Automatic report generation method and system for civil aircraft time sequence data analysis and medium
Through efficient data access and cloud analysis engine, combined with data visualization and reporting templates, the problems of inefficiency and insufficient flexibility in civilian time series data analysis are solved, and rapid and accurate data analysis and personalized report generation are achieved to adapt to diversity Analyze the requirements.
Patent Information
- Application Number
- CN202411424975.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-12
- Publication Date
- 2025-01-07
AI Technical Summary
The existing technology has problems such as inefficient, low accuracy and insufficient flexibility in the analysis and reporting of civil aircraft timing data and reporting. Manual analysis and semi-automation tools are difficult to adapt to changing needs, and automation tools are automated in the generation of reports, There are limitations in terms of format customization and content richness.
Through efficient data access and preprocessing, using the powerful analysis engine deployed in the cloud, it automatically generates analysis reports, and combines data visualization plug-ins and preset report templates to achieve in-depth analysis of civilian timing data and personalized report generation.
It realizes rapid and accurate analysis of large-scale time series data, improves the personalization and applicability of reports, ensures the efficiency and accuracy of data analysis, and adapts to the needs of different analysis scenarios.
Smart Images
Figure CN119272748A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of civil aircraft flight technology, and in particular to a method and system for automatically generating reports for civil aircraft time series data analysis, and a medium. Background Art
[0002] In the field of civil aviation, the analysis and report generation of flight data are very important. The overall development cycle of newly developed civil aircraft in China is long, and the flight data analysis process is heavy, with many sorties and status points. However, the analysis and report generation of civil aircraft time series data currently mainly rely on manual analysis and semi-automatic tools. The basic process of these methods or tools includes data collection, preprocessing, analysis, and report writing. These technologies include the use of database software and professional analysis tools (such as MATLAB or Excel), manual screening of data, or running preset analysis scripts, and manually entering the analysis results (text, analysis tables, analysis charts, etc.) into reports, and then adjusting the format to meet specific report requirements. Although these methods can meet basic analysis needs to a certain extent, they have obvious disadvantages such as low efficiency, low accuracy, and lack of flexibility. The manual writing of analysis reports is time-consuming and error-prone, and semi-automatic tools often cannot adapt well to changing analysis needs. Although some tools such as BI software (business intelligence software) provide a certain degree of automation support, such as automatic generation of charts and some basic text interpretations, these tools still have great limitations in terms of automatic report generation, format customization, and content richness.
[0003] Based on the above problems, the applicant proposed the technical solution of this application. Summary of the invention
[0004] In view of the above-mentioned defects of the prior art, the present invention provides a method, system and medium for automatically generating reports for civil aircraft time series data analysis. Through efficient data access and preprocessing, it ensures that the raw data collected from multiple sources are quickly converted into accurate data that can be analyzed. At the same time, in conjunction with a powerful analysis engine deployed in the cloud, it realizes in-depth analysis of large-scale data sets and automatically generates analysis reports, which can meet the needs of different analysis scenarios in civil aircraft flight and enhance the personalization and applicability of analysis reports.
[0005] In order to achieve the above object, the present invention discloses a method for automatically generating a report for civil aircraft time series data analysis, comprising the following steps:
[0006] Receive raw time series data from various flight test instruments and flight test systems, preprocess the raw time series data, and store the preprocessed standardized time series data in a cloud-based time series database;
[0007] According to different types of civil aircraft subjects, a data analysis algorithm corresponding to the civil aircraft subject is selected from a preset analysis engine, and the standardized time series data is operated using the data analysis algorithm to obtain operation result data;
[0008] Based on the calculation result data, generate data summary and statistical results, and according to the report requirements of the civil aircraft subject, use the data visualization plug-in to convert the calculation result data into a result time series diagram and a result statistical diagram;
[0009] According to a pre-set report template, the data summary and statistical results as well as the result time series diagram and result statistical diagram are filled into the report template, and an analysis report is generated and stored in a cloud server.
[0010] Preferably, the original time series data includes files in multiple data formats, and the multiple data formats include at least txt format, csv format and compressed file format;
[0011] The preprocessing of the original time series data comprises the following steps:
[0012] Performing data cleaning on the original time series data, wherein the data cleaning at least includes removing data points in the original time series data that exceed a set threshold range, filling missing values using an ARIMA model, identifying outliers, and correcting or marking the identified outliers based on context information and adjacent data points;
[0013] The original time series data after data cleaning is standardized, and the data standardization at least includes unifying the data format, aligning the frequency of data points with different sampling frequencies, normalizing the data and unifying the data accuracy.
[0014] Preferably, the cloud-based time series database adopts an IoTDB database, and the standardized time series data is stored in a TsFile format file.
[0015] Preferably, the analysis engine is implemented using Python scripting language, and a data analysis algorithm library for civil aircraft flight tests is established in the analysis engine, and the data analysis algorithm library stores data analysis algorithms and corresponding calling interfaces for different types of civil aircraft subjects.
[0016] Preferably, the data analysis algorithm is used to evaluate key parameters of a civil aircraft during flight, and the key parameters include at least flight performance, flight stability and control effectiveness.
[0017] Preferably, the pre-set report template is set using the FreeMarker template engine, the analysis report generated based on the report template is stored in a document database in binary text format, and the basic information of the analysis report is stored in a relational database, and the basic information includes at least the template name, template version and creation date.
[0018] Preferably, the pre-set report template is displayed in a graphical interface, the front end is constructed using the Vue framework, and the back end uses a REST API interface to achieve graphical loading.
[0019] Preferably, the data summary and statistical results as well as the result timing diagram and result statistical diagram are filled into the report template. Specifically, according to the variable placeholders defined in the report template, the data summary and statistical results as well as the result timing diagram and result statistical diagram are automatically matched to the corresponding template areas, and the template content is generated by the FreeMarker template engine by defining dynamic tags and macros.
[0020] The present invention also discloses a report automatic generation system for civil aircraft time series data analysis, comprising the following modules:
[0021] A data processing module is used to receive raw time series data from various flight test instruments and flight test systems, preprocess the raw time series data, and store the standardized time series data obtained after preprocessing in a time series database in the cloud;
[0022] An analysis engine module, configured to select a data analysis algorithm corresponding to a civil aircraft subject from a preset analysis engine according to different types of civil aircraft subjects, and use the data analysis algorithm to operate the standardized time series data to obtain operation result data;
[0023] A data visualization module, for generating a data summary and statistical results based on the calculation result data, and converting the calculation result data into a result time series diagram and a result statistical diagram using a data visualization plug-in according to the reporting requirements of the civil aircraft subject;
[0024] The report generation module is used to fill the data summary and statistical results, the result time series diagram and the result statistical diagram into the report template according to the pre-set report template, generate an analysis report and store it in the cloud server
[0025] The present invention also discloses a computer-readable storage medium, characterized in that a computer program is stored on the storage medium, and when the computer program is processed and executed, the above-mentioned automatic report generation method for civil aircraft time series data analysis is implemented.
[0026] Compared with the prior art, the present invention has the following beneficial effects:
[0027] 1. The present invention pre-processes the original time series data to provide high-quality and highly consistent standardized time series data for subsequent data analysis, and stores it in cloud time series data, providing real-time sharing and efficient reading for civil aircraft time series data.
[0028] 2. The present invention performs distributed computing by setting up an analysis engine on the cloud to achieve rapid processing of large-scale time series data and ensure the accuracy and efficiency of data analysis.
[0029] 3. The present invention introduces the FreeMarker template engine to design report templates, and realizes automatic report generation and secure sharing of report contents, thereby improving the accessibility and applicability of analysis reports.
[0030] The concept, specific structure and technical effects of the present invention will be further described below in conjunction with the accompanying drawings to fully understand the purpose, characteristics and effects of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] Figure 1 It is a flow chart of the method for automatically generating reports for civil aircraft time series data analysis according to the present invention.
[0032] Figure 2 It is another flow chart of the method for automatically generating reports for civil aircraft time series data analysis of the present invention. DETAILED DESCRIPTION
[0033] In order to make the technical means, creative features, objectives and effects of the invention easier to understand, the invention is further described below with reference to specific diagrams. However, the invention is not limited to the following implementation cases.
[0034] It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings in this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with this technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantive technical significance. Any structural modification, change in proportion or adjustment of size, without affecting the effects and purposes that can be achieved by the present invention, should still fall within the scope of the technical contents disclosed by the present invention.
[0035] In the process of civil aircraft flight testing, due to the diversity of flight test subjects and the complexity of the project, as well as the different sorties and status points of each test flight, the existing analysis methods are usually highly dependent on the professional knowledge and personal experience of the analysis engineer. This dependence results in the need to write the corresponding algorithm formula and code separately for each subject, which not only consumes a lot of resources, but also lacks flexibility and is difficult to adapt to changing needs.
[0036] like Figure 1 As shown, the method for automatically generating reports for civil aircraft time series data analysis disclosed in the present invention includes the following steps:
[0037] Step S1, receiving original time series data from various flight test instruments and flight test systems, preprocessing the original time series data, and storing the standardized time series data obtained after preprocessing in a time series database in the cloud.
[0038] Specifically, during the test flight of civil aircraft, real-time data collection is required, and the time span of data collection is long and the sampling frequency is high, for example, the sampling frequency exceeds 8Hz, and the flight parameters involved are as many as tens of thousands, with large amounts of data, various types, and different formats. The large amount of data generated in this way leads to huge volumes of collected data files, which contain extremely rich information. Different aircraft models and different data collection methods also result in huge differences in the format of the collected time series data files.
[0039] When receiving raw time series data, an efficient parallel job upload method is adopted, and accelerated processing is performed. The data import speed can reach 300-500Mbps. The cloud-based time series database uses the IoTDB database, and the standardized time series data obtained after preprocessing is stored in the TsFile format.
[0040] The original time series data includes files in various data formats, such as txt format, csv format, and compressed file format. For these files in various data formats, the data needs to be standardized through preprocessing to form subsequent standardized time series data.
[0041] It should be noted that time series data refers to a series of data points arranged in time order. In the field of civil aircraft, it usually refers to the data collected by the aircraft at different time points on flight status, performance parameters, etc. The IoTDB database is a data management engine for the collection, storage and analysis of time series data. It is lightweight, high-performance and easy to use. It can perfectly connect to the Hadoop and Spark ecosystems and is suitable for the needs of high-speed writing and complex analysis and query of massive time series data in industrial Internet of Things applications.
[0042] The raw time series data is preprocessed, including data cleaning and data standardization, wherein the data cleaning at least includes removing data points in the raw time series data that exceed a set threshold range, filling missing values using an ARIMA model, identifying outliers, and correcting or marking the identified outliers based on context information and adjacent data points. The data standardization at least includes unifying the data format, aligning the frequency of data points with different sampling frequencies, normalizing the data, and unifying the data accuracy.
[0043] In order to remove obviously invalid data points, a reasonable threshold range is set to identify and remove invalid data points that exceed the normal range. The autoregressive integrated moving average model ARIMA model prediction filling algorithm is used to predict missing values based on historical data trends. Compared with traditional filling methods, it can more effectively maintain the temporal continuity and physical consistency of data. Statistical methods and machine learning techniques such as the isolation forest algorithm are used to identify and process outliers, which can not only identify the anomalies of single data points, but also detect the pattern anomalies of data sequences. After identifying the outliers, suspicious data entries are automatically corrected or marked based on the context information and the relationship between adjacent data points. Data cleaning reduces the adverse effects of conditions such as electronic noise, environmental factors, and mechanical vibration unique to aircraft flight on the accuracy of data analysis, thereby ensuring the accuracy and reliability of data analysis.
[0044] The time series data generated by aircraft flight has the characteristics of multi-source heterogeneity, and the data recorded by different sensors may have different dimensions, units and numerical ranges. In order to ensure that all data can be compared and analyzed on the same bottle, it is necessary to standardize these multi-source data, such as unifying the data format, that is, converting the cleaned data into the unified TsFile file format built into IoTDB, to facilitate subsequent processing and storage. When aligning the data frequency, use the timestamp alignment method to ensure that all data are synchronized according to a unified time base to avoid data misalignment caused by differences in sampling frequencies of different sensors. After that, it is necessary to standardize the data progress, such as unifying the data into the same format in time format, normalizing the data so that the data falls within a unified numerical range, and unifying the accuracy level of the data by retaining a fixed number of decimal places. In some examples, adaptive interpolation algorithms (Spline interpolation, PCHIP interpolation, etc.) and resampling techniques are also used to adapt to the sampling frequencies of different sensors to ensure accurate alignment of data on a unified time axis.
[0045] The standardized time series data is uniformly stored in the cloud time series database IoTDB, avoiding local storage to reduce local storage pressure. This allows for rapid response to massive time series data operations and is no longer limited by local hardware conditions. As a database designed specifically for time series data, IoTDB has an efficient data compression algorithm, fast query response speed, and optimized indexing mechanism, ensuring efficient data reading and real-time processing capabilities, further accelerating the mining and transformation of data value.
[0046] Step S2, according to different types of civil aircraft subjects, select a data analysis algorithm corresponding to the civil aircraft subject from a preset analysis engine, use the data analysis algorithm to operate on the standardized time series data, and obtain operation result data.
[0047] Specifically, the preprocessed standardized time series data is submitted to a preset analysis engine. The analysis engine is implemented in Python scripting language, and a data analysis algorithm library for civil aircraft test flight is established in the analysis engine, and the data analysis algorithm library stores data analysis algorithms and corresponding call interfaces for different types of civil aircraft subjects. The analysis engine uses advanced data analysis algorithms and professional algorithms of related aircraft physics to conduct in-depth analysis of the data, and performs analysis and calculation according to the calculation requirements of different subjects. After the analysis engine is completed, if the analysis results can be successfully generated, the subsequent steps are carried out. If there are problems in the analysis process, the problems are collected and feedback is provided to facilitate subsequent optimization of data processing. The data analysis algorithms used in the analysis engine are, for example, time series analysis, machine learning models, etc. These data analysis algorithms are used to evaluate the key parameters of civil aircraft during flight, and the key parameters include at least flight performance, flight stability and control efficiency. The analysis engine is partially deployed in the cloud, written in Python scripting language libraries such as NumPy, SciPy, and pandas, based on the microservice architecture of the cloud platform, to achieve distributed computing, and use the high performance of the cloud server to ensure the efficiency of the operation.
[0048] Step S3, based on the calculation result data, generate a data summary and statistical results, and according to the reporting requirements of the civil aircraft subject, use a data visualization plug-in to convert the calculation result data into a result timing diagram and a result statistical diagram.
[0049] Specifically, based on the calculation result data generated in step S2, an easy-to-understand data summary and statistical report are generated to provide content materials for subsequent report templates, such as data dimension reduction, feature selection and importance sorting, focusing on key information and removing redundant data. According to the reporting requirements of each subject, the analysis results are plotted into result time series diagrams and analysis statistical diagrams using data visualization plug-ins.
[0050] Step S4, according to a pre-set report template, fill the data summary and statistical results as well as the result time series diagram and result statistical diagram into the report template, generate an analysis report and store it in the cloud server.
[0051] Pre-set report templates are maintained in the template library, which contains various predefined report templates that cover the needs of different flight subjects and analysis scenarios. The template library supports the creation, editing, deletion and version control of templates to ensure the latest and validity of the templates.
[0052] The pre-set report template is set using the FreeMarker template engine. The analysis report generated based on the report template is stored in a document database in binary text format. The basic information of the analysis report is stored in a relational database. The basic information includes at least the template name, template version and creation date. The pre-set report template is displayed in a graphical interface. The front end is built using the Vue framework, and the back end uses the REST API interface to achieve graphical loading. The pre-set report templates in the template library are displayed in real time on the front page. Users can select the required report template through the graphical interface of the front end. The template files in the database are all stored in a specific directory, which is convenient for direct access to the template files through a specific path.
[0053] In some examples, users can also set up custom templates in the FreeMarker template engine, using the FreeMarker template engine's tag mechanism and variable placeholder function to achieve this, and use the visual editor provided by the front-end page to select and adjust the necessary template elements such as text, charts, and tables. After the front-end is submitted, the generated custom template is stored in a specific directory together with the pre-set report template, and is provided to the FreeMarker template engine through the back-end interface to generate a report that meets the custom requirements.
[0054] The FreeMarker template engine uses the variable placeholders defined in the report template to automatically match the data summary and statistical results obtained from the calculation result data generated by the analysis engine to the corresponding template area, and fills the content of each template area by defining dynamic tags and macros, including inserting analysis summaries, statistical charts, key data tables, etc. The variable replacement mechanism fills the content into the preset position of the template, including charts, tables and text paragraphs to automatically generate report content. When dynamically filling data into the template, the format and layout of the report are adjusted at the same time, including automatic line breaks, adjusting chart size, and optimizing page blank areas to ensure the beauty of the report. After that, the FreeMarker template engine is used for dynamic rendering of the report, which can generate reports in different formats, such as pdf, word, excel, etc. It also supports online preview and download, such as using the Apache POI library to export report files.
[0055] It should be noted that the FreeMarker template engine is a Java-based template engine used to generate text output and is often used to generate dynamic web pages, emails, and configuration files. The Apache POI library is a popular Java library used to process Microsoft Office document files, such as Word, Excel, etc., so that these documents can be created and modified without using Microsoft Office software.
[0056] In some examples, online preview of generated analysis reports is provided, and the report content can be viewed without downloading. After confirming the report content, you can choose to download the report to local storage. In order to ensure the security of the report content, the access, preview or download functions of the report are all securely restricted. For example, only users with identity authorization and permission verification can operate, thereby protecting sensitive flight data from unauthorized access. In some examples, user identity authorization and permission verification are in the form of user management.
[0057] In some examples, such as Figure 2 In the flowchart shown, some feedback information will be collected and summarized for subsequent optimization and upgrading. For example, when data preprocessing fails, the user will be reminded to check the data quality; when data analysis fails, the user will be reminded to check the analysis algorithm and parameter settings; when report generation fails, the user will be reminded to check the report template and rendering engine.
[0058] This embodiment addresses the deficiencies in efficiency, accuracy, and adaptability of existing civil aircraft time series data analysis tools. Through efficient data access and preprocessing, it ensures that raw data collected from multiple sources are quickly converted into accurate data that can be analyzed. At the same time, it cooperates with a powerful analysis engine deployed in the cloud to achieve in-depth analysis of large-scale data sets and automatically generate analysis reports, which can meet the needs of different analysis scenarios in civil aircraft flight and enhance the personalization and applicability of analysis reports.
[0059] The second embodiment of the present invention discloses an automatic report generation system for civil aircraft time series data analysis, including a data processing module, an analysis engine module, a data visualization module, and a report generation module.
[0060] A data processing module is used to receive raw time series data from various flight test instruments and flight test systems, preprocess the raw time series data, and store the standardized time series data obtained after preprocessing in a time series database in the cloud;
[0061] An analysis engine module, configured to select a data analysis algorithm corresponding to a civil aircraft subject from a preset analysis engine according to different types of civil aircraft subjects, and use the data analysis algorithm to operate the standardized time series data to obtain operation result data;
[0062] A data visualization module, for generating a data summary and statistical results based on the calculation result data, and converting the calculation result data into a result time series diagram and a result statistical diagram using a data visualization plug-in according to the reporting requirements of the civil aircraft subject;
[0063] The report generation module is used to fill the data summary and statistical results as well as the result time series diagram and result statistical diagram into the report template according to a pre-set report template, generate an analysis report and store it in the cloud server.
[0064] Since the first embodiment corresponds to this embodiment, this embodiment can be implemented in conjunction with the first embodiment. The relevant technical details mentioned in the first embodiment are still valid in this embodiment, and the technical effects that can be achieved in the first embodiment can also be achieved in this embodiment. In order to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied in the first embodiment.
[0065] The third embodiment of the present invention relates to a computer-readable storage medium having a computer program / instruction stored thereon, wherein the computer program / instruction implements the steps of the method in the first embodiment when executed by a processor.
[0066] The preferred specific embodiments of the present invention are described in detail above. It should be understood that ordinary technicians in the field can make many modifications and changes based on the concept of the present invention without creative work. Therefore, all technical solutions that can be obtained by technicians in the technical field based on the concept of the present invention through logical analysis, reasoning or limited experiments on the basis of the prior art should be within the scope of protection determined by the claims.
Claims
1. A method for automatically generating reports for civil aircraft time series data analysis, characterized in that: The following steps are involved: Receive raw time series data from various flight test instruments and flight test systems, preprocess the raw time series data, and store the preprocessed standardized time series data in a cloud-based time series database; According to different types of civil aircraft subjects, a data analysis algorithm corresponding to the civil aircraft subject is selected from a preset analysis engine, and the standardized time series data is operated using the data analysis algorithm to obtain operation result data; Based on the calculation result data, generate data summary and statistical results, and according to the reporting requirements of the civil aircraft subject, use a data visualization plug-in to convert the calculation result data into a result time series diagram and a result statistical diagram; According to a pre-set report template, the data summary and statistical results as well as the result time series diagram and result statistical diagram are filled into the report template, and an analysis report is generated and stored in a cloud server.
2. The method for automatically generating reports for civil aircraft time series data analysis according to claim 1, characterized in that: The original time series data includes files in multiple data formats, and the multiple data formats include at least txt format, csv format and compressed file format; The preprocessing of the original time series data comprises the following steps: Performing data cleaning on the original time series data, wherein the data cleaning at least includes removing data points in the original time series data that exceed a set threshold range, filling missing values using an ARIMA model, identifying outliers, and correcting or marking the identified outliers based on context information and adjacent data points; The original time series data after data cleaning is standardized, and the data standardization at least includes unifying the data format, aligning the frequency of data points with different sampling frequencies, normalizing the data and unifying the data accuracy.
3. The method for automatically generating reports for civil aircraft time series data analysis according to claim 1, characterized in that: The cloud-based time series database uses an IoTDB database, and the standardized time series data is stored in a TsFile format file.
4. The method for automatically generating reports for civil aircraft time series data analysis according to claim 1, characterized in that: The analysis engine is implemented using the Python scripting language. A data analysis algorithm library for civil aircraft flight tests is established in the analysis engine. The data analysis algorithm library stores data analysis algorithms for different types of civil aircraft subjects and corresponding calling interfaces.
5. The method for automatically generating reports for civil aircraft time series data analysis according to claim 4, characterized in that: The data analysis algorithm is used to evaluate key parameters of a civil aircraft during flight, and the key parameters include at least flight performance, flight stability and control effectiveness.
6. The method for automatically generating reports for civil aircraft time series data analysis according to claim 1, characterized in that: The pre-set report template is set using the FreeMarker template engine, and the analysis report generated based on the report template is stored in a document database in binary text format. The basic information of the analysis report is stored in a relational database, and the basic information includes at least the template name, template version and creation date.
7. The method for automatically generating reports for civil aircraft time series data analysis according to claim 6, characterized in that: The pre-set report template is displayed in a graphical interface, the front end is built using the Vue framework, and the back end uses the REST API interface to achieve graphical loading.
8. The method for automatically generating reports for civil aircraft time series data analysis according to claim 6, characterized in that: The data summary and statistical results as well as the result timing diagram and result statistical diagram are filled into the report template. Specifically, according to the variable placeholders defined in the report template, the data summary and statistical results as well as the result timing diagram and result statistical diagram are automatically matched to the corresponding template areas, and the template content is generated by the FreeMarker template engine by defining dynamic tags and macros.
9. An automatic report generation system for civil aircraft time series data analysis, characterized in that: Includes the following modules: A data processing module is used to receive raw time series data from various flight test instruments and flight test systems, preprocess the raw time series data, and store the standardized time series data obtained after preprocessing in a time series database in the cloud; An analysis engine module, configured to select a data analysis algorithm corresponding to a civil aircraft subject from a preset analysis engine according to different types of civil aircraft subjects, and use the data analysis algorithm to operate the standardized time series data to obtain operation result data; A data visualization module, for generating a data summary and statistical results based on the calculation result data, and converting the calculation result data into a result time series diagram and a result statistical diagram using a data visualization plug-in according to the reporting requirements of the civil aircraft subject; The report generation module is used to fill the data summary and statistical results as well as the result time series diagram and result statistical diagram into the report template according to a pre-set report template, generate an analysis report and store it in the cloud server.
10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, which, when processed and executed, implements the method for automatically generating reports for civil aircraft time series data analysis according to any one of claims 1 to 8.