Network simulation data teaching system based on cloud computing teaching

Abstract

The invention discloses a network simulation data teaching system based on cloud computing teaching, and relates to the technical field of network teaching, and the system comprises a parameter collection module, a parameter analysis module, a controller, an online monitoring module and an auxiliary adjustment module. The parameter acquisition module is used for acquiring potential teaching associated data of the course on line after successful authentication, and transmitting the acquired potential teaching associated data to the parameter analysis module for analysis, so that the parameter analysis module analyzes and obtains the optimal playing speed of a teaching video in the course; the controller is used for driving the live broadcast teaching module to synchronize live broadcast video data of the teacher end to the student end according to the playing speed calculation value Vt; students can understand and memorize conveniently, and the teaching effect is improved; in the course teaching process, the auxiliary adjustment module is used for obtaining learning state labels of all students in real time and carrying out playing compensation index analysis so as to remind an administrator to accelerate or decelerate the playing speed of the current teaching video, and the teaching effect is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of network teaching, in particular to a network simulation data teaching system for cloud computing teaching. BACKGROUND

[0002] Online learning, also known as network education, is a network learning method, that is, students log in to an online learning platform through a PC or terminal and learn through the network.

[0003] The most popular on-demand and video recording teaching in online teaching is that teachers record videos in advance and upload them, and students download or watch the videos online for learning, which cannot guarantee that all students learn on time. Meanwhile, teachers cannot choose the appropriate course playing speed according to the number of students and the learning ability of students, which is not convenient for students to remember, thereby reducing the teaching effect. Based on the above shortcomings, the present application provides a network simulation data teaching system for cloud computing teaching. SUMMARY

[0004] The present application aims to at least solve one of the technical problems existing in the prior art. To this end, the present application provides a network simulation data teaching system for cloud computing teaching.

[0005] To achieve the above-mentioned purpose, the network simulation data teaching system for cloud computing teaching according to the first aspect of the present application comprises an authentication module, a parameter acquisition module, a course training module, a model creation module, a controller, a learning ability evaluation module, an online monitoring module and an auxiliary adjustment module.

[0006] The teacher end and the student end are connected with the authentication module, and the authentication module is used for verifying the login request of the teacher end and the student end; the verification method is face recognition or fingerprint recognition.

[0007] The parameter acquisition module is used for collecting potential teaching correlation data of the course online after authentication succeeds, and transmitting the collected potential teaching correlation data to the parameter analysis module for analysis; the potential teaching correlation data includes the number of students and the subject learning ability coefficient XL of each student.

[0008] The model creation module is used for obtaining the playing speed of the teaching video of all courses in the teaching system, and analyzing and mining the potential teaching correlation data of the corresponding course as the original sample set; based on the original sample set, the neural network model is trained to obtain the trained playing speed reference model.

[0009] The parameter analysis module is configured to integrate the potential teaching correlation data of the course into input data of the playback speed reference model, and then output a corresponding playback speed calculation value and mark it as Vt.

[0010] The controller is configured to drive the live teaching module to synchronize the live video data of the teacher end to the student end according to the playback speed calculation value Vt.

[0011] During the course teaching process, the online monitoring module is configured to control the camera and the audio acquisition unit of the student end to collect feature data in the student learning process through the network, and input the feature data into the learning state evaluation model to obtain a learning state label.

[0012] The auxiliary adjustment module is connected with the online monitoring module, and is configured to obtain learning state labels of all students in real time and analyze a playback compensation index BF; if the playback compensation index BF > B2, an acceleration signal is generated to the live teaching module to remind the administrator to accelerate the playback speed of the current teaching video.

[0013] If the playback compensation index BF < B1, a deceleration signal is generated to the live teaching module to remind the administrator to decelerate the playback speed of the current teaching video; B1 and B2 are both preset compensation thresholds, and B1 < B2.

[0014] Further, the specific analysis steps of the auxiliary adjustment module are as follows:

[0015] The learning state labels of all students are obtained in real time, and the proportions of the focused label, the interactive label, the resistant label and the confused label are counted and marked as Lb1, Lb2, Lb3 and Lb4 in sequence.

[0016] The learning attraction value Xb is calculated by the formula Xb = g1 × (Lb1 × 2 + Lb2) / (Lb3 + Lb4 × 0.5), wherein g1 is a preset coefficient factor.

[0017] The number of students Rb is counted, and the playback speed of the current teaching video is marked as Vb; the playback compensation index BF is calculated by the formula BF = (Xb × g2) / (Rb × g3 + Vb × g4), wherein g2, g3 and g4 are all preset coefficient factors.

[0018] Further, the course training module is configured to enable students to conduct simulated question training after the course, and record course training information; the course training information includes training subjects and corresponding training scores.

[0019] Further, the learning ability evaluation module is connected with the course training module, and is configured to obtain the course training information of the students and evaluate the subject learning ability coefficient XL, and the specific evaluation steps are as follows:

[0020] For the same training subject, the training results of the student in a preset time period are obtained and marked as Ri, i = 1, …, n; wherein i represents the i th training result;

[0021] Ri is arranged in descending order; the maximum value of Ri is obtained and marked as Rmax, and the minimum value of Ri is obtained and marked as Rmin; the difference between the maximum value Rmax and the minimum value Rmin is divided by the minimum value Rmin to obtain the difference ratio Cb, that is, Cb = (Rmax-Rmin) / Rmin;

[0022] The average result of the student is obtained according to the average value calculation formula and marked as RA; Ri is compared with R(i-1), when Ri>R(i-1), it indicates that the student has made progress in learning;

[0023] The proportion of the number of times that the student has made progress is Zb; the subject learning ability coefficient XL of the student is calculated by the formula XL = f x (Zb x a1 + RA x a2) / (Cb x a3), wherein a1, a2 and a3 are all preset coefficient factors, and f is a preset balance coefficient; the learning ability evaluation module is used to timestamp the subject learning ability coefficient XL of the student and store it to the controller.

[0024] Further, the specific training steps of the model creation module are:

[0025] The original sample set corresponding to the course is obtained, and data cleaning is performed on the original sample set; the data cleaning includes: filling or discarding the null value; and removing duplicate data;

[0026] The cleaned original sample set is split into a training set, a validation set and a test set according to a preset proportion;

[0027] An LSTM neural network model is established; wherein the number of LSTM input nodes of the long short-term memory neural network is specified according to the number of input variables; the number of hidden layer nodes and the number of output nodes representing the playing speed of the teaching video are set;

[0028] The training set, the validation set and the test set are input into the LSTM neural network model as historical characteristic values to perform model training, and the model is evaluated through a loss function to obtain an optimal playing speed reference model that minimizes the overall error of the training samples.

[0029] Further, the feature data includes sound information and face image information; the learning state evaluation model is constructed by an RBF neural network or a deep convolutional neural network.

[0030] Further, the teacher end is used for confirming / modifying the received learning state label and feeding back to the controller; the controller receives the learning state label and sends corresponding learning reminding information to the student end according to the learning state label, reminding the student to concentrate on learning; wherein the learning state label includes the concentration label, the interaction label, the resistance label and the confusion label.

[0031] Compared with the prior art, the beneficial effects of the present application are:

[0032] 1、 the parameter acquisition module in the application is used for collecting potential teaching correlation data of the course online after authentication succeeds, the potential teaching correlation data includes the number of students and the subject learning coefficient XL of each student, and the collected potential teaching correlation data is transmitted to the parameter analysis module for analysis, so that the parameter analysis module can analyze and obtain the best playing speed of the teaching video in the course; the parameter analysis module is used for integrating the potential teaching correlation data of the course into input data of a playing speed reference model, then outputting a corresponding playing speed calculation value and marking it as Vt, so as to facilitate the students to understand and remember, and improve the teaching effect;

[0033] 2、 in the course teaching process, the online monitoring module is used for collecting feature data in the student learning process through the network control of the camera and the audio acquisition unit of the student end; and the feature data is input into a learning state evaluation model to obtain a learning state label; the auxiliary adjustment module is used for acquiring the learning state label of all students in real time and performing BF analysis on a playing compensation index, if the playing compensation index BF is greater than B2, an acceleration signal is generated to the live teaching module to remind the administrator to accelerate the playing speed of the current teaching video; if the playing compensation index BF is less than B1, a deceleration signal is generated to the live teaching module to remind the administrator to decelerate the playing speed of the current teaching video, so as to facilitate the students to understand and remember, and improve the teaching effect. BRIEF DESCRIPTION OF DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0035] Figure 1 The system block diagram of the network simulation data teaching system for cloud computing teaching based on the present application. DETAILED DESCRIPTION

[0036] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0037] like Figure 1 As shown, the cloud computing-based network simulation data teaching system includes an authentication module, a parameter acquisition module, a parameter analysis module, a controller, a live teaching module, a course training module, a model creation module, an academic ability assessment module, an online monitoring module, and an auxiliary adjustment module.

[0038] The teacher's and student's ends are connected to the authentication module, which is used to verify the login requests of the teacher's and student's ends; the verification method is facial recognition or fingerprint recognition.

[0039] The parameter acquisition module is used to collect potential teaching-related data for this course online after successful authentication. The potential teaching-related data includes the number of students and the subject academic ability coefficient XL for each student. The collected potential teaching-related data is then transmitted to the parameter analysis module for analysis, so that the parameter analysis module can determine the optimal playback speed of the teaching videos in this course.

[0040] The parameter analysis module is used to perform a comprehensive analysis by combining the potential teaching-related data of this course with the playback speed reference model. The specific analysis steps are as follows:

[0041] After the parameter analysis module receives the potential teaching-related data for this course, it integrates the potential teaching-related data into the input data for the playback speed reference model; the input data is then input into the playback speed reference model, and the corresponding playback speed calculation value is output and marked as Vt.

[0042] The parameter analysis module is used to transmit the calculated playback speed value Vt to the controller; the controller is used to drive the live teaching module to synchronize the live video data from the teacher's end to the student's end at the playback speed of Vt.

[0043] The course training module is used by students to practice mock exams after class and records course training information, including the training subject and the corresponding training score.

[0044] In a cloud computing-based network simulation data teaching system, the model creation module is used to obtain the playback speed of the teaching videos of all courses in the teaching system and analyze and mine the potential teaching correlation data of all courses as the original sample set.

[0045] The neural network model is trained based on the original sample set to obtain a trained playback speed reference model; the potential teaching correlation data is represented by the number of students when the teaching video is played at this playback speed and the subject academic ability coefficient XL of each student.

[0046] It is worth noting that the specific training steps for the model creation module are as follows:

[0047] Obtain the original sample set for the corresponding course and perform data cleaning on the original sample set; data cleaning includes: filling or discarding null values; and removing duplicate data.

[0048] The cleaned original sample set is split into training set, validation set, and test set according to a preset ratio;

[0049] Establish an LSTM neural network model; wherein, the number of input nodes of the Long Short-Term Memory (LSTM) neural network is specified according to the number of input variables; set an appropriate number of hidden layer nodes and the number of output nodes representing the playback speed of the teaching video;

[0050] The training set, validation set, and test set are used as historical feature values ​​to input into the LSTM neural network model for model training. The model is evaluated through a loss function to obtain the optimal playback speed reference model that minimizes the overall error of the training samples.

[0051] This application discloses a cloud computing-based network simulation data teaching system, in which an academic ability assessment module is connected to a course training module. This module is used to obtain students' course training information and perform subject academic ability coefficient (XL) assessments. The specific assessment steps are as follows:

[0052] For the same training subject, obtain the students' training scores within a preset time period and label them as Ri, i = 1, ..., n; where i represents the i-th training score.

[0053] Sort Ri in descending order; find the maximum value of Ri and mark it as Rmax, find the minimum value of Ri and mark it as Rmin; divide the difference between the maximum value Rmax and the minimum value Rmin by the minimum value Rmin to get the difference ratio Cb, that is, Cb = (Rmax - Rmin) / Rmin;

[0054] The average score of students is calculated using the formula and labeled as RA. Ri is compared with R(i-1). When Ri > R(i-1), it indicates that the student has made progress in learning.

[0055] The percentage of times a student makes progress is Zb. The student's subject academic ability coefficient XL is calculated using the formula XL=f×(Zb×a1+RA×a2) / (Cb×a3), where a1, a2, and a3 are preset coefficient factors, and f is a preset equilibrium coefficient. The academic ability assessment module is used to timestamp the student's subject academic ability coefficient XL and store it in the controller.

[0056] A further technical solution involves the following: During the course instruction process, the online monitoring module is used to control the student's camera and audio acquisition unit via the network to collect feature data of the student's learning process; and inputs the feature data into the learning status assessment model to obtain learning status labels; wherein, the feature data includes sound information and facial image information; the learning status assessment model is constructed using an RBF neural network or a deep convolutional neural network;

[0057] In this embodiment, during the learning process, when the learning status label is focused or interactive, it indicates no abnormality; when the learning status label is resistant or confused, it indicates an abnormality, and the student needs to be reminded to adjust the learning status and improve learning efficiency.

[0058] The teacher's end is used to confirm / modify the received learning status tags and send feedback to the controller; after receiving the learning status tags, the controller sends corresponding learning reminder information to the student's end to remind the student to concentrate on learning; the learning status tags include focus tags, interaction tags, resistance tags, and confusion tags;

[0059] The auxiliary adjustment module is connected to the tag analysis module to obtain the learning status tags of all students in real time and perform playback compensation index (BF) analysis. The specific analysis steps are as follows:

[0060] The learning status tags of all students are obtained in real time, and the percentages of the focus tag, interaction tag, resistance tag and confusion tag are statistically obtained and labeled as Lb1, Lb2, Lb3 and Lb4 respectively.

[0061] The learning attraction value Xb is calculated using the formula Xb=g1×(Lb1×2+Lb2) / (Lb3+Lb4×0.5), where g1 is a preset coefficient factor;

[0062] Let the number of students be Rb, and the playback speed of the current teaching video be Vb. The playback compensation index BF is calculated using the formula BF=(Xb×g2) / (Rb×g3+Vb×g4), where g2, g3, and g4 are preset coefficient factors.

[0063] The playback compensation index BF is compared with the preset compensation threshold; the preset compensation threshold includes B1 and B2; and B1 < B2; if the playback compensation index BF > B2, an acceleration signal is generated to the live teaching module to remind the administrator to accelerate the playback speed of the current teaching video.

[0064] If the playback compensation index BF < B1, a deceleration signal is generated and sent to the live teaching module to remind the administrator to slow down the playback speed of the teaching video; this facilitates students' understanding and memorization, and improves teaching effectiveness.

[0065] The above formulas are all numerical calculations after removing dimensions. The formulas are obtained by software simulation based on a large amount of data and are closest to the real situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained by simulation based on a large amount of data.

[0066] Working principle of the invention:

[0067] Based on a cloud computing-based network simulation data teaching system, during operation, the authentication module verifies login requests from both teachers and students. The parameter acquisition module, upon successful authentication, collects potential teaching-related data online, including the number of students and each student's subject-specific academic ability coefficient (XL). This collected data is then transmitted to the parameter analysis module for analysis, which determines the optimal playback speed for the course's teaching videos. The parameter analysis module integrates this data into the input data for a playback speed reference model, outputting a calculated playback speed value labeled Vt. This facilitates student comprehension and memorization, improving teaching effectiveness.

[0068] During the course teaching process, the online monitoring module is used to control the camera and audio acquisition unit on the student's end through the network to collect characteristic data of the student's learning process; and input the characteristic data into the learning status assessment model to obtain learning status labels; the teacher's end is used to confirm / modify the received learning status labels and feed back to the controller; after receiving the learning status labels, the controller sends corresponding learning reminder information to the student's end according to the learning status labels to remind the student to concentrate on learning;

[0069] The auxiliary adjustment module is used to acquire the learning status tags of all students in real time and perform playback compensation index (BF) analysis. If the playback compensation index BF > B2, an acceleration signal is generated to the live teaching module to remind the administrator to speed up the playback of the current teaching video; if the playback compensation index BF < B1, a deceleration signal is generated to the live teaching module to remind the administrator to slow down the playback of the current teaching video. This facilitates students' understanding and memorization, and improves teaching effectiveness.

[0070] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0071] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A cloud computing-based network simulation data teaching system, characterized in that: It includes an authentication module, a parameter acquisition module, a course training module, a model creation module, a controller, an academic ability assessment module, an online monitoring module, and an auxiliary adjustment module; The teacher's and student's ends are connected to the authentication module, which is used to verify the login requests of the teacher's and student's ends; the verification method is facial recognition or fingerprint recognition. The parameter acquisition module is used to collect potential teaching-related data of this course online after successful authentication, and transmit the collected potential teaching-related data to the parameter analysis module for analysis; the potential teaching-related data includes the number of students and the subject academic ability coefficient XL of each student; The model creation module is used to obtain the playback speed of the teaching videos of all courses in the teaching system, and analyze and mine the potential teaching correlation data of the corresponding courses as the original sample set; the neural network model is trained based on the original sample set to obtain the trained playback speed reference model. The parameter analysis module is used to integrate the potential teaching-related data of this course into the input data of the playback speed reference model, and then output the corresponding playback speed calculation value and mark it as Vt; The controller is used to calculate the value Vt based on the playback speed to drive the live teaching module to synchronize the live video data from the teacher's end to the student's end; During the course instruction process, the online monitoring module is used to control the student's camera and audio acquisition unit through the network to collect characteristic data of the student's learning process; and input the characteristic data into the learning status assessment model to obtain learning status labels; The auxiliary adjustment module is connected to the online monitoring module; it is used to obtain the learning status tags of all students in real time and perform playback compensation index BF analysis; if the playback compensation index BF > B2, an acceleration signal is generated to the live teaching module to remind the administrator to accelerate the playback speed of the current teaching video. If the playback compensation index BF < B1, a deceleration signal is generated to the live teaching module to remind the administrator to slow down the playback speed of the current teaching video. B1 and B2 are both preset compensation thresholds, and B1 < B2.

2. The cloud computing-based network simulation data teaching system for educational purposes according to claim 1, characterized in that, The specific analysis steps for the auxiliary adjustment module are as follows: The learning status tags of all students are obtained in real time, and the percentages of the focus tag, interaction tag, resistance tag and confusion tag are statistically obtained and labeled as Lb1, Lb2, Lb3 and Lb4 respectively. The learning attraction value Xb is calculated using the formula Xb=g1×(Lb1×2+Lb2) / (Lb3+Lb4×0.5), where g1 is a preset coefficient factor; The number of students is counted as Rb; the playback speed of the current teaching video is marked as Vb; The playback compensation index BF is calculated using the formula BF=(Xb×g2) / (Rb×g3+Vb×g4), where g2, g3, and g4 are preset coefficient factors.

3. The cloud computing-based network simulation data teaching system for educational purposes according to claim 1, characterized in that, The course training module is used for students to conduct mock test training after class and to record course training information; the course training information includes training subjects and corresponding training scores.

4. The cloud computing-based network simulation data teaching system for educational purposes according to claim 3, characterized in that, The academic ability assessment module is connected to the course training module and is used to obtain students' course training information and conduct subject academic ability coefficient (XL) assessment. The specific assessment steps are as follows: For the same training subject, obtain the students' training scores within a preset time period and label them as Ri, i = 1, ..., n; Where i represents the i-th training score; Sort Ri in descending order; find the maximum value of Ri and mark it as Rmax, find the minimum value of Ri and mark it as Rmin; divide the difference between the maximum value Rmax and the minimum value Rmin by the minimum value Rmin to get the difference ratio Cb, that is, Cb = (Rmax - Rmin) / Rmin; The average score of students is calculated using the formula and labeled as RA. Ri is compared with R(i-1). When Ri > R(i-1), it indicates that the student has made progress in learning. The percentage of times a student makes progress is denoted as Zb. The student's subject academic ability coefficient XL is calculated using the formula XL = f × (Zb × a1 + RA × a2) / (Cb × a3), where a1, a2, and a3 are preset coefficient factors, and f is a preset equilibrium coefficient. The academic ability assessment module is used to timestamp the student's subject academic ability coefficient XL and store it in the controller.

5. The cloud computing-based network simulation data teaching system for educational purposes according to claim 1, characterized in that, The specific training steps of the model creation module are as follows: Obtain the original sample set for the corresponding course and perform data cleaning on the original sample set; data cleaning includes: filling or discarding null values; and removing duplicate data. The cleaned original sample set is split into training set, validation set, and test set according to a preset ratio; Establish an LSTM neural network model; wherein, the number of input nodes of the Long Short-Term Memory (LSTM) neural network is specified according to the number of input variables; set an appropriate number of hidden layer nodes and the number of output nodes representing the playback speed of the teaching video; The training set, validation set, and test set are used as historical feature values ​​to input into the LSTM neural network model for model training. The model is then evaluated using a loss function to obtain the optimal playback speed reference model that minimizes the overall error of the training samples.

6. The cloud computing-based network simulation data teaching system for educational purposes according to claim 1, characterized in that, The feature data includes audio information and facial image information; the learning state evaluation model is constructed using an RBF neural network or a deep convolutional neural network.

7. The cloud computing-based network simulation data teaching system for educational purposes according to claim 1, characterized in that, The teacher's end is used to confirm / modify the received learning status tags and send feedback to the controller; after receiving the learning status tags, the controller sends corresponding learning reminder information to the student's end to remind the student to concentrate on learning. The learning status tags include focused tags, interactive tags, resistant tags, and confused tags.

Images