Education evaluation report generation method and system

Abstract

The invention is suitable for the technical field of data processing, and provides an education evaluation report generation method and system, and the system comprises a data management module which is used for obtaining the data of evaluation indexes in each evaluation item in an evaluation report, and obtaining the index data; the index management module is used for adjusting the evaluation index and the weight thereof, and performing statistical processing on the index data according to the evaluation index and the weight thereof to obtain statistical data; the template management module is used for filling the index data into a Prompt template and inputting the filled Prompt template into a large language model, and the large language model analyzes facts reflected by the index data based on cue words in the Prompt template to obtain analysis content; and the report generation module is used for integrating the analysis content and the statistical data into an evaluation report template to obtain a target evaluation report. The large language model is used for deep data analysis, the evaluation report is generated, the report generation time is remarkably shortened, and manual errors and subjective deviations are reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular, relates to a method and system for generating an education evaluation report. Background Art

[0002] With the rapid development of information technology and artificial intelligence, the demand for intelligence in the field of education is growing. Education evaluation reports are mainly used to comprehensively evaluate the quality and effectiveness of an educational institution, course or educational program. It usually includes analysis of student performance, teaching quality, teaching staff, facilities and learning environment. The content of the report needs to be objective and fair, use clear and accurate language, and provide sufficient data support.

[0003] Traditional educational evaluation methods usually rely on manual analysis and report writing, which is not only time-consuming and labor-intensive, but also has subjective problems. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method and system for generating an education evaluation report, aiming to solve the problem of subjectivity in manual analysis and report writing.

[0005] The embodiment of the present application is implemented as follows: an education evaluation report generation system, the system comprising: a data management module, an indicator management module, a content generation module and a report generation module;

[0006] The data management module is used to obtain the data of the evaluation indicators in each evaluation item in the evaluation report to obtain the indicator data;

[0007] The indicator management module is used to adjust the evaluation indicators and their weights, and perform statistical processing on the indicator data according to the evaluation indicators and their weights to obtain statistical data;

[0008] The content generation module includes a template management module and a large language model, wherein the template management module is used to fill the indicator data into the Prompt template, and input the filled Prompt template into the large language model, and the large language model analyzes the facts reflected by the indicator data based on the prompt words in the Prompt template to obtain analysis content;

[0009] The report generation module is used to integrate the analysis content and the statistical data into an evaluation report template to obtain a target evaluation report.

[0010] As a further solution of the present application, the content generation module includes multiple large language models, each of which completes the analysis task of an evaluation project.

[0011] As a further solution of the present application, the system further includes:

[0012] The feedback module is used to obtain user feedback information on the target evaluation report, wherein the feedback information includes a score for the target evaluation report.

[0013] As a further solution of the present application, the data management module includes:

[0014] A data cleaning module, used to delete duplicate items in the indicator data and convert the indicator data into a unified format;

[0015] Exception handling module, used to calculate indicator data d i The average value μ of [j] j and standard deviation σ j , when the indicator data d i [j] satisfies |d i [j] - μ j |>kσ j , remove the value from the indicator data, where k is a constant and d i [j] is the i-th indicator data of the j-th indicator;

[0016] Missing value processing module, used to fill missing values ​​in indicator data;

[0017] The standardization module is used to convert the data of each indicator into the same dimension.

[0018] As a further solution of the present application, the indicator management module includes:

[0019] The indicator modification module is used to create new evaluation indicators or modify existing evaluation indicators;

[0020] The weight adjustment module is used to construct the matrix A = (a ij ) n×n , where a ij It represents the relative importance of the i-th evaluation index relative to the j-th evaluation index. The elements in the matrix A satisfy a ij >0, a ii =1, n is the dimension of matrix A, based on the formula Calculate the weight W of the i-th evaluation index i .

[0021] As a further solution of the present application, the indicator management module further includes:

[0022] The indicator optimization module is used to optimize the weights of evaluation indicators using machine learning algorithms.

[0023] As a further solution of the present application, the report generation module includes:

[0024] Evaluation report template setting module, used to adjust the layout and format of the evaluation report template;

[0025] The content filling module is used to fill the analysis content generated by the content generating module into the corresponding position of the evaluation report template.

[0026] As a further solution of the present application, the system further includes: a user interface module, which is used to provide a platform for interaction and operation for users;

[0027] The privacy protection module is responsible for protecting user data and system security.

[0028] Another object of the present application is to provide a method for generating an education evaluation report, which is applied to an education evaluation report generating system as described in any one of the above items, and the method comprises:

[0029] Obtain an evaluation report template, and obtain various evaluation items that need to be filled in according to the evaluation report template;

[0030] Obtaining indicator data for each of the evaluation items, and calculating a comprehensive score for each of the evaluation items based on the indicator data;

[0031] Fill the Prompt template with the indicator data of each evaluation item to obtain multiple input texts;

[0032] Input each of the input texts separately into a pre-trained large language model, and the large language model outputs the analysis content of each evaluation item;

[0033] Fill the analysis contents and comprehensive scores into the evaluation report template to obtain the target evaluation report.

[0034] As a further solution of the present application, the method of filling each of the analysis contents and the comprehensive score into the evaluation report template to obtain the target evaluation report further includes:

[0035] Obtaining user feedback information on the evaluation report, wherein the feedback information includes a rating scale and open questions;

[0036] The data from the rating scales were statistically analyzed and the responses to the open-ended questions were textually analyzed to extract key words and obtain feedback reports;

[0037] The large language model and the report template are optimized based on the feedback report.

[0038] The embodiment of the present application provides an education evaluation report generation system, which obtains the indicator data of each evaluation item in the evaluation report through the data management module, and the template management module fills the prompt template with the indicator data, and then inputs the filled prompt template into the large language model, and the large language model analyzes the facts reflected by the indicator data to obtain the analysis content; the indicator management system is used to adjust the evaluation indicators and their weights, and statistically process the indicator data according to the evaluation indicators and their weights to obtain statistical data; the report generation module integrates the analysis content and statistical data output by the large language model into the evaluation report template to obtain the target evaluation report. In this way, the large language model is used to perform in-depth data analysis and generate a comprehensive and accurate education evaluation report, which significantly shortens the report generation time, reduces manual errors and subjective biases, and makes the generated education evaluation report more consistent and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A structural block diagram of an education evaluation report generation system provided in an embodiment of the present application;

[0040] Figure 2 A structural block diagram of a data management module provided in an embodiment of the present application;

[0041] Figure 3 A structural block diagram of the indicator management module provided in the embodiment of the present application;

[0042] Figure 4 A structural block diagram of a report generation module provided in an embodiment of the present application;

[0043] Figure 5 A flowchart of a method for generating an education evaluation report provided in an embodiment of the present application;

[0044] Figure 6 A flowchart of another method for generating an education evaluation report provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0046] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0047] Figure 1 A structural block diagram of an education evaluation report generation system provided in an embodiment of the present application, such as Figure 1 As shown, in some embodiments of the present application, a system for generating an education evaluation report is proposed, and the system includes: a data management module 100, an indicator management module 200, a large language model 320 module and a report generation module 400.

[0048] The data management module 100 is used to obtain the data of the evaluation indicators in each evaluation item in the evaluation report to obtain the indicator data.

[0049] In some embodiments, the data management module 100 is connected to an online question-and-answer system or a performance management system through an interface, and obtains index data through various methods such as online questionnaires and performance exports. In some embodiments of the present application, in an evaluation report, multiple evaluation items are included, for example, student performance analysis, teaching quality evaluation, teacher level analysis, facility and environment evaluation, etc. For different evaluation items, the evaluation indicators are also different. Specifically, when analyzing student performance, the evaluation indicators can be mathematics scores, Chinese scores, etc., and the index data are the specific scores of each subject. When evaluating teaching quality, the evaluation indicators can be teaching ability, teaching attitude, classroom management, etc., and the index data are the specific scores of each evaluation indicator.

[0050] The indicator management module 200 is used to adjust the evaluation indicators and their weights, and perform statistical processing on the indicator data according to the evaluation indicators and their weights to obtain statistical data.

[0051] In some embodiments, statistical data is used to reflect the comprehensive score of the entire evaluation project. In an evaluation project, the influence or importance of various evaluation indicators on the evaluation project is different. The various evaluation indicators and their weights are adjusted through the indicator management system, and the indicator data is statistically processed according to the evaluation indicators and their weights, so that the obtained statistical data can better reflect the true situation of the entire evaluation project. Specifically, when conducting the evaluation project of "student performance analysis", the statistical data can be the weighted average score of each subject.

[0052] The content generation module 300 includes a template management module 310 and a large language model 320. The template management module 310 is used to fill the indicator data into the Prompt template, and input the filled Prompt template into the large language model 320. The large language model 320 analyzes the facts reflected by the indicator data based on the prompt words in the Prompt template to obtain analysis content.

[0053] In some embodiments, different evaluation items require different Prompt templates. For example, when conducting "student performance analysis", the student's performance needs to be filled in the subject corresponding to the Prompt template. The Prompt template also includes prompt words. When conducting "student performance analysis", the prompt words can be "analyze students' strong and weak subjects, and give targeted learning suggestions" or "based on the current performance status, predict possible future development directions, and propose improvement measures" and so on.

[0054] The report generation module 400 is used to integrate the analysis content and the statistical data into an evaluation report template to obtain a target evaluation report.

[0055] In this embodiment, the indicator data of each evaluation item in the evaluation report is obtained through the data management module 100, the template management module 310 fills the prompt template with the indicator data, and then inputs the filled prompt template into the large language model 320, the large language model 320 analyzes the facts reflected by the indicator data to obtain the analysis content; the indicator management system is used to set the evaluation indicators and their weights, and statistically process the indicator data according to the weights of the evaluation indicators to obtain statistical data; the report generation module 400 integrates the analysis content and statistical data output by the large language model 320 into the evaluation report template to obtain the target evaluation report. In this way, the large language model 320 is used to perform in-depth data analysis and generate a comprehensive and accurate education evaluation report, which significantly shortens the report generation time, reduces manual errors and subjective biases, and makes the generated education evaluation report more consistent and reliable.

[0056] like Figure 1 As shown, in some embodiments of the present application, the content generation module 300 includes a plurality of large language models 320, each of which completes the analysis task of an evaluation project.

[0057] In this embodiment, the evaluation report includes multiple evaluation items, such as student performance analysis, teaching quality evaluation, etc. For the analysis tasks of different evaluation items, different large language models 320 are sampled to achieve. A combination of multiple large language models 320, each large language model 320 performs the analysis task of an evaluation item, so that the generation of a complete evaluation report can be achieved and the difficulty of the overall design can be reduced. In some embodiments, each model performs only the analysis task of a specific evaluation item, so that the processing speed and accuracy can be improved.

[0058] In some embodiments of the present application, the input text data x can be obtained by obtaining an existing student performance analysis report, extracting the student performance from the analysis report, and filling the Prompt template with the student performance. i, and use the analysis report of the student's performance as the target output text y i , input text data x i The large language model 320 performs the analysis task of "student performance analysis" and generates text data f(x i ; θ), output text y according to the target i and generate text data f(x i ; θ) calculate the loss value, and adjust the parameters of the large model according to the loss value. The specific process can be expressed by the following formula;

[0059]

[0060] Among them, θ represents the model parameters, x i Represents input text data, y i represents the target output, L is the loss function, f(·) is the model function, θ * represents the adjusted model parameters.

[0061] like Figure 1 As shown, in some embodiments of the present application, the feedback module 500 is used to obtain user feedback information on the target evaluation report, and the feedback information includes a score for the target evaluation report.

[0062] In this embodiment, the user scores the target evaluation report generated by the large language model 320, and the score of the target evaluation report is fed back to the large language model 320, and the large language model 320 is rewarded or punished according to the score. In this way, human preferences are used as reward signals to guide the training process of the model, thereby enhancing the model's understanding and satisfaction of human intentions and generating outputs that are more in line with human expectations.

[0063] In some embodiments, the feedback module 500 is mainly responsible for collecting user evaluations and feedback on the report, and using this information to optimize the quality and process of report generation. The core tasks of the feedback module 500 include feedback collection, analysis and processing to improve the system. Specifically, feedback information can be obtained through online questionnaires, email feedback, and feedback functions within the system. The feedback information includes a rating scale and open questions. The rating scale includes various rating indicators. Users score according to various rating indicators, and take the average to obtain the average score of each rating indicator. Among them, the rating indicators include satisfaction with the analysis content of each evaluation project generated by the large language model 320. The answers to the open questions are subjected to text analysis, keywords and main opinions are extracted, and targeted improvement measures are formulated, and the improvement measures include optimizing the large language model, adjusting the evaluation report template, etc.

[0064] like Figure 2As shown, in some embodiments of the present application, the data management module 100 includes: a data cleaning module 110, which is used to delete duplicate items in the indicator data and convert the data into a unified format; an exception handling module 120, which is used to calculate the indicator data d i The average value μ of [j] j and standard deviation σ j , when the indicator data d i [j] satisfies |d i [j] - μ j |>kσ j , remove the value from the indicator data, where k is a constant and d i [j] is the ith indicator data of the jth indicator; the missing value processing module 130 is used to fill the missing values ​​in the indicator data; the standardization module 140 is used to convert each indicator data into the same dimension.

[0065] In this embodiment, data cleaning, outlier removal, missing value filling and standardization are performed on the indicator data, which can improve the quality of the indicator data and enable the large language model 320 to obtain more accurate results when performing data analysis.

[0066] In some embodiments, the data cleaning module 110 is used to remove noise and errors in the data to ensure data quality. Deleting duplicates in the data can ensure that each record is unique. Format consistency can convert data into a unified format, such as date format, numeric format, etc., using regular expressions and string processing functions.

[0067] In some embodiments, the exception handling module 120 identifies and processes outliers in the data to ensure the consistency and reliability of the data. Specifically, the mean and standard deviation can be used to identify outliers. i The average value μ of [j] j and standard deviation σ j , when the indicator data d i [j] satisfies |d i [j] - μ j |>kσ j When , the value is removed from the indicator data, where k is a constant, usually 2 or 3, and d i [j] is the i-th indicator number data of the j-th indicator.

[0068] In some embodiments, the missing value processing module 130 is used to fill or remove missing values ​​in the data. The missing values ​​can be filled with the mean value or with an interpolation method.

[0069] In some embodiments, the normalization module 140 is used to convert the indicator data to the same dimension for comparison and analysis. Common methods include minimum-maximum normalization and Z-score normalization. Among them, the minimum-maximum normalization is based on the formula Convert the data of each indicator to the same dimension. Z-score standardization is based on the formula Convert the data of each indicator to the same dimension, where d i [j] is the index data, μ j is the mean value and σ j is the standard deviation.

[0070] like Figure 3 As shown, in some embodiments of the present application, the indicator management module 200 includes an indicator modification module 210 and a weight adjustment module 220 .

[0071] The indicator modification module 210 is used to create a new evaluation indicator or modify an existing evaluation indicator. Specifically, the user can input the evaluation indicator and its weight through the user interface module 600. In this way, the user can adjust the evaluation indicator according to the needs and provide accurate evaluation standards and basis for report generation.

[0072] The weight adjustment module 220 is used to construct a matrix A=(a ij ) N×N , where a ij It represents the relative importance of the i-th evaluation index relative to the j-th evaluation index. The elements in the matrix A satisfy a ij >0, a ii =1, n is the dimension of matrix A, based on the formula Calculate the weight W of the i-th evaluation index i .

[0073] In this embodiment, the importance of each indicator in the overall evaluation is different. By adjusting various evaluation indicators and their weights, the obtained data can better reflect the actual situation of the entire evaluation project.

[0074] Specifically, in some embodiments, the element a in the matrix A ij It indicates the relative importance of the i-th evaluation index relative to the j-th evaluation index. It can be assigned a value based on the user's feelings. For example, if the i-th evaluation index is as important as the j-th evaluation index, then 1 point is assigned. ij =1; the i-th evaluation index is obviously more important than the j-th evaluation index, a ij = 5. Compared with the jth evaluation index, the i-th evaluation index is very important. ij=7. In this way, the entire matrix A can be constructed. By comparing the evaluation indicators in pairs, it is possible to intuitively compare which evaluation indicator is more important. Compared with mixing all the evaluation indicators together for importance assessment, it can simplify the problem and make the comparison more intuitive and accurate.

[0075] like Figure 3 In some implementations of the present application, the index management module 200 further includes an index optimization module 230, which is used to optimize the weights of the evaluation indexes using a machine learning algorithm. Specifically, in some embodiments, a random forest algorithm can be used to optimize the weights of the evaluation indexes, and the random forest can avoid the excessive sensitivity of a single model to certain noise data and has high robustness.

[0076] like Figure 4 As shown, in some embodiments of the present application, the report generation module 400 includes: an evaluation report template setting module 410 and a content filling module 420.

[0077] The evaluation report template setting module 410 is used to adjust the layout and format of the evaluation report template. By adjusting the evaluation report template, the generated target evaluation report can be made more in line with the user's expectations.

[0078] The content filling module 420 is used to fill the analysis content generated by the content generation module 300 into the corresponding position of the evaluation report template. The working process of the content filling module 420 can be represented by the following formula:

[0079] Report[i]=FillTemplate(T,Analysis[i])

[0080] Among them, Report[i] represents the i-th part of the report, FillTemplate represents the template filling function, T represents the template, and Analysis[i] represents the analysis results of the i-th part.

[0081] like Figure 1 As shown, in some embodiments of the present application, the system further includes a user interface module 600 and a privacy protection module 700. The user interface module 600 is used to provide a platform for interaction and operation for users, and the privacy protection module 700 is responsible for protecting user data and system security.

[0082] In some embodiments, the user interface module 600 includes a data input module, a report viewing module, a feedback submission module, and a user settings module. Specifically, the data input module allows the user to input evaluation indicators, upload data files, set system parameters, etc., and provides interface controls such as sliders, selection boxes, etc. for users to adjust system parameters. The report viewing module allows the user to view the generated report and provides a browsing function for the report content. The feedback submission module allows the user to evaluate the report and submit feedback, provides a form for scoring and open questions, and submits feedback data to the server. The user settings module allows the user to manage personal information, set system preferences, etc. The user interface module 600 provides a platform for interaction and operation for users, making it convenient for users to interact with the system.

[0083] like Figure 5 As shown, the present application also provides a method for generating an education evaluation report, which is applied to the above-mentioned education evaluation report generation system, and the method includes:

[0084] S110: Obtain an evaluation report template, and obtain various evaluation items that need to be filled in according to the evaluation report template;

[0085] S120: Obtaining indicator data of each evaluation item, and calculating a comprehensive score of each evaluation item according to the indicator data;

[0086] S130: Fill the Prompt template with the indicator data of each evaluation item to obtain multiple input texts;

[0087] S140: Input each of the input texts separately into the pre-trained large language model 320, and the large language model 320 outputs the analysis content of each evaluation item;

[0088] S150: Fill the analysis contents and comprehensive scores into the evaluation report template to obtain a target evaluation report.

[0089] In some embodiments, the content of each section of the evaluation report is split to obtain evaluation items, and the indicator data of each evaluation item is obtained respectively, the indicator data is processed to obtain the comprehensive score of each evaluation item, the indicator data is filled into the prompt template, and input into the large language model 320, the large language model 320 analyzes the indicator data and the comprehensive score to obtain the analysis content, and fills the analysis content into the evaluation report template to obtain a complete evaluation report. Using the large language model 320 to perform in-depth data analysis and generate a comprehensive and accurate education evaluation report significantly shortens the report generation time, reduces manual errors and subjective biases, and makes the generated education evaluation report more consistent and reliable.

[0090] like Figure 6As shown, in some embodiments of the present application, the method of filling each of the analysis contents and the comprehensive score into the evaluation report template to obtain a complete evaluation report further includes:

[0091] S210: Obtaining user feedback information on the evaluation report, wherein the feedback information includes a rating scale and open questions;

[0092] S220: Statistical analysis of the rating scale data and text analysis of the answers to the open-ended questions to extract keywords and obtain a feedback report;

[0093] S230: Optimizing the large language model and the report template based on the feedback report.

[0094] In this embodiment, the large language model, evaluation report template, etc. are optimized through user feedback on the target evaluation report, so that the target evaluation report subsequently generated by the system is more accurate and meets the user's expectations. Specifically, in some embodiments, by collecting the user's analysis content of each evaluation item generated by the large prediction model and scoring it, the large language model 320 is rewarded or punished according to the score. In this way, human preferences are used as reward signals to guide the training process of the model, thereby enhancing the model's understanding and satisfaction of human intentions and generating outputs that are more in line with human expectations.

[0095] It should be understood that, although each step in the flow chart of each embodiment of the present application is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is clear explanation in this article, the execution of these steps does not have strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0096] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0097] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0098] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

[0099] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An education evaluation report generation system, characterized in that: The system includes: a data management module, an indicator management module, a content generation module and a report generation module; The data management module is used to obtain the data of the evaluation indicators in each evaluation item in the evaluation report to obtain the indicator data; The indicator management module is used to adjust the evaluation indicators and their weights, and perform statistical processing on the indicator data according to the evaluation indicators and their weights to obtain statistical data; The content generation module includes a template management module and a large language model, wherein the template management module is used to fill the indicator data into the Prompt template, and input the filled Prompt template into the large language model, and the large language model analyzes the facts reflected by the indicator data based on the prompt words in the Prompt template to obtain analysis content; The report generation module is used to integrate the analysis content and the statistical data into an evaluation report template to obtain a target evaluation report.

2. The educational evaluation report generation system according to claim 1, characterized in that: The content generation module includes a plurality of large language models, each of which completes an analysis task of an evaluation project.

3. The educational evaluation report generation system according to claim 2, characterized in that: The system further comprises: The feedback module is used to obtain user feedback information on the target evaluation report, wherein the feedback information includes a score for the target evaluation report.

4. The educational evaluation report generation system according to claim 1, characterized in that: The data management module comprises: A data cleaning module, used to delete duplicate items in the indicator data and convert the indicator data into a unified format; Exception handling module, used to calculate indicator data d i The average value μ of [j] j and standard deviation σ j , when the indicator data d i [j] satisfies |d i [j] - μ j |>kσ j , remove the value from the indicator data, where k is a constant and d i [j] is the i-th indicator data of the j-th indicator; Missing value processing module, used to fill missing values ​​in indicator data; The standardization module is used to convert the data of each indicator into the same dimension.

5. The educational evaluation report generation system according to claim 1, characterized in that: The indicator management module includes: The indicator modification module is used to create new evaluation indicators or modify existing evaluation indicators; The weight adjustment module is used to construct the matrix A = (a ij ) n×n , where a ij It represents the relative importance of the i-th evaluation index relative to the j-th evaluation index. The elements in the matrix A satisfy a ij >0, a ii =1, n is the dimension of matrix A, based on the formula Calculate the weight W of the i-th evaluation index i .

6. The educational evaluation report generation system according to claim 5, characterized in that: The indicator management module also includes: The indicator optimization module is used to optimize the weights of evaluation indicators using machine learning algorithms.

7. The educational evaluation report generation system according to claim 1, characterized in that: The report generation module comprises: Evaluation report template setting module, used to adjust the layout and format of the evaluation report template; The content filling module is used to fill the analysis content generated by the content generating module into the corresponding position of the evaluation report template.

8. The educational evaluation report generation system according to claim 1, characterized in that: The system also includes: a user interface module, which is used to provide a platform for interaction and operation for users; The privacy protection module is responsible for protecting user data and system security.

9. A method for generating an education evaluation report, applied to an education evaluation report generating system as claimed in any one of claims 1 to 8, characterized in that: The method comprises: Obtain an evaluation report template, and obtain various evaluation items that need to be filled in according to the evaluation report template; Obtaining indicator data for each of the evaluation items, and calculating a comprehensive score for each of the evaluation items based on the indicator data; Fill the Prompt template with the indicator data of each evaluation item to obtain multiple input texts; Input each of the input texts separately into a pre-trained large language model, and the large language model outputs analysis content of each evaluation item; Fill the analysis contents and comprehensive scores into the evaluation report template to obtain the target evaluation report.

10. The method for generating an education evaluation report according to claim 9, characterized in that: After the method of filling each of the analysis contents and the comprehensive score into the evaluation report template to obtain the target evaluation report, the method further includes: Obtaining user feedback information on the evaluation report, wherein the feedback information includes a rating scale and open questions; The data from the rating scales were statistically analyzed and the responses to the open-ended questions were textually analyzed to extract key words and obtain feedback reports; The large language model and the report template are optimized based on the feedback report.

Images