Teaching information management method based on big data

Abstract

The invention discloses a teaching information management method based on big data, and particularly relates to the field of teaching, comprising data acquisition, behavior characteristic analysis, knowledge mastering evaluation, dynamic feedback adjustment, comprehensive evaluation and management strategy. The teaching behavior analysis depth is improved through multi-dimensional data fusion and non-linear feature analysis, real-time adjustment of an evaluation model along with knowledge mastery is achieved through a dynamic feedback mechanism, limitation of traditional static analysis is broken through, theoretical test and practice project data are integrated through an innovatively constructed three-dimensional evaluation system, and the teaching behavior evaluation efficiency is improved. A comprehensive evaluation model covering knowledge application and innovation ability development is formed, a dynamic path selection mechanism synchronously supports basic ability enhancement and high-order skill development requirements, a resource allocation strategy has instant intervention and long-term optimization characteristics, and adaptability and decision scientificity of a teaching management system are remarkably enhanced.

Description

Technical Field

[0001] The present invention relates to the field of teaching technology, and more specifically, to a teaching information management method based on big data. Background Art

[0002] With the acceleration of the process of educational informatization, teaching information management technology has become an important support for optimizing the allocation of educational resources. Current teaching management systems generally adopt basic data collection and linear analysis methods. By recording basic data such as student attendance, homework submission, and test scores, they use weighted average or simple statistical models to generate learning evaluation results, and apply the results to teaching warnings or resource allocation decisions.

[0003] Existing technologies have three flaws: First, the data dimension is limited to surface behavior records, and there is a lack of effective analysis of deep learning behaviors such as the frequency of classroom interactions and resource usage characteristics; second, the analysis process uses a fixed algorithm path and cannot dynamically adjust the analysis model according to the students' knowledge mastery level; third, the evaluation system focuses on theoretical performance indicators and ignores the correlation analysis between the quality of practical project completion and the development of high-level abilities, resulting in a deviation between management strategies and actual teaching needs. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a teaching information management method based on big data. Through the following scheme, it solves the defects proposed in the above-mentioned background technology, such as single data dimension, static analysis model, and one-sided neglect of practical relevance in the evaluation system, which restricts the accuracy of management strategies.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a teaching information management method based on big data, comprising: S1: Data collection: Obtain teaching information data from the teaching system, eliminate dimensional differences through standardized formulas, use historical mean and standard deviation to normalize the original data, and establish a unified dimensional system; S2: Behavioral Characteristics Analysis: The standardized teaching information data is subjected to nonlinear feature fusion to generate comprehensive learning behavior indicators, knowledge point test scores, and resource usage frequency data. The adjustment coefficient determined by principal component analysis is combined with the logarithmic function, hyperbolic tangent function, and ratio function to construct a composite calculation model to quantitatively reflect the basic learning behavior characteristics of students. S3: Knowledge Mastery Assessment: This method integrates learning behavior characteristic indicators, knowledge point test scores, and resource usage frequency data to assess students' knowledge mastery of the teaching content. A multiplicative relationship is used to express the positive correlation between behavior characteristics and test scores. Resource usage frequency is introduced as an inverse adjustment factor, and the stability of the assessment results is controlled by an empirically set smoothing constant. S4: Dynamic feedback regulation: Automatically selects the analysis path based on the evaluation results of S3, and directs the data flow to different calculation branches to calculate the learning path analysis indicators through the knowledge mastery threshold determined by cluster analysis; S5: Comprehensive evaluation: Based on the path analysis results of S4 and the completion data of practical projects, a teaching effectiveness evaluation index is generated; S6: Management strategy: Implement precise intervention through threshold-triggered graded warnings, divide resource allocation levels according to the teaching effectiveness evaluation index range, dynamically adjust teaching strategies based on periodic growth rates, and simultaneously generate structured evaluation files for individuals, classes, and semesters.

[0006] Preferably, the teaching system includes an online learning platform, a classroom response system, an online testing system, a resource management platform and a project management system, wherein: The online learning platform is used to manage assignment submissions and record timestamp data; The classroom response system and online discussion forum are used to collect the frequency of classroom interactions and the number of valid questions; The online testing system is used to implement knowledge point unit tests and store original scores; The resource management platform is used to collect statistics on learning resource usage behavior; The project management system is used to track the completion progress of the practical project modules.

[0007] Preferably, the teaching information data includes student attendance rate, homework submission timeliness rate, classroom interaction frequency, knowledge point test average score, learning resource usage frequency and practical project completion rate.

[0008] Preferably, the student attendance rate is calculated by calculating the percentage of the actual number of class attendances to the total number of courses through the electronic sign-in records of the online learning platform; the homework submission timeliness rate is calculated by comparing the homework submission timestamp data of the online learning platform with the preset deadline; the classroom interaction frequency is calculated by counting the number of valid questions and the number of discussions participated in through the interaction log between the classroom answering system and the online discussion area; the knowledge point test average score is calculated by calculating the arithmetic mean of the original score data of each knowledge point unit test of the online testing system; the learning resource usage frequency is generated by generating standardized indicators through the learning video viewing time, document download number and simulation experiment startup number of the resource management platform; the practical project completion rate is calculated by comparing the phased results acceptance record of the project management system with the task list to calculate the proportion of completed modules.

[0009] Preferably, the standardized formula is specifically expressed as: , Represents the i-th teaching information data, μ represents the historical mean value for the same period, and σ represents the standard deviation of historical data.

[0010] Preferably, the comprehensive learning behavior index integrates the standardized attendance rate, homework submission timeliness rate and classroom interaction frequency data through nonlinear combination, uses logarithmic transformation to weaken the influence of extreme values ​​for attendance rate data, uses hyperbolic tangent function to perform saturation processing on homework timeliness, and uses ratio function to reduce data discreteness for classroom interaction frequency. The characteristic values ​​after the three types of processing are compound calculated by the adjustment coefficient determined by principal component analysis to form a comprehensive index that characterizes the characteristics of learning behavior, wherein the base of the logarithmic function is the natural logarithm, the input range of the hyperbolic tangent function is the standardized value range, and the denominator of the ratio function adopts the absolute value smoothing strategy, and finally the characteristic expression of multidimensional behavior data is realized through linear combination.

[0011] Preferably, the comprehensive learning behavior indicator is specifically expressed as: , AR represents student attendance rate, AT represents the timely submission rate of homework, CI represents the frequency of classroom interaction, and α, β, and γ represent adjustment coefficients.

[0012] Preferably, the knowledge mastery evaluation value is based on the standardized learning behavior characteristic indicators, knowledge point test scores and learning resource usage frequency data, and a multiplication relationship is established between the learning behavior characteristic indicators and the knowledge point test scores to characterize the positive correlation between behavioral performance and knowledge acquisition. The standardized resource usage frequency is introduced as a denominator adjustment item in the calculation formula, and an empirically set smoothing constant is added to avoid division by zero errors and control the intensity of the impact of resource utilization efficiency on the evaluation results, ultimately forming a continuous quantitative indicator reflecting the students' knowledge mastery.

[0013] Preferably, the knowledge mastery evaluation value is specifically expressed as: , TS represents the average score of knowledge point test, RU represents the frequency of learning resource use, and ε is the smoothing constant.

[0014] Preferably, the S4 is based on a comparative analysis of the knowledge mastery evaluation value and a preset threshold. When the knowledge mastery evaluation value exceeds the demarcation threshold determined by cluster analysis, it enters the high-level capability analysis path, couples the standardized data of the practical project completion with the knowledge mastery evaluation value, and superimposes the resource utilization efficiency data corrected by the path adjustment coefficient to participate in the square root synthesis operation; when the knowledge mastery evaluation value does not reach the threshold, it enters the basic reinforcement analysis path. The basic reinforcement analysis path uses the sum of the standardized data of attendance rate and homework submission timeliness as the numerator, and uses the absolute difference between the frequency of classroom interaction and the knowledge mastery evaluation value as the denominator for ratio operation, and implements dimension normalization on the denominator through the path adjustment coefficient. Both types of path adjustment coefficients are obtained by fitting and optimizing historical data through the path analysis model.

[0015] Preferably, the knowledge mastery threshold is marked as θ. When KMA>θ, the learning path analysis indicator is specifically expressed as: , when KMA≤θ, the learning path analysis indicator is specifically expressed as: , 、 represents the path adjustment coefficient.

[0016] Preferably, the teaching effectiveness evaluation index is based on the coupling calculation of the learning path analysis index and the practical project completion data, and a multiplication relationship is established between the learning path analysis index output by S4 and the standardized practical project completion as an evaluation benchmark. The discreteness adjustment calculation of the absolute difference between the two is introduced in the denominator, and the adjustment parameters determined by regression analysis are used to control the impact of the difference on the evaluation result. The maximum value function is used to ensure that the denominator is not lower than the benchmark unit value, and finally a normalized evaluation index is formed that comprehensively reflects the rationality of the learning path selection and the matching degree of the practical results.

[0017] Preferably, the teaching effect evaluation index is specifically expressed as: , PC represents the completion of the practice project, and λ represents the dispersion adjustment coefficient.

[0018] Preferably, the S6 triggers a hierarchical early warning mechanism through preset thresholds, and automatically implements intervention plans for individuals who do not meet the standards; divides resource allocation levels according to the distribution of teaching effectiveness evaluation indexes, and allocates learning rights and practical tasks in a differentiated manner; establishes a dynamic adjustment mechanism for teaching plans based on periodic year-on-year growth rates, and initiates a special review process for abnormally fluctuating groups; and simultaneously generates standardized evaluation files covering individual, class, and semester dimensions for structured storage and traceability analysis of teaching management data, forming a traceable digital file system for teaching management.

[0019] Preferably, the graded warning mechanism sets a dynamic warning mechanism based on TGI. When the TGI is lower than 80% of the historical benchmark value, the yellow warning system is automatically triggered, and customized knowledge point reinforcement training content is pushed to the corresponding students; when the TGI falls below 60% of the historical benchmark value, it is upgraded to a red warning, and the teacher is notified to start the interview diagnosis process at the same time.

[0020] Preferably, the resource allocation level divides the student groups into four resource allocation levels according to the TGI distribution. The top 10% of the group automatically obtains access rights to high-level academic resources, the 10%-50% range of groups receives extended practical tasks, the 50%-90% range maintains standard teaching resource configuration, and the bottom 10% of the group activates the learning behavior tracking system. All resource adjustments are automatically distributed and controlled through the teaching management platform.

[0021] Preferably, the dynamic adjustment mechanism analyzes the TGI change rate at the end of each teaching cycle, maintains the existing teaching plan and marks it as a high-quality path for groups with a month-on-month growth of more than 15%, starts a teaching progress fine-tuning program for groups with a change rate between -5% and 15%, and automatically initiates a teaching plan review meeting for groups with a decrease of more than 5%.

[0022] The technical effects and advantages of the present invention are as follows: This method significantly improves the depth and accuracy of teaching behavior analysis through multi-dimensional data fusion, integrates composite indicators such as attendance patterns, resource usage characteristics, and classroom interaction quality, and uses a nonlinear feature fusion algorithm to analyze the inherent correlation of learning behavior. This breaks through the limitations of traditional single-dimensional evaluation and provides a more explanatory analytical basis for teaching management. The dynamic feedback adjustment mechanism effectively enhances system adaptability, switches analysis paths in real time based on knowledge mastery assessment values, establishes a flexible analysis framework between strengthening basic capabilities and developing advanced skills, and achieves a technological leap from static assessment to process-based intervention. The comprehensive evaluation system innovatively integrates the dual dimensions of theoretical tests and practical projects. Through the teaching effectiveness evaluation index, it constructs a three-dimensional evaluation model covering knowledge application, skill transfer, and innovation ability, providing decision-making support for the allocation of teaching resources that takes into account both immediate response and long-term development. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 Schematic diagram of the method structure of the present invention.

[0024] Figure 2 It is a schematic structural diagram of a complete embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0026] As attached Figure 1-2 A teaching information management method based on big data is shown, comprising: S1: Data collection: Obtain teaching information data from the teaching system, eliminate dimensional differences through standardized formulas, use historical mean and standard deviation to normalize the original data, and establish a unified dimensional system.

[0027] The teaching system includes an online learning platform, a classroom response system, an online testing system, a resource management platform and a project management system, among which: The online learning platform is used to manage assignment submissions and record timestamp data; The classroom response system and online discussion forum are used to collect the frequency of classroom interactions and the number of valid questions; The online testing system is used to implement knowledge point unit tests and store original scores; The resource management platform is used to collect statistics on learning resource usage behavior; The project management system is used to track the completion progress of the practical project modules.

[0028] The teaching information data includes student attendance rate, homework submission timeliness rate, classroom interaction frequency, knowledge point test average score, learning resource usage frequency and practical project completion rate.

[0029] The student attendance rate is calculated by calculating the percentage of the actual number of class attendances to the total number of courses through the electronic sign-in records of the online learning platform. The timeliness of homework submission is calculated by comparing the homework submission timestamp data of the online learning platform with the preset deadline. The frequency of classroom interaction is calculated by counting the number of valid questions and the number of discussions participated in through the interaction log between the classroom response system and the online discussion area. The average score of the knowledge point test is calculated by calculating the arithmetic mean of the original score data of each knowledge point unit test of the online testing system. The frequency of learning resource use is generated by generating standardized indicators through the learning video viewing time, document download number and simulation experiment startup number of the resource management platform. The completion rate of the practical project is calculated by comparing the phased results acceptance record of the project management system with the task list to calculate the proportion of completed modules.

[0030] The standardized formula is specifically expressed as: , X i Represents the i-th teaching information data, μ represents the historical mean value for the same period, and σ represents the standard deviation of historical data.

[0031] S2: Behavioral characteristic analysis: The standardized teaching information data is subjected to nonlinear feature fusion to generate comprehensive learning behavior indicators, knowledge point test scores, and resource usage frequency data. The adjustment coefficient determined by principal component analysis is combined with logarithmic function, hyperbolic tangent function and ratio function to construct a composite calculation model to quantitatively reflect students' basic learning behavior characteristics.

[0032] The comprehensive learning behavior indicator integrates the standardized attendance rate, homework submission timeliness rate and classroom interaction frequency data through nonlinear combination. The attendance rate data is transformed into a logarithmic form to weaken the influence of extreme values. The homework timeliness rate is saturated by the hyperbolic tangent function. The classroom interaction frequency is treated with a ratio function to reduce the data discreteness. The three types of processed eigenvalues ​​are compound calculated by the adjustment coefficient determined by principal component analysis to form a comprehensive indicator that characterizes the learning behavior characteristics. The base of the logarithmic function is the natural logarithm, the input range of the hyperbolic tangent function is the standardized value range, and the denominator of the ratio function adopts the absolute value smoothing strategy. Finally, the characteristic expression of the multidimensional behavior data is achieved through linear combination.

[0033] The comprehensive learning behavior indicator is specifically expressed as: , AR represents student attendance rate, AT represents the timely submission rate of homework, CI represents the frequency of classroom interaction, and α, β, and γ represent adjustment coefficients.

[0034] S3: Knowledge mastery assessment: By integrating learning behavior characteristic indicators, knowledge point test scores and resource usage frequency data, the students' knowledge mastery of the teaching content is evaluated. The positive correlation between behavioral characteristics and test scores is expressed using a multiplication relationship. Resource usage frequency is introduced as a reverse adjustment factor. The stability of the evaluation results is controlled by an empirically set smoothing constant.

[0035] The knowledge mastery assessment value is based on standardized learning behavior characteristic indicators, knowledge point test scores and learning resource usage frequency data. A multiplication relationship is established between the learning behavior characteristic indicators and the knowledge point test scores to characterize the positive correlation between behavioral performance and knowledge acquisition. The standardized resource usage frequency is introduced as a denominator adjustment term in the calculation formula. By adding an empirically set smoothing constant, division by zero errors are avoided and the influence of resource usage efficiency on the assessment results is controlled, ultimately forming a continuous quantitative indicator reflecting the students' knowledge mastery.

[0036] The knowledge mastery evaluation value is specifically expressed as: , KTS represents the average score of knowledge point test, RU represents the frequency of learning resource use, ε is the smoothing constant, and LBI is the comprehensive learning behavior index.

[0037] S4: Dynamic feedback adjustment: Automatically select the analysis path based on the evaluation results of S3, and direct the data flow to different calculation branches to calculate the learning path analysis indicators based on the knowledge mastery threshold determined by cluster analysis.

[0038] The S4 is based on a comparative analysis of the knowledge mastery assessment value and a preset threshold. When the knowledge mastery assessment value exceeds the demarcation threshold determined by cluster analysis, it enters the high-level capability analysis path, couples the standardized data of the practical project completion with the knowledge mastery assessment value, and superimposes the resource utilization efficiency data corrected by the path adjustment coefficient to participate in the square root synthesis operation; when the knowledge mastery assessment value does not reach the threshold, it enters the basic reinforcement analysis path. The basic reinforcement analysis path uses the sum of the standardized data of attendance rate and homework submission timeliness rate as the numerator, and uses the absolute difference between the frequency of classroom interaction and the knowledge mastery assessment value as the denominator for ratio operation, and implements dimension normalization processing on the denominator through the path adjustment coefficient. Both types of path adjustment coefficients are obtained by fitting and optimizing historical data through the path analysis model.

[0039] The knowledge mastery threshold is marked as θ. When KMA>θ, the learning path analysis indicator is specifically expressed as: ; When KMA≤θ, the learning path analysis indicator is specifically expressed as: , 、 represents the path adjustment coefficient, and PC represents the completion of the practice project.

[0040] S5: Comprehensive evaluation: Based on the path analysis results of S4 and combined with the completion data of practical projects, a teaching effectiveness evaluation index is generated.

[0041] The teaching effectiveness evaluation index is based on the coupling calculation of the learning path analysis index and the practical project completion data. The learning path analysis index output by S4 and the standardized practical project completion are multiplied as the evaluation benchmark. The discreteness adjustment calculation of the absolute difference between the two is introduced in the denominator. The adjustment parameter determined by regression analysis is used to control the impact of the difference on the evaluation result. The maximum value function is used to ensure that the denominator is not lower than the benchmark unit value, and finally a normalized evaluation index is formed that comprehensively reflects the rationality of the learning path selection and the matching degree of the practical results.

[0042] The teaching effect evaluation index is specifically expressed as: ,PC represents the degree of completion of the practice project, λ represents the dispersion adjustment coefficient, and LPA is the learning path analysis indicator.

[0043] S6: Management strategy: Implement precise intervention through threshold-triggered graded warnings, divide resource allocation levels according to the teaching effectiveness evaluation index range, dynamically adjust teaching strategies based on periodic growth rates, and simultaneously generate structured evaluation files for individuals, classes, and semesters.

[0044] The S6 triggers a hierarchical early warning mechanism through preset thresholds, automatically implementing intervention plans for individuals who do not meet the standards; divides resource allocation levels according to the distribution of teaching effectiveness evaluation index, and allocates learning permissions and practical tasks in a differentiated manner; establishes a dynamic adjustment mechanism for teaching plans based on the periodic year-on-year growth rate, and initiates a special review process for abnormally fluctuating groups; and simultaneously generates standardized evaluation files covering individual, class, and semester dimensions for structured storage and traceability analysis of teaching management data, forming a traceable digital file system for teaching management.

[0045] The graded warning mechanism sets a dynamic warning mechanism based on TGI. When the TGI is lower than the historical benchmark value by 80%, the yellow warning system is automatically triggered, and customized knowledge point intensive training content is pushed to the corresponding students; when the TGI falls below the historical benchmark value by 60%, it is upgraded to a red warning, and the teacher is notified to start the interview diagnosis process at the same time.

[0046] The resource allocation hierarchy divides student groups into four resource allocation levels based on TGI distribution. The top 10% of the group automatically obtains access rights to advanced academic resources, the 10%-50% range of groups receives extended practical tasks, the 50%-90% range maintains standard teaching resource allocation, and the bottom 10% of the group activates the learning behavior tracking system. All resource adjustments are automatically distributed and permission controlled through the teaching management platform.

[0047] The dynamic adjustment mechanism analyzes the TGI change rate at the end of each teaching cycle. For groups with a month-on-month increase of more than 15%, the existing teaching plan is maintained and marked as a high-quality path. For groups with a change rate between -5% and 15%, the teaching progress fine-tuning program is initiated. For groups with a decrease of more than 5%, a teaching plan review meeting is automatically initiated.

[0048] The present invention first obtains multi-dimensional data such as student attendance rate, homework submission timeliness rate, classroom interaction frequency, knowledge point test score, learning resource use frequency and practical project completion from the teaching system, eliminates dimensional differences through standardized formulas and establishes a unified data system; then, the standardized attendance rate, homework submission timeliness rate and interaction frequency are subjected to nonlinear feature fusion, and logarithmic transformation, hyperbolic tangent function and ratio function are used to generate comprehensive learning behavior indicators, knowledge point test scores and resource use frequency data; based on this result, the knowledge test score and resource use frequency data are integrated, and the product relationship and the inverse adjustment factor are used to calculate the learning behavior index. Generate a knowledge mastery assessment value; dynamically select an analysis path based on the assessment results; when the preset threshold is exceeded, couple the practical project completion to conduct a high-level capability analysis; if the standard is not met, implement a basic reinforcement analysis through the difference in attendance rate, homework timeliness and interaction frequency; generate a teaching effectiveness evaluation index based on the path analysis results combined with the practical project data, and ultimately trigger a customized intervention plan through a graded early warning mechanism, divide the resource allocation level according to the index range and dynamically adjust the teaching strategy, and simultaneously build a structured evaluation file covering individual, class, and semester dimensions to achieve intelligent regulation and precise decision-making support for the entire teaching management process.

[0049] Secondly: The drawings of the embodiments disclosed in the present invention only involve structures related to the embodiments disclosed in the present invention. Other structures may refer to conventional designs. The same embodiment and different embodiments of the present invention may be combined with each other without conflict. Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A teaching information management method based on big data, characterized in that: include: S1: Data collection: Obtain teaching information data from the teaching system, eliminate dimensional differences through standardized formulas, use historical mean and standard deviation to normalize the original data, and establish a unified dimensional system; S2: Behavioral Characteristics Analysis: The standardized teaching information data is subjected to nonlinear feature fusion to generate comprehensive learning behavior indicators, knowledge point test scores, and resource usage frequency data. The adjustment coefficient determined by principal component analysis is combined with the logarithmic function, hyperbolic tangent function, and ratio function to construct a composite calculation model to quantitatively reflect the basic learning behavior characteristics of students. S3: Knowledge Mastery Assessment: This method integrates learning behavior characteristic indicators, knowledge point test scores, and resource usage frequency data to assess students' knowledge mastery of the teaching content. A multiplicative relationship is used to express the positive correlation between behavior characteristics and test scores. Resource usage frequency is introduced as an inverse adjustment factor, and the stability of the assessment results is controlled by an empirically set smoothing constant. S4: Dynamic feedback regulation: Automatically selects the analysis path based on the evaluation results of S3, and directs the data flow to different calculation branches to calculate the learning path analysis indicators through the knowledge mastery threshold determined by cluster analysis; S5: Comprehensive evaluation: Based on the path analysis results of S4 and the completion data of practical projects, a teaching effectiveness evaluation index is generated; S6: Management strategy: Implement precise intervention through threshold-triggered graded warnings, divide resource allocation levels according to the teaching effectiveness evaluation index range, dynamically adjust teaching strategies based on periodic growth rates, and simultaneously generate structured evaluation files for individuals, classes, and semesters.

2. The teaching information management method based on big data according to claim 1, characterized in that: The teaching system includes an online learning platform, a classroom response system, an online testing system, a resource management platform and a project management system, among which: The online learning platform is used to manage assignment submissions and record timestamp data; The classroom response system and online discussion forum are used to collect the frequency of classroom interactions and the number of valid questions; The online testing system is used to implement knowledge point unit tests and store original scores; The resource management platform is used to collect statistics on learning resource usage behavior; The project management system is used to track the completion progress of the practical project modules; The teaching information data includes student attendance rate, homework submission timeliness rate, classroom interaction frequency, knowledge point test average score, learning resource usage frequency and practical project completion rate.

3. The teaching information management method based on big data according to claim 2, characterized in that: The student attendance rate is calculated by calculating the percentage of the actual number of class attendances to the total number of courses through the electronic sign-in records of the online learning platform. The timeliness of homework submission is calculated by comparing the homework submission timestamp data of the online learning platform with the preset deadline. The frequency of classroom interaction is calculated by counting the number of valid questions and the number of discussions participated in through the interaction log between the classroom response system and the online discussion area. The average score of the knowledge point test is calculated by calculating the arithmetic mean of the original score data of each knowledge point unit test of the online testing system. The frequency of learning resource use is generated by generating standardized indicators through the learning video viewing time, document download number and simulation experiment startup number of the resource management platform. The completion rate of the practical project is calculated by comparing the phased results acceptance record of the project management system with the task list to calculate the proportion of completed modules.

4. The teaching information management method based on big data according to claim 1, characterized in that: The comprehensive learning behavior indicator integrates the standardized attendance rate, homework submission timeliness rate and classroom interaction frequency data through nonlinear combination. The attendance rate data is transformed into a logarithmic form to weaken the influence of extreme values. The homework timeliness rate is saturated by the hyperbolic tangent function. The classroom interaction frequency is treated with a ratio function to reduce the data discreteness. The three types of processed eigenvalues ​​are compound calculated by the adjustment coefficient determined by principal component analysis to form a comprehensive indicator that characterizes the learning behavior characteristics. The base of the logarithmic function is the natural logarithm, the input range of the hyperbolic tangent function is the standardized value range, and the denominator of the ratio function adopts the absolute value smoothing strategy. Finally, the characteristic expression of the multidimensional behavior data is achieved through linear combination.

5. The teaching information management method based on big data according to claim 1, characterized in that: The knowledge mastery assessment value is based on standardized learning behavior characteristic indicators, knowledge point test scores and learning resource usage frequency data. A multiplication relationship is established between the learning behavior characteristic indicators and the knowledge point test scores to characterize the positive correlation between behavioral performance and knowledge acquisition. The standardized resource usage frequency is introduced as a denominator adjustment term in the calculation formula. By adding an empirically set smoothing constant, division by zero errors are avoided and the influence of resource usage efficiency on the assessment results is controlled, ultimately forming a continuous quantitative indicator reflecting the students' knowledge mastery.

6. The teaching information management method based on big data according to claim 1, characterized in that: The S4 is based on a comparative analysis of the knowledge mastery assessment value and a preset threshold. When the knowledge mastery assessment value exceeds the demarcation threshold determined by cluster analysis, it enters the high-level capability analysis path, couples the standardized data of the practical project completion with the knowledge mastery assessment value, and superimposes the resource utilization efficiency data corrected by the path adjustment coefficient to participate in the square root synthesis operation; when the knowledge mastery assessment value does not reach the threshold, it enters the basic reinforcement analysis path. The basic reinforcement analysis path uses the sum of the standardized data of attendance rate and homework submission timeliness rate as the numerator, and uses the absolute difference between the frequency of classroom interaction and the knowledge mastery assessment value as the denominator for ratio operation, and implements dimension normalization processing on the denominator through the path adjustment coefficient. Both types of path adjustment coefficients are obtained by fitting and optimizing historical data through the path analysis model.

7. The teaching information management method based on big data according to claim 1, characterized in that: The teaching effectiveness evaluation index is based on the coupling calculation of the learning path analysis index and the practical project completion data. The learning path analysis index output by S4 and the standardized practical project completion are multiplied as the evaluation benchmark. The discreteness adjustment calculation of the absolute difference between the two is introduced in the denominator. The adjustment parameter determined by regression analysis is used to control the impact of the difference on the evaluation result. The maximum value function is used to ensure that the denominator is not lower than the benchmark unit value, and finally a normalized evaluation index is formed that comprehensively reflects the rationality of the learning path selection and the matching degree of the practical results.

8. The teaching information management method based on big data according to claim 1, characterized in that: The S6 triggers a hierarchical early warning mechanism through preset thresholds, automatically implementing intervention plans for individuals who fail to meet the standards; divides resource allocation levels according to the distribution of teaching effect evaluation indexes, and allocates learning permissions and practical tasks in a differentiated manner; establishes a dynamic adjustment mechanism for teaching plans based on the periodic month-on-month growth rate, and initiates a special review process for groups with abnormal fluctuations; Standardized assessment files covering individual, class, and semester dimensions are generated simultaneously for structured storage and traceability analysis of teaching management data, forming a traceable digital archive system for teaching management.

9. The teaching information management method based on big data according to claim 8, characterized in that: The graded warning mechanism sets a dynamic warning mechanism based on TGI. When TGI falls below 80% of the historical benchmark value, the yellow warning system is automatically triggered, and customized knowledge point reinforcement training content is pushed to the corresponding students. When the TGI falls below 60% of the historical benchmark, it is upgraded to a red alert, and the teacher is notified to initiate the interview diagnosis process; The resource allocation hierarchy divides student groups into four resource allocation tiers based on TGI distribution. The top 10% of the group automatically obtains access to advanced academic resources, the 10%-50% range of groups receives expanded practical tasks, the 50%-90% range maintains standard teaching resource allocation, and the bottom 10% of the group activates the learning behavior tracking system. All resource adjustments are automatically distributed and controlled through the teaching management platform. The dynamic adjustment mechanism analyzes the TGI change rate at the end of each teaching cycle. For groups with a month-on-month increase of more than 15%, the existing teaching plan is maintained and marked as a high-quality path. For groups with a change rate between -5% and 15%, the teaching progress fine-tuning program is initiated. For groups with a decrease of more than 5%, a teaching plan review meeting is automatically initiated.

Images