Training effect evaluation method and system based on learning data analysis

Abstract

The invention relates to the technical field of informatization teaching, in particular to a training effect evaluation method and system based on learning data analysis. According to the method, the corresponding data of the student in the learning process is collected, the data is classified, and the classified data is preprocessed, so that the collected data has higher utilization value; meanwhile, whether the training effect meets the standard or not is judged through the average interaction ratio of interaction between the multiple trainees and the course and the variance of the interaction ratio of the trainees, and the judgment result can be more accurate; and under the condition that the training effect does not meet the standard, the reason is determined based on the average value of the interaction rate, and the corresponding processing mode is generated according to the reason, so that the related process of training is more accurately adjusted according to the processing mode, and the training effect is further improved.

Description

Technical Field

[0001] The present invention relates to the field of information-based teaching technology, and in particular to a training effect evaluation method and system based on learning data analysis. Background Art

[0002] In the field of education and training, scientifically and objectively evaluating training effectiveness has always been a core challenge. Traditional training effectiveness evaluation methods (such as questionnaires, expert scoring, or exams) are subject to high subjectivity, low efficiency, and delayed feedback, making them difficult to meet the needs of modern enterprises for dynamic, personalized, and real-time evaluation. With the development of educational technology and data science, evaluation methods based on learning data analysis have gradually become a research hotspot, but their technical implementation still faces multiple bottlenecks.

[0003] Chinese Patent Publication No. CN119415941A discloses a personnel training data information processing method and system, which includes: using deep learning-based data analysis and processing technology to perform semantic embedding encoding on the pre-training behavior data and post-training behavior data of the tracked employee, thereby automatically judging whether the training effect is positive or negative based on the principal component-based temporal aggregation representation between the semantic embedding features of the pre-training behavior data and the semantic embedding features of the post-training behavior data.

[0004] However, the existing technology still has the following problems: it fails to determine whether the training effect meets the standards based on the data of the user during the learning process, and fails to determine the cause and generate corresponding processing methods when it is determined that the training results do not meet the standards, so as to be unable to adjust the relevant training processes more accurately according to the processing methods, thereby further improving the training effect. Summary of the Invention

[0005] To this end, the present invention provides a training effect evaluation method and system based on learning data analysis to overcome the problem in the prior art that it cannot accurately determine whether the training results meet the standards, and cannot generate corresponding processing methods based on the reasons why the training effects do not meet the standards, thereby failing to more accurately adjust the relevant training processes and further improve the training effects.

[0006] To achieve the above objectives, the present invention provides a training effect evaluation method based on learning data analysis, comprising:

[0007] Collect students' corresponding data during the learning process;

[0008] Classify the collected data;

[0009] Perform data preprocessing on the classified data;

[0010] Generate learning information of each student for a single course in sequence based on various types of data after data preprocessing;

[0011] Calculating an average interaction ratio of the interactions between a number of students and the course in the learning information, wherein the average interaction ratio is the average value of the ratio of the number of actual interactions of the students in the course to the total number of interaction nodes in the course;

[0012] Based on the average interaction ratio, it is determined whether the training effect meets the standard. When it is determined that the training effect does not meet the standard, a corresponding processing method is generated based on the determined reason for not meeting the standard. The processing method includes adjusting the standard interval for screening out abnormal data during data preprocessing and adjusting the number of the interaction nodes.

[0013] Furthermore, the process of determining whether the training effect meets the standards based on the average interaction ratio includes: determining whether the training effect meets the standards based on the comparison result of the average interaction ratio and the pre-stored preset interaction ratio; if the average interaction ratio is greater than or equal to the first preset interaction ratio, determining that the training effect meets the standards; if the average interaction ratio is less than the first preset interaction ratio and greater than the second preset interaction ratio, determining whether the training effect meets the standards based on the variance of the interaction ratio of each student, wherein the interaction ratio is the ratio of the actual number of interactions in the course to the total number of interaction nodes in the course; if the average interaction ratio is less than or equal to the second preset interaction ratio, determining the reason why the training effect does not meet the standards based on the average value of the interaction rate, wherein the interaction rate is the ratio of the number of students participating in the interaction in a single interaction node to the total number of students.

[0014] Furthermore, the process of determining whether the training effect meets the standards based on the variance of the interaction ratio of each student includes: comparing the variance with the preset variance; if the variance is greater than the preset variance, determining that the training effect does not meet the standards, then determining the reason why the training effect does not meet the standards based on the average value of the interaction rate; if the variance is less than or equal to the preset variance, then adjusting the training duration of the next course in a single course group based on the difference between the variance and the preset variance.

[0015] Furthermore, the process of adjusting the training duration of the next course in the single course group based on the difference between the variance and the preset variance includes: calculating the difference between the variance and the preset variance; reducing the training duration based on the obtained difference, and the difference is proportional to the reduction in the training duration.

[0016] Furthermore, the process of determining the reason why the training effect does not meet the standards based on the average value of the interaction rate includes: determining the reason why the training effect does not meet the standards based on the comparison result of the average value of the interaction rate and the pre-stored preset average value; if the average value is greater than or equal to the first preset average value, it is determined that there is a problem with the standard interval for screening out abnormal data in data preprocessing, and the standard interval for screening out abnormal data is adjusted based on the difference between the average value and the preset average value; if the average value is less than the first preset average value and greater than the second preset average value, the reason why the training effect does not meet the standards is determined based on the average number of repeated plays of the course; if the average value is less than or equal to the second preset average value, it is determined that the training plan is unqualified, and a notification is issued.

[0017] Furthermore, the process of adjusting the standard interval for screening out abnormal data based on the difference between the average value and the preset average value includes: calculating the difference between the average value and the preset average value; reducing the standard interval based on the obtained difference, and the difference is proportional to the reduction of the standard interval.

[0018] Furthermore, the process of determining the reason why the training effect does not meet the standards based on the average number of repeated playbacks of the course includes: comparing the average number of repeated playbacks with the preset number of repeated playbacks; if the average number of repeated playbacks is greater than the preset number of repeated playbacks, the training plan is judged to be unqualified, and a notification is issued; if the average number of repeated playbacks is less than or equal to the preset number of repeated playbacks, the number of interactive nodes of a single course is adjusted based on the difference between the average number of repeated playbacks and the preset number of repeated playbacks.

[0019] Furthermore, the process of adjusting the number of interactive nodes of a single course based on the difference between the average number of repeated playbacks and the preset number of repeated playbacks includes: calculating the difference between the average number of repeated playbacks and the preset number of repeated playbacks; reducing the number of interactive nodes of a single course based on the obtained difference, and the difference is proportional to the extent of the reduction in the number.

[0020] Furthermore, the process of adjusting the training duration based on the number of interactive nodes includes: calculating the difference between the number of interactive nodes and a preset number; reducing the training duration based on the difference, and the difference is proportional to the reduction in the training duration.

[0021] To achieve the above objectives, the present invention provides a training effect evaluation system based on learning data analysis, comprising:

[0022] A data collection unit, which is used to collect corresponding data of students during the learning process;

[0023] a data classification unit, connected to the data collection unit, for classifying the collected data;

[0024] A data preprocessing unit, connected to the data classification unit, for performing data preprocessing on the classified data;

[0025] An information generating unit, connected to the data pre-processing unit, for sequentially generating learning information for each student for a single course based on the various types of data after data pre-processing;

[0026] a calculation unit connected to the information generation unit, configured to calculate an average interaction ratio of the interactions between a plurality of students and the course in the learning information, wherein the average interaction ratio is an average value of the ratio of the number of actual interactions of the plurality of students in the course to the total number of interaction nodes in the course;

[0027] An analysis unit is connected to the calculation unit and is used to determine whether the training effect meets the standard based on the average interaction ratio, and when it is determined that the training effect does not meet the standard, generate a corresponding processing method based on the determined reason for not meeting the standard, wherein the processing method includes adjusting the standard interval for screening out abnormal data during data preprocessing and adjusting the number of the interaction nodes.

[0028] Compared with the existing technology, the beneficial effect of the present invention is that the method collects the corresponding data of students in the learning process, classifies the data, and pre-processes the classified data, so that the collected data can be made more valuable; at the same time, the average interaction ratio of several students interacting with the course and the variance of the interaction ratio of each student are used to determine whether the training effect meets the standards, which can make the judgment result more accurate; and when the training effect does not meet the standards, the cause is determined based on the average value of the interaction rate, and a corresponding processing method is generated according to the cause, so that the relevant processes of the training can be adjusted more accurately according to the processing method, thereby further improving the training effect.

[0029] Furthermore, the present invention determines whether the training effect meets the standards by using the average interaction ratio and the pre-stored interaction ratio, which can more effectively determine whether the training effect meets the standards, thereby more accurately evaluating the training effect, and further adjusting the efficiency of the training process when the training effect does not meet the standards.

[0030] Furthermore, the present invention makes a secondary determination of the training effect based on the variance of the interaction ratio of each trainee when the interaction ratio is within a preset interaction ratio range, thereby being able to more accurately determine whether the training effect meets the standard.

[0031] Furthermore, the present invention adjusts the training duration of the next course in a single course group by the difference between the variance and the preset variance, which can adjust the training duration more accurately, so that training according to the adjusted training duration makes the training effect more effective.

[0032] Furthermore, the present invention determines the reason why the training effect does not meet the standards through the average value of the interaction rate, which can more accurately determine the reason why the training effect does not meet the standards, and thus more accurately adjust the training process according to the processing method generated by the reason, thereby further improving the training effect.

[0033] Furthermore, the present invention adjusts the standard interval for screening out abnormal data during data preprocessing by the difference between the average value and the preset average value, thereby making the collected data more effective and furthermore determining the evaluation effect more accurately.

[0034] Furthermore, the present invention determines the reason why the evaluation effect does not meet the standard by comparing the average number of repeated playbacks with the preset number of repeated playbacks when the average value is within the preset average value range, thereby adjusting the training process more accurately and further improving the effectiveness of the training.

[0035] Furthermore, the present invention adjusts the number of interactive nodes by the difference between the average number of repeated playbacks of a course and a preset number of repeated playbacks, thereby more accurately adjusting the number of interactive nodes and further more effectively adjusting the training process, making the training more effective.

[0036] Furthermore, the present invention adjusts the training duration by the number of interactive nodes, and can adjust the training duration more accurately, thereby more effectively adjusting the training process, and further making the training more effective. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a structural diagram of a training effect evaluation system based on learning data analysis according to an embodiment of the present invention;

[0038] Figure 2 This is a flowchart of the steps of a training effect evaluation method based on learning data analysis according to an embodiment of the present invention;

[0039] Figure 3 This is a flowchart of the steps for determining the result of comparing the average interaction ratio with the pre-stored preset interaction ratio according to an embodiment of the present invention;

[0040] Figure 4 4 is a flowchart of the steps for determining the result of comparing the average value of the interaction rate with a pre-stored preset average value according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0042] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0043] It should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0044] See also Figure 1 As shown, it is a structural diagram of a training effect evaluation system based on learning data analysis according to an embodiment of the present invention.

[0045] The system includes a data acquisition unit, a data classification unit, a data preprocessing unit, an information generation unit, a calculation unit and an analysis unit.

[0046] The data collection unit is used to collect corresponding data of students during the learning process;

[0047] The data classification unit is connected to the data collection unit and is used to classify the collected data;

[0048] The data preprocessing unit is connected to the data classification unit and is used to perform data preprocessing on the classified data;

[0049] The information generating unit is connected to the data pre-processing unit and is used to sequentially generate learning information of each student for a single course based on various types of data after data pre-processing;

[0050] The calculation unit is connected to the information generation unit and is used to calculate the average interaction ratio of the interaction between a number of students and the course in the learning information, wherein the average interaction ratio is the average value of the ratio of the number of actual interactions of the students in the course to the total number of interaction nodes in the course;

[0051] The analysis unit is connected to the calculation unit, and is used to determine whether the training effect meets the standard based on the average interaction ratio, and when it is determined that the training effect does not meet the standard, generate a corresponding processing method based on the determined reason for not meeting the standard, wherein the processing method includes adjusting the standard interval for screening out abnormal data during data preprocessing and adjusting the number of the interaction nodes.

[0052] Specifically, in this embodiment, the learning data of multiple users for a single course in a set of courses is mainly analyzed, and the data classification unit classifies the collected data, and the categories of classification specifically include: interaction ratio, completion rate, interaction rate, and the number of times the course is repeated; at the same time, the data preprocessing unit filters out abnormal data in the classified data, wherein the standard interval for screening is set to 0-10%; and the information generation unit generates the corresponding learning information of each student for a single course based on the preprocessed classified data, calculates the average interaction ratio of several students through the calculation unit, and determines whether the training effect meets the standard based on the average interaction ratio through the analysis unit, and uses the reason why the training effect does not meet the standard in the judgment result to generate a corresponding processing method.

[0053] See also Figure 2 As shown, it is a flowchart of the steps of the training effect evaluation method based on learning data analysis in an embodiment of the present invention.

[0054] The steps in the actual operation process of the system of the embodiment of the present invention include:

[0055] S1, collecting corresponding data of students during the learning process through the data collection unit;

[0056] S2, classifying the collected data by a data classification unit connected to the data collection unit;

[0057] S3, performing data preprocessing on the classified data by a data preprocessing unit connected to the data classification unit;

[0058] S4, generating learning information for each student for a single course in sequence according to the various types of data after data preprocessing by an information generating unit connected to the data preprocessing unit;

[0059] S5, calculating, by a calculation unit connected to the information generating unit, an average interaction ratio of the interactions between the plurality of students and the course in the learning information, wherein the average interaction ratio is an average value of the ratio of the number of actual interactions of the plurality of students in the course to the total number of interaction nodes in the course;

[0060] S6, determining whether the training effect meets the standards based on the average interaction ratio through an analysis unit connected to the calculation unit, and when it is determined that the training effect does not meet the standards, generating a corresponding processing method based on the determined reason for not meeting the standards, wherein the processing method includes adjusting the standard interval for screening out abnormal data during data preprocessing and adjusting the number of the interaction nodes.

[0061] See also Figure 3As shown, it is a flowchart of the steps of judging based on the comparison result of the average interaction ratio and the pre-stored preset interaction ratio according to an embodiment of the present invention. The process of judging whether the training effect meets the standard based on the average interaction ratio according to the embodiment of the present invention includes: judging whether the training effect meets the standard based on the comparison result of the average interaction ratio and the pre-stored preset interaction ratio; if the average interaction ratio is greater than or equal to the first preset interaction ratio, judging that the training effect meets the standard; if the average interaction ratio is less than the first preset interaction ratio and greater than the second preset interaction ratio, judging whether the training effect meets the standard based on the variance of the interaction ratio of each student, wherein the interaction ratio is the ratio of the actual number of interactions in the course to the total number of interaction nodes in the course; if the average interaction ratio is less than or equal to the second preset interaction ratio, determining the reason why the training effect does not meet the standard based on the average value of the interaction rate, wherein the interaction rate is the ratio of the number of students participating in the interaction in a single interaction node to the total number of students.

[0062] Specifically, in this embodiment, the average interaction ratio L0 can be divided into a first preset interaction ratio L1 and a second preset interaction ratio L2. The first preset interaction ratio L1 in the average interaction ratio standard is set to 0.8, and the second preset interaction ratio L2 is set to 0.55. It should be noted that in other embodiments, the values ​​of L1 and L2 can also be determined according to relative training effect requirements, and the values ​​of the average values ​​are rounded up. The comparison process based on the average value L with L1 and L2 is as follows:

[0063] If the average interaction ratio L0 is greater than or equal to the first preset interaction ratio L1, it is determined that the training effect meets the standard;

[0064] If the average interaction ratio L0 is less than the first preset interaction ratio L1 and greater than the second preset interaction ratio L2, it means that it is impossible to determine whether other factors cause this result. Then, whether the training effect meets the standard is determined based on the variance P of the interaction ratio of each trainee, where the interaction ratio is the ratio of the actual number of interactions in the course to the total number of interaction nodes in the course;

[0065] If the average interaction ratio L0 is less than or equal to the second preset interaction ratio L2, it is determined that the training effect does not meet the standard, and the reason why the training effect does not meet the standard is determined based on the average value Q of the interaction rate, where the interaction rate is the ratio of the number of students participating in the interaction in a single interaction node to the total number of students.

[0066] Specifically, the process of determining whether the training effect meets the standard based on the variance of the interaction ratio of each student in an embodiment of the present invention includes: comparing the variance with the preset variance; if the variance is greater than the preset variance, it is determined that the training effect does not meet the standard, and the reason why the training effect does not meet the standard is determined based on the average value of the interaction rate; if the variance is less than or equal to the preset variance, the training duration of the next course in a single course group is adjusted based on the difference between the variance and the preset variance.

[0067] Specifically, in this embodiment, the preset variance P0=0.95, and the comparison process based on the obtained variance P and the preset variance P0 is as follows:

[0068] If the variance P is greater than the preset variance P0, it means that the interaction ratio of each trainee is relatively discrete, and the training effect is determined to be not up to standard, and the reason why the training effect is not up to standard is determined based on the average value Q of the interaction rate;

[0069] If the variance P is less than or equal to the preset variance P0, it means that the student cannot keep up with the training content in the later stage of the course due to inability to maintain concentration. Then, the training duration of the next course in the single course group is adjusted based on the difference T between the variance and the preset variance.

[0070] Specifically, the process of adjusting the training duration of the next course in the single course group based on the difference between the variance and the preset variance in an embodiment of the present invention includes: calculating the difference between the variance and the preset variance; reducing the training duration based on the obtained difference, and the difference is proportional to the reduction in the training duration.

[0071] Specifically, in this embodiment, the preset difference value T0=0.1, and the comparison process based on the obtained difference value T and the preset difference value T0 is as follows:

[0072] If the difference T is less than or equal to the preset difference T0, the training duration is adjusted to 0.9 times the original training duration;

[0073] If the difference T is greater than the preset difference T0, the training duration is adjusted to 0.65 times the original training duration.

[0074] See also Figure 4As shown, it is a flowchart of the steps of determining the result of comparing the average value of the interaction rate with the pre-stored preset average value in an embodiment of the present invention. The process of determining the reason why the training effect does not meet the standard based on the average value of the interaction rate in an embodiment of the present invention includes: determining the reason why the training effect does not meet the standard based on the comparison result of the average value of the interaction rate with the pre-stored preset average value; if the average value is greater than or equal to the first preset average value, it is determined that there is a problem with the standard interval for screening out abnormal data in data preprocessing, and the standard interval for screening out abnormal data is adjusted based on the difference between the average value and the preset average value; if the average value is less than the first preset average value and greater than the second preset average value, the reason why the training effect does not meet the standard is determined based on the average number of repeated playbacks of the course; if the average value is less than or equal to the second preset average value, it is determined that the training plan is unqualified, and a notification is issued.

[0075] Specifically, in this embodiment, the average value Q0 of the interaction rate can be divided into a first preset average value Q1 and a second preset average value Q2. The first preset average value Q1 in the average value standard of the interaction rate is set to 0.8, and the second preset average value Q2 is set to 0.6. It should be noted that, in other embodiments, the values ​​of Q1 and Q2 can also be determined according to relative training effect requirements, and the values ​​of the average values ​​are rounded up. The specific comparison process based on the average value Q with Q1 and Q2 is as follows:

[0076] If the average value Q is greater than or equal to the first preset average value Q1, it indicates that too much data was screened out during the data preprocessing process, resulting in incomplete data and thus a misjudgment. It is determined that there is a problem with the standard interval for screening out abnormal data in the data preprocessing, and the standard interval for screening out abnormal data is adjusted based on the difference V between the average value and the preset average value;

[0077] If the average value Q is less than the first preset average value Q1 and greater than the second preset average value Q2, then the reason why the training effect does not meet the standard is determined based on the average number of repeated playbacks U of the course;

[0078] If the average value Q is less than or equal to the second preset average value Q2, the training plan is determined to be unqualified and a notification is issued.

[0079] Specifically, the process of adjusting the standard interval for screening out abnormal data based on the difference between the average value and the preset average value in an embodiment of the present invention includes: calculating the difference between the average value and the preset average value; reducing the standard interval based on the obtained difference, and the difference is proportional to the reduction degree of the standard interval.

[0080] Specifically, in this embodiment, the preset difference V0 between the average value and the preset average value is 0.05, and the comparison process based on the obtained difference V and the preset difference V0 is as follows:

[0081] If the difference V is less than or equal to the preset difference V0, the standard interval is adjusted to 0.9 times the original standard interval;

[0082] If the difference is greater than the preset difference V0, the standard interval is adjusted to 0.6 times the original standard interval.

[0083] Specifically, the process of determining the reason why the training effect does not meet the standards based on the average number of repeated playbacks of a course in an embodiment of the present invention includes: comparing the average number of repeated playbacks with the preset number of repeated playbacks; if the average number of repeated playbacks is greater than the preset number of repeated playbacks, it is determined that the training plan is unqualified, and a notification is issued; if the average number of repeated playbacks is less than or equal to the preset number of repeated playbacks, the number of interactive nodes of a single course is adjusted based on the difference between the average number of repeated playbacks and the preset number of repeated playbacks.

[0084] Specifically, in this embodiment, the preset number of repeated playbacks U0=3, and the comparison process based on the average number of repeated playbacks U and the preset number of repeated playbacks U0 is as follows:

[0085] If the average number of repeated playbacks U is greater than the preset number of repeated playbacks U0, the training program is determined to be unqualified, and a notification is issued;

[0086] If the average number of repeated playbacks U is less than or equal to the preset number of repeated playbacks U0, the number of interactive nodes of a single course is adjusted based on the difference W between the average number of repeated playbacks and the preset number of repeated playbacks.

[0087] Specifically, the process of adjusting the number of interactive nodes of a single course based on the difference between the average number of repeated playbacks and the preset number of repeated playbacks in an embodiment of the present invention includes: calculating the difference between the average number of repeated playbacks and the preset number of repeated playbacks; reducing the number of interactive nodes of a single course based on the obtained difference, and the difference is proportional to the extent of the reduction in the number.

[0088] Specifically, in this embodiment, the preset difference W0 between the average number of repeated playbacks and the preset number of repeated playbacks is 1, and the comparison process based on the difference W and the preset difference W0 is as follows:

[0089] If the difference W is less than or equal to the preset difference W0, the number of the interactive nodes of a single course is adjusted to 0.8 times the original number, wherein the adjusted number is rounded up;

[0090] If the difference W is greater than the preset difference W0, the number of the interactive nodes of a single course is adjusted to 0.6 times the original number, wherein the adjusted number is rounded up.

[0091] Specifically, the process of adjusting the training duration based on the number of interactive nodes in an embodiment of the present invention includes: calculating the difference between the number of interactive nodes and a preset number; reducing the training duration based on the difference, and the difference is proportional to the reduction in the training duration.

[0092] Specifically, in this embodiment, the preset difference M0 between the number of interactive nodes and the preset number is 1, and the comparison process based on the difference M and the preset difference M0 is as follows:

[0093] If the difference M is less than or equal to the preset difference M0, the training duration is adjusted to 0.85 times the original training duration, wherein the training duration is in minutes, and the number of minutes in the adjusted training duration is rounded up;

[0094] If the difference M is greater than the preset difference M0, the training duration is adjusted to 0.64 times the original training duration, wherein the training duration is in minutes, and the number of minutes in the adjusted training duration is rounded up.

[0095] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0096] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A training effect evaluation method based on learning data analysis, characterized in that: include: Collect students' corresponding data during the learning process; Classify the collected data; Perform data preprocessing on the classified data; Generate learning information of each student for a single course in sequence based on various types of data after data preprocessing; Calculating an average interaction ratio of the interactions between a number of students and the course in the learning information, wherein the average interaction ratio is the average value of the ratio of the number of actual interactions of the students in the course to the total number of interaction nodes in the course; Based on the average interaction ratio, it is determined whether the training effect meets the standard. When it is determined that the training effect does not meet the standard, a corresponding processing method is generated based on the determined reason for not meeting the standard. The processing method includes adjusting the standard interval for screening out abnormal data during data preprocessing and adjusting the number of the interaction nodes.

2. The training effect evaluation method based on learning data analysis according to claim 1 is characterized in that: The process of determining whether the training effect meets the standards based on the average interaction ratio includes: Determining whether the training effect meets the standard based on a comparison result of the average interaction ratio and a pre-stored preset interaction ratio; If the average interaction ratio is greater than or equal to a first preset interaction ratio, it is determined that the training effect meets the standard; If the average interaction ratio is less than the first preset interaction ratio and greater than the second preset interaction ratio, whether the training effect meets the standard is determined based on the variance of the interaction ratio of each trainee, wherein the interaction ratio is the ratio of the number of actual interactions in the course to the total number of interaction nodes in the course; If the average interaction ratio is less than or equal to the second preset interaction ratio, the reason why the training effect does not meet the standard is determined based on the average value of the interaction rate, where the interaction rate is the ratio of the number of trainees participating in the interaction in a single interaction node to the total number of trainees.

3. The training effect evaluation method based on learning data analysis according to claim 2 is characterized in that: The process of determining whether the training effect meets the standard based on the variance of the interaction ratio of each trainee includes: comparing the variance with a preset variance; If the variance is greater than the preset variance, it is determined that the training effect does not meet the standard, and the reason why the training effect does not meet the standard is determined based on the average value of the interaction rate; If the variance is less than or equal to the preset variance, the training duration of the next course in the single course group is adjusted based on the difference between the variance and the preset variance.

4. The training effect evaluation method based on learning data analysis according to claim 3 is characterized in that: The process of adjusting the training duration of the next course in the single course group based on the difference between the variance and the preset variance includes: Calculating a difference between the variance and the preset variance; The training duration is reduced based on the obtained difference, and the difference is proportional to the reduction extent of the training duration.

5. The training effect evaluation method based on learning data analysis according to claim 2 is characterized in that: The process for determining why the stated training effectiveness did not meet standards based on the average interaction rate includes: Determining the reason why the training effect does not meet the standard based on a comparison result of the average value of the interaction rate and a pre-stored preset average value; If the average value is greater than or equal to a first preset average value, it is determined that there is a problem with the standard interval for screening out abnormal data in data preprocessing, and the standard interval for screening out abnormal data is adjusted based on the difference between the average value and the preset average value; If the average value is less than the first preset average value and greater than the second preset average value, determining the reason why the training effect does not meet the standard based on the average number of repeated playbacks of the course; If the average value is less than or equal to the second preset average value, the training plan is determined to be unqualified and a notification is issued.

6. The training effect evaluation method based on learning data analysis according to claim 5 is characterized in that: The process of adjusting the standard interval for filtering out abnormal data based on the difference between the mean and the preset mean includes: Calculating the difference between the average value and the preset average value; The standard interval is reduced based on the obtained difference, and the difference is proportional to the reduction of the standard interval.

7. The training effect evaluation method based on learning data analysis according to claim 6 is characterized in that: The process for determining why the training effectiveness was substandard based on the average number of replays of the course included: Comparing the average number of repeated playbacks with a preset number of repeated playbacks; If the average number of repeated playbacks is greater than the preset number of repeated playbacks, the training program is determined to be unqualified, and a notification is issued; If the average number of repeated playbacks is less than or equal to the preset number of repeated playbacks, the number of interactive nodes of a single course is adjusted based on the difference between the average number of repeated playbacks and the preset number of repeated playbacks.

8. The training effect evaluation method based on learning data analysis according to claim 7 is characterized in that: The process of adjusting the number of interaction nodes of a single course based on the difference between the average number of repeated playbacks and the preset number of repeated playbacks includes: Calculating the difference between the average number of repeated playbacks and the preset number of repeated playbacks; The number of the interactive nodes of a single course is reduced based on the obtained difference, and the difference is proportional to the magnitude of the reduction in the number.

9. The training effect evaluation method and system based on learning data analysis according to claim 8, characterized in that: The process of adjusting the training duration based on the number of interacting nodes involves: Calculating the difference between the number of the interactive nodes and a preset number; The training duration is reduced based on the difference, and the difference is proportional to the reduction of the training duration.

10. A training effect evaluation system based on learning data analysis, characterized in that: include: A data collection unit, which is used to collect corresponding data of students during the learning process; a data classification unit, connected to the data collection unit, for classifying the collected data; A data preprocessing unit, connected to the data classification unit, for performing data preprocessing on the classified data; An information generating unit, connected to the data pre-processing unit, for sequentially generating learning information for each student for a single course based on the various types of data after data pre-processing; a calculation unit connected to the information generation unit, configured to calculate an average interaction ratio of the interactions between a plurality of students and the course in the learning information, wherein the average interaction ratio is an average value of the ratio of the number of actual interactions of the plurality of students in the course to the total number of interaction nodes in the course; An analysis unit is connected to the calculation unit and is used to determine whether the training effect meets the standard based on the average interaction ratio, and when it is determined that the training effect does not meet the standard, generate a corresponding processing method based on the determined reason for not meeting the standard, wherein the processing method includes adjusting the standard interval for screening out abnormal data during data preprocessing and adjusting the number of the interaction nodes.

Images