Chemical subject dynamic evaluation system based on intelligent feedback
Through the dynamic evaluation system of chemistry subjects with intelligent feedback, students' experimental data are collected and analyzed, personalized feedback is generated and real-time intervention is solved, and the lag problem of traditional evaluation systems is improved, and students' experimental skills and learning experience are improved.
Patent Information
- Application Number
- CN202510482195.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-17
- Publication Date
- 2025-07-29
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional chemistry discipline evaluation systems are unable to capture the details and changes in students' experiments in real time, resulting in lagging feedback and lack of targeting, and failing to provide timely personalized improvement suggestions.
A dynamic evaluation system for chemistry subjects is adopted with intelligent feedback, and experimental data and historical learning data are collected through the data acquisition module, and analyses student performance using machine learning algorithms, generate personalized feedback and intervene in real-time student operations.
It realizes personalized and precise learning support, improves students' experimental operation skills and theoretical knowledge, and enhances learning experience and teaching quality.
Smart Images
Figure CN120387735A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data analysis, and more specifically, to a dynamic evaluation system for the chemistry discipline based on intelligent feedback. Background Art
[0002] With the development of information technology, the education field is gradually moving towards the direction of intelligence and personalization, and the limitations of traditional teaching evaluation methods are gradually emerging, especially in the learning and evaluation of the chemistry discipline.
[0003] Chemistry is a discipline that combines experimentation and theory. Students need to master basic knowledge, experimental skills, and scientific thinking abilities. In traditional chemistry discipline evaluation systems, students' learning progress and experimental operations often rely on regular tests or manual evaluation by teachers, and the feedback is usually lagging and lacks pertinence. However, the learning process of students is a dynamically changing process, especially in chemistry experiments. Details in operations, depth of understanding, and problem-solving abilities are important factors affecting learning effects. Traditional evaluations often fail to capture these changes and details in real time, thus missing the best opportunity to provide students with timely and personalized improvement suggestions.
[0004] The dynamic evaluation system based on intelligent feedback collects students' learning data, combines artificial intelligence algorithms to dynamically analyze and evaluate students' learning status, and conducts real-time monitoring and analysis of students' experimental operations to help students improve their experimental skills, experimental efficiency, and safety. Summary of the Invention
[0005] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a dynamic evaluation system for the chemistry discipline based on intelligent feedback to solve the problems raised in the above background art.
[0006] To achieve the above object, the present invention provides the following technical solution. A dynamic evaluation system for the chemistry discipline based on intelligent feedback includes a data collection module, a data analysis module, and a feedback generation module; The data collection module collects data of students during the experiment process and students' historical learning data. The students' historical learning data includes students' test results and experimental feedback, processes the collected experimental data and historical learning data, and stores them in the cloud database; The data analysis module combines the collected experimental data with students' test results and experimental feedback, constructs a learning portrait of students, and uses machine learning algorithms to analyze students' performance in the experiment; The feedback generation module automatically generates personalized feedback information according to the output of the data analysis module, and during students' experimental operations, intervenes in students' deviation operations in real time and provides instant guidance.
[0007] In a preferred embodiment, the data acquisition module collects data of students during the experiment and students' historical learning data. The students' historical learning data includes students' test results and experimental feedback. The collected experimental data and historical learning data are processed and stored in a cloud database. The specific steps are as follows: Step A1, Data Acquisition: Install intelligent sensors in the experimental equipment and experimental environment to collect experimental data, and record students' experimental operations through cameras and motion capture devices, including the execution order of experimental steps, the use of tools, and operation accuracy. Integrate students' historical learning data, including previous test results and experimental feedback; Step A2, Data Processing and Storage: After cleaning and standardizing the collected experimental data and historical learning data, upload and store them in a cloud database through a secure encryption method for subsequent analysis and processing.
[0008] In a preferred embodiment, the data analysis module combines the collected experimental data with students' test results and experimental feedback to construct a learning portrait of students, and uses machine learning algorithms to analyze students' performance in the experiment, including the understanding of experimental steps, the accuracy of results, and the safety of operations, and identifies students' knowledge blind spots and operation problems. The specific steps are as follows: Step B1, Data Integration: Extract data of students during the experiment from the cloud database, including experimental step data, experimental result data, and experimental operation data, denoted as and extract students' test results and experimental feedback, denoted as Integrate the extracted experimental data with students' historical learning data to form a complete learning dataset X of students, where E is experimental data and H is students' historical learning data, represents the nth experimental record, represents the mth historical learning record; Step B2, Constructing the Learning Portrait: Combine the experimental data and historical learning data into a feature vector for each student, where The learning portrait of the i-th student includes his experimental steps, result accuracy, operation safety, and historical learning situation data, is the eigenvalue of the i-th student in the k-th dimension; Step B3, Data Analysis: Input the constructed learning portrait of students into a machine learning algorithm, and use a regression model to predict the results and analyze students' performance in the experiment. Further steps include: Step B301: Use the support vector regression model to maximize the error of the model by optimizing the objective function, map the features of the students into a high-dimensional space, and perform regression prediction. The prediction function formula is: The specific calculation formula of the objective function is where, is the predicted value, X is the learning profile of the input student, is the feature mapped by the kernel function, and are the weight vector and bias term of the model respectively, w is the weight vector of the hyperplane, is the bias term of the hyperplane, C is the penalty parameter used to control the error tolerance, is the prediction error of each student, and p is the total number of samples; Step B302: Use the training dataset of the students and the corresponding experimental results to train the regression model. The training process optimizes the parameters of the model by minimizing the loss function of the model. The specific formula is: where, MSE is the mean squared error, is the true value, is the predicted value, is the number of training samples; Step B303: Based on the performance of the students in the experimental steps, evaluate the number of steps correctly executed according to the similarity between the predicted results of the students and the actual operation steps, and calculate the step understanding score. The specific formula is ; Represent the result accuracy by calculating the difference between the predicted value and the true value , and perform an operation safety score according to whether the students follow the safety regulations in the experiment , where, S is the step understanding score of the experiment, and are the number of steps correctly executed and the total number of steps respectively, A is the result accuracy score, is the number of experimental results, is the true experimental result of the th student, is the predicted experimental result of the th student, is the safety score of the th operation step. If the safety rules are followed, the score is 1, otherwise it is 0, is the number of operation steps.
[0009] In a preferred embodiment, the feedback generation module automatically generates personalized feedback information based on the output of the data analysis module, and during the students' experimental operations, it intervenes in the students' deviated operations in real time and provides immediate guidance. The specific steps are as follows: Step C1, Deviation detection: Obtain the output data of the students' learning portraits and performance evaluations from the data analysis module, including the experimental step understanding score S, the result accuracy score A, and the operation safety score O. Detect the deviation by calculating the difference between the students' actual performance and the expected values. Set the expected score thresholds as , , as the standards. The specific calculation formulas are: , , , where , , respectively represent the deviations in experimental step understanding, result accuracy, and operation safety; Step C2, Generate feedback information according to the magnitude of the deviation. Use the predefined tolerances and as the judgment criteria. Generate feedback information according to the magnitude of the deviation. Use the predefined tolerances and as the judgment criteria. Judge whether the deviation of the students' performance exceeds the tolerance range according to the deviation and the set tolerances. When the deviation exceeds the tolerance range, generate personalized feedback information, and integrate the generated personalized feedback information into a complete structure and output it to the students' learning platform to help the students improve their experimental operations; The personalized feedback information includes experimental step understanding feedback, result accuracy feedback, and operation safety feedback; The experimental step understanding feedback is: ; The result accuracy feedback: ; The operation safety feedback is .
[0010] The beneficial effects of the present invention are as follows: collect the data of students during the experiment and the historical learning data of students, where the historical learning data of students includes the test results and experimental feedback of students, process the collected experimental data and historical learning data, and store them in the cloud database. Combine the collected experimental data with the test results and experimental feedback of students to construct a learning portrait of students, and use machine learning algorithms to analyze the performance of students in the experiment. According to the performance of students in the experiment, automatically generate personalized feedback information, and when students perform experimental operations, conduct real-time intervention on the deviation operations of students and provide immediate guidance. Through the closed-loop mechanism of data collection, analysis and feedback, the present invention can provide personalized and precise learning support for students, improve the experimental operation skills and the mastery of theoretical knowledge of students, enhance the learning experience, and promote the learning and teaching quality of the chemistry discipline. Description of the Drawings
[0011] Figure 1 It is a system flow chart of the present invention. Detailed Embodiments
[0012] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present application.
[0013] In the description of the present application, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present application, "a plurality" means two or more, unless otherwise specifically defined.
[0014] In the description of the present application, the term "for example" is used to mean "used as an example, illustration, or explanation". Any embodiment described as "for example" in the present application is not necessarily construed as being more preferred or having more advantages than other embodiments. In order to enable any person skilled in the art to implement and use the present invention, the following description is given. In the following description, details are set forth for the purpose of explanation. It should be understood that those skilled in the art can recognize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid unnecessary details from obscuring the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope that conforms to the principles and features disclosed in the present application.
[0015] Example 1 This example provides a dynamic assessment system for the chemistry discipline based on intelligent feedback as shown in Figure 1 Figure, which specifically includes a data collection module, a data analysis module, and a feedback generation module; The data collection module collects the data of students during the experiment and the historical learning data of students. The historical learning data of students includes the test results and experimental feedback of students. The collected experimental data and historical learning data are processed and stored in the cloud database; The data analysis module combines the collected experimental data with the test results and experimental feedback of students to construct a learning portrait of students, and uses machine learning algorithms to analyze the performance of students in the experiment; The feedback generation module automatically generates personalized feedback information according to the output of the data analysis module, and during the experiment operation of students, it performs real-time intervention on the deviation operations of students and provides immediate guidance.
[0016] In this example, specifically, the data collection module needs to be described. The data collection module collects the data of students during the experiment and the historical learning data of students. The historical learning data of students includes the test results and experimental feedback of students. The collected experimental data and historical learning data are processed and stored in the cloud database, enabling teachers and students to access the learning data anytime and anywhere, increasing the flexibility and convenience of learning. The specific steps are as follows: Step A1, Data collection: Install intelligent sensors in the experimental equipment and experimental environment to collect experimental data, and record the experimental operations of students through cameras and motion capture devices, including the execution order of experimental steps, the use of tools, and operation accuracy. Integrate the historical learning data of students, including previous test results and experimental feedback; Step A2, Data processing and storage: After cleaning and standardizing the collected experimental data and historical learning data, upload and store them in the cloud database through a secure encryption method for subsequent analysis and processing.
[0017] In this example, specifically, the data analysis module needs to be described. The data analysis module combines the collected experimental data with the test results and experimental feedback of students to construct a learning portrait of students, and uses machine learning algorithms to analyze the performance of students in the experiment, including the understanding of experimental steps, the accuracy of results, and the safety of operations. Identify the knowledge blind spots and operation problems of students, and automatically identify non-standard operations through data analysis, which can improve the safety of the experiment and the operation skills of students. The specific steps are as follows: Step B1. Data integration: Extract the data of students during the experiment from the cloud database, including experimental step data, experimental result data, and experimental operation data, denoted as , and extract the test results and experimental feedback of students, denoted as . Integrate the extracted experimental data with the historical learning data of students to form the complete learning dataset X of students, where E is the experimental data and H is the historical learning data of students, represents the nth experimental record, represents the mth historical learning record; Step B2. Construct learning portraits: Combine the experimental data and historical learning data into the feature vector of each student, where is the learning portrait of the ith student. The learning portrait of each student includes their experimental steps, result accuracy, operation safety, and historical learning situation data, is the eigenvalue of the ith student in the kth dimension. According to the performance and learning portraits of different students, the personalized learning plan can be adjusted at any time to make students more efficient in the learning process; Step B3. Data analysis: Input the constructed learning portraits of students into the machine learning algorithm and use the regression model to predict the results, analyze the performance of students in the experiment, which promotes the personalization and flexibility of teaching, optimizes the allocation of educational resources, and further includes the following steps: Step B301. Use the support vector regression model. By optimizing the objective function, maximize the error of the model, and map the features of students to a high-dimensional space for regression prediction. The prediction function formula is: . The specific calculation formula of the objective function is , where is the predicted value, X is the input learning portrait of the student, is the feature mapped by the kernel function, and are the weight vector and bias term of the model respectively, w is the weight vector of the hyperplane, is the bias term of the hyperplane, C is the penalty parameter used to control the tolerance of the error, is the prediction error of each student, and p is the total number of samples; Step B302. Use the training dataset of students and the corresponding experimental results to train the regression model. The training process optimizes the parameters of the model by minimizing the loss function of the model. The specific formula is: , where MSE is the mean square error, is the true value, is the predicted value, is the number of training samples; Step B303: Based on the performance of the student in the experimental steps, evaluate the number of steps correctly executed according to the similarity between the student's prediction result and the actual operation steps, and calculate the step understanding score. The specific formula is ; Represent the result accuracy by calculating the difference between the predicted value and the true value , and perform an operation safety score according to whether the student follows the safety regulations in the experiment , where S is the experimental step understanding score, and are the number of steps correctly executed and the total number of steps respectively, A is the result accuracy score, is the number of experimental results, is the th student's true experimental result, is the th student's predicted experimental result, is the th operation step's safety score. If the safety rules are followed, the score is 1, otherwise it is 0. is the number of operation steps.
[0018] In this embodiment, specifically, it is necessary to explain the feedback generation module. The feedback generation module automatically generates personalized feedback information according to the output of the data analysis module, and during the student's experimental operation, intervenes in the student's deviation operation in real time and provides instant guidance. Through timely feedback, it can guide the student to quickly adjust the learning strategy and find the best learning path. The specific steps are as follows: Step C1: Deviation detection: Obtain the student's learning portrait and the output data of the performance evaluation from the data analysis module, including the experimental step understanding score S, the result accuracy score A, and the operation safety score O. Detect the deviation by calculating the difference between the student's actual performance and the expectation. Set the expected scoring thresholds as , , as the standards. The specific calculation formulas are: , , , where , , represent the deviations in experimental step understanding, result accuracy, and operation safety respectively. Real-time monitoring and feedback of deviation operations can avoid potential safety hazards for students in the experiment and improve experimental safety; Step C2: Generate feedback information according to the magnitude of the deviation, using the predefined tolerances and As a judgment criterion, it is judged whether the deviation of the student's performance exceeds the tolerance range according to the deviation and the set tolerance. When the deviation exceeds the tolerance range, personalized feedback information is generated, and the generated personalized feedback information is integrated into a complete structure and output to the student's learning platform to help the student improve their experimental operation; The personalized feedback information includes feedback on the understanding of experimental steps, feedback on the accuracy of results, and feedback on operation safety; the feedback on the understanding of experimental steps is: ; The feedback on the accuracy of results: ; The feedback on operation safety is .
[0019] It should be noted that in the above embodiments, the descriptions of each embodiment have their own emphases. For parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0020] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0021] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.
[0022] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.
[0023] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing the steps of the function specified in one process or a plurality of processes and / or blocks Figure 1 in one block or a plurality of blocks Figure 1 in the process.
[0024] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn the basic inventive concept. Therefore, the appended claims are intended to be construed to cover the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.
[0025] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.
Claims
1. A dynamic assessment system for the chemistry discipline based on intelligent feedback, characterized in that: It includes a data acquisition module, a data analysis module, and a feedback generation module; The data acquisition module collects the data of students during the experiment and the historical learning data of students. The historical learning data of students includes the test results and experimental feedback of students. It processes the collected experimental data and historical learning data and stores them in the cloud database; The data analysis module combines the collected experimental data with the test results and experimental feedback of students, constructs a learning portrait of students, and uses machine learning algorithms to analyze the performance of students in the experiment; The feedback generation module automatically generates personalized feedback information according to the output of the data analysis module, and during the experiment operation of students, it conducts real-time intervention on the deviation operations of students and provides instant guidance.
2. The dynamic assessment system for the chemistry subject based on intelligent feedback according to claim 1, wherein: The data acquisition module collects the data of students during the experiment and the historical learning data of students. The historical learning data of students includes the test results and experimental feedback of students. It processes the collected experimental data and historical learning data and stores them in the cloud database. The specific steps are as follows: Step A1, data acquisition: Install intelligent sensors in the experimental equipment and experimental environment to collect experimental data, and record the experimental operations of students through cameras and motion capture devices, including the execution order of experimental steps, the use of tools, and operation accuracy. Integrate the historical learning data of students, including previous test results and experimental feedback; Step A2, data processing and storage: After cleaning and standardizing the collected experimental data and historical learning data, upload and store them in the cloud database through a secure encryption method.
3. The dynamic assessment system for chemistry subject based on intelligent feedback according to claim 1, characterized in that: The data analysis module combines the collected experimental data with the test results and experimental feedback of students, constructs a learning portrait of students, and uses machine learning algorithms to analyze the performance of students in the experiment. The specific steps are as follows: Step B1, Data Integration: Extract the data of students during the experiment from the cloud database, including experiment step data, experiment result data, and experiment operation data, expressed as , and extract the test results and experiment feedback of the students, expressed as , integrate the extracted experiment data with the historical learning data of the students to form a complete learning dataset X of the students, where E is the experiment data and H is the historical learning data of the students, represents the nth experiment record, represents the mth historical learning record; Step B2. Construct a learning profile: Combine the experimental data and historical learning data into a feature vector for each student , where is the learning profile of the i-th student. The learning profile of each student includes their experimental steps, result accuracy, operation safety, and historical learning data is the eigenvalue of the i-th student in the k-th dimension; Step B3, data analysis: Input the constructed learning portrait of students into the machine learning algorithm, and use the regression model to predict the results and analyze the performance of students in the experiment.
4. The dynamic assessment system for chemistry subject based on intelligent feedback according to claim 3, wherein: In the data analysis of step B3, input the constructed learning portrait of students into the machine learning algorithm, and use the regression model to predict the results and analyze the performance of students in the experiment. It further includes the following steps: Step B301: Use a support vector regression model. By optimizing the objective function, maximize the error of the model, map the features of the students to a high-dimensional space, and perform regression prediction. The prediction function formula is: , and the specific calculation formula of the objective function is , where is the predicted value, X is the learning profile of the input students, is the feature after being mapped by the kernel function, and are the weight vector and bias term of the model respectively, w is the weight vector of the hyperplane, is the bias term of the hyperplane, C is the penalty parameter used to control the error tolerance, is the prediction error of each student, and p is the total number of samples; Step B302: Use the training dataset of the student and the corresponding experimental results to train the regression model. The training process optimizes the parameters of the model by minimizing the loss function of the model. The specific formula is as follows: , where MSE is the mean squared error, is the true value, is the predicted value, is the number of training samples.
5. The dynamic evaluation system for chemistry subject based on intelligent feedback according to claim 4, wherein: Using the prediction results of the regression model to analyze the performance of students in the experiment, the steps include: Based on the performance of students in the experimental steps, evaluate the number of steps correctly executed according to the similarity between the predicted results of students and the actual operation steps, and calculate the step understanding score. The specific formula is ; Represent the result accuracy by calculating the difference between the predicted value and the true value , and conduct an operation safety score based on whether the student follows the safety regulations in the experiment , where S is the experimental step understanding score, and are the number of steps correctly executed and the total number of steps respectively, A is the result accuracy score, is the number of experimental results, is the th student's true experimental result, is the th student's predicted experimental result, is the safety score of the th operation step. If the safety rules are followed, the score is 1, otherwise it is 0, is the number of operation steps.
6. The dynamic assessment system for the chemistry discipline based on intelligent feedback according to claim 1, characterized in that: The feedback generation module automatically generates personalized feedback information according to the output of the data analysis module, and during the experiment operation of students, it conducts real-time intervention on the deviation operations of students and provides instant guidance. The specific steps are as follows: Step C1, Deviation Detection: Obtain the learning profile of the student and the output data of the performance evaluation from the data analysis module, including the experimental step understanding score S, the result accuracy score A, and the operation safety score O. Detect the deviation by calculating the difference between the actual performance of the student and the expectation. Set the expected score thresholds as , , as the standards. The specific calculation formulas are: , , , where , , represent the deviations in experimental step understanding, result accuracy, and operation safety respectively; Step C2: Generate feedback information based on the magnitude of the deviation, using a predefined tolerance and As the judgment criteria, generate feedback information based on the magnitude of the deviation, using a predefined tolerance and As the judgment criteria, determine whether the deviation in the student's performance exceeds the tolerance range based on the deviation and the set tolerance. When the deviation exceeds the tolerance range, generate personalized feedback information, and integrate the generated personalized feedback information into a complete structure and output it to the student's learning platform to help the student improve their experimental operation. The personalized feedback information includes feedback on the understanding of experimental steps, feedback on the accuracy of results, and feedback on operation safety.