Virtual teaching training method and system based on large language model and medium

Abstract

The invention discloses a virtual teaching training method and system based on a large language model and a medium, and the method comprises the following steps: determining preset feature parameters of virtual students according to teaching levels and subject contents; constructing a large language model, generating virtual students based on the large language model according to preset feature parameters of the virtual students, and inputting multi-modal teaching information; the virtual students perform model training and learning on the multi-modal teaching information to generate learning state information and feedback information; the virtual teaching expert proposes a suggestion for dynamically adjusting and optimizing the teaching strategy based on the evaluation result; dynamic learning and interactive feedback are carried out by simulating virtual students with different priori knowledge levels and cognitive competence, and meanwhile, real-time evaluation and personalized improvement suggestions are carried out on the teaching process by utilizing the constructed virtual expert system, so that a user is helped to continuously optimize a teaching strategy, and the teaching quality of a specific subject is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent education technology, and in particular to a virtual teaching training method, system and medium based on a large language model. Background Art

[0002] Existing intelligent education technologies mainly use computer simulation and virtual reality for teacher training. In the field of virtual teaching training, systems such as TeachLivE and Mursion mainly use mixed reality technology to create simulated classroom environments, provide teachers with risk-free teaching and behavior management training, and help teachers improve their teaching and management skills by controlling virtual student roles and simulating real classroom interactions.

[0003] The prior art has the following problems:

[0004] 1) Limitation of professional knowledge: Current intelligent education technology systems mainly focus on classroom management and general teaching skills training, and do not support the evaluation of teaching effectiveness of specific subject professional knowledge. Therefore, when using such systems, users may find it difficult to evaluate and adjust teaching methods and strategies for specific subjects.

[0005] 2) Irresettable: In existing intelligent education platforms, once a virtual student begins to receive education and training, its learning history and accumulated knowledge cannot be simply cleared or reset to the initial state. This memory allows the virtual student to adjust its behavior and response based on previous interactions and learning outcomes.

[0006] 3) Insufficient interactivity: Existing systems use actors to simulate the reactions of virtual students to increase the naturalness of interaction, but this method still relies on preset scripts, actors’ improvisations, or settings by operators behind the scenes. This may affect the personalization and pertinence of teaching, especially in situations where customized teaching is required for different students’ needs.

[0007] 4) Limitations of expert evaluation: Existing technologies lack automated expert evaluation functions, making it impossible to conduct systematic analysis and real-time feedback on teaching effectiveness, and it is difficult to provide objective improvement suggestions based on the entire teaching process and students’ learning performance. Summary of the invention

[0008] The purpose of the present invention is to propose a virtual teaching training method based on a large language model to solve the problems mentioned in the background technology.

[0009] In order to achieve the above-mentioned invention object, the first technical solution adopted by the present invention is: a virtual teaching training method based on a large language model, comprising the following steps:

[0010] S1, determining characteristic parameters of a preset virtual student according to the teaching level and subject content, wherein the characteristic parameters of the preset virtual student include prior knowledge level, cognitive level and learning style;

[0011] S2, constructing a large language model, generating a virtual student based on the large language model according to the preset characteristic parameters of the virtual student, and inputting multimodal teaching information;

[0012] S3, based on the multimodal teaching information input, the virtual student learns and updates the learning status, and generates feedback information according to the learning status;

[0013] S4, using a teaching expert system based on a large language model to analyze and evaluate the feedback information to obtain an evaluation result;

[0014] S5, adjusting and optimizing strategies based on the evaluation results, and transmitting the adjustment and optimization strategies to the terminal in real time.

[0015] Furthermore, in step S1, the prior knowledge level includes high school, college

[0016] Prior knowledge levels of different stages such as undergraduate or postgraduate students to simulate students' basic knowledge reserves;

[0017] The cognitive abilities include basic, intermediate and advanced cognitive levels to reflect students' ability to process information and learn;

[0018] The learning styles include three different learning styles: visual learners, auditory learners and kinesthetic learners, so that the behavior of virtual students is closer to the real personalized learning method.

[0019] Furthermore, in step S2, the steps of constructing a large language model are as follows:

[0020] Select and train a large language model, wherein the large language model includes a GPT-4 model or a Kimi model, etc.;

[0021] Based on the prior knowledge level, cognitive level and learning style, corresponding prior knowledge level data set, cognitive level data set and learning style data set are constructed;

[0022] Establish prompt words, and select matching data combinations from the prior knowledge level data set, the cognitive level data set, and the learning style data set according to the prompt words;

[0023] After setting the parameters, input the teaching information training model (simulating the teaching process), let the virtual students conduct model training and learning on the teaching materials (simulating the learning process), and output feedback records in real time. The parameters include knowledge level, cognitive level, and learning style;

[0024] Dynamically adjust model parameters based on feedback records to generate the final large language model.

[0025] Furthermore, characteristic subject teaching materials are established according to the teaching level and subject content, and the virtual students perform dynamic learning and interactive feedback according to the provided specific subject teaching materials, and the specific subject teaching materials include texts, images or videos.

[0026] Furthermore, based on the evaluation results, an adjustment and optimization strategy is output, and the adjustment and optimization strategy is transmitted to the terminal in real time, specifically including:

[0027] Obtaining the evaluation results, comparing the evaluation results with the set condition information, and obtaining the teaching effectiveness evaluation value;

[0028] Determine whether the teaching effectiveness evaluation value is less than or equal to the set teaching effectiveness threshold;

[0029] If it is less than or equal to the teaching effectiveness threshold, then the adjustment information for optimizing the teaching strategy is generated and transmitted to the terminal in real time;

[0030] If it is greater than the teaching effectiveness threshold, the advantages and desirability of the current teaching strategy are summarized and transmitted to the terminal in real time for the user's reference.

[0031] In order to achieve the above-mentioned invention object, the second technical solution adopted by the present invention is: a virtual teaching and training system based on a large language model, and a virtual teaching and training method applied to a large language model, comprising:

[0032] A virtual student module, which constructs a virtual student model and determines characteristic parameters of a preset virtual student according to the teaching level and subject content;

[0033] A virtual expert module, which is electrically connected to the virtual student module. The virtual expert module evaluates the teaching effect in real time based on the teaching materials and student feedback information, and makes corresponding suggestions;

[0034] The hardware device is electrically connected to the virtual student module and the virtual expert module, and is used to collect text, voice and image, and perform multimodal interaction with the virtual student model.

[0035] Furthermore, the hardware device includes a computer, a microphone and a camera.

[0036] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program enables a computer to execute to implement any of the above-mentioned virtual teaching and training methods based on a large language model.

[0037] Due to the application of the above-mentioned technical solution, the present invention has the following advantages compared with the prior art: the present application simulates virtual students with different prior knowledge levels and cognitive abilities to conduct dynamic learning and interactive feedback, and uses the constructed virtual expert system to conduct real-time evaluation and personalized improvement suggestions on the teaching process, thereby helping users to continuously optimize teaching strategies and improve the teaching quality of specific subjects. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A flowchart of a virtual teaching training method based on a large language model provided by an embodiment of the present invention is shown;

[0039] Figure 2 A flowchart of constructing a large language model in a virtual teaching training method based on a large language model provided by an embodiment of the present invention is shown;

[0040] Figure 3 A block diagram of a virtual teaching and training system based on a large language model provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0041] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0042] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or system comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or systems.

[0043] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0044] like Figure 1 As shown, an embodiment of the present invention provides a virtual teaching training method based on a large language model, comprising the following steps:

[0045] S1, determining the characteristic parameters of the preset virtual students according to the teaching level and subject content, the characteristic parameters of the preset virtual students include prior knowledge level, cognitive level and learning style;

[0046] S2, constructing a large language model, generating a virtual student based on the large language model according to the preset characteristic parameters of the virtual student, and inputting multimodal teaching information;

[0047] S3, the virtual student conducts model training and learning based on the multimodal teaching information, and generates learning status information and feedback information;

[0048] S4, using a teaching expert system based on a large language model to analyze and evaluate the feedback information to obtain an evaluation result;

[0049] S5, output adjustment and optimization strategy suggestions based on the evaluation results, and transmit the adjustment and optimization strategy suggestions to the terminal in real time.

[0050] It should be noted that by simulating virtual students with different prior knowledge levels and cognitive abilities to conduct dynamic learning and interactive feedback, and using the constructed virtual expert system to conduct real-time evaluation of the teaching process and provide personalized improvement suggestions, it helps users to continuously optimize teaching strategies and improve the teaching quality of specific subjects. By utilizing the latest large language models and natural language processing technologies, this method can create virtual students that can simulate different prior knowledge levels and cognitive abilities. These virtual students can conduct dynamic learning and interactive feedback based on the specific subject teaching materials (such as text, images, videos, etc.) provided by the user, thereby supporting users to continuously test and improve their teaching materials and teaching strategies in a risk-free, resettable simulation environment. The virtual teaching expert system can conduct real-time evaluation based on the teaching process and students' learning feedback, and provide personalized improvement suggestions to help users better understand the teaching effect and optimize teaching methods.

[0051] Furthermore, the present invention is suitable for teachers and educational researchers to develop virtual student models to improve teaching effectiveness for specific subjects, and is suitable for educational institutions (such as universities, primary and secondary schools) and training centers, especially in the optimization of teaching materials, testing of teaching strategies, and feedback on teaching effectiveness.

[0052] According to an embodiment of the present invention, in step S1, the prior knowledge level includes the prior knowledge level of different stages of high school, undergraduate or postgraduate students to simulate the basic knowledge reserve of students;

[0053] Cognitive skills include basic, intermediate and advanced cognitive levels to reflect students' ability to process information and learn;

[0054] Learning styles include three different learning styles: visual learners, auditory learners and kinesthetic learners, making the behavior of virtual students closer to real personalized learning methods.

[0055] like Figure 2 As shown, according to an embodiment of the present invention, in step S2, the steps of constructing a large language model are as follows:

[0056] S201, select and train a large language model, the large language model includes a GPT-4 model or a Kimi model, etc.;

[0057] S202, constructing a corresponding data set of prior knowledge level, cognitive level and learning style based on prior knowledge level, cognitive level and learning style;

[0058] S203, establishing prompt words, selecting a data combination that meets preset parameters from the data set of prior knowledge level, cognitive level and learning style to construct prompt words;

[0059] S204, training the large language model using the prompt words;

[0060] S205, using a test data set of a corresponding level (such as test questions of a corresponding subject) to test the model, and adjusting prompt words according to the feedback of the model and the test results to make the virtual student model meet the preset level.

[0061] According to an embodiment of the present invention, characteristic subject teaching materials are established according to the teaching level and subject content, and virtual students perform dynamic learning and interactive feedback according to the provided specific subject teaching materials. The specific subject teaching materials include text, images or videos.

[0062] It should be noted that when building a virtual expert, the large model can be trained in parallel using prompt words and teaching history. The content is "You are a teaching expert. Please give an evaluation and suggestions for the most recent teaching based on the above teaching materials and student feedback records." This allows the large language model to understand that the next task is to evaluate the previous teaching process and make suggestions for improvement. The prompt word is sent to the model together with the message record of the previous teaching process, so that it can have a global understanding of the teaching process and return the most recent teaching evaluation and suggestions.

[0063] According to an embodiment of the present invention, an evaluation is performed based on the teaching history, and optimization suggestions for the teaching strategy are given, and the suggestions are transmitted to the terminal in real time, specifically including:

[0064] Obtaining the evaluation results, comparing the evaluation results with the set condition information, and obtaining the teaching effectiveness evaluation value;

[0065] Determine whether the teaching effectiveness evaluation value is less than or equal to the set teaching effectiveness threshold;

[0066] If it is less than or equal to the teaching effectiveness threshold, then the adjustment information for optimizing the teaching strategy is generated and transmitted to the terminal in real time;

[0067] If it is greater than the teaching effectiveness threshold, the advantages and desirability of the current teaching strategy are summarized and transmitted to the terminal in real time for the user's reference.

[0068] like Figure 3 As shown, in order to achieve the above-mentioned invention object, the second technical solution adopted by the present invention is: a virtual teaching and training system based on a large language model, a virtual teaching and training method applied to a large language model, comprising:

[0069] Virtual student module, the virtual student module builds a virtual student model and determines the characteristic parameters of the preset virtual student according to the teaching level and subject content;

[0070] The virtual expert module is electrically connected to the virtual student module. The virtual expert module evaluates the teaching effect in real time based on the teaching materials and student feedback information and puts forward corresponding suggestions.

[0071] Hardware equipment, the hardware equipment is electrically connected to the virtual student module and the virtual expert module, and the hardware equipment is used to collect text, voice and images, and perform multimodal interaction with the virtual student model.

[0072] Application examples:

[0073] Case 1: A junior high school mathematics teacher wants to test the effectiveness of different teaching plans. Through the virtual student system, the teacher simulates and generates virtual students with corresponding prior knowledge levels, obtains the learning response of virtual students by uploading teaching materials (such as PPT or textbooks), and evaluates the effectiveness of each method. At the same time, the system provides real-time feedback to help teachers adjust teaching plans in real time. By combining the suggestions given by the system, teachers can improve the overall quality of teaching plans after repeated experiments.

[0074] Case 2: The teaching development department of a university hopes to implement a new teacher training system to improve teachers' professional knowledge teaching ability. Through the virtual student system, teachers simulate and generate college students with corresponding prior knowledge levels (high school graduates, freshmen, sophomores, etc.), and obtain feedback by uploading teaching materials (such as PPT or audio or video). At the end of the interaction, the system also provides evaluation and suggestions to help teachers improve the quality of professional knowledge teaching.

[0075] According to an embodiment of the present invention, the hardware device includes a computer, a microphone and a camera.

[0076] The present invention also provides a computer-readable storage medium, which stores a computer program, and the computer program enables a computer to execute to implement any of the above-mentioned virtual teaching and training methods based on a large language model.

[0077] In summary, this application simulates virtual students with different prior knowledge levels and cognitive abilities to conduct dynamic learning and interactive feedback, and uses the constructed virtual expert system to conduct real-time evaluation and personalized improvement suggestions on the teaching process, helping users to continuously optimize teaching strategies and improve the teaching quality of specific subjects.

[0078] Those skilled in the art will appreciate that, for ease of description, the example in which both the memory and the processor are provided with one is used for description. In an actual terminal or server, there may be multiple processors and memories. The memory may also be referred to as a storage medium or a storage device, etc., which is not limited in the embodiments of the present application.

[0079] It should be understood that in the embodiments of the present application, the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor may also be a general-purpose microprocessor, a graphics processing unit (GPU), or one or more integrated circuits for executing related programs to implement the functions required to be executed in the embodiments of the present application.

[0080] The processor can also be an integrated circuit chip with signal processing capabilities. In the implementation process, the various steps of the present application can be completed by the integrated logic circuit of the hardware in the processor or the instructions in the form of software. The above-mentioned processor can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or a combination of hardware and software modules in the decoding processor to be executed. The software module can be located in a random access memory, a flash memory and a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register and other mature storage media in the art. The storage medium is located in the memory, and the processor reads the information in the memory, and combines its hardware to complete the functions required to be performed by the unit included in the method, system and storage medium of the embodiment of the present application.

[0081] It should also be understood that the memory mentioned in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache.

[0082] By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct RAM bus random access memory (DR RAM).

[0083] The memory may also be a read-only optical disc (Compact Disc Read-Only Memory, CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may be independent and connected to the processor via a bus. The memory may also be integrated with the processor, and the memory may store a program. When the program stored in the memory is executed by the processor, the processor is used to execute the various steps of the determination method in the above-mentioned embodiment of the present application.

[0084] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, the memory (storage module) is integrated into the processor. It should be noted that the memory described herein is intended to include but is not limited to these and any other suitable types of memory.

[0085] It should be understood that the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0086] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. The steps of the method disclosed in conjunction with the embodiment of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software modules in a processor for execution. The software module can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory, and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it is not described in detail here.

[0087] Those of ordinary skill in the art will appreciate that the various illustrative logical blocks (ILBs) and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0088] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a program product of computer programming. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a processor, all or part of the processes or functions according to the embodiments of the present application are generated. The computer may be a general-purpose computer, a computer network, or other programmable device.

[0089] This embodiment also provides a computer-readable storage medium, which stores a computer program. The computer program enables a computer to execute to implement the above-mentioned virtual teaching training method based on a large language model.

[0090] It should be noted that computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., coaxial cable, optical fiber) or wireless (e.g., infrared, wireless, microwave, etc.) means, or can be transmitted from one website, computer, server or data center to a mobile phone processor by wired means. Computer-readable storage media can be any available medium that can be accessed by a computer or a data storage system such as a server or data center that includes one or more available media. Available media can be magnetic media (e.g., floppy disk, hard disk), optical media (e.g., DVD), or semiconductor media (e.g., solid-state hard disk), etc.

[0091] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A virtual teaching training method based on a large language model, characterized in that: The following steps are involved: S1, determining characteristic parameters of a preset virtual student according to the teaching level and subject content, wherein the characteristic parameters of the preset virtual student include prior knowledge level, cognitive level and learning style; S2, constructing a large language model, generating a virtual student based on the large language model according to the preset characteristic parameters of the virtual student, and inputting multimodal teaching information; S3, the virtual student conducts model training and learning based on the multimodal teaching information, and generates learning status information and feedback information; S4, using the teaching expert system based on the large language model to analyze and evaluate the input teaching information and the feedback information of the virtual students to obtain the evaluation results; S5, output adjustment and optimization strategy suggestions based on the evaluation results, and transmit the adjustment and optimization strategy suggestions to the terminal in real time.

2. The virtual teaching training method based on a large language model as claimed in claim 1, characterized in that: In step S1, the prior knowledge level includes the prior knowledge level of different stages of high school, undergraduate or postgraduate students to simulate the basic knowledge reserve of students; The cognitive abilities include basic, intermediate and advanced cognitive levels to reflect students' ability to process information and learn; The learning styles include three different learning styles: visual learners, auditory learners and kinesthetic learners, so that the behavior of virtual students is closer to the real personalized learning method.

3. The virtual teaching training method based on a large language model as claimed in claim 2, characterized in that: In step S2, the steps of building a large language model are as follows: Select and train a large language model, wherein the large language model includes a GPT-4 model or a Kimi model; Based on the prior knowledge level, cognitive level and learning style, corresponding prior knowledge level data set, cognitive level data set and learning style data set are constructed; Establish prompt words, and select matching data combinations from the prior knowledge level data set, the cognitive level data set, and the learning style data set according to the prompt words; After setting the parameters, input the teaching information training model, let the virtual students conduct model training and learning on the teaching materials, and output feedback records in real time. The parameters include knowledge level, cognitive level, and learning style. Dynamically adjust model parameters based on feedback records to generate the final large language model.

4. The virtual teaching training method based on a large language model as claimed in claim 1, characterized in that: Characteristic subject teaching materials are established according to the teaching level and subject content, and virtual students perform dynamic learning and interactive feedback based on the specific subject teaching materials provided. The specific subject teaching materials include texts, images or videos.

5. The virtual teaching training method based on a large language model as claimed in claim 1, characterized in that: Output adjustment and optimization strategy suggestions based on the evaluation results, and transmit the adjustment and optimization strategy suggestions to the terminal in real time, including: Obtaining the evaluation results, comparing the evaluation results with the set condition information, and obtaining the teaching effectiveness evaluation value; Determine whether the teaching effectiveness evaluation value is less than or equal to the set teaching effectiveness threshold; If it is less than or equal to the teaching effectiveness threshold, then adjustment information for optimizing the teaching strategy is generated and the adjustment information is transmitted to the terminal in real time; If it is greater than the teaching effectiveness threshold, the advantages and desirability of the current teaching strategy are summarized and transmitted to the terminal in real time for the user's reference.

6. A virtual teaching and training system based on a large language model, applied to the virtual teaching and training method based on a large language model as described in any one of claims 1 to 5, characterized in that: include: A virtual student module, which constructs a virtual student model and determines characteristic parameters of a preset virtual student according to the teaching level and subject content; A virtual expert module, which is electrically connected to the virtual student module. The virtual expert module evaluates the teaching effect in real time based on the teaching materials and student feedback information, and makes corresponding suggestions; The hardware device is electrically connected to the virtual student module and the virtual expert module, and is used to collect text, voice and image, and perform multimodal interaction with the virtual student model.

7. The virtual teaching and training system based on a large language model as claimed in claim 6, characterized in that: The hardware device includes a computer, a microphone and a camera.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which enables a computer to execute to implement the virtual teaching training method based on a large language model according to any one of claims 1 to 5.

Images