An English teaching interactive control system and control method thereof

Abstract

The present invention relates to the field of teaching technology, and in particular to an English teaching interactive control system and a control method thereof. The method comprises: establishing a communication connection between a server and a plurality of VR head displays; sending a group of identical scenario dialogue videos to each VR head display respectively, and receiving a response video fed back by each VR head display; classifying the response video fed back by each VR head display based on a pre-trained neural network model to obtain a plurality of classification groups; determining the weak items of each classification group, matching corresponding scenario teaching videos according to the weak items of each classification group, and sending the corresponding scenario teaching videos to each classification group; the present invention can carry out English teaching in a targeted manner.

Description

Technical Field

[0001] The present invention relates to the field of teaching technology, and in particular to an English teaching interactive control system and a control method thereof. Background Art

[0002] Compared with the teaching of other subjects, due to the lack of a native language environment, English teaching needs to continuously improve students' practical application ability through oral expression and situational dialogues. However, the existing English teaching system is single in form and lacks flexibility. Most of them use video or audio to teach, especially when conducting online teaching, which cannot form targeted interactions between teachers and students.

[0003] Therefore, how to develop an interactive English teaching solution that is suitable for distance learning and targeted is an urgent problem to be solved. Summary of the invention

[0004] The purpose of the present invention is to provide an English teaching interactive control system and a control method thereof, so as to solve one or more technical problems existing in the prior art and at least provide a beneficial choice or create conditions.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] An English teaching interactive control method, the method comprising the following steps:

[0007] Step S100: establishing a communication connection between the server and several VR head displays;

[0008] Step S200: sending a set of identical scenario dialogue videos to each VR head display, and receiving a response video fed back by each VR head display;

[0009] Step S300: classifying the response video fed back by each VR head display based on the pre-trained neural network model to obtain multiple classification groups; wherein each classification group corresponds to at least one VR head display;

[0010] Step S400: determine the weak items of each classification group, match the corresponding scenario teaching video according to the weak items of each classification group, and send the corresponding scenario teaching video to each classification group.

[0011] Further, in step S300, the response video fed back by each VR head display is classified based on the pre-trained neural network model to obtain multiple classification groups, including:

[0012] Step S310: Obtain the response video feedback from each VR head display;

[0013] Step S320: Recognize the response video fed back by each VR head display based on the pre-trained neural network model to obtain comprehensive evaluation information corresponding to each VR head display;

[0014] Step S330: cluster the comprehensive evaluation information corresponding to each VR head display to obtain multiple classification groups.

[0015] Further, in step S320, the neural network model obtained based on the pre-training recognizes the response video fed back by each VR head display to obtain the comprehensive evaluation information corresponding to each VR head display, including:

[0016] Step S321: Perform voice recognition on the response video fed back by the VR head display to obtain text response data; input the text response data into a pre-trained text classification model to obtain a first indicator; wherein the first indicator is one of the following: no response, inaccurate response, and accurate response;

[0017] Step S322, performing voice separation on the response video fed back by the VR head display to obtain voice response data; inputting the voice response data into a pre-trained voice classification model to obtain a second indicator; wherein the second indicator is one of the following: inaccurate pronunciation, incoherent pronunciation, and accurate pronunciation;

[0018] Step S323, performing image separation on the response video fed back by the VR head display to obtain image response data; inputting the image response data into a pre-trained image classification model to obtain a third indicator; wherein the third indicator is one of the following: stillness, slight movement, and expression conforming to the setting;

[0019] Step S324: Form a set of ternary data with the first indicator, the second indicator and the third indicator as comprehensive evaluation information corresponding to the VR head display.

[0020] Furthermore, the method further comprises:

[0021] Constructing a first neural network model, and training the first neural network model with multiple sets of first training data to obtain a text classification model; wherein each set of training data in the multiple sets of first training data includes: text response data, at least one text answer and identification information of text differences, wherein the text difference is difference information between the text response data and each text answer;

[0022] Constructing a second neural network model, and training the second neural network model with multiple sets of second training data to obtain a speech classification model; wherein each set of training data in the multiple sets of second training data includes: speech response data, at least one speech answer and identification information of speech differences, wherein the speech differences are difference information between the speech response data and each speech answer;

[0023] A third neural network model is constructed, and multiple sets of third training data are used to train the third neural network model to obtain an image classification model; wherein each set of training data in the multiple sets of third training data includes: image response data, at least one image answer and identification information of image differences, and the image differences are difference information between the image response data and each image answer.

[0024] Further, in step S330, the comprehensive evaluation information corresponding to each VR head display is clustered to obtain multiple classification groups, including:

[0025] VR head displays corresponding to the same ternary data are divided into a group to obtain multiple classification groups.

[0026] Further, in step S400, determining the weak items of each classification group, matching the corresponding scenario teaching video according to the weak items of each classification group, and sending the corresponding scenario teaching video to each classification group includes:

[0027] Determine the ternary data corresponding to each classification group;

[0028] Determine the first indicator, the second indicator and the third indicator corresponding to the ternary data. If the first indicator is no response or inaccurate response, semantic cultivation is regarded as a weak item; if the second indicator is inaccurate pronunciation or incoherent pronunciation, pronunciation cultivation is regarded as a weak item; if the third indicator is stillness or slight movement, expression cultivation is regarded as a weak item.

[0029] A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of any one of the above-mentioned English teaching interactive control methods are implemented.

[0030] An English teaching interactive control system, the system comprising:

[0031] at least one processor;

[0032] at least one memory for storing at least one program;

[0033] When the at least one program is executed by the at least one processor, the at least one processor implements any one of the above-mentioned English teaching interactive control methods.

[0034] The beneficial effects of the present invention are as follows: the present invention discloses an interactive control system for English teaching and a control method thereof. After establishing a communication connection between a server and several VR head displays, the present invention sends a group of identical scenario dialogue videos to each VR head display respectively, and receives a response video fed back by each VR head display, thereby classifying the response video fed back by each VR head display based on a pre-trained neural network model to obtain multiple classification groups; then determining the weak items of each classification group, matching the corresponding scenario teaching video according to the weak items of each classification group, and sending the corresponding scenario teaching video to each classification group. The present invention can carry out targeted English teaching by combining VR head display teaching with English teaching and classifying according to the response video. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0036] Figure 1 is a flow chart of an interactive control method for English teaching in an embodiment of the present invention;

[0037] Figure 2 It is a connection block diagram of the English teaching interactive control system in an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of this application, so as to fully understand the purpose, scheme and effect of this application. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0039] refer to Figure 1 ,like Figure 1 An interactive control method for English teaching provided in an embodiment of the present application is shown, and the method comprises the following steps:

[0040] Step S100: establishing a communication connection between the server and several VR head displays;

[0041] In some embodiments, the student logs in to the client through the VR headset, and submits the VR headset ID information and the corresponding student identity information when logging in;

[0042] Step S200: sending a set of identical scenario dialogue videos to each VR head display, and receiving a response video fed back by each VR head display;

[0043] It should be noted that a set of identical situational dialogue videos contains situational dialogue questions of various categories and difficulties, and the situational dialogue questions include a question and at least one answer corresponding to the question. Through a set of identical situational dialogue videos, the multi-dimensional English proficiency of each student can be tested.

[0044] Step S300: classifying the response video fed back by each VR head display based on the pre-trained neural network model to obtain multiple classification groups; wherein each classification group corresponds to at least one VR head display;

[0045] Step S400: determine the weak items of each classification group, match the corresponding scenario teaching video according to the weak items of each classification group, and send the corresponding scenario teaching video to each classification group.

[0046] In a preferred embodiment, in step S300, the response video fed back by each VR head display is classified based on the pre-trained neural network model to obtain multiple classification groups, including:

[0047] Step S310: Obtain the response video feedback from each VR head display;

[0048] Step S320: Recognize the response video fed back by each VR head display based on the pre-trained neural network model to obtain comprehensive evaluation information corresponding to each VR head display;

[0049] Step S330: cluster the comprehensive evaluation information corresponding to each VR head display to obtain multiple classification groups.

[0050] In a preferred embodiment, in step S320, the response video fed back by each VR head display is recognized based on the pre-trained neural network model to obtain comprehensive evaluation information corresponding to each VR head display, including:

[0051] Step S321: Perform voice recognition on the response video fed back by the VR head display to obtain text response data; input the text response data into a pre-trained text classification model to obtain a first indicator; wherein the first indicator is one of the following: no response, inaccurate response, and accurate response;

[0052] Step S322, performing voice separation on the response video fed back by the VR head display to obtain voice response data; inputting the voice response data into a pre-trained voice classification model to obtain a second indicator; wherein the second indicator is one of the following: inaccurate pronunciation, incoherent pronunciation, and accurate pronunciation;

[0053] Step S323, performing image separation on the response video fed back by the VR head display to obtain image response data; inputting the image response data into a pre-trained image classification model to obtain a third indicator; wherein the third indicator is one of the following: stillness, slight movement, and expression conforming to the setting;

[0054] Step S324: Form a set of ternary data with the first indicator, the second indicator and the third indicator as comprehensive evaluation information corresponding to the VR head display.

[0055] It should be noted that the order of step S321 to step S323 is not limited, and they can be executed synchronously or asynchronously, or in any order or combination.

[0056] In a preferred embodiment, the method further comprises:

[0057] Constructing a first neural network model, and training the first neural network model with multiple sets of first training data to obtain a text classification model; wherein each set of training data in the multiple sets of first training data includes: text response data, at least one text answer and identification information of text differences, wherein the text difference is difference information between the text response data and each text answer;

[0058] Constructing a second neural network model, and training the second neural network model with multiple sets of second training data to obtain a speech classification model; wherein each set of training data in the multiple sets of second training data includes: speech response data, at least one speech answer and identification information of speech differences, wherein the speech differences are difference information between the speech response data and each speech answer;

[0059] A third neural network model is constructed, and multiple sets of third training data are used to train the third neural network model to obtain an image classification model; wherein each set of training data in the multiple sets of third training data includes: image response data, at least one image answer and identification information of image differences, and the image differences are difference information between the image response data and each image answer.

[0060] Specifically, the text classification model, speech classification model, and image classification model are all neural network models, which are obtained by training with multiple sets of training data. The neural network model is a neural network model in machine learning, which reflects many basic characteristics of human brain functions and is a highly complex nonlinear learning system. The process of training the neural network model with training data is essentially a supervised learning process.

[0061] Taking the text classification model as an example, when the text response data and at least one text answer are obtained, the neural network model will output the identification information of the text difference. By verifying the text difference output by the neural network model, if the text difference output by the neural network model is within the preset range with the identified text difference, the supervised learning of this data is completed, and the supervised learning of the next set of data is carried out; if the output text difference is beyond the preset range with the identified text difference, the neural network model itself is adjusted until the neural network model reaches the expected accuracy, and then the supervised learning of the next set of data is carried out. Through the training data, the neural network model itself is continuously corrected and optimized, and the accuracy of the neural network model in processing the data is improved through the process of supervised learning, thereby making the text difference more accurate.

[0062] In a preferred embodiment, in step S330, the comprehensive evaluation information corresponding to each VR head display is clustered to obtain multiple classification groups, including:

[0063] VR head displays corresponding to the same ternary data are divided into a group to obtain multiple classification groups.

[0064] In a preferred embodiment, in step S400, determining the weak items of each classification group, matching the corresponding scenario teaching video according to the weak items of each classification group, and sending the corresponding scenario teaching video to each classification group includes:

[0065] Determine the ternary data corresponding to each classification group;

[0066] Determine the first indicator, the second indicator and the third indicator corresponding to the ternary data. If the first indicator is no response or inaccurate response, semantic cultivation is regarded as a weak item; if the second indicator is inaccurate pronunciation or incoherent pronunciation, pronunciation cultivation is regarded as a weak item; if the third indicator is stillness or slight movement, expression cultivation is regarded as a weak item.

[0067] and Figure 1 Corresponding to the method, refer to Figure 2 The embodiment of the present invention further provides an English teaching interactive control system, the system comprising: a memory 11, a processor 12, and a computer program stored in the memory 11 and executable on the processor 12.

[0068] The processor 12 and the memory 11 may be connected via a bus or other means.

[0069] The non-transient software program and instructions required to implement the English teaching interactive control method of the above embodiment are stored in the memory 11 , and when executed by the processor 12 , the English teaching interactive control method of the above embodiment is executed.

[0070] The contents of the above method embodiments are all applicable to the present system embodiments. The functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0071] In addition, an embodiment of the present invention also provides a computer-readable storage medium, which stores computer-executable instructions. The computer-executable instructions are executed by a processor or controller, for example, by a processor in the above-mentioned electronic device embodiment, so that the above-mentioned processor can execute the English teaching interactive control method in the above-mentioned embodiment.

[0072] It will be appreciated by those skilled in the art that all or some of the steps and systems in the invented method above can be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, and the computer-readable medium can include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassette, magnetic tape, disk storage or other magnetic storage device, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0073] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above-mentioned implementation mode. Technical personnel familiar with the field can also make various equivalent deformations or substitutions without violating the spirit of the present invention. These equivalent deformations or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. An interactive control method for English teaching, characterized in that: The method comprises the following steps: Step S100: establishing a communication connection between the server and several VR head displays; Step S200: sending a set of identical scenario dialogue videos to each VR head display, and receiving a response video fed back by each VR head display; Step S300: classifying the response video fed back by each VR head display based on the pre-trained neural network model to obtain multiple classification groups; wherein each classification group corresponds to at least one VR head display; Step S400, determining the weak items of each classification group, matching corresponding scene teaching videos according to the weak items of each classification group, and sending the corresponding scene teaching videos to each classification group; In step S300, the neural network model obtained by pre-training classifies the response video fed back by each VR head display to obtain multiple classification groups, including: Step S310: Obtain the response video feedback from each VR head display; Step S320: Recognize the response video fed back by each VR head display based on the pre-trained neural network model to obtain comprehensive evaluation information corresponding to each VR head display; Step S330: clustering the comprehensive evaluation information corresponding to each VR head display to obtain multiple classification groups; In step S320, the neural network model obtained based on the pre-training recognizes the response video fed back by each VR head display to obtain the comprehensive evaluation information corresponding to each VR head display, including: Step S321: Perform voice recognition on the response video fed back by the VR head display to obtain text response data; input the text response data into a pre-trained text classification model to obtain a first indicator; wherein the first indicator is one of the following: no response, inaccurate response, and accurate response; Step S322, performing voice separation on the response video fed back by the VR head display to obtain voice response data; inputting the voice response data into a pre-trained voice classification model to obtain a second indicator; wherein the second indicator is one of the following: inaccurate pronunciation, incoherent pronunciation, and accurate pronunciation; Step S323, performing image separation on the response video fed back by the VR head display to obtain image response data; inputting the image response data into a pre-trained image classification model to obtain a third indicator; wherein the third indicator is one of the following: stillness, slight movement, and expression conforming to the setting; Step S324: Form a set of ternary data by using the first indicator, the second indicator and the third indicator as comprehensive evaluation information corresponding to the VR head display; In step S400, the weak items of each classification group are determined, the corresponding scenario teaching videos are matched according to the weak items of each classification group, and the corresponding scenario teaching videos are sent to each classification group, including: Determine the ternary data corresponding to each classification group; Determine the first indicator, the second indicator and the third indicator corresponding to the ternary data. If the first indicator is no response or inaccurate response, semantic cultivation is regarded as a weak item; if the second indicator is inaccurate pronunciation or incoherent pronunciation, pronunciation cultivation is regarded as a weak item; if the third indicator is stillness or slight movement, expression cultivation is regarded as a weak item.

2. The English teaching interactive control method according to claim 1, characterized in that: The method further comprises: Constructing a first neural network model, and training the first neural network model with multiple sets of first training data to obtain a text classification model; wherein each set of training data in the multiple sets of first training data includes: text response data, at least one text answer and identification information of text differences, wherein the text difference is difference information between the text response data and each text answer; Constructing a second neural network model, and training the second neural network model with multiple sets of second training data to obtain a speech classification model; wherein each set of training data in the multiple sets of second training data includes: speech response data, at least one speech answer and identification information of speech differences, wherein the speech differences are difference information between the speech response data and each speech answer; A third neural network model is constructed, and multiple sets of third training data are used to train the third neural network model to obtain an image classification model; wherein each set of training data in the multiple sets of third training data includes: image response data, at least one image answer and identification information of image differences, and the image differences are difference information between the image response data and each image answer.

3. The English teaching interactive control method according to claim 1, characterized in that: In step S330, the comprehensive evaluation information corresponding to each VR head display is clustered to obtain multiple classification groups, including: VR head displays corresponding to the same ternary data are divided into a group to obtain multiple classification groups.

4. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the English teaching interactive control method according to any one of claims 1 to 3 are implemented.

5. An English teaching interactive control system, characterized in that: The system comprises: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the English teaching interactive control method according to any one of claims 1 to 3.

Images