Online education method and online education platform

Abstract

The present invention relates to the field of computer technology, and specifically discloses an online education method and an online education platform, which realizes accurate screening of students' online learning status and accurate evaluation of teaching quality. The online education method includes: the user end logs in and screens to obtain student identity information, and the learning management system LMS at the input end automatically screens and obtains students' real-time learning speed parameters and real-time class completion parameters according to the screening strategy; obtains the class matching status within the target time period according to the real-time learning speed parameters and real-time class completion parameters of the students' current subjects, and determines the concentration coefficient of the students' current subjects; judges the class matching status of the subject within the target time period according to the concentration coefficient of the students' current subjects, judges the teaching quality evaluation and adjusts the screening strategy; obtains the students' real-time learning speed parameter set and real-time class completion parameter set and inputs them into the evaluation model for teaching evaluation analysis.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an online education method and an online education platform. Background Art

[0002] With the development of technology, online education platforms have been able to provide a rich variety of teaching resources and interactive tools, which has greatly changed the traditional education model. Online education methods rely on advanced information technology, especially Internet technology, to provide learners with learning opportunities that transcend time and space. Personalized learning is a major advantage of online education. The platform can provide customized learning paths based on the learner's progress and interests. Interactivity promotes communication between learners and between learners and teachers through real-time discussion and feedback mechanisms.

[0003] Nowadays, the way of information interaction is also changing rapidly. Online learning models are being widely used. Through online education platforms, classroom teaching progress judgment and teaching quality evaluation can be realized, enabling educators to conduct timely analysis and accurate prediction of students or learners' online learning status.

[0004] However, existing online learning platforms only serve online classroom learning. In order to evaluate the quality of online education and teaching, it is necessary to collect a large amount of student learning status data and rely on the final performance of students to evaluate the teaching quality. However, for students with different concentration and learning abilities, the standards for teaching quality evaluation are inconsistent. Therefore, it is difficult to directly improve and analyze the online education methods based on the results of classroom performance teaching evaluation. Summary of the invention

[0005] The purpose of the present invention is to provide an online education method and an online education platform to solve the following technical problems:

[0006] How to achieve accurate screening of students' online learning status and accurate evaluation of teaching quality.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] An online education method, the method comprising the following steps:

[0009] Step 1: The user logs in and filters to obtain the student's identity information. The learning management system LMS at the input end automatically filters and obtains the student's real-time learning speed parameters and real-time class completion parameters according to the filtering strategy;

[0010] Screening strategies include:

[0011] Collect students’ complete class record data and students’ online login log data of the learning platform according to the initial screening frequency;

[0012] Set filtering criteria, including students' completion of standard lessons, login frequency, and online learning speed within the target time period;

[0013] Extract the data sets that meet the screening criteria to identify and judge students’ learning patterns, potential difficulty types, and excellent performance types as evaluation elements;

[0014] Step 2: Obtain the study hour matching status within the target time period according to the real-time learning speed parameter and the real-time class completion parameter of the student's current subject, and determine the concentration coefficient of the student's current subject;

[0015] Step 3: Based on step 2, determine whether the course hour matching status of the subject in the target time period meets the requirements according to the student's current subject concentration coefficient:

[0016] If yes, then proceed to the next step and conduct teaching quality assessment;

[0017] If not, adjust the screening strategy;

[0018] Step 4: Build an evaluation model, filter and obtain the students' real-time learning speed parameter set and real-time class completion parameter set within the target time period on the user side, input them into the evaluation model for teaching evaluation analysis, and output the teaching evaluation results on the output side.

[0019] Preferably, the method of analyzing the study hour matching status in step 2 is:

[0020] By formula Calculate the concentration coefficient ;in, is the total number of students, and ; is the target time period; is the start time of the target time period, is the end time of the target time period, and ≤ < ; For the Real-time learning speed parameters for each student; For the Real-time lesson completion parameters for each student; The first conversion function is matched for the learning hours; Matching the second conversion function for the learning hours; For the The learning ability coefficient of a student.

[0021] Preferably, step three includes:

[0022] The real-time concentration factor With preset threshold To compare:

[0023] like ∈ , then it is judged that the study hour matching status range is normal;

[0024] like < , then it is judged that the scope of the study hour matching status is abnormally small;

[0025] like > , then it is judged that the scope of the study hour matching status is abnormally large.

[0026] Preferably, the evaluation model building process is:

[0027] Collect the historical learning speed parameters and historical class completion parameters of all students at several time points in the target time period, select the class completion parameters of each subject and the learning speed parameters of students of related subjects at the corresponding time points, and generate training samples;

[0028] The model is built with convolutional neural network, and the model is trained through training samples of the class completion parameters of each subject and the related evaluation elements. The evaluation model of the class completion parameters of each subject is obtained and the history teaching quality evaluation parameters of each subject are output.

[0029] Preferably, the method of conducting teaching evaluation analysis in step 4 is:

[0030] According to the historical teaching quality evaluation parameters, the historical value change curve of each subject teaching quality evaluation parameter over time is established ;

[0031] According to the real-time teaching quality evaluation parameters, the real-time value change curve of each subject teaching quality evaluation parameter is established. ;

[0032] For each subject teaching quality assessment parameter, and Established in the same coordinate system, calculation Higher than Area value of the region ;in, The number of teaching subjects.

[0033] Preferably, the teaching evaluation results include:

[0034] The area value The preset threshold corresponding to the teaching quality assessment parameter of this subject To compare:

[0035] like ≥ , then the teaching evaluation result is judged to be unqualified;

[0036] like < , then the teaching evaluation result is judged to be qualified.

[0037] Preferably, the adjustment process of the screening strategy is:

[0038] like < , then increase the screening frequency and extend the length of each screening period;

[0039] like > , then reduce the screening frequency and shorten the length of each screening period;

[0040] Screening frequency after current subject adjustment ;

[0041] The length of the screening period after the current subject is adjusted ;

[0042] in, is the initial screening frequency; is the initial value of the target time period length; is the first preset weight coefficient, is the second preset weight coefficient; if < ,but ;like > ,but .

[0043] An online education platform for implementing an online education method, the platform comprising:

[0044] The user end is used to log in, filter and obtain student identity information;

[0045] An input terminal is used to input a screening strategy to automatically screen and obtain students' real-time learning speed parameters and real-time class completion parameters;

[0046] The data analysis module is used to obtain the class hour matching status within the target time period according to the real-time learning speed parameter and the real-time class hour completion parameter of the student's current subject, and determine the concentration coefficient of the student's current subject; and judge whether the class hour matching status of the subject within the target time period meets the requirements according to the concentration coefficient of the student's current subject: if yes, proceed to the next step to conduct teaching quality evaluation; if not, adjust the screening strategy;

[0047] A model building module is used to build an evaluation model, and to filter and obtain the real-time learning speed parameter set and the real-time class completion parameter set of students within the target time period of the user end, and input them into the evaluation model for teaching evaluation analysis;

[0048] The output end is used to output the teaching evaluation results according to the model construction module.

[0049] Beneficial effects of the present invention:

[0050] (1) By designing a screening strategy, the real-time learning speed parameters and real-time class completion parameters can be obtained. The specific acquisition method is as follows: first, the students' complete class record data and the students' online login log data of the learning platform are collected according to the initial screening frequency; then, the screening conditions are set, and the screening conditions include the students' standard class completion, login frequency, and online learning speed within the target time period; finally, the data set that meets the screening conditions is extracted to identify and judge the students' learning patterns, potential difficulty types, and excellent performance types as evaluation elements. Through the screening strategy, the online student learning information can be further collected, and the collection scope of the online learning status can be determined, so as to facilitate the accurate screening and acquisition of the online learning information of students that meet the evaluation conditions.

[0051] (2) The concentration of all current students is reflected by obtaining the comprehensive result of the difference between the real-time learning speed parameter and the real-time class completion parameter after conversion, that is, the concentration coefficient, reflecting the overall learning effect of students in the current class. This embodiment obtains a relatively objective quantitative standard by calculating the concentration coefficient, helping teachers and students to understand the learning efficiency and input more clearly, which is conducive to timely adjusting the learning plan according to the analysis results and optimizing the learning process.

[0052] (3) By constructing an evaluation model, the real-time learning speed parameter set and real-time class completion parameter set of students screened and obtained during the target time period on the user side are input into the evaluation model for teaching evaluation analysis, and the output end outputs the teaching evaluation results. By constructing an evaluation model, the real-time learning speed parameter set and real-time class completion parameter set of students screened and obtained during the target time period on the user side are subjected to data processing, feature selection, model training and verification, and other links to obtain teaching evaluation results that meet the requirements.

[0053] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0055] Figure 1 A step diagram of an online education method of the present invention;

[0056] Figure 2 This is a structural diagram of an online education platform of the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] However, the existing online learning platform only serves online classroom learning. In order to evaluate the quality of online education and teaching, a large amount of student learning status data needs to be collected, and the teaching quality is evaluated based on the final performance of students. However, for students with different concentration and learning abilities, the standards for teaching quality evaluation are inconsistent. Therefore, it is difficult to accurately express the teaching evaluation results directly based on classroom performance and realize the improvement and analysis process of online education methods.

[0059] The present invention is to solve the above technical problems, please refer to Figure 1 As shown, the present invention is an online education method and an online education platform, which can realize accurate screening of students' online learning status and accurate evaluation of teaching quality.

[0060] Among them, designing an online education method includes the following steps:

[0061] Step 1: The user logs in and filters to obtain the student's identity information. The learning management system LMS at the input end automatically filters and obtains the student's real-time learning speed parameters and real-time class completion parameters according to the filtering strategy;

[0062] Screening strategies include:

[0063] Collect students’ complete class record data and students’ online login log data of the learning platform according to the initial screening frequency;

[0064] Set filtering criteria, including students' completion of standard lessons, login frequency, and online learning speed within the target time period;

[0065] Extract the data sets that meet the screening criteria to identify and judge students’ learning patterns, potential difficulty types, and excellent performance types as evaluation elements;

[0066] Step 2: Obtain the study hour matching status within the target time period according to the real-time learning speed parameter and the real-time class completion parameter of the student's current subject, and determine the concentration coefficient of the student's current subject;

[0067] Step 3: Based on step 2, determine whether the course hour matching status of the subject in the target time period meets the requirements according to the student's current subject concentration coefficient:

[0068] If yes, then proceed to the next step and conduct teaching quality assessment;

[0069] If not, adjust the screening strategy;

[0070] Step 4: Build an evaluation model, filter and obtain the students' real-time learning speed parameter set and real-time class completion parameter set within the target time period on the user side, input them into the evaluation model for teaching evaluation analysis, and output the teaching evaluation results on the output side.

[0071] In the above technical scheme, in this embodiment, a screening strategy is designed to implement range screening of information on students' online learning status, thereby ensuring that data information that meets the teaching quality evaluation standards is obtained and enhancing the evaluation of teachers' online education level. Secondly, the results of data screening that does not meet the standards are adjusted, and the accuracy of students' online learning information is improved by adjusting the screening range and screening frequency, which facilitates the subsequent construction of a teaching evaluation system based on the evaluation model and improves the accuracy of data information processing on the entire online education platform.

[0072] First, in step one, the user end confirms the student identity, number, and class information, and the input end uses the learning management system LMS to automatically filter and obtain the student's real-time learning speed parameters and real-time class completion parameters as input information according to the filtering strategy. The real-time learning speed parameters and real-time class completion parameters of the students are obtained to reflect the student's learning ability, learning speed and other states, and the selection of these parameters is obtained through the filtering strategy. The data set obtained by the set filtering strategy is also used as the main evaluation element for judging the student's learning status.

[0073] In addition, by designing a screening strategy, the real-time learning speed parameters and real-time class completion parameters can be obtained. The specific acquisition method is: first, the students' complete class record data and the students' online login log data of the learning platform are collected according to the initial screening frequency; then, the screening conditions are set, and the screening conditions include the students' standard class completion, login frequency, and online learning speed within the target time period; finally, the data set that meets the screening conditions is extracted to identify and judge the students' learning patterns, potential difficulty types, and excellent performance types as evaluation elements. Through the screening strategy, the information on online student learning can be further collected, and the collection scope of online learning status can be determined, so as to facilitate the accurate screening and acquisition of students' online learning information that meets the evaluation conditions.

[0074] Secondly, in step 2, the student's current subject's real-time learning speed parameter and real-time class completion parameter are used to obtain the class matching status within the target time period, and the student's current subject's concentration coefficient is determined; the real-time learning speed parameter reflects the speed at which students complete learning content in a unit of time, and is an important indicator for evaluating students' learning efficiency. Among them, the real-time class completion parameter refers to the degree to which students complete learning content relative to the established class plan; the class matching status evaluates the degree to which students' actual learning speed matches the expected speed within the target time period, and reflects the specific situation through the degree of matching between the two.

[0075] Specifically, as an implementation of the present invention, the method of analyzing the study hour matching status in step 2 is:

[0076] By formula Calculate the concentration coefficient ;in, is the total number of students, and ; is the target time period; is the start time of the target time period, is the end time of the target time period, and ≤ < ; For the Real-time learning speed parameters for each student; For the Real-time lesson completion parameters for each student; The first conversion function is matched for the learning hours; Matching the second conversion function for the learning hours; For the The learning ability coefficient of a student.

[0077] In the above technical solution, the study hour matching state in this embodiment is obtained by the formula Calculate the concentration coefficient ; The concentration of all current students is reflected by obtaining the comprehensive result of the difference between the real-time learning speed parameter and the real-time class completion parameter after conversion, that is, the concentration coefficient, which reflects the overall learning effect of students in the current class. This embodiment obtains a relatively objective quantitative standard by calculating the concentration coefficient, which helps teachers and students to understand the learning efficiency and input more clearly, and is conducive to timely adjusting the learning plan according to the analysis results to optimize the learning process. At the same time, it also reminds us to pay attention to individual differences among students, set learning goals and rhythms reasonably, and improve students' learning effects.

[0078] It needs further explanation that the first conversion function of the study time matching Second conversion function matching the study hours They are obtained by fitting the test data of students in the normal online learning state of the current subject, and are used to convert the real-time learning speed parameters and the real-time class completion parameters into values ​​that meet the learning hour matching state. Therefore, the real-time learning speed parameters and the real-time class completion parameters are converted into the size of a reasonable expected range through matching comparison; the learning ability coefficient The settings are selected based on the comprehensive status of different students' historical academic performance and learning performance, which will not be elaborated here.

[0079] Next, in step three, based on step two, according to the concentration coefficient of the student's current subject, it is judged whether the class hours matching status of the subject in the target time period meets the requirements: if so, proceed to the next step to conduct teaching quality evaluation; if not, adjust the screening strategy. By setting a standard concentration coefficient threshold based on historical data, teaching experience and specific course objectives, it is judged that if the conditions are met, the concentration is high, indicating that the student's learning efficiency and investment are good in the target period, and the class hours matching status meets the standards. At this point, you can proceed to the next step, that is, to conduct a teaching quality evaluation, analyze whether the teaching content and methods are effective, and whether the student's understanding is in-depth, and provide suggestions for further optimizing teaching; if it is judged that the conditions are not met, the concentration is low, which means that the student's learning efficiency and investment are low in the target period, and the class hours matching status is not good; at this time, it is necessary to adjust the screening strategy by adjusting the screening frequency or adjusting the screening time range to accurately improve the student's concentration recognition range.

[0080] Specifically, as an implementation mode of the present invention, step three includes:

[0081] The real-time concentration factor With preset threshold To compare:

[0082] like ∈ , then it is judged that the study hour matching status range is normal;

[0083] like < , then it is judged that the scope of the study hour matching status is abnormally small;

[0084] like > , then it is judged that the scope of the study hour matching status is abnormally large.

[0085] In the above technical scheme, in this embodiment, the size of the acquired concentration coefficient is compared to determine if it is within the currently set threshold range, then the current study hour matching status range is judged to be normal, otherwise, further judgment is made: if it is less than the minimum value of the threshold interval, then the current matching status range is judged to be too small, and the screening range needs to be expanded; if it is greater than the maximum value of the threshold interval, then the matching range is judged to be too large, and the screening range needs to be narrowed.

[0086] Finally, in step 4, by constructing an evaluation model, the real-time learning speed parameter set and real-time class completion parameter set of students screened and obtained during the target time period on the user side are input into the evaluation model for teaching evaluation analysis, and the output end outputs the teaching evaluation results. By constructing an evaluation model, the real-time learning speed parameter set and real-time class completion parameter set of students screened and obtained during the target time period on the user side are subjected to data processing, feature selection, model training and verification, and other links to obtain teaching evaluation results that meet the requirements.

[0087] Specifically, as an implementation of the present invention, the evaluation model building process is:

[0088] Collect the historical learning speed parameters and historical class completion parameters of all students at several time points in the target time period, select the class completion parameters of each subject and the learning speed parameters of students of related subjects at the corresponding time points, and generate training samples;

[0089] The model is built with convolutional neural network, and the model is trained through training samples of the class completion parameters of each subject and the related evaluation elements. The evaluation model of the class completion parameters of each subject is obtained and the history teaching quality evaluation parameters of each subject are output.

[0090] In the above technical solution, this embodiment uses sufficient sample information to reflect the changes in learning behavior, ensuring that the relationship between input characteristics (learning speed parameters, lesson completion parameters) and target variables (teaching quality evaluation parameters) is clear. Then, the CNN structure is designed, including input layer, convolution layer, pooling layer, fully connected layer and output layer, to ensure that the model can process time series data.

[0091] First, the historical learning speed parameters and history class completion parameters of all students at several time points in the target time period are collected by screening to ensure the diversity and integrity of the data; the class completion parameters of each subject and the learning speed parameters of the students of the related subjects at the corresponding time points are selected to generate training samples. The samples should contain enough information to reflect the changes in learning behavior. Then, the target variable is input to ensure that the relationship between the input characteristics (learning speed parameters, class completion parameters) and the target variable (teaching quality evaluation parameters) is clear. Further, the model is constructed and trained. The model is built with a convolutional neural network, and the generated training samples are used as input for normalization to improve the efficiency of model training; the model is trained through the training samples of the class completion parameters of each subject and the associated evaluation elements, and the weights and bias terms are optimized to minimize the loss function. Different learning rates, iterations, etc. are tried to find the best model configuration. Finally, the evaluation model of the class completion parameters of each subject is obtained and the historical teaching quality evaluation parameters of each subject are output. Based on the evaluation parameters, the learning dynamics are captured and the teaching quality is judged. By regularly collecting new data, the model is continuously optimized to adapt to changes in the teaching environment.

[0092] Furthermore, as an implementation mode of the present invention, the teaching evaluation analysis in step 4 is performed as follows:

[0093] According to the historical teaching quality evaluation parameters, the historical value change curve of each subject teaching quality evaluation parameter over time is established ;

[0094] According to the real-time teaching quality evaluation parameters, the real-time value change curve of each subject teaching quality evaluation parameter is established. ;

[0095] For each subject teaching quality assessment parameter, and Established in the same coordinate system, calculation Higher than Area value of the region ;in, The number of teaching subjects.

[0096] In the above technical solution, the specific method of teaching evaluation analysis in this embodiment is to first obtain the dynamic change curve of the historical teaching quality evaluation parameter. Then, according to the real-time teaching quality evaluation parameters, the real-time value change curve of each subject teaching quality evaluation parameter over time is established. Finally, the changes in the teaching quality evaluation parameters of each subject were analyzed. and Established in the same coordinate system, calculation Higher than Area value of the region ;in, The number of teaching subjects.

[0097] As an implementation mode of the present invention, the teaching evaluation results based on the teaching evaluation method analysis include:

[0098] The area value The preset threshold corresponding to the teaching quality assessment parameter of this subject To compare:

[0099] like ≥ , then the teaching evaluation result is judged to be unqualified;

[0100] like < , then the teaching evaluation result is judged to be qualified.

[0101] In the above technical solution, the method of obtaining the teaching evaluation result in this embodiment is to compare the area value With preset threshold If the size ≥ , then the teaching evaluation result is judged to be unqualified and the teaching model needs to be improved and adjusted. < , the teaching evaluation result is judged to be qualified and the current teaching mode continues.

[0102] As an implementation mode of the present invention, the adjustment process of the screening strategy is:

[0103] like < , then increase the screening frequency and extend the length of each screening period;

[0104] like > , then reduce the screening frequency and shorten the length of each screening period;

[0105] Screening frequency after current subject adjustment ;

[0106] The length of the screening period after the current subject is adjusted ;

[0107] in, is the initial screening frequency; is the initial value of the target time period length; is the first preset weight coefficient, is the second preset weight coefficient; if < ,but ;like > ,but .

[0108] In the above technical solution, the adjustment process of the screening strategy in this embodiment includes further analysis of the situation that does not meet the screening interval. < , it is necessary to increase the screening frequency, ensure the collection of more online education information, and extend the length of each screening period.

[0109] And, the first preset weight coefficient and the second preset weight coefficient The ranges are obtained by fitting and calculating based on historical experience data and will not be elaborated here.

[0110] An online education platform for implementing an online education method, the platform comprising:

[0111] The user end is used to log in, filter and obtain student identity information;

[0112] An input terminal is used to input a screening strategy to automatically screen and obtain students' real-time learning speed parameters and real-time class completion parameters;

[0113] The data analysis module is used to obtain the class hour matching status within the target time period according to the real-time learning speed parameter and the real-time class hour completion parameter of the student's current subject, and determine the concentration coefficient of the student's current subject; and judge whether the class hour matching status of the subject within the target time period meets the requirements according to the concentration coefficient of the student's current subject: if yes, proceed to the next step to conduct teaching quality evaluation; if not, adjust the screening strategy;

[0114] A model building module is used to build an evaluation model, and to filter and obtain the real-time learning speed parameter set and the real-time class completion parameter set of students within the target time period of the user end, and input them into the evaluation model for teaching evaluation analysis;

[0115] The output end is used to output the teaching evaluation results according to the model construction module.

[0116] In the above technical scheme, the present invention also designs an online education platform, which integrates user login and identity confirmation, real-time learning parameter collection, data analysis and concentration evaluation; by analyzing the learning speed and class completion, dynamically adjusting the strategy, and constructing an evaluation model; finally outputting the teaching effect evaluation to optimize the learning experience.

[0117] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0118] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined in this application, they shall all fall within the protection scope of the present invention.

Claims

1. An online teaching method, characterized in that: The method comprises the following steps: Step 1: The user logs in and filters to obtain the student's identity information. The learning management system LMS at the input end automatically filters and obtains the student's real-time learning speed parameters and real-time class completion parameters according to the filtering strategy; The screening strategy includes: Collect students’ complete class record data and students’ online login log data of the learning platform according to the initial screening frequency; Setting screening conditions, including the completion rate of standard lessons, login frequency, and online learning speed of students within the target time period; Extract the data sets that meet the screening criteria to identify and judge students’ learning patterns, potential difficulty types, and excellent performance types as evaluation elements; Step 2: Obtain the study hour matching status within the target time period according to the real-time learning speed parameter and the real-time class completion parameter of the student's current subject, and determine the concentration coefficient of the student's current subject; Step 3: Based on step 2, determine whether the course hour matching status of the subject in the target time period meets the requirements according to the student's current subject concentration coefficient: If yes, then proceed to the next step and conduct teaching quality assessment; If not, adjust the screening strategy; Step 4: Build an evaluation model, filter and obtain the students' real-time learning speed parameter set and real-time class completion parameter set within the target time period on the user side, input them into the evaluation model for teaching evaluation analysis, and output the teaching evaluation results on the output side.

2. An online education method according to claim 1, characterized in that: The method of analyzing the study hour matching status in step 2 is: By formula Calculate the concentration coefficient ;in, is the total number of students, and ; is the target time period; is the start time of the target time period, is the end time of the target time period, and ≤ < ; For the Real-time learning speed parameters for each student; For the Real-time lesson completion parameters for each student; The first conversion function is matched for the learning hours; Matching the second conversion function for the learning hours; For the The learning ability coefficient of a student.

3. An online education method according to claim 2, characterized in that: The step three includes: The real-time concentration factor With preset threshold To compare: like , then it is judged that the study hour matching status range is normal; like < , then it is judged that the scope of the study hour matching status is abnormally small; like > , then it is judged that the scope of the study hour matching status is abnormally large.

4. An online education method according to claim 1, characterized in that: The evaluation model construction process is as follows: Collect the historical learning speed parameters and historical class completion parameters of all students at several time points in the target time period, select the class completion parameters of each subject and the learning speed parameters of students of related subjects at the corresponding time points, and generate training samples; The model is built with convolutional neural network, and the model is trained through training samples of the class completion parameters of each subject and the related evaluation elements. The evaluation model of the class completion parameters of each subject is obtained and the history teaching quality evaluation parameters of each subject are output.

5. An online education method according to claim 4, characterized in that: The method of conducting teaching evaluation analysis in step 4 is as follows: According to the historical teaching quality evaluation parameters, the historical value change curve of each subject teaching quality evaluation parameter over time is established ; According to the real-time teaching quality evaluation parameters, the real-time value change curve of each subject teaching quality evaluation parameter is established. ; For each subject teaching quality assessment parameter, and Established in the same coordinate system, calculation Higher than Area value of the region ;in, The number of teaching subjects.

6. An online education method according to claim 5, characterized in that: The teaching evaluation results include: The area value The preset threshold value corresponding to the teaching quality evaluation parameter of this subject To compare: like ≥ , then the teaching evaluation result is judged to be unqualified; like < , then the teaching evaluation result is judged to be qualified.

7. An online education method according to claim 3, characterized in that: The adjustment process of the screening strategy is: like < , then increase the screening frequency and extend the length of each screening period; like > , then reduce the screening frequency and shorten the length of each screening period; Screening frequency after current subject adjustment ; The length of the screening period after the current subject is adjusted ; in, is the initial screening frequency; is the initial value of the target time period length; is the first preset weight coefficient, is the second preset weight coefficient; if < ,but ;like > ,but .

8. An online education platform, used to implement the online education method according to any one of claims 1 to 7, characterized in that: The platform includes: The user end is used to log in, filter and obtain student identity information; An input terminal is used to input a screening strategy to automatically screen and obtain students' real-time learning speed parameters and real-time class completion parameters; The data analysis module is used to obtain the class hour matching status within the target time period according to the real-time learning speed parameter and the real-time class hour completion parameter of the student's current subject, and determine the concentration coefficient of the student's current subject; and judge whether the class hour matching status of the subject within the target time period meets the requirements according to the concentration coefficient of the student's current subject: if yes, proceed to the next step to conduct teaching quality evaluation; if not, adjust the screening strategy; A model building module is used to build an evaluation model, and to filter and obtain the real-time learning speed parameter set and the real-time class completion parameter set of the students within the target time period of the user end, and input them into the evaluation model for teaching evaluation analysis; The output end is used to output the teaching evaluation results according to the model construction module.

Images