Desktop teaching examination system and method based on multi-layer industrial network
Through the desktop teaching assessment method based on multi-layer industrial network, students' theoretical and practical data are analyzed, quality index is generated, and the teaching methods are used to identify and adjust the teaching methods. The problem of disconnection between theory and practice is solved, and the teaching effect is improved. Students' comprehensive abilities.
Patent Information
- Application Number
- CN202411100740.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-12
- Publication Date
- 2024-12-03
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In the traditional teaching model, it is difficult to combine the theoretical knowledge and practical operation ability of students, which leads to a disconnection between theory and practice, and it is difficult for the existing teaching management system to comprehensively evaluate and intervene, affecting the quality of education.
Using a desktop teaching assessment method based on multi-layer industrial network, by collecting and analyzing students' theoretical test data and practical operation test data, generating theoretical knowledge mastery quality index and practical operation ability quality index, using machine learning models for comprehensive analysis, and identifying Students with balanced theoretical and practical abilities may have students with potential disconnection, and their teaching adjustments will be made to them.
It has achieved a comprehensive assessment of students' comprehensive learning effects, accurately identified weak links of theory and practice, helped teachers to make targeted teaching adjustments, improve teaching effectiveness, promote the organic combination of theory and practice, and improve students' comprehensive abilities.
Smart Images

Figure CN119067491A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of educational technology, and more specifically, to a desktop teaching and assessment system and method based on a multi-layer industrial network. Background Art
[0002] In the modern education system, theoretical knowledge and practical operation ability are two important aspects of cultivating high-quality talents. However, the traditional teaching model often has the phenomenon of disconnection between theory and practice. The theoretical knowledge learned by students in class cannot be effectively applied to actual operations, or the practical operation ability is not enough to support the understanding and application of theoretical knowledge. This disconnection not only affects the development of students' comprehensive abilities, but also limits the improvement of education quality.
[0003] In recent years, with the development of educational informatization, teaching management systems have gradually introduced various data analysis technologies to help teachers and education administrators better understand students' learning situation. However, most of the existing teaching management systems and data analysis tools focus on one aspect of analysis, lack a comprehensive evaluation of the comprehensive ability of theory and practice, and are difficult to accurately identify and intervene in students who are out of touch with theory and practice. Therefore, there is an urgent need for a desktop teaching assessment method and system based on a multi-layer industrial network to comprehensively evaluate students' theoretical knowledge mastery quality index and practical operation ability quality index, and then judge the teaching adjustment method to improve the teaching effect. Summary of the invention
[0004] To achieve the above object, the present invention provides the following technical solutions:
[0005] A desktop teaching and assessment method based on a multi-layer industrial network includes the following steps:
[0006] Collect theoretical test data and practical test data of students in current teaching and practical operation and conduct preliminary analysis and operation, and judge whether there is a hidden danger of disconnection between theory and practice based on the preliminary analysis results;
[0007] If there is a hidden danger of disconnection between theory and practice, a quantitative analysis will be conducted on each student to generate a theoretical knowledge mastery quality index and a practical operation ability quality index;
[0008] Based on the theoretical knowledge mastery quality index and the practical operation ability quality index, a comprehensive analysis is performed through the pre-trained machine learning model to obtain the comprehensive learning effect coefficient;
[0009] Based on the comprehensive learning effect coefficient, each student is divided into students with balanced theoretical and practical abilities or students with potential disconnection;
[0010] Infer how instructional adjustments might be made for students classified as at risk of disconnection.
[0011] In a preferred embodiment, within a fixed time window, the theoretical test data and practical operation test data of each student are collected from the teaching management system or the teacher, and the scores of each student in all theoretical type tests within the fixed time window are collected. The score in the theoretical type test refers to the percentage value calculated according to the ratio of each score to the total score. Then, the scores of all theoretical type tests within the fixed time window are added and summed to obtain the target student's comprehensive theoretical test score.
[0012] The logic for obtaining the actual operation test scores is as follows: collect the scores of each student in all operation type tests within the fixed time window. The score in the operation type test refers to the percentage value calculated according to the ratio of each score to the total score. Then add up the scores of all operation type tests within the fixed time window to obtain the comprehensive score of the actual operation test for the target student.
[0013] In a preferred embodiment, the preliminary analysis operation refers to: obtaining each student's comprehensive theoretical test score and practical operation test score, marking the theoretical test comprehensive score as Ti, marking the practical operation test comprehensive score as Pi, i is the student number, calculating the score difference value Di between each student's theoretical test comprehensive score Ti and the practical operation test comprehensive score Pi, the score difference value Di is the difference between the theoretical test comprehensive score Ti and the practical operation test comprehensive score Pi, and then based on the score difference value Di, calculating the score difference average and score difference standard deviation of all students, comparing the score difference standard deviation with the preset threshold parameter, if the score difference standard deviation is less than or equal to the preset threshold parameter, a normal signal is generated, if the score difference standard deviation is not less than or equal to the preset threshold parameter, an abnormal signal is generated, and when the abnormal signal is generated, it indicates that there is a hidden danger of disconnection between theory and practice.
[0014] In a preferred embodiment, the logic for obtaining the theoretical knowledge mastery quality index is as follows:
[0015] In a fixed time window, all theoretical test data of the target students are obtained, the theoretical test data are standardized, the time decay factor and the difficulty coefficient are introduced, and each test score is weighted. The calculation formula is: Fi = wi*ai*di*fi; fi represents the standardized theoretical test data of theoretical test number i, wi represents the preset proportional coefficient of theoretical test number i, ai represents the time decay factor of theoretical test number i, di represents the difficulty coefficient of theoretical test number i, and its value range is between (0,1]. The higher the difficulty, the lower the difficulty coefficient. Fi represents the weighted standardized score of theoretical test number i. All theoretical weighted standardized scores are summed to obtain the comprehensive theoretical standardized score of the target student. Finally, the theoretical knowledge mastery quality index is calculated. The calculation formula is:
[0016] T total represents the comprehensive theoretical standardized score of the target student, QT represents the quality index of the target student's theoretical knowledge mastery, and W total Obtained through the following calculation: n is the total number of all theoretical test data.
[0017] The time decay factor acquisition logic is: The calculation of the time decay factor is based on the exponential decay model, and its formula is: ai = e λti ; ti represents the time length from the test of theoretical test number i to the current time, and the value of λ is determined based on the pre-trained and fitted time decay model.
[0018] In a preferred embodiment, the logic for obtaining the difficulty coefficient is: obtain the maximum value of the weighted standardized scores corresponding to all theoretical test data of the target student, and divide the weighted standardized score Fi of theoretical test number i by the maximum value to obtain a ratio value as the difficulty coefficient of the target student in theoretical test number i.
[0019] In a preferred embodiment, the logic for obtaining the practical operation capability quality index is:
[0020] In a fixed time window, all practical operation test data of the target students are obtained, the practical operation test data are standardized, the adjustment factor is introduced, and each test score is weighted. The calculation formula is: Zi = ki*Ri*zi; zi represents the standardized practical operation test data of practical operation test i, ki represents the preset proportional coefficient of practical operation test i, Ri is the adjustment factor of practical operation test i, Zi represents the practical weighted standardized score of practical operation test i, and then all the practical weighted standardized scores Zi are summed to obtain the comprehensive practical standardized score P of the target student. total, and finally calculate the practical operation ability quality index of the target student: μ total is the average of all practice weighted standardized scores Zi, σ total is the standard deviation of all practice weighted standardized scores Zi, and PT is the quality index of the target student's practical operation ability;
[0021] The logic for obtaining the adjustment factor is: rank i is the rank of the target student in all students in practical operation test i, N is the total number of all students, and Ri is the adjustment factor of the target student in practical operation test i.
[0022] In a preferred embodiment, the partitioning logic is:
[0023] Obtain the comprehensive learning effect coefficient of the target students, and preset a comprehensive learning effect reference value. If the comprehensive learning effect coefficient of the target students is greater than or equal to the preset comprehensive learning effect reference value, they will be classified as students with balanced theoretical and practical abilities; if the comprehensive learning effect coefficient of the target students is less than the preset comprehensive learning effect reference value, they will be classified as students with hidden dangers of disconnection.
[0024] In a preferred embodiment, for students classified as having a potential risk of disconnection, inferring the teaching adjustment method for them refers to:
[0025] Define the input variables as the theoretical knowledge mastery quality index and the practical operation ability quality index, define the output variables as the teaching adjustment method, fuzzify the input variables and convert the values of the input variables into fuzzy sets, fuzzify the output variables and convert the values of the output variables into fuzzy sets, formulate fuzzy rules, describe the teaching adjustment needs under different data type combinations, infer the fuzzified input variables through fuzzy rules, and determine the teaching adjustment method that needs to be made.
[0026] In a preferred embodiment, a desktop teaching and assessment system based on a multi-layer industrial network includes a training platform building module, a preliminary judgment module, a quantitative analysis module, a comprehensive analysis module, a division module, and a teaching adjustment module;
[0027] The training platform building module is used to build a network training platform, which is used to provide students with a network environment for theoretical teaching and practical assessment;
[0028] The preliminary judgment module is used to collect theoretical test data and practical operation test data of students in current teaching and practical operation based on the network training platform built by the training platform building module, and to perform preliminary analysis and operation, and to judge whether there is a hidden danger of disconnection between theory and practice based on the preliminary analysis results;
[0029] The quantitative analysis module is used to conduct quantitative analysis on each student when there is a hidden danger of disconnection between theory and practice, and generate a theoretical knowledge mastery quality index and a practical operation ability quality index;
[0030] The comprehensive analysis module is used to perform comprehensive analysis through the pre-trained machine learning model to obtain the comprehensive learning effect coefficient;
[0031] The classification module is used to classify each student into students with balanced theoretical and practical abilities or students with potential disconnection based on the comprehensive learning effect coefficient;
[0032] The teaching adjustment module is used to infer the teaching adjustment methods for students who are classified as having the risk of disconnection.
[0033] Technical effects and advantages of the present invention:
[0034] The present invention comprehensively evaluates students' comprehensive learning effects by analyzing the theoretical knowledge mastery quality index (QT) and the practical operation ability quality index (PT), overcoming the limitation of the single evaluation method in traditional teaching management. This comprehensive evaluation method can accurately identify students' weak links in theoretical knowledge and practical operation, and help teachers make targeted teaching adjustments.
[0035] The present invention uses data analysis and machine learning technology to scientifically determine teaching adjustment methods, including theoretical adjustment, practical adjustment and personalized adjustment, to help teachers optimize teaching strategies and improve teaching effects. According to students' QT and PT, the fuzzy logic model is used to determine the teaching adjustment needs, and personalized teaching support and intervention measures are provided for each student. This personalized teaching method can meet the learning needs of different students, improve students' learning interest and enthusiasm, and promote their all-round development.
[0036] By comprehensively analyzing students' learning data and rationally allocating teaching resources, it is ensured that each student can receive appropriate attention and support. Teachers can formulate reasonable teaching plans and resource allocation strategies based on the data and analysis results provided by the present invention to improve the utilization rate of teaching resources. The present invention analyzes QT and PT to find out the disconnection between students' theory and practice, and makes targeted adjustments to promote the organic combination of theoretical knowledge and practical skills. This training model helps students master theoretical knowledge in learning while improving their practical operation ability and enhancing their practical application ability.
[0037] The present invention not only focuses on students' academic performance, but also focuses on cultivating students' comprehensive qualities, and comprehensively improves students' comprehensive abilities through balanced teaching adjustments between theory and practice. This all-round training method helps students to perform well in their future studies, work and life, and have stronger competitiveness. The present invention provides scientific decision-making support for education managers through data analysis and comprehensive evaluation, helping them to formulate and optimize education policies and teaching strategies. Education managers can use the data and analysis results provided by the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;
[0039] Figure 1 The schematic diagram is a schematic diagram of a desktop teaching and assessment method based on a multi-layer industrial network in the present invention.
[0040] Figure 2 The schematic diagram of a desktop teaching and assessment system based on a multi-layer industrial network in the present invention. DETAILED DESCRIPTION
[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. 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.
[0042] Reference Figure 1 - Figure 2 The following embodiments are obtained:
[0043] Example 1: The disconnect between teaching theory and practice will lead to students' lack of necessary hands-on ability and problem-solving experience in actual operations. Although students may have mastered a wealth of theoretical knowledge, they often cannot effectively apply what they have learned when faced with practical problems, which affects work efficiency and quality. In addition, the difficulties and frustrations encountered by students in the actual working environment will increase, which may lead to a decrease in students' confidence in learning and work, affecting career development and career satisfaction. This disconnect will also make it difficult for educational institutions to achieve the goal of cultivating high-quality skilled talents, thereby affecting their reputation and competitiveness. When recruiting, companies will also be more inclined to look for talents with rich practical experience rather than just graduates with good academic performance. This not only increases the training costs of enterprises, but also exacerbates the contradictions between the education and employment markets, hindering the sustainable development of the economy and technology. Therefore, a desktop teaching assessment method based on a multi-layer industrial network is proposed, comprising the following steps: collecting theoretical test data and practical operation test data of students in current teaching and actual operation and conducting preliminary analysis operations, judging whether there is a hidden danger of disconnection between theory and practice based on the preliminary analysis results; if there is a hidden danger of disconnection between theory and practice, conducting quantitative analysis on each student to generate a theoretical knowledge mastery quality index and a practical operation ability quality index; based on the theoretical knowledge mastery quality index and the practical operation ability quality index, conducting a comprehensive analysis through a pre-trained machine learning model to obtain a comprehensive learning effect coefficient; based on the comprehensive learning effect coefficient, dividing each student into a student with balanced theoretical and practical ability or a student with a hidden danger of disconnection; and inferring the teaching adjustment method for students classified as having a hidden danger of disconnection.
[0044] In a fixed time window, such as a semester or a month, collect each student's theoretical test data and practical test data from the teaching management system or teachers, and collect each student's scores in all theoretical tests in the fixed time window. Theoretical tests include classroom tests, midterm exams, final exams, etc. The scores in theoretical tests refer to the percentage value calculated by the ratio of each score to the total score. Then add up the scores of all theoretical tests in the fixed time window to obtain the target student's comprehensive theoretical test score.
[0045] The logic for obtaining the actual operation test scores is: within a fixed time window, such as a semester or a month, collect the scores of each student in all operation type tests within the fixed time window. Operation type tests include experiments, practical training, projects, etc. The scores in the operation type tests refer to the percentage value calculated according to the ratio of each score to the total score. Then, the scores of all operation type tests in the fixed time window are added together to obtain the comprehensive scores of the target students' actual operation tests.
[0046] The preliminary analysis operation refers to: obtaining the comprehensive scores of the theoretical test and the practical operation test for each student, marking the comprehensive scores of the theoretical test as Ti, marking the comprehensive scores of the practical operation test as Pi, i is the student number, calculating the score difference value Di between the comprehensive scores of the theoretical test Ti and the comprehensive scores of the practical operation test Pi for each student, the score difference value Di is the difference between the comprehensive scores of the theoretical test Ti and the comprehensive scores of the practical operation test Pi, Di = Ti-Pi, and then based on the score difference value Di, calculating the average score difference and the standard deviation of the score difference of all students, the calculation formula of the average score and the standard deviation will not be repeated here, comparing the standard deviation of the score difference with the preset threshold parameter, if the standard deviation of the score difference is less than or equal to the preset threshold parameter, a normal signal is generated, if the standard deviation of the score difference is not less than or equal to the preset threshold parameter, an abnormal signal is generated, and when the abnormal signal is generated, it indicates that there is a hidden danger of disconnection between theory and practice. By calculating and analyzing the score difference value and standard deviation, educational administrators can identify whether there is a significant difference between theoretical teaching and practical operation teaching, thereby discovering the weak links in teaching. The generation of abnormal signals indicates that educators may need to make adjustments in teaching methods or content to better coordinate theoretical and practical teaching and improve students' comprehensive abilities. This method provides a way to quantitatively evaluate the overall performance of the entire class of students, which helps to better understand the learning situation and ability development of the entire class. Through continuous monitoring and adjustment, the quality of education can be effectively improved, and high-quality talents with balanced development of theoretical and practical abilities can be cultivated to meet the needs of society and industry.
[0047] The logic for obtaining the theoretical knowledge mastery quality index is as follows:
[0048] In a fixed time window, all theoretical test data of the target students are obtained and the theoretical test data are standardized. Standardization can eliminate the dimensional differences between different tests and make the data more comparable. Z-Score standardization is the most common standardization method. It converts the data into a standard normal distribution with a mean of 0 and a standard deviation of 1. Min-Max standardization eliminates dimensional differences by linearly converting the data to a specified range (usually [0,1]). Mean standardization scales the data to the range of [-1,1]. Percentage standardization converts the data into percentage values for easy comparison and analysis. The standardization processing method used is not specified, and it can also be other processing methods to achieve the purpose of eliminating the dimensional differences between different tests. The subsequent data standardization processing is not repeated. Then the time attenuation factor and difficulty coefficient are introduced to weight the test scores of each test. The calculation formula is: Fi = wi*ai*di*fi; fi represents the theoretical test number i after standardization. Test data, wi represents the preset proportional coefficient of theoretical test number i, reflecting the importance of each test, and setting weights according to specific circumstances, ai represents the time attenuation factor of theoretical test number i, which is used to adjust the time impact of the score. Earlier tests have less impact on the current quality index, di represents the difficulty coefficient of theoretical test number i, and its value range is between (0,1]. The higher the difficulty, the lower the difficulty coefficient, ensuring that tests of different difficulty levels have a reasonable impact on the total score, Fi represents the weighted standardized score of theoretical test number i, and all theoretical weighted standardized scores are summed to obtain the comprehensive theoretical standardized score of the target student, and finally calculate the theoretical knowledge mastery quality index. The calculation formula is:
[0049] T total represents the comprehensive theoretical standardized score of the target student, reflecting the overall performance of the student in all theoretical tests, QT represents the quality index of the target student's theoretical knowledge mastery, W total Obtained through the following calculation: n is the total number of all theoretical test data. The larger the theoretical knowledge mastery quality index QT is, the better the student's theoretical test score within a fixed time window is and the more solid the knowledge mastery is. It comprehensively considers the test score, time influence and test difficulty factors, and is a comprehensive evaluation of the student's theoretical learning level.
[0050] The time decay factor acquisition logic is: The calculation of the time decay factor is based on the exponential decay model, and its formula is: ai = e λti; ti represents the time length from the test of theoretical test number i to the current time, the time decay factor ai reflects the change in the impact of test scores over time, and the value of λ is determined based on the pre-trained and fitted time decay model; The following is a description of the specific fitting steps: Step 1: Collect historical data, collect a large number of students' historical theoretical test data from the teaching management system, the data includes each student's test scores at different time points and the time length t of these tests (the time length from the current time). Step 2: Data preprocessing, data cleaning: remove missing values and outliers to ensure the quality and reliability of the data. Standardization: Standardize the test scores to eliminate the dimensional differences between different tests. Step 3: Build a model and set the model form: Assume that the model form of the test score decays over time is: Sti = S0*e λti ; Sti is the test score at time ti, S0 is the initial test score, λ is the decay coefficient to be fitted, historical data is used to fit the decay coefficient λ through statistical methods such as least squares method, the goal is to find a λ that minimizes the error between the test score predicted by the model and the actual test score, define the loss function L, such as mean square error, use gradient descent or other optimization algorithms, minimize the loss function L(λ), find the optimal λ, use an independent validation set to verify the fitted model, and evaluate the model's predictive ability to meet the preset standard, then deploy and use it. The time decay factor can dynamically adjust the student's test score, so that the impact of the earlier test score on the current theoretical knowledge mastery quality index gradually decreases, and more accurately reflects the student's current learning status. By pre-training the fitted time decay model, the rationality and scientificity of the time decay factor can be ensured, and the accuracy and reliability of the evaluation results can be improved. Based on the analysis results of the time decay factor, personalized teaching support and improvement suggestions can be provided to students to help them better master theoretical knowledge.
[0051] The logic for obtaining the difficulty coefficient is: obtain the maximum value of the weighted standardized scores corresponding to all theoretical test data of the target student, and divide the weighted standardized score Fi of theoretical test number i by the maximum value to obtain the ratio value as the difficulty coefficient of the target student in theoretical test number i. By calculating the difficulty coefficient, the impact of tests of different difficulty levels can be adjusted to ensure the fairness and rationality of grade comparison. The higher the difficulty of the test, the lower its difficulty coefficient, so that the impact on the total score is more reasonable. The introduction of the difficulty coefficient enables the theoretical knowledge mastery quality index to more accurately reflect the students' performance in tests of different difficulty levels and comprehensively evaluate their theoretical knowledge mastery.
[0052] The logic of obtaining the practical operation ability quality index is as follows: within a fixed time window, obtain all the practical operation test data of the target students, standardize the practical operation test data, introduce adjustment factors, and weight each test score. The calculation formula is: Zi = ki*Ri*zi; zi represents the standardized practical operation test data of practical operation test i, ki represents the preset proportional coefficient of practical operation test i, Ri is the adjustment factor of practical operation test i, Zi represents the practical weighted standardized score of practical operation test i, and then sum up all the practical weighted standardized scores Zi to obtain the comprehensive practical standardized score P of the target student. total , and finally calculate the practical operation ability quality index of the target student: μ total is the average of all practice weighted standardized scores Zi, σ total Zi is the standard deviation of all the practice weighted standardized scores, which serves as the basis for calculating the practical operation ability quality index. PT is the practical operation ability quality index of the target student, which reflects the performance of the target student in practical operation relative to the performance of the overall students. The larger the practical operation ability quality index PT is, the better the student performs in the practical operation test, and the stronger his operation ability is compared with other students. A high index means that students can better apply theoretical knowledge to practical operations and have a stronger ability to solve practical problems. Students with a larger index usually perform stably in multiple operation tests, have excellent comprehensive abilities, and have high hands-on ability and practical skills.
[0053] The logic for obtaining the adjustment factor is: rank i is the ranking of the target student in the practical operation test i among all students, N is the total number of all students, Ri is the adjustment factor of the target student in the practical operation test i, and the adjustment factor is based on the ranking of the student in the practical operation test to ensure that the impact of different tests is reasonable.
[0054] Based on the theoretical knowledge mastery quality index and the practical operation ability quality index, a comprehensive analysis is performed through a pre-trained machine learning model to obtain a comprehensive learning effect coefficient. The machine learning model is not specifically limited here. Any model that can realize the comprehensive analysis of the theoretical knowledge mastery quality index and the practical operation ability quality index to generate a comprehensive learning effect coefficient is acceptable. In order to realize the technical solution of the present invention, the present invention provides a specific implementation method: CSE = β0 + β1*QT + β2*PT; β0 is the intercept of the model, β1 and β2 are the regression coefficients of the model, which are used to adjust the influence of the theoretical knowledge mastery quality index and the practical operation ability quality index. High CSE usually means that students have a very solid grasp of theoretical knowledge and can achieve excellent results in theoretical tests. Students have a deep understanding of the theoretical knowledge they have learned and can flexibly use knowledge to analyze and solve problems. High CSE also shows that students perform very well in practical operations and can effectively apply theoretical knowledge to practical operations. Students have strong hands-on ability and the ability to solve practical problems, and perform well in practical operations such as experiments and projects. High CSE means that students not only excel in theoretical knowledge, but also achieve high scores in practical operations, indicating that their comprehensive ability is outstanding and the connection between theory and practice is good. Students perform well in multiple dimensions, indicating that they have high comprehensive quality and comprehensive development potential. Students with high CSE have strong competitiveness in future career development because they not only have solid theoretical knowledge, but also have strong practical operation ability. These students can better adapt to the complex and changing work environment in the future because they have cultivated the ability to combine theory with practice during the learning stage.
[0055] The logic of division is: obtain the comprehensive learning effect coefficient of the target students, and preset a comprehensive learning effect reference value. If the comprehensive learning effect coefficient of the target students is greater than or equal to the preset comprehensive learning effect reference value, they are divided into students with balanced theoretical and practical abilities. If the comprehensive learning effect coefficient of the target students is less than the preset comprehensive learning effect reference value, they are divided into students with potential disconnection. Division can help identify students with balanced theoretical and practical abilities. These students have excellent performance in learning and practical operations and have high comprehensive abilities. For students who are classified as having potential disconnection, early warning can be given, and teachers can provide targeted counseling and intervention to help these students improve their learning methods and enhance their comprehensive abilities. According to the comprehensive learning effect coefficient of students, education managers can adjust and optimize teaching strategies, formulate more targeted teaching plans, and improve the overall quality of education. Teachers can provide personalized teaching support for different types of students to help students develop in a balanced way in theoretical knowledge and practical operations.
[0056] For students classified as at risk of disconnection, the inference of instructional adjustments is as follows:
[0057] Define the input variables as the theoretical knowledge mastery quality index and the practical operation ability quality index, define the output variable as the teaching adjustment method, fuzzify the input variables, convert the values of the input variables into fuzzy sets, fuzzify the output variables, convert the values of the output variables into fuzzy sets, formulate fuzzy rules, describe the teaching adjustment needs under different data type combinations, and reason the fuzzified input variables through fuzzy rules to determine the teaching adjustment methods that need to be made. Input variables: theoretical knowledge mastery quality index (QT), practical operation ability quality index (PT); output variables: teaching adjustment methods (including theoretical adjustment, practical adjustment, and personalized adjustment); fuzzification: fuzzify the input variables, the fuzzy set of the theoretical knowledge mastery quality index (QT): low, medium, high; the fuzzy set of the practical operation ability quality index (PT): low, medium, high; fuzzify the output variables: the fuzzy set of teaching adjustment methods: theoretical adjustment, practical adjustment, and personalized adjustment. Personalized adjustment means that both theoretical adjustment and practical adjustment need to be adjusted, and the personalized adjustment direction of students is formulated. According to the teaching adjustment needs under different data combinations, fuzzy rules are formulated:
[0058] If QT is low and PT is low, individual adjustments are needed;
[0059] If the QT is low and the PT is intermediate, a theoretical adjustment is required;
[0060] If QT is low and PT is high, a theoretical adjustment is required;
[0061] If QT is intermediate and PT is low, practice adjustments are needed;
[0062] If QT is moderate and PT is moderate, individual adjustments are needed;
[0063] If QT is moderate and PT is high, practice adjustments are necessary;
[0064] If QT is high and PT is low, practice adjustments are needed;
[0065] If QT is high and PT is moderate, individual adjustments are needed;
[0066] If QT is high and PT is high, no adjustment is needed;
[0067] Use fuzzy rules to infer the fuzzified input variables and determine the teaching adjustment methods that need to be made. The following is a specific description of fuzzy reasoning: Personalized adjustment: Applicable to students with low theoretical and practical abilities, or students with low theoretical and practical abilities and medium abilities in one. Such students need help in both theory and practice, so comprehensive adjustments are needed to strengthen their theoretical understanding and practical operation ability. Theoretical adjustment: Applicable to students with low theoretical knowledge but high practical operation ability. Such students need more theoretical knowledge support to help them make progress in theoretical learning. Practical adjustment: Applicable to students with high theoretical knowledge but low practical operation ability. Such students need more practical operation training to improve their practical operation ability. Output specific teaching adjustment suggestions, including theoretical adjustment, practical adjustment or personalized adjustment. Each student's learning situation is different. The judgment of teaching adjustment methods can help teachers understand students' specific needs and provide targeted teaching support. By accurately identifying students' weak links in theory and practice, teachers can provide targeted tutoring to maximize teaching effectiveness. Adopting different teaching adjustment methods for different students can avoid the "one-size-fits-all" teaching model, making teaching more efficient, allowing students to improve their weaknesses faster and develop their comprehensive abilities more comprehensively. According to the needs of different students, reasonable allocation of teaching resources ensures that each student can receive appropriate attention and help. Teachers can formulate reasonable teaching plans and resource allocation strategies based on the results of the adjustment judgments, improve the utilization rate of teaching resources, and personalized teaching adjustment methods can improve the overall teaching quality and help more students achieve good academic results. This student-centered teaching method helps to improve the teaching level and reputation of educational institutions, and also helps to improve students' professional quality and development potential.
[0068] Embodiment 2: A desktop teaching and assessment system based on a multi-layer industrial network, comprising a training platform building module, a preliminary judgment module, a quantitative analysis module, a comprehensive analysis module, a division module, and a teaching adjustment module;
[0069] The training platform building module is used to build a network training platform, which is used to provide students with a network environment for theoretical teaching and practical assessment;
[0070] The preliminary judgment module is used to collect theoretical test data and practical operation test data of students in current teaching and practical operation based on the network training platform built by the training platform building module, and to perform preliminary analysis and operation, and to judge whether there is a hidden danger of disconnection between theory and practice based on the preliminary analysis results;
[0071] The quantitative analysis module is used to conduct quantitative analysis on each student when there is a hidden danger of disconnection between theory and practice, and generate a theoretical knowledge mastery quality index and a practical operation ability quality index;
[0072] The comprehensive analysis module is used to perform comprehensive analysis through the pre-trained machine learning model to obtain the comprehensive learning effect coefficient;
[0073] The classification module is used to classify each student into students with balanced theoretical and practical abilities or students with potential disconnection based on the comprehensive learning effect coefficient;
[0074] The teaching adjustment module is used to infer the teaching adjustment methods for students who are classified as having the risk of disconnection.
[0075] It should be noted that the multi-layer industrial network of the training platform consists of four parts: wiring layer, field layer, control layer, and information layer. The information layer includes the manufacturing execution system (MES), the control layer includes the programmable logic controller (PLC) and some additional control modules (motion control module, input and output module, AD and DA conversion module, serial communication module, multi-function Ethernet module, MES module), the field network includes remote modules, sensors, actuators and other components for communication, and the wiring layer includes the communication wiring between sensors and control modules. The sensor is equipped with a missing and proximity switch, a thermometer, an electronic scale, a distance sensor, a power meter, a code reader, and a visual sensor. The actuator is equipped with a servo drive and a servo motor, a variable frequency drive and a variable frequency motor, a stepper drive and a stepper motor. The modular structure of the hardware components can be flexibly placed and portable, suitable for a variety of learning scenarios, and can be seamlessly integrated into traditional classroom environments and project-based work, presenting complex content in an easy-to-understand way. The industrial network part is divided into four levels. For the intelligent sensor detector part of portable storage, it can realize the configuration and status monitoring of missing and proximity switches such as photoelectric, capacitive, inductive, and through-beam sensors, the configuration and status monitoring of intelligent RFID readers, the configuration and status monitoring of intelligent temperature and humidity meters, the configuration and status monitoring of weighing scales, the configuration of electricity meters to monitor and test power output, the configuration of laser ranging sensors to monitor and test the travel amount of the screw rod, the configuration and monitoring of voltage and current by voltmeters and ammeters, and the configuration of visual sensors to input processing images.
[0076] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0077] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0078] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0079] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0080] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A desktop teaching and assessment method based on a multi-layer industrial network, characterized in that: The following steps are involved: Collect theoretical test data and practical test data of students in current teaching and practical operation and conduct preliminary analysis and operation, and judge whether there is a hidden danger of disconnection between theory and practice based on the preliminary analysis results; If there is a hidden danger of disconnection between theory and practice, a quantitative analysis will be conducted on each student to generate a theoretical knowledge mastery quality index and a practical operation ability quality index; Based on the theoretical knowledge mastery quality index and the practical operation ability quality index, a comprehensive analysis is performed through the pre-trained machine learning model to obtain the comprehensive learning effect coefficient; Based on the comprehensive learning effect coefficient, each student is divided into students with balanced theoretical and practical abilities or students with potential disconnection; Infer how instructional adjustments might be made for students classified as at risk of disconnection.
2. According to claim 1, a desktop teaching and assessment method based on a multi-layer industrial network is characterized in that: In a fixed time window, the theoretical test data and practical operation test data of each student are collected from the teaching management system or the teacher, and the scores of each student in all theoretical type tests in the fixed time window are collected. The score in the theoretical type test refers to the percentage value calculated according to the ratio of each score to the total score. Then, the scores of all theoretical type tests in the fixed time window are added together to obtain the comprehensive theoretical test score of the target student. The logic for obtaining the actual operation test scores is as follows: collect the scores of each student in all operation type tests within the fixed time window. The score in the operation type test refers to the percentage value calculated according to the ratio of each score to the total score. Then add up the scores of all operation type tests within the fixed time window to obtain the comprehensive score of the actual operation test for the target student.
3. A desktop teaching and assessment method based on a multi-layer industrial network according to claim 2, characterized in that: The preliminary analysis operation refers to: obtaining each student's comprehensive theoretical test score and practical operation test score, marking the comprehensive theoretical test score as Ti, marking the comprehensive practical operation test score as Pi, i is the student number, calculating the score difference value Di between each student's comprehensive theoretical test score Ti and the comprehensive practical operation test score Pi, the score difference value Di is the difference between the comprehensive theoretical test score Ti and the comprehensive practical operation test score Pi, and then based on the score difference value Di, calculating the score difference average and score difference standard deviation of all students, comparing the score difference standard deviation with the preset threshold parameter, if the score difference standard deviation is less than or equal to the preset threshold parameter, a normal signal is generated, if the score difference standard deviation is not less than or equal to the preset threshold parameter, an abnormal signal is generated, and when an abnormal signal is generated, it indicates that there is a hidden danger of disconnection between theory and practice.
4. A desktop teaching and assessment method based on a multi-layer industrial network according to claim 3, characterized in that: The logic for obtaining the theoretical knowledge mastery quality index is as follows: In a fixed time window, all theoretical test data of the target students are obtained, the theoretical test data are standardized, the time decay factor and the difficulty coefficient are introduced, and each test score is weighted. The calculation formula is: Fi = wi*ai*di*fi; fi represents the standardized theoretical test data of theoretical test number i, wi represents the preset proportional coefficient of theoretical test number i, ai represents the time decay factor of theoretical test number i, di represents the difficulty coefficient of theoretical test number i, and its value range is between (0,1], Fi represents the weighted standardized score of theoretical test number i, all theoretical weighted standardized scores are summed up to obtain the comprehensive theoretical standardized score of the target student, and finally the theoretical knowledge mastery quality index is calculated. The calculation formula is: T total represents the comprehensive theoretical standardized score of the target student, QT represents the quality index of the target student's theoretical knowledge mastery, and W total Obtained through the following calculation: n is the total number of all theoretical test data.
5. A desktop teaching and assessment method based on a multi-layer industrial network according to claim 4, characterized in that: The time decay factor acquisition logic is: The calculation of the time decay factor is based on the exponential decay model, and its formula is: ai = e λti ; ti represents the time length from the test of theoretical test number i to the current time, and the value of λ is determined based on the pre-trained and fitted time decay model.
6. A desktop teaching and assessment method based on a multi-layer industrial network according to claim 5, characterized in that: The logic for obtaining the difficulty coefficient is: obtain the maximum value of the weighted standardized scores corresponding to all theoretical test data of the target student, and divide the weighted standardized score Fi of theoretical test number i by the maximum value to obtain the ratio value as the difficulty coefficient of the target student in theoretical test number i.
7. A desktop teaching and assessment method based on a multi-layer industrial network according to claim 6, characterized in that: The logic for obtaining the practical operation ability quality index is: In a fixed time window, all practical operation test data of the target students are obtained, the practical operation test data are standardized, the adjustment factor is introduced, and each test score is weighted. The calculation formula is: Zi = ki*Ri*zi; zi represents the standardized practical operation test data of practical operation test i, ki represents the preset proportional coefficient of practical operation test i, Ri is the adjustment factor of practical operation test i, Zi represents the practical weighted standardized score of practical operation test i, and then all the practical weighted standardized scores Zi are summed to obtain the comprehensive practical standardized score P of the target student. total , and finally calculate the practical operation ability quality index of the target student: μ total is the average of all practice weighted standardized scores Zi, σ total is the standard deviation of all practice weighted standardized scores Zi, and PT is the quality index of the target student's practical operation ability; The logic for obtaining the adjustment factor is: rank i is the rank of the target student in all students in practical operation test i, N is the total number of all students, and Ri is the adjustment factor of the target student in practical operation test i.
8. A desktop teaching and assessment method based on a multi-layer industrial network according to claim 7, characterized in that: The division logic is: Obtain the comprehensive learning effect coefficient of the target students, and preset a comprehensive learning effect reference value. If the comprehensive learning effect coefficient of the target students is greater than or equal to the preset comprehensive learning effect reference value, they will be classified as students with balanced theoretical and practical abilities; if the comprehensive learning effect coefficient of the target students is less than the preset comprehensive learning effect reference value, they will be classified as students with hidden dangers of disconnection.
9. The desktop teaching and assessment method based on a multi-layer industrial network according to claim 8 is characterized in that: For students classified as at risk of disconnection, the inference of instructional adjustments is as follows: Define the input variables as the theoretical knowledge mastery quality index and the practical operation ability quality index, define the output variables as the teaching adjustment method, fuzzify the input variables and convert the values of the input variables into fuzzy sets, fuzzify the output variables and convert the values of the output variables into fuzzy sets, formulate fuzzy rules, describe the teaching adjustment needs under different data type combinations, infer the fuzzified input variables through fuzzy rules, and determine the teaching adjustment method that needs to be made.
10. A desktop teaching and assessment system based on a multi-layer industrial network, based on a desktop teaching and assessment method based on a multi-layer industrial network according to any one of claims 1 to 9, characterized in that: It includes training platform building module, preliminary judgment module, quantitative analysis module, comprehensive analysis module, division module and teaching adjustment module; The training platform building module is used to build a network training platform, which is used to provide students with a network environment for theoretical teaching and practical assessment; The preliminary judgment module is used to collect theoretical test data and practical operation test data of students in current teaching and practical operation based on the network training platform built by the training platform building module, and to perform preliminary analysis and operation, and to judge whether there is a hidden danger of disconnection between theory and practice based on the preliminary analysis results; The quantitative analysis module is used to conduct quantitative analysis on each student when there is a hidden danger of disconnection between theory and practice, and generate a theoretical knowledge mastery quality index and a practical operation ability quality index; The comprehensive analysis module is used to perform comprehensive analysis through the pre-trained machine learning model to obtain the comprehensive learning effect coefficient; The classification module is used to classify each student into students with balanced theoretical and practical abilities or students with potential disconnection risks based on the comprehensive learning effect coefficient; The teaching adjustment module is used to infer the teaching adjustment methods for students who are classified as having the risk of disconnection.
Citation Information
Cited By
Statistical analysis method for campus statistical events
CN120912401A
