Meteorological satellite data intelligent analysis method, system, device and medium

Abstract

The application discloses a meteorological satellite data intelligent analysis method, system, device and medium, and belongs to the field of satellite data processing. The application deeply fuses natural language understanding capability with a satellite data analysis process, significantly reduces the use threshold, provides an efficient man-machine interaction mode, improves analysis efficiency, is especially suitable for rapid response of non-professional users or in emergency scenarios, and realizes full-process automatic processing from a target to an analysis result, realizes the transition from "tool assistance" to "intelligent cooperation", greatly improves the intelligent level, does not depend on expert experience, does not need manual query, does not need manual frequent switching between various tool products, greatly improves the analysis efficiency, and has obvious technical advancement and application promotion value.

Description

Technical Field

[0001] This application relates to the field of satellite data processing, and in particular to a method, system, device, and medium for intelligent analysis of meteorological satellite data. Background Technology

[0002] Currently, the analysis and anomaly detection of meteorological satellite data mainly rely on a combination of automated processes based on preset rules and manual interpretation by experts. Typical existing technical solutions usually include the following steps:

[0003] 1) Data acquisition and preprocessing: The ground station receives raw observation data and satellite telemetry data transmitted from the satellite, and performs operational data preprocessing and telemetry data parsing.

[0004] 2) Feature Extraction and Product Inversion: Observational data primarily utilizes mature physical inversion algorithms or statistical models to extract or invert specific meteorological element products from standard data products. Telemetry data is mainly assessed in real-time using anomaly detection rules, and long-term trend analysis is performed using post-analysis algorithms.

[0005] 3) Anomaly Analysis and Handling: When anomalies are detected in observation or telemetry data, relevant technical personnel need to use various analysis tools, combined with their personal experience, to judge and analyze the abnormal state and find solutions.

[0006] The core of existing meteorological satellite data analysis methods is a linear process of "data → algorithm → anomaly status → manual analysis," where the algorithm is relatively independent of the business scenario and user needs. This model mainly relies on expert experience. Therefore, existing technologies have the following problems in practical applications:

[0007] 1) Rigid tools and poor adaptability: Various analytical tools can provide basic data query functions, but they are poorly adaptable to the flexible needs that frequently arise in real-world scenarios, such as combined analysis, correlation analysis, and data escaping. They rely heavily on the individual skills of the tool users.

[0008] 2) Low level of intelligence and high dependence on expert experience: The software only provides basic data analysis capabilities, and the mining of in-depth information heavily relies on the professional knowledge and experience of the analysts. This makes the analysis results subjective, unfriendly to beginners, and inefficient in knowledge transfer.

[0009] 3) Data storage is scattered and difficult to query: Different satellite telemetry data may be stored in databases of different types and with different table structures. Users may not be familiar with the specific table structure information and query methods, so it is necessary to develop corresponding query pages.

[0010] 4) Fragmented analysis process and obvious efficiency bottlenecks: In the chain from analysis to decision-making, users need to frequently switch, compare, and synthesize different software, interfaces, and products, which is cumbersome and time-consuming. Faced with massive amounts of high-frequency satellite data, manual processing is difficult to achieve efficient and continuous analysis.

[0011] 5) Limited interaction methods and inability to understand user intent: Existing systems mainly provide passive data query and graphical display functions, lacking proactive, semantic-level interaction capabilities.

[0012] The information disclosed in this background section is intended only to enhance the understanding of the overall background of this application and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0013] The purpose of this application is to provide a method, system, equipment and medium for intelligent analysis of meteorological satellite data.

[0014] To achieve the above objectives, this application provides an intelligent analysis method for meteorological satellite data, the method comprising:

[0015] The system receives natural language analysis instructions input by the user and performs semantic parsing on the instructions to obtain the analysis intent, which includes at least one analysis target and analysis action.

[0016] Based on the analytical intent, determine whether there exists a historical analytical path that is semantically similar to the analytical intent;

[0017] In response to the absence of a historical analysis path that is semantically similar to the analysis intent, a new analysis path is dynamically planned based on the analysis intent, the analysis path including the at least one analysis objective and analysis action;

[0018] Based on the analysis path, the required algorithms are dynamically selected from the algorithm library to form an analysis process;

[0019] The algorithm in the analysis process is automatically invoked to perform the acquisition, processing and analysis of meteorological satellite data in the analysis process, and to generate the analysis results of the meteorological satellite data.

[0020] During the processing, the user's input natural language analysis commands, the system response to the natural language analysis commands, the analysis results, and the analysis path are recorded throughout the process, forming an analysis behavior chain, and stored.

[0021] Based on the analysis results, an analysis report is generated, which includes the visualization analysis results of meteorological satellite data and processing suggestions for the natural language analysis instructions.

[0022] In some embodiments, the semantic parsing of the natural language analysis instruction to obtain the analysis intent includes:

[0023] By using a pre-built natural language understanding module for meteorological satellite data, the natural language analysis instructions are mapped into a set of structured parameters. The set of structured parameters is used as a component of the analysis intent to obtain the analysis intent. The set of structured parameters includes at least the target satellite identifier, time range, geographical region, data type, and analysis action.

[0024] In some embodiments, the method further includes:

[0025] Construct a process-aware memory, which stores the historically executed chain of analytical behaviors;

[0026] The step of determining whether there is a historical analysis path semantically similar to the analysis intent based on the analysis intent includes:

[0027] Based on the analytical intent, check whether there is a historical analytical path in the historically executed analytical behavior chain in the process-aware memory that is semantically similar to the analytical intent;

[0028] During the processing, the user's input natural language analysis commands, the system response to the natural language analysis commands, the analysis results, and the analysis path are recorded throughout the process, forming an analysis behavior chain, which is then stored, including:

[0029] During the processing, the system records every step of the user's operation, system response, analysis results and analysis path in real time during the data analysis process. It combines session identifier, user identifier and task type for context binding, and forms an analysis behavior chain in a traceable and revisitable data structure.

[0030] Based on the large language model, the organizational experience of the analysis behavior chain is extracted to obtain a reusable analysis path. The analysis path is then associated with other data in the analysis behavior chain. The analysis behavior chain is written into the process-aware memory in a structured storage manner, and a version record is generated.

[0031] In some embodiments, the method further includes:

[0032] In response to the existence of a historical analysis path that is semantically similar to the analysis intent, a matching historical analysis path is extracted from the process-aware memory, wherein the historical analysis path is a reusable analysis path extracted from organizational experience based on the historical analysis behavior chain;

[0033] The step of dynamically selecting the required algorithm from the algorithm library based on the historical analysis path to form an analysis process is executed.

[0034] In some embodiments, the step of dynamically selecting the required algorithm from the algorithm library according to the analysis path to form an analysis flow includes:

[0035] Based on the meteorological satellite data analysis task scenario and meteorological satellite data characteristics indicated by the analysis path, algorithms are dynamically selected, sorted, and combined from professional algorithm services to form an optimal algorithm chain, which is the analysis process.

[0036] In some embodiments, the method further includes:

[0037] The system invokes a dynamic table structure understanding model adapted to meteorological satellite data to detect table structures and map fields from heterogeneous meteorological satellite data sources, generating dynamic data query and analysis strategies for meteorological satellite data.

[0038] All meteorological satellite data, the dynamic data query and analysis strategies for meteorological satellite data, the data query, algorithm call and result generation during the analysis process are uniformly encapsulated and stored in an independent storage service to obtain a dedicated analysis sandbox for meteorological satellite data. The dedicated analysis sandbox for meteorological satellite data supports the mixed execution of structured query language and data analysis scripts of data analysis agents.

[0039] The automatic invocation of the algorithm in the analysis process executes the acquisition, processing, and analysis operations of meteorological satellite data in the analysis process, generating the analysis results of the meteorological satellite data, including:

[0040] The system automatically performs the acquisition, processing, and analysis of meteorological satellite data in the analysis process through the dedicated analysis sandbox for meteorological satellite data, and generates the analysis results of the meteorological satellite data.

[0041] In some embodiments, the analysis results include intermediate analysis results and visualization analysis results;

[0042] The step of generating an analysis report based on the analysis results includes:

[0043] Based on the intermediate analysis results and combined with stored historical handling cases, the rule engine and / or machine learning model generate handling suggestions based on the intermediate analysis results.

[0044] The proposed solutions and the results of the visualization analysis are output together to form an analysis report.

[0045] To achieve the above objectives, this application provides an intelligent analysis system for meteorological satellite data, the system comprising:

[0046] The natural language understanding module is used to receive natural language analysis instructions input by the user, and to perform semantic parsing on the natural language analysis instructions to obtain the analysis intent, wherein the analysis intent includes at least one analysis target and analysis action;

[0047] A task scheduling engine is used to determine whether there is a historical analysis path that is semantically similar to the analysis intent based on the analysis intent; and in response to the absence of a historical analysis path that is semantically similar to the analysis intent, dynamically plan a new analysis path based on the analysis intent, wherein the analysis path includes at least one analysis target and analysis action;

[0048] The task scheduling engine is also used to dynamically select the required algorithm from the algorithm library according to the analysis path to form an analysis process;

[0049] The data analysis execution unit is used to automatically perform the acquisition, processing and analysis operations of meteorological satellite data in the analysis process through a dedicated meteorological satellite data analysis sandbox, and generate the analysis results of the meteorological satellite data.

[0050] The operation memory storage module is used to record the natural language analysis instructions input by the user, the system response to the natural language analysis instructions, the analysis results and the analysis path throughout the processing, forming an analysis behavior chain;

[0051] An organizational experience extraction engine is used to extract organizational experience based on the analysis behavior chain, and the experience is stored by the operation memory storage module.

[0052] The feedback optimization unit is used to generate an analysis report based on the analysis results. The analysis report includes the visualization analysis results of meteorological satellite data and processing suggestions for the natural language analysis instructions.

[0053] The system utilizes a data analysis intelligent agent to automate the entire process from user natural language input to data analysis result output.

[0054] On the one hand, an electronic device is provided, comprising one or more processors and one or more memories, wherein at least one computer program is stored in the one or more memories, and the at least one computer program is loaded and executed by the one or more processors to implement various optional implementations of the above-mentioned intelligent analysis method for meteorological satellite data.

[0055] On the one hand, a computer-readable storage medium is provided, wherein at least one computer program is stored in the storage medium, and the at least one computer program is loaded and executed by a processor to implement various optional implementations of the above-mentioned intelligent analysis method for meteorological satellite data.

[0056] On one hand, a computer program product or computer program is provided, the computer program product or computer program comprising one or more lines of program code stored in a computer-readable storage medium. One or more processors of an electronic device read the one or more lines of program code from the computer-readable storage medium, and the one or more processors execute the one or more lines of program code, causing the electronic device to perform the meteorological satellite data intelligent analysis method of any of the above possible embodiments.

[0057] This application deeply integrates natural language understanding capabilities with satellite data analysis processes, significantly lowering the barrier to entry and providing a highly efficient human-computer interaction mode to improve analysis efficiency. It is especially suitable for non-professional users or rapid response in emergency scenarios. Furthermore, it achieves fully automated processing from target to analysis results, realizing a leap from "tool assistance" to "intelligent collaboration," greatly improving the level of intelligence. It no longer relies on expert experience and eliminates the need for manual queries and frequent switching between various tools, significantly improving analysis efficiency. It has significant technological advancements and application promotion value. Attached Figure Description

[0058] Figure 1 This is a schematic diagram illustrating an application scenario of an intelligent analysis method for meteorological satellite data provided in an embodiment of this application;

[0059] Figure 2 This is a flowchart of an intelligent analysis method for meteorological satellite data provided in an embodiment of this application;

[0060] Figure 3 This is a flowchart of an intelligent analysis method for meteorological satellite data provided in an embodiment of this application;

[0061] Figure 4 This is an example diagram illustrating the semantic understanding and data analysis results of a user question provided in an embodiment of this application;

[0062] Figure 5 This is an example diagram illustrating a data analysis result provided in an embodiment of this application;

[0063] Figure 6 This is an example diagram illustrating user operation step extraction and experience accumulation provided in an embodiment of this application;

[0064] Figure 7 This is a flowchart of an intelligent analysis method for meteorological satellite data provided in an embodiment of this application;

[0065] Figure 8 This is an architecture diagram of an intelligent meteorological satellite data analysis system provided in an embodiment of this application;

[0066] Figure 9 A schematic diagram of the structure of a meteorological satellite data intelligent analysis system provided in this application embodiment;

[0067] Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application;

[0068] Figure 11 This is a structural block diagram of a terminal provided in an embodiment of this application;

[0069] Figure 12 This is a schematic diagram of the structure of a server provided in an embodiment of this application. Detailed Implementation

[0070] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0071] In this application, the terms "first," "second," etc., are used to distinguish identical or similar items that have substantially the same function and purpose. It should be understood that there is no logical or temporal dependency between "first," "second," and "nth," nor does it limit the quantity or order of execution. It should also be understood that although the following description uses the terms "first," "second," etc., to describe various elements, these elements should not be limited by the terms. These terms are merely used to distinguish one element from another. For example, without departing from the various examples described, a first image is referred to as a second image, and similarly, a second image is referred to as a first image. Both the first image and the second image are images, and in some cases, they are separate and distinct images.

[0072] In this application, the term "at least one" means one or more, and the term "multiple" means two or more. For example, multiple data packets means two or more data packets.

[0073] It should be understood that the terminology used in the description of the various examples herein is for the purpose of describing particular examples only and is not intended to be limiting. As used in the description of the various examples and the appended claims, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0074] It should also be understood that the term "and / or" as used herein refers to and covers any and all possible combinations of one or more of the associated listed items. The term "and / or" describes an association between related objects, indicating the existence of three relationships; for example, A and / or B means: A exists alone, A and B exist simultaneously, or B exists alone. Additionally, the character " / " in this application generally indicates that the preceding and following related objects are in an "or" relationship.

[0075] It should also be understood that, in the various embodiments of this application, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0076] It should also be understood that determining B based on A does not mean determining B solely based on A, but also based on A and / or other information.

[0077] It should also be understood that the term “comprising” (also referred to as “includes”, “including”, “Comprises” and / or “Comprising”) as used in this specification specifies the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0078] It should also be understood that the term "if" can be interpreted as meaning "when" or "upon" or "in response to determination" or "in response to detection." Similarly, depending on the context, the phrases "if determination..." or "if detection [the stated condition or event]" can be interpreted as meaning "when determination..." or "in response to determination..." or "when detection [the stated condition or event]" or "in response to detection [the stated condition or event]."

[0079] The implementation environment of this application is described below.

[0080] Figure 1 This is a schematic diagram of the implementation environment for an intelligent meteorological satellite data analysis method provided in this application embodiment. The implementation environment includes a terminal 101, or it includes the terminal 101 and a meteorological satellite data intelligent analysis platform 102. The terminal 101 is connected to the meteorological satellite data intelligent analysis platform 102 via a wireless network or a wired network.

[0081] Terminal 101 is at least one of the following: smartphone, game console, desktop computer, tablet computer, e-book reader, MP3 (Moving Picture Experts Group Audio Layer III) player or MP4 (Moving Picture Experts Group Audio Layer IV) player, laptop computer, intelligent robot, and self-service payment device. Terminal 101 has an application installed and running that supports intelligent analysis of meteorological satellite data.

[0082] For example, the terminal 101 performs this task independently, and also receives data services from the meteorological satellite data intelligent analysis platform 102. This application embodiment does not limit this aspect.

[0083] The meteorological satellite data intelligent analysis platform 102 includes at least one of a single server, multiple servers, a cloud computing platform, and a virtualization center. The meteorological satellite data intelligent analysis platform 102 provides backend services for applications supporting gold grade prediction based on shortwave infrared mineral assemblage characteristics. Optionally, the meteorological satellite data intelligent analysis platform 102 undertakes the primary processing work, and the terminal 101 undertakes secondary processing work; or, the meteorological satellite data intelligent analysis platform 102 undertakes secondary processing work, and the terminal 101 undertakes primary processing work; or, the meteorological satellite data intelligent analysis platform 102 or the terminal 101 each undertakes processing work independently. Alternatively, the meteorological satellite data intelligent analysis platform 102 and the terminal 101 can collaborate using a distributed computing architecture.

[0084] Optionally, the meteorological satellite data intelligent analysis platform 102 includes at least one server 1021 and a database 1022. The database 1022 is used to store data. In this embodiment, the database 1022 stores sample data and provides data services to at least one server 1021.

[0085] A server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. A terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited to these.

[0086] Those skilled in the art will know that the number of terminals 101 and servers 1021 may be more or less. For example, there may be only one terminal 101 or server 1021, or there may be dozens or hundreds of terminals 101 or servers 1021, or even more. The embodiments of this application do not limit the number or type of terminals or servers.

[0087] Addressing the limitations of existing technologies, such as rigid tools, low levels of intelligence, fragmented analysis processes, and simplistic interaction methods, this invention overcomes the constraints of traditional satellite data analysis tools that are "heavy on operation, light on understanding, and difficult to pass on." Through a three-in-one architecture of "intelligent agent + memory + organized experience," it achieves a leap from "tool-assisted" to "intelligent collaboration," demonstrating significant technological advancement and application value. The intelligent agent is a natural language-driven agent, and the memory is process-aware memory. This novel intelligent analysis method for meteorological satellite data abandons the traditional process of "data → algorithm → anomaly state → manual analysis." Instead, it automates the entire process through the intelligent agent, eliminating reliance on human intervention or expert experience. Furthermore, the memory records and organizes the entire analysis process, storing accumulated experience. For subsequent new analysis needs, it can determine if there are semantically similar historical analysis paths, enabling the reuse of analysis paths. This not only improves analysis efficiency but also significantly enhances the intelligence of the analysis method.

[0088] In some embodiments, the intelligent analysis method for meteorological satellite data can be encapsulated as a software tool called a "meteorological satellite data intelligent analysis assistant." Users can interact directly with the assistant using natural language. Users can input commands in natural language into the assistant, which then executes the steps of the intelligent analysis method for meteorological satellite data and outputs an analysis report. In some embodiments, the analysis report can be output by displaying it on the terminal where the assistant is located, or by sending it to a designated account. This application embodiment does not limit the specific method used.

[0089] The following is through Figure 2 The illustrated embodiment provides a detailed explanation of the intelligent analysis method for meteorological satellite data. Figure 2 This is a flowchart of an intelligent analysis method for meteorological satellite data provided in an embodiment of this application. The method is applied to an electronic device, which may be a terminal or a server. (See also...) Figure 2 The method includes the following steps.

[0090] 201. An electronic device receives a natural language analysis instruction input by a user and performs semantic parsing on the natural language analysis instruction to obtain an analysis intent, wherein the analysis intent includes at least one analysis target and analysis action.

[0091] Among them, the natural language analysis instructions input by the user are analysis requests or user needs entered by the user in the form of natural language. For example, the user initiates an analysis request through natural language or interactive operation, such as "help me find out whether the satellite actually performed XX mission in the past 6 hours", "compare the changes in the satellite XX status in the past 24 hours", or "help me analyze the abnormal power status of the satellite in the past 24 hours", etc.

[0092] Analysis intent is a target description that can be executed by a machine after a structured understanding of natural language instructions. It includes the analysis target and the analysis action.

[0093] In meteorological satellite data analysis scenarios, traditional interaction methods typically rely on professional interfaces and manual configuration, which not only have a high barrier to entry but also fail to accurately capture users' high-level analytical needs. Therefore, this application introduces a natural language-driven interaction mechanism, allowing users to express their analytical intentions directly in everyday language, thereby lowering the barrier to entry and improving human-computer interaction efficiency.

[0094] In practice, users can input natural language analysis commands through an interactive interface, which reflect the user's high-level analytical needs. By leveraging natural language understanding, a natural and efficient human-computer interaction mechanism is established, enabling the system (also known as an assistant) to understand the user's analytical intent and provide proactive and accurate services.

[0095] In some embodiments, semantic parsing essentially transforms unstructured natural language into structured machine language. Specifically, during semantic parsing, an electronic device can use a pre-built natural language understanding module for meteorological satellite data to map the natural language analysis instructions into a set of structured parameters. This set of structured parameters is then used as a component of the analysis intent to obtain the analysis intent. The set of structured parameters includes at least the target satellite identifier, time range, geographical region, data type, and analysis action.

[0096] In one possible embodiment, the semantic parsing process involves the system parsing user instructions through a Natural Language Understanding (NLU) module to extract key entities (e.g., time, satellite, mission type, etc.) and analyze intent.

[0097] In step 201, the electronic device uses a semantic understanding model for the meteorological satellite domain to map the natural language analysis instructions into a combination of target satellite, observation time, geographical region, data type and analysis action, and converts the combination into structured task parameters that can be recognized by the execution engine, as the input basis for the generation of subsequent analysis paths.

[0098] Through the above processing, the user's vague expression is transformed into precise and actionable input, thus laying a solid foundation for subsequent analysis path planning and algorithm scheduling. The structured analysis intent output in this step will serve as the core basis for retrieving historical analysis paths and judging semantic similarity in step 202.

[0099] 202. The electronic device determines, based on the analysis intent, whether there is a historical analysis path that is semantically similar to the analysis intent.

[0100] After obtaining the structured analytical intent, the system faces two choices: one is to plan a completely new analytical path for the current task; the other is to try to reuse existing successful experiences. The latter can not only significantly improve analytical efficiency, but also effectively reduce the arbitrariness of human operation and ensure the consistency of analytical conclusions.

[0101] To this end, this application provides a process-aware memory mechanism that stores previously performed analysis paths. After obtaining the analysis intent, it can retrieve whether a similar analysis has been performed in the past. If not, a new analysis path can be planned. If it has been performed, the historical analysis path can be reused.

[0102] In some embodiments, this application constructs a process-aware memory to store complete chains of analytical actions generated during historical analysis. Each chain of analytical actions records the entire process from user instruction input to final result output, including operation sequence, system response, algorithm call, and decision basis.

[0103] Specifically, the electronic device constructs a process-aware memory, which stores historically executed chains of analytical actions. The specific storage process for this process-aware memory can be found in step 206 below, and will not be elaborated upon here. Correspondingly, in step 202, the electronic device can, based on the analytical intent, search the historically executed chains of analytical actions in the process-aware memory for historical analytical paths semantically similar to the analytical intent.

[0104] In step 202, based on the analysis intent output in step 201, a semantic search is performed in the process-aware memory to determine whether there is a historical analysis path that is highly similar to the analysis intent. This determination process not only considers the similarity of task objectives, but also comprehensively considers multiple dimensions such as time range, data type, and analysis actions to ensure the accuracy and applicability of the search results. This application embodiment does not limit this aspect.

[0105] By introducing a historical path judgment mechanism, the system can intelligently choose between "starting from scratch" and "reusing experience," thereby achieving a dual optimization of analysis efficiency and quality. The judgment result in this step will directly determine whether to dynamically plan a new path in step 203 or directly reuse an existing historical analysis path.

[0106] 203. In response to the absence of a historical analysis path that is semantically similar to the analysis intent, the electronic device dynamically plans a new analysis path based on the analysis intent, the analysis path including the at least one analysis target and analysis action.

[0107] When step 202 determines that there are no semantically similar historical analysis paths, the system needs to autonomously plan a completely new analysis path based on the current analysis intent. This analysis path must clearly cover at least one analysis objective and its corresponding analysis action, and ensure the completeness and executability of the path.

[0108] In some embodiments, the intelligent analysis method for meteorological and astronomical data can be automated through a data analysis agent. In step 203, in response to the absence of a historical analysis path semantically similar to the analysis intent, the electronic device can initiate the data analysis agent to plan based on the analysis intent and obtain a new analysis path.

[0109] Step 203 involves searching for a historical analysis path that is semantically similar to the stated analysis intent. In some embodiments, there is also a case where a historical analysis path that is semantically similar to the stated analysis intent exists.

[0110] Conversely to step 203, if a semantically similar historical analysis path is determined to exist, the system prioritizes retrieving a matching historical analysis path from the process-aware memory. It's important to note that the data reused here is not the original log record, but a reusable analysis template extracted from organizational experience. This template typically contains key information such as the historical task scenario, triggering conditions, algorithm call order, and parameter configuration. In other words, a historical analysis path can include the historical task scenario, triggering conditions, algorithm call order, and parameter configuration.

[0111] Specifically, in response to the existence of a historical analysis path semantically similar to the stated analytical intent, the electronic device extracts a matching historical analysis path from a process-aware memory. This historical analysis path is a reusable analysis path extracted based on organizational experience from historical analytical behavior chains. That is, after step 202, if the path does not exist, step 203 is executed; if it does exist, the matching historical analysis path is extracted. Based on the analysis path or historical analysis path, the electronic device dynamically selects the required algorithm from an algorithm library to form an analysis flow, and then executes subsequent steps.

[0112] Accordingly, in step 204 below, the electronic device can execute the step of dynamically selecting the required algorithm from the algorithm library based on the historical analysis path to form an analysis process.

[0113] It should be noted that step 202 is the process of determining whether the current analysis intent is the first analysis. If it is the first analysis, the agent task planning is initiated, and the analysis path is automatically generated. If it is not the first analysis, the memory is searched to find similar historical analysis processes, and a reusable analysis path is recommended.

[0114] For example, such as Figure 3 As shown, the electronic device receives a natural language analysis command input by a user and performs semantic parsing on the command to obtain an analysis intent. The analysis intent includes at least one analysis target and one analysis action. Based on the analysis intent, the electronic device determines whether a historical analysis path exists that is semantically similar to the analysis intent. If not, the electronic device dynamically plans a new analysis path based on the analysis intent, the analysis path including the at least one analysis target and one analysis action; if a matching historical analysis path exists, the electronic device retrieves it from a process-aware memory.

[0115] This application further introduces an automatic organizational experience extraction service based on a large language model. Specifically, by applying organizational experience extraction prompts to the operational memory tracking results data, the large language model can abstract highly generalizable analysis strategies from massive historical behavior chains and store, match, and recall them in a structured form.

[0116] Whether generated by dynamic programming or adapted from historical experience, the final determined analysis path will serve as the direct basis for subsequent algorithm selection and process orchestration.

[0117] 204. The electronic device dynamically selects the required algorithm from the algorithm library according to the analysis path to form an analysis process.

[0118] After determining the analysis path, the system needs to dynamically select the most suitable combination of algorithms from the algorithm library based on the specific requirements of the task. Meteorological satellite data analysis involves multi-source heterogeneous data types and analysis objectives, and fixed algorithm combinations often fail to balance accuracy and efficiency; therefore, dynamic scheduling is particularly crucial.

[0119] This application transforms the analysis process from "fixed algorithm execution" to "intelligent algorithm selection and collaborative analysis based on targets and scenarios," thereby improving the scenario adaptability and intelligent decision-making level of satellite data analysis algorithms.

[0120] In some embodiments, the algorithm library may store various algorithms, such as those for data querying, feature extraction, anomaly detection, and trend analysis. Specifically, the algorithm library may pre-store multiple algorithm modules, which can be dynamically invoked when analysis is needed to form an analysis process. Specifically, in step 204, the electronic device can dynamically invoke modules such as data querying, feature extraction, anomaly detection, and trend analysis from the algorithm library according to the analysis target (which may be the analysis intent), forming a customized analysis process.

[0121] In some embodiments, the electronic device can screen algorithms from professional algorithm services based on the task scenario indicated by the analysis path and the characteristics of meteorological satellite data, and sort and combine multiple candidate algorithms to select the optimal algorithm chain.

[0122] The selection process not only focuses on the applicability of a single algorithm but also compares the ranking and combination of multiple candidate algorithms to select the optimal algorithm chain, achieving the most efficient and effective analysis workflow. This optimal algorithm chain constitutes the analysis workflow for this task, defining the order of data processing, algorithm call relationships, and parameter passing methods. By dynamically constructing the analysis workflow, the system can obtain the analysis results that best meet the current task requirements with minimal computational cost.

[0123] 205. The electronic device automatically invokes the algorithm in the analysis process to perform the acquisition, processing and analysis of meteorological satellite data in the analysis process, and generates the analysis results of the meteorological satellite data.

[0124] After obtaining the analysis workflow, the system enters the actual data processing stage. Electronic devices can automatically execute the analysis workflow, realizing data acquisition, processing, and analysis operations to obtain analysis results.

[0125] In some embodiments, the analysis results may include intermediate analysis results and visualization analysis results. The intermediate analysis results are used to generate an analysis report, serving as the data basis for generating the report. The visualization analysis results may be visualization charts, such as multi-dimensional charts including trend graphs, heatmaps, and state diagrams. This application does not limit the specific form of the intermediate analysis results and visualization analysis results.

[0126] For meteorological satellite data, the meteorological satellite data may include raw observation data received from the satellite via ground stations, such as observation data obtained through visible light, infrared, water vapor channels, etc., and may also include telemetry data.

[0127] Understandably, different meteorological satellite data require different algorithms for processing and analysis, and since different meteorological satellite data have different structures, the query methods are naturally also different.

[0128] Because meteorological satellite data is typically stored in heterogeneous databases with complex table structures and a lack of standardized protocols, direct queries are not only difficult but also prone to errors. Therefore, this application introduces a dynamic table structure understanding and analysis mechanism, along with a dedicated analysis sandbox mechanism.

[0129] Specifically, the electronic device invokes a dynamic table structure understanding model adapted to meteorological satellite data to perform table structure detection and field mapping on heterogeneous meteorological satellite data sources, generating dynamic data query and analysis strategies for meteorological satellite data. Then, the electronic device can uniformly encapsulate all meteorological satellite data, the dynamic data query and analysis strategies for meteorological satellite data, data queries during the analysis process, algorithm calls, and result generation, and store them in an independent storage service, resulting in a dedicated meteorological satellite data analysis sandbox. This sandbox supports the mixed execution of structured query language and data analysis scripts by data analysis agents. That is, in some embodiments, the system uniformly encapsulates all relevant data, query strategies, and execution logic and deploys them to the dedicated meteorological satellite data analysis sandbox.

[0130] Electronic devices can access multi-source satellite data (observation, telemetry, orbit, etc.) by calling a database (satellite data source). The dynamic table structure described above helps to understand the model and achieve unified data format and spatiotemporal alignment.

[0131] In this embodiment, a table structure knowledge for commonly used storage of meteorological satellite data is constructed, and dynamic exploration and understanding can be performed based on the actual table structure, thereby achieving more accurate query capabilities for the database.

[0132] Accordingly, in step 205, the electronic device can automatically perform the acquisition, processing and analysis of meteorological satellite data in the analysis process through the dedicated meteorological satellite data analysis sandbox, and generate the analysis results of the meteorological satellite data.

[0133] This dedicated sandbox for meteorological satellite data analysis provides an isolated and reproducible execution environment that supports the mixed execution of structured query languages ​​and data analysis scripts, such as Python and SQL, enabling flexible analysis. Electronic devices can automatically acquire, clean, process, and analyze meteorological satellite data by calling this sandbox, and ultimately generate analysis results.

[0134] In some embodiments, the system automatically performs data acquisition, processing, and analysis through a data analysis sandbox, generating intermediate results and visualization charts. Through sandboxed execution, the system not only ensures the security and controllability of the analysis process but also achieves reproducibility and verifiability of the analysis workflow. The analysis results generated in this step will simultaneously serve as the basis for the behavior chain record in step 206 and the report generation in step 207.

[0135] 206. During the processing, the electronic device records the natural language analysis instructions input by the user, the system response to the natural language analysis instructions, the analysis results, and the analysis path, forming an analysis behavior chain, and stores it.

[0136] To maximize the value of a single analysis, this application designs a process-aware operational memory mechanism. This mechanism goes beyond simply outputting results; it records the entire analysis process in a fine-grained manner to facilitate subsequent reuse and traceability.

[0137] In some embodiments, during the processing, the electronic device records in real time every step of the user's operation, system response, analysis results, and analysis path during the data analysis process. It combines session identifier, user identifier, and task type for context binding, forming an analysis behavior chain in a traceable and revisitable data structure.

[0138] In a more specific implementation, user operation sequences, system response data, algorithm call chains, and decision-making basis are recorded according to the analysis session dimension; a unique identifier is assigned to each analysis trajectory and bound to the user identifier, task topic, and time context to form a traceable analysis behavior chain.

[0139] In some embodiments, the electronic device extracts organizational experience from the analysis behavior chain based on a large language model to obtain a reusable analysis path, associates the analysis path with other data in the analysis behavior chain, writes the analysis behavior chain into a process-aware memory in a structured storage manner, and generates a version record.

[0140] In these embodiments, an automatic organizational experience extraction service is built by using operation memory tracking result data (i.e., all data of the user's every step of operation and analysis process recorded in real time) and organizational experience extraction operation prompt words (which can be used to build an index for organizational experience, etc.), thereby realizing the storage, matching and retrieval capabilities of organizational experience and generating version records.

[0141] Furthermore, regarding the meteorological satellite data analysis operation memory retrieval mechanism, the complete operation sequence of the user can be saved through operation step storage; key analysis steps can be extracted from the analysis behavior chain through operation memory retrieval; analysis experience can be persistently saved through memory storage; and the ability to share key core operation steps and experience can be realized through the memory sharing mechanism.

[0142] In some more specific embodiments, the system abstracts the operation sequence in the analysis trajectory based on a large language model and extracts reusable analysis templates. The analysis templates are associated with triggering conditions, applicable scenarios and expected results, and written into the organizational experience base (i.e., a process-aware memory base). In subsequent analysis processes, the analysis templates are recalled through semantic matching as a reference for analysis path recommendation.

[0143] The analytical behavior chain and organizational experience formed in this step will become an important reference for similar tasks in the future, enabling the continuous accumulation and value-added of knowledge at the organizational level.

[0144] 207. The electronic device generates an analysis report based on the analysis results, the analysis report including the visualization analysis results of meteorological satellite data and processing suggestions for the natural language analysis instructions.

[0145] The ultimate goal of analysis is to support decision-making, but purely numerical results are often insufficient to directly guide action. Therefore, this application, based on the analysis results, further generates a structured analysis report, achieving a closed loop from "understanding the data" to "making decisions."

[0146] In some embodiments, the analysis results include intermediate analysis results and visualization analysis results. The visualization analysis results may include various forms such as trend charts, state diagrams, and heatmaps, and this application embodiment does not limit the specific forms.

[0147] The electronic device uses a rule engine and / or machine learning model to generate action recommendations based on the intermediate analysis results and stored historical action cases. The electronic device then outputs these action recommendations along with the visualized analysis results to form an analysis report.

[0148] In a more specific implementation, the proposed solutions not only identify the existing problems but also provide concrete solutions or operational plans. For example, based on anomaly detection results, actionable suggestions such as "it is recommended to check the battery charge and discharge control parameters" may be given.

[0149] In some embodiments, the system integrates action recommendations with visual analysis results to form a complete analysis report. Accordingly, this analysis report includes both intuitive data presentation and clear action guidelines, thereby helping users quickly transition from "understanding the data" to "making decisions."

[0150] For example, Figure 4 This is an example diagram illustrating the semantic understanding and data analysis results of a user question provided in an embodiment of this application, such as... Figure 4 As shown, after semantic understanding of user questions, data analysis results are obtained through analysis. These results may include conclusions and recommendations, as well as causal analysis and suggestions for the next steps.

[0151] For example, Figure 5 This is an example diagram illustrating a data analysis result provided in an embodiment of this application, such as... Figure 5 As shown, data analysis results can also include visualization results, which can be in the form of tables or trend charts.

[0152] Figure 6 This is an example diagram illustrating user operation step extraction and experience accumulation provided in an embodiment of this application, such as... Figure 6 As shown, experience can be extracted for each analysis process, based on the analysis of historical behaviors and preferences, and then some patterns can be summarized and stored as a basis for future analysis.

[0153] In a more specific implementation, the system also stores the current analysis process as "organizational experience" in a memory bank (i.e., a process-aware memory bank) for reuse in subsequent tasks, thereby achieving the accumulation and inheritance of knowledge.

[0154] At this point, the system has completed a closed loop from natural language input to intelligent analysis and then to decision support.

[0155] In one specific possible embodiment, Figure 7 This is a flowchart of an intelligent analysis method for meteorological satellite data provided in an embodiment of this application, such as... Figure 7 As shown, the method flow may include the following steps 1 to 8.

[0156] Step 1: The user inputs a natural language command.

[0157] Users submit their analysis requests in natural language, such as "Help me find out if the satellite has performed any XX missions in the past 6 hours."

[0158] Step 2: The Natural Language Understanding module parses the intent.

[0159] The system uses the NLU module to parse user commands and extract key entities (time, satellite, mission type, etc.) and analysis intent.

[0160] Step 3: Determine if this is the first analysis.

[0161] 1) If it is the first analysis, start the agent task planning and automatically generate the analysis path.

[0162] 2) If this is not the first time, search the memory to find similar historical analysis processes and recommend reusable analysis paths.

[0163] Step 4: Dynamically select and combine analysis algorithms.

[0164] Based on the analysis objectives, the intelligent agent dynamically calls modules such as data query, feature extraction, anomaly detection, and trend analysis from the algorithm library to form a customized analysis process.

[0165] Step 5: Perform the analysis and generate results.

[0166] The system automatically performs data acquisition, processing, and analysis through a data analysis sandbox, generating intermediate results and visualization charts.

[0167] Step 6: Process-aware memory mechanism.

[0168] The entire process records user actions, system responses, analysis paths, and decision-making basis, forming a traceable chain of analytical behavior.

[0169] Step 7: Output the analysis report and decision recommendations.

[0170] Generate structured analysis reports to provide decision support.

[0171] Step 8: Organize the accumulation and sharing of experience.

[0172] This analysis process will be stored in the memory bank as "organizational experience" for reuse in subsequent tasks, thus realizing the accumulation and inheritance of knowledge.

[0173] Figure 8 This is an architecture diagram of an intelligent meteorological satellite data analysis system provided in an embodiment of this application, such as... Figure 8 As shown, the core functional modules in this architecture are explained.

[0174] 1. User

[0175] Initiate analysis requests through natural language or interactive operations, such as "Help me analyze the satellite power anomalies in the past 24 hours".

[0176] 2. Step Extraction

[0177] Capture user input and actions in real time.

[0178] Analyze high-level intents and transform them into structured analysis steps.

[0179] Output: An executable analysis process fragment.

[0180] 3. Step-by-step memory storage (MemoryStore)

[0181] Persistently save the complete behavioral chain for each analysis.

[0182] Supports version management and audit traceability.

[0183] Build an organizational experience base to achieve knowledge accumulation.

[0184] 4. Step-by-step memory recall

[0185] Based on semantic retrieval historical similarity analysis process.

[0186] Provide historical pattern references to the operation step extraction module.

[0187] Supports intelligent reuse of "similar problems, similar solutions".

[0188] 5. Agent Engine

[0189] The system's brain is responsible for:

[0190] Natural Language Understanding

[0191] Task breakdown and planning

[0192] Process orchestration and scheduling

[0193] Coordinate all modules to complete end-to-end analysis.

[0194] 6. Data Analysis Sandbox

[0195] Provides a secure and isolated execution environment.

[0196] It supports running scripts such as Python and SQL, enabling flexible analysis.

[0197] Ensure that the analysis process is reproducible and verifiable.

[0198] 7. Data Ingest

[0199] Access to multi-source satellite data (observation, telemetry, orbit, etc.).

[0200] Achieve unified data format and spatiotemporal alignment.

[0201] Establish a stable downlink channel with the satellite data source.

[0202] 8. Results Display (Visualization)

[0203] Generate multi-dimensional charts (trend charts, heatmaps, status charts, etc.).

[0204] Supports interactive exploration and exception highlighting.

[0205] Output: Intuitive and interpretable analysis results.

[0206] 9. Recommendations for Handling the Issue

[0207] Recommendations for handling are generated based on rule engines or machine learning models.

[0208] By drawing on successful historical cases, the reliability of our recommendations can be improved.

[0209] Output: Actionable decision recommendations, such as "It is recommended to check the battery charge and discharge control parameters".

[0210] 10. Satellite data source

[0211] It provides raw observation data (visible light, infrared, water vapor channels, etc.) and telemetry data.

[0212] This application deeply integrates natural language understanding capabilities with satellite data analysis processes, significantly lowering the barrier to entry and providing a highly efficient human-computer interaction mode to improve analysis efficiency. It is especially suitable for non-professional users or rapid response in emergency scenarios. Furthermore, it achieves fully automated processing from target to analysis results, realizing a leap from "tool assistance" to "intelligent collaboration," greatly improving the level of intelligence. It no longer relies on expert experience and eliminates the need for manual queries and frequent switching between various tools, significantly improving analysis efficiency. It has significant technological advancements and application promotion value.

[0213] All the above-mentioned optional technical solutions can be combined in any way to form optional embodiments of this application, and will not be described in detail here.

[0214] Figure 9 This is a schematic diagram of the structure of a meteorological satellite data intelligent analysis system provided in an embodiment of this application. See also... Figure 9 The system includes:

[0215] The natural language understanding module is used to receive natural language analysis instructions input by the user, and to perform semantic parsing on the natural language analysis instructions to obtain the analysis intent, wherein the analysis intent includes at least one analysis target and analysis action;

[0216] A task scheduling engine is used to determine whether there is a historical analysis path that is semantically similar to the analysis intent based on the analysis intent; and in response to the absence of a historical analysis path that is semantically similar to the analysis intent, dynamically plan a new analysis path based on the analysis intent, wherein the analysis path includes at least one analysis target and analysis action;

[0217] The task scheduling engine is also used to dynamically select the required algorithm from the algorithm library according to the analysis path to form an analysis process;

[0218] The data analysis execution unit is used to automatically perform the acquisition, processing and analysis operations of meteorological satellite data in the analysis process through a dedicated meteorological satellite data analysis sandbox, and generate the analysis results of the meteorological satellite data.

[0219] The operation memory storage module is used to record the natural language analysis instructions input by the user, the system response to the natural language analysis instructions, the analysis results and the analysis path throughout the processing, forming an analysis behavior chain;

[0220] An organizational experience extraction engine is used to extract organizational experience based on the analysis behavior chain, and the experience is stored by the operation memory storage module.

[0221] The feedback optimization unit is used to generate an analysis report based on the analysis results. The analysis report includes the visualization analysis results of meteorological satellite data and processing suggestions for the natural language analysis instructions.

[0222] The system utilizes a data analysis intelligent agent to automate the entire process from user natural language input to data analysis result output.

[0223] It should be noted that the meteorological satellite data intelligent analysis system provided in the above embodiments is only illustrated by the division of the above functional modules when performing intelligent analysis of meteorological satellite data. In actual applications, the above functions may be assigned to different functional modules as needed, that is, the internal structure of the meteorological satellite data intelligent analysis system may be divided into different functional modules to complete all or part of the functions described above. In addition, the meteorological satellite data intelligent analysis system provided in the above embodiments and the meteorological satellite data intelligent analysis method embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0224] Figure 10This is a schematic diagram of the structure of an electronic device 1000 provided in an embodiment of this application. The electronic device 1000 can vary considerably depending on its configuration or performance. It includes one or more Central Processing Units (CPUs) 1001 and one or more memories 1002. The memories 1002 store at least one computer program, which is loaded and executed by the processor 1001 to implement the intelligent meteorological satellite data analysis method provided in the various method embodiments described above. The electronic device also includes other components for implementing its functions. For example, it may have wired or wireless network interfaces and input / output interfaces for input and output. Details regarding these components are not elaborated upon here.

[0225] The electronic device in the above method embodiments is implemented as a terminal. For example, Figure 11 This is a structural block diagram of a terminal provided in an embodiment of this application. The terminal 1100 can be a portable mobile terminal, such as a smartphone, tablet computer, MP3 (Moving Picture Experts Group Audio Layer III) player, MP4 (Moving Picture Experts Group Audio Layer IV) player, laptop computer, or desktop computer. The terminal 1100 may also be referred to as user equipment, portable terminal, laptop terminal, desktop terminal, or other names.

[0226] Typically, terminal 1100 includes a processor 1101 and a memory 1102.

[0227] Processor 1101 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 1101 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 1101 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 1101 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 1101 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0228] The memory 1102 may include one or more computer-readable storage media, which may be non-transitory. The memory 1102 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 1102 is used to store at least one instruction, which is executed by the processor 1101 to implement the intelligent analysis method for meteorological satellite data provided in the method embodiments of this application.

[0229] In some embodiments, the terminal 1100 may also optionally include a peripheral device interface 1103 and at least one peripheral device. The processor 1101, memory 1102, and peripheral device interface 1103 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 1103 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: a radio frequency circuit 1104, a display screen 1105, a camera assembly 1106, an audio circuit 1107, a positioning assembly 1108, and a power supply 1109.

[0230] Peripheral device interface 1103 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 1101 and memory 1102. In some embodiments, processor 1101, memory 1102 and peripheral device interface 1103 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 1101, memory 1102 and peripheral device interface 1103 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0231] The radio frequency (RF) circuit 1104 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 1104 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 1104 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 1104 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 1104 can communicate with other terminals through at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 11G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 1104 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0232] Display screen 1105 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 1105 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 1101 for processing. In this case, display screen 1105 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 1105, disposed on the front panel of terminal 1100; in other embodiments, there may be at least two display screens, disposed on different surfaces of terminal 1100 or in a folded design; in still other embodiments, display screen 1105 may be a flexible display screen, disposed on a curved or folded surface of terminal 1100. Furthermore, display screen 1105 may be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. The display screen 1105 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0233] The camera assembly 1106 is used to acquire images or videos. Optionally, the camera assembly 1106 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the terminal, and the rear-facing camera is located on the back of the terminal. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 1106 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cool light flash, which can be used for light compensation at different color temperatures.

[0234] The audio circuit 1107 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting the sound waves into electrical signals that are input to the processor 1101 for processing, or input to the radio frequency circuit 1104 for voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each positioned at a different location on the terminal 1100. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 1101 or the radio frequency circuit 1104 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 1107 may also include a headphone jack.

[0235] The positioning component 1108 is used to locate the current geographical location of the terminal 1100 in order to enable navigation or LBS (Location Based Service). The positioning component 1108 can be a positioning component based on the US GPS (Global Positioning System), China's BeiDou system, or Russia's Galileo system.

[0236] Power supply 1109 is used to power the various components in terminal 1100. Power supply 1109 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 1109 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, and a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0237] Those skilled in the art will understand that Figure 11 The structure shown does not constitute a limitation on terminal 1100 and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0238] The electronic device in the above method embodiments is implemented as a server. For example, Figure 12This is a schematic diagram of a server structure provided in an embodiment of this application. The server 1200 can vary significantly due to differences in configuration or performance. It includes one or more Central Processing Units (CPUs) 1201 and one or more memories 1202. The memories 1202 store at least one computer program, which is loaded and executed by the processor 1201 to implement the intelligent meteorological satellite data analysis method provided in the various method embodiments described above. Of course, the server also has wired or wireless network interfaces and input / output interfaces for input and output. The server also includes other components for implementing device functions, which will not be elaborated here.

[0239] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including at least one computer program, which is executable by a processor to perform the intelligent analysis method for meteorological satellite data in the above embodiments. For example, the computer-readable storage medium is a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.

[0240] In an exemplary embodiment, a computer program product or computer program is also provided, the computer program product or computer program comprising one or more lines of program code stored in a computer-readable storage medium. One or more processors of an electronic device read the one or more lines of program code from the computer-readable storage medium, and the one or more processors execute the one or more lines of program code, causing the electronic device to perform the above-described intelligent analysis method for meteorological satellite data.

[0241] In some embodiments, the computer program involved in the present application embodiments may be deployed and executed on a computer device, or executed on multiple computer devices located in one location, or executed on multiple computer devices distributed in multiple locations and interconnected through a communication network. Multiple computer devices distributed in multiple locations and interconnected through a communication network may constitute a blockchain system.

[0242] Those skilled in the art will understand that all or part of the steps of the above embodiments are implemented by hardware, or by a program instructing related hardware to implement them. The program is stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0243] The above description is only an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0244] The foregoing description of specific exemplary embodiments of this application is for illustrative and explanatory purposes. These descriptions are not intended to limit this application to the precise forms disclosed, and it will be apparent that many changes and variations can be made in accordance with the foregoing teachings. The exemplary embodiments were chosen and described in order to explain the specific principles of this application and its practical application, thereby enabling those skilled in the art to implement and utilize various different exemplary embodiments of this application, as well as various different choices and variations. The scope of this application is intended to be defined by the claims and their equivalents.

Claims

1. A method for intelligent analysis of meteorological satellite data, characterized in that, The method includes: The system receives natural language analysis instructions input by the user and performs semantic parsing on the instructions to obtain the analysis intent, which includes at least one analysis target and analysis action. Based on the analytical intent, determine whether there exists a historical analytical path that is semantically similar to the analytical intent; In response to the absence of a historical analysis path that is semantically similar to the analysis intent, a new analysis path is dynamically planned based on the analysis intent, the analysis path including the at least one analysis objective and analysis action; Based on the analysis path, the required algorithms are dynamically selected from the algorithm library to form an analysis process; The algorithm in the analysis process is automatically invoked to perform the acquisition, processing and analysis of meteorological satellite data in the analysis process, and to generate the analysis results of the meteorological satellite data. During the processing, the user's input natural language analysis commands, the system response to the natural language analysis commands, the analysis results, and the analysis path are recorded throughout the process, forming an analysis behavior chain, and stored. Based on the analysis results, an analysis report is generated, which includes the visualization analysis results of meteorological satellite data and processing suggestions for the natural language analysis instructions.

2. The intelligent analysis method for meteorological satellite data as described in claim 1, characterized in that, The step of semantically parsing the natural language analysis command to obtain the analysis intent includes: By using a pre-built natural language understanding module for meteorological satellite data, the natural language analysis instructions are mapped into a set of structured parameters. The set of structured parameters is used as a component of the analysis intent to obtain the analysis intent. The set of structured parameters includes at least the target satellite identifier, time range, geographical region, data type, and analysis action.

3. The intelligent analysis method for meteorological satellite data as described in claim 1, characterized in that, The method further includes: Construct a process-aware memory, which stores the historically executed chain of analytical behaviors; The step of determining whether there exists a historical analysis path semantically similar to the analysis intent based on the analysis intent includes: Based on the analytical intent, check whether there is a historical analytical path in the historically executed analytical behavior chain in the process-aware memory that is semantically similar to the analytical intent. During the processing, the user's input natural language analysis commands, the system response to the natural language analysis commands, the analysis results, and the analysis path are recorded throughout the process, forming an analysis behavior chain, which is then stored, including: During the processing, the system records every step of the user's operation, system response, analysis results and analysis path in real time during the data analysis process. It combines session identifier, user identifier and task type for context binding, and forms an analysis behavior chain in a traceable and revisitable data structure. Based on the large language model, the organizational experience of the analysis behavior chain is extracted to obtain a reusable analysis path. The analysis path is then associated with other data in the analysis behavior chain. The analysis behavior chain is written into the process-aware memory in a structured storage manner, and a version record is generated.

4. The intelligent analysis method for meteorological satellite data as described in claim 1 or 3, characterized in that, The method further includes: In response to the existence of a historical analysis path that is semantically similar to the analysis intent, a matching historical analysis path is extracted from the process-aware memory, wherein the historical analysis path is a reusable analysis path extracted from organizational experience based on the historical analysis behavior chain; The step of dynamically selecting the required algorithm from the algorithm library based on the historical analysis path to form an analysis process is executed.

5. The intelligent analysis method for meteorological satellite data as described in claim 1, characterized in that, The step of dynamically selecting the required algorithm from the algorithm library according to the analysis path to form an analysis process includes: Based on the meteorological satellite data analysis task scenario and meteorological satellite data characteristics indicated by the analysis path, algorithms are dynamically selected, sorted, and combined from professional algorithm services to form an optimal algorithm chain, which is the analysis process.

6. The intelligent analysis method for meteorological satellite data as described in claim 1, characterized in that, The method further includes: The system invokes a dynamic table structure understanding model adapted to meteorological satellite data to detect table structures and map fields from heterogeneous meteorological satellite data sources, generating dynamic data query and analysis strategies for meteorological satellite data. All meteorological satellite data, the dynamic data query and analysis strategies for meteorological satellite data, the data query, algorithm call and result generation during the analysis process are uniformly encapsulated and stored in an independent storage service to obtain a dedicated analysis sandbox for meteorological satellite data. The dedicated analysis sandbox for meteorological satellite data supports the mixed execution of structured query language and data analysis scripts of data analysis agents. The automatic invocation of the algorithm in the analysis process executes the acquisition, processing, and analysis operations of meteorological satellite data in the analysis process, generating the analysis results of the meteorological satellite data, including: The system automatically performs the acquisition, processing, and analysis of meteorological satellite data in the analysis process through the dedicated analysis sandbox for meteorological satellite data, and generates the analysis results of the meteorological satellite data.

7. The intelligent analysis method for meteorological satellite data as described in claim 1 or 6, characterized in that, The analysis results include intermediate analysis results and visualization analysis results; The step of generating an analysis report based on the analysis results includes: Based on the intermediate analysis results and combined with stored historical handling cases, the rule engine and / or machine learning model generate handling suggestions based on the intermediate analysis results. The proposed solutions and the results of the visualization analysis are output together to form an analysis report.

8. A meteorological satellite data intelligent analysis system, characterized in that, The system includes: The natural language understanding module is used to receive natural language analysis instructions input by the user, and to perform semantic parsing on the natural language analysis instructions to obtain the analysis intent, wherein the analysis intent includes at least one analysis target and analysis action; A task scheduling engine is used to determine whether there is a historical analysis path that is semantically similar to the analysis intent based on the analysis intent; and in response to the absence of a historical analysis path that is semantically similar to the analysis intent, dynamically plan a new analysis path based on the analysis intent, wherein the analysis path includes at least one analysis target and analysis action; The task scheduling engine is also used to dynamically select the required algorithm from the algorithm library according to the analysis path to form an analysis process; The data analysis execution unit is used to automatically perform the acquisition, processing and analysis operations of meteorological satellite data in the analysis process through a dedicated meteorological satellite data analysis sandbox, and generate the analysis results of the meteorological satellite data. The operation memory storage module is used to record the natural language analysis instructions input by the user, the system response to the natural language analysis instructions, the analysis results and the analysis path throughout the processing, forming an analysis behavior chain; An organizational experience extraction engine is used to extract organizational experience based on the analysis behavior chain, and the experience is stored by the operation memory storage module. The feedback optimization unit is used to generate an analysis report based on the analysis results. The analysis report includes the visualization analysis results of meteorological satellite data and processing suggestions for the natural language analysis instructions. The system utilizes a data analysis intelligent agent to automate the entire process from user natural language input to data analysis result output.

9. An electronic device, characterized in that, The electronic device includes one or more processors and one or more memories, wherein the one or more memories store at least one computer program, which is loaded and executed by the one or more processors to implement the intelligent analysis method for meteorological satellite data as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The storage medium stores at least one computer program, which is loaded and executed by a processor to implement the intelligent analysis method for meteorological satellite data as described in any one of claims 1 to 7.

Images