Information analysis method and system based on student data traceability

Abstract

The invention relates to the technical field of information analysis, in particular to an information analysis method and system based on student data traceability. The method comprises the following steps: acquiring a student subject learning quality data set; performing data preprocessing on the student subject learning quality data set to generate a subject learning quality preprocessing data set; performing influence factor screening on the subject learning quality preprocessing data set according to a preset regression analysis model to generate subject influence related factors; utilizing a Fahrenheit combination interval analysis method to carry out deep interval analysis on the subject influence correlation factors, and generating a student subject learning quality strategy; therefore, through influence factor analysis and strategy adjustment of the system, the problem that a traditional education analysis method is lack of individuation and dynamic adjustment is solved, and the scientificity and the implementation effect of education decision making are improved.

Description

Technical Field

[0001] The present invention relates to the field of information analysis technology, and in particular to an information analysis method and system based on student data tracing. Background Art

[0002] In the current field of educational data analysis, although a variety of information analysis methods and systems have been proposed, there are still significant deficiencies. Many existing technologies lack in-depth mining of individual student data, often only focusing on macro data, while ignoring key factors such as individual learning behavior and motivation, resulting in an incomplete understanding of student learning. Secondly, when dealing with missing values ​​and outliers, existing methods use simple interpolation or mean filling methods, which fail to effectively reflect the real learning status of students. In addition, the technology does not respond sufficiently to the dynamic changes of data, and many systems fail to update data analysis results in real time, resulting in delayed strategy adjustments and inability to adapt to the rapid changes in student learning. Most existing information analysis systems rely on linear models and traditional statistical analysis, and fail to make full use of modern machine learning and data mining technologies, which limits their prediction accuracy and scope of application. At the same time, many systems lack flexible visualization tools, making it difficult to transform complex data results into intuitive and easy-to-understand forms, making it difficult for educators to grasp the meaning behind the data when making decisions. Finally, insufficient data sharing and cross-platform integration capabilities make it impossible to effectively combine data from different sources, limiting the depth and breadth of comprehensive analysis, thereby affecting the rational allocation and utilization efficiency of educational resources. Summary of the invention

[0003] Based on this, it is necessary to provide an information analysis method and system based on student data tracing to solve at least one of the above technical problems.

[0004] To achieve the above purpose, an information analysis method based on student data tracing is provided, the method comprising the following steps:

[0005] Step S1: obtaining a student subject learning quality data set; performing data preprocessing on the student subject learning quality data set to generate a subject learning quality preprocessing data set;

[0006] Step S2: Screen the influencing factors of the subject learning quality preprocessing data set according to the preset regression analysis model to generate subject influence related factors; use the Wahrenheit combined interval analysis method to conduct in-depth interval analysis on the subject influence related factors to generate student subject learning quality strategies;

[0007] Step S3: Perform statistical analysis based on the student subject learning quality strategy, and use visualization tools to visualize and generate a student data traceability information report;

[0008] Step S4: Adjust the student subject learning quality strategy based on the student data traceability information report to generate a student subject learning quality adjustment data set; use the student subject learning quality adjustment data set to iterate the student subject learning quality data set, thereby completing the learning analysis task of student data traceability.

[0009] The beneficial effect of the present invention is that the student subject learning quality data set is obtained and preprocessed to ensure the integrity and accuracy of the data, laying a solid foundation for subsequent analysis. This process ensures that the generated subject learning quality preprocessing data set has good quality by removing noise data and outliers, so that the subsequent analysis can be more credible and effective. In step S2, the preset regression analysis model is applied to screen the influencing factors of the data set to generate subject influence related factors, which reflects the idea of ​​data-driven decision-making and can reveal the key factors that have a greater impact on the quality of student subject learning, which provides a practical and feasible guidance basis for teachers and education managers. In addition, the deep interval analysis of these influencing factors is carried out by the Fahrenheit combined interval analysis method, which further refines the strategy formulation for subject learning quality, so that students in different intervals can get personalized learning suggestions and strategies, and this targeting significantly improves the effectiveness of intervention measures. Through the combination of statistical analysis and visualization tools, the generated student data traceability information report not only provides an intuitive result display, but also provides detailed data support for subsequent strategy adjustments. The visualized results make complex data relationships easy to understand, promote communication and cooperation between teachers and managers, and promote the scientific and systematic decision-making of education. Finally, step S4 ensures continuous attention and improvement to the quality of students' subject learning through strategy adjustment and iterative analysis based on student data traceability information reports. This iterative process not only continuously optimizes the adjustment measures, but also provides a basis and guarantee for the personalized development of education and teaching. In summary, the present invention effectively solves the problems caused by the lack of in-depth analysis and personalized strategy formulation in traditional education analysis by constructing a systematic data analysis process, and improves the pertinence and effectiveness of educational intervention. Therefore, the present invention solves the problem of lack of personalization and dynamic adjustment in traditional education analysis methods through systematic analysis of influencing factors and strategy adjustment, and improves the scientific nature and implementation effect of educational decision-making.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: Obtaining student subject learning quality dataset;

[0012] Step S12: interpolate missing values ​​of the student subject learning quality data set to generate a student subject missing value processing data set; perform time series smoothing on the student subject missing value processing data set to generate a student subject time trend data set;

[0013] Step S13: Perform data standardization processing on the student subject time trend dataset to generate a subject learning quality preprocessing dataset.

[0014] The present invention lays the foundation for subsequent analysis by acquiring a student subject learning quality data set. This process not only ensures the comprehensiveness of the data, but also provides the necessary raw materials for in-depth research. By interpolating the student subject learning quality data set to fill in the missing values, a student subject missing value processing data set is generated. This link is crucial because missing data often leads to deviations and misleading analysis results, thereby affecting the effectiveness of educational decision-making. In addition, interpolation processing can provide a more coherent data stream while retaining data features, providing a more stable basis for subsequent analysis. The student subject missing value processing data set is subjected to time series smoothing processing to generate a student subject time trend data set. The introduction of time series smoothing effectively eliminates potential random fluctuations in the data, thereby better revealing the potential trends and laws of subject learning quality. This not only helps educators identify long-term changes in student learning conditions, but also provides a basis for formulating targeted teaching intervention measures. Further data standardization processing is performed on the student subject time trend data set to generate a subject learning quality preprocessing data set. The core of this step is to eliminate the influence of different dimensions on the analysis results and ensure that subsequent analysis can be carried out under a unified standard. Data standardization not only improves the comparability of analysis results, but also lays a solid foundation for the use of various machine learning and statistical models, making model training and verification more efficient and accurate.

[0015] Preferably, step S2 comprises the following steps:

[0016] Step S21: Screening the influencing factors of the subject learning quality preprocessing data set according to the preset regression analysis model to generate subject influence related factors, where the subject influence factors include student personal information, learning behavior data, learning motivation, academic expectation data and test score data;

[0017] Step S22: quantify the data according to the learning motivation to obtain the learning motivation data; map the learning behavior data and the learning motivation data to rectangular coordinate intervals to generate the subject influence coordinate data; construct a rectangular coordinate system for the subject influence coordinate data using the Fahrenheit combined interval analysis method to generate the Fahrenheit combined interval two-dimensional graph; perform deep interval analysis based on the Fahrenheit combined interval two-dimensional graph to generate the Fahrenheit subject combination interval data;

[0018] Step S23: Generate subject quality strategies for Huashi subject combination interval data based on student personal information, and generate student subject learning quality strategies, wherein the student subject learning quality strategies include high academic expectations-performance targeting strategies, medium academic expectations-performance targeting strategies and low academic expectations-performance targeting strategies.

[0019] The present invention screens the influencing factors of the subject learning quality preprocessing data set based on a preset regression analysis model, and generates subject influence-related factors, covering student personal information, learning behavior data, learning motivation, academic expectation data and test score data. This process ensures that the selected factors can fully reflect the multidimensional characteristics of the student learning process, making the subsequent analysis more representative and scientific. By performing data quantification processing on learning motivation, learning motivation data that can be used for subsequent analysis is obtained. The key to this link is to convert abstract learning motivation into quantifiable indicators, thereby providing a more solid foundation for data analysis. The learning behavior data and the learning motivation data are mapped to rectangular coordinate intervals to generate subject influence coordinate data. This process not only promotes the effective combination of different data dimensions, but also enables the subsequent Wahrenheit combined interval analysis method to be carried out in a more logical and systematic framework. The original Wahrenheit combined interval analysis method generates a Wahrenheit combined interval two-dimensional graph by constructing a rectangular coordinate system for the subject influence coordinate data, providing a visual basis for analysis. Based on the two-dimensional graph, a deep interval analysis is performed to generate Wahrenheit subject combination interval data, so that educators can intuitively identify the performance of different influencing factors in learning quality. This process not only enhances the depth of analysis, but also provides data support for the formulation of targeted educational strategies. Based on the personal information of students, the subject quality strategy is generated for the Huashi subject combination interval data, and the student subject learning quality strategies including high academic expectations-grade targeted strategies, medium academic expectations-grade targeted strategies and low academic expectations-grade targeted strategies are obtained. The formulation of these strategies not only reflects the accuracy of data analysis, but also provides educators with practical intervention measures, which helps to formulate personalized learning plans for students with different academic expectation levels, thereby improving the overall educational effect.

[0020] Preferably, step S21 includes the following steps:

[0021] Step S211: using the subject learning quality preprocessing data set as an input variable to the preset linear regression model to screen the influencing factors and generate linear regression screening data; using the Pearson correlation coefficient to construct a correlation matrix for the linear regression screening data and generate a Pearson correlation factor matrix; performing multicollinearity elimination on the Pearson correlation factor matrix and generating subject influencing factor data;

[0022] Step S212: perform dimensionality reduction processing on the subject influence factor data by principal component analysis to generate a key influence factor set; generate regression coefficients for the key influence factor set to generate a subject influence factor regression coefficient set; sort the subject influence factor regression coefficient set by absolute value contribution to generate subject influence coefficient sorting data;

[0023] Step S213: perform verification test on the subject influence coefficient ranking data to generate subject influence coefficient verification data; eliminate invalid values ​​from the influence coefficient verification data based on a preset influence screening dynamic threshold to generate subject influence related factors, where the subject influence related factors include student personal information, learning behavior data, learning motivation, academic expectation data and test score data.

[0024] The present invention uses the subject learning quality preprocessing data set as an input variable to the preset linear regression model. This process not only helps to identify potential influencing factors, but also lays a solid foundation for subsequent analysis. After generating linear regression screening data, the correlation matrix is ​​constructed using the Pearson correlation coefficient, which can reveal the linear relationship between the variables, which provides a clear perspective for understanding the impact of different factors on learning quality. By eliminating multicollinearity in the correlation matrix, redundant information can be effectively removed to generate subject influencing factor data. This process ensures the pertinence and scientificity of subsequent analysis. Generate a set of subject influencing factor regression coefficients, and sort the absolute value contribution of the regression coefficients to clearly identify the relative importance of each influencing factor in the subject learning quality. This provides data support for the subsequent formulation of improvement measures, allowing educators to focus on the most influential factors, thereby more effectively improving students' learning quality. In addition, the generated subject influence coefficient ranking data provides a clear direction for subsequent research, making the analysis process more logical and hierarchical. By eliminating invalid values ​​from the subject influence coefficient ranking data based on the preset influence screening dynamic threshold, it is ensured that the subject influence related factors finally obtained have good representativeness and effectiveness. The implementation of this process resulted in the final selection of influencing factors, including student personal information, learning behavior data, learning motivation, academic expectations data, and test score data, forming a comprehensive and systematic influencing factor framework. By integrating these factors, educators can have a deeper understanding of the multidimensional factors that affect the quality of subject learning, and thus develop more targeted educational strategies.

[0025] Preferably, the deep interval analysis based on the Fahrenheit combined interval two-dimensional graph includes the following steps:

[0026] Based on the academic expectation data as the X axis and the test score data as the Y axis, a rectangular coordinate system is constructed to obtain the Fahrenheit rectangular coordinate system;

[0027] The learning behavior data and learning motivation data were averaged to obtain the Fahrenheit mean data;

[0028] According to the Fahrenheit mean data and the given 0.67 standard deviation, the X axis and Y axis are divided into three intervals, and the X axis interval and Y axis interval are obtained, wherein the X axis interval includes the low academic expectation interval, the medium academic expectation interval and the high academic expectation interval, and the Y axis interval includes the low achievement interval, the medium achievement interval and the high achievement interval;

[0029] By pairing the X-axis interval and the Y-axis interval, we can obtain the Huashi subject combination interval data, which includes high academic expectation-performance data, middle academic expectation-performance data and low academic expectation-performance data.

[0030] The present invention provides an effective visualization tool and data basis for analyzing the quality of students' subject learning by systematically constructing a rectangular coordinate system for academic expectation data and test score data. First, the rectangular coordinate system with academic expectation data as the X axis and test score data as the Y axis is constructed, which not only clearly shows the relationship between the two, but also lays the foundation for subsequent analysis. By calculating the mean of learning behavior data and learning motivation data, the Fahrenheit mean data obtained further enhances the representativeness of the data, so that the learning characteristics of different students under the same academic expectations and performance levels can be quantified and compared. According to the Fahrenheit mean data and the given 0.67 standard deviation, the X axis and the Y axis are divided into intervals, and the academic expectations and test scores are divided into three intervals of low, medium and high, respectively, which not only makes the data structure clearer, but also can effectively reveal the performance of students under different academic expectation levels. Such interval division provides a clear entry point for subsequent in-depth analysis, so that students in different intervals can be accurately positioned in the interactive influence of academic expectations and test scores. In the process of interval matching, the generation of Huashi subject combination interval data enables effective identification of student groups with different combinations of academic expectations and test scores. Through the systematic analysis of high academic expectations-scores, medium academic expectations-scores, and low academic expectations-scores, targeted guidance strategies can be provided to educators. This data-based combination analysis not only improves the sophistication of the research, but also makes the teaching intervention measures for different student groups more operational and effective, thereby promoting the scientific and intelligent decision-making of education.

[0031] Preferably, step S23 includes the following steps:

[0032] Step S231: performing academic performance discrimination calculations on the high academic expectation-performance data, the middle academic expectation-performance data, and the low academic expectation-performance data based on the student's personal information, and generating high academic expectation-performance discrimination results, middle academic expectation-performance discrimination results, and low academic expectation-performance discrimination results;

[0033] Step S232: When the high academic expectation-grade discrimination result is less than or equal to the preset grade discrimination value, the learning time is extracted from the learning behavior data, and the learning time is compared with the average learning time data to generate high academic expectation-low grade learning time comparison data; if the high academic expectation-low grade learning time comparison data is greater than the average learning time data, the learning time is increased, and the behavior is motivated in combination with the learning motivation; when the high academic expectation-grade discrimination result is greater than the preset grade discrimination value, the student's personal information is highlighted, and the competition question data is generated and pushed, thereby completing the high academic expectation-grade targeted strategy;

[0034] Step S233: when the academic expectation-grade discrimination result is less than or equal to the preset grade discrimination value, the review frequency and homework completion status of the learning behavior data are extracted to generate the academic expectation-grade review frequency data and the academic expectation-grade homework completion status data; the academic expectation-grade homework completion status data of the middle school is subjected to big data data mining to generate the academic expectation-grade weak data of the middle school; the academic expectation-grade review frequency data of the middle school is used to perform targeted optimization on the academic expectation-grade weak data of the middle school; when the academic expectation-grade discrimination result is greater than the preset grade discrimination value, a confidence strengthening plan is generated for the student's personal information based on the cloud platform, thereby completing the academic expectation-grade targeted strategy of the middle school;

[0035] Step S234: When the low academic expectation-grade discrimination result is less than or equal to the preset grade discrimination value, a learning disability analysis is performed on the learning behavior data to generate low academic expectation-grade learning disability data; a learning time detection is performed on the low academic expectation-grade learning disability data to generate learning time deficiency data; based on the learning motivation data, learning support remedial processing is performed on the learning time deficiency data and the low academic expectation-grade learning disability data; when the low academic expectation-grade discrimination result is greater than the preset grade discrimination value, personalized motivation enhancement processing is performed on the learning motivation data to generate a low academic expectation-grade personalized motivation plan, thereby completing the low academic expectation-grade targeted strategy.

[0036] The present invention can clearly identify the performance of students under different academic expectation levels by distinguishing and calculating the performance of students with high academic expectations, middle academic expectations and low academic expectations. This discrimination not only provides educators with quantitative indicators to help them accurately locate the specific problems that students have in the learning process, but also makes subsequent intervention measures more targeted and effective. In the case where the high academic expectation-performance discrimination result is less than or equal to the preset performance discrimination value, the method of extracting the learning time data and comparing it with the average learning time reveals the shortcomings of students with high expectations but low performance in learning time, thereby providing a data basis for formulating a strategy to increase the learning time. In addition, by combining learning motivation for behavioral incentives, students' learning enthusiasm can be further enhanced and their learning effects can be improved. Similarly, at the level of middle academic expectations, by analyzing the review frequency and homework completion, and using big data mining technology to identify weak links, targeted optimization measures can be formed to help students improve their academic level. For students with low academic expectations, through learning obstacle analysis and learning time detection, they can have a deep understanding of the difficulties they encounter in the learning process, so as to help these students overcome learning obstacles through learning support remedial measures generated based on data. In addition, personalized motivation enhancement processing can effectively improve students' learning motivation and encourage them to participate more actively in the learning process. In summary, this series of strategy adjustments based on data analysis not only realizes real-time monitoring and feedback of students' learning status, but also provides a solid foundation for the formulation of personalized educational intervention measures, maximizes the application value of data, and improves the pertinence and effectiveness of education.

[0037] Preferably, step S3 comprises the following steps:

[0038] Step S31: Obtaining benchmark data; performing statistical analysis based on the student subject learning quality strategy to generate student subject learning statistical data;

[0039] Step S32: Compare the change trend of the student subject learning statistics data with the benchmark data to generate the student subject learning change trend data;

[0040] Step S33: Use a visualization analysis tool to visualize the student subject learning change trend data and generate a student subject learning change graph; perform a visualization result analysis on the student subject learning change graph, and generate a traceability report to generate a student data traceability information report.

[0041] The present invention can construct a quantitative evaluation standard by obtaining benchmark data and combining it with the student subject learning quality strategy for statistical analysis. This process enables educators to clearly understand the students' learning status and provide data support for subsequent educational intervention measures through the generated student subject learning statistical data. Next, the change trend of the student subject learning statistical data is compared with the benchmark data, which can not only reveal the improvement of the student's learning effect, but also clarify the actual effect of different educational strategies. The generation of this change trend helps educators evaluate the effectiveness of educational strategies and adjust teaching methods in time to meet students' learning needs. The use of visual analysis tools to visualize the student subject learning change trend data further enhances the intuitiveness and understandability of data interpretation. By generating a student subject learning change graph, educators can quickly identify key trends and abnormal points in the learning process, so as to take targeted measures to intervene. This visualization result analysis not only provides teachers with a data-driven decision-making basis, but also provides students and their parents with intuitive learning feedback, which helps to enhance their learning confidence and enthusiasm. Finally, through the generation of a traceability report, a comprehensive summary of students' learning changes and the reasons behind them can be made, thereby providing systematic advice and guidance for future learning planning. In summary, this series of steps based on data analysis and visualization not only improves the efficiency of monitoring the quality of students' subject learning, but also provides a scientific basis for the formulation of personalized education plans.

[0042] Preferably, step S4 comprises the following steps:

[0043] Step S41: conducting a student subject learning quality strategy assessment based on the student data traceability information report, and generating a student subject learning quality assessment strategy;

[0044] Step S42: adjusting and generating a data set for the student subject learning quality assessment strategy to generate a student subject learning quality adjustment data set;

[0045] Step S43: Use the student subject learning quality adjustment data set to iterate the student subject learning quality data set, thereby completing the learning analysis task of student data tracing.

[0046] The present invention can not only comprehensively analyze the performance of students in the learning process, but also accurately identify the key factors affecting the learning quality through the learning quality strategy evaluation based on the student data traceability information report. The generation of this strategy evaluation enables educators to effectively reflect and optimize the current education strategy based on specific data support, so as to better meet the personalized learning needs of students. The adjustment and generation of the student subject learning quality evaluation strategy further enhances the dynamic response ability of educational data. Through the adjustment of the evaluation strategy, educators can flexibly respond to the learning characteristics and needs of different student groups and formulate more accurate and effective learning support measures. This process not only improves the scientific nature of educational decision-making, but also enhances the adaptability of educational practice, and can maintain high efficiency in a constantly changing educational environment. The original learning quality data set is iterated using the student subject learning quality adjustment data set, which reflects the important role of data in the education feedback loop. Through this iteration, educators can update the feedback information of students' learning situation in real time to ensure the continuous optimization and adjustment of teaching strategies. This dynamic feedback mechanism enables the quality of education to be continuously improved, and provides students with more flexible and effective learning support, which helps to improve students' learning efficiency and overall academic performance.

[0047] Preferably, step S43 includes the following steps:

[0048] Step S431: using the student subject learning quality adjustment data set to perform data set comparison with the student subject learning quality data set to generate a student subject learning quality comparison data set;

[0049] Step S432: performing an update iterative analysis on the student subject learning quality comparison data set to generate a student subject learning quality iteration result;

[0050] Step S433: Dynamically adjust the student subject learning quality strategy based on the iterative results of the student subject learning quality, thereby completing the learning analysis task of student data tracing.

[0051] The present invention provides data-based decision support for educators by comparing the student subject learning quality adjustment data set with the original data set to generate a student subject learning quality comparison data set. This process allows educators to clearly identify the changing trend of students' learning quality and the reasons behind it, providing an objective basis for subsequent teaching strategy adjustments. The updated iterative analysis of the student subject learning quality comparison data set not only enhances the real-time performance of data processing, but also dynamically reflects the changes in students' performance during the learning process. Through this iterative analysis, educators can timely grasp the fluctuations in students' learning quality and then intervene in existing problems in a timely manner. This data-based dynamic feedback mechanism ensures that teaching adjustments can be flexibly changed according to actual conditions and improves the adaptability of educational strategies. Finally, the process of dynamically adjusting strategies based on the iterative results of student subject learning quality enables educators to continuously optimize teaching methods and improve teaching quality in practice. This dynamic adjustment process enables students' learning paths and learning strategies to be optimized in real time according to data feedback, ensuring that educational measures are always guided by students' actual needs, thereby improving learning effects and learning efficiency.

[0052] In this specification, an information analysis system based on student data tracing is provided, which is used to execute the above-mentioned information analysis method based on student data tracing. The information analysis system based on student data tracing includes:

[0053] Data acquisition and preprocessing module: used to acquire students' subject learning quality data set; perform data preprocessing on students' subject learning quality data set to generate subject learning quality preprocessing data set;

[0054] Influencing factor screening and analysis module: used to screen the influencing factors of the subject learning quality preprocessing data set according to the preset regression analysis model, and generate subject influence related factors; use the Huaren combined interval analysis method to conduct in-depth interval analysis on subject influence related factors, and generate student subject learning quality strategies;

[0055] Statistical analysis and visualization module: used to perform statistical analysis based on student subject learning quality strategies, and use visualization tools for visualization to generate student data traceability information reports;

[0056] Strategy adjustment and iteration module: used to adjust the student subject learning quality strategy based on the student data traceability information report and generate a student subject learning quality adjustment data set; use the student subject learning quality adjustment data set to iterate the student subject learning quality data set, thereby completing the learning analysis task of student data traceability.

[0057] The beneficial effect of the present invention is that the student subject learning quality data set is obtained and preprocessed to ensure the integrity and accuracy of the data, laying a solid foundation for subsequent analysis. This process ensures that the generated subject learning quality preprocessing data set has good quality by removing noise data and outliers, so that the subsequent analysis can be more credible and effective. In step S2, the preset regression analysis model is applied to screen the influencing factors of the data set to generate subject influence related factors, which reflects the idea of ​​data-driven decision-making and can reveal the key factors that have a greater impact on the quality of student subject learning, which provides a practical and feasible guidance basis for teachers and education managers. In addition, the deep interval analysis of these influencing factors is carried out by the Fahrenheit combined interval analysis method, which further refines the strategy formulation for subject learning quality, so that students in different intervals can get personalized learning suggestions and strategies, and this targeting significantly improves the effectiveness of intervention measures. Through the combination of statistical analysis and visualization tools, the generated student data traceability information report not only provides an intuitive result display, but also provides detailed data support for subsequent strategy adjustments. The visualized results make complex data relationships easy to understand, promote communication and cooperation between teachers and managers, and promote the scientific and systematic decision-making of education. Finally, step S4 ensures continuous attention and improvement to the quality of students' subject learning through strategy adjustment and iterative analysis based on student data traceability information reports. This iterative process not only continuously optimizes the adjustment measures, but also provides a basis and guarantee for the personalized development of education and teaching. In summary, the present invention effectively solves the problems caused by the lack of in-depth analysis and personalized strategy formulation in traditional education analysis by constructing a systematic data analysis process, and improves the pertinence and effectiveness of educational intervention. Therefore, the present invention solves the problem of lack of personalization and dynamic adjustment in traditional education analysis methods through systematic analysis of influencing factors and strategy adjustment, and improves the scientific nature and implementation effect of educational decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a flowchart of the steps of an information analysis method based on student data tracing;

[0059] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0060] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0061] Figure 4 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0062] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0063] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0064] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0065] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0066] To achieve this, please refer to Figures 1 to 4 , an information analysis method based on student data tracing, the method comprising the following steps:

[0067] Step S1: obtaining a student subject learning quality data set; performing data preprocessing on the student subject learning quality data set to generate a subject learning quality preprocessing data set;

[0068] Step S2: Screen the influencing factors of the subject learning quality preprocessing data set according to the preset regression analysis model to generate subject influence related factors; use the Wahrenheit combined interval analysis method to conduct in-depth interval analysis on the subject influence related factors to generate student subject learning quality strategies;

[0069] Step S3: Perform statistical analysis based on the student subject learning quality strategy, and use visualization tools to visualize and generate a student data traceability information report;

[0070] Step S4: Adjust the student subject learning quality strategy based on the student data traceability information report to generate a student subject learning quality adjustment data set; use the student subject learning quality adjustment data set to iterate the student subject learning quality data set, thereby completing the learning analysis task of student data traceability.

[0071] The beneficial effect of the present invention is that the student subject learning quality data set is obtained and preprocessed to ensure the integrity and accuracy of the data, laying a solid foundation for subsequent analysis. This process ensures that the generated subject learning quality preprocessing data set has good quality by removing noise data and outliers, so that the subsequent analysis can be more credible and effective. In step S2, the preset regression analysis model is applied to screen the influencing factors of the data set to generate subject influence related factors, which reflects the idea of ​​data-driven decision-making and can reveal the key factors that have a greater impact on the quality of student subject learning, which provides a practical and feasible guidance basis for teachers and education managers. In addition, the deep interval analysis of these influencing factors is carried out by the Fahrenheit combined interval analysis method, which further refines the strategy formulation for subject learning quality, so that students in different intervals can get personalized learning suggestions and strategies, and this targeting significantly improves the effectiveness of intervention measures. Through the combination of statistical analysis and visualization tools, the generated student data traceability information report not only provides an intuitive result display, but also provides detailed data support for subsequent strategy adjustments. The visualized results make complex data relationships easy to understand, promote communication and cooperation between teachers and managers, and promote the scientific and systematic decision-making of education. Finally, step S4 ensures continuous attention and improvement to the quality of students' subject learning through strategy adjustment and iterative analysis based on student data traceability information reports. This iterative process not only continuously optimizes the adjustment measures, but also provides a basis and guarantee for the personalized development of education and teaching. In summary, the present invention effectively solves the problems caused by the lack of in-depth analysis and personalized strategy formulation in traditional education analysis by constructing a systematic data analysis process, and improves the pertinence and effectiveness of educational intervention. Therefore, the present invention solves the problem of lack of personalization and dynamic adjustment in traditional education analysis methods through systematic analysis of influencing factors and strategy adjustment, and improves the scientific nature and implementation effect of educational decision-making.

[0072] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of an information analysis method based on student data tracing of the present invention. In this example, the information analysis method based on student data tracing includes the following steps:

[0073] Step S1: obtaining a student subject learning quality data set; performing data preprocessing on the student subject learning quality data set to generate a subject learning quality preprocessing data set;

[0074] In an embodiment of the present invention, the data set obtained is derived from the student's daily learning records, test scores, data on participation in activities, and other relevant background information. These data are missing, abnormal or inconsistent during the collection process, so the pre-processing of the data is crucial. The first step in data pre-processing is missing value processing, which can be achieved by various methods such as interpolation, mean filling or nearest neighbor filling, aiming to ensure the integrity and continuity of the data set. Proper handling of missing values ​​can effectively reduce the deviation in data analysis and improve the credibility of subsequent analysis. Then, the data is detected and processed for outliers, using box plots or Z-score methods to identify and eliminate those values ​​that are obviously deviated from the normal range, thereby ensuring the quality of the data. In addition, data standardization and normalization are also key links in pre-processing. This step can be performed by Z-score standardization or Min-Max normalization methods, with the purpose of converting data of different dimensions to the same standard to avoid analytical deviations caused by different dimensions.

[0075] Step S2: Screen the influencing factors of the subject learning quality preprocessing data set according to the preset regression analysis model to generate subject influence related factors; use the Wahrenheit combined interval analysis method to conduct in-depth interval analysis on the subject influence related factors to generate student subject learning quality strategies;

[0076] In the embodiment of the present invention, according to the preset regression analysis model, regression analysis is performed on multiple variables in the data set to identify the key factors affecting the learning quality of students. This process uses models such as linear regression, logistic regression or ridge regression to screen out statistically significant influencing factors by evaluating the regression coefficient and significance level of each variable. This not only enables researchers to quantitatively evaluate the degree of influence of each factor on the learning quality, but also provides a scientific basis for subsequent decision-making. After determining the factors related to the influence of the subject, the deep interval analysis is then performed using the Warren Buffett combined interval analysis method. This method first calculates the mean and standard deviation of the selected influencing factors to construct a corresponding rectangular coordinate system and map the data points to the coordinate system. By setting a specific standard deviation range, the analyst can divide these influencing factors into multiple intervals, such as high-impact intervals, medium-impact intervals, and low-impact intervals. This partitioning can effectively reveal the impact of different factors on learning quality at different levels, thereby forming a more targeted analysis result. Finally, the student subject learning quality strategy generated by the Warren Buffett combined interval analysis method will cover in-depth insights into each influencing factor, and then formulate corresponding improvement strategies. For example, if learning motivation is found to be in the high-impact interval, it indicates that students’ learning motivation is closely related to the quality of learning, and thus corresponding incentives should be formulated to enhance learning motivation.

[0077] Step S3: Perform statistical analysis based on the student subject learning quality strategy, and use visualization tools to visualize and generate a student data traceability information report;

[0078] In an embodiment of the present invention, based on the student subject learning quality strategy, statistical analysis includes calculating basic statistical indicators such as mean, variance, standard deviation, maximum and minimum values. These statistics can help researchers fully understand students' learning performance in different subjects and identify the overall trend and fluctuation of learning quality. In addition, in order to evaluate the influence of different factors on learning quality, the correlation coefficient is also calculated to identify the linear relationship between the variables. After completing the basic statistical analysis, it is a crucial step to use visualization tools to visualize the data. Visualization techniques such as scatter plots, bar graphs, box plots and heat maps can intuitively present statistical results and make complex data relationships easy to understand. For example, a scatter plot can intuitively show the relationship between learning motivation and academic performance, while a box plot can effectively show the distribution differences of student grades between different subjects. This visualization not only improves the readability of the data, but also provides strong support for subsequent decision-making. Finally, all statistical analysis results and visualization charts will be compiled into a comprehensive student data traceability information report. This report not only lists the various statistical indicators of student subject learning in detail, but also graphically displays the specific impact of each influencing factor on learning quality.

[0079] Step S4: Adjust the student subject learning quality strategy based on the student data traceability information report to generate a student subject learning quality adjustment data set; use the student subject learning quality adjustment data set to iterate the student subject learning quality data set, thereby completing the learning analysis task of student data traceability.

[0080] In an embodiment of the present invention, based on the student data traceability information report, educators can identify the pros and cons of the current learning strategy. This process includes an in-depth analysis of key indicators in the report, such as academic performance, learning motivation, learning behavior, etc. By comparing the data changes before and after the adjustment, educators can clearly identify which factors are driving the improvement of students' subject learning quality and which factors are causing the decline in learning effects. On this basis, the process of generating a student subject learning quality adjustment data set involves integrating the data analysis results into a new data set and adjusting the learning strategy in a targeted manner. For example, if the data report shows that students in a certain subject perform poorly under a specific learning strategy, educators can adjust the relevant teaching methods or introduce new learning resources to generate more targeted strategies. This process involves machine learning techniques, such as decision trees or support vector machines, to help analyze the expected impact of different strategies on students' learning effects. Next, using the student subject learning quality adjustment data set to iterate the student subject learning quality data set is a method of optimizing learning strategies through a feedback loop. This iterative process can be regarded as a closed-loop system, in which the adjusted strategy is applied to students again, new learning data is collected, and a new data set is formed. In this cycle, through repeated evaluation and adjustment, teaching strategies can be gradually refined to better suit students' individual needs and learning characteristics.

[0081] Preferably, step S1 comprises the following steps:

[0082] Step S11: Obtaining student subject learning quality dataset;

[0083] Step S12: interpolate missing values ​​of the student subject learning quality data set to generate a student subject missing value processing data set; perform time series smoothing on the student subject missing value processing data set to generate a student subject time trend data set;

[0084] Step S13: Perform data standardization processing on the student subject time trend dataset to generate a subject learning quality preprocessing dataset.

[0085] In an embodiment of the present invention, by obtaining a student subject learning quality data set, educators can collect multi-dimensional learning information, including student test scores, learning behaviors and other related indicators. The integrity and accuracy of this data set are the basis for subsequent analysis and determine the effectiveness of subsequent processing. For the missing values ​​in the data set, an interpolation method is used for processing. This method includes linear interpolation, spline interpolation, etc., which reasonably fills the missing values ​​by utilizing the trends and patterns of existing data points to generate a student subject missing value processing data set. The data set is smoothed for time series in order to eliminate short-term fluctuations in the data and extract potential long-term trends. Commonly used smoothing methods include moving average and exponential smoothing, which can effectively reduce data noise, improve the accuracy of data analysis, and ultimately generate a student subject time trend data set. Data standardization of the student subject time trend data set is to eliminate the differences between different feature dimensions and make the data more comparable. Standardization uses techniques such as Z-score standardization or Min-Max normalization to convert features of different dimensions into a unified standard range, which can effectively improve the stability and accuracy of subsequent analysis models.

[0086] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0087] Step S21: Screening the influencing factors of the subject learning quality preprocessing data set according to the preset regression analysis model to generate subject influence related factors, where the subject influence factors include student personal information, learning behavior data, learning motivation, academic expectation data and test score data;

[0088] Step S22: quantify the data according to the learning motivation to obtain the learning motivation data; map the learning behavior data and the learning motivation data to rectangular coordinate intervals to generate the subject influence coordinate data; construct a rectangular coordinate system for the subject influence coordinate data using the Fahrenheit combined interval analysis method to generate the Fahrenheit combined interval two-dimensional graph; perform deep interval analysis based on the Fahrenheit combined interval two-dimensional graph to generate the Fahrenheit subject combination interval data;

[0089] Step S23: Generate subject quality strategies for Huashi subject combination interval data based on student personal information, and generate student subject learning quality strategies, wherein the student subject learning quality strategies include high academic expectations-performance targeting strategies, medium academic expectations-performance targeting strategies and low academic expectations-performance targeting strategies.

[0090] In the embodiment of the present invention, the influencing factors of the subject learning quality preprocessing data set are screened by a preset regression analysis model, and the relevant factors that have a significant impact on students' academic performance can be effectively identified. These factors include student personal information, learning behavior data, learning motivation, academic expectation data and test score data. This screening process adopts a multivariate regression analysis method, and uses techniques such as the least squares method to ensure that the selected factors are statistically significant, thereby providing a reliable basis for the formulation of subsequent strategies. The learning motivation is quantified, and the qualitative data is converted into quantifiable learning motivation data using an appropriate scale (such as a Likert scale). Next, the learning behavior data and the learning motivation data are mapped to rectangular coordinate intervals. This step visualizes the quantitative results of each factor by constructing a two-dimensional coordinate system, thereby generating subject influence coordinate data. Subsequently, the Fahrenheit combined interval analysis method is used to construct a rectangular coordinate system to form a Fahrenheit combined interval two-dimensional graph. This method can not only show the relationship between different factors, but also group the influencing factors more carefully through deep interval analysis, thereby generating Fahrenheit subject combination interval data. Based on the students' personal information, the Huashi subject combination interval data is used to generate subject quality strategies. In specific implementation, techniques such as rule-based decision trees or cluster analysis can be used to associate the combined data of different academic expectations and performance, and generate corresponding student subject learning quality strategies. These strategies include high academic expectations-performance-targeted strategies, medium academic expectations-performance-targeted strategies, and low academic expectations-performance-targeted strategies, aiming to provide personalized learning guidance plans for different types of students.

[0091] Preferably, step S21 includes the following steps:

[0092] Step S211: using the subject learning quality preprocessing data set as an input variable to the preset linear regression model to screen the influencing factors and generate linear regression screening data; using the Pearson correlation coefficient to construct a correlation matrix for the linear regression screening data and generate a Pearson correlation factor matrix; performing multicollinearity elimination on the Pearson correlation factor matrix and generating subject influencing factor data;

[0093] Step S212: perform dimensionality reduction processing on the subject influence factor data by principal component analysis to generate a key influence factor set; generate regression coefficients for the key influence factor set to generate a subject influence factor regression coefficient set; sort the subject influence factor regression coefficient set by absolute value contribution to generate subject influence coefficient sorting data;

[0094] Step S213: perform verification test on the subject influence coefficient ranking data to generate subject influence coefficient verification data; eliminate invalid values ​​from the influence coefficient verification data based on a preset influence screening dynamic threshold to generate subject influence related factors, where the subject influence related factors include student personal information, learning behavior data, learning motivation, academic expectation data and test score data.

[0095] In the embodiment of the present invention, the subject learning quality preprocessing data set is used as input, and the influencing factors are screened by applying the preset linear regression model. The linear regression model fits the data by the least squares method, which can effectively reveal the linear relationship between the independent variable and the dependent variable. The linear regression screening data generated by this process provides basic data for subsequent analysis. The Pearson correlation coefficient is used to construct the correlation matrix of the linear regression screening data. The core of this step is to determine the linear correlation degree by calculating the correlation coefficient between each pair of variables. The generated Pearson correlation factor matrix can intuitively display the relationship between each variable. The construction of this matrix not only helps to identify potential important influencing factors, but also provides a basis for multicollinearity detection. On this basis, through the multicollinearity test (such as variance inflation factor, VIF), the variables with significant collinearity are excluded, thereby generating subject influencing factor data. This process ensures the statistical independence of the final selected variables and improves the reliability of the model. For the screened subject influencing factor data, the regression coefficient is generated, and the technical means used include the least squares method and standardized regression analysis to obtain the regression coefficient of each influencing factor on the subject learning quality. These regression coefficients reflect the degree of influence of each factor. Furthermore, these regression coefficients are ranked by absolute contribution to generate subject influence coefficient ranking data, so that educators can intuitively understand which factors have a greater contribution to the quality of subject learning. Based on the preset dynamic threshold for influence screening, invalid values ​​are eliminated from the subject influence coefficient ranking data, and the subject influence-related factors finally generated include student personal information, learning behavior data, learning motivation, academic expectation data, and test score data.

[0096] Preferably, the deep interval analysis based on the Fahrenheit combined interval two-dimensional graph includes the following steps:

[0097] Based on the academic expectation data as the X axis and the test score data as the Y axis, a rectangular coordinate system is constructed to obtain the Fahrenheit rectangular coordinate system;

[0098] The learning behavior data and learning motivation data were averaged to obtain the Fahrenheit mean data;

[0099] According to the Fahrenheit mean data and the given 0.67 standard deviation, the X axis and Y axis are divided into three intervals, and the X axis interval and Y axis interval are obtained, wherein the X axis interval includes the low academic expectation interval, the medium academic expectation interval and the high academic expectation interval, and the Y axis interval includes the low achievement interval, the medium achievement interval and the high achievement interval;

[0100] By pairing the X-axis interval and the Y-axis interval, we can obtain the Huashi subject combination interval data, which includes high academic expectation-performance data, middle academic expectation-performance data and low academic expectation-performance data.

[0101] In the embodiment of the present invention, a rectangular coordinate system is constructed based on academic expectation data as the X axis and test score data as the Y axis to form a Fahrenheit rectangular coordinate system. The core of this step is to intuitively display the relationship between academic expectations and test scores in a visual way, which is convenient for subsequent analysis and interpretation. Next, the learning behavior data and learning motivation data are averaged to generate Fahrenheit mean data, and the calculation of the mean provides a basis for the subsequent standard deviation interval division. This process ensures that the generated data is representative through statistical analysis of relevant data sets. After the mean data is generated, the X axis and the Y axis are divided into intervals according to the given 0.67 standard deviation to form three intervals, including a low academic expectation interval, a medium academic expectation interval, and a high academic expectation interval, as well as corresponding low score intervals, medium score intervals, and high score intervals. The application of this standard deviation division method can effectively reflect the degree of discreteness of the data, ensure that the divided intervals can cover different student groups and learning performance, so that the subsequent analysis is more targeted and effective. Subsequently, the intervals are paired according to the divided X-axis intervals and Y-axis intervals to generate Huashi subject combination interval data. The core of this step is to form high academic expectation-score data, medium academic expectation-score data, and low academic expectation-score data through cross-analysis of the combination of different academic expectations and score intervals. This interval pairing not only provides a basis for analyzing the impact of different academic expectations on students' learning outcomes, but also lays the foundation for formulating personalized teaching strategies.

[0102] Preferably, step S23 includes the following steps:

[0103] Step S231: performing academic performance discrimination calculations on the high academic expectation-performance data, the middle academic expectation-performance data, and the low academic expectation-performance data based on the student's personal information, and generating high academic expectation-performance discrimination results, middle academic expectation-performance discrimination results, and low academic expectation-performance discrimination results;

[0104] Step S232: When the high academic expectation-grade discrimination result is less than or equal to the preset grade discrimination value, the learning time is extracted from the learning behavior data, and the learning time is compared with the average learning time data to generate high academic expectation-low grade learning time comparison data; if the high academic expectation-low grade learning time comparison data is greater than the average learning time data, the learning time is increased, and the behavior is motivated in combination with the learning motivation; when the high academic expectation-grade discrimination result is greater than the preset grade discrimination value, the student's personal information is highlighted, and the competition question data is generated and pushed, thereby completing the high academic expectation-grade targeted strategy;

[0105] Step S233: when the academic expectation-grade discrimination result is less than or equal to the preset grade discrimination value, the review frequency and homework completion status of the learning behavior data are extracted to generate the academic expectation-grade review frequency data and the academic expectation-grade homework completion status data; the academic expectation-grade homework completion status data of the middle school is subjected to big data data mining to generate the academic expectation-grade weak data of the middle school; the academic expectation-grade review frequency data of the middle school is used to perform targeted optimization on the academic expectation-grade weak data of the middle school; when the academic expectation-grade discrimination result is greater than the preset grade discrimination value, a confidence strengthening plan is generated for the student's personal information based on the cloud platform, thereby completing the academic expectation-grade targeted strategy of the middle school;

[0106] Step S234: When the low academic expectation-grade discrimination result is less than or equal to the preset grade discrimination value, a learning disability analysis is performed on the learning behavior data to generate low academic expectation-grade learning disability data; a learning time detection is performed on the low academic expectation-grade learning disability data to generate learning time deficiency data; based on the learning motivation data, learning support remedial processing is performed on the learning time deficiency data and the low academic expectation-grade learning disability data; when the low academic expectation-grade discrimination result is greater than the preset grade discrimination value, personalized motivation enhancement processing is performed on the learning motivation data to generate a low academic expectation-grade personalized motivation plan, thereby completing the low academic expectation-grade targeted strategy.

[0107] In the embodiment of the present invention, the high, medium and low academic expectation-score data are used to perform academic performance discrimination calculations through student personal information, and a multivariate statistical analysis method, such as regression analysis or classification model, is applied. This method can effectively identify the potential factors affecting student performance and generate corresponding discrimination results. These discrimination results provide basic information for subsequent data processing, helping to identify student performance under different academic expectation levels. When the high academic expectation-score discrimination result is lower than the preset value, the learning time of the learning behavior data is extracted and compared with the average learning time. This process utilizes data mining technology, and through the analysis of time series data, the relationship between learning time and grades is identified, and learning time comparison data is generated. If the comparison result shows that the student's learning time is long, the system will trigger the corresponding behavioral incentive mechanism, and combine the learning motivation data for personalized learning support, thereby improving the student's learning enthusiasm and effect. Through the extraction of review frequency and homework completion, the middle school academic expectation-score homework completion data is deeply analyzed in combination with big data mining technology to generate weak data, reflecting the shortcomings of students in the learning process. This data-driven approach can effectively identify specific learning barriers, and then conduct targeted optimization based on review frequency data, thereby developing personalized learning plans for students. When the low academic expectations-performance discrimination results are not ideal, the system will conduct a learning barrier analysis, generate relevant data, and provide support and remedial treatment based on learning motivation data. This process emphasizes the combination of data analysis and personalized intervention. By monitoring learning time and learning barrier data, targeted incentive plans are developed to improve students' learning motivation and academic performance.

[0108] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0109] Step S31: Obtaining benchmark data; performing statistical analysis based on the student subject learning quality strategy to generate student subject learning statistical data;

[0110] Step S32: Compare the change trend of the student subject learning statistics data with the benchmark data to generate the student subject learning change trend data;

[0111] Step S33: Use a visualization analysis tool to visualize the student subject learning change trend data and generate a student subject learning change graph; perform a visualization result analysis on the student subject learning change graph, and generate a traceability report to generate a student data traceability information report.

[0112] In the embodiment of the present invention, the accuracy and reliability of the analysis are ensured by obtaining benchmark data. The benchmark data includes multi-dimensional information such as students' historical grades, learning behaviors, and learning motivations, forming the basis for analysis. Next, in the process of statistical analysis based on the student subject learning quality strategy, descriptive statistical methods such as mean, variance, standard deviation, etc. are used to generate student subject learning statistical data. These statistical data provide important quantitative basis for further analysis and can reflect the learning quality of students in different subjects. In the process of comparing the change trend of student subject learning statistical data with the benchmark data, trend analysis methods such as time series analysis or regression analysis are applied to generate student subject learning change trend data. This process can effectively identify the change pattern of learning quality, including the trend of improvement or decline, and provide a basis for subsequent teaching strategy adjustments. In addition, through the analysis of the change trend, educators can discover potential influencing factors, such as learning methods, teacher guidance, etc., and further improve educational intervention measures. The student subject learning change trend data is visualized using a visualization analysis tool to generate a student subject learning change graph. This part uses data visualization technology to intuitively display data changes through charts, line charts, bar charts, etc., making it easier for educators and managers to quickly understand changes in students' learning status.

[0113] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes:

[0114] Step S41: conducting a student subject learning quality strategy assessment based on the student data traceability information report, and generating a student subject learning quality assessment strategy;

[0115] Step S42: adjusting and generating a data set for the student subject learning quality assessment strategy to generate a student subject learning quality adjustment data set;

[0116] Step S43: Use the student subject learning quality adjustment data set to iterate the student subject learning quality data set, thereby completing the learning analysis task of student data tracing.

[0117] In the embodiment of the present invention, a targeted subject learning quality assessment strategy is formulated by comprehensively analyzing the multi-dimensional information such as the student's learning history, behavior pattern, and learning motivation. In this process, the evaluation model in statistics, such as regression analysis or variance analysis, can effectively identify the key factors affecting the student's learning quality, and generate corresponding evaluation strategies based on these factors. This strategy can not only reflect the student's current learning status, but also provide teachers with a clear direction for improvement. Based on the generation of the student subject learning quality assessment strategy, the data set is further adjusted. This adjustment process includes technical means such as data cleaning, feature selection, and data enhancement. By cleaning the data, unnecessary or redundant information is eliminated to ensure the accuracy of the analysis; feature selection is to screen out features that have a significant impact on learning quality through algorithms such as LASSO or random forests, thereby optimizing the structure of the data set. In addition, data enhancement technology improves the generalization ability of the model by generating new samples, ensuring that it can better adapt to the changing learning environment and individual differences in subsequent analysis. The generated student subject learning quality adjustment data set is used to iterate the data of the original student subject learning quality data set. This process uses iterative algorithms, such as stochastic gradient descent (SGD) or batch update methods, to continuously correct and optimize the original data set. Through repeated iterations of the data, not only can the quality of the data set be improved, but also the learning analysis can be made more accurate and reliable.

[0118] Preferably, step S43 includes the following steps:

[0119] Step S431: using the student subject learning quality adjustment data set to perform data set comparison with the student subject learning quality data set to generate a student subject learning quality comparison data set;

[0120] Step S432: performing an update iterative analysis on the student subject learning quality comparison data set to generate a student subject learning quality iteration result;

[0121] Step S433: Dynamically adjust the student subject learning quality strategy based on the iterative results of the student subject learning quality, thereby completing the learning analysis task of student data tracing.

[0122] In the embodiment of the present invention, the specific technical means are mainly concentrated on multiple important links such as data set comparison, iterative analysis and dynamic adjustment of strategies. The primary task of this process is to use the student subject learning quality adjustment data set to compare the original student subject learning quality data set. This comparison process relies on statistical analysis techniques, such as paired t-test or variance analysis, to identify significant differences in learning quality between the two. In this process, the generated student subject learning quality comparison data set lays the foundation for subsequent analysis and provides necessary data support. The student subject learning quality comparison data set is updated and iteratively analyzed. This analysis process can use iterative algorithms, such as time series prediction, Kalman filtering or incremental learning methods in machine learning, to achieve dynamic update and feedback of data. This iterative analysis can not only capture the trend of data changes over time, but also make the model more adaptable through a continuous feedback mechanism, thereby generating iterative results of student subject learning quality. These results provide educators with timely feedback on changes in student learning status, so that educational strategies can be consistent with students' actual conditions. Dynamically adjust the learning quality strategy based on the iterative results of student subject learning quality. This strategy adjustment process relies on the concept of feedback control system, including adaptive algorithms and optimization techniques.

[0123] In this specification, an information analysis system based on student data tracing is provided, which is used to execute the above-mentioned information analysis method based on student data tracing. The information analysis system based on student data tracing:

[0124] Data acquisition and preprocessing module: used to acquire students' subject learning quality data set; perform data preprocessing on students' subject learning quality data set to generate subject learning quality preprocessing data set;

[0125] Influencing factor screening and analysis module: used to screen the influencing factors of the subject learning quality preprocessing data set according to the preset regression analysis model, and generate subject influence related factors; use the Huaren combined interval analysis method to conduct in-depth interval analysis on subject influence related factors, and generate student subject learning quality strategies;

[0126] Statistical analysis and visualization module: used to perform statistical analysis based on student subject learning quality strategies, and use visualization tools for visualization to generate student data traceability information reports;

[0127] Strategy adjustment and iteration module: used to adjust the student subject learning quality strategy based on the student data traceability information report and generate a student subject learning quality adjustment data set; use the student subject learning quality adjustment data set to iterate the student subject learning quality data set, thereby completing the learning analysis task of student data traceability.

[0128] The beneficial effect of the present invention is that the student subject learning quality data set is obtained and preprocessed to ensure the integrity and accuracy of the data, laying a solid foundation for subsequent analysis. This process ensures that the generated subject learning quality preprocessing data set has good quality by removing noise data and outliers, so that the subsequent analysis can be more credible and effective. In step S2, the preset regression analysis model is applied to screen the influencing factors of the data set to generate subject influence related factors, which reflects the idea of ​​data-driven decision-making and can reveal the key factors that have a greater impact on the quality of student subject learning, which provides a practical and feasible guidance basis for teachers and education managers. In addition, the deep interval analysis of these influencing factors is carried out by the Fahrenheit combined interval analysis method, which further refines the strategy formulation for subject learning quality, so that students in different intervals can get personalized learning suggestions and strategies, and this targeting significantly improves the effectiveness of intervention measures. Through the combination of statistical analysis and visualization tools, the generated student data traceability information report not only provides an intuitive result display, but also provides detailed data support for subsequent strategy adjustments. The visualized results make complex data relationships easy to understand, promote communication and cooperation between teachers and managers, and promote the scientific and systematic decision-making of education. Finally, step S4 ensures continuous attention and improvement to the quality of students' subject learning through strategy adjustment and iterative analysis based on student data traceability information reports. This iterative process not only continuously optimizes the adjustment measures, but also provides a basis and guarantee for the personalized development of education and teaching. In summary, the present invention effectively solves the problems caused by the lack of in-depth analysis and personalized strategy formulation in traditional education analysis by constructing a systematic data analysis process, and improves the pertinence and effectiveness of educational intervention. Therefore, the present invention solves the problem of lack of personalization and dynamic adjustment in traditional education analysis methods through systematic analysis of influencing factors and strategy adjustment, and improves the scientific nature and implementation effect of educational decision-making.

[0129] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0130] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An information analysis method based on student data tracing, characterized in that: The following steps are involved: Step S1: Obtain student subject learning quality dataset; Perform data preprocessing on the student subject learning quality data set to generate a subject learning quality preprocessing data set; Step S2: Screen the influencing factors of the subject learning quality preprocessing data set according to the preset regression analysis model to generate subject influence related factors; use the Wahrenheit combined interval analysis method to conduct in-depth interval analysis on the subject influence related factors to generate student subject learning quality strategies; Step S3: Perform statistical analysis based on the student subject learning quality strategy to generate student learning quality statistical data; use visualization tools to visualize the student learning quality statistical data to generate a student subject learning change graph; perform visualization result analysis based on the student subject learning change graph to generate a student data traceability information report; Step S4: Adjust the student subject learning quality strategy based on the student data traceability information report to generate a student subject learning quality adjustment data set; use the student subject learning quality adjustment data set to iterate the student subject learning quality data set, thereby completing the learning analysis task of student data traceability.

2. The information analysis method based on student data tracing according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Obtaining student subject learning quality dataset; Step S12: interpolate missing values ​​of the student subject learning quality data set to generate a student subject missing value processing data set; perform time series smoothing on the student subject missing value processing data set to generate a student subject time trend data set; Step S13: Perform data standardization processing on the student subject time trend dataset to generate a subject learning quality preprocessing dataset.

3. The information analysis method based on student data tracing according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: Screening the influencing factors of the subject learning quality preprocessing data set according to the preset regression analysis model to generate subject influence related factors, where the subject influence factors include student personal information, learning behavior data, learning motivation, academic expectation data and test score data; Step S22: quantify the data according to the learning motivation to obtain the learning motivation data; map the learning behavior data and the learning motivation data to rectangular coordinate intervals to generate the subject influence coordinate data; construct a rectangular coordinate system for the subject influence coordinate data using the Fahrenheit combined interval analysis method to generate the Fahrenheit combined interval two-dimensional graph; perform deep interval analysis based on the Fahrenheit combined interval two-dimensional graph to generate the Fahrenheit subject combination interval data; Step S23: Generate subject quality strategies for Huashi subject combination interval data based on student personal information, and generate student subject learning quality strategies, wherein the student subject learning quality strategies include high academic expectations-performance targeting strategies, medium academic expectations-performance targeting strategies and low academic expectations-performance targeting strategies.

4. The information analysis method based on student data tracing according to claim 3 is characterized in that: Step S21 includes the following steps: Step S211: using the subject learning quality preprocessing data set as an input variable to the preset linear regression model to screen the influencing factors and generate linear regression screening data; using the Pearson correlation coefficient to construct a correlation matrix for the linear regression screening data and generate a Pearson correlation factor matrix; performing multicollinearity elimination on the Pearson correlation factor matrix and generating subject influencing factor data; Step S212: perform dimensionality reduction processing on the subject influence factor data by principal component analysis to generate a key influence factor set; generate regression coefficients for the key influence factor set to generate a subject influence factor regression coefficient set; sort the subject influence factor regression coefficient set by absolute value contribution to generate subject influence coefficient sorting data; Step S213: perform verification test on the subject influence coefficient ranking data to generate subject influence coefficient verification data; eliminate invalid values ​​from the influence coefficient verification data based on a preset influence screening dynamic threshold to generate subject influence related factors, where the subject influence related factors include student personal information, learning behavior data, learning motivation, academic expectation data and test score data.

5. The information analysis method based on student data tracing according to claim 3 is characterized in that: The deep interval analysis based on the Fahrenheit combination interval two-dimensional graph includes the following steps: Based on the academic expectation data as the X axis and the test score data as the Y axis, a rectangular coordinate system is constructed to obtain the Fahrenheit rectangular coordinate system; The learning behavior data and learning motivation data were averaged to obtain the Fahrenheit mean data; According to the Fahrenheit mean data and the given 0.67 standard deviation, the X axis and Y axis are divided into three intervals, and the X axis interval and Y axis interval are obtained, wherein the X axis interval includes the low academic expectation interval, the medium academic expectation interval and the high academic expectation interval, and the Y axis interval includes the low achievement interval, the medium achievement interval and the high achievement interval; By pairing the X-axis interval and the Y-axis interval, we can obtain the Huashi subject combination interval data, which includes high academic expectation-performance data, middle academic expectation-performance data and low academic expectation-performance data.

6. The information analysis method based on student data tracing according to claim 3 is characterized in that: Step S23 includes the following steps: Step S231: performing academic performance discrimination calculations on the high academic expectation-performance data, the middle academic expectation-performance data, and the low academic expectation-performance data based on the student's personal information, and generating high academic expectation-performance discrimination results, middle academic expectation-performance discrimination results, and low academic expectation-performance discrimination results; Step S232: When the high academic expectation-grade discrimination result is less than or equal to the preset grade discrimination value, the learning time is extracted from the learning behavior data, and the learning time is compared with the average learning time data to generate high academic expectation-low grade learning time comparison data; if the high academic expectation-low grade learning time comparison data is greater than the average learning time data, the learning time is increased, and the behavior is motivated in combination with the learning motivation; when the high academic expectation-grade discrimination result is greater than the preset grade discrimination value, the student's personal information is highlighted, and the competition question data is generated and pushed, thereby completing the high academic expectation-grade targeted strategy; Step S233: when the academic expectation-grade discrimination result is less than or equal to the preset grade discrimination value, the review frequency and homework completion status of the learning behavior data are extracted to generate the academic expectation-grade review frequency data and the academic expectation-grade homework completion status data; the academic expectation-grade homework completion status data of the middle school is subjected to big data data mining to generate the academic expectation-grade weak data of the middle school; the academic expectation-grade review frequency data of the middle school is used to perform targeted optimization on the academic expectation-grade weak data of the middle school; when the academic expectation-grade discrimination result is greater than the preset grade discrimination value, a confidence strengthening plan is generated for the student's personal information based on the cloud platform, thereby completing the academic expectation-grade targeted strategy of the middle school; Step S234: When the low academic expectation-grade discrimination result is less than or equal to the preset grade discrimination value, a learning disability analysis is performed on the learning behavior data to generate low academic expectation-grade learning disability data; a learning time detection is performed on the low academic expectation-grade learning disability data to generate learning time deficiency data; based on the learning motivation data, learning support remedial processing is performed on the learning time deficiency data and the low academic expectation-grade learning disability data; when the low academic expectation-grade discrimination result is greater than the preset grade discrimination value, personalized motivation enhancement processing is performed on the learning motivation data to generate a low academic expectation-grade personalized motivation plan, thereby completing the low academic expectation-grade targeted strategy.

7. The information analysis method based on student data tracing according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: Obtaining benchmark data; performing statistical analysis based on the student subject learning quality strategy to generate student subject learning statistical data; Step S32: Compare the change trend of the student subject learning statistics data with the benchmark data to generate the student subject learning change trend data; Step S33: Use a visualization analysis tool to visualize the student subject learning change trend data and generate a student subject learning change graph; perform a visualization result analysis on the student subject learning change graph, and generate a traceability report to generate a student data traceability information report.

8. The information analysis method based on student data tracing according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: conducting a student subject learning quality strategy assessment based on the student data traceability information report, and generating a student subject learning quality assessment strategy; Step S42: adjusting and generating a data set for the student subject learning quality assessment strategy to generate a student subject learning quality adjustment data set; Step S43: Use the student subject learning quality adjustment data set to iterate the student subject learning quality data set, thereby completing the learning analysis task of student data tracing.

9. The information analysis method based on student data tracing according to claim 8 is characterized in that: Step S43 includes the following steps: Step S431: using the student subject learning quality adjustment data set to perform data set comparison with the student subject learning quality data set to generate a student subject learning quality comparison data set; Step S432: performing an update iterative analysis on the student subject learning quality comparison data set to generate a student subject learning quality iteration result; Step S433: Dynamically adjust the student subject learning quality strategy based on the iterative results of the student subject learning quality, thereby completing the learning analysis task of student data tracing.

10. An information analysis system based on student data tracing, characterized in that: Used to execute the information analysis method based on student data tracing as claimed in claim 1, the information analysis system based on student data tracing comprises: Data acquisition and preprocessing module: used to acquire students' subject learning quality data set; perform data preprocessing on students' subject learning quality data set to generate subject learning quality preprocessing data set; Influencing factor screening and analysis module: used to screen the influencing factors of the subject learning quality preprocessing data set according to the preset regression analysis model, and generate subject influence related factors; use the Huaren combined interval analysis method to conduct in-depth interval analysis on subject influence related factors, and generate student subject learning quality strategies; Statistical analysis and visualization module: used to perform statistical analysis based on student subject learning quality strategies, and use visualization tools for visualization to generate student data traceability information reports; Strategy adjustment and iteration module: used to adjust the student subject learning quality strategy based on the student data traceability information report and generate a student subject learning quality adjustment data set; use the student subject learning quality adjustment data set to iterate the student subject learning quality data set, thereby completing the learning analysis task of student data traceability.

Images