Automatic teaching method, system and equipment for cardio-pulmonary resuscitation, medium and product

Abstract

The invention discloses an automatic teaching method, system and device for cardio-pulmonary resuscitation, a medium and a product, and relates to the field of medical teaching, and the system comprises a video monitoring module, an action analysis module, a content display module, a voice broadcast module and an automatic score counting module. Comprehensive monitoring, real-time feedback and automatic examination of the cardio-pulmonary resuscitation operation of the trainee are achieved through the automation technology, and the system has the advantages of being efficient, accurate, capable of reducing manual dependence and the like.

Description

Technical Field

[0001] The present application relates to the field of medical teaching, and in particular to an automatic teaching method, system, equipment, medium and product for cardiopulmonary resuscitation. Background Art

[0002] Cardiopulmonary resuscitation (CPR) is a vital skill in first aid that can save lives in cardiac arrest situations. However, correctly performing CPR requires precise movements and appropriate pressure. Traditional CPR training typically relies on CPR simulators and on-site supervision by instructors. CPR simulators can provide feedback on the strength and frequency of the trainee's compressions, but they are typically unable to monitor the trainee's overall movements and on-site hand signals for help.

[0003] Traditional CPR training still has the following problems:

[0004] Limited monitoring capabilities: The current all-in-one machine connects to the CPR simulator via Bluetooth and can only receive data provided by the simulator, such as compression depth and frequency, but cannot monitor the student's overall movements and gestures.

[0005] Reliance on manual guidance: Since it is impossible to monitor the trainees’ movements, the training process must rely on the guidance of on-site teachers. This may limit the training efficiency and quality when teacher resources are limited.

[0006] Lack of real-time feedback: When students perform CPR, if their movements are inaccurate or their gestures are incorrect, they cannot get immediate feedback and correction. Summary of the Invention

[0007] The purpose of this application is to provide an automatic teaching method, system, equipment, medium and product for cardiopulmonary resuscitation, which can realize real-time monitoring, guidance and assessment of students' cardiopulmonary resuscitation operations through automation technology.

[0008] To achieve the above objectives, this application provides the following solutions:

[0009] In a first aspect, the present application provides an automatic teaching system for cardiopulmonary resuscitation, comprising:

[0010] Video monitoring module, used to capture trainees' operation images in real time through cameras;

[0011] An action analysis module is used to process the operation image through a deep learning algorithm to determine whether the trainee's operation action is correct and obtain a first judgment result;

[0012] a content display module, configured to display the first judgment result, and display a teaching video when the first judgment result is negative;

[0013] A voice announcement module, configured to provide a voice prompt when the first judgment result is no, the prompt content including the error type and correction method;

[0014] The automatic scoring module is used to score students based on their operational performance and calculate the final scores.

[0015] In a second aspect, the present application provides an automatic teaching method for cardiopulmonary resuscitation, comprising:

[0016] Capture students’ operation images in real time through cameras;

[0017] Processing the operation image through a deep learning algorithm to determine whether the trainee's operation action is correct, thereby obtaining a first judgment result;

[0018] Displaying the first judgment result, and displaying a teaching video when the first judgment result is negative;

[0019] When the first judgment result is no, a voice prompt is given, and the prompt content includes the error type and correction method;

[0020] Scoring is performed based on the first judgment result, and the final score is calculated.

[0021] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the automatic teaching method for cardiopulmonary resuscitation described in the second aspect above.

[0022] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the automatic teaching method for cardiopulmonary resuscitation described in the second aspect above.

[0023] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the automatic teaching method for cardiopulmonary resuscitation described in the second aspect above.

[0024] According to the specific embodiments provided in this application, this application has the following technical effects:

[0025] The present application provides an automatic teaching method, system, equipment, medium and product for cardiopulmonary resuscitation. The system includes a video monitoring module, a motion analysis module, a content display module, a voice broadcast module and an automatic scoring module. Through automation technology, it realizes comprehensive monitoring, real-time feedback and automated assessment of students' cardiopulmonary resuscitation operations, and has the advantages of high efficiency, accuracy and reduced manual dependence. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 A schematic diagram of the functional modules of an automatic teaching system for cardiopulmonary resuscitation provided in Example 1 of the present application;

[0028] Figure 2 This is a schematic diagram of a cardiopulmonary resuscitation test simulation in Example 1 of the present application;

[0029] Figure 3 This is a schematic diagram of the results of the cardiopulmonary resuscitation test simulation in Example 1 of the present application;

[0030] Figure 4 This is a schematic diagram of an implementation of an automatic teaching system for cardiopulmonary resuscitation in Example 2 of this application;

[0031] Figure 5 A schematic diagram of a flow chart of an automatic teaching method for cardiopulmonary resuscitation provided in Example 2 of the present application;

[0032] Figure 6 A schematic diagram of the structure of a computer device provided in Example 3 of the present application. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0034] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0035] Example 1

[0036] like Figure 1 As shown, this embodiment provides an automatic teaching system for cardiopulmonary resuscitation, including:

[0037] The video monitoring module is used to capture the trainees' operation images in real time through the camera.

[0038] The action analysis module is used to process the operation image through a deep learning algorithm to determine whether the trainee's operation action is correct and obtain a first judgment result.

[0039] The content display module is used to display the first judgment result and display the teaching video when the first judgment result is no.

[0040] The voice broadcast module is used to provide a voice prompt when the first judgment result is no, and the prompt content includes the error type and correction method.

[0041] The automatic scoring module is used to score according to the first judgment result and calculate the final score.

[0042] The camera lens control module is used to adjust the position and focal length of the camera to ensure a clear image of the trainee's operation.

[0043] The card swiping and certificate issuance module is used for student identity verification and certificate issuance.

[0044] This embodiment uses cameras, image processing technology and deep learning algorithms to achieve comprehensive monitoring, real-time feedback, guidance and automated assessment of trainees' cardiopulmonary resuscitation operations.

[0045] The following is a detailed description of the functional modules mentioned above:

[0046] (1) Video surveillance module

[0047] The video surveillance module is also used to determine whether there are students entering the monitoring area and perform facial recognition, which specifically includes:

[0048] An environment monitoring unit, configured to capture images of the surrounding environment through a camera group, wherein the monitoring area of ​​the camera group can cover all areas around the cardiopulmonary resuscitation simulator;

[0049] An image processing unit, configured to process the surrounding environment image using image processing technology to obtain a processed surrounding environment image;

[0050] A motion detection unit is configured to process the processed surrounding environment image based on a motion detection algorithm to determine whether a student has entered the monitoring area, and obtain a second determination result;

[0051] A face recognition unit is used to perform face recognition based on the processed surrounding environment image when the second judgment result is yes.

[0052] Specifically, the video monitoring module is composed of multiple high-resolution cameras with a wide-angle field of view that can cover all areas around the cardiopulmonary resuscitation simulator.

[0053] Function implementation:

[0054] Environmental monitoring: The camera captures a video stream of the surrounding environment at a fixed frame rate, ensuring comprehensive monitoring. The video stream is transmitted to the image processing unit via wired or wireless means.

[0055] Image processing: Use advanced image processing techniques, such as denoising and contrast enhancement, to improve image quality for subsequent analysis.

[0056] Motion detection: Through background subtraction or other motion detection algorithms, dynamic changes in the scene are identified in real time to determine whether any students have entered the monitored area.

[0057] The specific process of background subtraction:

[0058] 1. Initialize the background model

[0059] Fixed frame initialization: Select the first frame in the video sequence or the average of several consecutive frames as the background.

[0060] Statistical initialization: Use the average or median value of pixels over a period of time as the background.

[0061] Codebook method: Maintain a color model for each pixel, recording the color observed at different times and its frequency of occurrence.

[0062] 2. Update the background model

[0063] In order to adapt to environmental changes (such as lighting changes, background object movement, etc.), the background model needs to be updated regularly.

[0064] Time weighted average: Each updated background model is based on the weighted average of the current background model and the current frame.

[0065] Frame difference method: When the difference between a pixel and the background is less than the set threshold, the background model will be updated.

[0066] 3. Background Subtraction

[0067] Pixel comparison: For each pixel, compare the pixel value of the current frame with the background model.

[0068] Threshold segmentation: When the difference between the pixel value and the background model is greater than the set threshold, the pixel is marked as foreground.

[0069] 4. Post-processing

[0070] Morphological operations: Use dilation and erosion operations to remove noise and fill holes in foreground objects.

[0071] Connected component analysis: Group foreground pixels into connected regions and mark or track these regions.

[0072] Student identification: Use facial recognition technology to confirm the identity of students for subsequent teaching and assessment.

[0073] Face recognition technology implementation process:

[0074] The Adaboost algorithm is used to train the classifier and select the most effective features from a large number of Haar-like features to recognize faces.

[0075] 1) Initialization

[0076] Given a training set (x1,y1),(x2,y2),...,(x N ,y N ), where x i is the eigenvector, y i is the corresponding class label (usually +1 or -1).

[0077] Initialize sample weights w1,w2,...,w N , initially the weight of each sample is equal, that is, w i =1 / N.

[0078] 2) Loop Iteration

[0079] Multiple iterations are used to build a strong classifier, and each iteration trains a new weak classifier and adds it to the final model.

[0080] Step 1: Weight Normalization

[0081] Make sure that the sum of all sample weights is 1:

[0082]

[0083] Among them, w is the initialization weight and N is the number of training sets.

[0084] Step 2: Train weak classifiers

[0085] Use the training set with weights to train a weak classifier h t , which minimizes the weighted error rate:

[0086]

[0087] Where I is the indicator function, when y i ≠h(x i ) is 1, otherwise it is 0.

[0088] Step 3: Calculate classifier weights

[0089] According to the weak classifier h tThe performance on the training set is used to calculate its weight α in the final strong classifier t :

[0090]

[0091] Among them, h t is a weak classifier, α t is the classifier weight, ∈ t is the error rate of the weak classifier on the training set, that is, the proportion of samples with classification errors.

[0092] Step 4: Update sample weights

[0093] According to the classifier h t The performance of the updated sample weights is increased, the weight of the samples that are misclassified is increased, and the weight of the samples that are correctly classified is reduced:

[0094]

[0095] Among them, Z t is a normalization factor that ensures that the weights sum to 1.

[0096] 3) Combined weak classifiers

[0097] After T iterations, we get T weak classifiers h1,h2,...,h T and their corresponding weights α1,α2,...,α T Finally, the weighted sum of these weak classifiers is combined into a strong classifier H(x):

[0098]

[0099] Where sign(x) is the sign function, which returns +1 when x ≥ 0 and -1 when x < 0.

[0100] Cooperate with the camera lens control module:

[0101] When the video monitoring module detects that a student is approaching the simulator, it immediately sends a signal to the camera lens control module, instructing it to adjust the camera angle for the best viewing angle. At the same time, the video monitoring module transmits the video stream in real time to the motion analysis module for motion analysis.

[0102] 2. Camera lens control module

[0103] The camera control module specifically includes:

[0104] The optimal viewing angle calculation unit is used to calculate the optimal shooting angle according to the position of the trainee and the position of the simulator;

[0105] The angle adjustment unit is used to adjust the angles of the cameras in the camera group according to the optimal shooting angle.

[0106] Specifically, the camera lens control module is responsible for adjusting the position and focal length of the camera to ensure a clear picture of the student's operation.

[0107] Function implementation:

[0108] Motor Control: The module contains a sophisticated motor and gear system that allows precise control of the camera's horizontal and vertical movement, as well as focal length adjustment.

[0109] Optimal viewing angle calculation: The module has a built-in algorithm that calculates the best shooting angle based on the position of the trainee and the simulator to ensure the accuracy of motion analysis.

[0110] 2.1 Image Capture:

[0111] The camera first captures a live video stream or a still image.

[0112] 2.2 Preprocessing:

[0113] Images may be preprocessed, such as resizing, grayscale conversion, denoising, etc., to reduce computational complexity and improve the accuracy of subsequent processing.

[0114] 2.3 Human body detection:

[0115] Object detection algorithm: Use the SSD algorithm to identify human bodies and models in images.

[0116] Feature extraction: The algorithm searches the image for regions that match the features learned during training.

[0117] Bounding box generation: Once a person is detected close to the model, the SSD algorithm draws a bounding box around the person and the model and gives a confidence score.

[0118] 2.3.1SSD Algorithm Description:

[0119] 1. Select the base network: Select a pre-trained VGG16 convolutional neural network as the feature extractor, which is responsible for extracting rich features from the input image.

[0120] 2. Construct auxiliary feature map

[0121] On top of the last few convolutional layers of the base network, some additional convolutional layers are added to generate feature maps of different scales and resolutions for detecting objects of different sizes.

[0122] 3. Default box generation

[0123] For each location on each feature map, a series of default boxes of fixed ratios and scales are generated, which will cover different areas and object sizes in the image.

[0124] 4. Feature Extraction

[0125] The input image is forward propagated through the base network and auxiliary layers to generate a series of feature maps.

[0126] 5. Prediction

[0127] For each default box on each feature map, the network predicts a class probability and a bounding box offset. Class probability: The probability that the object belongs to each class. Bounding box offset: The position and size offset of the actual object bounding box relative to the default box.

[0128] 6. Loss Function

[0129] Calculate the loss function, which usually consists of category loss and positioning loss. Category loss uses cross entropy loss, and positioning loss uses smooth L1 loss.

[0130] The loss function formula is as follows:

[0131]

[0132] Among them, L conf is the class loss, L loc is the positioning loss, N is the number of positive default boxes, and α is the weight of the positioning loss.

[0133] x: represents the output predicted by the model.

[0134] c: represents class prediction.

[0135] l: represents location prediction (locationprediction).

[0136] g: represents the true label (groundtruth).

[0137] 7. Training

[0138] The network is trained using optimization methods such as backpropagation and gradient descent to update the network weights by minimizing the loss function.

[0139] 8. Prediction and post-processing

[0140] During testing, the network outputs the class probability and bounding box offset for each default box.

[0141] Non-maximum suppression (NMS) is applied to remove overlapping detection boxes and only retain the most likely detection results.

[0142] 9. Output test results

[0143] The algorithm outputs the category and precise bounding box location of each detected object.

[0144] Feedback mechanism: After the adjustment is completed, the module sends a confirmation signal to other modules, indicating that the camera is ready for the next operation.

[0145] Cooperate with the motion analysis module:

[0146] After receiving the signal from the video surveillance module, the camera lens control module responds quickly and adjusts the camera to the preset optimal angle.

[0147] After the adjustment is completed, the motion analysis module is notified to start motion capture and analysis.

[0148] 3. Motion Analysis Module

[0149] The motion analysis module specifically includes:

[0150] A human skeleton drawing unit, used to identify and draw human skeletons of trainees and simulators from operation images using a deep learning algorithm;

[0151] an action comparison unit, configured to determine whether the trainee's operation action is correct based on the human skeleton diagram, and obtain a first determination result;

[0152] Error recording unit, used to record the type and number of errors in students' operations

[0153] Specifically, the motion analysis module is the key to evaluating the correctness of trainees' operations. It guides trainees' training by analyzing the images captured by the camera.

[0154] Function implementation:

[0155] Human pose estimation: Using deep learning algorithms, the human skeleton of the trainee and the simulator is identified and drawn from the camera image.

[0156] Deep learning algorithm description:

[0157] 1. Pose Estimation

[0158] Feature extraction: The input image is forward propagated through the trained network to extract features. (See Image Capture Algorithm for more information.)

[0159] Key point prediction: Based on the network output and peak detection of the heat map, the location of each key point is determined.

[0160] The network outputs a series of heatmaps and keypoint coordinates. Each location in the heatmap represents the probability of being a keypoint, while the keypoint coordinates are absolute positions relative to the input image. The peak points in the heatmap represent the locations of keypoints. The network finds the location of each keypoint by applying a peak detection algorithm (such as argmax) to the heatmap. The height of the peak represents the network's confidence in the keypoint's location.

[0161] 2. Skeleton connection

[0162] Key point pairing: Based on the knowledge of human anatomy, the predicted key points are paired to form a skeleton.

[0163] Draw a skeleton diagram: Use line segments to connect paired key points to form a human skeleton diagram.

[0164] 3. Post-processing

[0165] Smoothing: Smoothing the skeleton graph to remove jitter and unnatural pose changes.

[0166] Time series processing: Perform time series analysis on the poses of consecutive frames to obtain smoother and more coherent skeletal animation.

[0167] 4. Output

[0168] Output the drawn skeleton diagram for further analysis or application.

[0169] Action comparison: Compare the trainee's actual actions with standard CPR actions to identify deviations in the operation.

[0170] Error Log: This module records the type and number of errors made by students, providing data support for personalized feedback. When students begin to operate the simulator, the motion analysis module analyzes their movements in real time and issues prompts when errors are detected.

[0171] Personalized feedback description: The system automatically announces errors and records the trainee's CPR errors. CPR qualification requires meeting certain specific data, such as compression frequency per minute: 100-120 times; each compression depth: 50-60mm; compression-to-air ratio: 30:2; each airflow volume: 500-600ml; number of cycles: 5 times, etc. Specific parameters can be found in Figure 3 ,After the students complete the cycle, the above parameters will be automatically output and fed back to the students.

[0172] Collaboration with the Content Display Module: The motion analysis module transmits analysis results in real time to the Content Display Module and the Voice Broadcast Module. The Content Display Module uses these results to draw a skeleton diagram and real-time motions on the screen, while the Voice Broadcast Module provides immediate feedback based on the type of error. If an error is detected, the motion analysis module directs the Content Display Module to the appropriate instructional video.

[0173] 4. Content display module

[0174] The content display module is the key interface for students to interact with the device. It is responsible for displaying teaching content, real-time feedback and operation guides, such as Figure 2 and Figure 3 As shown, the content display module displays a schematic diagram of a cardiopulmonary resuscitation simulation test and the results of the cardiopulmonary resuscitation simulation test.

[0175] Function implementation:

[0176] Teaching page display: When the camera control module detects that the trainee raises his hand, the content display module immediately jumps to the training practice page; the basic steps, key points and precautions of cardiopulmonary resuscitation are displayed, providing students with a clear operation guide.

[0177] Real-time feedback drawing: Using the data collected by the camera and the results of the motion analysis module, the human skeleton diagram of the trainee and the simulator is drawn on the screen; the trainee's movements are displayed in real time, and the correctness of the movements is indicated by highlighting or color changes.

[0178] Guidance on incorrect movements: When the movement analysis module detects an incorrect movement, the content display module responds quickly and jumps to the corresponding teaching video page; it shows the correct movement demonstration to help students understand and correct the mistakes.

[0179] Operation reminder: After students finish watching the teaching video, the content display module provides operation reminders to guide students to continue practical exercises.

[0180] Results display: After the trainee completes 5 sets of cardiopulmonary resuscitation operations, the content display module will display the results calculated by the automatic scoring module; if the trainee passes, the pass message will be displayed; if the trainee fails, the fail message will be displayed and improvement suggestions will be given.

[0181] Coordination between modules: Closely cooperate with the motion analysis module and voice broadcast module to provide visual feedback and operation guidance based on the analysis results; during the trainee's operation, continuously receive the video stream from the camera control module to ensure the accuracy of real-time feedback.

[0182] 5. Voice broadcast module

[0183] The voice broadcast module provides students with instant feedback and guidance through voice prompts, enhancing interactivity and teaching effectiveness.

[0184] Function implementation:

[0185] Operation start prompt: When the trainee raises his hand to start training, the voice broadcast module will issue a prompt sound to start training.

[0186] Incorrect action prompts: Based on the results of the action analysis module, when a student makes an error in their action, the voice broadcast module will immediately issue a corresponding error prompt; the prompt content includes the error type and correction method, helping students to adjust their actions in time.

[0187] Teaching videos are accompanied by explanations: During the playback of teaching videos, the voice broadcast module provides voice explanations of the video content to enhance the learning effect.

[0188] Operation completion prompt: After the student completes the operation, the voice broadcast module will prompt the student whether the operation is completed and whether it has passed based on the results of the automatic scoring module.

[0189] Interactive guidance: During the entire training process, the voice broadcast module provides voice guidance of the operation steps to ensure that students follow the correct process.

[0190] Inter-module coordination: Works synchronously with the content presentation module to provide an audio-visual teaching experience; adjusts the broadcast content in a timely manner based on the analysis results of the action analysis module to ensure the accuracy and timeliness of feedback.

[0191] 6. Automatic classification module

[0192] The automatic scoring module is responsible for scoring students based on their operational performance and calculating the final scores.

[0193] Function implementation:

[0194] Action scoring: Based on the action data provided by the action analysis module, the automatic scoring module applies the preset scoring criteria to score; the scoring criteria cover all key steps and action essentials of cardiopulmonary resuscitation operations.

[0195] Score statistics: After the student completes 5 sets of cardiopulmonary resuscitation operations, the automatic scoring module calculates the total score to determine whether the student has passed the assessment.

[0196] Result output: Output the score results to the content display module and notify the voice broadcast module to provide corresponding voice prompts.

[0197] Data recording: Record students' performance and key data during the operation process to facilitate subsequent analysis and teaching improvement.

[0198] Inter-module coordination: Work closely with the action analysis module to ensure the accuracy and fairness of scoring; collaborate with the content presentation module and voice broadcast module to provide feedback on scores to students.

[0199] 7. Card swiping and issuing module

[0200] The card swiping and certificate issuance module is responsible for student identity verification and certificate issuance, and is the personnel management unit of the device.

[0201] Function implementation:

[0202] Identity verification: Students authenticate themselves by swiping their card or ID card. The module reads the student information and updates it to the system.

[0203] Score binding: Bind the student's operation score with the student's identity information to ensure that the score is attributed correctly.

[0204] Certificate printing: When the student passes the assessment, the card swiping and certificate issuance module prints the certificate according to the instructions of the background management page.

[0205] Information update: After each operation of the trainees, the training records and assessment results are updated to facilitate tracking of the trainees' learning progress.

[0206] Coordination between modules: Linked with the automatic scoring module, it triggers the certificate printing process after the students pass the assessment; works in conjunction with the background management page to manage student information and certificates.

[0207] Overall coordination of modules:

[0208] The above modules cooperate and collaborate through efficient data transmission and command response mechanisms.

[0209] When a student approaches the simulator and raises their hand, the video monitoring module immediately recognizes the gesture and triggers the motion analysis module to capture and analyze the motion. Simultaneously, the camera lens control module adjusts the camera position and parameters based on the video monitoring module's instructions.

[0210] If the motion analysis module detects an incorrect movement, it immediately sends instructions to the voice broadcast module for prompts and corrections. After the student completes the exercise, the automatic scoring module scores and compiles the student's performance. Based on the results, it sends instructions to the card swiping and certification module to issue a certificate or prompt the student to continue practicing.

[0211] Throughout the entire process, coordination and collaboration between modules are achieved through efficient data transmission and command response mechanisms. This mechanism ensures that the device can quickly and accurately respond to students' operations and commands, providing students with an intelligent, personalized teaching experience. Furthermore, data sharing and collaborative work between modules also improve the overall performance and reliability of the device.

[0212] In summary, the fully automated CPR teaching and proctoring system, through the close coordination and collaboration of its various modules, enables intelligent training and assessment of students' CPR skills. This system not only improves training efficiency and quality, but also provides students with a more convenient and personalized learning experience.

[0213] This embodiment uses automation technology to achieve comprehensive monitoring, real-time feedback, and automated assessment of trainees' cardiopulmonary resuscitation operations, with the following advantages:

[0214] Comprehensive monitoring: Through cameras and image processing technology, the system can monitor students' CPR movements and on-site distress gestures in real time, providing more comprehensive training feedback.

[0215] Real-time feedback: The system can instantly analyze students’ movements and provide real-time guidance if the movements are inaccurate, without having to wait for intervention from a live teacher.

[0216] Reduced reliance on manual labor: The system reduces reliance on on-site instructors, allowing students to receive high-quality training even when the instructor is not present.

[0217] Improve training consistency: The feedback provided by the system is based on unified standards, ensuring that all trainees receive consistent training content.

[0218] Data analysis: The system can collect and analyze large amounts of student training data to help improve training methods and processes.

[0219] Example 2

[0220] This embodiment provides an automatic teaching method for cardiopulmonary resuscitation, including:

[0221] Capture students’ operation images in real time through cameras;

[0222] Processing the operation image through a deep learning algorithm to determine whether the trainee's operation action is correct, thereby obtaining a first judgment result;

[0223] Displaying the first judgment result, and displaying a teaching video when the first judgment result is negative;

[0224] When the first judgment result is no, a voice prompt is given, and the prompt content includes the error type and correction method;

[0225] Scoring is performed based on the first judgment result, and the final score is calculated.

[0226] like Figure 4 and Figure 5 As shown, the execution steps of the automatic teaching method for cardiopulmonary resuscitation in this embodiment include:

[0227] Step S1: When compression data is generated on the cardiopulmonary resuscitation simulator, the all-in-one machine automatically finds the corresponding simulator through the camera and switches the screen to the cardiopulmonary resuscitation training mode.

[0228] Step S2: The camera transmits the captured image to the Android mainboard. The Android mainboard depicts the human skeleton diagram of the simulator and the trainee in real time based on the image content, and at the same time measures the distance between the all-in-one machine and the trainee. Combined with the trainee's pressing displacement degree on the skeleton diagram, the Android mainboard analyzes in real time whether the trainee's pressing and blowing actions are correct.

[0229] Step S3: If the student's movements are found to be non-standard during the actual operation, the student is given guidance through video and voice, and is informed of the standard movements.

[0230] Step S4: After the student reaches the required score in the training mode, he / she can take the online assessment. In the assessment mode, the all-in-one machine acts as an invigilator, collecting the student's cardiopulmonary resuscitation test movements throughout the process and checking whether all movements meet the assessment requirements.

[0231] Step S5: After the student passes the assessment, he / she uploads personal information through the ID card reader on the all-in-one machine to realize self-service ID issuance by the system.

[0232] Example 3

[0233] This embodiment provides a computer device, which can be a server or a terminal. Its internal structure diagram can be as follows: Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data in the automatic teaching method of cardiopulmonary resuscitation. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an automatic teaching method of cardiopulmonary resuscitation of Example 2 is implemented.

[0234] Those skilled in the art will understand that Figure 6The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application and does not constitute a limitation on the computer device to which the solution of the present application is applied. A specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of the above-mentioned method embodiments when executing the computer program.

[0235] Example 4

[0236] This embodiment provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the automatic teaching method for cardiopulmonary resuscitation according to embodiment 2 is implemented.

[0237] Example 5

[0238] This embodiment provides a computer program product, including a computer program. When the computer program is executed by a processor, the computer program implements the automatic teaching method for cardiopulmonary resuscitation of embodiment 2.

[0239] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0240] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0241] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0242] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0243] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. An automatic teaching system for cardiopulmonary resuscitation, characterized in that: The automatic teaching system for cardiopulmonary resuscitation comprises: Video monitoring module, used to capture trainees' operation images in real time through cameras; An action analysis module is used to process the operation image through a deep learning algorithm to determine whether the trainee's operation action is correct and obtain a first judgment result; a content display module, configured to display the first judgment result, and display a teaching video when the first judgment result is negative; A voice announcement module, configured to provide a voice prompt when the first judgment result is no, the prompt content including the error type and correction method; The automatic scoring module is used to score according to the first judgment result and calculate the final score.

2. The automatic teaching system for cardiopulmonary resuscitation according to claim 1, characterized in that: The automatic teaching system for cardiopulmonary resuscitation also includes: The camera lens control module is used to adjust the position and focal length of the camera to ensure a clear image of the trainee's operation.

3. The automatic teaching system for cardiopulmonary resuscitation according to claim 1, characterized in that: The automatic teaching system for cardiopulmonary resuscitation also includes: The card swiping and certificate issuance module is used for student identity verification and certificate issuance.

4. The automatic teaching system for cardiopulmonary resuscitation according to claim 1, characterized in that: The video monitoring module is also used to determine whether there are students entering the monitoring area and perform face recognition; The video monitoring module specifically includes: An environment monitoring unit, configured to capture images of the surrounding environment through a camera group, wherein the monitoring area of ​​the camera group can cover all areas around the cardiopulmonary resuscitation simulator; An image processing unit, configured to process the surrounding environment image using image processing technology to obtain a processed surrounding environment image; A motion detection unit is configured to process the processed surrounding environment image based on a motion detection algorithm to determine whether a student has entered the monitoring area, and obtain a second determination result; A face recognition unit is used to perform face recognition based on the processed surrounding environment image when the second judgment result is yes.

5. The automatic teaching system for cardiopulmonary resuscitation according to claim 4, characterized in that: The camera control module specifically includes: The optimal viewing angle calculation unit is used to calculate the optimal shooting angle according to the position of the trainee and the position of the simulator; The angle adjustment unit is used to adjust the angles of the cameras in the camera group according to the optimal shooting angle.

6. The automatic teaching system for cardiopulmonary resuscitation according to claim 1, characterized in that: The action analysis module specifically includes: A human skeleton drawing unit, used to identify and draw human skeletons of trainees and simulators from operation images using a deep learning algorithm; an action comparison unit, configured to determine whether the trainee's operation action is correct based on the human skeleton diagram, and obtain a first determination result; The error recording unit is used to record the types and times of errors made by trainees during operation.

7. An automatic teaching method for cardiopulmonary resuscitation, characterized in that: The automatic teaching method of cardiopulmonary resuscitation includes: Capture students’ operation images in real time through cameras; Processing the operation image through a deep learning algorithm to determine whether the trainee's operation action is correct, thereby obtaining a first judgment result; Displaying the first judgment result, and displaying a teaching video when the first judgment result is negative; When the first judgment result is no, a voice prompt is given, and the prompt content includes the error type and correction method; Scoring is performed based on the first judgment result, and the final score is calculated.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the automatic teaching method for cardiopulmonary resuscitation as claimed in claim 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the computer program implements the automatic teaching method of cardiopulmonary resuscitation described in claim 7.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the automatic teaching method of cardiopulmonary resuscitation described in claim 7.

Images