Student examination score intelligent analysis system

Abstract

The invention relates to the technical field of score data analysis, in particular to an intelligent analysis system for student examination scores. According to the invention, the independent learning effect trend of each student and the overall learning effect trend of all students in each examination are obtained; analyzing the difference characteristics between the learning effect trends, and obtaining the change correlation between the independent learning effect trend and the overall learning effect trend of each student under the current examination; obtaining score influence factors of each student under the current examination; adjusting the current original score data of each student to obtain the current adjustment score data of each student; according to the current adjustment score data of each student and the change of the adjacent previous original score data, clustering all students to obtain a student cluster; and analyzing the test score. According to the method, the accuracy of the clustering effect and the effectiveness of score analysis are improved by adaptively adjusting the examination scores of the students.

Description

Technical Field

[0001] The present invention relates to the technical field of performance data analysis, and particularly to an intelligent analysis system for students' examination results. Background Art

[0002] At the present stage, to understand the learning and development status of a student group, it is necessary to conduct irregular examinations. By comprehensively analyzing the results of each examination of students, the learning changes of students can be observed to ensure that every student does not fall behind in the learning process, which not only improves the effect of educational management, but also promotes the development of students' self-awareness and provides a scientific basis for educational decision-making.

[0003] In the prior art, the learning change trend of students is analyzed through the examination results of students in previous examinations. K-means clustering is used to cluster the learning change trend of current students, and student groups with similar learning trends are identified for targeted management. However, since the fluctuating changes in students' scores are not only related to the recent learning situation of students, but also have a certain relationship with external factors such as the difficulty of examinations, clustering only based on the fluctuating changes in learning scores will ignore the interference of the examination difficulty factor on the true learning effectiveness of students, resulting in incorrect analysis of students' learning scores. Summary of the Invention

[0004] In order to solve the technical problem of incorrect analysis of students' learning scores caused by ignoring the interference of the examination difficulty factor on the true learning effectiveness of students, the purpose of the present invention is to provide an intelligent analysis system for students' examination results, and the specific technical solution adopted is as follows:

[0005] The present invention provides an intelligent analysis system for students' examination results, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented:

[0006] Obtain the original score data of each student in each examination under a subject within the historical range of the current examination;

[0007] Obtain the independent learning effectiveness trend of each student in each examination according to the change trend and distribution characteristics of the original score data of each student within the neighborhood range of each examination, and obtain the overall learning effectiveness trend of all students in each examination; according to the difference characteristics between the independent learning effectiveness trend and the overall learning effectiveness trend of each student in each examination within the historical range of the current examination, obtain the change correlation between the independent learning effectiveness trend and the overall learning effectiveness trend of each student in the current examination;

[0008] Obtain the score impact factor of each student in the current exam based on the independent learning effectiveness trend and the corresponding change correlation of each student in the current exam; adjust the current original score data of each student according to the score impact factor of each student in the current exam and the change characteristics of the original score data of all students to obtain the current adjusted score data of each student; cluster all students according to the change between the current adjusted score data of each student and the previous original score data to obtain student clustering clusters;

[0009] Analyze the exam scores according to the student clustering clusters.

[0010] Further, the method for obtaining the independent learning effectiveness trend includes:

[0011] Within the neighborhood range of each exam, construct a line graph of the original score data of all exams; obtain the angle between the line segment between adjacent original score data and the horizontal direction;

[0012] After normalizing and mapping all the angles between adjacent original score data, calculate the mean of all the normalized mapping results as the overall score change trend;

[0013] Adjust the differences between the same adjacent original score data according to the distribution of the differences between adjacent original score data to obtain the average score change level;

[0014] Based on the overall score change trend and the average score change level of each student, obtain the independent learning effectiveness trend of each student in each exam. Both the overall score change trend and the average score change level are positively correlated with the independent learning effectiveness trend.

[0015] Further, the method for obtaining the average score change level includes:

[0016] Within the neighborhood range of each exam, calculate the difference between the original score data of the subsequent exam and the adjacent previous exam to obtain the difference sequence corresponding to the adjacent original score data;

[0017] Count the number of differences after the difference corresponding to each adjacent original score data in the difference sequence and perform a negative correlation mapping as the weighted value of the difference corresponding to each adjacent original score data; perform a weighted average on the differences between adjacent original score data according to the weighted values of the differences corresponding to different adjacent original score data of each student to obtain the average score change level.

[0018] Further, the method for obtaining the overall learning effectiveness trend includes:

[0019] Calculate the mean of the independent learning effectiveness trends of all students in each exam to obtain the overall learning effectiveness trend of all students in each exam.

[0020] Further, the method for obtaining the change correlation includes:

[0021] Obtain the change correlation between the independent learning effectiveness trend and the overall learning effectiveness trend of each student in the current exam based on the change difference between the independent learning effectiveness trend and the overall learning effectiveness trend of each student in the current exam and the matching distance between the independent learning effectiveness trend and the overall learning effectiveness trend in all exams within the historical range of the current exam. Both the change difference and the matching distance are negatively correlated with the change correlation.

[0022] Further, the method for obtaining the score impact factor includes:

[0023] Obtain the score impact factor of each student in the current exam based on the independent learning effectiveness trend of each student in the current exam and the corresponding change correlation. Both the independent learning effectiveness trend and the change correlation are positively correlated with the score impact factor.

[0024] Further, the method for obtaining the current adjusted score data includes:

[0025] Judge whether it is necessary to adjust the current raw score data of each student according to the change characteristics of the raw score data of all students. If adjustment is required, obtain the adjustment factor based on the score impact factor of each student in the current exam and the current raw score data;

[0026] After calculating the sum of the current raw score data of each student and the adjustment factor, perform normalization mapping to obtain the current adjusted score data of each student.

[0027] Further, the judgment of whether it is necessary to adjust the current raw score data of each student according to the change characteristics of the raw score data of all students includes:

[0028] Obtain the overall score level of each exam based on the central tendency of the raw score data of all students in each exam;

[0029] If the overall score level in the current exam is not equal to the overall score level of the previous exam of the current exam, judge that the current raw score data needs to be adjusted; otherwise, no adjustment is required.

[0030] Further, the method for obtaining the adjustment factor includes:

[0031] Calculate the product of the score impact factor of each student in the current exam and the current raw score data as the first product;

[0032] If the overall score level in the current exam is greater than the overall score level of the previous exam of the current exam, take the opposite of the first product, and the obtained value is used as the adjustment factor;

[0033] If the overall score level under the current test is lower than the overall score level of the test before the current test, the first product is used as an adjustment factor.

[0034] Furthermore, the method for obtaining the student clusters includes:

[0035] The difference between each student's current adjusted score data and the previous original score data is calculated, and K-means clustering is performed on all students to obtain student clusters.

[0036] The present invention has the following beneficial effects:

[0037] The present invention obtains the independent learning achievement trend of each student in each exam according to the change trend and distribution characteristics of the original score data of each student in the neighborhood range of each exam, and obtains the overall learning achievement trend of all students in each exam. The independent learning achievement trend reflects the learning situation and progress speed of individual students, and the overall learning achievement trend reflects the learning level and development trend of all students. In order to prevent students' scores from being affected by the difficulty of the exam and failing to reflect their true learning level, the change correlation between the independent learning achievement trend and the overall learning achievement trend of each student in each exam within the historical range of the current exam is obtained, the correlation between the individual student and the overall learning achievement is revealed, and the influence of the difficulty of the exam on the individual student is evaluated. The influence of factors is obtained; according to the independent learning performance trend and corresponding change correlation of each student in the current exam, the performance influence factor of each student in the current exam is obtained, and the influence degree of the student's learning performance on the performance in the current exam is quantified, so as to help students understand the specific influence of the current learning status on the performance; according to the performance influence factor of each student in the current exam and the change characteristics of the original performance data of all students, the current original performance data of each student is adjusted to obtain the current adjusted performance data of each student, reflecting the real learning performance and progress of the student; according to the change of the current adjusted performance data of each student and the adjacent previous original performance data, all students are clustered to obtain student clustering clusters, identify student groups with similar learning performance trends and performance change characteristics, and analyze students with different learning changes in a targeted manner; and analyze the test scores. The present invention improves the accuracy of clustering effect and the effectiveness of performance analysis by adaptively adjusting the test scores of students. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0039] Figure 1 Flowchart of the implementation method of an intelligent analysis system for students' exam scores provided by an embodiment of the present invention;

[0040] Figure 2 Schematic diagram of an intelligent analysis system for students' exam scores provided by an embodiment of the present invention. Detailed implementation manners

[0041] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in conjunction with the drawings and preferred embodiments, details the specific implementation manners, structures, features, and effects of an intelligent analysis system for students' exam scores proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0042] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0043] The following specifically describes the specific solution of an intelligent analysis system for students' exam scores provided by the present invention in conjunction with the drawings.

[0044] Please refer to Figure 1 , which shows the flowchart of the implementation method of an intelligent analysis system for students' exam scores provided by an embodiment of the present invention. The embodiment of the present invention provides an intelligent analysis system for students' exam scores. Refer to Figure 2 , including a memory 201, a processor 202, and a computer program 203 stored in the memory 201 and executable on the processor 202. When the processor 202 executes the computer program 203, the following method steps can be implemented. The flowchart corresponding to the method steps is as Figure 1 shown. Specifically, the method specifically includes:

[0045] Step S1: Obtain the original score data of each student in each exam under a subject within the historical range of the current exam.

[0046] In an embodiment of the present invention, considering that the difficulty of the exam may cause fluctuations in students' exam scores, in order to avoid misjudging students' learning effectiveness and timely discover students' academic performance, and provide timely feedback and guidance for teaching, it is necessary to analyze students' exam scores in previous times; First, evaluate the learning status of students after each exam, obtain the exam scores of all students from the student exam score record system, summarize those of one subject together and analyze them separately, and obtain the original score data of each student in each exam under one subject within the historical range of the current exam.

[0047] It should be noted that in an embodiment of the present invention, the historical range of the current exam is the time range composed of the current exam and the corresponding historical exams recorded in the student exam score record system.

[0048] It should be noted that in order to facilitate subsequent processing of the score data, all the original score data is normalized, and the obtained value is used as the new original score data for subsequent calculations, and cleaning is performed, which helps to remove invalid or incorrect records, handle missing values, and ensure the accuracy and integrity of the data.

[0049] Step S2: Obtain the independent learning effectiveness trend of each student in each exam according to the change trend and distribution characteristics of the original score data within the neighborhood range of each student in each exam, and obtain the overall learning effectiveness trend of all students in each exam; According to the difference characteristics between the independent learning effectiveness trend and the overall learning effectiveness trend of each student in each exam within the historical range of the current exam, obtain the change correlation between the independent learning effectiveness trend and the overall learning effectiveness trend of each student in the current exam.

[0050] By performing trend analysis on students' historical score data, it can be observed whether the students' scores show an upward or downward trend. This trend can intuitively reflect students' learning motivation and progress; The exam scores closer to each exam are more credible for analyzing the learning situation of each exam and can more accurately reflect the true learning effectiveness trend of each student; Therefore, obtain the independent learning effectiveness trend of each student in each exam according to the change trend and distribution characteristics of the original score data within the neighborhood range of each student in each exam.

[0051] Preferably, in an embodiment of the present invention, the method for obtaining the independent learning effectiveness trend includes:

[0052] Construct a line chart of the original score data of all exams within the neighborhood range of each exam; obtain the angle between the line segment between adjacent original score data and the horizontal direction; after normalizing the angles between all adjacent original score data, calculate the mean of all normalized mapping results as the overall score change trend; adjust the differences between the same adjacent original score data according to the time series distribution of the differences between adjacent original score data to obtain the average score change level.

[0053] According to the overall score change trend and the average score change level of each student, obtain the independent learning effectiveness trend of each student in each exam. Both the overall score change trend and the average score change level are positively correlated with the independent learning effectiveness trend. Among them, the positive correlation means that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. The specific relationship can be a multiplicative relationship, an additive relationship, the power of an exponential function, etc., which is determined by the actual application.

[0054] Preferably, in an embodiment of the present invention, the method for obtaining the average score change level includes:

[0055] Within the neighborhood range of each exam, calculate the difference between the original score data of the subsequent exam and the adjacent previous exam to obtain the difference sequence corresponding to the adjacent original score data;

[0056] Count the number of differences after the difference corresponding to each adjacent original score data in the difference sequence, and perform a negative correlation mapping as the weighted value of the difference corresponding to each adjacent original score data; perform a weighted average on the differences between adjacent original score data according to the weighted values of the differences corresponding to different adjacent original score data of each student to obtain the average score change level.

[0057] In an embodiment of the present invention, the formula for the independent learning effectiveness trend is expressed as:

[0058]

[0059] where, T i represents the independent learning effectiveness trend of the i-th student in each exam; N represents the number of differences between adjacent original score data within the neighborhood range of each exam; θ i，n represents the angle between the line segment between the n-th adjacent original score data of the i-th student and the horizontal direction; g(θ i，n ) represents the value after normalizing the angle θ i，n ; D i，n represents the number of differences after the difference corresponding to the n-th adjacent original score data in the difference sequence of the i-th student within the neighborhood range of each exam; B i，n represents the difference between the n-th adjacent original score data of the i-th student.

[0060] In the formula for the independent learning effectiveness trend, since the included angle can be positive or negative, g(θ i，n ) represents normalizing the maximum and minimum values of the included angle, scaling all included angles to the range of 0 - 1; represents calculating the mean of the normalized included angles between all adjacent original score data as the overall score change trend. The larger the included angle, the larger the mean of the normalized included angles, and the greater the overall score change trend; represents the average score change level. The larger the difference between adjacent original score data, the greater the change trend of the student's score. For the i-th student, in the difference sequence within the neighborhood range of each exam, the larger the number of differences after the n-th adjacent original score data corresponding difference, the farther the analyzed change trend is from the current original score data, and the lower the credibility of the analysis of the student's current learning state; conversely, the smaller the number of differences, the closer it is to the current original score data, the higher the credibility of the analysis of the student's current learning state, and the more the change trend needs to be adjusted to more accurately measure the independent learning effectiveness trend of each student; therefore, the larger the included angle, the greater the overall score change trend, the greater the average score change level, and the greater the corresponding independent learning effectiveness trend.

[0061] It should be noted that in an embodiment of the present invention, the neighborhood range of each exam is the range composed of each exam and the corresponding historical exam in the student exam score recording system. In other embodiments of the present invention, the size of the neighborhood range can be specifically set according to specific circumstances and will not be limited and elaborated herein.

[0062] It should be noted that in an embodiment of the present invention, the method of counting the number of differences after the difference corresponding to each adjacent original score data in the difference sequence and performing a negative correlation mapping is to take the reciprocal of the counted number of differences for negative correlation mapping, constructing a negative correlation relationship where the larger the number of differences, the farther it is from the current original score data, and the lower the credibility of the analysis of the current original score data; in other embodiments of the present invention, the counted number of differences can be used to construct a correlation relationship where the larger the number of differences, the farther it is from the current original score data, and the lower the credibility of the analysis of the current original score data through the exp(-) function; it is also possible to directly normalize the order of each adjacent original score data corresponding difference in the difference sequence as a weighting value; the smaller the order, the farther it is from the current original score data, and the lower the credibility of the analysis of the current original score data. The specific means are well-known technical means to those skilled in the art and will not be elaborated herein.

[0063] It should be noted that when implementing the negative correlation relationship, if the reciprocal is used, a manually set threshold, such as a value of 0.01, needs to be added to the denominator of the fraction to avoid the situation where the denominator of the fraction takes a value of 0.

[0064] By analyzing the overall learning effectiveness trend, the learning needs and performance of students can be comprehensively understood. Obtain the overall learning effectiveness trend of all students in each exam.

[0065] Preferably, in an embodiment of the present invention, the method for obtaining the overall learning effectiveness trend includes:

[0066] Average the independent learning effectiveness trends of all students in each exam to obtain the overall learning effectiveness trend of all students in each exam.

[0067] It should be noted that in other embodiments of the present invention, other methods such as the median or mode of the independent learning effectiveness trends of all students can also be selected to represent the overall learning effectiveness trend of all students. The specific means are well-known technical means to those skilled in the art and will not be elaborated here.

[0068] To eliminate the influence of exam difficulty fluctuations on the judgment of students' learning effectiveness and achieve the determination of students' learning performance status, analyze the difference characteristics between the independent learning effectiveness trend and the overall learning effectiveness trend of each student. When the learning effectiveness trend of a student has a smaller difference from the overall learning effectiveness trend of all students and maintains a high degree of consistency, it reflects the general level of the performance changes of this student and all student groups affected by external factors such as exam difficulty. This can better understand the learning situation and development trend of students. Therefore, according to the difference characteristics between the independent learning effectiveness trend and the overall learning effectiveness trend of each student in each exam within the historical range of the current exam, obtain the change correlation between the independent learning effectiveness trend and the overall learning effectiveness trend of each student in the current exam.

[0069] Preferably, in an embodiment of the present invention, the method for obtaining the change correlation includes:

[0070] Based on the change difference between the independent learning effectiveness trend and the overall learning effectiveness trend of each student in the current exam and the matching distance between the independent learning effectiveness trend and the overall learning effectiveness trend in all exams within the historical range of the current exam, obtain the change correlation between the independent learning effectiveness trend and the overall learning effectiveness trend of each student in the current exam. Both the change difference and the matching distance are negatively correlated with the change correlation. Among them, the negative correlation relationship means that the dependent variable will decrease as the independent variable increases, and the dependent variable will increase as the independent variable decreases. It can be a subtraction relationship, a division relationship, etc., which is determined by the actual application.

[0071] In an embodiment of the present invention, the formula for the change correlation is expressed as:

[0072]

[0073] Where x represents the serial number of the current exam; Rix Represents the change correlation between the independent learning effectiveness trend of the \(i\)-th student and the overall learning effectiveness trend under the current exam; \(T\) ix Represents the independent learning effectiveness trend of the \(i\)-th student under the current exam; \(T\) x Represents the overall learning effectiveness trend of all students under the current exam Represents the independent learning effectiveness trend of the \(i\)-th student in all exams within the historical scope of the current exam Represents the overall learning effectiveness trend of all students in all exams within the historical scope of the current exam Represents the DTW distance, i.e., the matching distance, between the independent learning effectiveness trend of each student and the overall learning effectiveness trend of all students in all exams within the historical scope of the current exam; \(\exp()\) represents the exponential function with the natural constant as the base; \(\text{sigmoid}\{\}\) represents the logistic function

[0074] In the formula for the change correlation, through the exponential function with the natural constant as the base Perform negative correlation mapping, \(\vert T\) ix - \(T\) x \(\vert\) represents the difference between the independent learning effectiveness trend and the overall learning effectiveness trend of the \(i\)-th student under the current exam. The greater the difference, the greater the difference between the corresponding student and the overall learning effectiveness trend level of all students, the smaller the change correlation, and the less susceptible to the influence of the exam difficulty factor The larger it is, the greater the matching distance between the independent learning effectiveness trend and the overall learning effectiveness trend of students within the historical scope, the smaller the correlation degree, and the smaller the change correlation

[0075] It should be noted that in an embodiment of the present invention, the matching distance is obtained by calculating the DTW distance, and a negative correlation mapping is performed on the DTW distance to construct a correlation relationship where the larger the DTW distance, the larger the matching distance, and the smaller the change correlation; in other embodiments of the present invention, the negative correlation mapping of the DTW distance can also be directly constructed by calculating the Pearson correlation coefficient between the independent learning effectiveness trend of each student and the overall learning effectiveness trend of all students within the historical scope. The specific DTW distance and correlation coefficient are well-known technical means in the art and will not be elaborated here

[0076] It should be noted that in other embodiments of the present invention It is also possible to first perform normalization and addition and then perform negative correlation mapping to construct a negative correlation relationship where the greater the change difference and the matching distance, the smaller the change correlation. The specific means are well-known technical means in the art and will not be elaborated here

[0077] Step S3: Obtain the score impact factor of each student in the current exam based on the independent learning effectiveness trend and the corresponding change correlation of each student in the current exam; adjust the current original score data of each student according to the score impact factor of each student in the current exam and the change characteristics of the original score data of all students to obtain the current adjusted score data of each student; cluster all students according to the change between the current adjusted score data of each student and the previous adjacent original score data to obtain student clustering clusters.

[0078] The evaluation criteria for the difficulty of the exam vary among each student or group, and it is impossible to judge the standard of the exam difficulty through subjective factors. Therefore, taking the overall learning effectiveness trend of all students as a benchmark provides a relatively objective evaluation criterion, which can reflect the general level of most students after being affected; by analyzing the change correlation between the learning effectiveness trend of each student and the overall learning effectiveness trend, the internal relationship between the exam difficulty and the students' exam scores can be revealed. The greater the change correlation, the greater the impact, and the smaller the change correlation, the smaller the impact; combined with the learning effectiveness trend of each student individually, the learning status and learning effect of the student can be intuitively reflected, and the impact of the exam difficulty on the students' exam scores in this exam can be comprehensively analyzed. Therefore, obtain the score impact factor of each student in the current exam based on the independent learning effectiveness trend and the corresponding change correlation of each student in the current exam.

[0079] Preferably, in an embodiment of the present invention, the method for obtaining the score impact factor includes:

[0080] Obtain the score impact factor of each student in the current exam according to the independent learning effectiveness trend and the corresponding change correlation of each student in the current exam. Both the independent learning effectiveness trend and the change correlation are positively correlated with the score impact factor. Among them, the positive correlation means that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. The specific relationship can be a multiplicative relationship, an additive relationship, the power of an exponential function, etc., which is determined by the actual application.

[0081] In an embodiment of the present invention, the formula for the score impact factor is expressed as:

[0082] Y ix =R ix ×T ix ;

[0083] Where x represents the serial number of the current exam; Y ix represents the score impact factor of the i-th student in the current exam; R ix represents the change correlation between the independent learning effectiveness trend of the i-th student and the overall learning effectiveness trend at the current moment; T ixIt represents the trend of the independent learning effectiveness of the i-th student under the current exam.

[0084] In the formula of the score impact factor, under the current exam, when the change correlation between the independent learning effectiveness trend of the i-th student and the overall learning effectiveness trend is high, the degree of influence of this student by the exam difficulty is large, the greater the impact on the score, and the greater the degree of adjustment should be; when the change correlation is smaller, it indicates that the degree of fluctuation of this student by the exam difficulty is small, the smaller the impact on the score, and the smaller the degree of adjustment should be; the greater the independent learning effectiveness trend of the i-th student, the more the overall score change trend of this student shows an upward trend, and the greater the degree of adjustment for this score, reflecting the true learning level; the smaller the independent learning effectiveness trend of the i-th student, the more the score change trend of this student shows a downward state, and the smaller the degree of adjustment for the score of the current exam.

[0085] It should be noted that in other embodiments of the present invention, other basic mathematical operations such as addition can also be used to construct a positive correlation relationship where the greater the independent learning effectiveness trend, the greater the corresponding change correlation, and the greater the score impact factor. The specific means are well-known technical means to those skilled in the art and will not be elaborated here.

[0086] By considering the changes in the original score data of all students in each exam, it can intuitively reflect the dynamic changes in the learning effects of students over a period of time; by analyzing the score impact factors of each student, a comprehensive and quantitative learning effectiveness evaluation index is provided, which can more accurately understand the learning status and development trend of students, and then adjust the original score data to avoid score deviations caused by factors such as exam difficulty, and obtain adjusted score data that is more in line with the actual learning level of students; in order to more accurately evaluate the recent learning performance of students and reduce the impact brought by the fluctuation of exam difficulty, comprehensively analyze the change level of the original score data and the score impact factor; so adjust the current original score data of each student according to the changes in the original score data of all students in each exam and the score impact factor of each student to obtain the current adjusted score data of each student.

[0087] Preferably, in an embodiment of the present invention, the method for obtaining the current adjusted score data includes:

[0088] Judge whether it is necessary to adjust the current original score data of each student according to the change characteristics of the original score data of all students. If adjustment is required, obtain the adjustment factor according to the score impact factor and the current original score data of each student under the current exam;

[0089] After calculating the sum of the current original score data and the adjustment factor of each student, perform normalization mapping to obtain the current adjusted score data of each student.

[0090] Preferably, in an embodiment of the present invention, determining whether to adjust the current original score data of each student according to the change characteristics of the original score data of all students includes:

[0091] Obtain the overall score level for each exam according to the central tendency of the original score data of all students in each exam;

[0092] If the overall score level in the current exam is not equal to the overall score level of the previous exam of the current exam, it is determined that the current original score data needs to be adjusted; otherwise, no adjustment is required.

[0093] It should be noted that comparing the overall score levels between exams can indicate the change characteristics of the original score data of all students. The difference between the overall score levels indicates that the overall original score data of all students has changed between different exams and is affected by the difficulty of the exams. Therefore, adjustment is required.

[0094] It should be noted that, in an embodiment of the present invention, the central tendency of the original score data of all students can be represented by calculating the mean of the original score data of all students to obtain the overall score level of all students. The larger the mean, the greater the tendency reflected by the original score data of all students, that is, the higher the overall score level. In other embodiments of the present invention, the mode or median of the original score data of all students can also be selected to reflect the score central tendency and level of all students. The specific means are well-known technical means to those skilled in the art and will not be elaborated here.

[0095] Preferably, in an embodiment of the present invention, the method for obtaining the adjustment factor includes:

[0096] Calculate the product of the score influence factor of each student in the current exam and the current original score data as the first product;

[0097] If the overall score level in the current exam is greater than the overall score level of the previous exam of the current exam, take the opposite of the first product as the adjustment factor; if the overall score level in the current exam is less than the overall score level of the previous exam of the current exam, take the first product as the adjustment factor.

[0098] In an embodiment of the present invention, the formula for the current adjusted score data is expressed as:

[0099]

[0100] where x represents the serial number of the current exam; Z ix represents the current adjusted score data of the i-th student; represents the mean of the original score data of all students under the current exam, that is, the overall score level under the current exam; represents the mean of the original score data of all students under the exam prior to the current exam, that is, the overall score level under the exam prior to the current exam; Q ix represents the original score data of the i-th student; Y ix represents the score impact factor of the i-th student under the current exam; sigmoid{} represents the logistic function.

[0101] In the formula for adjusting the score data currently, Y ix ×Q ix represents the first product. The greater the score impact factor, the greater the deviation that appears, and the greater the adjustment required for the original score data; the smaller the score impact factor, the smaller the deviation that appears, and the smaller the adjustment required for the original score data. If the overall score level under the current exam is less than the overall score level of the exam prior to the current exam, it indicates that the overall score trend of all students shows a downward level, and the current original score data needs to be adjusted upward to reflect the true learning level. Taking Y ix ×Q ix as the adjustment factor, the greater the score impact factor, the greater the adjustment factor, and the greater the current adjusted score data; the smaller the score impact factor, the smaller the adjustment factor, and the smaller the current adjusted score data. If the overall score level under the current exam is greater than the overall score level of the exam prior to the current exam, it indicates that the overall score trend of all students shows an upward level, and the current original score data needs to be adjusted downward. Taking -(Y ix ×Q ix ) as the adjustment factor, the greater the score impact factor, the greater the first product, and the greater the downward adjustment of the current original product data; on the contrary, the smaller the score impact factor, the smaller the first product, and the smaller the downward adjustment of the current original product data, and the closer the original score data is to the true level of the student.

[0102] By comparing the current adjusted score data of students with the previous original score data, the patterns of changes in students' scores can be identified. These patterns may reflect the states of students' learning progress, stability, and decline, etc.; clustering can classify students with similar learning states, reduce the workload of teachers in dealing with individual differences among students, and provide more targeted guidance and support for students within each clustering cluster. Therefore, all students are clustered based on the differences between the current adjusted score data of each student and the adjacent previous original score data to obtain student clustering clusters.

[0103] Preferably, in an embodiment of the present invention, the method for obtaining student clustering clusters includes:

[0104] Calculate the difference between the current adjusted score data of each student and the adjacent previous original score data, perform K-means clustering on all students, and obtain student clustering clusters.

[0105] The K-means clustering algorithm clusters multiple clustering objects into specified K clustering clusters according to the similarity between the clustering objects. Each clustering object belongs to and only belongs to one clustering cluster with the smallest distance to the center of the student clustering cluster. It should be noted that in an embodiment of the present invention, the number of clustering clusters is preset to 3 by the implementer according to the actual situation; in other embodiments of the present invention, the number of clustering clusters can be specifically set according to the specific situation, which is not limited and elaborated here. The specific K-means clustering algorithm is a well-known technical means to those skilled in the art and will not be elaborated here.

[0106] Step s4: Analyze the exam scores according to the student clustering clusters.

[0107] Different student clustering clusters represent different learning needs and characteristics. By analyzing the clustering clusters, these differences can be more clearly identified; the results of the clustering analysis can help students understand their learning characteristics in the whole, so as to formulate personalized learning paths that more conform to their learning styles and needs. Therefore, analyze the exam scores according to the student clustering clusters.

[0108] It should be noted that after obtaining the student clustering clusters, the student scores can be analyzed, including: calculating the mean value of the differences between the current adjusted score data and the adjacent previous original score data of all students within each student clustering cluster as the within-cluster score mean; arranging them in descending order, which can respectively represent the students corresponding to the learning states of progress, stability, and regression; according to the learning effects corresponding to each student, timely discover the problems of the students and formulate personalized learning strategies, for example: when the student is in a state of progress, continue to maintain the current situation, when in a stable state, while maintaining the current situation, think about improvement strategies, and when in a state of regression, timely analyze the internal or external reasons and make changes. Subsequently, analyze the scores of each subject to timely discover the changes in the learning scores of students in each subject.

[0109] In summary, the present invention obtains the independent learning effectiveness trend of each student in each exam based on the change trend and distribution characteristics of the original score data within the neighborhood range of each student in each exam, and obtains the overall learning effectiveness trend of all students in each exam; according to the difference characteristics between the independent learning effectiveness trend and the overall learning effectiveness trend of each student in each exam within the historical range of the current exam, obtains the change correlation between the independent learning effectiveness trend and the overall learning effectiveness trend of each student in the current exam; and then obtains the score influence factor of each student in the current exam; adjusts the current original score data of each student in combination with the change characteristics of the original score data of all students to obtain the current adjusted score data of each student; clusters all students according to the change between the current adjusted score data of each student and the previous adjacent original score data to obtain student clustering clusters; and analyzes the exam scores. The present invention improves the accuracy of the clustering effect and the effectiveness of the score analysis by adaptively adjusting the scores of students.

[0110] It should be noted that the above sequence of embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0111] Each embodiment in this specification is described in a progressive manner, and the same or similar parts among the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A student test score intelligent analysis system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the following steps are implemented: Get the original score data of each student in each exam under a subject within the historical range of the current exam; According to the change trend and distribution characteristics of the original score data of each student in the neighborhood of each exam, the independent learning performance trend of each student in each exam is obtained, and the overall learning performance trend of all students in each exam is obtained; according to the difference characteristics between the independent learning performance trend and the overall learning performance trend of each student in each exam within the historical range of the current exam, the change correlation between the independent learning performance trend and the overall learning performance trend of each student in the current exam is obtained; Obtain each student's score influence factor under the current exam according to the trend of each student's independent learning performance under the current exam and the corresponding change correlation; adjust each student's current original score data according to the score influence factor under the current exam and the change characteristics of all students' original score data to obtain each student's current adjusted score data; cluster all students according to the changes of each student's current adjusted score data and the adjacent previous original score data to obtain student clustering clusters; The test scores are analyzed according to the student clusters.

2. The intelligent analysis system for student test scores according to claim 1 is characterized in that: The method for obtaining the independent learning achievement trend includes: In the neighborhood of each test, a line graph of the original score data of all tests is constructed; the angle between the line segments of adjacent original score data and the horizontal direction is obtained; After normalizing the angles between all adjacent original score data, the average of all normalized mapping results is calculated as the overall score change trend; According to the distribution of the differences between the adjacent original score data, the differences between the same adjacent original score data are adjusted to obtain the average score change level; According to each student's overall score change trend and average score change level, we obtained each student's independent learning effectiveness trend in each exam. Both the overall score change trend and the average score change level are positively correlated with the independent learning effectiveness trend.

3. A student test score intelligent analysis system according to claim 2, characterized in that: The method for obtaining the average score change level includes: In the neighborhood of each test, the difference between the original score data of the next test and the previous test is calculated to obtain the difference sequence corresponding to the adjacent original score data; The number of differences after the corresponding difference of each adjacent original score data in the difference sequence is counted, and negative correlation mapping is performed as the weighted value of the difference corresponding to each adjacent original score data; the difference between adjacent original score data is weighted averaged according to the weighted value of the difference corresponding to each student's different adjacent original score data to obtain the average score change level.

4. The intelligent analysis system for student test scores according to claim 1 is characterized in that: The method for obtaining the overall learning effectiveness trend includes: The independent learning performance trends of all students in each exam are averaged to obtain the overall learning performance trend of all students in each exam.

5. The intelligent analysis system for student test scores according to claim 1 is characterized in that: The method for obtaining the change correlation includes: According to the change difference between each student's independent learning achievement trend and the overall learning achievement trend in the current exam and the matching distance between the independent learning achievement trend and the overall learning achievement trend in all exams in the historical range of the current exam, the change correlation between each student's independent learning achievement trend and the overall learning achievement trend in the current exam is obtained, and the change difference and matching distance are negatively correlated with the change correlation.

6. The intelligent analysis system for student test scores according to claim 1, characterized in that: The method for obtaining the performance influencing factor includes: According to the trend of each student's independent learning effectiveness in the current exam and the corresponding change correlation, the performance influencing factor of each student in the current exam is obtained. The trend and change correlation of independent learning effectiveness are positively correlated with the performance influencing factor.

7. The intelligent analysis system for student test scores according to claim 1 is characterized in that: The method for obtaining the current adjusted score data includes: Determine whether the current original score data of each student needs to be adjusted based on the change characteristics of the original score data of all students. If adjustment is required, obtain the adjustment factor based on the score influence factor of each student in the current exam and the current original score data; After calculating the sum of each student's current original score data and the adjustment factor, normalization mapping is performed to obtain each student's current adjusted score data.

8. The intelligent analysis system for student test scores according to claim 7, characterized in that: The determining whether the current original score data of each student needs to be adjusted according to the change characteristics of the original score data of all students includes: According to the central tendency of the original score data of all students in each test, the overall score level of each test is obtained; If the overall score level of the current exam is not equal to the overall score level of the exam before the current exam, it is determined that the current original score data needs to be adjusted; otherwise, no adjustment is required.

9. The intelligent analysis system for student test scores according to claim 8, characterized in that: The method for obtaining the adjustment factor includes: Calculate the product of each student's score impact factor under the current exam and the current original score data as the first product; If the overall score level of the current test is greater than the overall score level of the test before the current test, the first product is negated and the obtained value is used as the adjustment factor; If the overall score level under the current test is lower than the overall score level of the test before the current test, the first product is used as an adjustment factor.

10. The intelligent analysis system for student test scores according to claim 1, characterized in that: The method for obtaining the student clusters includes: The difference between each student's current adjusted score data and the previous original score data is calculated, and K-means clustering is performed on all students to obtain student clusters.

Images