Method and device for generating score improvement scheme
By obtaining students' test score data, daily score indicators and student performance indicators, evaluating the correlation between different indicator combinations, and generating a score improvement plan that is most suitable for students, solving the problem of in-depth analysis and data correlation in the existing technology. The problem of this achievement has achieved more accurate results.
Patent Information
- Application Number
- CN202411398128.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-09
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
When generating student achievement improvement plans, the existing technology cannot deeply analyze the relevant factors that lead to poor grades, and the correlation between data is not taken into account, resulting in inaccurate plans.
By obtaining students' test score data, daily grade indicators and student performance indicators, we determine the sample data set that meets the correlation verification conditions, and input them into the fusion model to evaluate the correlation between different indicator combinations and determine the most suitable one for students. Target indicator combination.
Ensure that the correlation between the data is fully considered, and the generated grade improvement plan is more accurate, which can help students accurately identify the most relevant factors that affect grades, thereby improving grades.
Smart Images

Figure CN118917744A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing technology, and in particular to a method and device for generating a performance improvement plan. Background Art
[0002] In recent years, with the continuous advancement of computer technology and educational informatization, computer and artificial intelligence technology have gradually been applied to daily educational and teaching activities. Analyzing student performance can effectively help students improve their learning methods and strategies, and can also help schools and parents understand students' learning abilities in a timely manner and customize learning plans.
[0003] At present, the main method is to obtain a large number of historical test scores of students, analyze the student's score distribution chart, and then obtain information such as the mean score. Then, based on the recent test score status, obtain the student's score analysis results and generate a student's score improvement plan.
[0004] However, the grade improvement plan generated in this way can only obtain the changes in student grades based on student grades, which will cause the results of the analysis to be affected by subjective human factors. For example, factors such as student poor performance and uneven exam difficulty will cause errors in the results of the grade analysis, and the generated grade improvement plan will be unable to accurately determine the relevant factors that lead to poor student grades, which will in turn cause the grade improvement plan to be incompatible with the students and unable to help students improve their grades.
[0005] In addition, in the process of generating plans to improve students' grades, the existing technology does not consider the impact of the correlation between data on the generated plan. Instead, the collected data is simply pre-processed to reduce the errors between the data, and then input into the evaluation model for analysis. This method destroys the original characteristics of the data and thus affects the accuracy of the generated plan.
[0006] How to efficiently generate student performance improvement plans, ensure the correlation between collected data, and retain the true characteristics of the original data for predictive analysis is an urgent problem to be solved in this field. Summary of the invention
[0007] In view of this, the present application provides a method and device for generating a score improvement plan, the main purpose of which is to improve the current existing technology that can only obtain changes in student grades based on student grades, but cannot conduct in-depth analysis, resulting in the score analysis results only reflecting subjects with poor grades, and cannot deeply determine the relevant factors that lead to students' poor grades, which in turn leads to the technical problem that the generated score analysis report cannot accurately help students improve their grades.
[0008] In a first aspect, the present application provides a method for generating a performance improvement plan, comprising: Obtain test score data, regular performance indicators and student performance indicators of target students; Determine a sample data set that meets the correlation verification condition from the test score data, the regular performance index and the student performance index; Inputting the sample data set into the fusion model, evaluating the correlation between the various indicator combinations between the regular performance indicators and the student performance indicators in the sample data set and the test performance data in the sample data set, and determining the target indicator combination with the highest adaptability to the target student based on the obtained correlation evaluation results; The target indicator combination is sent to the target student as a performance improvement plan for the target student.
[0009] Optionally, determining a sample data set that meets the correlation verification condition from the test score data, the regular score index, and the student performance index includes: Determine a sample data set to be verified based on the regular performance index and the student performance index; Based on the test score data, determining a standard sample data set corresponding to the sample data set to be verified; Performing significant correlation verification on the sample data set to be verified based on the standard sample data set to obtain a target sample data set in the sample data set to be verified that meets the correlation verification condition; The target sample data set and the standard sample data set are determined as the sample data sets.
[0010] Optionally, performing significant correlation verification on the sample data set to be verified based on the standard sample data set to obtain a target sample data set that meets the correlation verification condition in the sample data set to be verified includes: Determine the correlation test value based on the sample value of the standard sample data set, the sample mean and the sample standard deviation of the sample data set to be verified by the following formula 1; Based on a predetermined test level α, a predetermined threshold value P and the correlation verification value t, performing significant correlation verification on the sample data set to be verified; If it is determined that t<p, it means that P>α at the t-test value level, and it is determined that there is a significant correlation between the sample data set to be verified and the standard sample data set; If it is determined that t>p, it means that P<α at the t-test value level, and it is determined that there is no significant correlation between the sample data set to be verified and the standard sample data set; Taking the sample data set to be verified with significant correlation as the target sample data set; Formula 1 In Formula 1, u0 represents the sample mean of the sample data set to be verified, u represents the sample value of the standard sample data set, s represents the sample standard deviation of the sample data set to be verified, and n represents the sample size of the sample data set to be verified.
[0011] Optionally, the step of inputting the sample data set into a fusion model and evaluating the correlation between a plurality of indicator combinations between regular performance indicators and student performance indicators in the sample data set and the test performance data in the sample data set, respectively, includes: Based on the test score data set in the sample data set and the first data set including multiple regular performance indicators, constructing a first prediction model in the fusion model to predict the correlation between the test score data and the regular performance indicators; Based on the test score data set in the sample data set and the second data set including multiple student performance indicators, construct a second prediction model in the fusion model to predict the correlation between the test score data and the student performance indicators; The first prediction model is used as the first prediction parameter of the correlation evaluation model in the fusion model, and the second prediction model is used as the second prediction parameter of the correlation evaluation model. The first prediction parameter and the second prediction parameter are cross-combined to construct the correlation evaluation model to evaluate the correlation between the test score data and the multiple indicator combinations.
[0012] Optionally, the process of evaluating the correlation between the test score data and the plurality of indicator combinations includes: Based on the first prediction result obtained by predicting the regular performance index in each indicator combination through the first prediction model, and the second prediction result obtained by predicting the student performance index in each indicator combination through the second prediction model, covariance processing is performed through the following formula 2 to obtain the correlation evaluation results between the test score data and the multiple indicator combinations respectively; Formula 2 In formula 2, cov means covariance processing. represents variance, and XY represents different first prediction parameters and second prediction parameters corresponding to a set of indicator combinations.
[0013] Optionally, determining the target indicator combination with the highest adaptability to the target student based on the obtained correlation evaluation result includes: Selecting a predetermined number of indicator combinations with the highest correlation evaluation results from the multiple indicator combinations to form candidate indicator combinations; Based on the normalized evaluation value of the candidate indicator combination and the weight value of each indicator in the candidate indicator combination, constructing a suitability evaluation model in the fusion model to evaluate the suitability of the candidate indicator combination with the target student; Based on the adaptability evaluation model, the target indicator combination with the highest adaptability to the target student is determined among the multiple indicator combinations.
[0014] Optionally, constructing the adaptability evaluation model in the fusion model based on the normalized evaluation value of the candidate indicator combination and the weight value of each indicator in the candidate indicator combination includes: The correlation evaluation result obtained by the candidate indicator combination in the correlation evaluation model is normalized by the following formula 3 to obtain a normalized evaluation value of the candidate indicator combination; Formula 3 In Formula 3, P is a normalized evaluation value, xmin is a minimum value among the correlation evaluation results corresponding to the plurality of candidate indicator combinations, xmax is a maximum value among the correlation evaluation results corresponding to the plurality of candidate indicator combinations, and xori is a normalized correlation evaluation result of the candidate indicators; Performing standard deviation analysis on the normalized evaluation value using the following formula 4 to obtain the standard deviation value of the candidate indicator combination; Formula 4 In formula 4, SW is the standard deviation corresponding to the candidate indicator combination, Pi is the normalized evaluation value corresponding to the i-th candidate indicator combination, is the average value of the normalized evaluation value corresponding to the i-th candidate indicator combination, and n represents the number of candidate indicator combinations; According to the standard deviation value, the weight value of each indicator in the candidate indicator combination is determined by the following formula 5; Formula 5 In formula 5, qj is the weight value of the jth indicator in the candidate indicator combination, SWj is the standard deviation value of the jth candidate indicator combination, and k is the number of indicators included in the candidate indicator combination; Based on the normalized evaluation value and the weight value of each indicator in the candidate indicator combination, an adaptability evaluation model in the fusion model is constructed.
[0015] Optionally, the constructing the adaptability evaluation model in the fusion model based on the normalized evaluation value of the candidate indicator combination and the weight value of each indicator in the candidate indicator combination further includes: The adaptability evaluation model is constructed by the following formula 6 to obtain the adaptability evaluation result: ; Formula 6 In formula 6, is the suitability evaluation result of the i-th candidate indicator combination, q j is the weight value of the jth indicator in the candidate indicator combination, is the normalized evaluation value of the i-th candidate indicator combination.
[0016] In a second aspect, the present application provides a device for generating a performance improvement plan, comprising: An acquisition module is configured to acquire test score data, regular performance indicators, and student performance indicators of target students; A determination module is configured to determine a sample data set that meets the correlation verification condition from the test score data, the regular score index and the student performance index; An evaluation module is configured to input the sample data set into a fusion model, evaluate the correlation between the various indicator combinations between the regular performance indicators and the student performance indicators in the sample data set and the test performance data in the sample data set, and determine the target indicator combination with the highest adaptability to the target student based on the obtained correlation evaluation results; The sending module is configured to send the target indicator combination to the target student as a performance improvement plan for the target student.
[0017] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for generating a performance improvement plan described in the first aspect is implemented.
[0018] In a fourth aspect, the present application provides an electronic device comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the method for generating a performance improvement plan as described in the first aspect when executing the computer program.
[0019] By means of the above technical scheme, the present application provides a method and device for generating a score improvement plan. Compared with the current existing technology, the present application fully considers the influence of the correlation between data on the generation plan by determining a sample data set that meets the correlation verification conditions from the test score data, the regular score indicators and the student performance indicators, and ensures the correlation between the collected data, and can retain the true characteristics of the original data to a greater extent for predictive analysis; by inputting the sample data set into the fusion model, the correlation between the various indicator combinations between the regular score indicators and the student performance indicators in the sample data set and the test score data in the sample data set is evaluated respectively, and the target indicator combination with the highest adaptability to the target student is determined based on the obtained correlation evaluation results. On the basis of the correlation evaluation based on the regular score indicators, the student performance indicators can be introduced for evaluation, which can make the evaluation results more accurate. The target indicator combination can also be more accurately determined in the multiple indicator combinations through the correlation evaluation and adaptability evaluation, and then the student's score improvement plan is generated, so that the generated score improvement plan has the highest adaptability to the student, which can help students accurately find the most relevant factors affecting the grades, and then accurately help students improve their grades. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0022] Figure 1 A schematic diagram of a process for generating a performance improvement plan provided in an embodiment of the present application is shown; Figure 2 A schematic diagram of a process for generating a performance improvement plan provided in an embodiment of the present application is shown; Figure 3 A schematic diagram of a process for generating a performance improvement plan provided in an embodiment of the present application is shown; Figure 4 A schematic diagram showing an example provided by an embodiment of the present application; Figure 5 A schematic diagram showing an example provided by an embodiment of the present application; Figure 6 A schematic diagram of a process for generating a performance improvement plan provided in an embodiment of the present application is shown; Figure 7 A schematic diagram of the structure of a device for generating a performance improvement solution provided in an embodiment of the present application is shown; Figure 8 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION
[0023] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.
[0024] In order to improve the technical problem that the existing technology can only obtain the change of student grades based on student grades, but cannot conduct in-depth analysis, the result of the grade analysis can only reflect the subjects with poor grades, and cannot deeply determine the relevant factors that lead to the poor grades of students, and thus the generated grade analysis report cannot accurately help students improve their grades. This embodiment provides a method for generating a grade improvement plan, such as Figure 1 As shown, the method includes: Step 101: Obtain the test score data, regular performance indicators and student performance indicators of the target students.
[0025] In an embodiment of the present application, the target student may be any one or more of the students whose performance analysis is required. Accordingly, the test performance data may include the performance of a single test of the target student or the performance of multiple tests of the target student.
[0026] Furthermore, regular performance indicators may include daily homework scores, teacher scores and classroom performance scores; student performance indicators may include the target students' learning environment indicators, learning status indicators, learning style indicators and learning behavior indicators.
[0027] Step 102: Determine a sample data set that meets the correlation verification conditions from the test score data, regular performance indicators, and student performance indicators.
[0028] In the embodiment of the present application, because the direct embodiment of the effects of regular performance indicators and student performance indicators is the test score data, there is a certain significant correlation between the test score data and the regular performance indicators and student performance indicators, but there may be one or more performances between the regular performance indicators and the student performance indicators that are close to the scores of the test score data, while the others are poor.
[0029] Correspondingly, there are also situations where the test score data is high, while the scores of regular performance indicators and student performance indicators are low. This type of data is relatively extreme, and there is obviously no correlation between the test score data and the regular performance indicators and student performance indicators. This type of data is input into the model training as a training sample set, which will affect the model's fit and prediction accuracy. Therefore, the single sample verification method is adopted to verify the direct and significant correlation between the test score data of a single sample and the regular performance indicators and student performance indicators.
[0030] In some examples, the sample data set is a data set consisting of data that meets the significant correlation criteria between test score data and regular performance indicators and student performance indicators.
[0031] Step 103: Input the sample data set into the fusion model, evaluate the correlation between the various indicator combinations between the regular performance indicators and the student performance indicators in the sample data set and the test score data in the sample data set, and determine the target indicator combination with the highest adaptability to the target student based on the obtained correlation evaluation results.
[0032] In some examples, the fusion model may include a correlation analysis module and a suitability analysis module used in step 103. Specifically, the fusion model may integrate the student's regular grades and performance, and output the most suitable performance improvement plan for the target student by performing correlation evaluation and suitability analysis.
[0033] Furthermore, the correlation evaluation can evaluate several combinations of indicators that are most relevant to students' test scores.
[0034] Exemplarily, in the fusion model, several indicator combinations can be selected from a plurality of indicator combinations through the correlation analysis module, for example, the selected indicator combinations are indicator combination A, indicator combination B, indicator combination C and indicator combination D; further, in step 103, the adaptability analysis module can be used to further select the indicator combination with the highest adaptability from the selected indicator combination A, indicator combination B, indicator combination C and indicator combination D.
[0035] Step 104: Send the target indicator combination to the target student as a performance improvement plan for the target student.
[0036] It should be noted that the generated performance improvement plan, when including a target indicator combination, may also include the improvement method corresponding to each indicator in the target combination, as well as the improvement method for the overall indicator combination, etc. The specific content of the performance improvement plan is not limited here.
[0037] Furthermore, the performance improvement plan may be a performance analysis report, a performance analysis video, a performance analysis icon, a performance analysis animation, etc. The specific form of the performance improvement plan is not limited herein.
[0038] Compared with the current existing technology, this embodiment fully considers the impact of the correlation between data on the generation plan by determining a sample data set that meets the correlation verification conditions from the test score data, the regular score indicators and the student performance indicators, ensures the correlation between the collected data, and can retain the true characteristics of the original data to a greater extent for predictive analysis; by inputting the sample data set into the fusion model, the correlation between the various indicator combinations between the regular score indicators and the student performance indicators in the sample data set and the test score data in the sample data set is evaluated respectively, and the target indicator combination with the highest adaptability to the target student is determined based on the obtained correlation evaluation results. On the basis of the correlation evaluation based on the regular score indicators, the student performance indicators can be introduced for evaluation, which can make the evaluation results more accurate. The target indicator combination can also be more accurately determined from the various indicator combinations through the correlation evaluation and adaptability evaluation, and then the student's score improvement plan is generated, so that the generated score improvement plan has the highest adaptability to the student, which can help students accurately find the most relevant factors affecting the score, and then accurately help students improve their scores.
[0039] As a refinement and extension of the above embodiment, when determining a sample data set that meets the correlation verification condition from the test score data, the regular score index and the student performance index, the following methods may be used but are not limited to: Figure 2 As shown, the method includes: Step 201: Determine a sample data set to be verified based on regular performance indicators and student performance indicators.
[0040] In an embodiment of the present application, the sample data set to be verified is a collection of data sets corresponding to regular performance indicators and data sets corresponding to student performance indicators. For example, the regular performance indicators include daily homework scores w2, teacher scores w3, and classroom performance scores w4, and correspondingly, learning environment indicators w5, learning status indicators w6, learning style indicators w7, and learning behavior indicators w8; further, the sample data set to be verified is a collection of data corresponding to w2~w8.
[0041] Step 202: Based on the test score data, determine the standard sample data set corresponding to the sample data set to be verified.
[0042] In some examples, based on step 201 , the test score data may be represented by w1 , and the standard sample data set is a data set determined based on the test score data w1 .
[0043] Specifically, the test score data w1 may be historical test scores corresponding to the tests that the student has participated in. The specific historical test scores may include weekly test scores, monthly test scores, midterm test scores, final test scores, and the like.
[0044] The daily homework score w2 may be the score of the homework assigned by the teacher in the student's daily study, which may specifically include classroom homework scores, in-class test scores, winter vacation homework scores, summer vacation homework scores, etc.
[0045] The teacher score w3 may be the score obtained by the teacher on the student's learning situation, which may specifically include the teacher's comprehensive score on the student's homework completion, grade fluctuations, daily performance and other abilities.
[0046] The classroom performance score w4 can be obtained by the teacher's scoring of the student's learning situation during class, and can specifically include the teacher's comprehensive performance score of the student's speech, enthusiasm, knowledge mastery, etc. in class.
[0047] The learning environment index w5 includes the comprehensive scores of students' individual, group, collective, and discrete learning environments. For example, the learning environment index w5 can be obtained through a comprehensive analysis of the length of time students spend studying without interacting with others around them, the length of time students spend studying in small groups or group discussions, the length of time students spend studying in a class collective, and the length of time students spend not studying.
[0048] The learning status index w6 includes the comprehensive scores of students' learning status such as concentration, fatigue, inattention, and peace; for example, the learning status index w6 can be obtained by comprehensively analyzing the length of time students are in an immersive learning state, the length of time students doze off, daydream, etc. during learning, the length of time students make small movements during learning, and the length of time students exhibit other undisciplined behaviors.
[0049] The learning style index w7 includes the comprehensive scores of students' learning styles such as independent learning, in-class learning, guided learning, and partner learning. For example, the learning style index w7 can be obtained by comprehensively analyzing the length of time students spend on spontaneous learning outside of class time, the length of time students spend on in-class learning, the length of time teachers spend communicating with students, and the length of time students spend discussing with each other.
[0050] The learning behavior indicator w8 includes the comprehensive scores of learning behaviors such as attendance, classroom interaction, in-class tests, and grade examinations; for example, the learning behavior indicator w8 can be obtained through a comprehensive analysis of students' attendance time, the number of students' classroom interactions (the number of times they raise their hands in class, the number of times they answer questions in class, etc.), students' in-class tests (whether the students pass), and students' grade examinations (whether the students reach the grade standard score).
[0051] It should be noted that the collected w1~w8 are converted into scores or values through a preset scoring mechanism, which can be obtained by pre-processing through relative scores, standardization, etc., which can reduce data interference caused by subjective factors.
[0052] Step 203: Perform significant correlation verification on the sample data set to be verified based on the standard sample data set, and obtain a target sample data set that meets the correlation verification condition in the sample data set to be verified.
[0053] When executing step 203, the following steps may be adopted but are not limited to: It should be noted that the T-test method is needed to judge data outliers. Specifically, because the direct manifestation of the effect of w2~w8 is w1, there is a certain significant correlation between w1 and w2~w8, but there may be one or more performances between w2~w8 that are close to the score of w1, and the others are poor; there are also cases where w1 has a high score and w2~w8 have low scores. This type of data is more extreme, and there is obviously no correlation between w1 and w2~w8. This type of data is input into the model training as a training sample set, which will affect the model's fit and prediction accuracy. Therefore, the single sample verification method is adopted to verify the direct significant correlation between w1 and w2~w8 of a single sample.
[0054] Step 11: Determine the correlation test value based on the sample value of the standard sample data set, the sample mean and the sample standard deviation of the sample data set to be verified by the following formula 1. The specific formula 1 is as follows: Formula 1 In Formula 1, u0 represents the sample mean of the sample data set to be verified, u represents the sample value of the standard sample data set, s represents the sample standard deviation of the sample data set to be verified, and n represents the sample size of the sample data set to be verified.
[0055] Specifically, consider w2~w8 as a sample set, w1 as a known theoretical value, and propose the hypothesis: H0: , there is a significant correlation between w1 and w2~w8; H1: , there is no significant correlation between w1 and w2~w8; The t-test value was obtained by using the above formula 1, the target test level α was determined to be 0.05, and the P value was determined by looking up the boundary value table.
[0056] Step 12: Based on the predetermined test level α, the predetermined threshold value P and the correlation verification value t, perform significant correlation verification on the sample data set to be verified. If it is judged that t<p, execute step 13; if it is judged that t>p, execute step 14; Step 13: If it is determined that t<p, it means that P>α at the t-test value level, and it is determined that there is a significant correlation between the sample data set to be verified and the standard sample data set.
[0057] Specifically, if t<p, it means that P>α at the t test value level. Then at the α test level, the H0 hypothesis is established, and there is a significant correlation between w1 and w2~w8.
[0058] Step 14: If it is determined that t>p, it means that P<α at the t-test value level, and it is determined that there is no significant correlation between the sample data set to be verified and the standard sample data set.
[0059] Specifically, if t>p, it means that P<α at the t test value level. Then at the α test level, the H1 hypothesis is established, and there is no significant correlation between w1 and w2~w8.
[0060] Step 15: Use the sample data set to be verified that has significant correlation as the target sample data set.
[0061] Furthermore, through this method, it is determined whether there is a significant correlation between w1 and the single sample sets w2~w8. If there is a significant correlation, it will be used as a sample set for the next step of model training. If there is no significant correlation, the sample data will be invalidated.
[0062] Step 204: determine the target sample data set and the standard sample data set as sample data sets.
[0063] When inputting the sample data set into the fusion model, evaluating the correlation between the various combinations of regular performance indicators and student performance indicators in the sample data set and the test performance data in the sample data set, and determining the target indicator combination with the highest adaptability to the target student based on the obtained correlation evaluation results, the following methods may be used but are not limited to: Figure 3 As shown, the method includes: Step 301: Based on the test score data set in the sample data set and the first data set containing multiple regular performance indicators, a first prediction model in the fusion model is constructed to predict the correlation between the test score data and the regular performance indicators.
[0064] In an embodiment of the present application, the combination of regular performance indicators may be a combination of daily homework scores, teacher scores, and classroom performance scores.
[0065] For example, if the test score data is w1, the daily homework score is w2, the teacher score is w3, and the classroom performance score is w4, then the first data set may include a variety of regular performance indicator combinations, which may specifically include: The combination of daily homework scores and teacher scores is w2+w3; The combination of daily homework scores and classroom performance scores is w2+w4; The combination of teacher rating and classroom performance score is w3+w4.
[0066] Furthermore, the first prediction model is used to predict the correlation between the various combinations of regular performance indicators in the first data set and the test score data. Specifically, the correlation between the test score data and the combination of daily homework scores and teacher scores, the correlation between the test score data and the combination of daily homework scores and classroom performance scores, and the correlation between the test score data and the combination of teacher scores and classroom performance scores can be predicted based on the first prediction model, that is, the correlation between w1 and w2+w3, the correlation between w1 and w2+w4, and the correlation between w1 and w3+w4 can be predicted respectively.
[0067] For this embodiment, the first prediction model may include a prediction model for predicting the correlation between w1 and w2+w3, a prediction model for predicting the correlation between w1 and w2+w4, and a prediction model for predicting the correlation between w1 and w3+w4.
[0068] In some examples, the prediction process of the first prediction model may include: Step 21, construct an m*n matrix; for example: lab-w2+lab-w3, lab-w2+lab-w4, lab-w3+lab-w4; there are 3 combinations in total, and 3 prediction models can be obtained.
[0069] Step 22: Construct a prediction model based on the matrix; the prediction model is as follows: Figure 4 As shown, a deep learning network framework is constructed using convolutional neural networks, multi-layer perceptrons (MLPs), etc.; further, the convolutional neural network model of the prediction model is composed of 1 input layer, 1 convolutional layer, 1 flattening layer, 2 fully connected layers, 2 discarded layers, and 1 output layer.
[0070] Step 23, determine the loss function of the prediction model; the activation function of each network layer is ReLU, the optimizer used to train the network is adam, and the loss function is shown in the following formula 7: Formula 7 In formula 7, yi represents the observed value, Represents the predicted value.
[0071] Step 24: Continuously optimize the model parameters through the loss function to obtain the first prediction model with the minimum prediction loss as the first preset parameter part of the fusion model.
[0072] Step 302: Based on the test score data set in the sample data set and the second data set containing multiple student performance indicators, a second prediction model in the fusion model is constructed to predict the correlation between the test score data and the student performance indicators.
[0073] In an embodiment of the present application, the combination of multiple student performance indicators may be a combination of a learning environment indicator, a learning status indicator, a learning method indicator, and a learning behavior indicator.
[0074] For example, if the learning environment indicator is w5, the learning state indicator is w6, the learning method indicator is w7, and the learning behavior indicator is w8, then the second data set may include a variety of student performance indicator combinations, which may specifically include: The combination of learning environment indicators and learning status indicators is w5+w6; The combination of learning environment indicators and learning style indicators is w5+w7; The combination of learning environment indicators and learning behavior indicators is w5+w8; The combination of learning status indicator and learning style indicator is w6+w7; The combination of learning status indicator and learning behavior indicator is w6+w8; The combination of learning style indicators and learning behavior indicators is w7+w8.
[0075] Furthermore, by using the second prediction model to predict the correlation between multiple student performance indicator combinations and the test score data, the correlation between the test score data and the combination of learning environment indicators and learning status indicators (that is, predicting the correlation between w1 and w5+w6), the correlation between the test score data and the combination of learning environment indicators and learning style indicators (that is, predicting the correlation between w1 and w5+w7), the correlation between the test score data and the combination of learning environment indicators and learning behavior indicators (that is, predicting the correlation between w1 and w5+w8), the correlation between the test score data and the combination of learning status indicators and learning style indicators (that is, predicting the correlation between w1 and w6+w7), the correlation between the test score data and the combination of learning status indicators and learning behavior indicators (that is, predicting the correlation between w1 and w6+w8), and the correlation between the test score data and the combination of learning style indicators and learning behavior indicators (that is, predicting the correlation between w1 and w7+w8) can be predicted based on the second prediction model.
[0076] In some examples, the prediction process of the second prediction model may include: Step 31, construct an m*n matrix; for example: lab-w5+lab-w6, lab-w5+lab-w7, lab-w5+lab-w8, lab-w6+lab-w7, lab-w6+lab-w8, lab-w7+lab-w8.
[0077] Step 32: construct a prediction model based on the matrix; train the prediction model, a total of 6 combinations, obtain 6 second prediction models, and train the model in the same way to obtain the second preset parameter part of the fusion model.
[0078] Step 33: Determine the loss function of the prediction model (as shown in Formula 7 in Step 23); the activation function of each network layer is ReLU, and the optimizer used to train the network is adam.
[0079] Step 34: Continuously optimize the model parameters through the loss function to obtain a second prediction model with the minimum prediction loss as the second preset parameter part of the fusion model.
[0080] Step 303: Use the first prediction model as the first prediction parameter of the correlation evaluation model in the fusion model, and use the second prediction model as the second prediction parameter of the correlation evaluation model, and cross-combine the first prediction parameter with the second prediction parameter to construct a correlation evaluation model to evaluate the correlation between the test score data and the multiple indicator combinations.
[0081] It should be noted that since the first prediction model and the second prediction model are trained separately, the parameters of the first prediction model and the second prediction model are extended to the fusion model, which can maximize the retention of the characteristics of the original data feature training and avoid the situation where the parameters of the fusion model are re-adjusted, resulting in the loss of some data features.
[0082] When evaluating the correlation between test score data and a combination of multiple indicators, the following steps may be used, but are not limited to: Based on the first prediction result obtained by predicting the regular performance indicators in each indicator combination through the first prediction model, and the second prediction result obtained by predicting the student performance indicators in each indicator combination through the second prediction model, covariance processing is performed through the following formula 2 to obtain the correlation evaluation results between the test score data and the various indicator combinations.
[0083] Formula 2 In formula 2, cov means covariance processing. represents variance, and XY represents different first prediction parameters and second prediction parameters corresponding to a set of indicator combinations.
[0084] In an embodiment of the present application, the multiple indicator combinations can be a combination of multiple regular performance indicator combinations U=[u1, u2, u3] and multiple student performance indicator combinations I=[i1, i2, i3, i4, i5, i6], that is, 18 indicator combinations can be obtained.
[0085] Specifically, U=[u1, u2, u3] can correspond to w2+w3, w2+w4, w3+w4; correspondingly, I=[i1, i2, i3, i4, i5, i6] can correspond to w5+w6, w5+w7, w5+w8, w6+w7, w6+w8, w7+w8.
[0086] In some examples, such as Figure 5 Shown is a schematic diagram of the fusion model, including a first prediction model, a second prediction model, a correlation evaluation model and an adaptability evaluation model. Specifically, the convolutional neural network model of the fusion model is composed of 1 input layer, 2 convolutional layers, 2 flattening layers, 3 fully connected layers, 1 discarded layer, and 1 output layer.
[0087] It should be noted that the larger the evaluation result corresponding to the indicator combination, the more relevant the indicator combination is to the performance.
[0088] Furthermore, when determining the target indicator combination with the highest adaptability to the target student based on the obtained correlation evaluation results, the following methods may be used but are not limited to: Figure 6 As shown, the method includes: Step 401: Select a predetermined number of indicator combinations with the highest correlation evaluation results from a plurality of indicator combinations to form candidate indicator combinations.
[0089] Exemplarily, the top m groups of indicator combinations (m≥2) with the highest correlation evaluation indicators are screened out from the multiple indicator combinations.
[0090] Step 402: Based on the normalized evaluation value of the candidate indicator combination and the weight value of each indicator in the candidate indicator combination, a suitability evaluation model in the fusion model is constructed to evaluate the suitability of the candidate indicator combination with the target student.
[0091] When executing step 402, the following methods may be used, but are not limited thereto, and specifically include: Step 41: normalize the correlation evaluation result of the candidate indicator combination obtained in the correlation evaluation model by the following formula 3 to obtain a normalized evaluation value of the candidate indicator combination; Formula 3 In Formula 3, P is the normalized evaluation value, xmin is the minimum value among the correlation evaluation results corresponding to the multiple candidate indicator combinations, xmax is the maximum value among the correlation evaluation results corresponding to the multiple candidate indicator combinations, and xori is the normalized correlation evaluation result of the candidate indicators.
[0092] Exemplarily, based on step 401, if the candidate indicator combinations include indicator combination 1 (w2, w3, w4, w5), indicator combination 2 (w2, w3, w4, w7) and indicator combination 3 (w1, w3, w4, w5), it is necessary to perform normalization calculations on each indicator combination to obtain the normalized correlation evaluation value corresponding to each indicator combination.
[0093] Step 42: Perform standard deviation analysis on the normalized evaluation value using the following formula 4 to obtain the standard deviation value of the candidate indicator combination; Formula 4 In formula 4, SW is the standard deviation corresponding to the candidate indicator combination, Pi is the normalized evaluation value corresponding to the i-th candidate indicator combination, is the average value of the normalized evaluation value corresponding to the i-th candidate indicator combination, and n represents the number of candidate indicator combinations.
[0094] Exemplarily, based on step 41, it is necessary to calculate the normalized correlation evaluation values corresponding to indicator combination 1, indicator combination 2, and indicator combination 3 respectively to obtain the standard deviation corresponding to each indicator combination.
[0095] Step 43: According to the standard deviation value, the weight value of each indicator in the candidate indicator combination is determined by the following formula 5.
[0096] Formula 5 In Formula 5, qj is the weight value of the jth indicator in the candidate indicator combination, SWj is the standard deviation value of the jth candidate indicator combination, and k is the number of indicators included in the candidate indicator combination.
[0097] Exemplarily, based on step 42, it is necessary to determine the weight values corresponding to w2, w3, w4, and w5 in indicator combination 1 based on the standard deviation of indicator combination 1, and it is necessary to determine the weight values corresponding to w2, w3, w4, and w7 in indicator combination 1 based on the standard deviation of indicator combination 2. Examples are not given one by one here, wherein the sum of the weights of the indicators in each indicator combination is equal to 1.
[0098] Step 44: Based on the normalized evaluation value and the weight value of each indicator in the candidate indicator combination, an adaptability evaluation model in the fusion model is constructed.
[0099] The adaptability evaluation model is constructed by the following formula 6 to obtain the adaptability evaluation result: ; Formula 6 In formula 6, is the suitability evaluation result of the i-th candidate indicator combination, q j is the weight value of the jth indicator in the candidate indicator combination, is the normalized evaluation value of the i-th candidate indicator combination.
[0100] Step 403: Based on the adaptability evaluation model, determine the target indicator combination with the highest adaptability to the target students among the multiple indicator combinations.
[0101] Exemplarily, based on step 43, a suitability analysis is performed on each indicator combination in the suitability evaluation model, and the indicator combination with the highest suitability is selected as the target indicator combination.
[0102] Compared with the current existing technology, this embodiment fully considers the impact of the correlation between data on the generation plan by determining a sample data set that meets the correlation verification conditions from the test score data, the regular score indicators and the student performance indicators, ensures the correlation between the collected data, and can retain the true characteristics of the original data to a greater extent for predictive analysis; by inputting the sample data set into the fusion model, the correlation between the various indicator combinations between the regular score indicators and the student performance indicators in the sample data set and the test score data in the sample data set is evaluated respectively, and the target indicator combination with the highest adaptability to the target student is determined based on the obtained correlation evaluation results. On the basis of the correlation evaluation based on the regular score indicators, the student performance indicators can be introduced for evaluation, which can make the evaluation results more accurate. The target indicator combination can also be more accurately determined from the various indicator combinations through the correlation evaluation and adaptability evaluation, and then the student's score improvement plan is generated, so that the generated score improvement plan has the highest adaptability to the student, which can help students accurately find the most relevant factors affecting the score, and then accurately help students improve their scores.
[0103] Further, as Figure 1 , Figure 2 , Figure 3 and Figure 6 The specific implementation of the method shown in the embodiment provides a device for generating a performance improvement plan, such as Figure 7 As shown, the device includes: an acquisition module 51, a determination module 52, an evaluation module 53, and a sending module 54.
[0104] An acquisition module 51 is configured to acquire the test score data, regular performance index and student performance index of the target student; A determination module 52 is configured to determine a sample data set that meets the correlation verification condition from the test score data, the regular score index and the student performance index; An evaluation module 53 is configured to input the sample data set into a fusion model, evaluate the correlation between the various indicator combinations between the regular performance indicators and the student performance indicators in the sample data set and the test performance data in the sample data set, and determine the target indicator combination with the highest adaptability to the target student based on the obtained correlation evaluation results; The sending module 54 is configured to send the target indicator combination to the target student as a performance improvement plan for the target student.
[0105] In some examples of this embodiment, the determination module 52 is specifically configured to determine the sample data set to be verified based on the regular performance indicators and the student performance indicators; determine the standard sample data set corresponding to the sample data set to be verified based on the test performance data; perform significant correlation verification on the sample data set to be verified based on the standard sample data set to obtain a target sample data set in the sample data set to be verified that meets the correlation verification conditions; and determine the target sample data set and the standard sample data set as the sample data sets.
[0106] In some examples of this embodiment, the determination module 52 is further configured to determine the correlation test value based on the sample value of the standard sample data set, the sample mean and the sample standard deviation of the sample data set to be verified by the following formula 1: Based on the predetermined test level α, the predetermined boundary value P and the correlation verification value t, the sample data set to be verified is verified for significant correlation; if it is determined that t<p, it means that P>α at the t test value level, then it is determined that there is a significant correlation between the sample data set to be verified and the standard sample data set; if it is determined that t>p, it means that P<α at the t test value level, then it is determined that there is no significant correlation between the sample data set to be verified and the standard sample data set; the sample data set to be verified with significant correlation is used as the target sample data set; Formula 1 In Formula 1, u0 represents the sample mean of the sample data set to be verified, u represents the sample value of the standard sample data set, s represents the sample standard deviation of the sample data set to be verified, and n represents the sample size of the sample data set to be verified.
[0107] In some examples of this embodiment, the evaluation module 53 is specifically configured to construct a first prediction model in the fusion model based on the test score data set in the sample data set and a first data set containing multiple regular performance indicators to predict the correlation between the test score data and the regular performance indicators; construct a second prediction model in the fusion model based on the test score data set in the sample data set and a second data set containing multiple student performance indicators to predict the correlation between the test score data and the student performance indicators; use the first prediction model as the first prediction parameter of the correlation evaluation model in the fusion model, and use the second prediction model as the second prediction parameter of the correlation evaluation model, and cross-combine the first prediction parameter with the second prediction parameter to construct the correlation evaluation model to evaluate the correlation between the test score data and the multiple indicator combinations.
[0108] In some examples of this embodiment, the evaluation module 53 is further configured to perform covariance processing based on the first prediction result obtained by predicting the usual performance index in each indicator combination through the first prediction model, and the second prediction result obtained by predicting the student performance index in each indicator combination through the second prediction model through the following formula 2, to obtain the correlation evaluation results between the test score data and the multiple indicator combinations respectively; Formula 2 In formula 2, cov means covariance processing. represents variance, and XY represents different first prediction parameters and second prediction parameters corresponding to a set of indicator combinations.
[0109] In some examples of the present embodiment, the evaluation module 53 is further configured to select a predetermined number of indicator combinations with the highest correlation evaluation results from the multiple indicator combinations to form candidate indicator combinations; based on the normalized evaluation value of the candidate indicator combination and the weight value of each indicator in the candidate indicator combination, construct a suitability evaluation model in the fusion model to evaluate the suitability of the candidate indicator combination with the target student; based on the suitability evaluation model, determine the target indicator combination with the highest suitability with the target student among the multiple indicator combinations.
[0110] In some examples of this embodiment, the evaluation module 53 is further configured to perform normalization processing on the correlation evaluation result obtained by the candidate indicator combination in the correlation evaluation model by the following formula 3 to obtain a normalized evaluation value of the candidate indicator combination; Formula 3 In Formula 3, P is a normalized evaluation value, xmin is a minimum value among the correlation evaluation results corresponding to the plurality of candidate indicator combinations, xmax is a maximum value among the correlation evaluation results corresponding to the plurality of candidate indicator combinations, and xori is a normalized correlation evaluation result of the candidate indicators; Performing standard deviation analysis on the normalized evaluation value using the following formula 4 to obtain the standard deviation value of the candidate indicator combination; Formula 4 In formula 4, SW is the standard deviation corresponding to the candidate indicator combination, Pi is the normalized evaluation value corresponding to the i-th candidate indicator combination, is the average value of the normalized evaluation value corresponding to the i-th candidate indicator combination, and n represents the number of candidate indicator combinations; According to the standard deviation value, the weight value of each indicator in the candidate indicator combination is determined by the following formula 5; Formula 5 In formula 5, qj is the weight value of the jth indicator in the candidate indicator combination, SWj is the standard deviation value of the jth candidate indicator combination, and k is the number of indicators included in the candidate indicator combination; Based on the normalized evaluation value and the weight value of each indicator in the candidate indicator combination, an adaptability evaluation model in the fusion model is constructed.
[0111] In some examples of this embodiment, the evaluation module 53 is further configured to construct the adaptability evaluation model through the following formula 6 to obtain the adaptability evaluation result ; Formula 6 In formula 6, is the suitability evaluation result of the i-th candidate indicator combination, q j is the weight value of the jth indicator in the candidate indicator combination, is the normalized evaluation value of the i-th candidate indicator combination.
[0112] It should be noted that for other corresponding descriptions of the functional units involved in the device for generating a performance improvement plan provided in this embodiment, reference can be made to Figure 1 , Figure 2 , Figure 3 and Figure 6 The corresponding description in will not be repeated here.
[0113] Based on the above Figure 1 , Figure 2 , Figure 3 and Figure 6The method shown in the embodiment also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned Figure 1 , Figure 2 , Figure 3 and Figure 6 The method shown.
[0114] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of the present application.
[0115] like Figure 8 The figure shows a hardware structure diagram of an electronic device of the present invention, including: at least one processor 601; and, A memory 602 is communicatively connected to at least one of the processors 601; wherein, The memory 602 stores instructions that can be executed by at least one of the processors. The instructions are executed by at least one of the processors so that the at least one processor can execute the method for generating a performance improvement plan as described above.
[0116] Figure 8 A processor 601 is taken as an example.
[0117] The electronic device may further include: an input device 603 and a display device 604 .
[0118] The processor 601, the memory 602, the input device 603 and the display device 604 may be connected via a bus or other means. Figure 8 The example of connecting through bus is taken in the following.
[0119] The memory 602 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the method for generating a performance improvement plan in the embodiment of the present application, for example, Figure 1 , Figure 2 , Figure 3 and Figure 6 The processor 601 executes various functional applications and data processing by running the non-volatile software programs, instructions and modules stored in the memory 602, that is, the method for generating the performance improvement plan in the above embodiment is implemented.
[0120] The memory 602 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created according to the use of the method for generating a performance improvement scheme, etc. In addition, the memory 602 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 602 may optionally include a memory remotely arranged relative to the processor 601, and these remote memories may be connected to a device for executing the method for generating a performance improvement scheme via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0121] The input device 603 can receive user clicks and generate signal inputs related to user settings and function control of the method for generating the performance improvement plan. The display device 604 can include display devices such as a display screen.
[0122] The one or more modules are stored in the memory 602, and when executed by the one or more processors 601, the method for generating a performance improvement plan in any of the above method embodiments is executed.
[0123] Optionally, the above-mentioned physical device may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.
[0124] Those skilled in the art will appreciate that the above-mentioned physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or a combination of certain components, or different arrangements of components.
[0125] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the above-mentioned physical device, and supports the operation of the information processing program and other software and / or programs. The network communication module is used to realize the communication between the components inside the storage medium, and the communication with other hardware and software in the information processing physical device.
[0126] Through the description of the above implementation methods, the technicians in this field can clearly understand that the present application can be implemented by means of software plus necessary general hardware platforms, or by hardware. By applying the scheme of this embodiment, compared with the current existing technology, this embodiment fully considers the influence of the correlation between data on the generation scheme by determining the sample data set that meets the correlation verification conditions from the test score data, the usual performance index and the student performance index, ensuring the correlation between the collected data, and can retain the true characteristics of the original data to a greater extent for prediction analysis; by inputting the sample data set into the fusion model, the correlation between the various indicator combinations between the usual performance index and the student performance index in the sample data set and the test score data in the sample data set is evaluated respectively, and the target indicator combination with the highest adaptability to the target student is determined based on the obtained correlation evaluation result, and the student performance index can be introduced for evaluation on the basis of the correlation evaluation based on the usual performance index, so that the evaluation result can be more accurate, and the target indicator combination can be more accurately determined in the various indicator combinations through the correlation evaluation and adaptability evaluation, so as to generate the student's performance improvement plan, so that the generated performance improvement plan has the highest adaptability to the student, which can help the student accurately find the most relevant factors affecting the performance, and then accurately help the student improve the performance.
[0127] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0128] The above is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features applied for herein.
Claims
1. A method for generating a performance improvement plan, characterized in that: include: Obtain test score data, regular performance indicators and student performance indicators of target students; Determine a sample data set that meets the correlation verification condition from the test score data, the regular performance index and the student performance index; Inputting the sample data set into the fusion model, evaluating the correlation between the various indicator combinations between the regular performance indicators and the student performance indicators in the sample data set and the test performance data in the sample data set, and determining the target indicator combination with the highest adaptability to the target student based on the obtained correlation evaluation results; The target indicator combination is sent to the target student as a performance improvement plan for the target student.
2. The method according to claim 1, characterized in that The step of determining a sample data set that meets the correlation verification condition from the test score data, the regular score index, and the student performance index includes: Determine a sample data set to be verified based on the regular performance index and the student performance index; Based on the test score data, determining a standard sample data set corresponding to the sample data set to be verified; Performing significant correlation verification on the sample data set to be verified based on the standard sample data set to obtain a target sample data set in the sample data set to be verified that meets the correlation verification condition; The target sample data set and the standard sample data set are determined as the sample data sets.
3. The method according to claim 2, characterized in that The performing significant correlation verification on the sample data set to be verified based on the standard sample data set to obtain a target sample data set in the sample data set to be verified that meets the correlation verification condition, includes: Determine the correlation test value based on the sample value of the standard sample data set, the sample mean and the sample standard deviation of the sample data set to be verified by the following formula 1; Based on a predetermined test level α, a predetermined threshold value P and the correlation verification value t, performing significant correlation verification on the sample data set to be verified; If it is determined that t<p, it means that P>α at the t-test value level, and it is determined that there is a significant correlation between the sample data set to be verified and the standard sample data set; If it is determined that t>p, it means that P<α at the t-test value level, and it is determined that there is no significant correlation between the sample data set to be verified and the standard sample data set; Taking the sample data set to be verified with significant correlation as the target sample data set; Formula 1 In Formula 1, u0 represents the sample mean of the sample data set to be verified, u represents the sample value of the standard sample data set, s represents the sample standard deviation of the sample data set to be verified, and n represents the sample size of the sample data set to be verified.
4. The method according to claim 3, characterized in that The step of inputting the sample data set into the fusion model and evaluating the correlation between the various combinations of regular performance indicators and student performance indicators in the sample data set and the test performance data in the sample data set, respectively, includes: Based on the test score data set in the sample data set and the first data set including multiple regular performance indicators, construct a first prediction model in the fusion model to predict the correlation between the test score data and the regular performance indicators; Based on the test score data set in the sample data set and the second data set including multiple student performance indicators, constructing a second prediction model in the fusion model to predict the correlation between the test score data and the student performance indicators; The first prediction model is used as the first prediction parameter of the correlation evaluation model in the fusion model, and the second prediction model is used as the second prediction parameter of the correlation evaluation model. The first prediction parameter and the second prediction parameter are cross-combined to construct the correlation evaluation model to evaluate the correlation between the test score data and the multiple indicator combinations.
5. The method according to claim 4, characterized in that The process of evaluating the correlation between the test score data and the combination of the multiple indicators includes: Based on the first prediction result obtained by predicting the regular performance index in each indicator combination through the first prediction model, and the second prediction result obtained by predicting the student performance index in each indicator combination through the second prediction model, covariance processing is performed through the following formula 2 to obtain the correlation evaluation results between the test score data and the multiple indicator combinations respectively; Formula 2 In formula 2, cov means covariance processing. represents variance, and XY represents different first prediction parameters and second prediction parameters corresponding to a set of indicator combinations.
6. The method according to any one of claims 1 to 5, characterized in that The step of determining the target indicator combination with the highest adaptability to the target student based on the obtained correlation evaluation result includes: Selecting a predetermined number of indicator combinations with the highest correlation evaluation results from the multiple indicator combinations to form candidate indicator combinations; Based on the normalized evaluation value of the candidate indicator combination and the weight value of each indicator in the candidate indicator combination, constructing a suitability evaluation model in the fusion model to evaluate the suitability of the candidate indicator combination with the target student; Based on the adaptability evaluation model, the target indicator combination with the highest adaptability to the target student is determined among the multiple indicator combinations.
7. The method according to claim 6, characterized in that The constructing of the adaptability evaluation model in the fusion model based on the normalized evaluation value of the candidate indicator combination and the weight value of each indicator in the candidate indicator combination includes: The correlation evaluation result obtained by the candidate indicator combination in the correlation evaluation model is normalized by the following formula 3 to obtain a normalized evaluation value of the candidate indicator combination; Formula 3 In Formula 3, P is a normalized evaluation value, xmin is a minimum value among the correlation evaluation results corresponding to the plurality of candidate indicator combinations, xmax is a maximum value among the correlation evaluation results corresponding to the plurality of candidate indicator combinations, and xori is a normalized correlation evaluation result of the candidate indicators; Performing standard deviation analysis on the normalized evaluation value using the following formula 4 to obtain the standard deviation value of the candidate indicator combination; Equation 4 In formula 4, SW is the standard deviation corresponding to the candidate indicator combination, Pi is the normalized evaluation value corresponding to the i-th candidate indicator combination, is the average value of the normalized evaluation value corresponding to the i-th candidate indicator combination, and n represents the number of candidate indicator combinations; According to the standard deviation value, the weight value of each indicator in the candidate indicator combination is determined by the following formula 5; Formula 5 In formula 5, qj is the weight value of the jth indicator in the candidate indicator combination, SWj is the standard deviation value of the jth candidate indicator combination, and k is the number of indicators included in the candidate indicator combination; Based on the normalized evaluation value and the weight value of each indicator in the candidate indicator combination, an adaptability evaluation model in the fusion model is constructed.
8. The method according to claim 7, characterized in that The step of constructing the adaptability evaluation model in the fusion model based on the normalized evaluation value of the candidate indicator combination and the weight value of each indicator in the candidate indicator combination further includes: The adaptability evaluation model is constructed by the following formula 6 to obtain the adaptability evaluation result: ; Formula 6 In formula 6, is the suitability evaluation result of the i-th candidate indicator combination, q j is the weight value of the jth indicator in the candidate indicator combination, is the normalized evaluation value of the i-th candidate indicator combination.
9. A device for generating a performance improvement plan, characterized in that: include: An acquisition module is configured to acquire test score data, regular performance indicators, and student performance indicators of target students; A determination module is configured to determine a sample data set that meets the correlation verification condition from the test score data, the regular score index and the student performance index; An evaluation module is configured to input the sample data set into a fusion model, evaluate the correlation between the various indicator combinations between the regular performance indicators and the student performance indicators in the sample data set and the test performance data in the sample data set, and determine the target indicator combination with the highest adaptability to the target student based on the obtained correlation evaluation results; The sending module is configured to send the target indicator combination to the target student as a performance improvement plan for the target student.
10. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.
Citation Information
Cited By
Teaching scheme generation method and system based on student score change analysis
CN120580104A
