Artificial intelligence-based virtual simulation teaching management method and system

Abstract

The application relates to the technical field of education and teaching management, and discloses a virtual simulation teaching management method and system based on artificial intelligence, which comprises the following steps: obtaining historical class data of students, performing data analysis to obtain model parameters according to the historical class data, and constructing a first student behavior evaluation model; obtaining motion coefficients by analyzing motion data according to current class data, and constructing a classroom performance coefficient; obtaining a second student behavior evaluation model according to the motion coefficients and the classroom performance coefficient; classifying student behavior data according to the second student behavior evaluation model, correcting the classification results, and obtaining correction results; constructing a student information coefficient according to the correction results, performing data analysis, and constructing a student seat information distribution map; and objectively evaluating the class behavior of students according to the behavior correction data and the student seat information distribution map. The method objectively and quantitatively evaluates the performance of students through artificial intelligence technology.

Description

Technical Field

[0001] This invention relates to the field of educational management, and in particular to a virtual simulation teaching management method and system based on artificial intelligence. Background Technology

[0002] With the continuous development and maturation of artificial intelligence (AI) technology, its application is gradually expanding across various industries, especially in education, where AI has brought revolutionary changes to teaching models. Virtual simulation teaching systems, as an emerging educational technology, have been widely used in the education sector. This system simulates real teaching scenarios, constructing virtual teacher and student avatars, allowing students to interact with virtual characters in a simulated environment, thus achieving an immersive learning experience. Simultaneously, the popularization of digital information technology has made virtual simulation classroom teaching management technology an important component of intelligent education classroom construction and a significant trend in smart campus development.

[0003] In one existing technology, the virtual simulation teaching management system mainly focuses on virtual simulation operation teaching, emphasizing the interaction between students and virtual scenes and the learning of skills. Teachers judge students' mastery of knowledge by observing their performance in the virtual environment and make teaching adjustments based on this observation.

[0004] In existing technologies, teacher evaluations are often highly subjective and fail to comprehensively reflect students' learning progress and mastery, which is a shortcoming of virtual simulation teaching management systems in evaluating student performance. Therefore, how to achieve scientific management of virtual simulation classrooms, especially how to use artificial intelligence technology to objectively and quantitatively evaluate student performance, has become an urgent technical problem to be solved. Summary of the Invention

[0005] This invention provides a virtual simulation teaching management method and system based on artificial intelligence, aiming to solve the problem that the evaluation of teachers in the existing technology is often highly subjective and cannot fully reflect the students' learning progress and mastery.

[0006] In a first aspect, to address the aforementioned technical problems, this invention provides a virtual simulation teaching management method based on artificial intelligence, executed by a computer, comprising:

[0007] Acquire students' historical class attendance data, which includes historical behavior data, historical homework data, and basic student data;

[0008] Based on the historical class data, data analysis is performed to obtain model parameters, and a first student behavior evaluation model for the virtual simulation teaching classroom is constructed based on the model parameters.

[0009] Obtain students' current class data;

[0010] Based on the current class data, motion data analysis is performed to obtain motion coefficients, and classroom performance coefficients are constructed based on the motion coefficients.

[0011] Based on the action coefficient and the classroom performance coefficient, the corresponding parameters in the first student behavior evaluation model are replaced to obtain the second student behavior evaluation model;

[0012] Based on the second student behavior evaluation model, the student behavior data in the current class data is classified to obtain the classification results;

[0013] Based on the second student behavior evaluation model, the student's behavior correction data is obtained, and the classification results are corrected to obtain the corrected data.

[0014] Based on the correction results, student information coefficients are constructed, and data analysis is performed using a spectral clustering algorithm. Based on the analysis results, a student seating information distribution map is constructed.

[0015] Based on the behavior correction data and the student seating information distribution map, data comparison and location identification operations are performed to complete an objective evaluation of students' classroom behavior.

[0016] As an optional implementation, based on the historical class data, data analysis is performed to obtain model parameters. Based on these model parameters, a first student behavior evaluation model for the virtual simulation classroom is constructed, including:

[0017] The model parameters include classroom performance coefficient, homework performance coefficient, practical training course grade coefficient, and student action coefficient.

[0018] The calculation expression for the first student behavior evaluation model is:

[0019]

[0020] in, This represents the first student behavior evaluation model. , and These represent the classroom performance coefficient, homework performance coefficient, and practical training course grade coefficient, respectively. , and These represent the interaction action coefficient, the focused action coefficient, and the practical action coefficient, respectively. , These represent the corresponding weight parameters.

[0021] As an optional implementation, the step of performing motion data analysis based on the current class data to obtain motion coefficients, and constructing classroom performance coefficients based on the motion coefficients, includes:

[0022] The current class data is provided by the virtual simulation teaching platform, and the action data includes, but is not limited to, interactive behavior data, focus behavior data, and practical behavior data.

[0023] The motion data analysis operation includes data collection and preprocessing definition, motion types and their indicators, motion data analysis, and calculation of motion coefficients;

[0024] The analysis of the interactive behavior data includes: obtaining the first basic action information of each student during the time period in which the action occurs, including the number of times each student asks questions, answers questions, participates in discussions, submits assignments, and performs practical training courses during the time period; and finding the relationship between the action and the first basic action information through statistical analysis or machine learning methods.

[0025] The analysis of the focused behavior data includes: obtaining the second basic action information of each student during the time period in which the action occurs, including the duration of each student watching the teaching video, the time spent reading the textbook, and the frequency of taking notes during the time period; and finding the relationship between the action and the second basic action information through statistical analysis or machine learning methods.

[0026] The analysis of the practical behavior data includes: obtaining the third basic action information of each student during the time period in which the action occurs, including the number of times each student completed the experiment, the number of programming exercises, and the success rate of the simulated operation during the time period; and finding the relationship between the action and the third basic action information through statistical analysis or machine learning methods.

[0027] The formula for calculating the action coefficient is as follows:

[0028]

[0029] in, Represented as the action coefficient based on focus time. Represented as an action coefficient based on interaction frequency. Action coefficient based on frequency of practice These represent the time periods before and after the action occurs, and the duration of the action, respectively. This is represented as the student's relevant historical academic data. This is represented by the number of inputs and outputs. This is represented as the grade for the practical training course. This is expressed as the number of practices and the success rate. These are respectively represented as specific functions for calculating the corresponding action coefficients;

[0030] The formula for calculating the classroom performance coefficient is as follows:

[0031]

[0032] in, This represents the student's current classroom performance coefficient. This represents the weight of each action coefficient at the current time, and satisfies... .

[0033] As an optional implementation, the step of classifying the student behavior data in the current class data according to the second student behavior evaluation model to obtain the classification result includes:

[0034] Based on the established second student behavior evaluation model, we analyze the student behavior data collected during the current class period and give preliminary behavior classification results.

[0035] The preliminary behavior classification results are cleaned, standardized, and normalized to ensure data quality and consistency, and the classification variables are converted into numerical representations to obtain processed classification data.

[0036] Meaningful features are extracted from the processed classification data, and the features most helpful for prediction are selected to construct a feature matrix. and label vector ,in Includes selected features, Includes the target variable;

[0037] The preprocessed feature matrix Input into the pre-trained second student behavior evaluation model In order to obtain the final behavior classification results.

[0038] As an optional implementation, the step of obtaining student behavior correction data based on the second student behavior evaluation model and correcting the classification results to obtain the correction result includes:

[0039] If the behavioral data of the classification result meets the standards set by the platform, the result is used directly and the next step is performed. The output result is the correction result.

[0040] If the behavioral data of the classification results does not meet the standards set by the platform, analyze the students' behavioral patterns, identify the aspects that need improvement, generate personalized behavioral correction data, and repeat the steps of obtaining classroom performance coefficients until the conditions are met. The output behavioral correction data is the correction result.

[0041] As an optional implementation, the student information coefficients are constructed based on the correction results, including:

[0042] Detailed action information for each student is extracted using optical character recognition technology, and this information is integrated with the behavior classification results to form a complete student behavior dataset.

[0043] Based on the student behavior dataset, student information coefficients are calculated, including focus coefficient, interaction coefficient, practice coefficient, and homework coefficient.

[0044] As an optional implementation, the step of performing data analysis based on the above and using a spectral clustering algorithm, and constructing a student seating information distribution map based on the analysis results, includes:

[0045] Based on the student information coefficients, students are divided according to the behavioral classification results, multiple student information groups are constructed, and each student in the student information group corresponds to a seat information.

[0046] Based on the multiple action coefficients corresponding to the student information coefficients, multiple student information groups are classified. Based on the classification results, multiple seat information corresponding to the multiple student information groups are grouped, and multiple seat information in each group is obtained.

[0047] The spectral clustering algorithm is used to treat student information groups as nodes in a graph. The nodes are clustered by calculating the eigenvectors of the Laplacian matrix. The graph formed by the seat information in each seat information group is used as the student seat information distribution map.

[0048] As an optional implementation, the step of performing data comparison and location identification operations based on the behavior correction data and the student seating information distribution map to complete an objective evaluation of students' classroom behavior includes:

[0049] The behavior correction data is combined with the basic information in the student seating distribution map to generate a comprehensive score.

[0050] By using a specific algorithm, behavioral scores and information scores are reasonably integrated to obtain a comprehensive score that can fully reflect the student's performance;

[0051] The comprehensive score of each student is mapped to the corresponding seat area on the student seating information distribution map, and the overall score of each seat area is calculated to complete the objective evaluation of the student's class behavior.

[0052] Secondly, the present invention provides a virtual simulation teaching management system based on artificial intelligence, configured in a computer, comprising:

[0053] The data acquisition module includes students' historical behavior data, historical homework data, and basic student data.

[0054] The first student behavior evaluation model construction module is used to perform data analysis operations based on the historical class data to obtain model parameters, and to construct the first student behavior evaluation model of the virtual simulation teaching classroom based on the model parameters.

[0055] The second student behavior evaluation model construction module is used to perform action data analysis based on the current class data to obtain action coefficients, construct classroom performance coefficients based on the action coefficients, and replace the corresponding parameters in the first student behavior evaluation model based on the action coefficients and the classroom performance coefficients to obtain the second student behavior evaluation model.

[0056] The correction result acquisition module is used to acquire students' behavior correction data based on the second student behavior evaluation model, and to perform correction operations on the classification results to obtain the correction results;

[0057] The student seating information distribution map construction module is used to construct student information coefficients based on the correction results, perform data analysis using spectral clustering algorithm, and construct a student seating information distribution map based on the analysis results.

[0058] The objective evaluation module is used to perform data comparison and location identification operations based on the behavior correction data and the student seating information distribution map to complete an objective evaluation of students' classroom behavior.

[0059] Thirdly, the present invention also provides a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute any one of the above-described artificial intelligence-based virtual simulation teaching management methods.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] This invention provides a virtual simulation teaching management method based on artificial intelligence. The method includes: acquiring students' historical class data, including historical behavior data, historical homework data, and basic student data; performing data analysis based on the historical class data to obtain model parameters, and constructing a first student behavior evaluation model for the virtual simulation teaching classroom based on the model parameters; acquiring students' current class data; performing action data analysis based on the current class data to obtain action coefficients, and constructing classroom performance coefficients based on the action coefficients; replacing corresponding parameters in the first student behavior evaluation model based on the action coefficients and the classroom performance coefficients to obtain a second student behavior evaluation model; classifying student behavior data in the current class data based on the second student behavior evaluation model to obtain classification results; acquiring corrected student behavior data based on the second student behavior evaluation model, and correcting the classification results to obtain corrected data; constructing student information coefficients based on the corrected results, and performing data analysis using a spectral clustering algorithm to construct a student seating information distribution map based on the analysis results; and performing data comparison and location identification operations based on the corrected behavior data and the student seating information distribution map to complete an objective evaluation of students' class behavior.

[0062] This method utilizes a computer system to collect and process student classroom data. By constructing a student behavior evaluation model in a virtual simulated classroom, it performs cluster analysis on the student classroom data and obtains preliminary scores. Based on OCR technology, it extracts the action information of each student, classifies the action information, identifies and analyzes each student's position and class status, and calculates the student's classroom performance coefficient and comprehensive score through specific formulas and algorithms, thereby achieving an objective and quantitative evaluation of student performance. Attached Figure Description

[0063] Figure 1 This is a schematic diagram of a virtual simulation teaching management method based on artificial intelligence provided in an embodiment of the present invention;

[0064] Figure 2 This is a schematic diagram illustrating the process of constructing a student behavior evaluation model for a virtual simulation teaching classroom, as provided in an embodiment of the present invention.

[0065] Figure 3 This is a schematic diagram of the structure of a virtual simulation teaching management system based on artificial intelligence provided in an embodiment of the present invention. Detailed Implementation

[0066] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0067] With the continuous development and maturation of artificial intelligence (AI) technology, its application is gradually expanding across various industries, especially in education, where AI has brought revolutionary changes to teaching models. Virtual simulation teaching systems, as an emerging educational technology, have been widely used in the education sector. This system simulates real teaching scenarios, constructing virtual teacher and student avatars, allowing students to interact with virtual characters in a simulated environment, thus achieving an immersive learning experience. Simultaneously, the popularization of digital information technology has made virtual simulation classroom teaching management technology an important component of intelligent education classroom construction and a significant trend in smart campus development.

[0068] In one existing technology, the virtual simulation teaching management system mainly focuses on virtual simulation operation teaching, emphasizing the interaction between students and virtual scenes and the learning of skills. Teachers judge students' mastery of knowledge by observing their performance in the virtual environment and make teaching adjustments based on this observation.

[0069] In existing technologies, teacher evaluations are often highly subjective and fail to comprehensively reflect students' learning progress and mastery, which is a shortcoming of virtual simulation teaching management systems in evaluating student performance. Therefore, how to achieve scientific management of virtual simulation classrooms, especially how to use artificial intelligence technology to objectively and quantitatively evaluate student performance, has become an urgent technical problem to be solved.

[0070] To solve the above problems, refer to Figure 1 The first embodiment of the present invention provides a virtual simulation teaching management method based on artificial intelligence, including the following steps:

[0071] S1, Obtain students' historical class attendance data, which includes historical behavior data, historical homework data, and students' basic data;

[0072] S2, Based on the historical class data, perform data analysis to obtain model parameters, and construct the first student behavior evaluation model for the virtual simulation teaching classroom based on the model parameters;

[0073] S3. Based on the current class data, perform action data analysis to obtain action coefficients, construct classroom performance coefficients based on the action coefficients, and replace the corresponding parameters in the first student behavior evaluation model with the action coefficients and the classroom performance coefficients to obtain the second student behavior evaluation model.

[0074] S4. Obtain student behavior correction data based on the second student behavior evaluation model, and perform correction operations on the classification results to obtain the correction results;

[0075] S5. Based on the correction results, construct student information coefficients and perform data analysis using spectral clustering algorithm. Based on the analysis results, construct a student seating information distribution map.

[0076] S6. Based on the behavior correction data and the student seating information distribution map, perform data comparison and location recognition operations to complete an objective evaluation of the student's classroom behavior;

[0077] In step S1, the student's historical class attendance data is obtained, which includes historical behavior data, historical homework data, and basic student data.

[0078] In one implementation, obtaining students' historical class data includes:

[0079] All student class data is provided by the pre-built virtual simulation teaching platform, specifically the student's classroom performance uploaded by the classroom monitoring system, such as the number of times they speak, the frequency of interaction, and their level of concentration.

[0080] Specifically, this involves connecting with the school's existing learning management system to extract information such as students' classroom participation and attendance records;

[0081] Specifically, this involves teachers manually entering or evaluating students' classroom performance, including the quality of their questions, the accuracy of their answers, and their contributions to group discussions.

[0082] Specifically, it integrates with the online homework submission platform used by schools, automatically capturing the submission time, completion quality, and grading results for each assignment;

[0083] Specifically, for paper-based assignments, the assignment content is digitized using scanners or OCR technology and uploaded to the virtual simulation teaching management system for unified management;

[0084] Specifically, it involves connecting the school's student registration management system to the virtual simulation teaching management system to obtain students' personal file information, such as grade, class, subject preferences, and special skills;

[0085] It should be noted that the historical class data includes student basic data, student classroom actions, teacher-uploaded homework data, and student-uploaded homework data; student basic data includes student grades and corresponding practical training course grades; student classroom actions include student actions and the time when the actions occurred.

[0086] In step S2, data analysis is performed based on the historical class data to obtain model parameters, and a first student behavior evaluation model for the virtual simulation teaching classroom is constructed based on the model parameters.

[0087] In one implementation, data analysis is performed based on the historical lesson data to obtain model parameters, and a first student behavior evaluation model for the virtual simulation classroom is constructed based on the model parameters, including:

[0088] The model parameters include classroom performance coefficient, homework performance coefficient, practical training course grade coefficient, and student action coefficient.

[0089] The calculation expression for the first student behavior evaluation model is:

[0090]

[0091] in, This represents the first student behavior evaluation model. , and These represent the classroom performance coefficient, homework performance coefficient, and practical training course grade coefficient, respectively. , and These represent the interaction action coefficient, the focused action coefficient, and the practical action coefficient, respectively. , These represent the corresponding weight parameters;

[0092] Furthermore, the steps for constructing the student behavior evaluation model include:

[0093] Data preprocessing. The acquired student historical class attendance data (including historical behavior data, historical homework data, and basic student data) is cleaned and standardized. Duplicate, erroneous, or incomplete data records are removed, and data from different sources is converted to a uniform format to ensure data quality and consistency.

[0094] Feature extraction and selection. Key features are extracted from the preprocessed data, such as classroom participation, attention span, homework completion quality, and trends in academic performance. Features that significantly influence student performance and behavior are selected as model inputs through statistical analysis and correlation analysis.

[0095] Data analysis and modeling. Using descriptive statistics, visualization tools, and other methods, we gain a deep understanding of data distribution and latent patterns, identify outliers and complex relationships between data, and select appropriate machine learning algorithms based on data characteristics, such as linear regression, decision trees, random forests, support vector machines, and neural networks, to build student behavior evaluation models. Historical data is used as the training set, and model parameters are adjusted to optimize predictive performance. Cross-validation and other techniques are used to evaluate the model's generalization ability, ensuring its applicability to new data.

[0096] Model parameter determination. The optimal model and its parameter settings are determined by comparing and evaluating multiple candidate models. These parameters include, but are not limited to, model structure, weights, and thresholds, and are used for subsequent behavior evaluation and prediction.

[0097] Construct the first student behavior evaluation model. Based on the determined model parameters, formally construct the first student behavior evaluation model for the virtual simulation teaching classroom.

[0098] In step S3, action data analysis is performed based on the current class data to obtain action coefficients. Classroom performance coefficients are constructed based on the action coefficients. Based on the action coefficients and the classroom performance coefficients, the corresponding parameters in the first student behavior evaluation model are replaced to obtain the second student behavior evaluation model.

[0099] In one implementation, based on current class data, action data analysis is performed to obtain action coefficients; classroom performance coefficients are constructed based on these action coefficients; and corresponding parameters in the first student behavior evaluation model are replaced based on the action coefficients and the classroom performance coefficients to obtain a second student behavior evaluation model, including:

[0100] The current class data is provided by the virtual simulation teaching platform, and the action data includes, but is not limited to, interactive behavior data, focus behavior data, and practical behavior data.

[0101] The motion data analysis operation includes data collection and preprocessing definition, motion types and their indicators, motion data analysis, and calculation of motion coefficients;

[0102] The analysis of the interactive behavior data includes: obtaining the first basic action information of each student during the time period in which the action occurs, including the number of times each student asks questions, answers questions, participates in discussions, submits assignments, and performs practical training courses during the time period; and finding the relationship between the action and the first basic action information through statistical analysis or machine learning methods.

[0103] The analysis of the focused behavior data includes: obtaining the second basic action information of each student during the time period in which the action occurs, including the duration of each student watching the teaching video, the time spent reading the textbook, and the frequency of taking notes during the time period; and finding the relationship between the action and the second basic action information through statistical analysis or machine learning methods.

[0104] The analysis of the practical behavior data includes: obtaining the third basic action information of each student during the time period in which the action occurs, including the number of times each student completed the experiment, the number of programming exercises, and the success rate of the simulated operation during the time period; and finding the relationship between the action and the third basic action information through statistical analysis or machine learning methods.

[0105] The formula for calculating the action coefficient is as follows:

[0106]

[0107] in, Represented as the action coefficient based on focus time. Represented as an action coefficient based on interaction frequency. Action coefficient based on frequency of practice These represent the time periods before and after the action occurs, and the duration of the action, respectively. This is represented as the student's relevant historical academic data. This is represented by the number of inputs and outputs. This is represented as the grade for the practical training course. This is expressed as the number of practices and the success rate. These are respectively represented as specific functions for calculating the corresponding action coefficients;

[0108] The formula for calculating the classroom performance coefficient is as follows:

[0109]

[0110] in, This represents the student's current classroom performance coefficient. This represents the weight of each action coefficient at the current time, and satisfies... ;

[0111] Furthermore, the expression for the second student behavior evaluation model is as follows:

[0112]

[0113] in, This represents the second student behavior evaluation model. , and These represent the updated classroom performance coefficient, homework performance coefficient, and practical training course grade coefficient, respectively. , and These represent the updated interaction action coefficient, focus action coefficient, and practical action coefficient, respectively. , These represent the corresponding weight parameters.

[0114] In step S4, student behavior correction data is obtained based on the second student behavior evaluation model, and the classification results are corrected to obtain the correction results.

[0115] In one implementation, the step of obtaining corrected student behavior data based on the second student behavior evaluation model and correcting the classification results to obtain corrected results includes:

[0116] If the behavioral data of the classification result meets the standards set by the platform, the result is used directly and the next step is performed. The output result is the correction result.

[0117] If the behavioral data of the classification results does not meet the standards set by the platform, analyze the students' behavioral patterns, identify the aspects that need improvement, generate personalized behavioral correction data, and repeat the steps of obtaining classroom performance coefficients until the conditions are met. The output behavioral correction data is the correction result.

[0118] Further, the step of classifying the student behavior data in the current class data according to the second student behavior evaluation model to obtain the classification result includes:

[0119] Based on the established second student behavior evaluation model, we analyze the student behavior data collected during the current class period and give preliminary behavior classification results.

[0120] The preliminary behavior classification results are cleaned, standardized, and normalized to ensure data quality and consistency, and the classification variables are converted into numerical representations to obtain processed classification data.

[0121] Meaningful features are extracted from the processed classification data, and the features most helpful for prediction are selected to construct a feature matrix. and label vector ,in Includes selected features, Includes the target variable;

[0122] The preprocessed feature matrix Input into the pre-trained second student behavior evaluation model In order to obtain the final behavior classification results;

[0123] It should be noted that the final revised result combines the revised classification results and behavior correction data to comprehensively evaluate the students' overall behavior performance and generate a detailed report, which includes each student's behavior improvement status, current behavior classification, and influencing factors.

[0124] In step S5, student information coefficients are constructed based on the correction results, and data analysis is performed using a spectral clustering algorithm. Based on the analysis results, a student seating information distribution map is constructed.

[0125] In one implementation, student information coefficients are constructed based on the correction results, and data analysis is performed using a spectral clustering algorithm. A student seating information distribution map is then constructed based on the analysis results, including:

[0126] Based on the student information coefficients, students are divided according to the behavioral classification results, multiple student information groups are constructed, and each student in the student information group corresponds to a seat information.

[0127] Based on the multiple action coefficients corresponding to the student information coefficients, multiple student information groups are classified. Based on the classification results, multiple seat information corresponding to the multiple student information groups are grouped, and multiple seat information in each group is obtained.

[0128] The spectral clustering algorithm is used to treat student information groups as nodes in a graph. The nodes are clustered by calculating the eigenvectors of the Laplacian matrix. The graph formed by the seat information in each seat information group is used as the student seat information distribution map.

[0129] Furthermore, student information coefficients are constructed based on the correction results, including:

[0130] The Optical Character Recognition (OCR) technology is used to automatically extract detailed action information of each student from classroom records, video materials, etc., and integrate this information with the behavior classification results to form a complete student behavior dataset.

[0131] Based on the student behavior dataset, student information coefficients are calculated, including focus coefficient, interaction coefficient, practice coefficient, and homework coefficient.

[0132] It should be noted that the determination of the time period of the action is achieved using the Dynamic Time Warping (DTW) algorithm in time series analysis. When processing data from different devices with slight time discrepancies, DTW can find the optimal time matching path, piecing together fragmented behavioral data according to the actual occurrence sequence, accurately marking the start and end times of each action, thereby extracting complete action information.

[0133] In step S6, based on the behavior correction data and the student seating information distribution map, data comparison and location identification operations are performed to complete an objective evaluation of the student's classroom behavior.

[0134] In one implementation, the step of performing data comparison and location identification operations based on the behavior correction data and the student seating information distribution map to complete an objective evaluation of students' classroom behavior includes:

[0135] The behavior correction data is combined with basic information (such as historical grades, attendance records, etc.) from the student seating information distribution map to generate a comprehensive score;

[0136] By using a specific algorithm, behavioral scores and information scores are reasonably integrated to obtain a comprehensive score that can fully reflect the student's performance;

[0137] The comprehensive score of each student is mapped to the corresponding seat area on the student seating information distribution map, and the overall score of each seat area is calculated to complete the objective evaluation of the student's class behavior.

[0138] To facilitate understanding of the present invention, some preferred embodiments of the present invention will be described in further detail below.

[0139] In a preferred embodiment, an artificial intelligence-based virtual simulation teaching management method is executed by a computer, the method further comprising:

[0140] Various student behavioral data in the classroom, specifically including: the number of times students look up, the number of times they look down and the duration of looking down, the degree of looking down, the number of times they sway their bodies, the number of times they yawn, the number of times they slouch at their desks during class and their corresponding frequencies, are used to construct a more comprehensive student behavior evaluation model. The calculation formula is as follows:

[0141] Lateness rating calculation formula:

[0142]

[0143] in, For the first Total number of students in the class For the first Lesson number The number of times each student was late. The total number of classes;

[0144] Early departure score is calculated using the following formula:

[0145]

[0146] in, For the first Total number of students in the class For the first Lesson number The number of times a student leaves early, The total number of classes;

[0147] The number of times you look up is calculated using the following formula:

[0148]

[0149] in, For the first Total number of students in the class For the first Lesson number The number of times each student looked up;

[0150] The "looking down" score is calculated using the following formula:

[0151]

[0152] in, For the first Total number of students in the class For the first Lesson number The duration of each student's head being down. For the first The number of times each student looks down during a lesson;

[0153] The head-turning score is calculated using the following formula:

[0154]

[0155] in, For the first Total number of students in the class For the first Lesson number Number of times each student turned their head

[0156] The number of body swings is calculated using the following formula:

[0157]

[0158] in, For the first Total number of students in the class For the first Lesson number The student's body swayed several times;

[0159] The frequency of yawning among students is calculated using the following formula:

[0160]

[0161] in, For the first Total number of students in the class For the first Lesson number The number of times a student yawns;

[0162] The frequency with which students slouch over their desks during class is calculated using the following formula:

[0163]

[0164] in, For the first Total number of students in the class For the first Lesson number The number of times a student slumps over their desk during class.

[0165] Reference Figure 2 The construction of the student behavior evaluation model for the virtual simulation teaching classroom specifically includes the following steps:

[0166] S201, obtains student action information through image processing;

[0167] It should be noted that in practical applications, student action information includes student head information, student facial features information, student body information, and student facial information. Student action information includes the student's class status, such as looking up, looking down, turning their head, etc.

[0168] S202, preprocess student attendance information, and statistically analyze the lateness, early departure, and absence information of each student in the attendance information;

[0169] S203, Establish a scoring mechanism for lateness and early departure;

[0170] S204, the lateness and early departure scoring mechanism is revised to obtain student lateness scores and student early departure scores;

[0171] S205, Construct a student status identification model;

[0172] It should be noted that the lateness score, early departure score, number of times the student looked up, number of times the student looked down, and number of times the student turned their head are used as input data for the student status identification model.

[0173] S206, Calculate the student status classification error value based on the lateness score and early departure score;

[0174] S207 uses classification error values ​​to adjust student tardiness and early departure scores, thus constructing a student behavior evaluation model for a virtual simulation teaching classroom.

[0175] In summary, this invention provides a virtual simulation teaching management method based on artificial intelligence. The method includes: acquiring students' historical class data, which includes historical behavior data, historical homework data, and basic student data; performing data analysis based on the historical class data to obtain model parameters, and constructing a first student behavior evaluation model for the virtual simulation teaching classroom based on the model parameters; acquiring students' current class data; performing action data analysis based on the current class data to obtain action coefficients, and constructing classroom performance coefficients based on the action coefficients; replacing corresponding parameters in the first student behavior evaluation model based on the action coefficients and the classroom performance coefficients to obtain a second student behavior evaluation model; classifying student behavior data in the current class data based on the second student behavior evaluation model to obtain classification results; acquiring corrected student behavior data based on the second student behavior evaluation model, and correcting the classification results to obtain corrected data; constructing student information coefficients based on the corrected results, and performing data analysis using a spectral clustering algorithm to construct a student seating information distribution map based on the analysis results; and performing data comparison and location identification operations based on the corrected behavior data and the student seating information distribution map to complete an objective evaluation of students' class behavior.

[0176] This method utilizes a computer system to collect and process student classroom data. By constructing a student behavior evaluation model in a virtual simulated classroom, it performs cluster analysis on the student classroom data and obtains preliminary scores. Based on OCR technology, it extracts the action information of each student, classifies the action information, identifies and analyzes each student's position and class status, and calculates the student's classroom performance coefficient and comprehensive score through specific formulas and algorithms, thereby achieving an objective and quantitative evaluation of student performance.

[0177] Reference Figure 3 The second embodiment of the present invention provides a virtual simulation teaching management system based on artificial intelligence, comprising:

[0178] 101 Data acquisition module, used for data including students' historical behavior data, historical homework data, and students' basic data;

[0179] 102 First Student Behavior Evaluation Model Construction Module, used to perform data analysis operations based on the historical class data to obtain model parameters, and to construct the first student behavior evaluation model of the virtual simulation teaching classroom based on the model parameters;

[0180] 103 The second student behavior evaluation model construction module is used to perform action data analysis operations based on the current class data to obtain action coefficients, construct classroom performance coefficients based on the action coefficients, and replace the corresponding parameters in the first student behavior evaluation model based on the action coefficients and the classroom performance coefficients to obtain the second student behavior evaluation model;

[0181] The 104 Correction Result Acquisition Module is used to acquire student behavior correction data based on the second student behavior evaluation model, and to perform correction operations on the classification results to obtain the correction results.

[0182] The 105 student seating information distribution map construction module is used to construct student information coefficients based on the correction results, perform data analysis using spectral clustering algorithm, and construct a student seating information distribution map based on the analysis results.

[0183] The 106 objective evaluation module is used to perform data comparison and location identification operations based on the behavior correction data and the student seating information distribution map to complete the objective evaluation of students' classroom behavior.

[0184] It should be noted that the artificial intelligence-based virtual simulation teaching management system provided in this embodiment of the invention is used to execute all the process steps of the artificial intelligence-based virtual simulation teaching management method in the above embodiment. The working principles and beneficial effects of the two are one-to-one, so they will not be described again.

[0185] In summary, this invention provides an artificial intelligence-based virtual simulation teaching management method. The method includes: acquiring students' historical class attendance data, which includes historical behavior data, historical homework data, and basic student data; performing data analysis based on the historical class attendance data to obtain model parameters, and constructing a first student behavior evaluation model for the virtual simulation teaching classroom based on the model parameters; acquiring students' current class attendance data; performing action data analysis based on the current class attendance data to obtain action coefficients, and constructing classroom performance coefficients based on the action coefficients; replacing corresponding parameters in the first student behavior evaluation model based on the action coefficients and the classroom performance coefficients to obtain a second student behavior evaluation model; classifying student behavior data in the current class attendance data based on the second student behavior evaluation model to obtain classification results; acquiring corrected student behavior data based on the second student behavior evaluation model and correcting the classification results to obtain corrected data; constructing student information coefficients based on the corrected results and performing data analysis using a spectral clustering algorithm to construct a student seating information distribution map based on the analysis results; and performing data comparison and location identification operations based on the corrected behavior data and the student seating information distribution map to complete an objective evaluation of students' class attendance behavior.

[0186] This method utilizes a computer system to collect and process student classroom data. By constructing a student behavior evaluation model in a virtual simulated classroom, it performs cluster analysis on the student classroom data and obtains preliminary scores. Based on OCR technology, it extracts the action information of each student, classifies the action information, identifies and analyzes each student's position and class status, and calculates the student's classroom performance coefficient and comprehensive score through specific formulas and algorithms, thereby achieving an objective and quantitative evaluation of student performance.

[0187] This invention also provides an electronic device. The electronic device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, such as an artificial intelligence-based virtual simulation teaching management method program. When the processor executes the computer program, it implements the steps described in the various embodiments of the artificial intelligence-based virtual simulation teaching management method, for example... Figure 1 Step S1 is shown. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the above-described device embodiments, such as the 101 data acquisition module.

[0188] For example, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.

[0189] The electronic device may be a desktop computer, laptop, handheld computer, or smart tablet, etc. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. It may include more or fewer components than described above, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0190] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the electronic device, connecting all parts of the electronic device via various interfaces and lines.

[0191] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0192] Wherein, if the modules / units integrated in the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0193] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0194] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A virtual simulation teaching management method based on artificial intelligence, characterized in that, The computer is executed, comprising: obtaining the historical class data of students, the historical class data includes historical behavior data, historical homework data and student basic data; According to the historical class data, the model parameters are obtained by data analysis operation, and the first student behavior evaluation model of virtual simulation teaching classroom is constructed according to the model parameters; Obtain the current class data of students; According to the current class data, the action coefficient is obtained by action data analysis operation, and the classroom performance coefficient is constructed according to the action coefficient; According to the action coefficient and the classroom performance coefficient, the corresponding parameters in the first student behavior evaluation model are replaced to obtain the second student behavior evaluation model; According to the second student behavior evaluation model, the student behavior data in the current class data is classified to obtain the classification result; Based on the second student behavior evaluation model, the behavior correction data of the student is obtained, and the classification result is corrected to obtain the correction result; According to the correction result, the student information coefficient is constructed, and the data analysis operation is carried out by using spectral clustering algorithm, and the student seat information distribution map is constructed according to the analysis result; According to the behavior correction data and the student seat information distribution map, data comparison and position recognition operation is carried out, and the objective evaluation of student class behavior is completed; Wherein, according to the historical class data, the model parameters are obtained by data analysis operation, and the first student behavior evaluation model of virtual simulation teaching classroom is constructed according to the model parameters, comprising: The model parameters include classroom performance coefficient, homework performance coefficient, practical course score coefficient and student action coefficient; The calculation expression of the first student behavior evaluation model is: wherein, represents a first student behavior evaluation model, , and respectively represent a class performance coefficient, a homework performance coefficient, and a practical course score coefficient, , and respectively represent an interaction action coefficient, a concentration action coefficient, and a practice action coefficient, , respectively represent corresponding weight parameters; Wherein, according to the current class data, the action coefficient is obtained by action data analysis operation, and the classroom performance coefficient is constructed according to the action coefficient, comprising: The current class data is provided by virtual simulation teaching platform, and the action data includes but is not limited to interactive behavior data, focused behavior data and practical behavior data; The action data analysis operation includes data collection and preprocessing definition, action type and index, action data analysis and calculation of action coefficient; The analysis of interactive behavior data includes: obtaining the first basic action information of each student in the action time period, including the number of questions, the number of answers, the number of discussions, the number of homework submissions and the practical course score of each student in the time period, and finding out the relationship between the action and the first basic action information by statistical analysis or machine learning method; The analysis of focused behavior data includes: obtaining the second basic action information of each student in the action time period, including the duration of watching teaching video, the time of reading teaching material and the frequency of taking notes of each student in the time period, and finding out the relationship between the action and the second basic action information by statistical analysis or machine learning method. The analysis of the practice behavior data includes: obtaining third basic action information of each student in the action occurrence time period, including the number of experiments completed by each student, the number of programming exercises, and the success rate of simulation operations in the time period, and finding the relationship between the action and the third basic action information through statistical analysis or machine learning method; The calculation formula of the action coefficient is as follows: wherein, action coefficient based on concentration time, action coefficient based on interaction frequency, action coefficient based on practice frequency, respectively represent time periods before and after and lasting for the action, represent relevant historical performance data of the student, represent input and output times, represent practical course performance, represent the number of times and success rate of practical behavior, respectively represent specific functions for calculating the corresponding action coefficients; The calculation formula of the classroom performance coefficient is as follows: wherein, represents the current class performance coefficient of the student, represents the weight of the current action coefficient, and satisfies ; The behavior correction data of the student is obtained based on the second student behavior evaluation model, and the classification result is corrected to obtain a correction result, including: If the behavior data of the classification result meets the platform set standard, the result is directly used and the next step operation is entered, and the output result is the correction result; If the behavior data of the classification result does not meet the platform set standard, the behavior mode of the student is analyzed, the aspects that need to be improved are identified, personalized behavior correction data is generated, and the step of obtaining the classroom performance coefficient is repeatedly executed until the condition is met, and the output behavior correction data is the correction result.

2. The virtual simulation teaching management method based on artificial intelligence according to claim 1, characterized in that, The student behavior data in the current class data is classified according to the second student behavior evaluation model to obtain a classification result, including: Based on the second student behavior evaluation model, the student behavior data collected during the current class is analyzed to give a preliminary behavior classification result; The preliminary behavior classification result is cleaned, standardized and normalized to ensure the quality and consistency of the data, and the classification variable is converted into a numerical type to obtain processed classification data; extracting meaningful features from the processed classification data, screening out the most helpful features for prediction, and constructing a feature matrix and a label vector wherein comprising selected features, comprising a target variable; The pre-processed feature matrix is input into the trained second student behavior evaluation model to obtain a final behavior classification result.

3. The virtual simulation teaching management method based on artificial intelligence according to claim 1, characterized in that, According to the correction result, a student information coefficient is constructed, including: Detailed action information of each student is extracted using optical character recognition technology, and these information is integrated with the behavior classification result to form a complete student behavior data set; According to the student behavior data set, a student information coefficient is calculated, including a concentration coefficient, an interaction coefficient, a practice coefficient and a homework coefficient.

4. The virtual simulation teaching management method based on artificial intelligence according to claim 1, characterized in that, The data analysis operation is performed using a spectral clustering algorithm, and a student seat information distribution map is constructed according to the analysis result, including: Based on the student information coefficient, the students are divided according to the behavior classification result to construct multiple student information groups, and each student in the student information group corresponds to a seat information; According to the multiple action coefficients corresponding to the student information coefficient, multiple student information groups are classified, and according to the classification result, multiple seat information corresponding to multiple student information groups are grouped to obtain multiple seat information in each group; The spectral clustering algorithm is used to regard the student information group as a node of a graph, the nodes are clustered by calculating the eigenvectors of the Laplacian matrix, and the graph formed by the seat information in each seat information group is taken as a student seat information distribution map.

5. The virtual simulation teaching management method based on artificial intelligence according to claim 1, characterized in that, According to the behavior correction data and the student seat information distribution map, data comparison and position recognition operation is performed to complete the objective evaluation of the student's class behavior, including: The behavior correction data and the basic information in the student seat information distribution map are combined to generate a comprehensive score; The behavior score and the information score are reasonably fused by a specific algorithm to obtain a comprehensive score that can comprehensively reflect the performance of the student. The comprehensive score of each student is mapped to a seat area of a seat information distribution map corresponding to the student, an overall score of each seat area is calculated, and an objective evaluation of the student's classroom behavior is completed.

6. An artificial intelligence-based virtual simulation teaching management system, characterized in that, The computer is configured to implement the virtual simulation teaching management method based on artificial intelligence according to any one of claims 1 to 5, comprising: A data acquisition module, the data including historical behavior data, historical homework data and basic data of the student; A first student behavior evaluation model construction module is configured to obtain model parameters by performing data analysis on the historical classroom data, and to construct a first student behavior evaluation model of the virtual simulation teaching classroom according to the model parameters; A second student behavior evaluation model construction module is configured to obtain a motion coefficient by performing motion data analysis on the current classroom data, to construct a classroom performance coefficient according to the motion coefficient, and to replace corresponding parameters in the first student behavior evaluation model with the motion coefficient and the classroom performance coefficient to obtain a second student behavior evaluation model; A correction result acquisition module is configured to obtain behavior correction data of the student based on the second student behavior evaluation model, to correct the classification result, and to obtain a correction result; A student seat information distribution map construction module is configured to construct a student information coefficient based on the correction result, to perform data analysis using a spectral clustering algorithm, and to construct a student seat information distribution map based on the analysis result; An objective evaluation module is configured to perform data comparison and position recognition based on the behavior correction data and the student seat information distribution map, and to complete an objective evaluation of the student's classroom behavior.

7. A computer readable storage medium characterized in that, The computer readable storage medium comprises a stored computer program, wherein the computer readable storage medium controls the device where the computer readable storage medium is located to execute the virtual simulation teaching management method based on artificial intelligence according to any one of claims 1 to 5 when the computer program is running.

Images