Method and device for generating education management report, electronic equipment and storage medium

Abstract

This invention relates to the field of education management technology, and discloses a method, apparatus, electronic device, and storage medium for generating education management reports. The method includes: determining the report type corresponding to the education management problem text and at least one target education statistical indicator corresponding to the report type based on education statistical indicators in the education management problem text; determining the education data corresponding to the education management problem text based on the at least one target education statistical indicator and data constraint information in the education management problem text; extracting features from the education data to obtain data feature information; determining the report template corresponding to the education management problem text based on the report type and data feature information; performing a data analysis task corresponding to the report template to obtain data analysis results; and filling the report template with the data analysis results to obtain an education management report. By implementing the method of this application, the problems of fixed structure and high randomness in the content of education management reports can be solved.

Description

Technical Field

[0001] This invention relates to the field of education management technology, specifically to methods, apparatus, electronic devices, and storage media for generating education management reports. Background Technology

[0002] With the development of information technology, higher education management is gradually moving towards digitalization and intelligence. Higher education administrators need to regularly or irregularly prepare various education management reports, such as undergraduate teaching quality reports, faculty analysis reports, student academic performance warning reports, and annual employment quality reports.

[0003] However, current methods for generating education management reports have some shortcomings. For example, the static template-based method makes it difficult to adapt to diverse data types and analytical needs due to the fixed structure of static templates. The method of generating education management reports based on pre-defined scenarios using large language models (LLMs) results in highly random content due to the LLM's ability to understand and integrate recalled data, making it difficult to guarantee content standardization and consistency. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for generating education management reports, in order to solve the problems of fixed structure and highly random content in education management reports.

[0005] In a first aspect, the present invention provides a method for generating an education management report, the method comprising: determining, based on the education statistical indicators in the education management problem text, a report type corresponding to the education management problem text and at least one target education statistical indicator corresponding to the report type; determining, based on the at least one target education statistical indicator and data constraint information in the education management problem text, education data corresponding to the education management problem text; extracting features from the education data to obtain data feature information; determining, based on the report type and data feature information, a report template corresponding to the education management problem text; performing a data analysis task corresponding to the report template to obtain data analysis results; and filling the report template with the data analysis results to obtain an education management report.

[0006] The method for generating education management reports provided in this embodiment can accurately determine the report type (i.e., business domain) and one or more target education management statistical indicators corresponding to the report type based on the education statistical indicators in the education management problem text. Furthermore, based on at least one target education management statistical indicator and the data constraint information in the education management problem text, it can accurately determine the data support required for the education management report, i.e., the education data. By extracting features from the education data, data feature information can be obtained. Then, based on the report type and data feature information, the report template corresponding to the education management report can be dynamically determined. The data analysis results are obtained by executing the data analysis task corresponding to the report template, and then the data analysis results are filled into the report template. Therefore, a complete education management report with a reasonable structure and highlighting key points can be obtained. Compared with static templates with fixed structures, this application can avoid the mismatch problem of using complex charts with sparse data or displaying only simple conclusions with rich data. Compared with generating education management reports using large language models, it can avoid the problem of strong content randomness.

[0007] In one optional implementation, a report template corresponding to an educational management problem text is determined based on the report type and data feature information. This includes: searching a report template library based on the report type to determine an initial report template corresponding to the educational management problem text. The report template library includes the correspondence between report types and initial report templates. If the data feature information indicates that the data dimension of the educational data is less than a first preset value and the sparsity of the educational data is greater than a second preset value, then the initial report template is determined as the report template. If the data feature information indicates that the data dimension of the educational data is greater than or equal to the first preset value, the sparsity of the educational data is less than or equal to the second preset value, and the volatility of the educational data is greater than or equal to a third preset value, then the related educational statistical indicators among the target educational statistical indicators are determined based on the correlation between the target educational statistical indicators, and a correlation analysis section for performing correlation analysis on the related educational statistical indicators is added to the initial report template to obtain the report template.

[0008] By leveraging the report type corresponding to the educational management issue text, an initial report template can be quickly and accurately determined. Then, based on the data characteristics of educational data, such as data dimensions, sparsity, and volatility, the initial report template can be differentiated. This allows for the rapid identification of a report template that matches the educational management issue text, ensuring that the report remains concise and effective when data is scarce, while strengthening in-depth analysis when data is abundant and highly volatile, fully mining the value of the data, and enhancing the relevance and decision-making reference value of the educational management report.

[0009] In one optional implementation, the report template includes multiple chapters; performing the data analysis task corresponding to the report template to obtain data analysis results includes: retrieving an education indicator library based on the report type to obtain at least one target education statistical indicator corresponding to the report type, the education indicator library including the correspondence between report types and target education statistical indicators; determining the chapter education statistical indicators corresponding to each chapter in the report template from the at least one target education statistical indicator, and determining the chapter data constraint information corresponding to each chapter from the data constraint information; generating a data analysis sub-task corresponding to each chapter based on the chapter education statistical indicators and chapter data constraint information corresponding to each chapter; and performing the data analysis sub-task corresponding to each chapter to obtain a data analysis sub-result corresponding to each chapter, the data analysis results including each data analysis sub-result.

[0010] By leveraging the chapter-specific educational statistics and data constraints for each chapter, a single, large-scale overall data analysis task can be broken down into multiple, more granular, and clearly defined sub-tasks. This reduces the difficulty of implementing complex analytical logic, facilitates modular processing within the system, and enhances the flexibility of task scheduling and execution. Furthermore, each sub-task focuses solely on the corresponding chapter's educational statistics and data constraints, ensuring clear task objectives and a focused processing scope. This reduces interference from irrelevant data and logic, improving the execution efficiency and computational accuracy of individual tasks. Simultaneously, it facilitates independent anomaly monitoring and error localization for each sub-task.

[0011] In one optional implementation, the data analysis results are populated into a report template to obtain an education management report, including: visualizing the data analysis sub-results corresponding to each chapter to obtain visualized data for each chapter; generating text content for each chapter based on the fusion result of the visualized data and the data analysis sub-results; and populating the visualized data and text content for each chapter into the corresponding chapter to obtain the education management report.

[0012] By integrating the visualized data and data analysis sub-results for each chapter, the corresponding text content for each chapter is generated. This ensures that the generated text content is supported by both precise numerical data and intuitively corroborated by visual data. The visualized data and text content for each chapter are then populated into the corresponding chapters, achieving seamless integration between the report content and the template framework. This eliminates the tedious processes of manual typesetting, content proofreading, and chapter matching, significantly shortening the overall education management report generation cycle and improving the efficiency and quality of education management report generation.

[0013] In an optional implementation, the method further includes: for each chapter, performing anomaly detection on the data analysis sub-results of the chapter to obtain anomaly detection results; if the anomaly detection results indicate that the data analysis sub-results have failed anomaly detection, then the chapter's educational statistical indicators corresponding to the data analysis sub-results are identified as anomalous educational statistical indicators, and each next-level educational statistical indicator corresponding to the anomalous educational statistical indicator is identified; based on the ratio of the periodic change corresponding to each next-level educational statistical indicator to the periodic change corresponding to the anomalous educational statistical indicator, the influence coefficient of each next-level educational statistical indicator on the anomalous educational statistical indicator is obtained; the influence coefficients greater than a fourth preset value are identified as target influence coefficients; the target influence coefficients and the next-level educational statistical indicators corresponding to the target influence coefficients are processed using an intelligent agent to generate anomaly analysis data; and the anomaly analysis data is filled into the chapters to obtain the first new education management report.

[0014] Anomaly detection can be performed on the data analysis sub-results of all chapters to identify abnormal educational statistical indicators. By identifying the multiple next-level educational statistical indicators that have the greatest impact on the abnormal educational statistical indicators, anomaly analysis data can be generated. Finally, the anomaly analysis data is filled into the anomaly analysis chapter to form an optimized education management report, which further enriches the content of the optimized education management report.

[0015] In an optional implementation, the method further includes: combining the data analysis sub-results, data analysis sub-tasks, chapter statistical definitions, and chapter educational data corresponding to each chapter to obtain traceability information corresponding to each chapter, wherein the chapter statistical definition is the statistical definition corresponding to the chapter educational statistical indicators, the chapter educational data is the educational data corresponding to the chapter educational statistical indicators, and the chapter educational statistical indicators correspond to the data analysis sub-tasks; filling the traceability information corresponding to each chapter into the corresponding chapter in the form of annotation information to obtain the second new education management report.

[0016] By filling the corresponding traceability information into the relevant chapters, the traceability information can be displayed to users or auditors along with the Second New Education Management Report, thereby improving the transparency and credibility of the education management report.

[0017] In some optional implementations, the method further includes: if a file export format for the education management report is received, exporting the education management report according to the file export format; and / or, if dimension adjustment information for the education management report is received, adjusting the education management report according to the dimension adjustment information to obtain a third new education management report; and / or, if caliber correction information for the education management report is received, adjusting the education management report according to the caliber correction information to obtain a fourth new education management report.

[0018] Exporting education management reports according to the user-specified file export format can adapt to diverse usage scenarios and platform environments, improving the compatibility, standardization, and ease of use of education management reports, and reducing the need for users to perform additional format conversion operations.

[0019] By receiving and adjusting the dimensions of education management reports, the system can flexibly adapt to users' multi-level analysis needs, from macro-level overviews to micro-level details, thereby enhancing the relevance, interactivity, and reusability of education management reports.

[0020] By receiving and responding to caliber correction information for education management reports, and adaptively adjusting the content of education management reports according to the caliber correction information, a flexible processing mechanism is constructed in which the statistical caliber of education management reports can be dynamically corrected and the content can be optimized in real time. This effectively solves the deviation in the content of education management reports caused by inconsistent statistical calibers.

[0021] In some optional implementations, the method further includes: after adjusting the education management report according to the caliber correction information to obtain the fourth new education management report, if an instruction to add caliber correction information to the database is received, the statistical caliber of the corrected education statistical indicators is corrected based on the caliber correction information to obtain the corrected statistical caliber, and the corrected education statistical indicators are the target education statistical indicators corresponding to the caliber correction information; the corrected statistical caliber is used to replace the statistical caliber of the corrected education statistical indicators in the education indicator database to obtain the updated education indicator database.

[0022] The corrected statistical caliber corresponding to the corrected educational statistical indicators will be updated to the educational indicator database. When using the corrected educational statistical indicators again in the future, users will not need to repeatedly correct the statistical caliber of the corrected educational statistical indicators, which can further ensure a better user experience.

[0023] Secondly, the present invention provides an apparatus for generating an education management report, the apparatus comprising: a first determining module, configured to determine, based on education statistical indicators in the education management problem text, a report type corresponding to the education management problem text and at least one target education statistical indicator corresponding to the report type; a second determining module, configured to determine, based on at least one target education statistical indicator and data constraint information in the education management problem text, education data corresponding to the education management problem text; a feature extraction module, configured to extract features from the education data to obtain data feature information; a third determining module, configured to determine, based on the report type and data feature information, a report template corresponding to the education management problem text; an execution module, configured to execute a data analysis task corresponding to the report template to obtain data analysis results; and a first filling module, configured to fill the report template with the data analysis results to obtain an education management report.

[0024] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the method for generating an education management report as described in the first aspect or any corresponding embodiment.

[0025] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the method for generating an education management report according to the first aspect or any corresponding embodiment described above.

[0026] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the method for generating an education management report according to the first aspect or any corresponding embodiment described above. Attached Figure Description

[0027] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0028] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first process of generating an education management report according to an embodiment of the present invention; Figure 3 This is a schematic diagram of a second process for generating an education management report according to an embodiment of the present invention; Figure 4 This is a schematic diagram of a process for determining a report template according to an embodiment of the present invention; Figure 5 This is a flowchart illustrating a specific method for generating an education management report according to an embodiment of the present invention; Figure 6 This is a structural block diagram of an educational management report generation device according to an embodiment of the present invention; Figure 7 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0030] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0031] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0032] With the development of information technology, higher education management is gradually moving towards digitalization and intelligence. Higher education administrators need to regularly or irregularly prepare various education management reports, such as undergraduate teaching quality reports, faculty analysis reports, student academic performance warning reports, and annual employment quality reports.

[0033] However, current methods for generating education management reports have some shortcomings. For example, when using Business Intelligence (BI) tools such as Tableau, Power BI, and FineBI to generate education management reports, the content generated by these tools is mainly a list of data charts, lacking the complete narrative structure required for education management reports, thus resulting in insufficient usability of the generated reports.

[0034] For example, Educational Management Information Systems (EMIS) are core business systems commonly deployed in universities, including student registration management systems, academic affairs management systems, personnel management systems, and research management systems. These systems can generate standardized statistical reports, but the content of these reports is usually static tables or fixed templates, lacking a complete narrative structure, which in turn leads to insufficient usability of the generated educational management reports.

[0035] For example, the method of generating education management reports based on static templates is difficult to adapt to diverse data types and analysis needs due to the fixed structure of static templates; and the method of generating education management reports based on pre-set scenarios of large language models (LLMs) is difficult to guarantee in terms of content standardization and consistency because the generated content is highly dependent on the large language model's ability to understand and integrate the recalled data.

[0036] Based on the aforementioned deficiencies, this application starts with the text of educational management issues raised by users, dynamically generates a report template for the text of educational management issues based on the corresponding report type and educational data, and then automatically generates a well-structured and focused educational management report using the report template.

[0037] As an optional application scenario of this invention, such as Figure 1 As shown, application 101 is installed in electronic device 110, and user 130 can interact with application 101 through electronic device 110 and / or access device of electronic device 110.

[0038] For example, Application 101 can be any application that provides educational management report generation services. For instance, Application 101 could be a question-and-answer interactive application, such as a text-to-text application. Figure 1 In the application scenario shown, if application 101 is active, electronic device 110 can display the interface 102 of application 101. Interface 102 may include various pages that application 101 can provide, such as interactive pages, settings pages, query pages, etc.

[0039] In some embodiments, electronic device 110 is communicatively connected to server 120 to provide services to application 101. Electronic device 110 may be a mobile terminal, fixed terminal, or portable terminal, etc., including but not limited to mobile phones, desktop computers, laptop computers, multimedia tablets, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices, or any combination thereof. In some embodiments, electronic device 110 may also support any type of interface, and server 120 may be various types of computing systems or servers capable of providing computing power, including but not limited to mainframes, edge computing nodes, computing devices in cloud environments, etc.

[0040] It should be noted that, Figure 1 This is merely an example of an application scenario and does not limit the scope of protection of this invention.

[0041] The embodiments of the present invention will now be described with reference to the accompanying drawings. It should be understood that the pages shown in the drawings are merely examples, and various page designs are possible in practice. The various graphic elements on the page may have different arrangements and different visual representations; one or more elements may be omitted or replaced, and one or more other elements may also be present, without any limitation in the embodiments of the present invention. Furthermore, the embodiments described below primarily pertain to electronic device 110. It should be understood that the actions described relative to electronic device 110 can be performed by application 101 on electronic device 110, or can be performed by application 101 in conjunction with its server (e.g., server 120).

[0042] According to an embodiment of the present invention, an embodiment of a method for generating an education management report is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0043] This embodiment provides a method for generating education management reports, which can be used on electronic devices. Figure 2 This is a flowchart of a method for generating an education management report according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Based on the educational statistical indicators in the educational management problem text, determine the report type corresponding to the educational management problem text and at least one target educational statistical indicator corresponding to the report type.

[0044] As mentioned earlier, question-and-answer interactive applications can provide interactive pages where users can input educational management questions such as "conduct a trend analysis of the employment rate of XX University in the past three years" or "analyze the changing trend of the student-faculty ratio in the School of Computer Science in the past three years." The electronic device responds to the user's input and obtains the educational management question text.

[0045] Educational statistical indicators can be standardized, statistically comparable data items used to quantitatively describe, analyze, and evaluate the operational status and management effectiveness of education. As specific examples, educational statistical indicators related to student development may include employment rate, college entrance rate, failure rate, retake rate, graduation rate, etc.; educational statistical indicators related to teacher structure may include student-teacher ratio, student-teacher ratio, etc.; and educational statistical indicators related to teaching operations may include course pass rate, grade point average (GPA), class completion rate, etc.

[0046] After acquiring text containing educational management issues, electronic devices can perform intent recognition and element extraction to obtain educational statistical indicators such as "student-teacher ratio," "failure rate," and "research funding." As a specific example, the electronic device can segment the text to obtain individual words, then determine whether each word is in a pre-set educational indicator database. If a target word exists in the database, it is identified as an educational statistical indicator; otherwise, it is not.

[0047] In addition, in some cases, the text of educational management issues can be input into a pre-trained large language model or intelligent agent, so that the large language model or intelligent agent can recognize the text of educational management issues and obtain the educational statistical indicators in the text of educational management issues.

[0048] The report type can be determined by the business domain to which the education management report to be generated belongs, based on the education statistical indicators in the education management problem text. As a specific example, a report type library can be retrieved based on the education statistical indicators in the education management problem text to obtain the report type corresponding to the education management problem text. The report type library includes the correspondence between education statistical indicators and report types.

[0049] For example, if the educational statistical indicator is "student-teacher ratio", the report type can be "teacher development"; if the educational statistical indicator is "failure rate", the report type can be "teaching quality".

[0050] After determining the report type, one or more target educational statistical indicators can be identified based on that report type. As a concrete example, a pre-set educational indicator library can be queried based on the report type to quickly determine one or more target educational statistical indicators corresponding to that report type. Alternatively, the report type can be input into the built-in... Figure 1 The agent or large language model in application 101 shown can be used to quickly obtain one or more target educational statistical indicators corresponding to this report type.

[0051] For example, if the report type is set as "faculty development", the corresponding target educational statistics indicators can be: student-teacher ratio, number of full-time teachers, percentage of full-time teachers by professional title (senior, associate senior, intermediate, junior), percentage of full-time teachers by degree (doctor, master, bachelor and others), number and percentage of dual-qualified teachers, average research funding per full-time teacher, average annual teaching workload per teacher, etc.

[0052] It should be noted that at least one target educational statistical indicator can include educational statistical indicators from the educational management problem text. Using the educational statistical indicators from the educational management problem text, the report type (i.e., business area) corresponding to the educational management report to be generated can be determined. However, the educational statistical indicators in the educational management problem text are only one indicator for that report type (i.e., business area). Therefore, identifying at least one target educational statistical indicator corresponding to that report type can supplement other educational statistical indicators that the user did not mention but that require attention within that report type (i.e., business area), thus enriching the content of the generated educational management report.

[0053] Step S202: Based on at least one target educational statistical indicator and the data constraint information in the educational management problem text, determine the educational data corresponding to the educational management problem text.

[0054] Data constraint information can be the time dimension of the educational data mentioned by the user in the text of the educational management question and used to limit the required educational data, such as "the past three years", "this semester" and the analysis dimension "computer science school", "undergraduate students", etc.

[0055] After acquiring the text of an educational management issue, the electronic device can perform intent recognition and element extraction on the text to obtain data constraint information such as "School of Computer Science," "Undergraduate Students," "Graduate Students," "Past Three Years," and "This Semester." The extraction of data constraint information can be referred to the extraction of educational statistical indicators as described earlier, and will not be repeated here.

[0056] The question-and-answer interactive application of this application can communicate with the education management information system. After determining the data constraint information in the education management question text, it can query the database of the education management information system based on the data constraint information and at least one target education statistical indicator to obtain the education data required in the process of generating education management reports.

[0057] Following the previous example, the target educational statistical indicators are set as the student-teacher ratio, the percentage of full-time teachers with senior professional titles, etc., as mentioned earlier; the dimension information can be the entire school; and the time information can be the past three years (academic years 2023, 2024, and 2025). Based on this, querying the database of the education management information system yields educational data such as: 2023 academic year: 800 full-time teachers, 16,000 full-time students, 160 senior professional titles; 2024 academic year: 820 full-time teachers, 16,500 full-time students, 172 senior professional titles; 2025 academic year: 850 full-time teachers, 17,000 full-time students, 187 senior professional titles. It should be noted that the above data is only a specific example.

[0058] Step S203: Extract features from the educational data to obtain data feature information.

[0059] The data characteristics here can be represented from multiple aspects such as data dimension, data sparsity, and data volatility. Among them, data dimension is used to represent the number and classification structure of statistical attributes contained in educational data, such as time dimension, school dimension, major dimension, grade dimension, etc.; data sparsity is used to represent the degree of missing data, the uniformity of distribution, or the effective sampling density of educational data in each dimension; data volatility is used to represent the degree of fluctuation, dispersion, and stability of the trend of educational data as it changes over time or other conditions.

[0060] As a concrete example, educational data can be input into a large language model or intelligent agent, enabling the model or agent to extract features from the data across multiple dimensions, such as data dimensionality, sparsity, and volatility, thereby obtaining data feature information. Furthermore, Chain-of-Thought (COT) technology can be employed, designing different prompts and specifying the order of execution steps to guide the large language model or intelligent agent to extract features from the educational data according to a pre-defined reasoning process, thus obtaining data feature information.

[0061] In addition, a pre-built knowledge graph in the field of education can be introduced as an external memory support for the large language model or intelligent agent. During the feature extraction process, the large language model or intelligent agent can be guided to obtain the correlation between educational statistical indicators and the data feature extraction rules by querying the knowledge graph. This helps it to more accurately complete the feature extraction of educational data from dimensions such as data dimension, data sparsity, and data volatility, thereby improving the accuracy of data feature information.

[0062] Of course, in some cases, corresponding statistical calculation rules can be configured in advance for data dimensions, data sparsity and data volatility, and then the educational data can be traversed and statistically analyzed based on the preset statistical calculation rules to obtain data feature information.

[0063] For example, if the educational management problem text is "to conduct a trend analysis of the employment rate of XX University in the past three years", then we can start from the data dimension, and count the number of colleges and majors of the university involved in the educational data, etc.; data sparsity can be the integrity assessment result obtained by evaluating the data integrity of educational data; data volatility can be the volatility assessment result obtained by evaluating the degree of change of educational data.

[0064] Step S204: Based on the report type and data characteristic information, determine the report template corresponding to the educational management problem text.

[0065] Here, an initial report template can be determined based on the report type corresponding to the educational management issue text, i.e., the business domain corresponding to the educational management issue text. Then, the initial report template can be dynamically adjusted based on data feature information, such as deleting or adding chapters, to obtain the final report template for the educational management issue text. The initial report template can be a pre-defined template corresponding to the report type, and it can contain basic chapters corresponding to the report type.

[0066] Of course, the report type and data characteristics can also be input into the agent or large language model built into the question-and-answer interaction application, and the agent or large language model can be used to dynamically generate report templates corresponding to the educational management problem text.

[0067] Step S205: Execute the data analysis task corresponding to the report template to obtain the data analysis results.

[0068] Data analysis tasks can be a series of tasks performed by electronic devices to process and analyze educational data in order to match the output requirements of report templates.

[0069] As a concrete example, once the report template is determined, the various chapters within the report template can be identified. Then, based on the content to be displayed in each chapter, the corresponding data analysis sub-tasks can be determined. Finally, the data analysis sub-tasks corresponding to each chapter can be organized together to obtain the data analysis tasks corresponding to the report template.

[0070] Additionally, the data analysis sub-tasks corresponding to each chapter in the data analysis task can be transformed into query statements. Electronic devices can then execute these queries to obtain the data analysis sub-results for each chapter. Alternatively, an intelligent agent or a large language model can be used to execute the data analysis sub-tasks for each chapter to obtain the corresponding data analysis sub-results. After obtaining the data analysis sub-results for each chapter, these sub-results can be organized together to obtain the final data analysis result.

[0071] Step S206: Fill the report template with the data analysis results to obtain the education management report.

[0072] Here, the data analysis sub-results corresponding to each chapter can be populated into the corresponding chapters of the report template to obtain the education management report. After obtaining the education management report, it can be evaluated from multiple dimensions such as user ratings, frequency of use, and human review results to select high-quality education management reports. These high-quality reports can then be refined into structured initial report templates and stored in the report template library.

[0073] In addition, typical conclusion paragraphs can be extracted from high-quality education management reports, and these paragraphs, along with their corresponding statistical definitions and contextual information, can be stored in a case study library. During the generation of subsequent education management reports, these typical conclusion paragraphs can be referenced to improve the completeness and industry relevance of the reports. Furthermore, when storing typical conclusion paragraphs in the case study library, they can be categorized and stored according to teaching, faculty, academic performance, employment, and other relevant factors.

[0074] The method for generating education management reports provided in this embodiment can accurately determine the report type (i.e., business domain) and one or more target education management statistical indicators corresponding to the report type based on the education statistical indicators in the education management problem text. Furthermore, based on at least one target education management statistical indicator and the data constraint information in the education management problem text, it can accurately determine the data support required for the education management report, i.e., the education data. By extracting features from the education data, data feature information can be obtained. Then, based on the report type and data feature information, the report template corresponding to the education management report can be dynamically determined. The data analysis results are obtained by executing the data analysis task corresponding to the report template, and then the data analysis results are filled into the report template. Therefore, a complete education management report with a reasonable structure and highlighting key points can be obtained. Compared with static templates with fixed structures, this application can avoid the mismatch problem of using complex charts with sparse data or displaying only simple conclusions with rich data. Compared with generating education management reports using large language models, it can avoid the problem of strong content randomness.

[0075] This embodiment provides a method for generating education management reports, which can be used on electronic devices. Figure 3 This is a flowchart of a method for generating an education management report according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps: Step S301: Based on the educational statistical indicators in the educational management problem text, determine the report type corresponding to the educational management problem text and at least one target educational statistical indicator corresponding to the report type. For details, please refer to [link to details]. Figure 2Step S201 of the illustrated embodiment will not be described again here.

[0076] Step S302: Based on at least one target educational statistical indicator and data constraint information in the educational management problem text, determine the educational data corresponding to the educational management problem text. For details, please refer to [link to relevant documentation]. Figure 2 Step S202 of the illustrated embodiment will not be described again here.

[0077] Step S303 involves feature extraction from the educational data to obtain data feature information. For details, please refer to [link to relevant documentation]. Figure 2 Step S203 of the illustrated embodiment will not be described again here.

[0078] Step S304: Based on the report type and data characteristic information, determine the report template corresponding to the educational management issue text.

[0079] Specifically, step S304 includes: Step S3041: Based on the report type, retrieve the report template library to determine the initial report template corresponding to the educational management problem text. The report template library includes the correspondence between report types and initial report templates.

[0080] The report template library can be a pre-built database containing the correspondence between report types and initial report templates. The initial report template can be a standardized report framework pre-defined in the report template library, establishing a fixed correspondence with a specific report type, and not personalized or adjusted for the specific educational management issue at hand. As a concrete example, an initial report template may have basic sections such as an overview, sub-analysis, and conclusion.

[0081] Step S3042: If the data dimension representing the educational data is less than the first preset value and the sparsity of the educational data is greater than the second preset value, then the initial report template is determined as the report template.

[0082] The first and second preset values ​​can be flexibly adjusted according to the actual situation, and this application does not specifically limit the first and second preset values.

[0083] If the data dimension representing the educational data is less than the first preset value and the sparsity of the educational data is greater than the second preset value, it indicates that the currently available educational data is limited and the data integrity is insufficient, making it unsuitable for loading complex analysis modules and multi-dimensional display formats. Therefore, in some cases, the initial report template can be directly determined as the report template; in other cases, analysis modules with high requirements for data volume and data continuity in the initial report template can be removed, and only basic statistical modules can be retained to avoid the problem of modules having no content to fill and charts being unable to be generated due to insufficient data.

[0084] For example, the educational management issue text is set as a trend analysis of the employment rate of XX University over the past three years. Given that the data dimension representing the educational data is lower than the first preset value and the sparsity of the educational data is higher than the second preset value, the overview section of the report template can be used to analyze the average employment rate of XX University over the past three years, the sub-analysis section can be used to analyze the average employment rate of each college under XX University, and the conclusion section can be used to summarize the content of the overview section and the sub-analysis section.

[0085] Step S3043: If the data dimension representing the educational data is greater than or equal to the first preset value, the sparsity of the educational data is less than or equal to the second preset value, and the volatility of the educational data is greater than or equal to the third preset value, then based on the correlation between the target educational statistical indicators, the related educational statistical indicators among the target educational statistical indicators are determined, and a correlation analysis section for conducting correlation analysis on the related educational statistical indicators is added to the initial report template to obtain the report template.

[0086] The third preset value here can be flexibly adjusted according to the actual situation, and this application does not impose specific limitations on the third preset value.

[0087] The identification of interrelated educational statistical indicators based on the correlation between target educational statistical indicators can be achieved in several ways. Specifically, this can include: performing cluster analysis on the target educational statistical indicators and identifying those within the same category as interrelated indicators; calculating the Pearson correlation coefficient between any two target educational statistical indicators, and determining these two indicators as interrelated indicators requiring correlation analysis if the Pearson correlation coefficient exceeds a threshold; or using a pre-trained classification model to identify interrelated indicators requiring correlation analysis.

[0088] For example, target education statistical indicators include employment rate, professional relevance rate, average salary, student-teacher ratio, per-student funding, failure rate, and graduation rate. Cluster analysis of these target education statistical indicators reveals correlations between employment rate, professional relevance rate, and average salary; between student-teacher ratio and per-student funding; and between failure rate and graduation rate.

[0089] After identifying the relevant educational statistical indicators that need to be analyzed for correlation, a section can be generated for users to conduct correlation analysis on the relevant educational statistical indicators. This section can then be added to the initial report template to obtain the final report template.

[0090] In some cases, if the data dimension representing the educational data is greater than or equal to the first preset value, the sparsity of the educational data is less than or equal to the second preset value, and the volatility of the educational data is greater than or equal to the third preset value, then multi-dimensional combined charts can be configured in the sub-sections of the report template to better show the specific numerical variation patterns of the corresponding chapter's educational statistical indicators.

[0091] As a specific example, such as Figure 4 As shown, users can input educational management question text into an electronic device via the interactive page described above. The electronic device can respond to the user's input and obtain the educational management question text. Then, the electronic device can perform intent recognition and element extraction on the educational management question text to obtain educational statistical indicators and data constraint information. Subsequently, based on the educational statistical indicators in the educational management question text, the corresponding report type and at least one target educational statistical indicator corresponding to that report type can be determined. Therefore, educational data can be determined based on at least one target educational statistical indicator and data constraint information, and features of the educational data can be extracted from data dimension, data sparsity, and data volatility to obtain data characteristic information of the educational data in terms of data dimension, data sparsity, and data volatility. Finally, a report template for the educational management question text is determined based on the extracted data characteristic information and the report type.

[0092] By leveraging the report type corresponding to the educational management issue text, an initial report template can be quickly and accurately determined. Then, based on the data characteristics of educational data, such as data dimensions, sparsity, and volatility, the initial report template can be differentiated. This allows for the rapid identification of a report template that matches the educational management issue text, ensuring that the report remains concise and effective when data is scarce, while strengthening in-depth analysis when data is abundant and highly volatile, fully mining the value of the data, and enhancing the relevance and decision-making reference value of the educational management report.

[0093] Step S305: Execute the data analysis task corresponding to the report template to obtain the data analysis results.

[0094] Specifically, step S305 includes: Step S3051: Search the education indicator library based on the report type to obtain at least one target education statistical indicator corresponding to the report type. The education indicator library includes the correspondence between report types and target education statistical indicators.

[0095] The target educational statistical indicators stored in this educational indicator library can be predefined educational statistical indicators with unified indicator names, statistical definitions, and business implications.

[0096] By using the report type search education indicator database, one can not only comprehensively identify one or more target education statistical indicators corresponding to the report type, but also eliminate the possibility of errors in the final education management report due to inconsistent statistical standards, since the target education statistical indicators have unified indicator names, statistical scope and business meaning.

[0097] Step S3052: Determine the chapter education statistics indicators corresponding to each chapter in the report template from at least one target education statistics indicator, and determine the chapter data constraint information corresponding to each chapter from the data constraint information.

[0098] Here, the chapter education statistics indicators corresponding to each chapter can be determined from at least one target education statistics indicator based on the titles of each chapter in the report template, and the chapter data constraints information corresponding to each chapter can be determined from the data constraint information.

[0099] For example, an educational management issue text could be "Please analyze the teaching quality of undergraduate students in the School of Computer Science during the first semester of the 2025-2026 academic year." The corresponding report template could then include the following chapters: Chapter 1, Overall Overview of Teaching Quality; Chapter 2, Course Grade Distribution Analysis; Chapter 3, Specific Analysis of Failure Rates; Chapter 4, Comparison of Teaching Quality Differences Among Different Majors; and Chapter 5, Summary and Reminders Regarding Teaching Quality. Accordingly, the educational statistical indicators for Chapter 1 could be course average scores, course pass rates, and student evaluation scores; the data constraints could be the School of Computer Science, the first semester of the 2025-2026 academic year, and undergraduate students. Similarly, the educational statistical indicators for Chapter 2 could be course average scores and course pass rates; the data constraints could be the School of Computer Science, the first semester of the 2025-2026 academic year, and undergraduate students. Chapters 3, 4, and 5 will not be elaborated upon here. Furthermore, the above data is merely an example and is not intended to impose specific limitations.

[0100] Step S3053: Based on the chapter-specific educational statistics indicators and chapter-specific data constraints for each chapter, generate a data analysis subtask for each chapter.

[0101] This section uses a single chapter as an example to introduce the generation of data analysis subtasks corresponding to that chapter. If a chapter has multiple chapter-specific educational statistical indicators, then each chapter's educational statistical indicator can be associated with the chapter's data constraints to generate a data analysis subtask represented in a structured form. Therefore, each chapter can have one or more data analysis subtasks.

[0102] Following the previous example, the average course score in Chapter 2 shown above can be represented by the data analysis subtask corresponding to the average course score in the form of "Chapter Educational Statistics Indicator: Average Course Score; Data Constraint Information: School of Computer Science, First Semester of the 2025-2026 Academic Year, Undergraduate".

[0103] After obtaining the data analysis subtasks for each chapter, the system can automatically select the most suitable data layer, such as the detail layer, summary layer, or application layer, based on the task requirements of each subtask. For example, when the task requirement for a subtask is a macro-level indicator, the application layer or summary layer can be automatically selected; when the task requirement is a micro-level detail, the detail layer can be automatically selected. After automatically selecting the most suitable data layer for each subtask, the relevant data layer information can be updated to the subtask, resulting in an updated data analysis subtask.

[0104] Step S3054: Execute the data analysis sub-tasks corresponding to each chapter to obtain the data analysis sub-results corresponding to each chapter. The data analysis results include each data analysis sub-result.

[0105] Here, the data analysis subtask can be converted into an SQL query statement, which is then executed by an electronic device to obtain the data analysis sub-results. The specific process of converting the data analysis subtask into an SQL query statement can be as follows: First, query the education indicator database based on the chapter's educational statistical indicators in the data analysis subtask to obtain the corresponding SQL template or statistical definition. For example, the obtained SQL template could be: `SELECT COUNT(student_id) FROM table_x WHERE student_type = 'undergraduate'`. Second, the data constraint information from the data analysis subtask is filled in as parameters of the WHERE clause. Finally, the table name following `FROM` is determined based on whether the query is from a detailed table, an application layer, or a summary table, determined by the data layer. Of course, if the statistical indicators obtained from the education indicator database correspond to the chapter's educational statistical indicators, the corresponding SQL query statement can also be generated using the statistical indicators, data constraint information, and data layer information.

[0106] Alternatively, all data analysis subtasks from different chapters can be placed into a shared task pool. These subtasks can then be merged to create an updated shared task pool. Finally, the updated shared task pool is executed to obtain the corresponding data analysis results for each subtask. By merging the data analysis subtasks from different chapters, frequent access to the education management information system's database and redundant queries can be avoided.

[0107] As mentioned earlier, data analysis subtasks can be represented in a structured form, so the structured elements of any two data analysis subtasks can be compared. When the structured elements of any two data analysis subtasks are exactly the same, they can be merged into one data analysis subtask. When the structured elements of any two data analysis subtasks are not exactly the same, it indicates that the two data analysis subtasks are different tasks, so there is no need to merge them.

[0108] During the execution of data analysis subtasks, if a subtask fails on its first attempt, the corresponding SQL query statement can be adjusted. If the failure persists after adjustment, the reason for the failure can be identified, such as inability to connect to the database or failure to retrieve educational data. Finally, the reason for the failure is matched against a pre-defined catch-all text. This catch-all text can be a pre-defined explanatory text or placeholder, designed to ensure the integrity of the entire education management report and prevent interruptions or code errors caused by the absence of a single educational statistical indicator.

[0109] In addition, the data analysis results for a data analysis subtask can be the index values ​​of the educational statistics indicators for the corresponding chapter of the data analysis subtask.

[0110] By leveraging the chapter-specific educational statistics and data constraints for each chapter, a single, large-scale overall data analysis task can be broken down into multiple, more granular, and clearly defined sub-tasks. This reduces the difficulty of implementing complex analytical logic, facilitates modular processing within the system, and enhances the flexibility of task scheduling and execution. Furthermore, each sub-task focuses solely on the corresponding chapter's educational statistics and data constraints, ensuring clear task objectives and a focused processing scope. This reduces interference from irrelevant data and logic, improving the execution efficiency and computational accuracy of individual tasks. Simultaneously, it facilitates independent anomaly monitoring and error localization for each sub-task.

[0111] Step S306: Fill the report template with the data analysis results to obtain the education management report.

[0112] Specifically, step S306 includes: Step S3061: Visualize the data analysis sub-results corresponding to each chapter to obtain the visualized data corresponding to each chapter.

[0113] Here, we can use the time dimension in the data analysis sub-results and the indicator characteristics of the corresponding chapter's educational statistics indicators to determine the chart type for each sub-result. For example, combining the time dimension of a time series with trend-type indicator characteristics can determine that the chart type is a line chart; then, the data analysis sub-results can be formatted to generate visual data that matches the determined chart type.

[0114] Step S3062: Based on the fusion results of the visualization data and data analysis sub-results corresponding to each chapter, generate the text content corresponding to each chapter.

[0115] Here, the distribution characteristics of the visualized data can be determined by analyzing the visualized data. Then, by using the distribution characteristics and data analysis sub-results, and by using preset templates and knowledge bases and calling the built-in intelligent agent or large language model of the question-and-answer interactive application, the text content corresponding to each chapter can be obtained.

[0116] Step S3063: Fill the corresponding chapters with the visualization data and text content to obtain the education management report.

[0117] Here, you can first display the visual data and then the text content, filling the corresponding chapters with the visual data and text content to obtain an education management report.

[0118] By integrating the visualized data and data analysis sub-results for each chapter, the corresponding text content for each chapter is generated. This ensures that the generated text content is supported by both precise numerical data and intuitively corroborated by visual data. The visualized data and text content for each chapter are then populated into the corresponding chapters, achieving seamless integration between the report content and the template framework. This eliminates the tedious processes of manual typesetting, content proofreading, and chapter matching, significantly shortening the overall education management report generation cycle and improving the efficiency and quality of education management report generation.

[0119] In some alternative implementations, the method further includes: Step a1: For each chapter, perform anomaly detection on the data analysis sub-results of the chapter to obtain the anomaly detection results.

[0120] Step a2: If the anomaly detection result indicates that the data analysis sub-result has failed the anomaly detection, then the chapter education statistics indicator corresponding to the data analysis sub-result is identified as an abnormal education statistics indicator, and the next level education statistics indicator corresponding to the abnormal education statistics indicator is determined.

[0121] Step a3: Based on the ratio of the contemporaneous change of each lower-level educational statistical indicator to the contemporaneous change of the abnormal educational statistical indicator, obtain the influence coefficient of each lower-level educational statistical indicator on the abnormal educational statistical indicator.

[0122] Step a4: The influence coefficient that is greater than the fourth preset value is determined as the target influence coefficient; Step a5: Use the intelligent agent to process the target influence coefficient and the corresponding next-level educational statistical indicators to generate anomaly analysis data.

[0123] Step a6: Fill the anomaly analysis data into the anomaly analysis section of the education management report to obtain the first new education management report.

[0124] Here, the data analysis sub-result, i.e., the indicator value shown above, can be compared with the preset indicator value to perform anomaly detection on the data analysis sub-result. If the indicator value is less than or equal to the preset indicator value, an anomaly detection result indicating that the data analysis sub-result has passed the anomaly detection is obtained; if the indicator value is greater than the preset indicator value, an anomaly detection result indicating that the data analysis sub-result has failed the anomaly detection is obtained.

[0125] For example, if the abnormal educational statistics indicator is the overall employment rate of the university, then the next level of educational statistics indicator is the employment rate of each college. As another example, if the abnormal educational statistics indicator is the employment rate of the School of Computer Science, then the next level of educational statistics indicator is the employment rate of each major under the School of Computer Science.

[0126] The change over the same period can be an educational statistical indicator, representing the difference between the indicator value within the current statistical period and the indicator value within the same statistical period. For example, the current statistical period could be the first semester of the 2025-2026 academic year; the same statistical period could be the first semester of the 2024-2025 academic year.

[0127] As a specific example, different weights can be set for different lower-level educational statistical indicators. Then, the first product is obtained by multiplying the change in the same period corresponding to the lower-level educational statistical indicator with its corresponding weight. The ratio of the first product to the change in the same period corresponding to the abnormal educational statistical indicator is then calculated to obtain the influence coefficient of the lower-level educational statistical indicator on the abnormal educational statistical indicator.

[0128] Here, the calculated influence coefficients can be sorted from largest to smallest, and the first preset number of influence coefficients can be taken as the target influence coefficient. After determining the target influence coefficient, the target influence coefficient and the corresponding next-level educational statistical indicators can be filled into the preset context information template to obtain the context information; then, the intelligent agent can be used to process the context information to obtain anomaly analysis data for abnormal educational statistical indicators.

[0129] For example, the original description stated: "The initial employment rate for all undergraduate students this year was 85%, a decrease of 3.2 percentage points year-on-year." Additional diagnostic analysis revealed that the main reasons for the decline were the School of Software and the School of Civil Engineering. Specifically, the School of Software's employment rate decreased by 15% year-on-year, contributing 55% to the overall decline and making it the primary factor leading to the overall downturn.

[0130] Anomaly detection can be performed on the data analysis sub-results of all chapters to identify abnormal educational statistical indicators. By identifying the multiple next-level educational statistical indicators that have the greatest impact on the abnormal educational statistical indicators, anomaly analysis data can be generated. Finally, the anomaly analysis data is filled into the anomaly analysis chapter to form an optimized education management report, which further enriches the content of the optimized education management report.

[0131] In some alternative implementations, the method further includes: Step b1: Combine the data analysis sub-results, data analysis sub-tasks, chapter statistical definitions, and chapter educational data for each chapter to obtain the traceability information for each chapter. Here, the chapter statistical definition is the statistical definition corresponding to the chapter educational statistical indicators, the chapter educational data is the educational data corresponding to the chapter educational statistical indicators, and the chapter educational statistical indicators correspond to the data analysis sub-tasks.

[0132] Step b2 involves filling the corresponding chapters with the traceability information in the form of annotations to obtain the second new education management report.

[0133] The statistical scope here can be the calculation formula corresponding to the chapter education statistical indicators, and the chapter education data can be the education data corresponding to the chapter education statistical indicators.

[0134] By filling the corresponding traceability information into the relevant chapters, the traceability information can be displayed to users or auditors along with the Second New Education Management Report, thereby improving the transparency and credibility of the education management report.

[0135] In some alternative implementations, the method further includes: Step c1: If a file export format for the education management report is received, then export the education management report according to the file export format.

[0136] The file export formats available here are PDF, WORD, PPT, and JSON. PDF is used for formal external release and archiving; WORD allows for easy manual modification and annotation; PPT can meet the presentation needs of educational management meetings; and JSON can provide machine-readable structured output and support interface integration with third-party systems.

[0137] During the export of the education management report according to the file export format, the layout of charts, text styles, and headers and footers can be automatically adjusted to ensure the readability and aesthetics of the education management report.

[0138] As mentioned above, users can use the interactive page provided by the question-and-answer application to select the file export format for the education management report. The electronic device can respond to the user's selection and export the education management report according to the file export format.

[0139] Exporting education management reports according to the user-specified file export format can adapt to diverse usage scenarios and platform environments, improving the compatibility, standardization, and ease of use of education management reports, and reducing the need for users to perform additional format conversion operations.

[0140] In some alternative implementations, the method further includes: Step d1: If a dimension adjustment message for the education management report is received, the education management report is adjusted according to the dimension adjustment message to obtain the third new education management report.

[0141] The dimension adjustment information here refers to adjusting the analytical dimensions in the educational management question text. For example, if the user initially inputs the educational management question text as "conduct a trend analysis of the employment rate of XX University over the past three years," an educational management report has already been generated for this question text. Subsequently, the user inputs "disassemble by college," and the electronic device responds to the user's new input, receives the dimension adjustment information for the already generated educational management report, and adjusts the educational management report based on the dimension adjustment information to obtain a third new educational management report.

[0142] Of course, after receiving the user's dimension adjustment information, the electronic device can also use the education management report generation method shown above, and combine the content entered by the user twice, to regenerate a third new education management report according to the adjusted analysis dimensions.

[0143] By receiving and adjusting the dimensions of education management reports, the system can flexibly adapt to users' multi-level analysis needs, from macro-level overviews to micro-level details, thereby enhancing the relevance, interactivity, and reusability of education management reports.

[0144] In some alternative implementations, the method further includes: Step e1: If a correction message for the educational management report is received, the educational management report is adjusted according to the correction message to obtain the fourth new educational management report.

[0145] The caliber correction information here can be used to adjust the statistical caliber in educational management question texts. For example, if the user initially inputs the educational management question text "Analyze the changing trend of the student-to-faculty ratio in the Computer Science Department over the past three years," an educational management report has already been generated for this question text. Subsequently, the user inputs "The student-to-faculty ratio should not include external teachers." The electronic device responds to the user's new input, receives the caliber correction information for the already generated educational management report, and adjusts the educational management report based on the caliber correction information to obtain a fourth new educational management report.

[0146] By receiving and responding to caliber correction information for education management reports, and adaptively adjusting the content of education management reports according to the caliber correction information, a flexible processing mechanism is constructed in which the statistical caliber of education management reports can be dynamically corrected and the content can be optimized in real time. This effectively solves the deviation in the content of education management reports caused by inconsistent statistical calibers.

[0147] In some alternative implementations, the method further includes: Step f1: After adjusting the education management report according to the caliber correction information to obtain the fourth new education management report, if an instruction to enter the caliber correction information is received, the statistical caliber of the corrected education statistical indicators is corrected based on the caliber correction information to obtain the corrected statistical caliber. The corrected education statistical indicators are the target education statistical indicators corresponding to the caliber correction information.

[0148] Step f2: Replace the statistical scope of the corrected education statistical indicators in the education indicator database with the corrected statistical scope to obtain the updated education indicator database.

[0149] After providing the user with the Fourth New Education Management Report, this application can also display a prompt message on the interactive page shown above, such as "It has been detected that you have excluded external teachers. Do you want to apply this rule as the default statistical caliber for the 'teacher-student ratio' indicator?" If the electronic device receives an input instruction from the user such as "Yes" or "Agree" to add the data to the database, it will correct the statistical caliber of the corresponding target education statistical indicator, i.e., the corrected education statistical indicator, based on the caliber correction information to obtain the corrected statistical caliber. Then, it will replace the corrected education statistical indicator's statistical caliber in the education indicator database with the corrected statistical caliber to obtain the updated education indicator database.

[0150] The corrected statistical caliber corresponding to the corrected educational statistical indicators will be updated to the educational indicator database. When using the corrected educational statistical indicators again in the future, users will not need to repeatedly correct the statistical caliber of the corrected educational statistical indicators, which can further ensure a better user experience.

[0151] The method for generating education management reports provided in this embodiment can quickly and accurately determine the initial report template by leveraging the report type corresponding to the education management problem text. Then, based on the data characteristics information representing the data dimensions, sparsity, and volatility of education data, the initial report template is differentiated. This can quickly determine a report template that matches the education management problem text, thereby ensuring that the report remains concise and effective when data is scarce, and strengthens in-depth analysis when data is abundant and highly volatile, fully mining the value of data and improving the relevance and decision-making reference value of education management reports.

[0152] As a specific application embodiment of the present invention, such as Figure 5 As shown, users can input text about educational management issues into the electronic device via the interactive page described above. The electronic device can respond to the user's input and retrieve the text. Then, the electronic device can perform intent recognition and element extraction on the text to determine the corresponding report template (see the previous description for details). Based on the chapter-specific educational statistics indicators and data constraints in the report template, a data analysis sub-task is generated for each chapter. This sub-task is executed to obtain the sub-results. Based on the sub-results, visual data and text content for each chapter are generated and then populated into the corresponding chapter to obtain the educational management report. In addition, this solution can also perform anomaly detection on the data analysis sub-results corresponding to each chapter. If a data analysis sub-result fails the anomaly detection, for example, if the indicator value of the data analysis sub-result is higher than the average level, the educational statistics indicator of the corresponding chapter can be identified as an abnormal educational statistics indicator. The solution can then be combined with the next-level educational statistics indicator corresponding to the abnormal educational statistics indicator to analyze the reasons for the abnormality of the abnormal educational statistics indicator. Finally, anomaly analysis data for the abnormal educational statistics indicator is generated and filled into the corresponding chapter to obtain the first new education management report.

[0153] This embodiment also provides an apparatus for generating education management reports, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0154] This embodiment provides an apparatus for generating education management reports, such as... Figure 6 As shown, it includes: The first determining module 610 is used to determine the report type corresponding to the education management problem text and at least one target education statistical indicator corresponding to the report type based on the education statistical indicators in the education management problem text.

[0155] The second determining module 620 is used to determine the educational data corresponding to the educational management problem text based on at least one target educational statistical indicator and data constraint information in the educational management problem text.

[0156] The feature extraction module 630 is used to extract features from educational data to obtain data feature information.

[0157] The third determination module 640 is used to determine the report template corresponding to the educational management problem text based on the report type and data feature information.

[0158] Execution module 650 is used to execute the data analysis task corresponding to the report template and obtain the data analysis results.

[0159] The first filling module 660 is used to fill the report template with the data analysis results to obtain the education management report.

[0160] In some optional implementations, the third determining module 640 is further configured to retrieve a report template library based on the report type, determine the initial report template corresponding to the educational management problem text, and the report template library includes the correspondence between report types and initial report templates; if the data dimension representing the educational data is less than a first preset value and the sparsity of the educational data is greater than a second preset value, then the initial report template is determined as the report template; if the data dimension representing the educational data is greater than or equal to the first preset value, the sparsity of the educational data is less than or equal to the second preset value, and the volatility of the educational data is greater than or equal to a third preset value, then the related educational statistical indicators among the target educational statistical indicators are determined based on the correlation between the target educational statistical indicators, and a correlation analysis section for performing correlation analysis on the related educational statistical indicators is added to the initial report template to obtain the report template.

[0161] In some optional implementations, the execution module 650 is further configured to: retrieve an education indicator library based on the report type to obtain at least one target education statistical indicator corresponding to the report type; the education indicator library includes the correspondence between report types and target education statistical indicators; determine the chapter education statistical indicators corresponding to each chapter in the report template from the at least one target education statistical indicator; and determine the chapter data constraint information corresponding to each chapter from the data constraint information; generate a data analysis sub-task corresponding to each chapter based on the chapter education statistical indicators and chapter data constraint information corresponding to each chapter; and execute the data analysis sub-task corresponding to each chapter to obtain a data analysis sub-result corresponding to each chapter, the data analysis result including each data analysis sub-result.

[0162] In some optional implementations, the first filling module 660 is further configured to perform visualization processing on the data analysis sub-results corresponding to each chapter to obtain the visualization data corresponding to each chapter; generate the text content corresponding to each chapter based on the fusion result of the visualization data and data analysis sub-results corresponding to each chapter; and fill the visualization data and text content corresponding to each chapter into the corresponding chapter to obtain the education management report.

[0163] In some optional implementations, if the report template corresponding to the education management report includes an anomaly analysis section, the device further includes: The anomaly detection module is used to perform anomaly detection on the data analysis sub-results of each chapter and obtain the anomaly detection results.

[0164] The fourth determination module is used to determine the chapter education statistics indicators corresponding to the data analysis sub-result as abnormal education statistics indicators if the abnormal detection result characterizes the data analysis sub-result as an abnormal education statistics indicator, and to determine the next level education statistics indicators corresponding to the abnormal education statistics indicators.

[0165] The fifth determination module is used to obtain the influence coefficient of each lower-level educational statistical indicator on the abnormal educational statistical indicator based on the ratio of the contemporaneous change of each lower-level educational statistical indicator to the contemporaneous change of the abnormal educational statistical indicator.

[0166] The sixth determination module is used to determine the influence coefficient that is greater than the fourth preset value as the target influence coefficient.

[0167] The generation module is used to process the target influence coefficient and the corresponding next-level educational statistical indicators using an intelligent agent to generate anomaly analysis data.

[0168] The second filling module is used to fill the chapters with anomaly analysis data to obtain the first new education management report.

[0169] In some alternative embodiments, the device further includes: The combination module is used to combine the data analysis sub-results, data analysis sub-tasks, chapter statistical definitions, and chapter educational data corresponding to each chapter to obtain the traceability information corresponding to each chapter. Among them, the chapter statistical definition is the statistical definition corresponding to the chapter educational data, the chapter educational data is the educational data corresponding to the chapter educational statistical indicators, and the chapter educational statistical indicators correspond to the data analysis sub-tasks.

[0170] The third filling module is used to fill the corresponding chapters with the traceability information in the form of annotation information to obtain the second new education management report.

[0171] In some alternative embodiments, the device further includes: The first receiving module is used to export the education management report according to the file export format if it receives a file export format for the education management report.

[0172] The second receiving module is used to adjust the education management report according to the dimension adjustment information if it receives the dimension adjustment information, so as to obtain a third new education management report.

[0173] The third receiving module is used to adjust the education management report according to the correction information received, so as to obtain the fourth new education management report.

[0174] In some alternative embodiments, the device further includes: The correction module is used to correct the statistical caliber of the corrected education statistical indicators based on the caliber correction information if it receives an instruction to enter the database for caliber correction information, so as to obtain the corrected statistical caliber. The corrected education statistical indicators are the target education statistical indicators corresponding to the caliber correction information.

[0175] The replacement module is used to replace the statistical definitions of corrected educational statistical indicators in the educational indicator database with corrected statistical definitions, thereby obtaining an updated educational indicator database.

[0176] The educational management report generation apparatus provided in this embodiment of the invention can execute the educational management report generation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the various modules and units described above are the same as in the corresponding embodiments described above, and will not be repeated here.

[0177] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0178] The following is a detailed reference. Figure 7The diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 701, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 702 or a program loaded from memory 708 into random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the electronic device. The processor 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0179] Typically, the following devices can be connected to I / O interface 705: input devices 706 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 707 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 708 including, for example, magnetic tapes, hard disks, etc.; and communication devices 709. Communication device 709 allows electronic devices to exchange data via wireless or wired communication with other devices. Although Figure 7 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0180] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 709, or installed from a memory 708, or installed from a ROM 702. When the computer program is executed by the processor 701, it performs the functions defined in the method for generating an education management report according to embodiments of the present invention.

[0181] Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0182] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium after being downloaded via a network. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the method for generating education management reports shown in the above embodiments is implemented.

[0183] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0184] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for generating an education management report, characterized in that, The method includes: Based on the educational statistical indicators in the educational management problem text, determine the report type corresponding to the educational management problem text and at least one target educational statistical indicator corresponding to the report type; Based on the at least one target educational statistical indicator and the data constraint information in the educational management problem text, determine the educational data corresponding to the educational management problem text; Feature extraction is performed on the educational data to obtain data feature information; Based on the report type and the data feature information, determine the report template corresponding to the education management problem text; Execute the data analysis task corresponding to the report template to obtain the data analysis results; The data analysis results are then filled into the report template to obtain the education management report.

2. The method according to claim 1, characterized in that, The step of determining the report template corresponding to the educational management problem text based on the report type and the data feature information includes: Based on the report type, a report template library is retrieved to determine the initial report template corresponding to the educational management problem text. The report template library includes the correspondence between report types and initial report templates. If the data feature information indicates that the data dimension of the educational data is less than a first preset value and the sparsity of the educational data is greater than a second preset value, then the initial report template is determined as the report template. If the data feature information indicates that the data dimension of the educational data is greater than or equal to the first preset value, the sparsity of the educational data is less than or equal to the second preset value, and the volatility of the educational data is greater than or equal to the third preset value, then based on the correlation between the target educational statistical indicators, the related educational statistical indicators among the target educational statistical indicators are determined, and a correlation analysis section for performing correlation analysis on the related educational statistical indicators is added to the initial report template to obtain the report template.

3. The method according to claim 1, characterized in that, The execution of the data analysis task corresponding to the report template, and the resulting data analysis results, include: Based on the report type, an education indicator database is retrieved to obtain at least one target education statistical indicator corresponding to the report type. The education indicator database includes the correspondence between report types and target education statistical indicators. The chapter education statistics indicators corresponding to each chapter in the report template are determined from the at least one target education statistics indicator, and the chapter data constraint information corresponding to each chapter is determined from the data constraint information; Based on the chapter-specific educational statistics indicators and chapter-specific data constraints for each chapter, generate a data analysis sub-task for each chapter. Execute the data analysis sub-task corresponding to each chapter to obtain the data analysis sub-result corresponding to each chapter, and the data analysis result includes each of the data analysis sub-results.

4. The method according to claim 3, characterized in that, The step of filling the report template with the data analysis results to obtain the education management report includes: The data analysis sub-results corresponding to each chapter are visualized to obtain the visualized data corresponding to each chapter. Based on the fusion result of the visualization data and the data analysis sub-results corresponding to each chapter, the text content corresponding to each chapter is generated; The visualization data and text content corresponding to each chapter are filled into the corresponding chapter to obtain the education management report.

5. The method according to claim 4, characterized in that, The method further includes: For each chapter, anomaly detection is performed on the data analysis sub-results of that chapter to obtain anomaly detection results; If the anomaly detection result indicates that the data analysis sub-result has failed the anomaly detection, then the chapter education statistics indicator corresponding to the data analysis sub-result is determined as an abnormal education statistics indicator, and each next-level education statistics indicator corresponding to the abnormal education statistics indicator is determined. Based on the ratio of the same-period change corresponding to each of the next-level educational statistical indicators to the same-period change corresponding to the abnormal educational statistical indicators, the influence coefficient of each of the next-level educational statistical indicators on the abnormal educational statistical indicators is obtained. The influence coefficient that is greater than the fourth preset value is determined as the target influence coefficient; The intelligent agent is used to process the target influence coefficient and the next-level educational statistical indicators corresponding to the target influence coefficient to generate anomaly analysis data; The anomaly analysis data is then filled into the relevant section to obtain the first new education management report.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: The data analysis sub-results, data analysis sub-tasks, chapter statistical criteria, and chapter educational data corresponding to each chapter are combined to obtain the traceability information corresponding to each chapter. The chapter statistical criteria are the statistical criteria corresponding to the chapter educational statistical indicators, the chapter educational data are the educational data corresponding to the chapter educational statistical indicators, and the chapter educational statistical indicators correspond to the data analysis sub-tasks. The traceability information corresponding to each chapter is filled into the corresponding chapter in the form of annotation information to obtain the second new education management report.

7. The method according to any one of claims 1 to 5, characterized in that, The method further includes: If a file export format for the education management report is received, then the education management report is exported according to the file export format. And / or, If a dimension adjustment information for the education management report is received, the education management report is adjusted according to the dimension adjustment information to obtain a third new education management report; And / or, If a correction message is received regarding the definition of the education management report, the education management report is adjusted according to the correction message to obtain the fourth new education management report.

8. The method according to claim 7, characterized in that, After adjusting the education management report according to the aforementioned corrective information to obtain the fourth new education management report, the method further includes: If an instruction to input the caliber correction information is received, the statistical caliber of the corrected educational statistical indicators is corrected based on the caliber correction information to obtain the corrected statistical caliber, wherein the corrected educational statistical indicators are the target educational statistical indicators corresponding to the caliber correction information. The updated education indicator database is obtained by replacing the statistical caliber of the corrected education statistical indicators in the education indicator database with the corrected statistical caliber.

9. An apparatus for generating an education management report, characterized in that, The device includes: The first determining module is used to determine, based on the educational statistical indicators in the educational management problem text, the report type corresponding to the educational management problem text and at least one target educational statistical indicator corresponding to the report type. The second determining module is used to determine the educational data corresponding to the educational management problem text based on the at least one target educational statistical indicator and the data constraint information in the educational management problem text; The feature extraction module is used to extract features from the educational data to obtain data feature information; The third determining module is used to determine the report template corresponding to the education management problem text based on the report type and the data feature information; The execution module is used to execute the data analysis task corresponding to the report template and obtain the data analysis results; The first filling module is used to fill the report template with the data analysis results to obtain the education management report.

10. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the method for generating an education management report according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the method for generating an education management report according to any one of claims 1 to 8.

Images