Value-added information processing method based on examination scores, electronic equipment and storage medium

Abstract

The invention provides a value-added information processing method based on examination scores, electronic equipment and a storage medium, and relates to the technical field of data processing. Comprising the steps of splitting a student set into a plurality of groups according to actual scores of to-be-analyzed students in a target examination in the student set; according to the actual score of each student in the first examination and the actual score of each student in the second examination in each group, establishing a score prediction model corresponding to each group; according to the score prediction model corresponding to each group and the actual score of each student in each group in the first examination, predicting the predicted score of each student in each group in the second examination; according to the predicted score of each student in each group in the second examination and the actual score of each student in the second examination, determining score residual data of each student; according to the score residual data of the to-be-analyzed students and the number of the to-be-analyzed students, value-added information of the to-be-analyzed students in the second examination is determined. And the accuracy of the value-added information calculation result is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, electronic device and storage medium for processing value-added information based on test scores. Background Art

[0002] The SGP (Student Growth Percentile) value-added indicator refers to the value-added indicator in the SGP model used in student growth evaluation. The value-added indicator can be used to evaluate students' academic growth.

[0003] The existing SGP model requires a sufficiently large sample size during calculation to meet the statistical requirements for stability. In addition, the existing SGP model does not take into account the changing patterns brought about by the original scores, nor does it take into account the different changing patterns of different score ranges, resulting in poor accuracy in the calculation results of the SGP value-added index. Summary of the invention

[0004] The purpose of this application is to provide a method, electronic device and storage medium for processing value-added information based on test scores in order to improve the accuracy of the value-added information calculation results in view of the deficiencies in the above-mentioned prior art.

[0005] To achieve the above purpose, the technical solution adopted in the embodiment of the present application is as follows: In a first aspect, an embodiment of the present application provides a method for processing value-added information based on test scores, comprising: According to the actual scores of each to-be-analyzed student in the student set in the target test, the student set is divided into a plurality of groups, each of which includes a plurality of students, and students with the same scores are distributed in the same group; According to the actual scores of each student in each group in the first test and the actual scores of each student in the second test, a score prediction model corresponding to each group is established; Predicting the predicted scores of each student in each group in the second test according to the score prediction model corresponding to each group and the actual scores of each student in each group in the first test; Determine, according to the predicted scores of each student in each group in the second test and the actual scores of each student in each group in the second test, the score residual data of each student in each group, wherein the score residual data is used to represent the difference between the predicted score and the actual score; According to the score residual data of each student to be analyzed and the number of students to be analyzed, the value-added information of each student to be analyzed in the second test is determined.

[0006] Optionally, the student set is divided into a plurality of groups according to the actual scores of each student to be analyzed in the target test in the student set, including: Determine the ranking of each student to be analyzed according to their actual scores in the target test; The student set is divided into multiple groups according to the ranking of each student to be analyzed and the preset group capacity.

[0007] Optionally, establishing a score prediction model corresponding to each group according to the actual score of each student in each group in the first test and the actual score of each student in the second test includes: Establishing an initial prediction model, wherein the initial prediction model includes: a predicted performance parameter, an actual performance parameter, a first constant parameter, and a second constant parameter; According to the initial prediction model and the constraint information between the prediction data and the observation data, an expression of the first constant parameter and an expression of the second constant parameter are established; the expression of the first constant parameter is related to the actual score of each student in the group in the first test and the actual score of each student in the second test; the expression of the second constant parameter is related to the first constant parameter and the actual score of each student in the group in the first test and the actual score of each student in the second test; the constraint information is used to indicate that the residual sum of squares between the prediction data and the observation data is minimized; Determine the value of the first constant parameter corresponding to each group according to the actual score of each student in each group in the first test and the actual score of each student in the second test, and the expression of the first constant parameter; Determine the value of the second constant parameter corresponding to each group according to the value of the first constant parameter corresponding to each group, the actual score of each student in each group in the first test and the actual score of each student in the second test, and the expression of the second constant parameter; Substitute the value of the first constant parameter corresponding to each group and the value of the second constant parameter corresponding to each group into the initial prediction model to obtain the score prediction model corresponding to each group.

[0008] Optionally, the initial prediction model is expressed by the following formula: Y=b 0 X+b 1 , where Y is the predicted performance parameter, X is the actual performance parameter, and b 0 is the second constant parameter, b 1 is the first constant parameter.

[0009] Optionally, the expression of the first constant parameter is: ; The expression of the second constant parameter is: ; in, is the number of students in the group, represents the actual score of the i-th student in the group in the first exam, represents the actual score of the i-th student in the group in the second exam, represents the mean of the actual scores of each student in the group in the first test, It represents the mean of the actual scores of each student in the group in the second test.

[0010] Optionally, predicting the predicted score of each student in each group in the second test according to the score prediction model corresponding to each group and the actual score of each student in each group in the first test includes: Using the actual scores of the target students in the target group in the first test as the values ​​of the actual score parameters in the score prediction model corresponding to the target group, and calculating the values ​​of the predicted score parameters in the score prediction model through the score prediction model corresponding to the target group; The value of the predicted score parameter in the score prediction model is used as the predicted score of the target student in the target group in the second test.

[0011] Optionally, determining the value-added information of each student to be analyzed in the second test according to the score residual data of each student to be analyzed and the number of students to be analyzed includes: Perform residual ranking according to the residual data of the scores of each student to be analyzed, and determine the residual ranking index corresponding to each student to be analyzed; the residual ranking index is used to indicate the rank of the residual ranking; According to the residual ranking index corresponding to each student to be analyzed, the number of students to be analyzed and the target calculation formula, the value-added information of each student to be analyzed in the second test is determined.

[0012] Optionally, determining the value-added information of each student to be analyzed in the second test according to the residual ranking index corresponding to each student to be analyzed, the number of students to be analyzed, and the target calculation formula includes: Substituting the residual ranking index corresponding to the target student to be analyzed and the number of students to be analyzed into the target calculation formula, and calculating the value-added information of the target student to be analyzed in the second test; Among them, the target calculation formula is: PR=100-(100R-50) / N, PR is the calculation result, R is the residual ranking index, and N is the number of students to be analyzed.

[0013] In a second aspect, the embodiment of the present application further provides a value-added information processing device based on test scores, including: a grouping module, a building module, a prediction module, and a determination module; The grouping module is used to divide the student set into multiple groups according to the actual scores of each student to be analyzed in the target test, each of which includes multiple students, and students with the same scores are distributed in the same group; The establishment module is used to establish a score prediction model corresponding to each group according to the actual score of each student in each group in the first test and the actual score of each student in the second test; The prediction module is used to predict the predicted score of each student in each group in the second test according to the score prediction model corresponding to each group and the actual score of each student in each group in the first test; The determination module is used to determine the score residual data of each student in each group according to the predicted score of each student in each group in the second test and the actual score of each student in each group in the second test, wherein the score residual data is used to represent the difference between the predicted score and the actual score; The determination module is used to determine the value-added information of each student to be analyzed in the second test according to the score residual data of each student to be analyzed and the number of students to be analyzed.

[0014] Optionally, the grouping module is specifically used to determine the ranking of each student to be analyzed according to the actual score of each student to be analyzed in the target examination; The student set is divided into multiple groups according to the ranking of each student to be analyzed and the preset group capacity.

[0015] Optionally, the establishment module is specifically used to establish an initial prediction model, wherein the initial prediction model includes: a predicted performance parameter, an actual performance parameter, a first constant parameter, and a second constant parameter; According to the initial prediction model and the constraint information between the prediction data and the observation data, an expression of the first constant parameter and an expression of the second constant parameter are established; the expression of the first constant parameter is related to the actual score of each student in the group in the first test and the actual score of each student in the second test; the expression of the second constant parameter is related to the first constant parameter and the actual score of each student in the group in the first test and the actual score of each student in the second test; the constraint information is used to indicate that the residual sum of squares between the prediction data and the observation data is minimized; Determine the value of the first constant parameter corresponding to each group according to the actual score of each student in each group in the first test and the actual score of each student in the second test, and the expression of the first constant parameter; Determine the value of the second constant parameter corresponding to each group according to the value of the first constant parameter corresponding to each group, the actual score of each student in each group in the first test and the actual score of each student in the second test, and the expression of the second constant parameter; Substitute the value of the first constant parameter corresponding to each group and the value of the second constant parameter corresponding to each group into the initial prediction model to obtain the score prediction model corresponding to each group.

[0016] Optionally, the initial prediction model is expressed by the following formula: Y=b 0 X+b 1 , where Y is the predicted performance parameter, X is the actual performance parameter, and b 0 is the second constant parameter, b 1 is the first constant parameter.

[0017] Optionally, the expression of the first constant parameter is: ; The expression of the second constant parameter is: ; in, is the number of students in the group, represents the actual score of the i-th student in the group in the first exam, represents the actual score of the i-th student in the group in the second exam, represents the mean of the actual scores of each student in the group in the first test, It represents the mean of the actual scores of each student in the group in the second test.

[0018] Optionally, the prediction module is specifically configured to use the actual scores of the target students in the target group in the first test as the values ​​of the actual score parameters in the score prediction model corresponding to the target group, and calculate the values ​​of the predicted score parameters in the score prediction model through the score prediction model corresponding to the target group; The value of the predicted score parameter in the score prediction model is used as the predicted score of the target student in the target group in the second test.

[0019] Optionally, the determination module is specifically used to perform residual ranking according to the residual data of the scores of each student to be analyzed, and determine the residual ranking index corresponding to each student to be analyzed; the residual ranking index is used to indicate the rank of the residual ranking; According to the residual ranking index corresponding to each student to be analyzed, the number of students to be analyzed and the target calculation formula, the value-added information of each student to be analyzed in the second test is determined.

[0020] Optionally, the determination module is specifically used to substitute the residual ranking index corresponding to the target student to be analyzed and the number of students to be analyzed into the target calculation formula to calculate and obtain the value-added information corresponding to the target student to be analyzed in the second test; Among them, the target calculation formula is: PR=100-(100R-50) / N, PR is the calculation result, R is the residual ranking index, and N is the number of students to be analyzed.

[0021] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the storage medium communicate via the bus, and the processor executes the machine-readable instructions to implement the value-added information processing method based on test scores as provided in the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for processing value-added information based on test scores as provided in the first aspect is executed.

[0023] The beneficial effects of this application are: The present application provides a method for processing value-added information based on test scores, an electronic device, and a storage medium, including: dividing a student set into multiple groups according to the actual scores of each to-be-analyzed student in the student set in a target test; establishing a score prediction model corresponding to each group according to the actual scores of each student in each group in a first test and the actual scores of each student in a second test; predicting the predicted scores of each student in each group in a second test according to the score prediction model corresponding to each group and the actual scores of each student in each group in the first test; determining the score residual data of each student in each group according to the predicted scores of each student in the second test and the actual scores of each student in the second test; and determining the value-added information of each student to be analyzed in the second test according to the score residual data of each student to be analyzed and the number of students to be analyzed. This solution can group students based on their actual scores in the student set, and realize grouping students according to different strata and different score distribution ranges, so that the learning level of students in each group is relatively balanced, with reference and comparison; through the two actual scores of each student in the group, the model is constructed to obtain the score prediction model corresponding to each group. The score prediction model can follow the change law of the two scores and make score predictions, making the prediction accuracy of the model higher. Based on the predicted scores and actual scores, the residual results of students can be obtained. Since the score prediction models corresponding to different groups are different, the score change law in different student strata and score distribution ranges is fully considered, making the residual results of students in different score ranges more accurate. Based on the residual results, the percentile is calculated, and the value-added achieved by each student under the change law of his or her stratum can be obtained, which improves the accuracy of the value-added information calculation results.

[0024] In addition, by ranking all students' residual data and calculating the value-added information using the percentile formula, it can be used as a standardized measurement method to evaluate students' learning in a more standardized, intuitive and objective manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 A flowchart of a method for processing value-added information based on test scores provided in an embodiment of the present application; Figure 2A flowchart of another method for processing value-added information based on test scores provided in an embodiment of the present application; Figure 3 A flowchart of another method for processing value-added information based on test scores provided in an embodiment of the present application; Figure 4 A flowchart of another method for processing value-added information based on test scores provided in an embodiment of the present application; Figure 5 A flowchart of another method for processing value-added information based on test scores provided in an embodiment of the present application; Figure 6 A schematic diagram of a value-added information processing device based on test scores provided in an embodiment of the present application; Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0028] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0029] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0030] The SGP (Student Growth Percentile) value-added indicator refers to the value-added indicator in the SGP model used in student growth evaluation. The value-added indicator can be used to evaluate students' academic growth.

[0031] The SGP method also has its applicable conditions and limitations. In statistics, it needs to meet the requirement that the sample size is not less than 5,000 people. Usually, the unified examination at the city and county level can generally meet this requirement, but it is often not met by smaller district-level units and single schools. In response to this problem, some domestic scholars have used the simple SGP algorithm to conduct some empirical analysis and research, but many studies have found that the simple SGP algorithm has large errors and has been questioned. The reason for the large error of the simple SGP algorithm may be that when the sample size is small, the simple model has too many groups and the number of people in the group is too small, and the single group data cannot meet the statistical stability requirements, so the difference between the groups is large, which does not solve the problem of inapplicability for small sample sizes. Moreover, the simple SGP uses the percentile formula PR=100-(100R-50) / N in the calculation principle in both steps, and all calculations are based on the ranking of grade data. It does not take into account the change law of the actual score, which is a continuous data, and loses the possibility that the calculation results are affected by multiple factors such as the difficulty and distribution of the exam, and each score segment has different change laws. Therefore, the accuracy of the simple SGP algorithm in calculating the value-added index is not high.

[0032] Based on this, this solution provides a value-added information processing method based on test scores. Taking into account the differences in the changing rules between student stratification and score distribution intervals, students are grouped according to their score rankings, and a model is constructed through the two actual scores of each student in the group to obtain the score prediction model corresponding to each group. The score prediction model can follow the changing rules of the two scores and make score predictions, making the model more accurate. Based on the predicted scores and actual scores, the residual results of the students can be obtained. Since the score prediction models corresponding to different groups are different, the score change rules in different student stratification and score distribution intervals are fully considered, making the residual results of students in different score ranges more accurate, so that the percentile rank calculation is performed based on the residual results, and the value-added information obtained is more accurate.

[0033] Figure 1 The flowchart of a method for processing value-added information based on test scores provided in an embodiment of the present application is shown in FIG. 1 . The execution subject of the method may be a computer device, such as Figure 1 As shown, the method may include: S101. Split the student set into multiple groups according to the actual scores of each to-be-analyzed student in the student set in the target test.

[0034] Each group includes multiple students, and students with the same scores are distributed in the same group.

[0035] The students included in the student set can be all the candidates of a single school or all the candidates of the district-level examination. The target examination can be a few key examinations selected from multiple examinations or an examination that requires value-added assessment.

[0036] Exemplarily, when the target exam is several key exams among the selected multiple exams, the average of the actual scores of a single student in the several key exams can be used as the student's actual score in the target exam.

[0037] When the target test is a test that requires a value-added assessment, the actual score of this test that requires a value-added assessment can be used as the student's actual score in the target test.

[0038] Optionally, all students to be analyzed in the student set can be grouped according to their actual scores in the target test, so as to achieve grouping of students according to different strata and different score distribution ranges, so that the learning level of students in each group is more balanced, which is of reference and comparison value.

[0039] It is worth noting that the number of students included in each group does not have to be exactly the same, and students with the same grades need to be distributed in the same group.

[0040] S102: Establish a score prediction model corresponding to each group according to the actual score of each student in each group in the first test and the actual score of each student in the second test.

[0041] The first test may refer to a benchmark test, the second test may refer to a comparative test, and the second test may be a test that is later than the first test. According to the actual scores of each student in each group in the first test and the actual scores of each student in the second test, a score prediction model corresponding to each group can be constructed through a linear regression equation. Since the score prediction model is constructed separately for different groups to find the change rules of student scores in the same layer, the model construction with a small sample size is realized.

[0042] S103 . Predict the predicted scores of each student in each group in the second test according to the score prediction model corresponding to each group and the actual scores of each student in each group in the first test.

[0043] Based on the construction method of the score prediction model, the constructed score prediction model can fully learn the changing rules of students' scores in the first examination and the second examination, and based on the changing rules, on the basis of the actual scores of the first examination, predict the predicted scores of each student in each group in the second examination.

[0044] The predicted score is also the expected score, that is, based on the score change pattern of each student in the group and on the premise of following the change pattern, the expected score that the student should achieve in the second exam compared to the actual score in the first exam.

[0045] S104: Determine the score residual data of each student in each group according to the predicted score of each student in each group in the second test and the actual score of each student in each group in the second test.

[0046] The grade residual data are used to characterize the difference between the predicted grades and the actual grades.

[0047] Based on the predicted scores of each student in each group in the second test and the actual scores of each student in the second test, the score residual data of each student in each group can be obtained.

[0048] The residual score data represents the difference between the predicted score that students are expected to achieve under the premise of a sequential change law and the score they actually achieve. The greater the actual score is than the predicted score, the greater the student's progress is than expected.

[0049] S105 , determining the value-added information of each student to be analyzed in the second test according to the score residual data of each student to be analyzed and the number of students to be analyzed.

[0050] Optionally, a percentile calculation may be performed based on the residual score data of all students to be analyzed and the number of students to be analyzed to obtain the percentile corresponding to each student to be analyzed, and the percentile is used as the value-added information of the students to be analyzed in the second test. The number of students to be analyzed also refers to the number of students in the student set.

[0051] Through the above method, we can obtain the added value achieved by each student under the constraints of the changing rules of his or her stratum (or grade segment), thereby improving the accuracy of the added value calculation results.

[0052] By representing the value-added information in percentile form, the integrity of the data can be maintained.

[0053] Optionally, the value-added information of students in the second examination can be used to analyze the academic changes of students in the second examination compared to the first examination, wherein the academic changes may include: learning progress, learning regression, and may also include: slight learning improvement, obvious learning improvement, etc.

[0054] It is worth mentioning that the first test can be used as a benchmark test to compare and analyze the academic changes produced in the second test.

[0055] Assuming that the first test is the previous test, the second test can be the next test corresponding to the previous test, and of course, the second test can also be any test after the previous test. Usually, the first test and the second test can be selected as two consecutive tests to gradually evaluate the student's learning situation.

[0056] In summary, the present embodiment provides a method for processing value-added information based on test scores, comprising: dividing the student set into multiple groups according to the actual scores of each to-be-analyzed student in the student set in the target test; establishing a score prediction model corresponding to each group according to the actual scores of each student in each group in the first test and the actual scores of each student in the second test; predicting the predicted scores of each student in each group in the second test according to the score prediction model corresponding to each group and the actual scores of each student in each group in the first test; determining the score residual data of each student in each group according to the predicted scores of each student in the second test and the actual scores of each student in the second test; determining the value-added information of each student to be analyzed in the second test according to the score residual data of each student to be analyzed and the number of students to be analyzed. This solution can group students based on their actual scores in the student set, and realize grouping students according to different strata and different score distribution ranges, so that the learning level of students in each group is relatively balanced, with reference and comparison; through the two actual scores of each student in the group, the model is constructed to obtain the score prediction model corresponding to each group. The score prediction model can follow the change law of the two scores and make score predictions, making the prediction accuracy of the model higher. Based on the predicted scores and actual scores, the residual results of students can be obtained. Since the score prediction models corresponding to different groups are different, the score change law in different student strata and score distribution ranges is fully considered, making the residual results of students in different score ranges more accurate. Based on the residual results, the percentile is calculated, and the value-added achieved by each student under the change law of his or her stratum can be obtained, which improves the accuracy of the value-added information calculation results.

[0057] Figure 2 A flowchart of another method for processing value-added information based on test scores provided in an embodiment of the present application; optionally, in step S101, the student set is divided into multiple groups according to the actual scores of each student to be analyzed in the target test in the student set, which may include: S201. Determine the ranking of each student to be analyzed based on the actual scores of each student to be analyzed in the target test.

[0058] First, each student to be analyzed can be ranked according to the actual scores in the target test to obtain a ranking sequence of each student to be analyzed.

[0059] S202: Divide the student set into multiple groups according to the ranking of each student to be analyzed and the preset group capacity.

[0060] The preset group capacity may refer to the number of students to be accommodated in a group. Under normal circumstances, the student set may be divided into multiple groups according to the ranking sequence of each student to be analyzed and the preset group capacity.

[0061] For example, assuming that the ranking sequence is {1; 2; 3; 4...N}; N is 500; then, and the preset grouping capacity is 50, students ranked 1-50 are divided into one group, students ranked 51-100 are divided into another group, and so on, until the allocation is completed.

[0062] Of course, there are some cases where the three students ranked 50-52 may have the same scores. In this case, the students ranked 51 and 52 can also be split into the same group as the student ranked 50, and the students ranked 53-102 can be split into another group.

[0063] The above are just some examples of grouping methods. In actual applications, the preset grouping capacity can also be flexibly adjusted, and the number of students ultimately included in different groups may also be different.

[0064] Figure 3 A flowchart of another method for processing value-added information based on test scores provided in an embodiment of the present application; Optionally, in step S102, according to the actual scores of each student in each group in the first test and the actual scores of each student in the second test, a score prediction model corresponding to each group is established, which may include: S301, establishing an initial prediction model, wherein the initial prediction model includes: a predicted performance parameter, an actual performance parameter, a first constant parameter, and a second constant parameter.

[0065] In this embodiment, a univariate linear regression relationship may be used to establish an initial prediction model.

[0066] The initial prediction model can be expressed as: Y=b 0 X+b 1 .

[0067] Among them, Y is the predicted performance parameter, X is the actual performance parameter, and b 0 is the second constant parameter, b 1 is the first constant parameter.

[0068] S302: Establish an expression of a first constant parameter and an expression of a second constant parameter according to an initial prediction model and constraint information between prediction data and observation data.

[0069] Among them, the expression of the first constant parameter is related to the actual score of each student in the group in the first test and the actual score of each student in the second test; the expression of the second constant parameter is related to the first constant parameter and the actual score of each student in the group in the first test and the actual score of each student in the second test; the constraint information is used to indicate that the residual sum of squares between the predicted data and the observed data is minimized.

[0070] Usually, in order to determine the first constant parameter b in a univariate linear regression equation 1 and the second constant parameter b 0 , the least squares method can be used.

[0071] Suppose there is a set of data points , ), , ), , )… , )… , ), the goal is to find b 0 and b 1 , so that Y = b 0 X+b 1 best fit these data points.

[0072] Each data point in the array can correspond to a student in the group. It can represent the student's actual score in the first exam. It can represent the student's actual score in the second test.

[0073] The least squares method determines b by minimizing the sum of squares of the following errors: 0 and b 1 :

[0074] In order to find the minimum value of S, we can 0 and b 1 Find the partial derivatives and set them equal to 0 to obtain the system of equations. By solving the system of equations, we can get the constant parameters b respectively. 1 and the second constant parameter b 0 expression.

[0075] Since the final score prediction model is to predict the score in the second exam by the student's actual score in the first exam, the student's actual score in the second exam can be used as the As observed data, it can also be understood as real data, and the predicted data is Y. Through the expression of the initial prediction model, it can be used Represents forecast data.

[0076] Based on the above derivation process, the first constant parameter b is obtained 1 and the second constant parameter b 0 They are all related to the actual scores of each student in the group in the first exam and the actual scores in the second exam.

[0077] S303: Determine the value of the first constant parameter corresponding to each group according to the actual score of each student in each group in the first test, the actual score of each student in the second test, and the expression of the first constant parameter.

[0078] In this embodiment, the first constant parameter established by the above steps is The expression can be: ; Second constant parameter The expression can be: ; in, is the number of students in the group, represents the actual score of the i-th student in the group in the first exam, represents the actual score of the i-th student in the group in the second exam, represents the mean of the actual scores of each student in the group in the first test, It represents the mean of the actual scores of each student in the group in the second test.

[0079] As shown in the example above, the data points contained in the group are , ), , ), , )… , )… , ), first, we can use the formula based on the actual scores of each student in the group in the first test: , calculate the mean of the actual scores of each student in the group in the first exam In the same way, the mean of the actual scores of each student in the group in the first test is calculated. .

[0080] Then the data points contained in the group , ), , ), , )… , )… , ) and the calculated mean are substituted into the expression of the first constant parameter to calculate the value of the first constant parameter corresponding to the group.

[0081] S304, determining the value of the second constant parameter corresponding to each group according to the value of the first constant parameter corresponding to each group, the actual score of each student in each group in the first test and the actual score of each student in the second test, and the expression of the second constant parameter.

[0082] Then the value of the first constant parameter corresponding to the group and the mean obtained above are and Substitute it into the expression of the second constant parameter to obtain the value of the second constant parameter corresponding to the group.

[0083] Since the actual scores of the students in different groups in the first test and the actual scores of the students in the second test are different, the values ​​of the first constant parameter and the values ​​of the second constant parameter corresponding to the different groups are also different.

[0084] S305. Substitute the value of the first constant parameter corresponding to each group and the value of the second constant parameter corresponding to each group into the initial prediction model to obtain the score prediction model corresponding to each group.

[0085] The initial prediction model can be understood as a model common to all groups. By substituting the value of the first constant parameter corresponding to each group and the value of the second constant parameter corresponding to each group into the initial prediction model, the performance prediction model corresponding to each group can be obtained respectively.

[0086] Since the values ​​of the first constant parameter and the second constant parameter corresponding to each group are different, the score prediction model corresponding to each group is also different and unique. The score prediction model corresponding to each group is fitted based on the two actual scores of each student in the group, and can truly and accurately reflect the score change pattern of each student in the group.

[0087] Figure 4 A flowchart of another method for processing value-added information based on test scores provided in an embodiment of the present application; optionally, in step S103, predicting the predicted score of each student in each group in the second test according to the score prediction model corresponding to each group and the actual score of each student in each group in the first test may include: S401. Taking the actual scores of the target students in the target group in the first test as the values ​​of the actual score parameters in the score prediction model corresponding to the target group, and calculating the values ​​of the predicted score parameters in the score prediction model through the score prediction model corresponding to the target group.

[0088] The target group can be any group among all groups, and the target student can be any student among all students in the target group. When applying the score prediction model to predict scores, since the unknown parameters in the score prediction model are only: actual score parameters and predicted score parameters. Based on the construction process of the score prediction model, it can be known that the actual score of the target student in the first test can be used as the value of the actual score parameter in the score prediction model, so as to calculate the value of the predicted score parameter.

[0089] S402: Using the value of the predicted score parameter in the score prediction model as the predicted score of the target student in the target group in the second test.

[0090] Then, the calculated value of the predicted score parameter can be used as the predicted score of the target student in the target group in the second test.

[0091] For any student in the group, we only need to use the student's actual score in the first test as input and input it into the score prediction model corresponding to the group to obtain the student's predicted score in the second test.

[0092] Optionally, in step S104, determining the score residual data of each student in each group according to the predicted score of each student in each group in the second test and the actual score of each student in each group in the second test may include: The predicted score of the target student in the target group in the second test is calculated from the actual score of the target student in the second test to obtain the score residual data of the target student. The score residual data refers to the difference between the actual score and the expected score.

[0093] Figure 5 A flowchart of another method for processing value-added information based on test scores provided in an embodiment of the present application; optionally, in step S105, determining the value-added information of each student to be analyzed in the second test according to the score residual data of each student to be analyzed and the number of students to be analyzed may include: S501. Perform residual ranking according to the residual data of the scores of each student to be analyzed, and determine the residual ranking index corresponding to each student to be analyzed.

[0094] The residual ranking index is used to indicate the ranking of the residual ranking.

[0095] By performing residual ranking on the residual data of the scores of each student to be analyzed, a residual ranking index corresponding to each student to be analyzed can be obtained. In this embodiment, the rank of the residual ranking is used as the residual ranking index, so that the residual ranking index can indicate the relative position of each student to be analyzed in the student set.

[0096] The residual can reflect the degree of deviation between students' actual scores and expected scores, thereby revealing the students' learning progress or regression.

[0097] In this embodiment, when residual ranking is performed based on the score residual data, the ranking is performed from large to small. The larger the score residual data, the higher the ranking, and the smaller the corresponding residual ranking index.

[0098] S502: Determine the value-added information of each student to be analyzed in the second test according to the residual ranking index corresponding to each student to be analyzed, the number of students to be analyzed, and the target calculation formula.

[0099] Optionally, the target calculation formula may adopt a percentile formula, and the specific formula is as follows: PR=100-(100R-50) / N, where PR is the calculation result, R is the residual ranking index, and N is the number of students to be analyzed.

[0100] Percentile rank provides a standardized measurement method, making it more objective to compare the performance of different students, at different times, and in different subjects. Through percentile rank, we can intuitively understand the relative position of students in the whole and thus evaluate their learning progress.

[0101] For each student to be analyzed, the residual ranking index of the student to be analyzed and the number of students to be analyzed can be substituted into the target calculation formula to obtain the calculation result PR corresponding to the student to be analyzed, and the calculation result can be used as the value-added information of the student to be analyzed in the second test.

[0102] The number of students to be analyzed refers to the total number of students in the student set.

[0103] By analyzing the value-added information of the students in the second test, the degree of change in the students' learning compared to the first test can be evaluated.

[0104] In some embodiments, the value-added information in the second test can be compared with a threshold to assess the degree of learning change of the student.

[0105] Since the calculated value-added information is a percentile between 1 and 100, assuming that the threshold is set to 50, it can be determined that when the value-added information exceeds 50, the student's learning has improved compared to the first exam, and when the value-added information is less than 50, it is considered that the student's learning has regressed, and when the value-added information is exactly 50, it is considered that the student's learning remains stable. Among them, when the value-added information exceeds 50, the more it exceeds, the greater the learning progress can be considered. Similarly, when the value-added information is less than 50, the more it is less than 50, the greater the learning regression is considered.

[0106] Of course, a threshold interval can also be set. For example, when the value-added information is between 1 and 35, it is considered that learning has regressed; when the value-added information is between 36 and 70, it is considered that learning has improved slightly; and when the value-added information is between 71 and 100, it is considered that learning has improved significantly.

[0107] From the above percentile calculations, it can be seen that when a student’s actual score is higher than the predicted score, the student’s residual ranking index is smaller, the value-added information is greater, and thus the learning progress is greater.

[0108] Since the predicted grades are the grades that students should achieve based on the pattern of grade changes in the student's stratification, the higher the student's actual grade is than the predicted grade, the more progress the student has made beyond expectations and the greater the student's value-added information.

[0109] By ranking all students' residual data and using the percentile formula to calculate the value-added information, a standardized measurement method can be used to evaluate students' learning progress. This method has the advantages of standardization, intuitiveness and personalization, which helps to develop more appropriate learning plans and teaching strategies.

[0110] In summary, the present embodiment provides a method for processing value-added information based on test scores, comprising: dividing the student set into multiple groups according to the actual scores of each to-be-analyzed student in the student set in the target test; establishing a score prediction model corresponding to each group according to the actual scores of each student in each group in the first test and the actual scores of each student in the second test; predicting the predicted scores of each student in each group in the second test according to the score prediction model corresponding to each group and the actual scores of each student in each group in the first test; determining the score residual data of each student in each group according to the predicted scores of each student in the second test and the actual scores of each student in the second test; determining the value-added information of each student to be analyzed in the second test according to the score residual data of each student to be analyzed and the number of students to be analyzed. This solution can group students based on their actual scores in the student set, and realize grouping students according to different strata and different score distribution ranges, so that the learning level of students in each group is relatively balanced, with reference and comparison; through the two actual scores of each student in the group, the model is constructed to obtain the score prediction model corresponding to each group. The score prediction model can follow the change law of the two scores and make score predictions, making the prediction accuracy of the model higher. Based on the predicted scores and actual scores, the residual results of students can be obtained. Since the score prediction models corresponding to different groups are different, the score change law in different student strata and score distribution ranges is fully considered, making the residual results of students in different score ranges more accurate. Based on the residual results, the percentile is calculated, and the value-added achieved by each student under the change law of his or her stratum can be obtained, which improves the accuracy of the value-added information calculation results.

[0111] In addition, by ranking all students' residual data and calculating the value-added information using the percentile formula, it can be used as a standardized measurement method to evaluate students' learning in a more standardized, intuitive and objective manner.

[0112] The following describes the apparatus, device, storage medium, etc. used to execute a method for processing value-added information based on test scores provided in this application. The specific implementation process and technical effects are described above and will not be repeated below.

[0113] Figure 6 A schematic diagram of a value-added information processing device based on test scores provided in an embodiment of the present application, the functions implemented by the device correspond to the steps performed by the above method. The device can be understood as the above-mentioned computer device, or server, or server processor, or can also be understood as a component independent of the above-mentioned server or processor that implements the functions of the present application under the control of the server, such as Figure 6As shown, the apparatus may include: a grouping module 610, a building module 620, a prediction module 630, and a determination module 640; A grouping module 610 is used to divide the student set into multiple groups according to the actual scores of each student to be analyzed in the target test, each group includes multiple students, and students with the same scores are distributed in the same group; Establishing module 620, for establishing a score prediction model corresponding to each group according to the actual score of each student in each group in the first test and the actual score of each student in the second test; Prediction module 630, used to predict the predicted score of each student in each group in the second test according to the score prediction model corresponding to each group and the actual score of each student in each group in the first test; A determination module 640 is used to determine the score residual data of each student in each group according to the predicted score of each student in each group in the second test and the actual score of each student in each group in the second test, wherein the score residual data is used to represent the difference between the predicted score and the actual score; The determination module 640 is used to determine the value-added information of each student to be analyzed in the second test according to the score residual data of each student to be analyzed and the number of students to be analyzed.

[0114] Optionally, the grouping module 610 is specifically used to determine the ranking of each student to be analyzed according to the actual score of each student to be analyzed in the target test; The student set is divided into multiple groups according to the ranking of each student to be analyzed and the preset group capacity.

[0115] Optionally, a building module 620 is specifically used to build an initial prediction model, the initial prediction model includes: a predicted performance parameter, an actual performance parameter, a first constant parameter and a second constant parameter; According to the initial prediction model and the constraint information between the prediction data and the observation data, an expression of the first constant parameter and an expression of the second constant parameter are established; the expression of the first constant parameter is related to the actual score of each student in the group in the first test and the actual score of each student in the second test; the expression of the second constant parameter is related to the first constant parameter and the actual score of each student in the group in the first test and the actual score of each student in the second test; the constraint information is used to indicate that the residual sum of squares between the prediction data and the observation data is minimized; Determine the value of the first constant parameter corresponding to each group according to the actual score of each student in each group in the first test, the actual score of each student in the second test, and the expression of the first constant parameter; Determine the value of the second constant parameter corresponding to each group according to the value of the first constant parameter corresponding to each group, the actual score of each student in each group in the first test and the actual score of each student in the second test, and the expression of the second constant parameter; Substitute the value of the first constant parameter corresponding to each group and the value of the second constant parameter corresponding to each group into the initial prediction model to obtain the score prediction model corresponding to each group.

[0116] Optionally, the initial prediction model is expressed by the following formula: Y=b 0 X+b 1 , where Y is the predicted performance parameter, X is the actual performance parameter, and b 0 is the second constant parameter, b 1 is the first constant parameter.

[0117] Optionally, the expression of the first constant parameter is: ; The expression of the second constant parameter is: ; in, is the number of students in the group, represents the actual score of the i-th student in the group in the first exam, represents the actual score of the i-th student in the group in the second exam, represents the mean of the actual scores of each student in the group in the first test, It represents the mean of the actual scores of each student in the group in the second test.

[0118] Optionally, the prediction module 630 is specifically configured to use the actual scores of the target students in the target group in the first test as the values ​​of the actual score parameters in the score prediction model corresponding to the target group, and calculate the values ​​of the predicted score parameters in the score prediction model through the score prediction model corresponding to the target group; The value of the predicted score parameter in the score prediction model is used as the predicted score of the target student in the target group in the second test.

[0119] Optionally, the determination module 640 is specifically used to perform residual ranking according to the residual data of the scores of each student to be analyzed, and determine the residual ranking index corresponding to each student to be analyzed; the residual ranking index is used to indicate the rank of the residual ranking; According to the residual ranking index corresponding to each student to be analyzed, the number of students to be analyzed and the target calculation formula, the value-added information of each student to be analyzed in the second test is determined.

[0120] Optionally, the determination module 640 is specifically configured to substitute the residual ranking index corresponding to the target student to be analyzed and the number of students to be analyzed into the target calculation formula to calculate the value-added information corresponding to the target student to be analyzed in the second test; Among them, the target calculation formula is: PR=100-(100R-50) / N; Among them, PR is the calculation result, R is the residual ranking index, and N is the number of students to be analyzed.

[0121] The above-mentioned device is used to execute the method provided by the aforementioned embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0122] The above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more digital singnal processors (DSP), or one or more field programmable gate arrays (FPGA). For another example, when a module is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0123] The above modules can be connected or communicated with each other via a wired connection or a wireless connection. The wired connection may include a metal cable, an optical cable, a hybrid cable, etc., or any combination thereof. The wireless connection may include a connection in the form of a LAN, a WAN, Bluetooth, a ZigBee, or NFC, or any combination thereof. Two or more modules may be combined into a single module, and any one module may be divided into two or more units. Those skilled in the art will clearly understand that for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in this application.

[0124] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application; the device may be integrated into a terminal device or a chip of a terminal device; and the terminal may be a computing device with data processing capabilities.

[0125] The device includes: a processor 701 and a storage medium 702 .

[0126] The storage medium 702 is used to store programs, and the processor 701 calls the programs stored in the storage medium 702 to execute the above method embodiment. The specific implementation method and technical effect are similar and will not be repeated here.

[0127] Among them, the storage medium 702 stores program code. When the program code is executed by the processor 701, the processor 701 executes various steps in the value-added information processing method based on test scores according to various exemplary embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0128] Processor 701 may be a general-purpose processor, such as a central processing unit (CPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, and may implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application may be directly embodied as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0129] The storage medium 702, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The storage medium may include at least one type of storage medium, for example, a flash memory, a hard disk, a multimedia card, a card-type storage medium, a random access storage medium (Random Access Memory, RAM), a static random access storage medium (Static Random Access Memory, SRAM), a programmable read-only storage medium (Programmable Read Only Memory, PROM), a read-only storage medium (Read Only Memory, ROM), an electrically erasable programmable read-only storage medium (Electrically Erasable Programmable Read-Only Memory, EEPROM), a magnetic storage medium, a disk, an optical disk, and the like. The storage medium is any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The storage medium 702 in the embodiment of the present application can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0130] Optionally, the present application also provides a program product, such as a computer-readable storage medium, including a program, which is used to execute the above method embodiment when executed by a processor.

[0131] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0132] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0133] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0134] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: processor) to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only storage medium (English: Read-Only Memory, referred to as: ROM), random access storage medium (English: Random Access Memory, referred to as: RAM), disk or optical disk and other media that can store program codes.

Claims

1. A method for processing value-added information based on test scores, characterized in that: include: According to the actual scores of each to-be-analyzed student in the student set in the target test, the student set is divided into a plurality of groups, each of which includes a plurality of students, and students with the same scores are distributed in the same group; According to the actual scores of each student in each group in the first test and the actual scores of each student in the second test, a score prediction model corresponding to each group is established; Predicting the predicted scores of each student in each group in the second test according to the score prediction model corresponding to each group and the actual scores of each student in each group in the first test; Determine, according to the predicted scores of each student in each group in the second test and the actual scores of each student in each group in the second test, the score residual data of each student in each group, wherein the score residual data is used to represent the difference between the predicted score and the actual score; According to the score residual data of each student to be analyzed and the number of students to be analyzed, the value-added information of each student to be analyzed in the second test is determined.

2. The method according to claim 1, characterized in that The student set is divided into a plurality of groups according to the actual scores of each student to be analyzed in the target test, including: Determine the ranking of each student to be analyzed according to their actual scores in the target test; The student set is divided into multiple groups according to the ranking of each student to be analyzed and the preset group capacity.

3. The method according to claim 1, characterized in that The step of establishing a score prediction model corresponding to each group according to the actual scores of each student in each group in the first test and the actual scores of each student in the second test includes: Establishing an initial prediction model, wherein the initial prediction model includes: a predicted performance parameter, an actual performance parameter, a first constant parameter, and a second constant parameter; According to the initial prediction model and the constraint information between the prediction data and the observation data, an expression of the first constant parameter and an expression of the second constant parameter are established; the expression of the first constant parameter is related to the actual score of each student in the group in the first test and the actual score of each student in the second test; the expression of the second constant parameter is related to the first constant parameter and the actual score of each student in the group in the first test and the actual score of each student in the second test; the constraint information is used to indicate that the residual sum of squares between the prediction data and the observation data is minimized; Determine the value of the first constant parameter corresponding to each group according to the actual score of each student in each group in the first test and the actual score of each student in the second test, and the expression of the first constant parameter; Determine the value of the second constant parameter corresponding to each group according to the value of the first constant parameter corresponding to each group, the actual score of each student in each group in the first test and the actual score of each student in the second test, and the expression of the second constant parameter; Substitute the value of the first constant parameter corresponding to each group and the value of the second constant parameter corresponding to each group into the initial prediction model to obtain the score prediction model corresponding to each group.

4. The method according to claim 3, characterized in that The initial prediction model is expressed by the following formula: Y=b0X+b1, wherein Y is the predicted performance parameter, X is the actual performance parameter, b0 is the second constant parameter, and b1 is the first constant parameter.

5. The method according to claim 3, characterized in that: The expression of the first constant parameter is: ; The expression of the second constant parameter is: ; in, is the number of students in the group, represents the actual score of the i-th student in the group in the first exam, represents the actual score of the i-th student in the group in the second exam, represents the mean of the actual scores of each student in the group in the first test, It represents the mean of the actual scores of each student in the group in the second test.

6. The method according to claim 3, characterized in that The predicting the predicted score of each student in each group in the second test according to the score prediction model corresponding to each group and the actual score of each student in each group in the first test includes: Using the actual scores of the target students in the target group in the first test as the values ​​of the actual score parameters in the score prediction model corresponding to the target group, and calculating the values ​​of the predicted score parameters in the score prediction model through the score prediction model corresponding to the target group; The value of the predicted score parameter in the score prediction model is used as the predicted score of the target student in the target group in the second test.

7. The method according to claim 1, characterized in that The step of determining the value-added information of each student to be analyzed in the second test according to the residual score data of each student to be analyzed and the number of students to be analyzed includes: Perform residual ranking according to the residual data of the scores of each student to be analyzed, and determine the residual ranking index corresponding to each student to be analyzed; the residual ranking index is used to indicate the rank of the residual ranking; According to the residual ranking index corresponding to each student to be analyzed, the number of students to be analyzed and the target calculation formula, the value-added information of each student to be analyzed in the second test is determined.

8. The method according to claim 7, characterized in that Determining the value-added information of each student to be analyzed in the second test according to the residual ranking index corresponding to each student to be analyzed, the number of students to be analyzed, and the target calculation formula includes: The residual ranking index corresponding to the target student to be analyzed and the number of students to be analyzed are substituted into the target calculation formula to calculate the value-added information of the target student to be analyzed in the second test, wherein the target calculation formula is: PR=100-(100R-50) / N, PR is the calculation result, R is the residual ranking index, and N is the number of students to be analyzed.

9. An electronic device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores program instructions executable by the processor. When the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the program instructions to implement the value-added information processing method based on test scores as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method for processing value-added information based on test scores as claimed in any one of claims 1 to 8 is implemented.

Images