Holographic practical training platform based on mixed reality

Abstract

The invention discloses a holographic practical training platform based on mixed reality, which belongs to the field of mixed reality, and comprises the following steps: a data collection module obtains course content and environment data; the data processing module preprocesses the data to generate a course data set and an environment data set; the three-dimensional generation module performs three-dimensional modeling of a training course according to the course data set to obtain a three-dimensional holographic course model; the neural network construction module is used for training a convolutional network based on historical data and generating an environment feature recognition model; the matching calculation module inputs the environment data into an environment feature recognition model, generates teaching environment features, matches the teaching environment features with a three-dimensional course model, and imports the teaching environment features into MR equipment; the access module accesses students and a tutor into a simulation environment through MR equipment, synchronizes actions of the students and the tutor in real time, and enhances teaching interaction. According to the system, teaching interactivity and immersion are improved, and personalized learning is promoted.

Description

Technical Field

[0001] The present invention belongs to the field of mixed reality, and in particular relates to a holographic training platform based on mixed reality. Background Art

[0002] Mixed reality (MR) technology is a further development of virtual reality technology. This technology presents virtual scene information in real scenes, builds an interactive feedback information loop between the real world, the virtual world and the user, and enhances the realism of the user experience. Currently, in the undergraduate education process, experimental training is an important part of cultivating students' understanding and cognitive abilities. However, due to factors such as safety, venue, and cost, many experimental practice courses are difficult to carry out using traditional teaching methods.

[0003] For example, during experiments in chemical engineering, biology and other majors, due to the toxicity and harmfulness of some reagents or strains, misoperation can easily cause varying degrees of personal injury, so schools are cautious about such experiments. Even colleges and universities that have the ability to carry out these experiments often require a high-level experimental environment that can accommodate a very limited number of students. Teachers need to use a lot of text descriptions in the teaching process, which is difficult for students with insufficient spatial sense to understand. How to convert the text and picture materials of the textbooks into three-dimensional knowledge content and present it in a more intuitive and three-dimensional form is also a reform topic that has been studied in the process of education and teaching. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a holographic training platform based on mixed reality, comprising:

[0005] The data collection module is used to obtain the course content of engineering majors and collect environmental data during teaching courses;

[0006] A data processing module, connected to the data collection module, for preprocessing the course content and the environmental data to obtain a course data set and an environmental data set;

[0007] A three-dimensional generation module, connected to the data processing module, is used to perform three-dimensional modeling of the course data set for practical teaching to obtain a three-dimensional holographic course model;

[0008] A neural network construction module, connected to the three-dimensional generation module, is used to construct a convolutional network model, and train the convolutional network model based on a historical data set to obtain an environmental feature recognition model;

[0009] A matching calculation module, connected to the neural network construction module, is used to input the environmental data set into the environmental feature recognition model, generate teaching environment features, match the teaching environment features with the three-dimensional holographic course model, import the MR course model into the MR device, and generate an MR training course import device;

[0010] The access module is connected to the matching calculation module and is used to access the students and the instructors to the course simulation environment based on the MR training course import device, and synchronously simulate the actions of the students and the instructors in the environment.

[0011] Preferably, the data collection module comprises:

[0012] The course acquisition submodule is used to obtain the course content of engineering majors based on the database, and at the same time obtain the students' learning progress, interests and needs, and build students' learning profiles;

[0013] The environment recognition submodule is used to obtain the spatial information of various objects and surfaces in the environment through a depth camera and perform dynamic positioning.

[0014] Preferably, the course content includes, but is not limited to: course text, 3D model, graphic data, experimental data, and measurement data;

[0015] The student's learning progress, interests and needs include but are not limited to: the student's learning progress, behavior patterns, and interaction records.

[0016] Preferably, the data processing module includes:

[0017] The course content processing submodule is used to generate a course data set after identifying the characteristics of the course content of engineering majors, and at the same time combine the students' learning progress, interests and needs as labels with the course data set;

[0018] The environmental data processing submodule is used to perform edge-aware image processing on the environmental data through a spatial filter, and then perform time smoothing and hole filling on the data to generate the environmental data set.

[0019] Preferably, the three-dimensional generation module includes:

[0020] A classification submodule, used to classify the course data set according to course types to generate a classified data set;

[0021] The three-dimensional model generation submodule is used to construct a three-dimensional model of each item in the classification data set based on the modeling software, and connect the constructed classification models through a topological structure to generate three-dimensional holographic course models of different scenes.

[0022] Preferably, the neural network building module comprises:

[0023] Model building submodule, used to build convolutional neural network models;

[0024] A model optimization submodule, used to construct a self-attention module and a residual module, and introduce the self-attention module and the residual module into the convolutional neural network model to generate an improved convolutional network;

[0025] The training submodule is used to obtain a historical environment recognition data set, and train the improved convolutional network with the historical environment recognition data set to obtain an environmental feature recognition model.

[0026] A neural network construction submodule, connected to the three-dimensional generation module, is used to construct a convolutional network model, and train the convolutional network model based on a historical data set to obtain a feature matching model;

[0027] Preferably, the matching calculation module includes:

[0028] An environmental feature generation submodule is used to input the environmental data set into the environmental feature recognition model for processing through multiple convolutional layers and fully connected layers, map the generated features to a target feature space that matches the teaching environment, and generate the teaching environment features;

[0029] The matching submodule is used to match the three-dimensional holographic course model with the teaching environment characteristics, and to superimpose the three-dimensional holographic course model in the real scene based on the matching result to generate an MR course model.

[0030] The import submodule is used to import the MR course model into the MR device to generate an MR training course import device.

[0031] Preferably, the access module includes:

[0032] The collaborative access submodule is used to connect students and instructors to a virtual environment based on the MR training course import device to simulate different operations and situations to demonstrate the connection between theory and practice;

[0033] The feedback module is used to give feedback based on students' operations, interactions and simulation results.

[0034] Compared with the prior art, the present invention has the following advantages and technical effects:

[0035] Through 3D modeling and MR technology, the present invention enables students to conduct practical training in a virtual environment to enhance their understanding and operational capabilities. Combining environmental data and course content, the teaching content can be dynamically adjusted according to student performance to provide a more personalized learning path. Students and tutors can interact synchronously in a virtual environment, transcending the limitations of physical space, and providing a flexible teaching and tutoring mode. In addition, the teaching environment can be identified and adjusted through a neural network model to optimize learning conditions and improve teaching effectiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0037] Figure 1 It is a schematic diagram of a holographic training platform based on mixed reality according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] 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.

[0039] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0040] The following is an explanation of the technical points in this embodiment:

[0041] The core technologies of Mixed Reality (MR) and Virtual Training mainly include the following aspects:

[0042] 1. Augmented Reality (AR) and Virtual Reality (VR) technologies:

[0043] AR technology superimposes digital information onto the real world, allowing users to see virtual objects and data in real environments.

[0044] VR technology creates a completely virtual environment, in which users are fully immersed through devices such as head-mounted displays.

[0045] 2. Computer Graphics:

[0046] 3D Modeling and Rendering: Create realistic 3D models and make them look real in a virtual environment through rendering techniques.

[0047] Physics engine: simulates the physical rules of the real world (such as gravity, collision, etc.) to ensure that the behavior in the virtual environment is consistent with the real world.

[0048] 3. Positioning and tracking technology:

[0049] Spatial positioning: Use sensors (such as lidar, cameras, gyroscopes, etc.) to accurately track the user's position and movements in the real world.

[0050] Gaze tracking: Tracking the user’s gaze so that displayed content can be adjusted accordingly in the virtual environment.

[0051] 4. Human-computer interaction technology:

[0052] Gesture recognition: Recognize user gestures through cameras or other sensors, allowing natural interaction in virtual environments.

[0053] Speech Recognition: Allows users to interact with the virtual environment through voice commands.

[0054] Embodiment 1

[0055] like Figure 1 As shown, in this embodiment, a holographic training platform based on mixed reality is provided, including:

[0056] The data collection module is used to obtain the course content of engineering majors and collect environmental data during teaching courses;

[0057] Further optimizing the scheme, the data collection module includes:

[0058] The course acquisition submodule is used to obtain the course content of engineering majors based on the database, and at the same time obtain the students' learning progress, interests and needs, and build students' learning profiles;

[0059] The environment recognition submodule is used to obtain the spatial information of various objects and surfaces in the environment through a depth camera and perform dynamic positioning.

[0060] Further optimizing the scheme, the course content includes but is not limited to: course text, 3D model, graphic data, experimental data, and measurement data;

[0061] The student's learning progress, interests and needs include but are not limited to: the student's learning progress, behavior patterns, and interaction records.

[0062] First, it is necessary to clarify the requirements and core functions of the platform:

[0063] Through holographic technology, engineering teaching content (such as mechanical principles, circuit design, construction engineering, etc.) can be presented in 3D or holographic form, making it convenient for students to conduct interactive learning.

[0064] In the platform, students can interact with virtual models, charts, experimental environments, etc. through MR devices to conduct virtual experiments, simulation operations, etc.

[0065] Based on students' learning progress, interests and needs, data matching is performed through neural networks to recommend relevant teaching content, experiments, or real-time feedback.

[0066] The specific process of acquiring data is as follows: Use the depth camera to capture images and depth data in the environment. Turn on the camera, configure the corresponding parameters, such as resolution and frame rate, and obtain depth frames and color frames. The depth values ​​in the depth image need to be converted into a displayable form. You can use the tools provided by the depth camera SDK, such as rs.colorizer(), to map depth values ​​to colors for visualization on the screen.

[0067] Course data includes course texts, 3D models, graphic data, experimental data, measurement data, etc. These data can be collected through digital means (such as CAD, 3D scanning, sensors, etc.), and track students' learning progress, behavior patterns, interaction records, etc., and establish students' learning files.

[0068] A data processing module, connected to the data collection module, for preprocessing the course content and the environmental data to obtain a course data set and an environmental data set;

[0069] Further optimizing the scheme, the data processing module includes:

[0070] The course content processing submodule is used to generate a course data set after identifying the characteristics of the course content of engineering majors, and at the same time combine the students' learning progress, interests and needs as labels with the course data set;

[0071] The environmental data processing submodule is used to perform edge-aware image processing on the environmental data through a spatial filter, and then perform time smoothing and hole filling on the data to generate the environmental data set.

[0072] The sensor scans and builds a 3D map of the environment in real time to obtain spatial information about each object and surface in the environment.

[0073] Through SLAM (Simultaneous Localization and Mapping) technology, the system can track the location of the device in real time and keep it synchronized with the spatial mapping.

[0074] After the environment space is mapped, the system can determine the position and orientation of the 3D model through feature points (such as walls, desktops, floors, etc.) or physical objects (such as furniture, machinery and equipment). These feature points are usually achieved through image recognition or depth perception. MR devices can "anchor" 3D models to specific physical locations, for example: "fixing" virtual 3D models to a certain location in the real world. Anchor points can be user-defined or automatically identified, such as walls, floors, desktops, etc. automatically determined through spatial mapping. For objects with mobility (such as mechanical parts or circuit board assemblies), the system can adjust the relationship between the 3D model and the real environment through visual tracking technology (such as object detection, key point tracking). Add physical properties (such as weight, inertia, friction, etc.) to the 3D model to ensure that the model is realistic when interacting with the environment. For example, virtual mechanical parts should be able to move, rotate, and even collide with objects in the real environment according to real physical rules. Ensure that the size of the 3D model matches the actual size in the environment. Virtual objects can be placed in the appropriate spatial position using automated algorithms or manual adjustments.

[0075] The course data set includes:

[0076] Course structure: chapters, sections, subject content, etc.

[0077] Teaching objectives: The teaching objectives to be achieved by the course may be the mastery of skills and knowledge points.

[0078] Multimedia resources: text, images, videos, animations, etc., as teaching resources in the course.

[0079] Interactive content: Quizzes, discussion questions, simulations and other interactive forms.

[0080] A three-dimensional generation module, connected to the data processing module, is used to perform three-dimensional modeling of the course data set for practical teaching to obtain a three-dimensional holographic course model;

[0081] Further optimizing the scheme, the three-dimensional generation module includes:

[0082] A classification submodule, used to classify the course data set according to course types to generate a classified data set;

[0083] The three-dimensional model generation submodule is used to construct a three-dimensional model of each item in the classification data set based on the modeling software, and connect the constructed classification models through a topological structure to generate three-dimensional holographic course models of different scenes.

[0084] In order to enhance the integration of the virtual model with the real environment, it is necessary to dynamically adjust the lighting and shadows of the virtual model to keep them consistent with the light sources and shadows in the real environment. This mainly includes:

[0085] 1. Use sensors to obtain lighting conditions in the real environment (such as light intensity, light source direction, etc.).

[0086] 2. Adjust the lighting effect of the virtual 3D model according to the actual lighting in the environment to ensure that the lighting effect of the model is consistent with that of the environment to avoid appearing abrupt.

[0087] 3. Use dynamic lighting models to calculate and generate shadows of virtual models in real time, ensuring that the shadows are consistent with objects in the environment.

[0088] According to the course structure and teaching content, start to build a three-dimensional model of the course:

[0089] Build a 3D graph that shows the entire course structure. For example, you can divide the course into multiple modules, topics, or stages, and show the relationship between them through 3D nodes and lines. Each module can be represented by a 3D graph, and the lines between the nodes show the teaching relationship between them.

[0090] For the core knowledge points in the course, they can be transformed into 3D objects or scenes. For example, a chemistry course can model chemical elements as molecular structures; a physics course can display mechanical principles, motion trajectories, etc. through 3D models.

[0091] Areas include but are not limited to:

[0092] Chemical industry: For example, modeling equipment such as reactors, pipes, pumps, and valves to simulate chemical reaction processes.

[0093] Energy sector: such as the structure and operation of wind turbines, solar panels, and thermal power plants.

[0094] Pharmaceutical field: such as various links of drug production, experimental equipment, molecular structure, etc.

[0095] Medical device field: such as the three-dimensional structure of medical devices, simulating their working principles and functions.

[0096] A neural network construction module, connected to the three-dimensional generation module, is used to construct a convolutional network model, and train the convolutional network model based on a historical data set to obtain an environmental feature recognition model;

[0097] Further optimizing the scheme, the neural network building module includes:

[0098] Model building submodule, used to build convolutional neural network models;

[0099] A model optimization submodule, used to construct a self-attention module and a residual module, and introduce the self-attention module and the residual module into the convolutional neural network model to generate an improved convolutional network;

[0100] The training submodule is used to obtain a historical environment recognition data set, and train the improved convolutional network with the historical environment recognition data set to obtain an environmental feature recognition model.

[0101] A neural network construction submodule, connected to the three-dimensional generation module, is used to construct a convolutional network model, and train the convolutional network model based on a historical data set to obtain a feature matching model;

[0102] When modeling, it is necessary to ensure that the details of each device, component, and system are accurate, and it is also necessary to consider the rendering effect of the model so that it can be clearly presented through the 3D view.

[0103] A matching calculation module, connected to the neural network construction module, is used to input the environmental data set into the environmental feature recognition model, generate teaching environment features, match the teaching environment features with the three-dimensional holographic course model, import the MR course model into the MR device, and generate an MR training course import device;

[0104] Further optimizing the scheme, the matching calculation module includes:

[0105] An environmental feature generation submodule is used to input the environmental data set into the environmental feature recognition model for processing through multiple convolutional layers and fully connected layers, map the generated features to a target feature space that matches the teaching environment, and generate the teaching environment features;

[0106] The matching submodule is used to match the three-dimensional holographic course model with the teaching environment characteristics, and to superimpose the three-dimensional holographic course model in the real scene based on the matching result to generate an MR course model.

[0107] The import submodule is used to import the MR course model into the MR device to generate an MR training course import device.

[0108] Holographic technology is used to display three-dimensional images, allowing students to observe teaching content from different angles and enhance the learning experience. To achieve this, you need to choose a suitable holographic platform:

[0109] To demonstrate with AR or VR, it is necessary to develop corresponding applications that combine 3D modeling data with AR / VR hardware devices (such as AR glasses, VR helmets, holographic projectors, etc.). These technologies can enhance students' understanding of complex systems, such as seeing the operation of each step in the pharmaceutical process or simulating the operation of equipment in chemical equipment.

[0110] In a mixed reality environment, users usually interact with virtual 3D models through gestures, voice, or other input methods. In order to achieve a smooth interactive experience, the 3D model needs to be able to respond to the user's actions and adapt to the environment:

[0111] MR devices use sensors to capture user gestures or movements to control the movement, rotation, or zooming of virtual models. For example, students can grab and operate virtual mechanical parts through gestures.

[0112] Provide virtual tools or interactive interfaces to allow students to perform more operations with 3D models, such as splicing mechanical parts, simulating circuit connections, adjusting building structures, etc.

[0113] The access module is connected to the matching calculation module and is used to access the students and the instructors to the course simulation environment based on the MR training course import device, and synchronously simulate the actions of the students and the instructors in the environment.

[0114] Further optimizing the scheme, the access module includes:

[0115] The collaborative access submodule is used to connect students and instructors to a virtual environment based on the MR training course import device to simulate different operations and situations to demonstrate the connection between theory and practice;

[0116] The feedback module is used to give feedback based on students' operations, interactions and simulation results.

[0117] To enhance students' sense of immersion and interaction, the system should also provide real-time feedback and be able to adaptively adjust virtual content according to the environment and user behavior.

[0118] When students complete an operation, the system will give immediate feedback based on the operation results, such as sound prompts, visual changes, physical feedback, etc.

[0119] Based on students' interactive feedback in the MR environment (such as whether the operation is successful or not, learning progress, etc.), the system can dynamically adjust the learning path and provide more personalized learning content and experiments.

[0120] By analyzing students’ learning progress, interests, and interaction methods, the platform can use neural networks to intelligently recommend appropriate 3D models and environment settings. For example, the platform can automatically push specific experimental modules or 3D models based on students’ learning history and current progress to help students learn more effectively.

[0121] Design interactive features for the model based on teaching needs. For example, allow students to view different model parts, adjust parameters, simulate experimental processes, or provide step-by-step guidance through touch, gestures, or voice commands. For example, students can rotate a chemical reactor to understand its internal structure, or observe different results of chemical reactions by changing variables.

[0122] Demonstrate the connection between theory and practice by simulating different operations and situations. For example, simulate the load change of energy system, the synthesis process of medicine, or the fault diagnosis of equipment. Such dynamic simulation can help students understand complex concepts.

[0123] Integrate the 3D holographic model into the existing teaching platform or learning management system (LMS) so that it can be combined with classroom teaching, online learning, laboratory practice, etc. For example, students can access the 3D holographic course model through the platform for independent learning or tutoring.

[0124] The core technology of platform development and implementation in this invention:

[0125] 1. Unity3D (3D graphics rendering engine)

[0126] It is mainly used to create 3D environments and virtual experimental scenes. The Unity3D engine has powerful 3D rendering capabilities and plug-ins that support MR development, which can achieve complex scene construction and interactive effects.

[0127] MR SDK (Mixed Reality Development Kit): MRTK or Open XR, used to develop applications compatible with specific MR devices. The SDK provides device-specific functional interfaces such as gesture recognition, spatial scanning, etc.

[0128] 2. 3D Modeling

[0129] Use Blender (open source 3D modeling and rendering software), 3ds Max (Autodesk's 3D modeling, animation and rendering tool), Maya (Autodesk's high-end 3D modeling and animation software) modeling tools to create detailed 3D models of equipment and experimental environments. These models need to be optimized to ensure smooth operation on MR devices.

[0130] 3. CAD import and optimization

[0131] Import chemical equipment from existing CAD models and perform polygon optimization and detail adjustment in the software.

[0132] 4. Gesture and voice recognition

[0133] Gesture recognition library: Use the built-in or third-party gesture recognition library of the MR device to implement experimental operations through gestures, such as grabbing, tapping, rotating the device, etc.

[0134] Speech recognition system: Integrate with services such as Microsoft’s Azure Speech service (speech recognition and conversion service provided by Microsoft Azure) to interpret and execute user voice commands, such as starting or pausing experiments or obtaining data analysis.

[0135] 5. Spatial mapping and positioning

[0136] SLAM (Simultaneous Localization and Mapping) technology: used to scan and map the real environment, ensuring that virtual content can be accurately superimposed on the real world, achieving seamless integration of real scenes and virtual elements.

[0137] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A holographic training platform based on mixed reality, characterized in that: include: The data collection module is used to obtain the course content of engineering majors and collect environmental data during teaching courses; A data processing module, connected to the data collection module, for preprocessing the course content and the environmental data to obtain a course data set and an environmental data set; A three-dimensional generation module, connected to the data processing module, is used to perform three-dimensional modeling of the course data set for practical teaching to obtain a three-dimensional holographic course model; A neural network construction module, connected to the three-dimensional generation module, is used to construct a convolutional network model, and train the convolutional network model based on a historical data set to obtain an environmental feature recognition model; A matching calculation module, connected to the neural network construction module, is used to input the environmental data set into the environmental feature recognition model, generate teaching environment features, match the teaching environment features with the three-dimensional holographic course model, import the MR course model into the MR device, and generate an MR training course import device; The access module is connected to the matching calculation module and is used to access the students and the instructors to the course simulation environment based on the MR training course import device, and synchronously simulate the actions of the students and the instructors in the environment.

2. The holographic training platform based on mixed reality according to claim 1, characterized in that: The data collection module includes: The course acquisition submodule is used to obtain the course content of engineering majors based on the database, and at the same time obtain the students' learning progress, interests and needs, and build students' learning profiles; The environment recognition submodule is used to obtain the spatial information of various objects and surfaces in the environment through a depth camera and perform dynamic positioning.

3. The holographic training platform based on mixed reality according to claim 2, characterized in that: The course content includes but is not limited to: course text, 3D models, graphic data, experimental data, and measurement data; The student's learning progress, interests and needs include but are not limited to: the student's learning progress, behavior patterns, and interaction records.

4. The holographic training platform based on mixed reality according to claim 1, characterized in that: The data processing module comprises: The course content processing submodule is used to generate a course data set after identifying the characteristics of the course content of engineering majors, and at the same time combine the students' learning progress, interests and needs as labels with the course data set; The environmental data processing submodule is used to perform edge-aware image processing on the environmental data through a spatial filter, and then perform time smoothing and hole filling on the data to generate the environmental data set.

5. The holographic training platform based on mixed reality according to claim 1, characterized in that: The three-dimensional generation module includes: A classification submodule, used to classify the course data set according to course types to generate a classified data set; The three-dimensional model generation submodule is used to construct a three-dimensional model of each item in the classification data set based on the modeling software, and connect the constructed classification models through a topological structure to generate three-dimensional holographic course models of different scenes.

6. The holographic training platform based on mixed reality according to claim 1, characterized in that: The neural network building blocks include: Model building submodule, used to build convolutional neural network models; A model optimization submodule, used to construct a self-attention module and a residual module, and introduce the self-attention module and the residual module into the convolutional neural network model to generate an improved convolutional network; The training submodule is used to obtain a historical environment recognition data set, and train the improved convolutional network with the historical environment recognition data set to obtain an environmental feature recognition model. The neural network construction submodule is connected to the three-dimensional generation module and is used to construct a convolutional network model, and train the convolutional network model based on the historical data set to obtain a feature matching model.

7. The holographic training platform based on mixed reality according to claim 1, characterized in that: The matching calculation module includes: An environmental feature generation submodule is used to input the environmental data set into the environmental feature recognition model for processing through multiple convolutional layers and fully connected layers, map the generated features to a target feature space that matches the teaching environment, and generate the teaching environment features; The matching submodule is used to match the three-dimensional holographic course model with the teaching environment characteristics, and to superimpose the three-dimensional holographic course model in the real scene based on the matching result to generate an MR course model. The import submodule is used to import the MR course model into the MR device to generate an MR training course import device.

8. The holographic training platform based on mixed reality according to claim 1, characterized in that: The access module comprises: The collaborative access submodule is used to connect students and instructors to a virtual environment based on the MR training course import device to simulate different operations and situations to demonstrate the connection between theory and practice; The feedback module is used to give feedback based on students' operations, interactions and simulation results.

Images