Intelligent guiding system for putting on and taking off protective clothing based on virtual reality technology

Abstract

The invention belongs to the field of virtual reality technology and medical training cross technology, and particularly relates to a protective clothing wearing and taking-off intelligent guidance system based on virtual reality technology, which comprises hardware equipment and a software module, the data acquisition module is used for providing an immersive scene and acquiring student action data according to the head-mounted VR equipment and the data glove; the calculation and storage unit is used for supporting real-time action data processing and 3D scene rendering by adopting an edge calculation terminal; and a cloud database is provided for storing protective clothing putting-on and taking-off standard processes corresponding to different pathogens, an action feature library and trainee training data. According to the invention, the multi-scene standardized wearing and taking-off process is output through the high-fidelity 3D animation, and the multi-language switching and the adaptive design of the barrier user are combined, so that the medical staff with different language backgrounds and body conditions can efficiently receive the unified and standard training content.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of virtual reality technology and medical training, in particular to a protective clothing dressing and undressing intelligent guidance system based on virtual reality technology. BACKGROUND

[0002] In the prevention and control of infectious diseases, especially in the face of highly pathogenic pathogens (such as COVID-19, Ebola virus, etc.), correct dressing and undressing of protective clothing is a crucial link to protect the lives of medical personnel - according to the World Health Organization (WHO) report in 2023, the number of medical staff infections caused by improper dressing and undressing of protective clothing accounts for 38% of the total number of occupational exposure cases.

[0003] However, the existing protective clothing dressing and undressing training system has the following defects that cannot be ignored, which is difficult to meet the training needs in high-risk scenarios:

[0004] 1. Limited training mode and high risk: The current mainstream training relies on "instructor on-site demonstration + student real operation", which consumes a large number of physical protective clothing (each set of medical N95 protective clothing costs about 80-150 yuan, and a certain first-class hospital consumes more than 500 sets of protective clothing for a single training), and cannot be carried out anytime and anywhere; Special period prone to cluster infection.

[0005] 2. Lack of standardization and consistency: There are significant differences in teaching details among different instructors, for example: internal medicine instructors require "wearing protective masks first, then wearing gloves", and infectious disease instructors require "wearing gloves first, then adjusting masks", resulting in 42% of new medical staff in a certain hospital having "disorderly wearing sequence of protective masks"; and the learning effect of students is greatly affected by the experience of instructors, and the examination of a medical alliance in a certain area shows that the compliance rate of dressing and undressing standards of students from different hospitals differs by 35%.

[0006] 3. Lack of immediate feedback and error correction mechanism: In real person practice, the subtle errors of students (such as "protective clothing sleeve does not completely wrap around the wrist of the glove" and "fingers touch the lens when removing goggles") are difficult to be captured by the naked eye in real time, and it is extremely difficult to correct after forming muscle memory - according to the tracking data of a certain CDC, 23% of medical staff still have "exposure risk in the process of removing and taking off" due to early error operation without correction.

[0007] 4. Strong subjectivity of examination and lack of quantitative basis: Traditional examination relies on the subjective judgment of the examiner, for example: the same student's dressing and undressing operation is judged as "qualified" (considering that "the action is slow but there is no key error") by A examiner, and as "unqualified" (considering that "it takes more than 1 minute and the details are not standardized") by B examiner; and the examination result only records "qualified / unqualified", and cannot provide quantitative data such as "error step type" and "time consumption of each link", which is not conducive to managers to evaluate the overall training quality.

[0008] In summary, traditional protective clothing donning and doffing training cannot meet the "standardized, immersive, and intelligent" requirements for the prevention and control of highly pathogenic pathogens. Therefore, an intelligent guidance system for donning and doffing protective clothing based on virtual reality technology has been invented. Summary of the Invention

[0009] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0010] A smart guidance system for donning and doffing protective clothing based on virtual reality technology includes hardware devices and software modules. The hardware devices include:

[0011] The VR display and interaction unit is used to provide immersive scenes and collect student motion data based on head-mounted VR devices and data gloves;

[0012] The computing and storage unit is used to support real-time motion data processing and 3D scene rendering using edge computing terminals; and is equipped with a cloud database to store standard procedures for donning and doffing protective clothing for different pathogens, motion feature libraries and trainee training data.

[0013] The software module includes:

[0014] The standard process visualization module is used to integrate the standard procedures for putting on and taking off protective clothing in different scenarios of prevention and control of highly pathogenic pathogens using 3D animation. It also provides scene selection, tutorial playback, and autonomous control functions to intuitively present key operational details and ensure that users establish a unified standard understanding.

[0015] The multilingual and accessibility adaptation module is used to provide real-time multilingual switching based on standard process content, and to design differentiated adaptation solutions for hearing-impaired and visually-impaired users, while also supporting regional protection standard adaptation.

[0016] The multimodal action recognition and feedback module is used to acquire user operation data through action acquisition devices, and compare it in real time with a deep learning model and a standard action library to identify the compliance of the operation; and for erroneous operations, it provides multi-dimensional real-time feedback through vision, touch and voice to guide users to correct errors.

[0017] The personalized training model module is used to analyze the students' skill weaknesses based on their historical training data and automatically generate personalized training plans; it also supports difficulty gradient adjustment, from novice mode to expert mode, to gradually improve the students' operational proficiency.

[0018] The emergency scenario simulation module is used to simulate sudden and emergency decision-making scenarios during the process of putting on and taking off protective clothing. It matches the difficulty of the scenario with the user's basic skill level, provides standardized emergency handling guidelines and collaborative simulation training, and evaluates the correctness and timeliness of the user's emergency operations.

[0019] The remote collaborative guidance module supports experts to remotely access trainees' VR scenes, view trainees' operation process in real time, and guide trainees through virtual annotations; it can also organize multi-person collaborative training to improve teamwork capabilities without the need for physical space gathering.

[0020] The training effectiveness tracking and review module integrates historical data from multiple modules, generates a skills mastery trend chart, predicts skills forgetting points based on the Ebbinghaus forgetting curve and triggers retraining reminders; it also outputs multi-dimensional review reports to support long-term skills management.

[0021] The quantitative assessment and data management module is used to set assessment standards based on long-term training data, conduct standardized assessments, and generate objective assessment reports; it also stores training data throughout the entire process, supporting user queries and group analysis by managers.

[0022] As a preferred embodiment of the intelligent guidance system for donning and doffing protective clothing based on virtual reality technology described in this invention, the multilingual and accessibility adaptation module includes:

[0023] The multilingual real-time switching module supports multiple mainstream languages, allowing for instant switching within VR scenes via voice commands or gestures. The subtitles, voice broadcasts, and error prompts of 3D animation tutorials are also updated synchronously.

[0024] The accessibility adaptation module is designed to first enhance visual and tactile feedback for hearing-impaired users; then, for visually impaired users, it adds an enhanced voice navigation mode, and the data gloves add tactile positioning points.

[0025] The regional content adaptation module is used to automatically adjust the standard process details based on the user's location.

[0026] As a preferred embodiment of the intelligent guidance system for donning and doffing protective clothing based on virtual reality technology described in this invention, the multimodal motion recognition and feedback module includes:

[0027] The action recognition module uses a CNN+LSTM deep learning model to combine action data from the data glove with eye-tracking data from the VR device to compare student actions with a standard action feature library in real time.

[0028] The real-time feedback module is used to provide simultaneous reminders through visual, tactile, and voice feedback when an error is identified.

[0029] As a preferred embodiment of the intelligent guidance system for donning and doffing protective clothing based on virtual reality technology described in this invention, the emergency scenario simulation module includes:

[0030] A multi-type emergency scenario generation module is used to build in a variety of high-frequency emergency scenarios, which can be activated by random triggering or autonomous selection.

[0031] The Emergency Response Standardization Guidelines module is used to provide WHO-recommended standardized procedures for each emergency scenario, and demonstrates them in real time through 3D animation, while also supporting slow-motion playback and annotation of key steps.

[0032] As a preferred embodiment of the intelligent guidance system for donning and doffing protective clothing based on virtual reality technology described in this invention, the emergency scenario simulation module further includes:

[0033] The emergency decision-making training module is used to set up selective interactions in scenarios;

[0034] The emergency collaboration simulation module is used in conjunction with the remote collaboration guidance module to simulate multi-person emergency cooperation scenarios, and trainees are required to complete the collaborative operation within a specified time.

[0035] As a preferred embodiment of the intelligent guidance system for donning and doffing protective clothing based on virtual reality technology described in this invention, the training effect tracking and review module includes:

[0036] The long-term data tracking module is used to automatically generate skill mastery trend charts based on the historical data of trainees stored in the cloud database.

[0037] The forgetting curve analysis module uses the Ebbinghaus forgetting curve algorithm, combined with the training interval of trainees, to predict skill forgetting points and automatically trigger retraining reminders.

[0038] As a preferred embodiment of the intelligent guidance system for donning and doffing protective clothing based on virtual reality technology described in this invention, the training effect tracking and review module further includes:

[0039] The multi-dimensional review report module is used to generate monthly / quarterly review reports and compare individual skill changes with the department's average level.

[0040] The automatic retraining plan generation module is used to generate customized retraining plans by calling the basic algorithm of the personalized training model module for areas with a high risk of skill degradation or forgetting.

[0041] Compared with existing technologies:

[0042] 1. By outputting standardized donning and doffing procedures in multiple scenarios using high-fidelity 3D animation, and combining multi-language switching and design for adaptability to users with disabilities, it has the advantage of enabling medical personnel with different language backgrounds and physical conditions to efficiently receive unified and standardized training content;

[0043] 2. By linking motion capture devices with deep learning models to conduct real-time motion comparison, and with multi-dimensional error feedback including vision, touch, and voice, it has the advantages of replacing manual monitoring, correcting operational deviations in a timely manner, and helping users form muscle memory for correct operation.

[0044] 3. By analyzing users' historical practice data to identify skill weaknesses, it automatically generates specialized training plans and matches them with difficulty levels. This has the advantage of enabling customized training that moves from a "one-size-fits-all" approach to precisely addressing weaknesses, thereby improving individual training efficiency.

[0045] 4. By simulating emergency scenarios of donning and doffing protective clothing, matching the difficulty of the scenarios with the user's basic skills, and providing standardized handling guidelines, it has the advantage of extending routine training to actual combat response and improving the emergency response capabilities of medical personnel in high-risk scenarios;

[0046] 5. By supporting users to initiate remote guidance requests on demand, it allows experts to access VR scenes to conduct annotation explanations and action demonstrations, which has the advantages of breaking spatial limitations, solving the problem of insufficient expert resource coverage, and providing users with instant professional support;

[0047] 6. By integrating training data from multiple modules to generate skill trend charts, and combining them with forgetting curves to trigger retraining reminders and output review reports, it has the advantages of enabling long-term tracking of skill changes, avoiding post-learning forgetting, and forming a closed loop of "training-review-retraining" consolidation;

[0048] 7. By setting assessment standards and recording quantitative indicators based on full-process data, generating objective reports and storing data to support group analysis, it has the advantages of replacing subjective assessment, ensuring fair and traceable evaluation, and feeding back into the optimization and training of preceding modules.

[0049] 8. By leveraging data from various modules, training, practice, and guidance can be conducted in a virtual environment, completely avoiding the risk of cross-infection in offline gatherings and ensuring training safety. At the same time, training can be conducted without relying on physical protective clothing, eliminating the consumption of physical resources. Attached Figure Description

[0050] Figure 1 This is a schematic diagram of the overall framework of the present invention;

[0051] Figure 2 This is a schematic diagram of the multilingual and accessibility adaptation module framework of the present invention;

[0052] Figure 3 This is a schematic diagram of the framework of the multimodal action recognition and feedback module of the present invention;

[0053] Figure 4 This is a schematic diagram of the emergency scenario simulation module framework of the present invention;

[0054] Figure 5 This is a schematic diagram of the training effect tracking and review module framework of the present invention. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0056] This invention provides an intelligent guidance system for putting on and taking off protective clothing based on virtual reality technology. Please refer to [link / reference]. Figures 1-5 It includes hardware devices and software modules, wherein the hardware devices include:

[0057] The VR display and interaction unit is used to provide immersive scenes and collect student motion data based on head-mounted VR devices and data gloves;

[0058] The computing and storage unit is used to support real-time motion data processing and 3D scene rendering using edge computing terminals; and is equipped with a cloud database to store the standard procedures for putting on and taking off protective clothing, motion feature library and trainee training data for different pathogens (COVID-19, Ebola, etc.).

[0059] The software module includes:

[0060] The standard process visualization module is used to integrate the standard procedures for putting on and taking off protective clothing in different highly pathogenic pathogen prevention and control scenarios (such as COVID-19 and Ebola) using 3D animation as a carrier. It provides scene selection, tutorial playback, and autonomous control (pause / slow motion / jump) functions to intuitively present key operational details (such as seal check and wearing sequence) and ensure that users establish a unified standard understanding.

[0061] The multilingual and accessibility adaptation module is used to provide real-time multilingual switching based on standard process content, and to design differentiated adaptation solutions for hearing-impaired and visually-impaired users, while also supporting regional protection standard adaptation.

[0062] The multimodal action recognition and feedback module is used to acquire user operation data through action acquisition devices, and compare it in real time with a deep learning model and a standard action library to identify the compliance of the operation; and for erroneous operations, it provides multi-dimensional real-time feedback through vision, touch and voice to guide users to correct errors.

[0063] The personalized training model module analyzes students' skill weaknesses based on their historical training data (error type, error frequency, and time spent on each step), and automatically generates personalized training plans. For example, for students who frequently make mistakes in removing and removing goggles, it adds "specific training on goggle removal"; for students who seriously exceed the time limit, it optimizes "time allocation guidance for key steps"; and it supports difficulty gradient adjustment, from novice mode (with real-time step prompts) to expert mode (no prompts and must be completed within a specified time), gradually improving students' operational proficiency.

[0064] The emergency scenario simulation module is used to simulate sudden and emergency decision-making scenarios during the process of putting on and taking off protective clothing. It matches the difficulty of the scenario with the user's basic skill level, provides standardized emergency handling guidelines and collaborative simulation training, and evaluates the correctness and timeliness of the user's emergency operations.

[0065] The remote collaborative guidance module supports experts to remotely access trainees' VR scenes, view trainees' operation processes in real time, and guide trainees through virtual annotations (such as drawing the correct action trajectory in the VR scene); it can also organize multi-person collaborative training (such as simulating the scenario of "medical staff cooperating in putting on and taking off protective clothing"), improve teamwork ability, and does not require physical space gathering.

[0066] The training effectiveness tracking and review module integrates historical data from multiple modules, generates a skills mastery trend chart, predicts skills forgetting points based on the Ebbinghaus forgetting curve and triggers retraining reminders; it also outputs multi-dimensional review reports to support long-term skills management.

[0067] The quantitative assessment and data management module is used to set assessment standards based on long-term training data, conduct standardized assessments, and generate objective assessment reports; it also stores training data throughout the entire process, supporting user queries and group analysis by managers.

[0068] The multilingual and accessibility adaptation module includes:

[0069] The multilingual real-time switching module supports multiple mainstream languages ​​(including Chinese, English, Spanish, Arabic, etc.) to enable instant switching within VR scenes via voice commands (such as "switch to English") or gesture operations (such as "make an 'L' sign with both hands"). The subtitles, voice broadcasts, and error prompts of the 3D animation tutorials are updated synchronously. For example, after switching to Arabic, the voice broadcast and text prompt for "Error: Gloves not covered by cuffs" are changed to Arabic, and the direction of the operation guide arrows in the 3D animation is adapted to the right-to-left reading habit of Arabic.

[0070] The accessibility module is designed to first enhance visual feedback for hearing-impaired users (e.g., in addition to highlighting and flashing error messages, a floating window with "error type icon + text description" is added, and the flashing frequency is increased to 2 times / second) and tactile feedback (the vibration intensity of the data gloves is increased by 30%, and the vibration mode is bound to the error type—e.g., "protective clothing damaged" corresponds to continuous vibration of the palm, and "glove worn incorrectly" corresponds to intermittent vibration of the fingers). Next, for visually impaired users, an enhanced voice navigation mode is added (e.g., "distance prompts" are added to each step in 3D scenes, such as "You are currently 0.5 meters away from the protective clothing placement platform, and the glove storage box is 10 centimeters to your left"), and tactile positioning points are added to the data gloves (e.g., the fingertips of the gloves have built-in protrusions; when touching virtual devices in VR scenes, the protrusions will correspond to the device type—"When touching the goggles, the index finger protrusion vibrates").

[0071] The regionalized content adaptation module is used to automatically adjust the details of standard procedures according to the user's region (such as adapting to the differences in WHO protection guidelines in different regions—for Africa, a special tutorial on "wearing boot covers for double protection" is added; for Europe, "FPP2 mask wearing guidelines" are added).

[0072] The multimodal action recognition and feedback module includes:

[0073] The action recognition module uses a CNN+LSTM deep learning model to combine action data from data gloves with eye-tracking data from VR devices to compare trainees' actions with a standard action feature library in real time (such as "when removing goggles, the distance between fingers and the goggles must be ≥5cm" and "after wearing protective clothing, there is no exposed area on any part of the body").

[0074] The real-time feedback module is used to provide simultaneous reminders when errors are identified through visual feedback (the error area is highlighted and flashed in the VR scene, such as "a red warning box is displayed where the cuff does not cover the glove"), tactile feedback (the corresponding finger vibrates when the data glove is touched, such as "the index finger vibrates 3 times when the goggles are touched"), and voice feedback (the system announces the error type and correction method, such as "Error: The cuff is not covered by the glove at the wrist. Please pull the cuff of the protective suit up to cover the glove at the wrist").

[0075] The emergency scenario simulation module includes:

[0076] A multi-type emergency scenario generation module is used to build in various high-frequency emergency scenarios, which can be activated randomly or by user selection, including:

[0077] Unexpected scenarios during donning and doffing: such as "the zipper is broken when putting on protective clothing", "the lenses fog up when wearing goggles", "sneezing suddenly when removing a mask";

[0078] Scenarios of protective failure: such as "torn cuffs of protective clothing", "torn fingertips of gloves", "loose face shield";

[0079] The Emergency Response Standardization Guidance Module is used to provide WHO-recommended standardized procedures for each emergency scenario and demonstrate them in real time through 3D animation (e.g., in the scenario of "broken zipper on protective clothing", the animation demonstrates "first stop putting on and taking off the protective clothing, seal the broken zipper with waterproof tape, then report to the infection control specialist and assess whether to replace the protective clothing"), and supports slow-motion playback and annotation of key steps.

[0080] The emergency decision-making training module is used to set up interactive choices in scenarios, such as "After discovering that the glove is torn, the system provides two options: ① immediately remove and put on the gloves again ② temporarily treat the tear with sealing tape and continue working". After the trainee makes a choice, the system immediately provides feedback on whether the choice is correct or not (e.g., when choosing ②, it prompts "Error: The torn gloves are a critical protective failure and must be removed and put on immediately to avoid skin exposure") and analyzes the basis for the decision.

[0081] The emergency collaboration simulation module is used in conjunction with the remote collaboration guidance module to simulate multi-person emergency cooperation scenarios (such as "one medical staff member's protective clothing is damaged, and another medical staff member assists them in properly removing and replacing the protective clothing"). Trainees are required to complete the collaborative operation within a specified time and evaluate indicators such as the smoothness of cooperation, emergency handling time, and error rate.

[0082] The training effectiveness tracking and review module includes:

[0083] The long-term data tracking module is used to automatically generate a skills mastery trend chart based on the trainees' historical data (monthly error types, time changes, and assessment scores) stored in the cloud database. For example, it can show that "the error rate of removing goggles has decreased from 25% in the first training to 2% in the third month", or "the overtime rate has increased from 15% to 8% (indicating skill degradation)".

[0084] The forgetting curve analysis module uses the Ebbinghaus forgetting curve algorithm, combined with the training interval, to predict skill forgetting points (e.g., "30 days after the last training, the error rate of the 'protective clothing sealing inspection' step is expected to increase by 10%), and automatically triggers retraining reminders (e.g., the system pushes "Your protective clothing sealing inspection skill needs retraining, click to enter the special practice").

[0085] The multi-dimensional review report module is used to generate monthly / quarterly review reports and compare individual skill changes with the department's average level. For example, the report may indicate that "your 'putting on gloves' process takes 5 seconds faster than the department's average, but your 'removing protective clothing' error rate is 3% higher than the department's average. It is recommended to focus on retraining the removal process."

[0086] The automatic retraining plan generation module is used to generate customized retraining plans by calling the basic algorithm of the personalized training model module for areas with a high risk of skill degradation or forgetting (such as "retraining for 'emergency handling of damaged protective clothing', which includes 3 scenario simulations + 2 assessments").

[0087] In practical use, the specific steps are as follows:

[0088] S1 integrates the standard process of donning and doffing protective clothing in different scenarios of prevention and control of highly pathogenic pathogens through a standard process visualization module using 3D animation. It also provides scene selection, tutorial playback, and autonomous control functions to intuitively present key operational details and ensure that users establish a unified standard understanding.

[0089] S2 provides real-time multilingual switching based on standard process content through multilingual and accessibility adaptation modules, and designs differentiated adaptation solutions for hearing-impaired and visually-impaired users, while also supporting regional protection standard adaptation.

[0090] S3 uses a multimodal motion recognition and feedback module to acquire user operation data through motion acquisition devices, and compares it in real time with a deep learning model and a standard motion library to identify the compliance of the operation; and for erroneous operations, it provides multi-dimensional real-time feedback through vision, touch and voice to guide users to correct errors.

[0091] S4 uses a personalized training model module to analyze students' skill weaknesses based on their historical training data and automatically generate personalized training plans. It also supports difficulty gradient adjustment, gradually improving students' operational proficiency from novice mode to expert mode.

[0092] S5 uses an emergency scenario simulation module to simulate unexpected and emergency decision-making scenarios during the donning and doffing of protective clothing. It matches the difficulty of the scenarios with the user's basic skill level, provides standardized emergency handling guidelines and collaborative simulation training, and evaluates the correctness and timeliness of the user's emergency operations.

[0093] The S6 supports remote access to trainees' VR scenes through the remote collaborative guidance module, allowing experts to view trainees' operation process in real time and provide guidance to trainees through virtual annotations; it can also organize multi-person collaborative training to improve teamwork capabilities without the need for physical space gathering.

[0094] S7 integrates historical data from multiple modules through the training effectiveness tracking and review module, generates a skills mastery trend chart, predicts skills forgetting points based on the Ebbinghaus forgetting curve and triggers retraining reminders; and outputs multi-dimensional review reports to support long-term skills management.

[0095] S8 uses a quantitative assessment and data management module to set assessment standards based on long-term training data, conduct standardized assessments, and generate objective assessment reports; it also stores training data throughout the entire process, supporting user queries and manager group analysis.

[0096] Although the present invention has been described above with reference to embodiments, various modifications can be made and components can be replaced with equivalents without departing from the scope of the invention. In particular, as long as there is no structural conflict, the features in the disclosed embodiments can be combined with each other in any manner. The lack of an exhaustive description of these combinations in this specification is merely for the sake of brevity and resource conservation. Therefore, the present invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A smart guidance system for donning and doffing protective clothing based on virtual reality technology, comprising hardware devices and software modules, characterized in that, The hardware device includes: The VR display and interaction unit is used to provide immersive scenes and collect student motion data based on head-mounted VR devices and data gloves; The computing and storage unit is used to support real-time motion data processing and 3D scene rendering using edge computing terminals; and is equipped with a cloud database to store standard procedures for donning and doffing protective clothing for different pathogens, motion feature libraries and trainee training data. The software module includes: The standard process visualization module is used to integrate the standard procedures for putting on and taking off protective clothing in different scenarios of prevention and control of highly pathogenic pathogens using 3D animation. It also provides scene selection, tutorial playback, and autonomous control functions to intuitively present key operational details and ensure that users establish a unified standard understanding. The multilingual and accessibility adaptation module is used to provide real-time multilingual switching based on standard process content, and to design differentiated adaptation solutions for hearing-impaired and visually-impaired users, while also supporting regional protection standard adaptation. The multimodal action recognition and feedback module is used to acquire user operation data through action acquisition devices, and compare it in real time with a deep learning model and a standard action library to identify the compliance of the operation; and for erroneous operations, it provides multi-dimensional real-time feedback through vision, touch and voice to guide users to correct errors. The personalized training model module is used to analyze the students' skill weaknesses based on their historical training data and automatically generate personalized training plans; it also supports difficulty gradient adjustment, from novice mode to expert mode, to gradually improve the students' operational proficiency. The emergency scenario simulation module is used to simulate sudden and emergency decision-making scenarios during the process of putting on and taking off protective clothing. It matches the difficulty of the scenario with the user's basic skill level, provides standardized emergency handling guidelines and collaborative simulation training, and evaluates the correctness and timeliness of the user's emergency operations. The remote collaborative guidance module supports experts to remotely access trainees' VR scenes, view trainees' operation process in real time, and guide trainees through virtual annotations; it can also organize multi-person collaborative training to improve teamwork capabilities without the need for physical space gathering. The training effectiveness tracking and review module integrates historical data from multiple modules, generates a skills mastery trend chart, predicts skills forgetting points based on the Ebbinghaus forgetting curve and triggers retraining reminders; it also outputs multi-dimensional review reports to support long-term skills management. The quantitative assessment and data management module is used to set assessment standards based on long-term training data, conduct standardized assessments, and generate objective assessment reports; it also stores training data throughout the entire process, supporting user queries and group analysis by managers.

2. The intelligent guidance system for putting on and taking off protective clothing based on virtual reality technology according to claim 1, characterized in that, The multilingual and accessibility adaptation module includes: The multilingual real-time switching module supports multiple mainstream languages, allowing for instant switching within VR scenes via voice commands or gestures. The subtitles, voice broadcasts, and error prompts of 3D animation tutorials are also updated synchronously. The accessibility adaptation module is designed to first enhance visual and tactile feedback for hearing-impaired users; then, for visually impaired users, it adds an enhanced voice navigation mode, and the data gloves add tactile positioning points. The regional content adaptation module is used to automatically adjust the standard process details based on the user's location.

3. The intelligent guidance system for putting on and taking off protective clothing based on virtual reality technology according to claim 1, characterized in that, The multimodal action recognition and feedback module includes: The action recognition module uses a CNN+LSTM deep learning model to combine action data from the data glove with eye-tracking data from the VR device to compare student actions with a standard action feature library in real time. The real-time feedback module is used to provide simultaneous reminders through visual, tactile, and voice feedback when an error is identified.

4. The intelligent guidance system for putting on and taking off protective clothing based on virtual reality technology according to claim 1, characterized in that, The emergency scenario simulation module includes: A multi-type emergency scenario generation module is used to build in a variety of high-frequency emergency scenarios, which can be activated by random triggering or autonomous selection. The Emergency Response Standardization Guidelines module is used to provide WHO-recommended standardized procedures for each emergency scenario, and demonstrates them in real time through 3D animation, while also supporting slow-motion playback and annotation of key steps.

5. The intelligent guidance system for putting on and taking off protective clothing based on virtual reality technology according to claim 4, characterized in that, The emergency scenario simulation module also includes: The emergency decision-making training module is used to set up selective interactions in scenarios; The emergency collaboration simulation module is used in conjunction with the remote collaboration guidance module to simulate multi-person emergency cooperation scenarios, and trainees are required to complete the collaborative operation within a specified time.

6. The intelligent guidance system for putting on and taking off protective clothing based on virtual reality technology according to claim 1, characterized in that, The training effectiveness tracking and review module includes: The long-term data tracking module is used to automatically generate skill mastery trend charts based on the historical data of trainees stored in the cloud database. The forgetting curve analysis module uses the Ebbinghaus forgetting curve algorithm, combined with the training interval of trainees, to predict skill forgetting points and automatically trigger retraining reminders.

7. The intelligent guidance system for putting on and taking off protective clothing based on virtual reality technology according to claim 6, characterized in that, The training effectiveness tracking and review module also includes: The multi-dimensional review report module is used to generate monthly / quarterly review reports and compare individual skill changes with the department's average level. The automatic retraining plan generation module is used to generate customized retraining plans by calling the basic algorithm of the personalized training model module for areas with a high risk of skill degradation or forgetting.

Images