then, the system assigns weights to these codes, such as 0.5, 0.3, and 0.2, and performs a weighted sum to obtain a new weighted one-hot code. This process is repeated for each unit in the network, ultimately forming a weighted weather state transmission network.

[0156] In this way, the data storage system can effectively integrate the meteorological state information of each unit in the network and generate a more representative weighted one-heat code for the target meteorological state. This not only improves the efficiency and accuracy of data processing but also helps to gain a more comprehensive understanding of the distribution and changing trends of meteorological states throughout the network. Thus, by weighting the one-heat codes of meteorological states in network units, a more comprehensive and accurate analysis of the meteorological state transmission network is achieved. This method not only enhances data processing capabilities but also provides strong technical support for fields such as weather forecasting and environmental monitoring, helping to improve the performance and accuracy of related applications.

[0157] In some alternative embodiments, obtaining the target meteorological state weighted one-heat code based on the vector-integrated meteorological state transmission network includes: performing feature encoding on the vector-integrated meteorological state transmission network based on the meteorological monitoring dataset to obtain the target meteorological state weighted one-heat code.

[0158] In this embodiment, the data storage system employs more complex steps to obtain the weighted one-thermal code of the target meteorological state based on the vector-integrated meteorological state transmission network. This process involves in-depth analysis of the meteorological monitoring dataset and the application of feature encoding techniques.

[0159] First, the data storage system acquires a meteorological monitoring dataset, which is a collection containing a large amount of meteorological observation data, including various meteorological parameters such as temperature, humidity, wind speed, wind direction, and air pressure. This data forms the basis for feature encoding.

[0160] Next, the data storage system uses this data to perform feature encoding on the vector-integrated meteorological state transmission network. Feature encoding is a process of converting raw data into a format that is easier for machine learning models to understand. In this context, the purpose of feature encoding is to extract meteorological state-related features from the meteorological monitoring dataset and embed these features into the vector-integrated meteorological state transmission network.

[0161] In detail, the data storage system analyzes various parameters in the meteorological monitoring dataset to identify features closely related to changes in meteorological conditions. For example, the system might discover that within a specific temperature and humidity range, the meteorological condition is more likely to change from sunny to rainy. Based on this finding, the system encodes the features of corresponding nodes in the vector-integrated meteorological condition transmission network to reflect the probability of such meteorological condition changes.

[0162] When performing feature encoding, data storage systems also consider temporal and spatial factors. For example, the system may analyze the evolution of weather conditions over different time periods or their geographical distribution, and encode this information into the network.

[0163] After feature encoding is completed, the data storage system generates a weighted one-thermal code for the target meteorological state. This code not only reflects the current meteorological state of each network unit, but also incorporates feature information extracted from the meteorological monitoring dataset, thus making it more representative and predictive.

[0164] For example, a data storage system is processing a meteorological monitoring dataset containing temperature, humidity, and wind speed data. By analyzing this data, the system discovers that when temperature and humidity reach certain thresholds, an increase in wind speed often foreshadows impending rain. Therefore, when encoding features in the vector-integrated meteorological state transmission network, the system pays special attention to network units that meet this condition and reflects a high probability of rain in their weighted one-hot encoding.

[0165] In this way, the data storage system can more accurately capture and predict changes in meteorological conditions, providing more reliable data support for applications such as weather forecasting and disaster early warning. Furthermore, by performing feature encoding on the vector-integrated meteorological state transmission network based on the meteorological monitoring dataset, a more accurate and comprehensive weighted one-heat encoding of the target meteorological state is obtained, improving the processing efficiency and accuracy of meteorological data.

[0166] In the following steps, the step of performing feature encoding on the vector-integrated meteorological state transmission network based on the meteorological monitoring dataset to obtain the target meteorological state weighted one-thermal encoding includes: mapping the vector-integrated meteorological state transmission network onto the meteorological monitoring dataset according to the feature encoding rules between the meteorological monitoring dataset and the target multi-mode meteorological monitoring data to obtain a third meteorological state weighted one-thermal encoding; and obtaining the target meteorological state weighted one-thermal encoding based on the third meteorological state weighted one-thermal encoding.

[0167] Based on this technical solution, the data storage system will take a series of refined operations to perform feature encoding on the vector-integrated meteorological state transmission network according to the meteorological monitoring dataset, and finally obtain the weighted unique thermal encoding of the target meteorological state.

[0168] First, the data storage system defines the feature encoding rules between the meteorological monitoring dataset and the target multi-model meteorological monitoring data. These rules define how to convert the raw meteorological monitoring data into a format that machine learning or data analysis algorithms can understand. For example, the rules may include how to discretize continuous variables such as temperature, humidity, and wind speed, or how to combine multiple meteorological parameters to form a comprehensive feature.

[0169] Subsequently, based on these feature encoding rules, the data storage system maps the vector-integrated meteorological state transmission network to the meteorological monitoring dataset. This mapping process aims to find the correspondence between each node or edge in the network and a specific feature in the meteorological monitoring data. Through this mapping, the system can link the abstract meteorological state in the network with the actual meteorological observation data.

[0170] During the mapping process, the data storage system generates a third-state weighted one-heat code for each network unit. This code is generated based on the specific characteristics of the network unit in the meteorological monitoring dataset. For example, if a network unit represents a specific meteorological model, its third-state weighted one-heat code will be determined based on the frequency, intensity, and other characteristics of that model in the meteorological monitoring dataset.

[0171] Finally, based on these third-meteorological-state weighted one-thermal codes, the data storage system derives the target meteorological-state weighted one-thermal code. This process may involve the aggregation, averaging, or other statistical processing of multiple third-meteorological-state weighted one-thermal codes to obtain a target code that comprehensively reflects the current state of the entire meteorological-state transmission network.

[0172] For example, a data storage system is processing a meteorological monitoring dataset containing multiple parameters such as temperature, humidity, and wind speed. First, the system converts these parameters into features suitable for use by a machine learning model, based on feature encoding rules. Then, the system maps each node in the vector-integrated meteorological state propagation network to these features, generating a third-level meteorological state weighted one-hot code for each node. These codes may reflect the correlation between different meteorological parameters; for example, high temperature and humidity may indicate upcoming rainfall. Finally, the system integrates these third-level meteorological state weighted one-hot codes to obtain a target meteorological state weighted one-hot code that represents the current meteorological state of the entire network.

[0173] In this way, the data storage system can more effectively extract useful information from meteorological monitoring datasets and integrate it into the analysis of meteorological state transmission networks, thereby improving the ability to predict and understand changes in meteorological states. Thus, by mapping the vector-integrated meteorological state transmission network onto the meteorological monitoring dataset based on the feature encoding rules between the meteorological monitoring dataset and the target multi-mode meteorological monitoring data, an accurate and comprehensive weighted one-heat encoding of the target meteorological state is obtained. This method not only enhances the data storage system's ability to process complex meteorological data but also provides more accurate and reliable data support for research and applications in fields such as meteorological forecasting and environmental monitoring, demonstrating significant technological progress and practical application value.

[0174] In one optional technical approach, obtaining the target meteorological state weighted unique thermal code based on the third meteorological state weighted unique thermal code includes: adjusting the dimension of the third meteorological state weighted unique thermal code based on the dimension information of the target transitional meteorological state unique thermal code to obtain the target meteorological state weighted unique thermal code; wherein, the dimension of the target meteorological state weighted unique thermal code is consistent with the dimension of the target transitional meteorological state unique thermal code; when the target transitional meteorological state unique thermal code is a first transitional meteorological state unique thermal code, then the target meteorological state weighted unique thermal code is a first meteorological state weighted unique thermal code; when the target transitional meteorological state unique thermal code is a second transitional meteorological state unique thermal code, then the target meteorological state weighted unique thermal code is a second meteorological state weighted unique thermal code.

[0175] Under this technical approach, the operations performed by the data storage system become more complex and sophisticated, especially when processing meteorological state-weighted one-hot codes. This section will detail the process of deriving the target meteorological state-weighted one-hot code from the third meteorological state-weighted one-hot code.

[0176] First, the data storage system acquires the third meteorological state weighted one-hot encoding, which is the mapping result of the meteorological state transmission network after feature encoding and vector integration of the meteorological monitoring dataset in the previous steps. The third meteorological state weighted one-hot encoding reflects the meteorological state and its weight of each node or region in the network.

[0177] Next, the system references the dimensional information of the one-heat code for the target transitional meteorological state. The one-heat code for the transitional meteorological state represents the temporary state during the meteorological state transition process, and its dimensional information indicates the number and representation of different meteorological states. For example, if there are five different meteorological states, then the one-heat code for the transitional meteorological state will have five dimensions, with each dimension corresponding to a specific meteorological state.

[0178] Next, the data storage system will adjust the dimensions of the weighted one-hot encoding for the third meteorological state based on the dimensional information of the one-hot encoding for the target transitional meteorological state. This step aims to ensure structural consistency between the weighted one-hot encoding for the target meteorological state and the one-hot encoding for the transitional meteorological state, thereby facilitating subsequent data analysis and model training. Dimensional adjustment may include adding or reducing encoding dimensions, reallocating weights, and other operations.

[0179] After dimensional adjustment, the data storage system obtains the target meteorological state weighted one-heat code. This code not only inherits the meteorological state information from the third meteorological state weighted one-heat code, but also adapts to the dimensional structure of the transitional meteorological state one-heat code, thus possessing greater analytical value and predictive accuracy.

[0180] In detail, if the unique thermal code of the target transitional meteorological state is the unique thermal code of the first transitional meteorological state, then the weighted unique thermal code of the target meteorological state after dimensional adjustment is called the weighted unique thermal code of the first meteorological state. Similarly, if the unique thermal code of the target transitional meteorological state is the unique thermal code of the second transitional meteorological state, then the obtained weighted unique thermal code of the target meteorological state is the weighted unique thermal code of the second meteorological state.

[0181] For example, the data storage system initially obtained a four-dimensional vector as the weighted one-hot code for the third meteorological state, representing four different meteorological states and their weights. Now, the system learns that the one-hot code for the target transitional meteorological state is five-dimensional, meaning that five meteorological states need to be considered. Therefore, the system will adjust the dimensions of the third meteorological state weighted one-hot code, possibly by adding a dimension to the original four-dimensional code and reallocating the weights of each dimension, to obtain a five-dimensional weighted one-hot code for the target meteorological state.

[0182] In this way, the data storage system can flexibly adapt to the needs of meteorological state representation with different dimensions and complexities, improving the versatility and accuracy of data processing. Thus, by adjusting the dimensions of the third meteorological state's weighted one-hot encoding based on the dimensional information of the target transitional meteorological state's one-hot encoding, a target meteorological state's weighted one-hot encoding with dimensions consistent with the transitional meteorological state's one-hot encoding is obtained. This method not only enhances the data storage system's ability to process variable meteorological data but also provides more accurate and flexible data support for meteorological forecasting and analysis.

[0183] In some preferred embodiments, determining the unprocessed unique hot code of the target algorithm branch based on the weighted unique hot code of the target meteorological state includes: using the weighted unique hot code of the target meteorological state as the unprocessed unique hot code of the target algorithm branch; or, weighting the unprocessed unique hot code of the target transitional meteorological state and the weighted unique hot code of the target meteorological state to obtain the unprocessed unique hot code of the target algorithm branch; wherein, when the target algorithm branch is the (v+1)th algorithm branch, the weighted unique hot code of the target meteorological state is the first meteorological state weighted unique hot code, and the unprocessed unique hot code of the target transitional meteorological state is the first transitional meteorological state unique hot code; when the target algorithm branch is the vth algorithm branch, the weighted unique hot code of the target meteorological state is the second meteorological state weighted unique hot code, and the unprocessed unique hot code of the target transitional meteorological state is the second transitional meteorological state unique hot code.

[0184] In this embodiment, the data storage system adopts a more flexible and precise strategy when determining the one-hot encoding to be processed for the target algorithm branch. This step is a crucial link in the data processing flow, directly affecting the processing effect and accuracy of subsequent algorithm branches.

[0185] First, the data storage system might directly use the weighted one-hot encoding of the target weather state as the one-hot encoding to be processed in the target algorithm branch. This approach is suitable for scenarios where the weather state has a significant impact on the algorithm branch and there is no need to consider transitional weather states. For example, under certain specific weather conditions, such as high temperature and dryness, the algorithm branch may need to pay special attention to fire risk; in this case, it is reasonable to directly use the weighted one-hot encoding of the corresponding weather state as the encoding to be processed.

[0186] However, in many cases, the data storage system considers the influence of the one-hot encoding of the target transitional meteorological state. The transitional meteorological state represents the shift from one meteorological state to another and can contain important dynamic information. Therefore, the system performs weighted processing on the one-hot encoding of the target transitional meteorological state and the weighted one-hot encoding of the target meteorological state to obtain the one-hot encoding to be processed for the target algorithm branch.

[0187] The specific method of weighted processing may vary depending on the application scenario, but it usually involves numerically weighting and summing the corresponding dimensions of the two codes. In this way, the one-hot code to be processed simultaneously integrates the current weather state and the trend of weather state change, providing more comprehensive input information for the algorithm branches.

[0188] It is worth noting that the weighted one-hot encoding of meteorological states and the one-hot encoding of transitional meteorological states will differ depending on the target algorithm branch. For example, when the target algorithm branch is the (v+1)th algorithm branch, the system will use the first meteorological state weighted one-hot encoding and the first transitional meteorological state one-hot encoding for weighted processing; while when the target algorithm branch is the vth algorithm branch, the second meteorological state weighted one-hot encoding and the second transitional meteorological state one-hot encoding will be used.

[0189] For example, a data storage system is processing a meteorological dataset containing parameters such as temperature, humidity, and wind speed, and needs to determine the fire risk level of a certain area based on this data. At a certain point in time, the system detects a sudden rise in temperature and a sudden drop in humidity, which may indicate an increased fire risk. In this case, the system weights this meteorological change trend (i.e., the transitional meteorological state) with the current meteorological state (high temperature, low humidity) to obtain a unique thermal code that integrates dynamic and static information. This code is then input into the corresponding algorithm branch for a more accurate fire risk assessment.

[0190] In this way, the data storage system can flexibly generate one-hot codes containing rich information to be processed according to the needs of different algorithm branches. This not only improves the targeting and accuracy of data processing, but also provides a solid foundation for subsequent data analysis and decision support. Thus, by flexibly weighting the target meteorological state one-hot code or weighting it with the target transitional meteorological state one-hot code, one-hot codes to be processed that adapt to the needs of different algorithm branches are obtained. This method not only improves the granularity and accuracy of data processing, but also provides more comprehensive and dynamic data support for various application scenarios, demonstrating significant technological progress and practical application value.

[0191] In some other preferred embodiments, the step of weighting the target transitional meteorological state one-hot code and the target meteorological state weighted one-hot code to obtain the one-hot code to be processed for the target algorithm branch includes: determining the confidence coefficients corresponding to the target transitional meteorological state one-hot code and the target meteorological state weighted one-hot code respectively; and weighting the target transitional meteorological state one-hot code and the target meteorological state weighted one-hot code according to the confidence coefficients corresponding to the target transitional meteorological state one-hot code and the target meteorological state weighted one-hot code respectively to obtain the object to be processed for the target algorithm branch.

[0192] Based on this embodiment, when performing weighted processing of the target transitional meteorological state one-hot coding and the target meteorological state weighted one-hot coding, the data storage system employs a more refined method to determine the one-hot coding to be processed. This process involves two main steps: determining the confidence coefficient and weighted processing.

[0193] First, the data storage system determines the confidence coefficients for the one-hot code and the weighted one-hot code of the target transitional weather state, respectively. The confidence coefficient is an indicator used to measure the reliability of data or information, and its value is typically between 0 and 1. Here, the confidence coefficient reflects the system's level of trust in or assessment of the accuracy of these two codes. For example, if the weighted one-hot code of the target weather state is calculated based on a large amount of historical data and an accurate model, it may have a higher confidence coefficient; while if the one-hot code of the target transitional weather state is based on recent weather trend predictions, its confidence coefficient may be slightly lower.

[0194] Next, the data storage system weights these two codes based on their respective confidence coefficients. Specifically, the system multiplies each dimension value of each code by its corresponding confidence coefficient, then adds the two weighted codes together to obtain the object to be processed in the target algorithm branch. This process ensures that the one-hot code to be processed considers both the current meteorological state (reflected by the weighted one-hot code of the target meteorological state) and the dynamic trend of the meteorological state (reflected by the one-hot code of the target transitional meteorological state), and allocates reasonable weights according to their respective confidence levels.

[0195] For example, the data storage system obtains a weighted one-hot code for a target weather state [0.8, 0.1, 0.1, 0] and a one-hot code for a target transitional weather state [0.2, 0.2, 0.5, 0.1], representing four different weather states. The system determines the confidence coefficient of the weighted one-hot code for the target weather state to be 0.9, and the confidence coefficient of the one-hot code for the target transitional weather state to be 0.7. During weighting, the system multiplies each dimension value of each code by its confidence coefficient and then sums them. For example, for the first dimension, the weighted value is 0.8 + 0.9 + 0.2 + 0.7 = 0.86. Similarly, the weighted values ​​for other dimensions can be calculated to obtain the final one-hot code to be processed.

[0196] This method allows the data storage system to comprehensively consider the reliability of current meteorological conditions and their changing trends, generating more accurate and comprehensive unique heat codes for the data to be processed. This not only improves the scientific rigor and rationality of data processing but also provides a more reliable data foundation for subsequent data analysis and decision support.

[0197] As can be seen, by determining the confidence coefficients of the target transitional meteorological state one-hot encoding and the target meteorological state weighted one-hot encoding, and then performing weighted processing based on these confidence coefficients, the data storage system obtains a more accurate and comprehensive target algorithm branch of the object to be processed. This method not only improves the accuracy and reliability of data processing, but also provides more robust and reliable data support for various application scenarios, demonstrating significant technological progress and practical application potential.

[0198] In one exemplary embodiment, determining the confidence coefficients corresponding to the one-hot encoding of the target transitional meteorological state and the weighted one-hot encoding of the target meteorological state respectively includes: processing the one-hot encoding of the target transitional meteorological state and the weighted one-hot encoding of the target meteorological state through a feature focusing strategy to obtain the confidence coefficients corresponding to the one-hot encoding of the target transitional meteorological state and the weighted one-hot encoding of the target meteorological state respectively.

[0199] In this embodiment, the data storage system employs a feature-focusing strategy when determining the confidence coefficients corresponding to the one-hot encoding and the weighted one-hot encoding of the target transitional meteorological state. This strategy aims to evaluate the accuracy and reliability of the encoding through in-depth analysis, thereby providing a scientific basis for subsequent weighted processing.

[0200] First, the data storage system applies a feature-focused strategy, a method that assesses the quality or reliability of data by extracting and analyzing key features. In this scenario, the system performs detailed processing on the one-heat coding and weighted one-heat coding of the target transitional weather state.

[0201] In detail, for the unique thermal coding of a target transitional weather state, the system may consider factors such as the consistency of its transition trend, its consistency with historical data, and the accuracy of the prediction model. For example, if the transition of a certain transitional weather state is highly consistent with common patterns in historical data, and the prediction model performs relatively accurately under that state, then the confidence coefficient of the coding may be increased accordingly.

[0202] Similarly, for weighted one-heat coding of target meteorological conditions, the system evaluates the rationality of its weight allocation, its matching degree with real-time meteorological data, and the scientific nature of the weighting strategy. For example, if the weighted one-heat coding can accurately reflect the current meteorological conditions and the weight allocation is consistent with meteorological principles, then its confidence coefficient will also be improved accordingly.

[0203] Through comprehensive evaluation of feature-focusing strategies, the data storage system can generate a reasonable confidence coefficient for each code. These confidence coefficients not only reflect the accuracy and reliability of the code but also provide important reference for subsequent weighted processing.

[0204] For example, a data storage system is processing a meteorological dataset containing parameters such as temperature, humidity, and wind speed. The system first applies a feature-focused strategy to conduct in-depth analysis of the one-hot encoding and weighted one-hot encoding of the target transitional meteorological state. During the analysis, the system may find that the transition of a certain meteorological state highly matches common patterns in historical data, and the prediction model has a high accuracy rate under this state. Therefore, a high confidence coefficient is assigned to the one-hot encoding of this transitional meteorological state. Simultaneously, for the weighted one-hot encoding, the system may evaluate the rationality of its weight allocation based on real-time meteorological data and meteorological principles, and determine its confidence coefficient accordingly.

[0205] Finally, after obtaining these confidence coefficients, the data storage system uses them to weight the target transitional meteorological state one-hot code and the target meteorological state weighted one-hot code, thereby obtaining a more accurate and comprehensive one-hot code to be processed. This method not only improves the scientific nature and accuracy of data processing, but also provides a more reliable data foundation for subsequent data analysis and decision support.

[0206] As can be seen, this data storage system uses a feature-focusing strategy to determine the confidence coefficients of the one-hot encoding and weighted one-hot encoding of the target transitional meteorological state. This method comprehensively considers the accuracy and reliability of the encoding, providing a scientific basis for subsequent weighted processing. This not only improves the accuracy and reliability of data processing but also provides more robust and accurate data support for various application scenarios, demonstrating significant technological progress and practical application value.

[0207] It is worth mentioning that, through a feature-focusing strategy, the unique-heat code and the weighted unique-heat code of the target transitional meteorological state are processed to obtain the confidence coefficients corresponding to the unique-heat code and the weighted unique-heat code of the target meteorological state, respectively. This process includes: constructing a multi-dimensional feature evaluation model that integrates meteorological principles, historical data analysis, and machine learning techniques; using this model to dynamically extract features from the unique-heat code of the target transitional meteorological state, identifying the continuity and stability of its transition trend and its similarity to historical transition patterns, and assigning a transition confidence coefficient accordingly; simultaneously, performing static feature analysis on the weighted unique-heat code of the target meteorological state to evaluate the rationality of its weights in each dimension, its consistency with current real-time meteorological data, and its representativeness in long-term meteorological data, and assigning a state confidence coefficient based on the analysis results; finally, combining the analysis results of dynamic and static features, the final confidence coefficients of the unique-heat code and the weighted unique-heat code of the target meteorological state are comprehensively determined.

[0208] In detail, the data storage system employs a sophisticated and comprehensive feature-focusing strategy when determining the confidence coefficients of the target transitional meteorological state's one-heat code and the target meteorological state's weighted one-heat code. This process involves constructing a multi-dimensional feature evaluation model, the design of which integrates in-depth meteorological principles, rich historical data analysis experience, and advanced machine learning techniques.

[0209] First, the data storage system utilizes this multidimensional feature evaluation model to dynamically extract features from the one-heat code of the target transitional meteorological state. This step primarily focuses on the transition trend of the transitional meteorological state, including its coherence, stability, and similarity to historical transition patterns. For example, the system analyzes whether the transitional state exhibits a smooth and continuous trend, and whether this trend aligns with previously observed meteorological transition patterns. Based on these analyses, the system assigns a transition confidence coefficient to the one-heat code of the target transitional meteorological state, reflecting the confidence and stability of the transitional state.

[0210] Simultaneously, the data storage system performs static feature analysis on the weighted one-hot code for the target meteorological state. This step focuses on evaluating the rationality of the weights in each dimension of the weighted one-hot code, its consistency with current real-time meteorological data, and its representativeness in long-term meteorological data. For example, the system checks whether the weight allocation in the weighted one-hot code is scientific and conforms to basic meteorological principles, and compares it with real-time meteorological observation data to verify its accuracy. Furthermore, the system examines the frequency and stability of the code in historical data to assess its representativeness. Based on the results of these static feature analyses, the system assigns a state confidence coefficient to the weighted one-hot code for the target meteorological state, which reflects the accuracy and reliability of the code.

[0211] Finally, the data storage system combines the analysis results of dynamic and static characteristics to comprehensively determine the final confidence coefficients of the target transitional meteorological state one-heat code and the target meteorological state weighted one-heat code. This process ensures the scientific rigor and comprehensiveness of the confidence coefficients, providing a solid foundation for subsequent data processing and decision support.

[0212] For example, a data storage system is processing a dataset containing multiple meteorological parameters such as temperature, humidity, and wind speed. When analyzing the dataset using a multidimensional feature evaluation model, the system finds that the transition trend of a certain target's transitional meteorological state's one-thermal encoding is highly similar to historical cold air southward patterns, exhibiting consistent and stable changes. Therefore, it assigns a high transition confidence coefficient to this dataset. Simultaneously, for a target's weighted one-thermal encoding of its meteorological state, the system finds that its weight allocation is reasonable, highly consistent with real-time observation data, and highly representative of historical data. Therefore, it also assigns a high state confidence coefficient to this dataset.

[0213] This method enables data storage systems to more accurately evaluate and process meteorological data, improving the scientific rigor and reliability of data processing. This not only helps improve the accuracy of weather forecasts but also provides more robust and reliable data support for various application scenarios.

[0214] In summary, the data storage system determines the confidence coefficients of the target transitional meteorological state one-hot encoding and the target meteorological state weighted one-hot encoding by employing a feature-focusing strategy and a multi-dimensional feature evaluation model. This method comprehensively considers the analysis results of dynamic and static features, providing a scientific basis for subsequent weighted processing.

[0215] In another exemplary embodiment, the method further includes: when the u-th round of structured attribute vector identification does not belong to the Y-th round of structured attribute vector identification, determining the first transitional meteorological state unique thermal code as the unprocessed unique thermal code of the v+1-th algorithm branch of the structured storage analysis algorithm.

[0216] In this embodiment, the method executed by the data storage system covers more case handling, especially the branching logic when processing structured attribute vector recognition. When the data storage system reaches the u-th round of structured attribute vector recognition and finds that the recognition result of this round does not belong to any of the previously performed Y rounds of structured attribute vector recognition, the system will adopt a specific strategy to determine the one-hot encoding to be processed in the next algorithm branch.

[0217] In detail, if the structured attribute vector identification in round u is unique, meaning it does not repeat the identification results of the previous round Y, then the data storage system will consider using the one-thermal encoding of the first transitional meteorological state. This encoding may represent the transition from one meteorological state to another, containing important dynamic information, which is very valuable for analyzing the changing trends of meteorological data and predicting future states.

[0218] In this scenario, the data storage system identifies the one-hot encoding of the first transitional meteorological state as the one-hot encoding to be processed in the (v+1)th branch of the structured storage analysis algorithm. This means that in subsequent branch processing, the algorithm will primarily focus on the information contained in this transitional state in order to more accurately capture and predict changes in meteorological states.

[0219] For example, a data storage system is monitoring the weather conditions of a region and has performed multiple rounds of structured attribute vector identification. In a certain round (round u), the system finds that the current weather state is different from the identification results of all previous rounds (round Y), which may mean that the weather conditions in the region are undergoing significant changes. At this point, the system will choose to use the one-hot encoding of the first transitional weather state, which reflects the transition of the weather state from the previous state to the current state. Then, the system uses this one-hot encoding as the input to the (v+1)th algorithm branch to further analyze the possible impacts and consequences of this weather state transition.

[0220] In this way, the data storage system can handle different weather conditions more flexibly, especially sudden or significant weather changes. This not only improves the system's adaptability to complex weather conditions but also enables more accurate weather forecasting and analysis.

[0221] In this way, the data storage system can flexibly select the one-hot encoding to be processed based on the actual situation when processing structured attribute vector recognition. Especially when encountering new and unique meteorological states, the system can utilize the one-hot encoding of the first transitional meteorological state to deeply analyze the changing trends of the meteorological state, thereby improving the accuracy and foresight of meteorological data analysis. This flexibility and precision not only enhance the practical value of the system but also provide a more comprehensive and in-depth data foundation for meteorological forecasting and decision support.

[0222] In some standalone embodiments, the method further includes: storing the target multi-mode meteorological monitoring data in a structured manner based on the target structured meteorological attribute feature set.

[0223] In detail, based on the target structured meteorological attribute feature set, the target multi-mode meteorological monitoring data is structured and stored, including: constructing a flexible and scalable data storage architecture that can adapt to meteorological monitoring data of different modes; defining a series of data storage templates according to the target structured meteorological attribute feature set, each template corresponding to a specific meteorological attribute or feature; classifying and mapping the target multi-mode meteorological monitoring data to the corresponding data storage templates according to their attributes or features; designing a reasonable data structure and indexing mechanism within each template to ensure efficient data retrieval and updating; simultaneously implementing data compression and encryption strategies to optimize storage space and ensure data security; and finally, ensuring the accuracy and integrity of the stored data through automated data verification and error correction mechanisms. This method enables structured, efficient, and secure storage of target multi-mode meteorological monitoring data.

[0224] In the implementation of the data storage system, the process of structuring and storing target multi-mode meteorological monitoring data based on the target structured meteorological attribute feature set is highly refined and systematic.

[0225] First, the data storage system will construct a flexible and scalable data storage architecture. This architecture is designed to take into account the diversity and complexity of meteorological monitoring data, thus enabling it to adapt to different modalities of data, such as temperature, humidity, wind speed, and air pressure. This flexibility ensures that the storage architecture can effectively adapt regardless of changes in data type.

[0226] Next, the system will define a series of data storage templates based on the target structured meteorological attribute feature set. Each template is designed according to specific meteorological attributes or features, such as temperature templates and humidity templates. These templates not only provide structured storage space for the data, but also make data classification and retrieval more convenient.

[0227] Then, the target multi-mode meteorological monitoring data is categorized and mapped to corresponding data storage templates based on its own attributes or characteristics. For example, temperature data is stored in the temperature template, while wind speed data is stored in the wind speed template. This categorized storage method facilitates data organization and management, while also improving data accessibility.

[0228] Within each template, the data storage system employs a well-designed data structure and indexing mechanism. These mechanisms ensure efficient data retrieval and updates. For example, by creating an index, the system can quickly locate specific data records, thereby improving data processing efficiency.

[0229] In addition, the system will implement data compression and encryption strategies. Data compression can reduce storage space usage and lower storage costs, while data encryption can ensure data security and prevent data leakage or unauthorized access.

[0230] Finally, the data storage system ensures the accuracy and integrity of the stored data through automated data validation and error correction mechanisms. This mechanism automatically detects and corrects errors or inconsistencies in the data, thereby improving data quality.

[0231] For example, a data storage system is processing a meteorological monitoring dataset containing three modalities: temperature, humidity, and wind speed. The system first defines corresponding data storage templates for these three modalities. Then, it maps temperature data to a temperature template, humidity data to a humidity template, and wind speed data to a wind speed template. Within each template, the system indexes the data for rapid retrieval and updates. Simultaneously, the system compresses and encrypts the data to save storage space and ensure data security. Finally, through automated data validation and error correction mechanisms, the system ensures the accuracy and completeness of the stored data.

[0232] In summary, the data storage system achieves structured, efficient, and secure storage of target multi-mode meteorological monitoring data by constructing a flexible and scalable storage architecture, defining data storage templates, classifying and mapping data, designing data structures and indexing mechanisms, implementing data compression and encryption strategies, and employing automated data verification and error correction mechanisms. This approach not only improves the efficiency and quality of data processing but also provides a solid foundation for subsequent data analysis and decision support.

[0233] Furthermore, Figure 2 This is a schematic diagram of the structure of a data storage system 200 provided in an embodiment of this application. Figure 2 The data storage system 200 shown includes a processor 210, which can call and run computer programs from memory to implement the methods in the embodiments of this application.

[0234] Optionally, such as Figure 2 As shown, the data storage system 200 may further include a memory 230. The processor 210 can retrieve and run computer programs from the memory 230 to implement the methods described in this embodiment.

[0235] The memory 230 can be a separate device independent of the processor 210, or it can be integrated into the processor 210.

[0236] Optionally, such as Figure 2 As shown, the data storage system 200 may also include a transceiver 220, which the processor 210 can control to interact with other devices. Specifically, it can send information or data to other devices or receive information or data sent by other devices.

[0237] Optionally, the data storage system 200 can implement the corresponding processes of the storage engine or components (such as processing modules) in the storage engine or the device on which the storage engine is deployed in the various methods of the embodiments of this application. For the sake of brevity, these will not be described in detail here.

[0238] It should be understood that the processor in the embodiments of this application may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method embodiments can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor described above can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0239] It is understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0240] It should be understood that the above-described memory is exemplary and not a limiting description. For example, the memory in the embodiments of this application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DR RAM), etc. That is to say, the memory in the embodiments of this application is intended to include, but is not limited to, these and any other suitable types of memory.

[0241] Based on the above, a computer-readable storage medium is provided, on which a computer program is stored, the computer program implementing the above method when running.

[0242] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art.

Claims

1. A method for storing meteorological data in multiple structural types, characterized in that, Applied to a data storage system, the method includes: Obtain the target multi-mode meteorological monitoring data to be stored, and the meteorological type label corresponding to the target multi-mode meteorological monitoring data. The meteorological type label is used to describe the structured meteorological attribute feature set of the target multi-mode meteorological monitoring data. The target multi-mode meteorological monitoring data is split into data to obtain the meteorological monitoring dataset of the target multi-mode meteorological monitoring data, and the meteorological monitoring dataset is enhanced to obtain the enhanced meteorological monitoring dataset. Based on the meteorological type labels, the enhanced meteorological monitoring dataset is subjected to X rounds of structured attribute vector recognition using a structured storage analysis algorithm to obtain the target structured meteorological attribute feature set of the target multi-mode meteorological monitoring data; Specifically, during the Y-round structured attribute vector identification in the X-round structured attribute vector identification, the transitional meteorological state one-hot encoding of the structured storage analysis algorithm is mapped to the meteorological state transmission network obtained in the target multi-mode meteorological monitoring data. After vector integration of the meteorological state one-hot encodings of at least Z network units in the meteorological state transmission network with the meteorological state one-hot encodings of their corresponding neighboring network units, these are used as the objects to be processed in the next algorithm branch of the structured storage analysis algorithm. The Z network units include the network units corresponding to the modality identifiers when the target multi-mode meteorological monitoring data is split. X and Z are both positive integers, and Y is a positive integer not greater than X.

2. The method according to claim 1, characterized in that, Based on the meteorological type label, the enhanced meteorological monitoring dataset is subjected to X rounds of structured attribute vector recognition using a structured storage analysis algorithm to obtain the target structured meteorological attribute feature set of the target multi-mode meteorological monitoring data, including: In the u-th round of structured attribute vector recognition, the first transitional meteorological state unique thermal code generated by the v-th algorithm branch of the structured storage analysis algorithm is obtained. The first transitional meteorological state unique thermal code is obtained based on the enhanced meteorological monitoring dataset and the meteorological type label, where v is a positive integer and u is a positive integer not greater than X. When the u-th round of structured attribute vector identification belongs to the Y-th round of structured attribute vector identification, the first transitional meteorological state unique thermal code is mapped to the target multi-mode meteorological monitoring data to obtain the meteorological state transmission network, and the meteorological state unique thermal codes of Z network units in the meteorological state transmission network are weighted with the meteorological state unique thermal codes of the corresponding neighboring network units to obtain the first meteorological state weighted unique thermal code; Based on the weighted one-hot encoding of the first meteorological state, the one-hot encoding to be processed in the (v+1)th branch of the structured storage analysis algorithm is determined, and further identification processing is performed to obtain the uth intermediate structured meteorological attribute feature set of the target multi-mode meteorological monitoring data. Based on the meteorological type label, the structured attribute vector of the intermediate structured meteorological attribute feature set of the uth round is identified in the (u+1)th round using the structured storage analysis algorithm to obtain the target structured meteorological attribute feature set; The method further includes: when the u-th round of structured attribute vector identification does not belong to the Y-th round of structured attribute vector identification, determining the first transitional meteorological state unique thermal code as the unprocessed unique thermal code of the v+1-th algorithm branch of the structured storage analysis algorithm.

3. The method according to claim 2, characterized in that, The step of obtaining the unique thermal code of the first transitional meteorological state generated by the v-th algorithm branch of the structured storage analysis algorithm includes: Obtain the (u-1)th round intermediate structured meteorological attribute feature set of the target multi-mode meteorological monitoring data; Based on the meteorological type label and the intermediate structured meteorological attribute feature set of the (u-1)th round, the unique thermal code of the first transitional meteorological state generated by the vth algorithm branch is obtained.

4. The method according to claim 3, characterized in that, The (u-1)th round intermediate structured meteorological attribute feature set for acquiring the target multi-mode meteorological monitoring data includes: In response to u equaling 1, the enhanced meteorological monitoring dataset is determined as the intermediate structured meteorological attribute feature set of the (u-1)th round; In response to u being greater than 1, the structured attribute vector identification of the enhanced meteorological monitoring dataset is performed in the (u-1)th round using the structured storage analysis algorithm based on the meteorological type label, thereby obtaining the intermediate structured meteorological attribute feature set in the (u-1)th round.

5. The method according to claim 3, characterized in that, The process of obtaining the first transitional meteorological state unique thermal code generated by the v-th algorithm branch based on the meteorological type label and the intermediate structured meteorological attribute feature set of the (u-1)th round includes: When the v-th algorithm branch is the first algorithm branch of the structured storage analysis algorithm, the meteorological type label and the intermediate structured meteorological attribute feature set of the u-1th round are processed through the v-th algorithm branch to obtain the unique thermal encoding of the first transitional meteorological state. When the v-th algorithm branch is a transitional algorithm branch of the structured storage analysis algorithm, the second transitional meteorological state unique thermal code generated by the (v-1)-th algorithm branch of the structured storage analysis algorithm is obtained, and the unique thermal code to be processed of the v-th algorithm branch is determined based on the second transitional meteorological state unique thermal code. The unique thermal code to be processed of the v-th algorithm branch is processed by the v-th algorithm branch to obtain the first transitional meteorological state unique thermal code.

6. The method according to claim 5, characterized in that, The process of processing the meteorological type label and the intermediate structured meteorological attribute feature set of the u-1th round through the v-th algorithm branch to obtain the unique thermal encoding of the first transitional meteorological state includes: Mine the unique thermal code of the meteorological type label; Mining the linear meteorological state one-heat encoding of the intermediate structured meteorological attribute feature set in the (u-1)th round; The first transitional meteorological state unique code is obtained by processing the meteorological type one-hot encoding of the meteorological type label and the linear meteorological state one-hot encoding of the intermediate structured meteorological attribute feature set in the (u-1)th round through the v-th algorithm branch.

7. The method according to claim 5, characterized in that, The step of determining the one-hot code to be processed in the v-th algorithm branch based on the one-hot code of the second transitional meteorological state includes: The unique thermal code of the second transitional meteorological state is determined as the unique thermal code to be processed in the v-th algorithm branch; Alternatively, the second transitional meteorological state one-hot encoding is mapped to the target multi-mode meteorological monitoring data to obtain the meteorological state transmission network. The meteorological state one-hot encodings of the Z network units in the meteorological state transmission network are weighted with the meteorological state one-hot encodings of their corresponding neighboring network units to obtain the second meteorological state weighted one-hot encoding. Based on the second meteorological state weighted one-hot encoding, the one-hot encoding to be processed for the vth algorithm branch is determined.

8. The method according to claim 2 or 7, characterized in that, The one-hot encoding of the meteorological state of Z network units in the meteorological state transmission network is weighted with the one-hot encoding of the meteorological state of their corresponding neighboring network units to obtain the weighted one-hot encoding of the target meteorological state, including: For each of the Z network units, the meteorological state one-hot code of the network unit is weighted with the meteorological state one-hot code of the neighboring network units to obtain the current meteorological state one-hot code of the network unit, thus obtaining the meteorological state transmission network after vector integration. Based on the meteorological state transmission network after vector integration, the target meteorological state weighted monothermic code is obtained, which is either a first meteorological state weighted monothermic code or a second meteorological state weighted monothermic code. The step of obtaining the target meteorological state weighted one-heat code based on the vector-integrated meteorological state transmission network includes: performing feature encoding on the vector-integrated meteorological state transmission network based on the meteorological monitoring dataset to obtain the target meteorological state weighted one-heat code; The step of performing feature encoding on the vector-integrated meteorological state transmission network based on the meteorological monitoring dataset to obtain the target meteorological state weighted one-thermal encoding includes: mapping the vector-integrated meteorological state transmission network onto the meteorological monitoring dataset according to the feature encoding rules between the meteorological monitoring dataset and the target multi-mode meteorological monitoring data to obtain a third meteorological state weighted one-thermal encoding; and obtaining the target meteorological state weighted one-thermal encoding based on the third meteorological state weighted one-thermal encoding. The step of obtaining the target meteorological state weighted unique thermal code based on the third meteorological state weighted unique thermal code includes: adjusting the dimension of the third meteorological state weighted unique thermal code based on the dimension information of the target transition meteorological state unique thermal code to obtain the target meteorological state weighted unique thermal code; wherein, the dimension of the target meteorological state weighted unique thermal code is consistent with the dimension of the target transition meteorological state unique thermal code, and when the target transition meteorological state unique thermal code is the first transition meteorological state unique thermal code, then the target meteorological state weighted unique thermal code is the first meteorological state weighted unique thermal code, and when the target transition meteorological state unique thermal code is the second transition meteorological state unique thermal code, then the target meteorological state weighted unique thermal code is the second meteorological state weighted unique thermal code.

9. The method according to claim 2 or 7, characterized in that, Based on the weighted unique-hot encoding of the target meteorological state, the unprocessed unique-hot encoding of the target algorithm branch is determined, including: using the weighted unique-hot encoding of the target meteorological state as the unprocessed unique-hot encoding of the target algorithm branch; or, weighting the unprocessed unique-hot encoding of the target transitional meteorological state and the weighted unique-hot encoding of the target meteorological state to obtain the unprocessed unique-hot encoding of the target algorithm branch; wherein, when the target algorithm branch is the (v+1)th algorithm branch, the weighted unique-hot encoding of the target meteorological state is the first meteorological state weighted unique-hot encoding, and the unprocessed unique-hot encoding of the target transitional meteorological state is the first transitional meteorological state unique-hot encoding; when the target algorithm branch is the vth algorithm branch, the weighted unique-hot encoding of the target meteorological state is the second meteorological state weighted unique-hot encoding, and the unprocessed unique-hot encoding of the target transitional meteorological state is the second transitional meteorological state unique-hot encoding. The step of weighting the target transitional meteorological state one-hot code and the target meteorological state weighted one-hot code to obtain the one-hot code to be processed for the target algorithm branch includes: determining the confidence coefficients corresponding to the target transitional meteorological state one-hot code and the target meteorological state weighted one-hot code respectively; and weighting the target transitional meteorological state one-hot code and the target meteorological state weighted one-hot code according to the confidence coefficients corresponding to the target transitional meteorological state one-hot code and the target meteorological state weighted one-hot code respectively to obtain the object to be processed for the target algorithm branch. The step of determining the confidence coefficients corresponding to the one-hot encoding of the target transitional meteorological state and the weighted one-hot encoding of the target meteorological state includes: processing the one-hot encoding of the target transitional meteorological state and the weighted one-hot encoding of the target meteorological state through a feature focusing strategy to obtain the confidence coefficients corresponding to the one-hot encoding of the target transitional meteorological state and the weighted one-hot encoding of the target meteorological state.

10. A data storage system, characterized in that, The method includes 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, causing the at least one processor to perform the method according to any one of claims 1-9.

Images