Data precipitation analysis method, device, equipment and computer program product

Abstract

The invention discloses a data precipitation analysis method, device and equipment and a computer program product, and relates to the technical field of big data analysis, and the method comprises the steps: obtaining source data; based on the configuration data, generating a corresponding data operation task according to the source data, and adding the data operation task into a task pool; when it is detected that the task pool is idle, a data operation task is executed based on the large language model, the source data is precipitated and analyzed, and a data analysis result is generated. According to the method, the data precipitation analysis process in the traditional engineering and the existing deep learning technology is simplified by utilizing the excellent text understanding ability and the powerful learning ability of the large language model, and the adaptation cost and the labor cost are reduced, so that an automatic data precipitation analysis process with high adaptability is established; and the automatic working link can be quickly assembled by adapting to each scene. Therefore, the problems that an existing method is poor in universality and high in cost are solved, and the method has the advantages of being lower in cost and higher in universality.

Description

Technical Field

[0001] The present application relates to the field of big data analysis technology, and in particular to a data precipitation analysis method, device, equipment and computer program product. Background Art

[0002] At present, data sedimentation and analysis has gradually become one of the important tasks in various industries. These data include customer data, market data, policy data, etc. in various industries. For example, in the financial and banking fields, there are many years of accumulated customer information, credit rating and other customer data, stock, bond and other secondary market data, financial statements of various related companies, balance sheets and other financial data.

[0003] In this field, data analysts accumulate and analyze these data, which will generate huge commercial value. This is an important part of the work of many financial and banking practitioners. For example, they analyze customer data to understand customer consumption habits, credit ratings, transaction records, etc., so as to provide customers with more personalized services; they analyze market data to understand the changing trends and price fluctuations of the financial market, so as to provide investors with more accurate investment advice.

[0004] Data sedimentation analysis usually has the following characteristics: 1) Timeliness and repetitiveness. Data sedimentation must be carried out continuously and needs to be analyzed and summarized periodically. 2) High professionalism. Data sedimentation requires professionals in the field to organize, clean, and annotate data, and data analysis requires experienced analysts to keenly perceive the laws reflected in the data in order to give valuable conclusions and results. 3) Large amount of data. Data sedimentation analysis needs to rely on rich samples to generate value, so the cost of manual processing is high.

[0005] Due to the above characteristics, the workload of data sedimentation analysis is heavy, and this type of work often requires a lot of time and human resources.

[0006] At present, the main method of data sedimentation and analysis is automation + manual.

[0007] 1. In terms of data sedimentation, we mainly use engineered data processing + manual assistance. According to specific application scenarios and data structures, we develop adaptable data cleaning, integration, and integration programs to process the original data, sediment it into valuable data, and store it in the data warehouse. In this process, professionals are required to design data structures, develop data, and review it.

[0008] 2. In terms of data analysis, it is mainly manual analysis and data mining. Manual analysis is based on the accumulated valuable data. Data analysts with this professional background use some automatic or auxiliary tools (analysis tools, visualization tools) and combine professional ability and personal experience to analyze and summarize the data. Data mining is to use intelligent technologies such as machine learning and deep learning to mine valuable information from data in a certain field, such as predicting customer behavior and detecting fraud.

[0009] Indeed, there are many automated traditional engineering or artificial intelligence methods to improve efficiency in the data sedimentation and analysis process, but the following problems still exist:

[0010] 1) Weak versatility and adaptability. When precipitating and processing the raw data accumulated in different professional fields or different data scenarios in the same field, it is usually necessary to build an adaptive precipitation process; the analysis of valuable data in different professional fields also usually requires the participation of professionals with background knowledge in the field. In addition, the accuracy and reliability of these analysis methods will also be greatly affected by the subjective factors of a small number of analysts.

[0011] 2) High cost. To build an engineering process for data sedimentation analysis, if you do not use artificial intelligence data mining technology and only use traditional engineering development methods, you will need to conduct a series of work such as scenario demand analysis, data structure analysis, software development, system operation and maintenance, etc. The development cost is high and the time cycle is long. After introducing data mining technology, a lot of labeling and model training are required based on the data, and the cost cannot be ignored.

[0012] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0013] The main purpose of this application is to provide a data precipitation analysis method, device, equipment and computer program product, aiming to solve the technical problems of poor versatility and high cost of existing data precipitation analysis methods.

[0014] To achieve the above objectives, the present application proposes a data precipitation analysis method, which includes:

[0015] Get source data;

[0016] Based on the preset configuration data, a corresponding data operation task is generated according to the source data, and the data operation task is added to the preset task pool;

[0017] When it is detected that the task pool is idle, the data operation task is executed based on a preset large language model, the source data is precipitated and analyzed, and a data analysis result is generated.

[0018] In one embodiment, the data operation task includes a precipitation task and an analysis task, and the step of performing the data operation task based on a preset large language model, precipitating and analyzing the source data, and generating a data analysis result includes:

[0019] Based on the large language model, the precipitation task is executed to precipitate the source data to obtain valuable data;

[0020] Based on the large language model, executing the analysis task, performing data analysis on the valuable data, and obtaining analysis data;

[0021] The data analysis result is generated according to the analysis data.

[0022] In one embodiment, the step of executing the precipitation task based on the large language model, precipitating the source data, and obtaining valuable data includes:

[0023] According to the precipitation task, the source data is standardized to obtain first data;

[0024] Processing the first data by using the large language model to obtain second data;

[0025] The second data is integrated through the large language model to obtain the valuable data.

[0026] In one embodiment, the analysis task includes a global analysis task and a local analysis task. The steps of executing the analysis task based on the large language model and performing data analysis on the valuable data to obtain the analysis data include:

[0027] Based on the global analysis prompt words in the configuration data and according to the global analysis task, a global value assessment is performed on the value data to obtain global analysis data;

[0028] According to the local analysis task, the value data is subjected to local feature analysis by using the large language model to obtain local analysis data;

[0029] The analysis data is obtained according to the global analysis data and the local analysis data.

[0030] In one embodiment, the data analysis result includes a data analysis report and / or a visual data analysis chart, and the step of generating the data analysis result according to the analysis data includes:

[0031] Generate the data analysis report based on the report generation prompt word in the configuration data and the analysis data;

[0032] and / or;

[0033] In response to a preset visualization task, the visualization data analysis chart is generated according to the analysis data.

[0034] In one embodiment, after the step of performing the analysis task based on the large language model and performing data analysis on the valuable data to obtain the analysis data, the step further includes:

[0035] Monitor the precipitation task and analysis task to obtain task execution logs;

[0036] The task execution log, value data, analysis data and data analysis results are stored in a preset database for user query;

[0037] When it is detected that the precipitation task or analysis task is executed abnormally, an alarm message is generated and sent to the user terminal so that the user can manually intervene in the processing.

[0038] In one embodiment, before the step of generating corresponding data operation tasks according to the source data based on the preset configuration data and adding the data operation tasks to the preset task pool, the step further includes:

[0039] Get basic configuration information and data analysis samples;

[0040] In response to the prompt word configuration request, generating a first prompt word according to a preset initial prompt word template;

[0041] Generate a personalized prompt word template according to the first prompt word and the data analysis sample;

[0042] The configuration data is generated according to the basic configuration information and the personalized prompt word template.

[0043] In addition, to achieve the above purpose, the present application also proposes a data precipitation analysis device, the data precipitation analysis device comprising:

[0044] A data acquisition module, used for acquiring source data;

[0045] A task generation module, used to generate corresponding data operation tasks according to the source data based on preset configuration data, and add the data operation tasks to a preset task pool;

[0046] The result generation module is used to execute the data operation task based on a preset large language model when it is detected that the task pool is idle, to precipitate and analyze the source data, and to generate a data analysis result.

[0047] In addition, to achieve the above-mentioned purpose, the present application also proposes a data precipitation analysis device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the data precipitation analysis method described above.

[0048] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the data precipitation analysis method described above are implemented.

[0049] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the data precipitation analysis method described above.

[0050] This application provides a data precipitation analysis method, which uses the excellent text understanding ability and powerful learning ability of the large language model to simplify the data precipitation analysis process in traditional engineering and existing deep learning technology, so as to reduce the adaptation cost and the human cost of professional participation, thereby building a set of highly adaptable automated data precipitation analysis system processes, which can adapt to various scenarios and quickly assemble a data precipitation analysis automated work link. Thus, the technical problems of poor versatility and high cost of existing data precipitation analysis methods are solved, and it has the advantages of lower cost and greater versatility. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0053] Figure 1 A schematic diagram of a process flow provided for the first embodiment of the data precipitation analysis method of this application;

[0054] Figure 2 A schematic diagram of the process flow provided for Example 2 of the data precipitation analysis method of this application;

[0055] Figure 3 A schematic diagram of the system architecture of the data precipitation analysis method provided in Embodiment 1 or 2 of the present application;

[0056] Figure 4 A brief flow chart of the data precipitation analysis method provided in Example 1 or 2 of the present application;

[0057] Figure 5 This is a schematic diagram of the module structure of the data precipitation analysis device according to an embodiment of the present application;

[0058] Figure 6 Schematic diagram of the device structure of the hardware operating environment involved in the data precipitation analysis method in the embodiment of the present application.

[0059] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0060] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0061] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0062] The main solutions of the embodiments of this application are:

[0063] Get source data;

[0064] Based on the preset configuration data, a corresponding data operation task is generated according to the source data, and the data operation task is added to the preset task pool;

[0065] When it is detected that the task pool is idle, the data operation task is executed based on a preset large language model, the source data is precipitated and analyzed, and a data analysis result is generated.

[0066] Although there are many automated traditional engineering or artificial intelligence methods in existing technologies to improve efficiency, the following problems still exist:

[0067] 1) Weak versatility and adaptability. When precipitating and processing the raw data accumulated in different professional fields or different data scenarios in the same field, it is usually necessary to build an adaptive precipitation process; the analysis of valuable data in different professional fields also usually requires the participation of professionals with background knowledge in the field. In addition, the accuracy and reliability of these analysis methods will also be greatly affected by the subjective factors of a small number of analysts.

[0068] 2) High cost. If you build an engineering process for data accumulation and analysis without using artificial intelligence data mining technology and only use traditional engineering development methods, you will need to conduct a series of work such as scenario demand analysis, data structure analysis, software development, system operation and maintenance, etc. The development cost is high and the time cycle is long. After introducing data mining technology, a lot of labeling and model training are required based on the data, and the cost cannot be ignored.

[0069] This application provides a solution that uses the excellent text understanding ability and powerful learning ability of the large language model to simplify the data precipitation analysis process in traditional engineering and existing deep learning technology to reduce the adaptation cost and the human cost of professional participation, thereby building a set of highly adaptable automated data precipitation analysis system processes that can adapt to various scenarios and quickly assemble an automated work link for data precipitation analysis. As a result, the technical problems of poor versatility and high cost of existing data precipitation analysis methods are solved, with the advantages of lower cost and greater versatility.

[0070] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a data precipitation analysis system, etc. The following takes the data precipitation analysis system as an example to illustrate this embodiment and the following embodiments.

[0071] Based on this, the present application embodiment provides a data precipitation analysis method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the data precipitation analysis method of the present application.

[0072] In this embodiment, the data precipitation analysis method includes steps S10 to S30:

[0073] Step S10, obtaining source data;

[0074] It should be noted that raw data refers to the original data collected before any processing or analysis. It is the starting point of data analysis and can be structured (such as tables in a database) or unstructured (such as text files, social media posts, etc.).

[0075] Step S20, based on preset configuration data, generating corresponding data operation tasks according to the source data, and adding the data operation tasks to a preset task pool;

[0076] The data sedimentation analysis system parses and processes the source data according to the preset configuration data (such as data cleaning rules, conversion rules, analysis templates, etc.), and generates specific data operation tasks. These tasks define a series of operations that need to be performed on the source data, such as data cleaning, conversion, aggregation, etc. The purpose is to convert the source data into a form suitable for further analysis and processing, while ensuring the consistency and automation of data processing, and adding the data operation tasks to the preset task pool.

[0077] It should be noted that the Task Pool is a system for storing and managing pending data operation tasks, allowing the system to schedule and execute tasks based on resource availability and task priority.

[0078] In a feasible implementation manner, before step S20, steps S401 to S404 may also be included:

[0079] Step S401, obtaining basic configuration information and data analysis samples;

[0080] Step S402, in response to the prompt word configuration request, generating a first prompt word according to a preset initial prompt word template;

[0081] Step S403, generating a personalized prompt word template according to the first prompt word and the data analysis sample;

[0082] Step S404: generating the configuration data according to the basic configuration information and the personalized prompt word template.

[0083] The data precipitation analysis system obtains basic configuration information and data analysis samples. The basic configuration information provides parameters and rules for data processing, while the data analysis samples provide references for specific analysis contexts and expected results. The purpose is to provide necessary context and guidance for subsequent data precipitation analysis tasks, ensuring that the data processing process can be executed according to specific business needs and historical data. Then, in response to the prompt word configuration request, a first prompt word is generated according to a preset initial prompt word template, and then a personalized prompt word template is customized using the first prompt word and the data analysis sample. The personalized prompt word template can more accurately reflect specific business needs and data characteristics, thereby improving the accuracy and efficiency of data processing and analysis, so as to more effectively guide subsequent data operation tasks. Finally, the basic configuration information and the personalized prompt word template are combined to generate configuration data. The basic configuration information provides basic parameters for data processing and analysis, while the personalized prompt word template is customized according to specific business needs and data characteristics. Combining the two, configuration data that meets both general requirements and specific requirements can be generated, which can accurately guide large language models or other data processing tools to perform specific data operation tasks.

[0084] It should be noted that the basic configuration information (Basic Configuration Information) includes basic information such as data source information, data format, and expected data processing flow; Data Analysis Examples (Data AnalysisExamples): past data analysis results or samples, used to provide specific analysis context and expected results; Configuration Data (Configuration Data) is data generated based on the basic configuration information and personalized prompt word templates, used to guide the generation and execution of data operation tasks.

[0085] In this implementation, by obtaining basic configuration information and data analysis samples, the system can customize the data processing process according to specific business needs and historical data, improve the pertinence and effectiveness of data processing, and use the preset initial prompt word template and personalized prompt word template to automatically generate accurate configuration data to guide the execution of precipitation tasks and analysis tasks, reduce manual intervention, and improve efficiency. The personalized prompt word template enables the system to adapt to different data characteristics and analysis needs, and improve the flexibility and adaptability of data processing. By accurately configuring data, the system can more effectively allocate resources, perform data operation tasks, and avoid resource waste. The configuration data generated by combining basic configuration information and personalized prompt word templates can more accurately guide the large language model to perform data precipitation and analysis tasks, and improve the accuracy of the results. Users can participate in the customization of the data processing process through configuration requests, and enhance the user's trust and satisfaction with the data processing results. As a result, not only the automation and intelligence level of the data processing process is improved, but also the adaptability and user experience of the system are enhanced, and some common technical problems and technical defects in data processing are solved.

[0086] Step S30, when it is detected that the task pool is idle, the data operation task is executed based on a preset large language model, the source data is precipitated and analyzed, and a data analysis result is generated.

[0087] The data sedimentation and analysis system monitors the status of the task pool. Once it detects that the task pool is idle, the system executes data operation tasks based on the preset large language model, sediments and analyzes the source data, and generates data analysis results. The purpose is to use idle resources to efficiently perform data operation tasks, and at the same time use the powerful capabilities of the large language model to deeply analyze the data, thereby generating valuable data analysis results.

[0088] It should be noted that the Large Language Model is a pre-trained deep learning model that specializes in processing and understanding natural language data and can perform complex text analysis and generation tasks.

[0089] This embodiment provides a data precipitation analysis method, which uses the excellent text understanding ability and powerful learning ability of the large language model to simplify the data precipitation analysis process in traditional engineering and existing deep learning technology, so as to reduce the adaptation cost and the human cost of professional participation, thereby building a set of highly adaptable automated data precipitation analysis system processes, which can adapt to various scenarios and quickly assemble a data precipitation analysis automated work link. As a result, the technical problems of poor versatility and high cost of existing data precipitation analysis methods are solved, and it has the advantages of lower cost and greater versatility.

[0090] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can refer to the above introduction, and will not be repeated later. Figure 2 The data operation task includes a precipitation task and an analysis task. Step S30 includes steps S301 to S303:

[0091] Step S301, based on the large language model, executing the precipitation task, precipitating the source data, and obtaining valuable data;

[0092] Step S302, executing the analysis task based on the large language model, performing data analysis on the valuable data, and obtaining analysis data;

[0093] Step S303: generating the data analysis result according to the analysis data.

[0094] The data precipitation analysis system uses the powerful text understanding and processing capabilities of the large language model (LLM) to perform precipitation tasks, conduct in-depth analysis and processing of source data to extract valuable information for subsequent analysis, namely, value data. The large language model can identify patterns, trends and key information in the data, thereby performing effective data precipitation. The purpose is to extract useful information from a large amount of source data that may contain noise, laying a solid foundation for subsequent in-depth analysis. Then, the large language model (LLM) is used to perform analysis tasks and conduct in-depth analysis of the precipitated value data. The large language model can understand complex language structures and semantics, thereby performing advanced data analysis tasks such as sentiment analysis, topic modeling, trend prediction, etc. The purpose is to extract deeper insights and information from value data to provide support for decision-making. Finally, the analysis data is converted into understandable and actionable data analysis results, which usually includes data aggregation, interpretation and visualization so that users can quickly grasp the key information and insights of the data. The purpose is to convert complex analysis data into an easy-to-understand format so that non-technical users can also obtain valuable information from it to support decision-making.

[0095] In a feasible implementation, step S301 may include steps S3011 to S3013:

[0096] Step S3011, performing standardization processing on the source data according to the precipitation task to obtain first data;

[0097] Step S3012, processing the first data by using the large language model to obtain second data;

[0098] Step S3013: Integrate the second data through the large language model to obtain the valuable data.

[0099] The data precipitation analysis system standardizes the source data according to the precipitation task. Standardization is an important step in data preprocessing. It involves converting the source data into a unified format and standard for subsequent processing and analysis. This process may include data cleaning, format conversion, data normalization, etc. The purpose of obtaining the first data is to ensure the consistency and compatibility of the data so that the data can be effectively processed and analyzed, and reduce analysis errors caused by inconsistent data formats or data quality problems. Then, the powerful natural language processing capabilities of the large language model (LLM) are used to deeply process the first data that has undergone preliminary standardization, extract deeper information and knowledge from the first data, and convert the original data into second data containing rich semantic information to provide support for further data analysis and decision-making. The large language model can understand and process complex language structures and perform advanced tasks such as entity recognition, relationship extraction, and sentiment analysis. Finally, the capabilities of the large language model (LLM) are used to integrate the second data, that is, the data that has undergone preliminary processing, extract coherent and meaningful insights from scattered information, and convert them into valuable data that can be directly used for decision-making or further analysis.

[0100] In this implementation, the problems of data overload and low efficiency of information extraction are solved by filtering and refining data through sedimentation tasks. The consistency and traceability of data are ensured through a unified data processing process and data integration, and the quality of data management is improved. Data standardization processing solves the problem of inconsistent data formats, so that data can be processed compatibly by different systems and tools. The advanced analysis function of the large language model is used to improve the depth and breadth of information extraction and solve the problem of insufficient depth of data analysis. Data rules are implemented in the data integration process, which strengthens data management and control capabilities and helps ensure data accuracy, consistency and security. Through data integration, the reusability of data is improved, the cost of data processing is reduced, and the efficiency of data utilization is improved.

[0101] In another feasible implementation, the analysis task includes a global analysis task and a local analysis task, and step S302 may include steps S3021 to S3023:

[0102] Step S3021, based on the global analysis prompt words in the configuration data and according to the global analysis task, performing a global value assessment on the value data to obtain global analysis data;

[0103] Step S3022, according to the local analysis task, using the large language model, performing local feature analysis on the value data to obtain local analysis data;

[0104] Step S3023: obtaining the analysis data according to the global analysis data and the local analysis data.

[0105] The data precipitation analysis system uses the global analysis prompts provided in the configuration data to guide the large language model to conduct a comprehensive analysis of the valuable data. Through the global analysis of the valuable data, an understanding and evaluation of the overall situation of the data is obtained, which includes identifying the main trends, patterns and key features in the data, and obtaining global analysis data. The global analysis prompts may contain information about the analysis objectives, key indicators and expected results. This information helps the model understand the context and objectives of the analysis. Then, according to the local analysis tasks, the large language model is used to perform local feature analysis on the valuable data, deeply explore the local information in the data, and provide more detailed data analysis results. This can be used to identify specific problems, optimize specific processes or understand the nuances of the data, and obtain local analysis data. Local feature analysis aims to identify and understand specific details and micro patterns in the data, which helps to reveal the deep characteristics and potential local trends of the data. Finally, the global analysis data and the local analysis data are integrated to obtain analysis data. This process may include data fusion, comparative analysis and comprehensive evaluation, with the aim of obtaining a complete data view that includes both macro trends and micro details.

[0106] In this embodiment, by combining global and local analysis tasks, the system can simultaneously consider the macro trends and micro features of the data, solve the limitation problem of a single analysis perspective, and the automated analysis process improves the speed of data processing and solves the problem of low efficiency of traditional manual analysis. The advanced analysis function of the large language model is used to improve the depth and breadth of information extraction and solve the problem of insufficient accuracy of data analysis. The system filters and refines data through sedimentation tasks, solving the problems of data overload and low efficiency of information extraction. The detailed global and local analysis results provide strong support for decision-making and solve the problem that traditional data analysis results are difficult to directly apply to decision-making. The automated data analysis process can provide real-time or near real-time data analysis results and solve the problem of insufficient timeliness of traditional report generation methods. The application of large language models reduces the need for manual intervention, reduces labor costs and time consumption, and improves the efficiency of report generation.

[0107] In another feasible implementation, the data analysis result includes a data analysis report and / or a visual data analysis chart, and step S303 may include steps S3031 to S3032:

[0108] Step S3031, generating the data analysis report based on the report generation prompt words in the configuration data and the analysis data;

[0109] and / or;

[0110] Step S3032, in response to a preset visualization task, generating the visualization data analysis chart according to the analysis data.

[0111] The data precipitation analysis system generates a data analysis report based on the report generation prompt words in the configuration data and the analysis data. The report can accurately reflect the results of the data analysis and convey it to the users of the report in an easy-to-understand manner. The report generation prompt words may contain key information, such as the structure of the report, the data points that must be included, the specific analysis perspective, etc., which are the basis for generating high-quality data analysis reports, and / or; in response to a preset visualization task, the visual data analysis chart is generated according to the analysis data so that the user can intuitively understand the trends, patterns and relationships in the data. The selection of visualization tools and chart types (such as bar charts, line charts, pie charts, etc.) depends on the nature of the data and the needs of the user, providing an intuitive data representation to help users quickly grasp the key information and insights of the data and enhance the comprehensibility and attractiveness of the data.

[0112] It should be noted that the Data Analysis Report is a detailed document generated based on the analysis data, which contains the interpretation, summary and prediction of the data. Visualized Data Analysis Charts are graphical representations generated based on the analysis data, such as bar charts, line charts, pie charts, etc., which are used to display data intuitively. Report Generation Prompt is an instruction or prompt in the configuration data, which is used to guide the generation of data analysis reports.

[0113] In this embodiment, automated report generation and intuitive visual charts help solve the problem of information overload and improve the efficiency of information extraction. The automated report generation process can provide real-time or near real-time data analysis results, solving the problem of insufficient timeliness of traditional report generation methods. Automated report generation reduces the need for manual intervention, reduces labor costs and time consumption, and improves the efficiency of report generation. Detailed data analysis reports and intuitive visual charts provide strong support for decision-making, solving the problem that traditional data analysis results are difficult to directly apply to decision-making. Through a variety of visual charts, the system can present data in a variety of ways, solving the problem of a single data presentation method.

[0114] In another feasible implementation manner, after step S302, steps S501 to S503 may also be included:

[0115] Step S501, monitoring the precipitation task and the analysis task to obtain a task execution log;

[0116] Step S502, storing the task execution log, value data, analysis data and data analysis results in a preset database for user query;

[0117] Step S503: when it is detected that the precipitation task or analysis task is executed abnormally, an alarm message is generated and sent to the user terminal so that the user can manually intervene in the process.

[0118] The data precipitation analysis system monitors the execution process of precipitation tasks and analysis tasks in real time to capture and record the running status, performance indicators and any abnormal conditions of the tasks, and obtain the task execution log. Monitoring can be achieved through logging, performance counters, exception capture and other technologies. The purpose is to ensure that the execution history of the task can be tracked and reviewed, which is very important for troubleshooting, performance optimization and business auditing. Then the task execution log, value data, analysis data and data analysis results are transferred from temporary storage or memory to a persistent storage system, that is, the preset database. The database provides a structured way to store and manage these data so that they can be effectively retrieved and analyzed, ensuring the persistent storage and easy access of the data so that users can query and analyze the data at any time, thereby improving the availability and reuse of the data. Based on the real-time monitoring of precipitation tasks and analysis tasks, the system can identify any deviation from the expected behavior or performance indicators, which may indicate that an error or abnormality has occurred during the execution of the task. Once an abnormality is detected, the system will automatically generate an alarm message and send it to the user terminal through the preset communication channel to ensure that when there is a problem with the task execution, the user can be informed in time and take necessary manual intervention measures to avoid data loss, processing errors or system failures.

[0119] It should be noted that the task execution log (Task Execution Logs) records detailed information during the execution of sedimentation tasks and analysis tasks, including start time, end time, execution status, etc.

[0120] In this implementation, through real-time monitoring and logging, the problem of insufficient data monitoring is solved, and the monitoring and auditing capabilities of data processing processes are enhanced. Persistent data storage solves the problems of data loss and inconsistency, ensuring the integrity and reliability of data. Timely anomaly detection and alarm mechanisms solve the problem of abnormal response delays, and improve the response speed and processing efficiency to abnormal situations. Enhanced data security measures, such as zero-trust storage and data encryption, solve data security issues and protect data from unauthorized access and leakage risks. Optimized data processing technologies, such as near-data computing and data indexing, solve data processing performance bottlenecks and improve data processing speed and efficiency. Optimization of data storage and management improves data management and query efficiency, allowing users to quickly access and analyze data.

[0121] In this embodiment, by combining the precipitation task and the analysis task, the system can directly process and generate data analysis results from the source data, realize the complete process from data input to insight output, and use the powerful capabilities of the large language model to enable the system to deeply understand the data content, perform complex data precipitation and analysis tasks, and extract the deep value in the data. The automated precipitation and analysis process reduces the need for manual intervention and improves the speed and efficiency of data processing. Through the precipitation task, the system can extract valuable information from a large amount of source data and provide high-quality input for subsequent analysis. The analysis task based on the large language model can more accurately identify patterns and trends in the data and improve the quality of the analysis results. By generating detailed data analysis results, the system supports complex decision-making based on data and improves the scientificity and effectiveness of decision-making. As a result, not only the automation and intelligence level of data processing is improved, but also the value mining of data and the application ability of analysis results are enhanced, while solving some common technical problems and technical defects in data processing and analysis.

[0122] For example, in order to help understand the implementation process of the data precipitation analysis method obtained by combining the first embodiment and the second embodiment, please refer to Figure 3 and Figure 4 , Figure 3 A schematic diagram of the system architecture of the data precipitation analysis method provided in Embodiment 1 or 2 of the present application, Figure 4 A brief flow chart of the data precipitation analysis method provided in Example 1 or 2 of the present application, specifically:

[0123] The data sedimentation analysis system consists of the following three layers: user layer, service layer and storage layer. Figure 3 The system architecture and the core modules included in each layer of the architecture are shown.

[0124] The main function of the user layer is to support the interaction between the system and users, so that the system obtains user needs and users obtain system feedback. The service layer will generate corresponding data sedimentation or analysis tasks based on user needs, process the data accordingly, and produce results. It will also record logs in each link and issue early warnings for failed tasks. The storage layer is used to manage user data, log data and sedimented value data, providing a data basis for each service of the service layer.

[0125] The important modules and functions in the data precipitation analysis system are as follows:

[0126] 1) Tenant management: For different data scenarios, tenants are used as carriers. After the user registers in the system, the system creates a tenant for the user. Each tenant requires the user to fill in the relevant personalized information for data processing. Subsequent specific data processing work will depend on the tenant and configuration information.

[0127] 2) Configuration Center: For different tenants, users need to add basic configurations for subsequent data processing. The core configuration is divided into project configuration and prompt word configuration. 1) Project configuration, including basic data source configuration, data precipitation processing steps (such as whether to clean data, data processing methods and data integration mapping tables, etc.), processing cycle, processing start time, etc.; 2) Prompt word configuration, the capabilities of the large language model need to be triggered by prompt words. The system will recommend prompt words suitable for data precipitation and analysis. Users can optimize based on their own needs based on the recommendations, and finally use it as a fixed configuration for subsequent large language model-assisted data precipitation or analysis.

[0128] 3) Result query: Users need to query the results of the system's data processing, including 1) querying and maintaining valuable data after intermediate data precipitation, so as to better promote the development of data analysis; 2) obtaining the final data analysis results; 3) obtaining the visualization results of data analysis; 4> checking the logs in each link, etc.

[0129] 4) Scheduling service: An important service of the service layer is a scheduler. The scheduling service generates a task pool, starts executing specific data processing tasks according to a tenant configuration, calls corresponding services, and promotes efficient operation of the system.

[0130] 5) Log and alarm services: important auxiliary services of the service layer, whose main functions are to monitor the progress of data services, record logs or issue warnings for abnormalities.

[0131] The overall processing flow of this embodiment is as follows: Figure 4 As shown, it mainly includes 6 steps, among which steps 0, 1, and 5 are interactions between the user and the system; the other steps are internal operations of the system.

[0132] 0) Users register or log in to their own tenants in the system: In personalized data scenarios, users register tenants or provide tenant information when logging in for subsequent configuration management and task result query.

[0133] 1) Configuration settings: The user fills in the basic configuration information including:

[0134] a) Link information of the data source in this scenario or uploaded source data;

[0135] b) If available, the data structure mapping table between source data and sedimentation data can be provided (optional);

[0136] c) Steps to process source data, including sedimentation, analysis, visualization, etc., can be selected singly or multiple times, and specific operations in the sedimentation, analysis, and visualization steps can be selected singly or multiple times - sedimentation includes: 1) Data standardization: cleaning special characters, unifying uppercase and lowercase, converting traditional Chinese characters, etc. for core text fields; 2) Chart standardization: extracting content from images and tables in core content - images will be subject to text recognition extraction or image content interpretation and description, and tables will be converted to MarkDown format or structured storage to ensure that the chart content is standardized into a text form that is easy for subsequent large language models to understand and use; the analysis configuration is further divided into two parts: data summary and key point extraction, focusing on global and local analysis respectively.

[0137] d) Setting the cycle or trigger conditions of data processing tasks, such as weekly processing or adding 10,000 new data items to process;

[0138] e) Other information such as the mailbox for receiving alarm emails, the number for receiving SMS messages, etc.

[0139] In addition, prompt words need to be configured or maintained: when configuring the precipitation and analysis operations in c), some operations will be completed in conjunction with the large language model, such as interpreting the image content in precipitation, summarizing the data and extracting key points in analysis, etc. These operating systems will provide common prompt words, but still allow 1) the system to recommend prompt words, and users can change them according to the recommended prompt word templates; 2) in order to make the data processing effect better, users can provide several data samples before and after processing, and the system will integrate them into the prompt words to enhance the processing effect of the large language model; 3) after the first two steps, users will generate multiple personalized prompt word templates for different operations, which can be mounted on specific operations for use.

[0140] 2) Task Scheduling: The scheduling service will continuously poll and check the configuration information of each tenant, and then add the corresponding data operation tasks to the task pool at the time required by the configuration information. If the task pool is idle, the specific operation task (precipitation, analysis, visualization, etc.) will be started immediately.

[0141] 3) Data precipitation: Generally, the data precipitation service performs precipitation operations according to the user's configuration. The basic steps include data standardization, processing and integration. a) The system cleans the source data according to the configuration requirements, removes data with null values ​​and large deviations, and if the user configures standardization, performs capitalization unification, traditional and simplified conversion, etc.; b) Data processing, if configured, can use the text analysis capabilities of the large language model to calibrate and polish the values ​​of the fields in the source data, convert tables, extract image content, etc.; c) If there is a mapping table of the source data and value data structure in the configuration, it is mapped through the mapping table engineering. It is also possible to map after understanding the mapping table through the large language model; if there is no mapping table, the source data can only be integrated line by line after the large language model learns the examples of the data before and after the user configuration. The data precipitation service will eventually output the value data after cleaning, calibration, and integration. As the object of data analysis, the value data will be stored and can be queried and changed by the user through the user end.

[0142] 4) Data analysis: The system's data analysis of valuable data includes three parts. a) Global data analysis: With the help of the analysis capabilities of the large language model, the global value of the valuable data is evaluated in conjunction with the global analysis prompts configured by the user, and the overall evaluation, trend, and suggestions of the data are given; b) Local data analysis: More attention is paid to extracting local information and anomalies, and local features such as key points, labels, and key questions and answers are extracted based on prompts; c) Data analysis report generation: Based on the prompts generated in the report, the data analysis report is generated according to the results of global and local analysis according to user requirements. Finally, if there is a visualization requirement, the HTML style of the corresponding visualization chart can be generated based on the data characteristics, and then the user's visualization needs can be met by using engineering rendering.

[0143] 5) Result query: All products of data precipitation and analysis will be stored in the corresponding database, and the result query service supports users to query the above content; at the same time, the logs in each process are also stored in the log database, and users can query the logs through this service. In addition to users actively pulling to obtain results, the query service supports push, for example, a) after the data operation is completed, the completion message will be pushed to the user for easy reference; b) task abnormalities will send an alarm to the user to remind manual intervention.

[0144] Compared with the prior art, the data precipitation method described in this embodiment has the following advantages:

[0145] 1) High degree of automation: The automated data precipitation and analysis mode based on a large language model can automatically complete the data precipitation and analysis work that is suitable for the scenario, with little or no human intervention required.

[0146] 2) Strong versatility: It is applicable to various scenarios and fields, and is not restricted to specific industries or fields. This enables this method to be widely used in various business scenarios and fields, improving the flexibility and adaptability of enterprises.

[0147] 3) Adopting an automated data precipitation and analysis model based on a large language model, it is easy to expand and upgrade. With the development of large language model technology and changes in business needs, it can be continuously optimized and improved to meet the needs of enterprises.

[0148] 4) High data accuracy: Data analysis is based on the emergence capability of large language models and is rooted in massive data analysis, eliminating the influence of subjective factors of individual analysts.

[0149] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the data precipitation analysis method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0150] This application also provides a data precipitation analysis device, please refer to Figure 5 , the data precipitation analysis device comprises:

[0151] A data acquisition module 10, used to acquire source data;

[0152] The task generation module 20 is used to generate corresponding data operation tasks according to the source data based on the preset configuration data, and add the data operation tasks to the preset task pool;

[0153] The result generation module 30 is used to execute the data operation task based on a preset large language model, precipitate and analyze the source data, and generate a data analysis result when it is detected that the task pool is idle.

[0154] Optionally, the data operation task includes a precipitation task and an analysis task, and the result generation module 30 is further used to:

[0155] Based on the large language model, the precipitation task is executed to precipitate the source data to obtain valuable data;

[0156] Based on the large language model, executing the analysis task, performing data analysis on the valuable data, and obtaining analysis data;

[0157] The data analysis result is generated according to the analysis data.

[0158] Optionally, the result generating module 30 is further used for:

[0159] According to the precipitation task, the source data is standardized to obtain first data;

[0160] Processing the first data by using the large language model to obtain second data;

[0161] The second data is integrated through the large language model to obtain the valuable data.

[0162] Optionally, the analysis task includes a global analysis task and a local analysis task, and the result generation module 30 is further used to:

[0163] Based on the global analysis prompt words in the configuration data and according to the global analysis task, a global value assessment is performed on the value data to obtain global analysis data;

[0164] According to the local analysis task, the value data is subjected to local feature analysis by using the large language model to obtain local analysis data;

[0165] The analysis data is obtained according to the global analysis data and the local analysis data.

[0166] Optionally, the data analysis result includes a data analysis report and / or a visual data analysis chart, and the result generation module 30 is further used to:

[0167] Generate the data analysis report based on the report generation prompt word in the configuration data and the analysis data;

[0168] and / or;

[0169] In response to a preset visualization task, the visualization data analysis chart is generated according to the analysis data.

[0170] Optionally, the result generating module 30 is further used for:

[0171] Monitor the precipitation task and analysis task to obtain task execution logs;

[0172] The task execution log, value data, analysis data and data analysis results are stored in a preset database for user query;

[0173] When it is detected that the precipitation task or analysis task is executed abnormally, an alarm message is generated and sent to the user terminal so that the user can manually intervene in the processing.

[0174] Optionally, the task generation module 20 is further used to:

[0175] Get basic configuration information and data analysis samples;

[0176] In response to the prompt word configuration request, generating a first prompt word according to a preset initial prompt word template;

[0177] Generate a personalized prompt word template according to the first prompt word and the data analysis sample;

[0178] The configuration data is generated according to the basic configuration information and the personalized prompt word template.

[0179] The data precipitation analysis device provided by the present application adopts the data precipitation analysis method in the above embodiment, which can solve the technical problems of poor versatility and high cost of the existing data precipitation analysis method. Compared with the prior art, the beneficial effects of the data precipitation analysis device provided by the present application are the same as the beneficial effects of the data precipitation analysis method provided by the above embodiment, and the other technical features in the data precipitation analysis device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0180] The present application provides a data precipitation analysis device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the data precipitation analysis method in the above-mentioned embodiment one.

[0181] Reference below Figure 6 , which shows a schematic diagram of the structure of a data precipitation analysis device suitable for implementing the embodiment of the present application. The data precipitation analysis device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The data sedimentation analysis device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0182] like Figure 6As shown, the data precipitation analysis device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the data precipitation analysis device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the data precipitation analysis device to communicate with other devices wirelessly or wired to exchange data. Although the data precipitation analysis device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided alternatively.

[0183] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0184] The data precipitation analysis device provided by the present application adopts the data precipitation analysis method in the above embodiment, which can solve the technical problems of poor versatility and high cost of the existing data precipitation analysis method. Compared with the prior art, the beneficial effects of the data precipitation analysis device provided by the present application are the same as the beneficial effects of the data precipitation analysis method provided by the above embodiment, and the other technical features in the data precipitation analysis device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0185] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0186] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0187] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, the computer-readable program instructions being used to execute the data precipitation analysis method in the above-mentioned embodiment.

[0188] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0189] The computer-readable storage medium may be included in the data precipitation analysis device; or it may exist independently without being assembled into the data precipitation analysis device.

[0190] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the data precipitation analysis device, the data precipitation analysis device:

[0191] Get source data;

[0192] Based on the preset configuration data, a corresponding data operation task is generated according to the source data, and the data operation task is added to the preset task pool;

[0193] When it is detected that the task pool is idle, the data operation task is executed based on a preset large language model, the source data is precipitated and analyzed, and a data analysis result is generated.

[0194] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0195] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0196] The modules involved in the embodiments of the present application may be implemented by software or hardware, wherein the name of the module does not limit the unit itself in some cases.

[0197] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned data precipitation analysis method, and can solve the technical problems of poor versatility and high cost of the existing data precipitation analysis method. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the data precipitation analysis method provided in the above-mentioned embodiment, and will not be repeated here.

[0198] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned data precipitation analysis method when executed by a processor.

[0199] The computer program product provided by the present application can solve the technical problems of poor versatility and high cost of the existing data precipitation analysis method. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the data precipitation analysis method provided by the above embodiment, which will not be repeated here.

[0200] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A data precipitation analysis method, characterized in that: The method comprises: Get source data; Based on the preset configuration data, a corresponding data operation task is generated according to the source data, and the data operation task is added to the preset task pool; When it is detected that the task pool is idle, the data operation task is executed based on a preset large language model, the source data is precipitated and analyzed, and a data analysis result is generated.

2. The method according to claim 1, characterized in that The data operation task includes a precipitation task and an analysis task. The step of performing the data operation task based on a preset large language model, precipitating and analyzing the source data, and generating a data analysis result includes: Based on the large language model, the precipitation task is executed to precipitate the source data to obtain valuable data; Based on the large language model, executing the analysis task, performing data analysis on the valuable data, and obtaining analysis data; The data analysis result is generated according to the analysis data.

3. The method according to claim 2, characterized in that The step of executing the precipitation task based on the large language model, precipitating the source data, and obtaining valuable data includes: According to the precipitation task, the source data is standardized to obtain first data; Processing the first data by using the large language model to obtain second data; The second data is integrated through the large language model to obtain the valuable data.

4. The method according to claim 2, characterized in that The analysis task includes a global analysis task and a local analysis task. The steps of executing the analysis task based on the large language model, performing data analysis on the valuable data, and obtaining the analysis data include: Based on the global analysis prompt words in the configuration data and according to the global analysis task, a global value assessment is performed on the value data to obtain global analysis data; According to the local analysis task, the value data is subjected to local feature analysis by using the large language model to obtain local analysis data; The analysis data is obtained according to the global analysis data and the local analysis data.

5. The method according to claim 2, characterized in that The data analysis result includes a data analysis report and / or a visual data analysis chart. The step of generating the data analysis result according to the analysis data includes: Generate the data analysis report based on the report generation prompt word in the configuration data and the analysis data; and / or; In response to a preset visualization task, the visualization data analysis chart is generated according to the analysis data.

6. The method according to claim 2, characterized in that After the step of executing the analysis task based on the large language model, analyzing the valuable data, and obtaining the analysis data, the method further includes: Monitor the precipitation task and analysis task to obtain task execution logs; The task execution log, value data, analysis data and data analysis results are stored in a preset database for user query; When it is detected that the precipitation task or analysis task is executed abnormally, an alarm message is generated and sent to the user terminal so that the user can manually intervene in the processing.

7. The method according to claim 1, characterized in that Before the step of generating corresponding data operation tasks according to the source data based on the preset configuration data and adding the data operation tasks to the preset task pool, the step further includes: Get basic configuration information and data analysis samples; In response to the prompt word configuration request, generating a first prompt word according to a preset initial prompt word template; Generate a personalized prompt word template according to the first prompt word and the data analysis sample; The configuration data is generated according to the basic configuration information and the personalized prompt word template.

8. A data precipitation analysis device, characterized in that: The device comprises: A data acquisition module, used for acquiring source data; A task generation module, used to generate corresponding data operation tasks according to the source data based on preset configuration data, and add the data operation tasks to a preset task pool; The result generation module is used to execute the data operation task based on a preset large language model when it is detected that the task pool is idle, to precipitate and analyze the source data, and to generate a data analysis result.

9. A data precipitation analysis device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the data precipitation analysis method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the data precipitation analysis method according to any one of claims 1 to 7 are implemented.

Images