Education data processing method based on coexistence of standard reference and norm reference

Abstract

The present application relates to the technical field of data processing, and more particularly to an educational data processing method based on coexistence of standard reference and norm reference, comprising: obtaining real-time access times, accuracy and interaction frequency; determining a first temporary target; determining a second temporary target; determining a processing target; determining a target evaluation index and an analysis evaluation index; and determining an evaluation grade after adjusting the reference threshold according to the index deviation. The present application can accurately capture the performance of students in different learning scenarios, real-time evaluate their learning state and dynamically adjust by fusing the dual evaluation mechanism of standard reference and norm reference. Through the gradual adjustment of the standard reference threshold and the deep application of the clustering analysis model, the limitations of single evaluation method can be eliminated, the evaluation result is more comprehensive, accurate and personalized, and the problem of low recognition accuracy of the processing device caused by poor data objectivity due to single evaluation standard is effectively solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to an educational data processing method based on coexistence of standard reference and norm reference. BACKGROUND

[0002] In the modern education process, how to effectively evaluate the learning performance and interactive participation of students has become a key problem to improve the quality of education. With the combination of online and offline learning, the diversity and complexity of educational data have also increased, and the traditional evaluation method is difficult to fully reflect the individual differences and behavior characteristics of students.

[0003] The patent document with publication number CN115186014A discloses a data processing method for educational training, which includes: obtaining the frequency of looking around, the typical hesitation time for interaction and the hesitation stability degree of each child in the target classroom; calculating the attraction degree of the classroom to each child according to the typical hesitation time and hesitation stability degree of each child in the target classroom; calculating the behavior difference distance between any two children according to the attraction degree of the classroom to each child, the frequency of looking around and the hesitation time sequence in the target classroom; classifying each child in the target classroom according to the behavior difference distance to obtain multiple types; the hesitation time sequence is a sequence composed of each interaction hesitation time of the corresponding child in the classroom; for any type: calculate the spatial distance between each child in the type and other children in the type according to the frequency of looking around of each child in the type and the looking around state sequence corresponding to the target time period, calculate the behavior membership degree of each child in the type according to the spatial distance, take the child with the maximum behavior membership degree as the representative child of the type corresponding to the target time period, and take the representative child of the type corresponding to the target time period as the recommended simulation object when the later preschool teacher reviews the target time; the looking around state sequence corresponding to the target time period is a sequence composed of the looking around state corresponding to each collection time of the corresponding child in the target time period.

[0004] Therefore, the data processing method for educational training has the following problems: this method mainly relies on the behavior data in a single classroom, such as the frequency of looking around, the interaction hesitation time, etc. These data have subjective bias, which affects the accuracy of the evaluation results. SUMMARY

[0005] Therefore, the present application provides an educational data processing method based on coexistence of standard reference and norm reference, which overcomes the problem of low recognition accuracy of processing equipment caused by poor data objectivity due to a single evaluation standard in the prior art by combining standard reference and norm reference.

[0006] To achieve the above object, the application provides an educational data processing method based on standard reference and norm reference coexistence, comprising:

[0007] Obtaining real-time access times of each target to be evaluated in an online learning platform, real-time accuracy rates of each target to be evaluated after testing, and real-time interaction frequencies of each target to be evaluated in offline classrooms;

[0008] Determining a plurality of first temporary targets according to the real-time access times and a preset standard reference threshold value;

[0009] Determining a plurality of second temporary targets according to the real-time accuracy rates of each first temporary target;

[0010] Determining a plurality of processing targets according to the real-time interaction frequencies and the real-time access times of each second temporary target;

[0011] Determining target evaluation indexes according to the real-time access times, the real-time accuracy rates and the real-time interaction frequencies of each processing target;

[0012] Determining analysis evaluation indexes according to a preset norm reference value, the real-time accuracy rates of all targets to be evaluated, all real-time access times and all real-time interaction frequencies, and a preset clustering analysis model;

[0013] Adjusting the preset standard reference threshold value according to the target evaluation indexes and the analysis evaluation indexes to form an adjusted standard reference threshold value;

[0014] Determining target evaluation indexes based on the adjusted standard reference threshold value, and determining evaluation grades of the targets to be evaluated according to the target evaluation indexes.

[0015] Further, determining a plurality of first temporary targets according to the real-time access times and a preset standard reference threshold value comprises:

[0016] When the real-time access times are less than the preset standard reference threshold value, determining that the target to be evaluated is a first temporary target, and forming a plurality of first temporary targets.

[0017] Further, determining a plurality of second temporary targets according to the real-time accuracy rates of each first temporary target comprises:

[0018] When the real-time accuracy rate is greater than a preset accuracy rate threshold value, calculating a standard deviation of the real-time accuracy rate within a preset first determination duration to form an accuracy rate fluctuation value;

[0019] When the accuracy rate fluctuation value is greater than a preset accuracy rate fluctuation threshold value, determining that the first temporary target is the second temporary target, and forming a plurality of second temporary targets.

[0020] Further, determining a number of processing targets according to the real-time interaction frequency and the real-time access times of each of the second temporary targets comprises:

[0021] calculating a standard deviation of the real-time interaction frequency in a preset second determination duration, forming an interaction frequency fluctuation value;

[0022] calculating a standard deviation of the real-time access times in the preset second determination duration, forming an access times fluctuation value;

[0023] determining a number of processing targets according to the interaction frequency fluctuation value and the access times fluctuation value.

[0024] Further, determining a number of processing targets according to the interaction frequency fluctuation value and the access times fluctuation value comprises:

[0025] plotting a change curve according to the interaction frequency fluctuation value, forming an interaction change curve;

[0026] plotting a change curve according to the access times fluctuation value, forming an access change curve;

[0027] calculating a cosine similarity of the interaction change curve and the access change curve, forming a change synchronization degree;

[0028] when the change synchronization degree is less than a preset synchronization degree threshold, determining that the second temporary target is an influence target;

[0029] selecting non-influence targets in all the to-be-evaluated targets as processing targets, forming a number of processing targets.

[0030] Further, determining a target evaluation index according to the real-time access times, the real-time accuracy rate and the real-time interaction frequency of each of the processing targets comprises:

[0031] normalizing the real-time access times, forming a normalized access times;

[0032] normalizing the real-time accuracy rate, forming a normalized accuracy rate;

[0033] normalizing the real-time interaction frequency, forming a normalized interaction frequency;

[0034] performing weighted summation on the normalized access times, the normalized accuracy rate, the normalized interaction frequency, a preset access times weight, a preset accuracy rate weight and a preset interaction frequency weight, forming a target evaluation index.

[0035] Further, the analysis evaluation index is determined according to the preset norm reference value, the real-time correctness, the real-time access times and the real-time interaction frequency of all the to-be-evaluated targets, and a preset cluster analysis model, and includes:

[0036] The real-time correctness of all the to-be-evaluated targets is sorted to determine the ranking value of each to-be-evaluated target.

[0037] The sum of the ranking value and the preset norm reference value is calculated to obtain a lower limit of the ranking range, and the difference between the ranking value and the preset norm reference value is calculated to obtain an upper limit of the ranking range, thereby forming a ranking range.

[0038] The analysis evaluation index is determined according to the real-time correctness, the real-time access times and the real-time interaction frequency of all the to-be-evaluated targets in the ranking range.

[0039] Further, the analysis evaluation index is determined according to the real-time correctness, the real-time access times and the real-time interaction frequency of all the to-be-evaluated targets in the ranking range, and includes:

[0040] The real-time correctness, the real-time access times and the real-time interaction frequency of all the to-be-evaluated targets in the ranking range are input into the preset cluster analysis model to obtain the analysis evaluation index.

[0041] Further, the preset standard reference threshold is adjusted according to the target evaluation index and the analysis evaluation index to form an adjusted standard reference threshold, and includes:

[0042] The relative deviation of the target evaluation index and the analysis evaluation index is calculated to form an index deviation.

[0043] When the index deviation is greater than a preset deviation threshold, the preset standard reference threshold is adjusted according to the relative deviation of the index deviation and the preset deviation threshold and a preset adjustment coefficient to form an adjusted standard reference threshold.

[0044] Further, the evaluation level of the to-be-evaluated target is determined according to the target evaluation index, and includes:

[0045] The evaluation level corresponding to the target evaluation index is queried in a preset evaluation index table to obtain the evaluation level of the to-be-evaluated target.

[0046] Compared with the prior art, the present application has the beneficial effect that by fusing the double evaluation mechanism of standard reference and norm reference, the performance of students in different learning scenarios can be accurately captured, their learning state can be evaluated in real time and dynamically adjusted. Through the step-by-step adjustment of the standard reference threshold and the deep application of the clustering analysis model, the limitations of single evaluation method can be eliminated, making the evaluation results more comprehensive, accurate and personalized. In addition, this method not only can timely find the weak links of students in the learning process, but also can dynamically adjust the threshold and evaluation standard according to the actual performance, improve the flexibility and adaptability of education evaluation, and effectively solve the problem of low recognition accuracy of processing equipment caused by poor data objectivity due to single evaluation standard.

[0047] Further, by comparing the real-time access times with the preset standard reference threshold, those targets that may have insufficient participation can be effectively screened out, so as to timely identify potential low activity problems. By marking these low access targets in advance, it can provide basis for subsequent teaching strategy adjustment and resource optimization, and ensure that the evaluation process is more accurate and targeted.

[0048] Further, by comparing the correct rate fluctuation value with the preset correct rate fluctuation threshold, targets with unstable performance can be identified. Even if the overall correct rate is high, the large fluctuation may imply unstable learning state. Using fluctuation analysis, a more comprehensive evaluation than simply relying on static correct rate can be provided, thereby helping to identify potential problems and optimize the learning process of learners. This method helps to more objectively analyze the state of learners and provide data support for educational decision-making.

[0049] Further, by analyzing the fluctuation of interaction frequency and access times, targets with unstable performance are identified. This can accurately locate the targets that need intervention and avoid making judgments based on static data, thereby improving the accuracy of evaluation and the effectiveness of intervention, and ensuring that learning goals can be properly focused and supported.

[0050] Further, by quantifying the fluctuation of interaction frequency and access times and calculating the change synchronization degree, targets with different performance fluctuations can be effectively distinguished, and targets that do not meet the synchronization requirement are marked as impact targets, thereby optimizing the subsequent processing process and improving the accuracy of evaluation results.

[0051] Further, by the method of weighted summation, multi-dimensional data can be integrated and each index can be given a reasonable weight, so that the target evaluation index is more accurate and objective. Through this index, the target can be comprehensively evaluated, which helps decision makers to identify and prioritize targets with excellent performance.

[0052] Further, by combining ranking, ranking calculation and comparison with normal reference value, the performance of each target to be evaluated can be objectively evaluated, avoiding the deviation caused by single standard, and ensuring that the analysis and evaluation index is more accurate and comprehensive. At the same time, with the support of cluster analysis model, the accuracy and reliability of evaluation can be effectively improved in multiple dimensions.

[0053] Further, through the application of cluster analysis model, multiple evaluation dimensions can be effectively integrated to provide a comprehensive and accurate evaluation index. By combining real-time data, the actual performance of the target can be dynamically reflected, avoiding the limitations of single evaluation standard, thereby providing a scientific basis for decision-making.

[0054] Further, according to the difference between the actual performance of the target and the evaluation index, the standard reference threshold is dynamically adjusted to ensure that the evaluation system is more accurate and flexible. By adjusting the threshold, the deviation in different situations can be addressed, improving the accuracy and adaptability of evaluation, thereby optimizing the decision-making process.

[0055] Further, by searching the evaluation index table, the corresponding evaluation grade can be efficiently and accurately assigned to the target to be evaluated, reducing the interference of human factors and ensuring the consistency and objectivity of evaluation. At the same time, the entire evaluation process has the advantages of standardization and automation, which helps to improve the transparency and efficiency of evaluation. BRIEF DESCRIPTION OF DRAWINGS

[0056] Figure 1 The flowchart of the education data processing method based on the coexistence of standard reference and normal reference of the present embodiment is shown in the figure.

[0057] Figure 2 The logic decision diagram for determining the first temporary target of the present embodiment is shown in the figure.

[0058] Figure 3 The logic decision diagram for determining the second temporary target of the present embodiment is shown in the figure.

[0059] Figure 4 The logic decision diagram for determining the influence target of the present embodiment is shown in the figure. DETAILED DESCRIPTION

[0060] In order to make the purpose and advantages of the present application more clear and explicit, the present application will be further described below in combination with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present application, and do not limit the present application.

[0061] The preferred embodiments of the present application will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application, and are not intended to limit the protection scope of the present application.

[0062] Please refer to Figure 1As shown, it is the flow chart of the education data processing method based on the coexistence of standard reference and norm reference in this embodiment;

[0063] The embodiment provides an education data processing method based on the coexistence of standard reference and norm reference, which comprises the following steps:

[0064] Obtaining the real-time access frequency of each to-be-evaluated target in an online learning platform, the real-time accuracy rate of each to-be-evaluated target after testing and the real-time interaction frequency of each to-be-evaluated target in an offline classroom;

[0065] Determining a plurality of first temporary targets according to the real-time access frequency and a preset standard reference threshold value;

[0066] Determining a plurality of second temporary targets according to the real-time accuracy rate of each of the first temporary targets;

[0067] Determining a plurality of processing targets according to the real-time interaction frequency and the real-time access frequency of each of the second temporary targets;

[0068] Determining a target evaluation index according to the real-time access frequency, the real-time accuracy rate and the real-time interaction frequency of each of the processing targets;

[0069] Determining an analysis evaluation index according to a preset norm reference value, the real-time accuracy rate of all to-be-evaluated targets, all the real-time access frequencies and all the real-time interaction frequencies and a preset clustering analysis model;

[0070] Adjusting the preset standard reference threshold value according to the target evaluation index and the analysis evaluation index to form an adjusted standard reference threshold value;

[0071] Determining a target evaluation index based on the adjusted standard reference threshold value, and determining an evaluation grade of the to-be-evaluated target according to the target evaluation index.

[0072] The real-time data of each to-be-evaluated target is usually obtained through the data interface of the integrated online learning platform, test system and classroom interaction tool. The access frequency of the online learning platform can be automatically recorded through student login behavior, course browsing record, etc., and is updated in real time; the accuracy rate after testing is collected through the interface of the test system, the performance data of each test of the student is collected in real time, and the real-time accuracy rate is calculated; the interaction frequency of the offline classroom is collected through the interaction equipment in the classroom (such as smart blackboard, classroom management system, student response system, etc.), such as the number of times of answering questions, the number of times of asking questions, the frequency of raising hands, etc. These data are monitored and stored in real time through a unified data collection platform to ensure the accuracy and timeliness of each index for subsequent analysis and processing.

[0073] The preset standard reference threshold is a benchmark value used to distinguish whether the learning behavior of a student meets the basic standard, which is usually determined by historical data on the platform or expected learning goals, and is usually set between 8 visits and 12 visits. In this embodiment, it is set to 10 visits, which can ensure that the student's learning participation on the platform reaches a certain level, avoiding mis-evaluation of low-participation students as good students.

[0074] The preset norm reference value is a benchmark ranking value used to evaluate the relative performance of the target to be evaluated, which depends on the overall distribution of the target group to be evaluated, especially the ranking of the target in the group. It is usually set to the ranking value of a preset percentage of the total number of targets in the target group, ensuring that the relative position of the evaluated target in the group meets the predetermined standard. It is usually set to the top 10% or 30% of the total number of targets in the target group. In this embodiment, the preset norm reference value is set to the top 20% of the total number of targets in the target group, which can ensure moderate screening and stratification during system evaluation, avoiding excessive concentration or excessive dispersion of evaluation results, thereby optimizing the ranking and evaluation of the target.

[0075] The preset clustering analysis model is the KAMILA clustering algorithm model. KAMILA clustering analysis model is a multi-modal data analysis method based on clustering algorithm. KAMILA clustering algorithm combines K-means clustering method with multi-instance learning, which can process multi-dimensional data and effectively perform clustering analysis in different types of modal data. Specifically, KAMILA clustering algorithm represents each data instance as multiple sub-instances (i.e. multiple features or data points), and uses the relationship between each sub-instance for clustering. This method not only can effectively cluster structured data, but also can handle uncertainty and noise in data, especially suitable for scenarios in the education field that need to consider multiple evaluation indicators (such as test scores, interaction frequency, etc.) for comprehensive evaluation. In this embodiment, the KAMILA clustering model can process data from different data sources (such as online learning platform visit times, test accuracy, and classroom interaction frequency) at the same time, forming a multi-dimensional evaluation system. Through multi-instance learning, it can better handle data with uncertainty and noise, ensuring more robust clustering results. Through clustering analysis, it can take into account the evaluation methods of standard reference and norm reference, solve the problem of fragmented evaluation standards in traditional methods, and provide more comprehensive and objective evaluation results.

[0076] Firstly, real-time data of the target to be evaluated in different learning scenarios is obtained, including the access frequency of the online learning platform, the accuracy rate after testing, and the interaction frequency of offline classes. By setting a standard reference threshold, a first temporary target is determined, and a second temporary target is further selected according to the real-time accuracy rate. Then, the processing target is determined by combining the interaction frequency and the access frequency, and the target evaluation index is calculated according to these data. Next, the analysis evaluation index is generated through the norm reference value and the clustering analysis model, and then the standard reference threshold is adjusted. Finally, based on the adjusted standard reference threshold, the final evaluation level of the target to be evaluated is determined.

[0077] By fusing the dual evaluation mechanism of standard reference and norm reference, the performance of students in different learning scenarios can be accurately captured, and their learning status can be evaluated and dynamically adjusted in real time. Through the gradual adjustment of the standard reference threshold and the deep application of the clustering analysis model, the limitations of single evaluation method can be eliminated, making the evaluation results more comprehensive, accurate and personalized. In addition, this method not only can timely find the weak links of students in the learning process, but also can dynamically adjust the threshold and evaluation standard according to the actual performance, improve the flexibility and adaptability of education evaluation, and effectively solve the problem of low recognition accuracy of processing equipment caused by poor data objectivity due to single evaluation standard.

[0078] Please continue to refer to Figure 2 As shown in the logic decision diagram for determining the first temporary target of the embodiment;

[0079] Specifically, determining a plurality of first temporary targets according to the real-time access frequency and the preset standard reference threshold comprises:

[0080] When the real-time access frequency is less than the preset standard reference threshold, the target to be evaluated is determined as a first temporary target, forming a plurality of first temporary targets.

[0081] According to the comparison of the real-time access frequency and the preset standard reference threshold, when the real-time access frequency of the target to be evaluated is less than the preset standard reference threshold, the target is determined as a first temporary target. Through this determination, the system can screen out targets with insufficient access, and analyze and process them separately, so as to further evaluate the performance of the target according to other indicators.

[0082] By comparing the real-time access frequency and the preset standard reference threshold, targets that may have insufficient participation can be effectively screened out, so as to timely identify potential low activity problems. By marking these low access targets in advance, it can provide basis for subsequent teaching strategy adjustment and resource optimization, and ensure that the evaluation process is more accurate and targeted.

[0083] Please continue to refer to Figure 3As shown, it is the logical decision diagram for determining the second temporary target in this embodiment;

[0084] Specifically, determining several second temporary targets according to the real-time accuracy of each first temporary target includes:

[0085] When the real-time accuracy is greater than the preset accuracy threshold, the standard deviation of the real-time accuracy in a preset first determination duration is calculated to form an accuracy fluctuation value;

[0086] When the accuracy fluctuation value is greater than a preset accuracy fluctuation threshold, the first temporary target is determined as the second temporary target to form several second temporary targets.

[0087] The preset accuracy threshold is a standard value for judging whether the learning target performs well, which depends on the requirements of the educational scene and the distribution of historical data, and is usually set between 80%-90%, and is set to 85% in this embodiment, which helps to filter out those targets that basically meet the learning requirements, and ensures that the subsequent analysis can focus on the low accuracy targets that need more attention.

[0088] The preset first determination duration is a time period for calculating the real-time accuracy fluctuation value, which depends on the evaluation cycle and stability requirements of the target performance, and is usually set between 10 minutes and 30 minutes, and is set to 15 minutes in this embodiment, which can balance the evaluation accuracy and the change of real-time data, and ensure that the performance trend of the target can be reflected in time during the evaluation process.

[0089] The preset accuracy fluctuation threshold is a parameter for evaluating the stability of the target performance, which is set based on the historical performance fluctuation of the target group, and is usually set between 5%-15%, and is set to 10% in this embodiment, which helps to identify targets with high accuracy but large fluctuations, avoids ignoring targets with high accuracy but instability, and ensures that learners with inconsistent performance are screened for intervention.

[0090] After the first temporary target is screened out, further analysis is performed according to the real-time accuracy of each target. When the real-time accuracy is greater than the preset accuracy threshold, the system calculates the accuracy standard deviation in a certain time period to obtain the accuracy fluctuation value. If the fluctuation value is greater than the preset accuracy fluctuation threshold, the target is determined as the second temporary target. This process helps to screen out targets with large performance fluctuations for more in-depth evaluation and adjustment.

[0091] By comparing the correct rate fluctuation value with the preset correct rate fluctuation threshold, unstable targets can be identified, even if their overall correct rate is high. The fluctuation analysis can provide a more comprehensive evaluation than relying solely on static correct rate, thereby helping to identify potential problems and optimize the learning process of learners. This method helps to more objectively analyze the state of learners and provides data support for educational decision-making.

[0092] Specifically, determining a number of processing targets according to the real-time interaction frequency and the real-time access times of each second temporary target includes:

[0093] Calculating the standard deviation of the real-time interaction frequency in the preset second determination duration to form an interaction frequency fluctuation value;

[0094] Calculating the standard deviation of the real-time access times in the preset second determination duration to form an access times fluctuation value;

[0095] Determining a number of processing targets according to the interaction frequency fluctuation value and the access times fluctuation value.

[0096] The preset second determination duration is a time period for calculating the real-time interaction frequency and access times fluctuation value, which depends on the collection period of interaction data and the requirement of target activity frequency, and is usually set between 20 minutes and 60 minutes. In this embodiment, it is set to 30 minutes, which can cover a relatively complete interaction process and ensure that the calculation of fluctuation value is more comprehensive and accurate, which is helpful for analyzing the performance fluctuation of the target.

[0097] The setting of the preset second determination duration helps to reduce the interference of short-term data fluctuation, ensure the stability and accuracy of the calculation of fluctuation value, and provide a more comprehensive and reliable basis for target evaluation, thereby improving the accuracy of analysis results and the effectiveness of decision-making.

[0098] First, the standard deviations of the real-time interaction frequency and the real-time access times in the preset second determination duration are calculated to obtain the interaction frequency fluctuation value and the access times fluctuation value, respectively. Then, according to the changes of the two fluctuation values, it is judged which second temporary targets show greater fluctuations. According to the size of the fluctuation value, the targets that need to be further processed are selected to form a number of processing targets.

[0099] By analyzing the fluctuations of interaction frequency and access times, unstable targets can be identified. This can accurately locate the targets that need to be intervened, avoid making judgments based on static data, thereby improving the accuracy of evaluation and the effect of intervention, and ensuring that learning targets can be properly paid attention to and supported.

[0100] Please continue to refer to Figure 4 As shown in the figure, it is a logical decision diagram for determining the influence target in this embodiment.

[0101] Specifically, determining a number of processing targets according to the interaction frequency fluctuation value and the access frequency fluctuation value includes:

[0102] Plotting a change curve according to the interaction frequency fluctuation value to form an interaction change curve;

[0103] Plotting a change curve according to the access frequency fluctuation value to form an access change curve;

[0104] Calculating a cosine similarity of the interaction change curve and the access change curve to form a change synchronization degree;

[0105] When the change synchronization degree is less than a preset synchronization degree threshold, determining that the second temporary target is an impact target;

[0106] Selecting non-impact targets in all the to-be-evaluated targets as processing targets to form a number of processing targets.

[0107] The preset synchronization degree threshold is a standard value for determining the change synchronization between the interaction frequency fluctuation value and the access frequency fluctuation value, and depends on specific evaluation scenarios and data characteristics. It is usually set between 0.6 and 0.8, and is set to 0.75 in this embodiment. It can effectively screen out targets with large differences in interaction frequency and access frequency fluctuation, ensure that the actual situation can be accurately reflected when processing targets, and thus improve the reliability and practicability of target evaluation.

[0108] First, change curves are plotted according to the interaction frequency fluctuation value and the access frequency fluctuation value to generate an interaction change curve and an access change curve. Then, a cosine similarity of the two change curves is calculated to obtain a change synchronization degree. When the change synchronization degree is less than a preset synchronization degree threshold, the second temporary target is determined as an impact target. Finally, non-impact targets are selected from the to-be-evaluated targets as processing targets to form a number of processing targets.

[0109] By quantifying the fluctuations of interaction frequency and access frequency and calculating the change synchronization degree, targets with different performance fluctuations can be effectively distinguished, and targets that do not meet the synchronization requirement are marked as impact targets, thereby optimizing the subsequent processing process and improving the accuracy of the evaluation result.

[0110] Specifically, determining a target evaluation index according to the real-time access frequency, the real-time accuracy rate, and the real-time interaction frequency of each processing target includes:

[0111] Normalizing the real-time access frequency to form a normalized access frequency;

[0112] Normalizing the real-time accuracy rate to form a normalized accuracy rate;

[0113] normalizing the real-time interaction frequency to form a normalized interaction frequency;

[0114] weighting and summing the normalized access frequency, the normalized accuracy rate, the normalized interaction frequency, a preset access frequency weight, a preset accuracy rate weight, and a preset interaction frequency weight to form a target evaluation index.

[0115] The preset access frequency weight is used to represent the influence degree of the access frequency on the target evaluation index, and is determined by the business requirements of the target and the importance of the access frequency. Generally, it is set between 0 and 1, and in this embodiment, it is set to 0.3, which can reflect the importance of the access frequency while avoiding excessive dependence on a single indicator.

[0116] The preset accuracy rate weight is used to represent the influence degree of the accuracy rate on the target evaluation index, and is determined by the accuracy requirement of the target task. Generally, it is set between 0 and 1, and in this embodiment, it is set to 0.4, which can emphasize the importance of accuracy and ensure that accuracy is fully considered in task evaluation.

[0117] The preset interaction frequency weight is used to represent the influence degree of the interaction frequency on the target evaluation index, and is determined by the actual significance of the interaction behavior to the target. Generally, it is set between 0 and 1, and in this embodiment, it is set to 0.3, which can balance the influence of the interaction frequency and ensure that the interaction factor is not ignored in target evaluation.

[0118] First, the real-time access frequency, the real-time accuracy rate, and the real-time interaction frequency are weighted and processed, and the respective preset weights are considered. Then, by means of weighted summation, the target evaluation index of each processing target is calculated, which comprehensively reflects the performance of the target in each indicator.

[0119] The weighted summation method can integrate multi-dimensional data and give each indicator a reasonable weight, so that the target evaluation index is more accurate and objective. Through this index, the target can be comprehensively evaluated, which helps decision makers to identify and prioritize those targets that perform well.

[0120] Specifically, the analysis evaluation index is determined according to the preset norm reference value, the real-time accuracy rate of all the targets to be evaluated, the real-time access frequency of all the targets to be evaluated, and the real-time interaction frequency of all the targets to be evaluated, and a preset cluster analysis model.

[0121] The real-time accuracy rates are sorted and the ranking values of each target to be evaluated are determined.

[0122] The sum of the ranking value and the preset norm reference value is calculated to obtain the lower limit of the ranking range, and the difference between the ranking value and the preset norm reference value is calculated to obtain the upper limit of the ranking range, forming a ranking range.

[0123] The real-time correctness, the real-time access times and the real-time interaction frequency of all the to-be-evaluated targets within the ranking range are determined to obtain the analysis evaluation index.

[0124] Firstly, the real-time correctness of all the to-be-evaluated targets is sorted according to the preset norm reference value to determine the ranking value of each target. Then, the sum of each ranking value and the preset norm reference value is calculated to obtain the lower limit of the ranking range, and the difference is calculated to determine the upper limit, forming the ranking range. Within this range, the real-time correctness, access times and interaction frequency of each target are combined to finally determine the analysis evaluation index.

[0125] By combining sorting, ranking calculation and comparison with the norm reference value, the performance of each to-be-evaluated target can be objectively and comprehensively evaluated, avoiding the deviation caused by a single standard and ensuring that the analysis evaluation index is more accurate and comprehensive. At the same time, with the support of the clustering analysis model, the accuracy and reliability of the evaluation can be effectively improved in multiple dimensions.

[0126] Specifically, determining the analysis evaluation index according to the real-time correctness, the real-time access times and the real-time interaction frequency of all the to-be-evaluated targets within the ranking range comprises:

[0127] The real-time correctness, the real-time access times and the real-time interaction frequency of all the to-be-evaluated targets within the ranking range are input into the preset clustering analysis model to obtain the analysis evaluation index.

[0128] According to the determined ranking range, the real-time correctness, real-time access times and real-time interaction frequency of all the to-be-evaluated targets within the ranking range are taken as inputs and brought into the preset clustering analysis model. The model will comprehensively evaluate the performance of each target according to these input data and output an analysis evaluation index.

[0129] Through the application of the clustering analysis model, multiple evaluation dimensions can be effectively integrated to provide a comprehensive and accurate evaluation index. By combining real-time data, the actual performance of the target can be dynamically reflected, avoiding the limitations of a single evaluation standard, thereby providing a scientific basis for decision-making.

[0130] Specifically, adjusting the preset standard reference threshold value according to the target evaluation index and the analysis evaluation index to form an adjusted standard reference threshold value comprises:

[0131] The relative deviation of the target evaluation index and the analysis evaluation index is calculated to form an index deviation.

[0132] When the index deviation is greater than a preset deviation threshold value, the preset standard reference threshold value is adjusted according to the relative deviation of the index deviation and the preset deviation threshold value and a preset adjustment coefficient to form an adjusted standard reference threshold value.

[0133] The preset deviation threshold is used to determine whether the difference between the target evaluation index and the analysis evaluation index is significant, thereby deciding whether to adjust the standard reference threshold. The preset deviation threshold is usually set between 0.05 and 0.1, and is set to 0.08 in this embodiment, aiming to balance accuracy and flexibility, and avoid excessive adjustment caused by too small threshold, affecting stability.

[0134] First, the index deviation is obtained by calculating the relative deviation between the target evaluation index and the analysis evaluation index. When the index deviation exceeds the preset deviation threshold, the preset standard reference threshold is adjusted according to the relative deviation of the index deviation, the deviation threshold and the preset adjustment coefficient, thereby forming a new adjusted standard reference threshold.

[0135] According to the difference between the actual performance of the target and the evaluation index, the standard reference threshold is dynamically adjusted to ensure that the evaluation system is more accurate and flexible. By adjusting the threshold, it can cope with the deviation under different situations, improve the accuracy and adaptability of evaluation, and thus optimize the decision-making process.

[0136] Specifically, determining the evaluation level of the target to be evaluated according to the target evaluation index comprises:

[0137] In the preset evaluation index table, the evaluation level corresponding to the target evaluation index is queried to obtain the evaluation level of the target to be evaluated.

[0138] The preset evaluation index table is a pre-set standardized table that records the correspondence between different target evaluation indexes and corresponding evaluation levels, and is designed according to the performance level and evaluation standard of the target. It is generally set within a suitable index range, and is usually set according to the needs of actual application scenarios.

[0139] The evaluation level refers to the evaluation result level determined according to the value of the target evaluation index, which is usually divided from low to high according to the performance. The evaluation level is set according to the evaluation standard, performance requirements and business needs of the target.

[0140] In this embodiment, the preset evaluation index table is:

[0141]

[0142] First, the target evaluation index is queried to search the preset evaluation index table. According to the value of the target evaluation index, the corresponding evaluation level is found, and the level is assigned to the target to be evaluated. Through this query method, a specific evaluation level can be quickly generated for each target.

[0143] By looking up the evaluation index table, the corresponding evaluation grade can be efficiently and accurately assigned to the target to be evaluated, the interference of human factors is reduced, and the consistency and objectivity of the evaluation are ensured. Meanwhile, the whole evaluation process has the advantages of standardization and automation, which helps to improve the transparency and efficiency of the evaluation.

[0144] Thus far, the technical solutions of the present application have been described in connection with the preferred embodiments shown in the drawings, but those skilled in the art will readily understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to the relevant technical features without departing from the principles of the present application, and the technical solutions after such changes or replacements will all fall within the protection scope of the present application.

[0145] The above description is only preferred embodiments of the present application and is not intended to limit the present application; for those skilled in the art, the present application can have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. An educational data processing method based on coexistence of a standard reference and a norm reference, characterized by, The method comprises: acquiring real-time access times of each target to be evaluated in an online learning platform, real-time accuracy rates of each target to be evaluated after testing, and real-time interaction frequencies of each target to be evaluated in an offline classroom; determining a plurality of first temporary targets according to the real-time access times and a preset standard reference threshold value; determining a plurality of second temporary targets according to the real-time accuracy rates of each first temporary target; determining a plurality of processing targets according to the real-time interaction frequencies and the real-time access times of each second temporary target; determining a target evaluation index according to the real-time access times, the real-time accuracy rates, and the real-time interaction frequencies of each processing target; determining an analysis evaluation index according to a preset norm reference value, the real-time accuracy rates of all targets to be evaluated, all real-time access times, and all real-time interaction frequencies, and a preset cluster analysis model; adjusting the preset standard reference threshold value according to the target evaluation index and the analysis evaluation index to form an adjusted standard reference threshold value; determining a target evaluation index based on the adjusted standard reference threshold value, and determining an evaluation grade of the target to be evaluated according to the target evaluation index.

2. The educational data processing method based on the coexistence of the standard reference and the norm reference according to claim 1, characterized in that, The method comprises: when the real-time access times are less than the preset standard reference threshold value, determining that the target to be evaluated is a first temporary target, and forming a plurality of first temporary targets.

3. The educational data processing method based on the coexistence of the standard reference and the norm reference according to claim 2, characterized in that, The method comprises: when the real-time accuracy rate is greater than a preset accuracy rate threshold value, calculating a standard deviation of the real-time accuracy rate within a preset first determination time period to form an accuracy rate fluctuation value; when the accuracy rate fluctuation value is greater than a preset accuracy rate fluctuation threshold value, determining that the first temporary target is a second temporary target, and forming a plurality of second temporary targets.

4. The educational data processing method based on the coexistence of the standard reference and the norm reference according to claim 3, characterized in that, The method comprises: calculating a standard deviation of the real-time interaction frequency within a preset second determination time period to form an interaction frequency fluctuation value; calculating a standard deviation of the real-time access times within the preset second determination time period to form an access times fluctuation value; determining a plurality of processing targets according to the interaction frequency fluctuation value and the access times fluctuation value.

5. The educational data processing method based on the coexistence of the standard reference and the norm reference according to claim 4, characterized in that, The method comprises: drawing a change curve according to the interaction frequency fluctuation value to form an interaction change curve; drawing a change curve according to the access times fluctuation value to form an access change curve; calculating a cosine similarity of the interaction change curve and the access change curve to form a change synchronization degree; when the change synchronization degree is less than a preset synchronization degree threshold value, determining that the second temporary target is an impact target; selecting non-impact targets in all targets to be evaluated as processing targets to form a plurality of processing targets.

6. The educational data processing method based on the coexistence of the standard reference and the norm reference according to claim 5, characterized in that, The method comprises: performing normalization processing on the real-time access times to form a normalized access time; The real-time correctness is normalized to form a normalized correctness; The real-time interaction frequency is normalized to form a normalized interaction frequency; The normalized access frequency, the normalized correctness, the normalized interaction frequency, a preset access frequency weight, a preset correctness weight, and a preset interaction frequency weight are weighted and summed to form a target evaluation index.

7. The educational data processing method based on the coexistence of the standard reference and the norm reference according to claim 6, characterized in that, The analysis evaluation index is determined according to a preset norm reference value, the real-time correctness, the real-time access frequency, and the real-time interaction frequency of all the to-be-evaluated targets, and a preset cluster analysis model. The real-time correctness of all the to-be-evaluated targets is sorted to determine a ranking value of each to-be-evaluated target. The sum of the ranking value and the preset norm reference value is calculated to obtain a lower limit of a ranking range, and the difference between the ranking value and the preset norm reference value is calculated to obtain an upper limit of the ranking range, forming a ranking range. The analysis evaluation index is determined according to the real-time correctness, the real-time access frequency, and the real-time interaction frequency of all the to-be-evaluated targets in the ranking range.

8. The educational data processing method based on the coexistence of the standard reference and the norm reference according to claim 7, characterized in that, The analysis evaluation index is determined according to the real-time correctness, the real-time access frequency, and the real-time interaction frequency of all the to-be-evaluated targets in the ranking range, including: The real-time correctness, the real-time access frequency, and the real-time interaction frequency of all the to-be-evaluated targets in the ranking range are input into the preset cluster analysis model to obtain the analysis evaluation index.

9. The educational data processing method based on the coexistence of the standard reference and the norm reference according to claim 8, characterized in that, The preset standard reference threshold is adjusted according to the target evaluation index and the analysis evaluation index to form an adjusted standard reference threshold, including: The relative deviation of the target evaluation index and the analysis evaluation index is calculated to form an index deviation. When the index deviation is greater than a preset deviation threshold, the preset standard reference threshold is adjusted according to the relative deviation of the index deviation and the preset deviation threshold and a preset adjustment coefficient to form an adjusted standard reference threshold.

10. The educational data processing method based on the coexistence of the standard reference and the norm reference according to claim 9, characterized in that, The evaluation level of the to-be-evaluated target is determined according to the target evaluation index, including: The evaluation level corresponding to the target evaluation index is queried in a preset evaluation index table to obtain the evaluation level of the to-be-evaluated target.

Images