Student core ability evaluation research and analysis system

Abstract

The invention belongs to the technical field of teaching systems, and discloses a student core ability evaluation, investigation and analysis system, which comprises a data acquisition unit for acquiring comprehensive performance data of students, including academic performance, classroom performance, practice items, competition and physique evaluation; the knowledge graph construction unit extracts structured information from the data by applying a natural language processing technology, and constructs a student core ability knowledge graph; the core capability evaluation unit extracts data of a specific time period from the atlas based on a long-short-term memory network model, and performs classification prediction to obtain a core capability evaluation result; the result display unit is responsible for visually displaying the results; and the feedback unit provides targeted feedback and improvement suggestions for students, teachers and parents. The whole system aims to comprehensively and deeply evaluate and improve the core ability of students. According to the technical scheme, the ability development of students can be dynamically monitored, and an accurate evaluation result can be provided.

Description

Technical Field

[0001] The present invention belongs to the technical field of teaching systems, and particularly relates to a student core ability evaluation, research and analysis system. Background Art

[0002] In the existing education evaluation system, the evaluation of students' core abilities usually relies on single-dimensional data (such as academic performance), lacking a comprehensive consideration of students' comprehensive qualities. In addition, traditional evaluation methods are difficult to capture the dynamic changes in students' ability development and cannot provide personalized feedback and guidance for students. Therefore, a technical solution that can integrate multi-dimensional data, dynamically monitor students' ability development, and provide accurate evaluation is needed. Summary of the Invention

[0003] The present invention aims to provide a student core ability evaluation system and method based on knowledge graphs and LSTM, which can realize a comprehensive and dynamic evaluation of students' core abilities through multi-dimensional data collection, knowledge graph construction, and dynamic prediction of the LSTM model, and provide decision-making support for educators.

[0004] To achieve the above object, the present invention provides a student core ability evaluation, research and analysis system, including: A data collection unit for obtaining students' comprehensive performance data, where the students' comprehensive performance data includes students' academic performance, classroom performance, practical projects, competition results, and physical fitness evaluation data in each time period; A knowledge graph construction unit for using natural language processing technology to extract structured information from students' comprehensive performance data and constructing a student core ability knowledge graph based on the extracted structured information; A core ability evaluation unit for classifying and predicting the students' comprehensive performance data extracted within a preset time period in the student core ability knowledge graph by inputting the extracted students' comprehensive performance data into a core ability evaluation model to obtain corresponding core ability evaluation results; wherein, the core ability evaluation model is constructed based on a long short-term memory network; A result display unit for visually displaying the core ability evaluation results; A feedback unit for providing feedback and improvement suggestions for students, teachers, and parents.

[0005] Optionally, the data collection unit specifically includes: A data acquisition module for obtaining students' academic performance, classroom performance, practical projects, competition results, and physical fitness evaluation data in each time period; A data preprocessing module for cleaning, annotating, and format-converting the collected students' comprehensive performance data to form preprocessed students' comprehensive performance data.

[0006] Optionally, the knowledge graph construction unit specifically includes: An information extraction module for extracting entities, relationships, and events from the comprehensive student performance data using natural language processing technology to form structured information; A knowledge fusion module for fusing the extracted structured information with an existing knowledge base to construct a knowledge graph of students' core competencies.

[0007] Optionally, the core competency evaluation unit specifically includes: A model construction module for constructing an initial core competency evaluation model based on a long short-term memory network; A training and optimization module for training the initial core competency evaluation model and optimizing hyperparameters to obtain an optimized core competency evaluation model; A model application module for performing a research and analysis task on students' core competencies according to the optimized core competency evaluation model.

[0008] Optionally, the training and optimization module specifically includes: A training data acquisition module for acquiring training data, which includes comprehensive student performance training data and corresponding evaluation results; A training module for extracting the hyperparameter combinations included in the initial core competency evaluation model; training the core competency evaluation models corresponding to each hyperparameter combination based on the training data and evaluating the training results to obtain the evaluation scores corresponding to each hyperparameter combination; A hyperparameter optimization module for constructing a walrus population with each hyperparameter combination as a walrus; performing parameter optimization within the walrus population based on the evaluation scores corresponding to each hyperparameter combination combined with the walrus optimization algorithm to obtain the optimal hyperparameter combination; constructing an optimized core competency evaluation model based on the optimal hyperparameter combination.

[0009] Optionally, the hyperparameter optimization module specifically includes: A parameter setting sub-module for setting the value range, population size, and number of iterations of the hyperparameter combination; Performing multiple iterative updates on each hyperparameter combination in the walrus population based on the walrus optimization algorithm. During each iterative update, calculating the evaluation scores corresponding to each hyperparameter combination and updating the walrus population based on the evaluation scores corresponding to each hyperparameter combination until the number of iterations reaches the preset number and then outputting the optimal hyperparameter combination.

[0010] Optionally, the result display unit specifically includes: A chart display module for displaying the core competency evaluation results in the form of charts.

[0011] Optionally, it further includes a system optimization unit, specifically including: A data update module for updating the student core ability knowledge graph according to the student comprehensive performance data obtained in real time; A user feedback module for optimizing the system according to user feedback.

[0012] The technical effects of the present invention are as follows: (1) Comprehensiveness: By integrating multi-dimensional data, the present invention can achieve a comprehensive evaluation of students' core abilities.

[0013] (2) Dynamics: Through the knowledge graph and the LSTM model, the present invention can capture the dynamic changes in the development of students' abilities.

[0014] (3) Precision: Based on hyperparameter optimization and the walrus optimization algorithm, the present invention can improve the prediction accuracy of the model.

[0015] (4) Visualization and feedback: Through intuitive visualization and personalized feedback, the present invention can provide reliable decision-making support for educators and students. Description of the Drawings

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0017] The drawings forming a part of this application are used to provide a further understanding of this application. The schematic embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation of this application. In the drawings: Figure 1 It is a schematic diagram of the model structure in the embodiment of the present invention; Figure 2 It is a flowchart of the evaluation implementation in the embodiment of the present invention. Detailed Embodiments

[0018] The various exemplary embodiments of the present invention will now be described in detail. This detailed description should not be considered as a limitation of the present invention, but rather as a more detailed description of certain aspects, features, and implementation schemes of the present invention.

[0019] It should be understood that the terms described in the present invention are only for describing specific embodiments and are not intended to limit the present invention. Additionally, for the numerical ranges in the present invention, it should be understood that each intermediate value between the upper and lower limits of the range is also specifically disclosed. Intermediate values within any stated value or stated range, as well as each smaller range between any other stated value or intermediate value within the stated range, are also included in the present invention. The upper and lower limits of these smaller ranges may be independently included or excluded from the range.

[0020] Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. Although the present invention only describes preferred methods, any method similar or equivalent to those described herein may also be used in the implementation or testing of the present invention. All documents mentioned in this specification are incorporated by reference to disclose and describe the methods related to the documents. In case of conflict with any incorporated document, the content of this specification shall prevail.

[0021] Regarding the use of "comprising", "including", "having", "containing", etc. herein, they are all open-ended terms, meaning including but not limited to.

[0022] It should be noted that, without conflict, the embodiments in this application and the features in the embodiments can be combined with each other. The following will refer to the accompanying drawings and describe the application in detail in combination with the embodiments.

[0023] As Figure 1 - Figure 2 shown, in this embodiment, a student core ability evaluation and research analysis system is provided, including: a data acquisition unit for obtaining student comprehensive performance data, where the student comprehensive performance data includes academic achievements, classroom performance, practical projects, competition results, and physical fitness assessment data of students in each time period; a knowledge graph construction unit for using natural language processing technology to extract structured information from the student comprehensive performance data and constructing a student core ability knowledge graph based on the extracted structured information; a core ability evaluation unit for classifying and predicting by inputting the extracted student comprehensive performance data within a preset time period in the student core ability knowledge graph into a core ability evaluation model to obtain corresponding core ability evaluation results, where the core ability evaluation model is constructed based on a long short-term memory network; a result display unit for visually displaying the core ability evaluation results; and a feedback unit for providing feedback and improvement suggestions for students, teachers, and parents.

[0024] In the existing education evaluation system, the evaluation of students' core competencies usually relies on single-dimensional data (such as academic performance), lacking a comprehensive consideration of students' overall qualities. This evaluation method mainly focuses on students' knowledge mastery, while ignoring their comprehensive performance in aspects such as ideological and moral character, physical and mental health, artistic accomplishment, and social practice. In addition, traditional evaluation methods are difficult to capture the dynamic changes in students' ability development and cannot provide personalized feedback and guidance to students. For example, teachers' empirical evaluations often have strong subjective colors, and the evaluation results may be affected by teachers' personal cognitive levels and emotional states. At the same time, this evaluation method is mostly periodic, relying on regular exams or assessments, and it is difficult to provide real-time feedback on students' learning situations.

[0025] With the advancement of education evaluation reform, education evaluation is shifting from "empirical evaluation" to "digital evaluation", from "single evaluation" to "comprehensive evaluation", and from "result evaluation" to "process evaluation". Through constructing a dynamically updated evaluation model and full-scenario, multi-modal data collection, the new generation of digital technologies can achieve a comprehensive consideration of students' overall qualities. For example, through big data and artificial intelligence technologies, multi-dimensional data such as students' academic levels, classroom performances, social practices, and physical and mental health can be collected and analyzed. This multi-dimensional data collection not only includes text information but also covers multi-modal data such as audio, video, and psychological indicators, which can comprehensively present the critical moments and typical behaviors in students' growth processes.

[0026] In addition, intelligent evaluation systems can track students' learning behaviors in real time, provide personalized learning resources, and dynamically adjust teaching strategies. Through a data-driven and precise learning evaluation mechanism, the learning process of students can be continuously monitored, problems of students can be discovered in a timely manner, and targeted feedback can be provided. This evaluation method not only pays attention to students' academic achievements but also can comprehensively reflect students' growth processes and overall qualities.

[0027] To sum up, there are many limitations in the traditional education evaluation system, which are difficult to meet the requirements of the new era's education reform. Therefore, a technical solution that can integrate multi-dimensional data, dynamically monitor students' ability development, and provide precise evaluation is needed to promote the transformation of education evaluation from single, static, and empirical to comprehensive, dynamic, and intelligent.

[0028] This embodiment aims to provide a student core competency evaluation system and method based on knowledge graphs and LSTM. Through multi-dimensional data collection, knowledge graph construction, and dynamic prediction of the LSTM model, a comprehensive and dynamic evaluation of students' core competencies can be achieved, and decision-making support can be provided for educators.

[0029] The system provided in this embodiment realizes a comprehensive evaluation of students' core capabilities by integrating multi-dimensional data of students' academic achievements, classroom performance, practical projects, competition results, and physical fitness evaluations. At the same time, with the help of knowledge graphs and LSTM models, the system can capture the dynamic changes in students' ability development. Based on hyperparameter optimization and the walrus optimization algorithm, the prediction accuracy of the model is improved, ensuring the accuracy of the evaluation. Finally, through intuitive visual displays and personalized feedback, the system provides strong decision-making support for educators and students.

[0030] The specific implementation process of this embodiment includes: Student information acquisition: Collect data on students' academic achievements, classroom performance, practical projects, competition results, physical fitness evaluations, etc. through multiple channels such as intelligent terminals, educational platforms, and school management systems.

[0031] Clean, annotate, and transform the collected unstructured data (such as text, images, audio) to form structured data for analysis.

[0032] Knowledge graph construction: Use natural language processing techniques (such as the UIE model of PaddleNLP) to extract entities (students, courses, competitions), relationships (student - achievement, student - competition result), and events (practical activities) from text data.

[0033] Integrate the extracted structured information with the existing basic student information database to construct a knowledge graph of students' core capabilities.

[0034] The knowledge graph can integrate data from different sources and in different formats into a unified graph structure, enabling data interoperability.

[0035] This embodiment correlates multi-dimensional data such as academic achievements, classroom performance, practical projects, competition results, and physical fitness evaluations to form a complete student ability graph. Through the graph structure, potential relationships between different data can be intuitively discovered. For example, analyze the correlation between academic achievements and classroom performance, or the connection between practical projects and innovation ability. In addition, as new data is continuously added, the knowledge graph can be updated in real time to maintain the timeliness and integrity of the data.

[0036] In the evaluation of students' core capabilities, the knowledge graph can help educators comprehensively understand the ability structure of students, discover the laws hidden behind the data, and thus provide more accurate evaluations and guidance.

[0037] Evaluation of students' core capabilities: Extract information related to students for one semester or academic year from the knowledge graph, input the extracted relevant information into the core ability evaluation model for classification prediction, and output the corresponding evaluation results; The core competence evaluation model is constructed based on the Long Short-Term Memory network (LSTM). By solving the problem of long-term dependence, improving robustness, and having a flexible information selection mechanism, LSTM provides a more accurate and comprehensive analysis ability for educational evaluation. The construction and optimization process of the model is as follows: Define the LSTM model architecture, including the input layer, LSTM layer, fully connected layer, and output layer.

[0038] Initialize the hyperparameters of the model, such as the number of hidden layer units, number of layers, learning rate, Dropout ratio, etc.

[0039] Obtain the training data, including the training data of students' comprehensive performance and the corresponding evaluation results (such as teachers' comprehensive evaluation, ability level); Divide the training data into a 70% training set, a 15% validation set, and a 15% test set.

[0040] Extract the key hyperparameters of the LSTM model, such as the number of hidden layer units, number of layers, learning rate, Dropout ratio, etc.

[0041] Initialize the Walrus Optimization Algorithm: Set the value range of the hyperparameter combination, set the population size and the number of iterations.

[0042] Randomly generate an initial walrus population, where each walrus represents a hyperparameter combination.

[0043] Model training and evaluation: For each hyperparameter combination, use the training set to train the LSTM model. Use the validation set to verify and evaluate the model performance, calculate the evaluation score, and use the evaluation score as the fitness value of this hyperparameter combination.

[0044] According to the rules of the Walrus Optimization Algorithm, iteratively update the hyperparameter combinations in the population; in each iteration, calculate the evaluation score of the new hyperparameter combination and update the population. Repeat the above process until the preset number of iterations is reached, and output the optimal hyperparameter combination: Select the hyperparameter combination with the highest fitness value from the final walrus population as the optimal hyperparameter combination.

[0045] Reconstruct the LSTM model using the optimal hyperparameter combination. Based on the optimized LSTM model, classify and predict the relevant information of students, and output the corresponding evaluation results of students' core competencies.

[0046] The Walrus Optimization Algorithm can efficiently solve complex optimization problems by simulating the group behavior and signal mechanism of walruses and combining the dynamic adjustment of the exploration and exploitation phases. In this embodiment, the Walrus Optimization Algorithm is used to automatically optimize the hyperparameters, avoiding the cumbersome manual tuning and improving the generalization ability and fusion effect of the model.

[0047] Implementable. In this embodiment, the evaluation results and development trends of students' core competencies are visually presented in the form of charts, and personalized development suggestions are provided for students, such as recommending suitable practical activities or learning resources, and a comprehensive ability report of students is provided for teachers and parents to help them better understand the strengths and weaknesses of students.

[0048] In this embodiment, through the combination of data collection, knowledge graph construction, LSTM model training, and walrus optimization algorithm, the dynamic evaluation and accurate prediction of students' core competencies are realized. Through hyperparameter optimization, the performance and reliability of the model are further improved, providing scientific technical support for educational evaluation.

[0049] As mentioned above, only the specific implementation mode of this application that is better is described, but the protection scope of this application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed in this application should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. A research and analysis system for evaluating students' core competencies, characterized in that, including: A data acquisition unit for obtaining students' comprehensive performance data, where the students' comprehensive performance data includes academic achievements, classroom performance, practical projects, competition results, and physical fitness assessment data of students in various time periods; A knowledge graph construction unit for extracting structured information from the students' comprehensive performance data using natural language processing technology and constructing a knowledge graph of students' core competencies based on the extracted structured information; A core competency evaluation unit for classifying and predicting by inputting the extracted students' comprehensive performance data within a preset time period in the knowledge graph of students' core competencies into a core competency evaluation model to obtain corresponding core competency evaluation results; among them, the core competency evaluation model is constructed based on a long short-term memory network; A result display unit for visually displaying the core competency evaluation results; A feedback unit for providing feedback and improvement suggestions for students, teachers, and parents.

2. The student core competence evaluation, research and analysis system according to claim 1, wherein The data acquisition unit specifically includes: A data acquisition module for obtaining academic achievements, classroom performance, practical projects, competition results, and physical fitness assessment data of students in various time periods; A data preprocessing module for cleaning, annotating, and format-converting the collected students' comprehensive performance data to form preprocessed students' comprehensive performance data.

3. The student core competency evaluation and research analysis system according to claim 1, wherein, The knowledge graph construction unit specifically includes: An information extraction module for extracting entities, relationships, and events from the students' comprehensive performance data using natural language processing technology to form structured information; A knowledge fusion module for fusing the extracted structured information with an existing knowledge base to construct a knowledge graph of students' core competencies.

4. A student core competency evaluation, research and analysis system according to claim 1, characterized in that The core competency evaluation unit specifically includes: A model construction module for constructing an initial core competency evaluation model based on a long short-term memory network; A training and optimization module for training the initial core competency evaluation model and optimizing hyperparameters to obtain an optimized core competency evaluation model; A model application module for performing a research and analysis task on the core competencies of students according to the optimized core competency evaluation model.

5. The research and analysis system for evaluating students' core competencies according to claim 4, wherein, The training and optimization module specifically includes: A training data acquisition module for obtaining training data, where the training data includes students' comprehensive performance training data and corresponding evaluation results; A training module for extracting the hyperparameter combinations included in the initial core competency evaluation model; training the core competency evaluation models corresponding to each hyperparameter combination based on the training data and evaluating the training results to obtain the evaluation scores corresponding to each hyperparameter combination; A hyperparameter optimization module for constructing a walrus population with each hyperparameter combination as a walrus; performing parameter optimization within the walrus population based on the evaluation scores corresponding to each hyperparameter combination combined with the walrus optimization algorithm to obtain an optimal hyperparameter combination; constructing an optimized core competency evaluation model based on the optimal hyperparameter combination.

6. The student core competence evaluation research and analysis system according to claim 5, characterized in that, The hyperparameter optimization module specifically includes: A parameter setting sub-module for setting the value range, population size, and number of iterations of the hyperparameter combination; Based on the walrus optimization algorithm, each hyperparameter combination in the walrus population is iteratively updated multiple times. During each iterative update process, the evaluation scores corresponding to each hyperparameter combination are calculated, and the walrus population is updated based on the evaluation scores corresponding to each hyperparameter combination until the optimal hyperparameter combination is output after the number of iterations reaches the preset number of times.

7. The student core competence evaluation and research analysis system according to claim 1, characterized in that The result display unit specifically includes: The chart display module is used to display the core ability evaluation results in the form of charts.

8. The research and analysis system for evaluating students' core competencies according to claim 1, characterized in that, It also includes a system optimization unit, which specifically includes: The data update module is used to update the student core ability knowledge graph according to the student comprehensive performance data obtained in real time; The user feedback module is used to optimize the system according to user feedback.

Images