Engineering education authentication auxiliary system

Abstract

The invention discloses an engineering education authentication auxiliary system, and relates to the technical field of education, and the system comprises the following components: a global standard integration library, an automatic analysis engine, a deep content comparison and teaching target and ability cultivation evaluation, and a visual report generation and continuous optimization and feedback mechanism. According to the engineering education authentication auxiliary system, the global standard integration library and the automatic analysis engine are integrated, comprehensive coverage and deep analysis of the engineering education standard are achieved, the automatic analysis engine arranged in the system can automatically analyze various requirements of the global and regional engineering education standard, and meanwhile, the engineering education authentication auxiliary system can automatically analyze the requirements of the global and regional engineering education standard. The NLP technology and the machine learning algorithm are adopted to carry out deep content comparison and teaching target and ability cultivation evaluation, and the system not only can identify the direct corresponding relation between the course content and the standard, but also can deeply understand the teaching target and the ability cultivation target behind the course, so that a more accurate and valuable evaluation result is provided for a user.

Description

Technical Field

[0001] The present invention relates to the field of educational technology, and in particular to an engineering education certification auxiliary system. Background Art

[0002] With the rapid development of information technology and the widespread application of the Internet of Things (IoT), the importance of engineering education accreditation has become increasingly prominent. The traditional engineering education evaluation process is cumbersome and time-consuming, relying on a large amount of manual review and comparison, which is not only inefficient but also difficult to ensure the accuracy and consistency of the evaluation. Globally, ABET and EUR-ACE authoritative organizations have formulated detailed engineering education standards to ensure that the quality of education is in line with international standards. However, the complexity and diversity of these standards have brought great challenges to the accreditation of educational institutions.

[0003] The traditional engineering education certification system has several significant shortcomings. The manual review process is cumbersome and prone to errors. Especially when faced with a large amount of complex teaching materials and standard documents, it is difficult for auditors to ensure the comprehensiveness and accuracy of the evaluation. Due to the lack of effective automated analysis methods, educational institutions often need to invest a lot of manpower and time to complete certification preparations, which increases the cost and cycle of certification. The traditional manual review method has problems such as strong subjectivity, time-consuming, and low efficiency. It is difficult to fully and accurately reflect the teaching quality and standard compliance of educational institutions. Therefore, it is particularly important to develop an engineering education certification auxiliary system. Summary of the invention

[0004] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide an engineering education certification auxiliary system. The system realizes a comprehensive, accurate and efficient evaluation of the quality of engineering education by integrating global standards, automated analysis, in-depth content comparison, teaching objectives and ability training evaluation, visual report generation, and continuous optimization and feedback mechanism, providing strong certification support for educational institutions.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an engineering education certification auxiliary system, which includes a global standard integrated library, an automated analysis engine, in-depth content comparison and teaching objectives and ability training evaluation, visual report generation and continuous optimization and feedback mechanism;

[0006] The global standard integrated library: The system has established an integrated library that comprehensively covers global and regional engineering education standards including ABET and EUR-ACE;

[0007] The automated analysis engine: A built-in efficient automated analysis engine can automatically analyze various requirements of engineering education standards, including but not limited to curriculum system, experimental projects, internship experience, teaching objectives and ability training objectives;

[0008] The in-depth content comparison: using NLP technology to deeply analyze the course outlines, lab reports, and internship record teaching materials provided by educational institutions, identify and extract key information, accurately compare with standard requirements, and identify directly corresponding and potentially related items;

[0009] The teaching objectives and ability development evaluation: Through machine learning algorithms, the system can not only identify the direct correspondence between course content and standards, but also deeply understand the teaching objectives and ability development objectives behind the course, and evaluate its potential contribution to improving students' comprehensive abilities;

[0010] Visual report generation: Based on the analysis results, the system automatically generates a detailed and intuitive evaluation report, including compliance analysis, problem points and improvement suggestions;

[0011] The continuous optimization and feedback mechanism: The system supports user feedback and data accumulation, and improves the accuracy and efficiency of evaluation by continuously learning and optimizing algorithm models.

[0012] Furthermore, the global standard integrated library explicitly includes global and regional engineering education standards that need to be included in the integrated library, including but not limited to ABET and EUR-ACE, which are represented by the concept of set. S is the standard set, S1 is the ABET standard, and S2 is the EUR-ACE standard. Then S={S1, S2}. For each selected standard, comprehensive data collection is carried out, including standard documents, specifications, and requirements. The collected data is sorted and classified, and a database structure is designed to store the sorted data. The sorted and classified data is entered into the database, the accuracy of the entered data is calculated, the entered data is verified and optimized, the established integrated library is tested and evaluated, and the integrated library is regularly maintained and updated.

[0013] Furthermore, the automated analysis engine imports the engineering education standard data in the global standard integration library into the automated analysis engine, cleans and formats the data, designs and implements a module specifically used to parse the engineering education standard requirements. These modules should have the ability to identify, classify and extract key information. For key areas such as curriculum system, experimental projects, internship experience, teaching objectives and capacity building objectives, after the automated analysis engine is started, it traverses the imported standard data according to preset parsing rules and algorithms. For each standard or requirement, the engine will identify the field to which it belongs, extract key information, and store this information in the system's internal data structure. It will integrate the parsed requirements data, establish the relationship between them, and build a comprehensive and structured engineering education standard analysis model.

[0014] Furthermore, the automated analysis engine outputs the analysis results of the automated analysis engine in the form of visual reports, data tables, and charts according to user needs. The reports should clearly display the specific requirements of each standard, key information points, and the relationships between them, to help users quickly understand and evaluate the compliance and quality of engineering education standards, perform performance testing on the automated analysis engine, evaluate its analysis speed, accuracy, and stability indicators, iteratively optimize the engine based on test results and user feedback, improve analysis efficiency, accuracy, and user experience, and timely upgrade and expand the analysis engine.

[0015] Furthermore, the deep content comparison obtains electronic or scanned copies of course outlines, laboratory reports, and internship records from educational institutions, performs manual review or data cleaning when necessary, cleans and preprocesses the collected data, performs word segmentation according to language characteristics, processes punctuation, unifies the text format, and uses NLP technology to extract key information. Let the key information set extracted from the course outline be K C ={k c1 ,k c2 ,…,k cq}, the key information set extracted from the experimental report is K E ={k e1 ,k e2 ,…,k er}, the key information set extracted from the internship records is K I ={k i1 ,k i2 ,…,k is}, set the set of engineering education standard requirements to be S = {s1,s2,…,s t}, compare the extracted key information with the standard requirements, and set the similarity function of the comparison as sim(k i ,s j ), used to calculate the key information k i Comply with standard requirements j According to the comparison results, they are divided into direct corresponding items and potential related items. Let the set of direct corresponding items be D = {d1, d2, ..., d u}, the set of potential associated items is P = {p1, p2, ..., p v}, evaluate the accuracy and reliability of the comparison results, Where |D correct | and |P correct | are the numbers of elements correctly classified into the direct correspondence set and the potential association set, respectively, and |D| and |P| are the total numbers of elements in these two sets, respectively.

[0016] Furthermore, the teaching objectives and ability development assessment collects multi-source data such as course syllabus, teaching materials, student homework, test scores and internship reports, organizes and annotates the teaching objectives and ability development objectives corresponding to each course, cleans and preprocesses the collected data, removes noise and missing values, and the preprocessed course content set is C′={c′1,c′2,…,c′ m}, the teaching target set is T′={t′1,t′2,…,t′ n}, the ability training target set is A′={a′1,a′2,…,a′ p}, the set of students’ learning performance is S′={s′1,s′2,…,s′ q}.

[0017] Furthermore, the teaching objectives and ability training evaluation extracts valuable features from the preprocessed data, assuming that the features extracted from the course content, the feature vectors extracted from the teaching objectives, and the feature vectors extracted from the ability training objectives are used to evaluate the trained model using the test data. The evaluation indicators may include the mean square error Where N is the number of test samples, y i is the true value, To predict the value, the new course data is input into the trained model to obtain the evaluation results of its potential contribution to the improvement of students' comprehensive abilities.

[0018] Furthermore, the visual report generation organizes and classifies the results of the analysis, classifies the compliance data, problem point data and improvement suggestion data respectively, designs the overall structure of the evaluation report, including the cover, directory, introduction, main content and conclusion, calculates the compliance degree of each standard, and the compliance degree is expressed as a percentage P. Display the degree of compliance in the form of charts and clearly present the compliance status of different aspects. Sort out the problem points found in the analysis process, and give a detailed description of each problem point, including the manifestation of the problem and the scope of impact. For each problem point, put forward specific and feasible improvement suggestions, prioritize the improvement suggestions, layout the sorted content according to the determined framework, use clear and easy-to-read fonts and formats, select color schemes, highlight key points and key information, use charts, graphics, and icon elements to enhance the intuitiveness of the report, check the data accuracy, logical coherence and clarity of language expression in the report, and generate the final visual evaluation report in PDF and Word format.

[0019] Furthermore, the continuous optimization and feedback mechanism sets a clear feedback entrance on the system interface, provides multiple feedback methods, encourages users to actively provide feedback through system prompts and reward mechanisms, regularly sends feedback invitations to users, understands their satisfaction with system functions and evaluation results and improvement suggestions, collects user feedback data, classifies and organizes the feedback data, analyzes user feedback data, identifies common problems and individual cases, evaluates the impact of feedback on algorithm models and system performance, determines priorities and solutions, uses evaluation indicators to evaluate the current algorithm model, performs model diagnosis on evaluation accuracy issues mentioned in user feedback, identifies potential causes and bottlenecks, adjusts model parameters, optimizes algorithm structure or introduces new features based on the diagnosis results, and deploys the optimized model to the production environment.

[0020] Furthermore, the continuous optimization and feedback mechanism continuously collects new teaching materials and student performance data, enriches data sources, preprocesses and labels the collected data, provides high-quality data sets for model training, sets periodic retraining plans, improves the adaptability and generalization ability of the model, monitors the operation of the system and evaluation results in real time, collects system operation logs and performance indicator data, optimizes system resource allocation, improves algorithm execution efficiency or improves data processing algorithms based on monitoring results and performance analysis, communicates with users regularly, uses user feedback as input for a new round of optimization, continuously iterates and optimizes algorithm models and system functions, and forms a closed-loop feedback mechanism.

[0021] Compared with the existing technology, an engineering education certification auxiliary system has the following beneficial effects:

[0022] 1. The engineering education certification auxiliary system of the present invention achieves comprehensive coverage and in-depth analysis of engineering education standards by integrating the global standard integration library and the automated analysis engine. The built-in automated analysis engine of the system can automatically analyze the various requirements of global and regional engineering education standards, including curriculum system, experimental projects, internship experience, teaching objectives and ability training objectives, which greatly improves the comprehensiveness of the evaluation. At the same time, NLP technology and machine learning algorithms are used for in-depth content comparison and teaching objectives and ability training evaluation to ensure the accuracy of the evaluation results. The system can not only identify the direct correspondence between course content and standards, but also deeply understand the teaching objectives and ability training objectives behind the course, and evaluate its potential contribution to the improvement of students' comprehensive abilities, thereby providing users with more accurate and valuable evaluation results.

[0023] 2. Traditional engineering education certification systems often stay at the comparison of surface content, and it is difficult to evaluate the actual contribution of the education process to students' comprehensive abilities. This system uses machine learning algorithms to not only identify the direct correspondence between course content and standards, but also deeply understand the teaching objectives and ability training objectives behind the courses, and evaluate their potential contribution to improving students' comprehensive abilities. This function makes the evaluation results more comprehensive and in-depth, which helps educational institutions better understand teaching effectiveness, optimize teaching content and methods, and further improve the quality of education. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 An operation flow chart of an engineering education certification auxiliary system. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] Embodiment 1

[0028] Obtain electronic or scanned copies of course outlines, lab reports, and internship records from educational institutions to ensure that the collected data covers all relevant courses and teaching activities, remove noise from the data, such as irrelevant text, repeated content, and incorrect formats, and convert teaching materials in different formats into a format that the system can process. Segment the text, process punctuation, and unify the text format to prepare for subsequent NLP processing.

[0029] Use NLP tools to segment the preprocessed text and tag each word with parts of speech to facilitate subsequent extraction of key information. According to the requirements of engineering education standards, design key information extraction rules, and use NLP technology to extract key information such as course objectives, experimental projects, and internship experiences from the text. The extracted key information is stored in a structured form to facilitate subsequent comparison and analysis.

[0030] The engineering education standard data in the global standard integrated library is imported into the system to ensure the accuracy and completeness of the data. A similarity function is designed to calculate the similarity between the extracted key information and the standard requirements. According to the similarity calculation results, the comparison results are divided into direct corresponding items and potential related items. Direct corresponding items indicate that the content in the teaching materials is completely consistent with the standard requirements, and potential related items indicate that the content in the teaching materials is related to the standard requirements, but further analysis and confirmation are required.

[0031] Use the accuracy score indicator to evaluate the accuracy of the comparison results, accuracy (Precision): Among them, TP (True Positive) represents true positives, that is, the number of positive examples correctly judged; FP represents false positives, that is, the number of positive examples wrongly judged. It analyzes the possible sources of errors in the comparison process and proposes improvement measures. The comparison results are visualized in the form of charts and tables, including a detailed list of directly corresponding items and potential related items, and similarity scores. It provides problem points and improvement suggestions to help educational institutions quickly locate problems and take measures. It sets a user feedback portal to collect users' opinions and suggestions on the comparison results, and continuously optimizes the comparison algorithm and display method based on user feedback.

[0032] Embodiment 2

[0033] The engineering education standard data in the global standard integrated library is imported into the automated analysis engine, and the imported data is cleaned and formatted. The cleaned and formatted data set is D′={d′1,d′2,…,d′ n}, including removing redundant information, correcting erroneous data, and unifying data formats to ensure data accuracy and consistency.

[0034] Design and implement modules specifically used to parse the requirements of engineering education standards. These modules should have strong capabilities to identify, classify and extract key information. Develop corresponding parsing algorithms and rule sets for key areas such as curriculum system, experimental projects, internship experience, teaching objectives and ability training objectives. These algorithms and rule sets should be able to accurately identify and extract the core information and key indicators of each field.

[0035] After the automated analysis engine is started, it will traverse the imported standard data according to the preset parsing rules and algorithms. For each standard or requirement, the engine will identify the field to which it belongs, and apply the corresponding parsing algorithm for in-depth analysis to extract key information. The parsed key information will be stored in the system's internal data structure, including databases and memory data structures, for subsequent data processing and analysis. Based on the parsed key information, a comprehensive and structured engineering education standard analysis model will be constructed. The model should be able to clearly display the relationship between the various standards and provide strong support for subsequent evaluation work.

[0036] The analysis results are output in the form of visual reports, data tables, and charts. These output forms should be intuitive and easy to understand, and can help users quickly understand and evaluate the compliance and quality of engineering education standards. The automated analysis engine is performance tested to evaluate its key indicators of analysis speed, accuracy, and stability. Through performance testing, problems and deficiencies in the engine can be discovered, providing a basis for subsequent optimization work. According to the test results and user feedback, the automated analysis engine is iteratively optimized. The optimization work can include improving the analysis algorithm, optimizing the data structure, and improving the system performance. Through continuous optimization, the analysis efficiency and user experience can be significantly improved.

[0037] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An engineering education certification auxiliary system, characterized in that: The system includes a global standard integrated library, an automated analysis engine, in-depth content comparison and teaching objectives and ability development assessment, visual report generation, and continuous optimization and feedback mechanisms: The global standard integrated library: The system has established an integrated library that comprehensively covers global and regional engineering education standards including ABET and EUR-ACE; The automated analysis engine: A built-in efficient automated analysis engine can automatically analyze various requirements of engineering education standards, including but not limited to curriculum system, experimental projects, internship experience, teaching objectives and ability training objectives; The in-depth content comparison: using NLP technology to deeply analyze the course outlines, lab reports, and internship record teaching materials provided by educational institutions, identify and extract key information, accurately compare with standard requirements, and identify directly corresponding and potentially related items; The teaching objectives and ability development evaluation: Through machine learning algorithms, the system can not only identify the direct correspondence between course content and standards, but also deeply understand the teaching objectives and ability development objectives behind the course, and evaluate its potential contribution to improving students' comprehensive abilities; Visual report generation: Based on the analysis results, the system automatically generates a detailed and intuitive evaluation report, including compliance analysis, problem points and improvement suggestions; The continuous optimization and feedback mechanism: The system supports user feedback and data accumulation, and improves the accuracy and efficiency of evaluation by continuously learning and optimizing algorithm models.

2. According to claim 1, an engineering education certification auxiliary system is characterized in that: The global standard integrated library explicitly includes global and regional engineering education standards that need to be included in the integrated library, including but not limited to ABET and EUR-ACE. The concept of set is used to represent it. Suppose the standard set is S, the ABET standard is S1, and the EUR-ACE standard is S2, then S={S1,S2}. For each selected standard, comprehensive data collection is carried out, including standard documents, specifications, and requirements. The collected data is sorted and classified, and a database structure is designed to store the sorted data. The sorted and classified data is entered into the database, the accuracy of the entered data is calculated, the entered data is verified and optimized, the established integrated library is tested and evaluated, and the integrated library is regularly maintained and updated.

3. According to claim 1, an engineering education certification auxiliary system is characterized in that: The automated analysis engine imports the engineering education standard data in the global standard integration library into the automated analysis engine, cleans and formats the data, designs and implements a module specifically used to parse the engineering education standard requirements. These modules should have the ability to identify, classify and extract key information. For key areas such as curriculum system, experimental projects, internship experience, teaching objectives and ability training objectives, after the automated analysis engine is started, it traverses the imported standard data according to preset parsing rules and algorithms. For each standard or requirement, the engine will identify the field to which it belongs, extract key information, and store this information in the system's internal data structure. It will integrate the parsed requirements data, establish the relationship between them, and build a comprehensive and structured engineering education standard analysis model.

4. According to claim 3, an engineering education certification auxiliary system is characterized in that: The automated analysis engine outputs the analysis results of the automated analysis engine in the form of visual reports, data tables, and charts according to user needs. The report should clearly display the specific requirements of each standard, key information points, and the relationship between them, to help users quickly understand and evaluate the compliance and quality of engineering education standards. The automated analysis engine is performance tested to evaluate its analysis speed, accuracy, and stability indicators. Based on the test results and user feedback, the engine is iteratively optimized to improve analysis efficiency, accuracy, and user experience, and the analysis engine is upgraded and expanded in a timely manner.

5. According to claim 1, the engineering education certification auxiliary system is characterized in that: The deep content comparison obtains electronic or scanned copies of course outlines, laboratory reports, and internship records from educational institutions, performs manual review or data cleaning when necessary, cleans and preprocesses the collected data, performs word segmentation according to language characteristics, processes punctuation, unifies the text format, and uses NLP technology to extract key information. Let the key information set extracted from the course outline be K C ={k c1 ,k c2 ,…,k cq }, the key information set extracted from the experimental report is K E ={k e1 ,k e2 ,…,k er }, the key information set extracted from the internship records is K I ={k i1 ,k i2 ,…,k is }, set the set of engineering education standard requirements to be S = {s1,s2,…,s t }, compare the extracted key information with the standard requirements, and set the similarity function of the comparison as sim(k i ,s j ), used to calculate the key information k i Comply with standard requirements j According to the comparison results, they are divided into direct corresponding items and potential related items. Let the set of direct corresponding items be D = {d1, d2, ..., d u }, the set of potential associated items is P = {p1, p2, ..., p v }, evaluate the accuracy and reliability of the comparison results, Where |D correct | and |P correct | are the numbers of elements correctly classified into the direct correspondence set and the potential association set, respectively, and |D| and |P| are the total numbers of elements in these two sets, respectively.

6. According to claim 1, an engineering education certification auxiliary system is characterized in that: The teaching objectives and ability training evaluation collects multi-source data such as course syllabus, teaching materials, student homework, test scores and internship reports, organizes and marks the teaching objectives and ability training objectives corresponding to each course, cleans and preprocesses the collected data, removes noise and missing values, and the preprocessed course content set is C′={c1′,c2′,…,c m ′}, the teaching target set is T′={t1′,t2′,…,t n ′}, the ability training target set is A′={a1′,a2′,…,a p ′}, the set of students’ learning performance is S′={s1′,s2′,…,s′ q }.

7. According to claim 6, an engineering education certification auxiliary system is characterized in that: The teaching objectives and ability training evaluation extracts valuable features from the preprocessed data, assuming that the features extracted from the course content, the feature vectors extracted from the teaching objectives, and the feature vectors extracted from the ability training objectives are used to evaluate the trained model using the test data. The evaluation indicators may include the mean square error Where N is the number of test samples, y i is the true value, To predict the value, the new course data is input into the trained model to obtain the evaluation results of its potential contribution to the improvement of students' comprehensive abilities.

8. According to claim 1, an engineering education certification auxiliary system is characterized in that: The visual report generation organizes and classifies the results of the analysis, classifies the compliance data, problem point data and improvement suggestion data respectively, designs the overall structure of the evaluation report, including the cover, directory, introduction, main content and conclusion, calculates the compliance degree of each standard, and the compliance degree is expressed as a percentage P. Display the degree of compliance in the form of charts and clearly present the compliance status of different aspects. Sort out the problem points found in the analysis process, and give a detailed description of each problem point, including the manifestation of the problem and the scope of impact. For each problem point, put forward specific and feasible improvement suggestions, prioritize the improvement suggestions, layout the sorted content according to the determined framework, use clear and easy-to-read fonts and formats, select color schemes, highlight key points and key information, use charts, graphics, and icon elements to enhance the intuitiveness of the report, check the data accuracy, logical coherence and clarity of language expression in the report, and generate the final visual evaluation report in PDF and Word format.

9. According to claim 1, an engineering education certification auxiliary system is characterized in that: The continuous optimization and feedback mechanism sets a clear feedback entrance on the system interface, provides multiple feedback methods, encourages users to actively provide feedback through system prompts and reward mechanisms, regularly sends feedback invitations to users, understands their satisfaction with system functions and evaluation results and improvement suggestions, collects user feedback data, classifies and organizes the feedback data, analyzes user feedback data, identifies common problems and individual cases, evaluates the impact of feedback on algorithm models and system performance, determines priorities and solutions, uses evaluation indicators to evaluate the current algorithm model, performs model diagnosis for evaluation accuracy issues mentioned in user feedback, identifies potential causes and bottlenecks, adjusts model parameters, optimizes algorithm structure or introduces new features based on the diagnosis results, and deploys the optimized model to the production environment.

10. The engineering education certification auxiliary system according to claim 9, characterized in that: The continuous optimization and feedback mechanism continuously collects new teaching materials and student performance data, enriches data sources, preprocesses and labels the collected data, provides high-quality data sets for model training, sets periodic retraining plans, improves the adaptability and generalization ability of the model, monitors the operation of the system and evaluation results in real time, collects system operation logs and performance indicator data, optimizes system resource allocation, improves algorithm execution efficiency or improves data processing algorithms based on monitoring results and performance analysis, communicates with users regularly, uses user feedback as input for a new round of optimization, continuously iterates and optimizes algorithm models and system functions, and forms a closed-loop feedback mechanism.

Images