Method and system for monitoring effectiveness of all-people cardio-pulmonary resuscitation training

Abstract

The invention provides a whole-people cardio-pulmonary resuscitation training effectiveness monitoring method and system, and the method comprises the steps: building an online learning platform, and generating a cardio-pulmonary resuscitation training plan based on an American heart association guide, a practical experience case library and an Ebbinghaus forgetting curve principle; acquiring electroencephalogram signal data and an operation video when the trainee end completes training; according to the electroencephalogram signal data, the concentration degree of the student terminal on different learning plates in theoretical knowledge training is analyzed; performing operation key point analysis on the operation video through a target identification and target tracking algorithm; and screening unqualified items from the training result score table by combining the corresponding relationship between different learning plates and operation key points, the concentration analysis result and the operation key point analysis result score, remaking a consolidation training plan, and sending the consolidation training plan to the student end for consolidation training. And updating the training result score table according to the concentration analysis result of consolidation training and the operation key point analysis result until all scores are qualified. According to the method, the training quality and the training efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of training management, and in particular to a method and system for monitoring the effectiveness of universal cardiopulmonary resuscitation training. Background Art

[0002] With the development of Internet technology, the mode of teaching and training through video or audio is becoming more and more popular and has become a training method accepted by the public. However, the current cardiopulmonary resuscitation training uses video training or audio training, which has some disadvantages.

[0003] For trainees, the learning effect is difficult to guarantee. Video training usually requires trainees to have strong self-management and self-discipline. Trainees are easily disturbed by various distractions, such as mobile phone information and surrounding environment, which leads to lack of concentration and low learning efficiency. For trainees with poor self-discipline, they may just watch the video in a cursory manner without truly mastering the knowledge and skills. As a result, during the operation training stage, trainees do not correctly master the essentials of the movements, resulting in problems such as irregular movements. For instructors, instructors cannot obtain in real time whether trainees have truly mastered the learning content. For different learning modules, the degree of mastery of different trainees varies. During the operation training stage, the "one-to-many" training model makes it impossible for instructors to grasp whether the essentials of each trainee's movements are standardized, which easily leads to omission of details, and low training quality and efficiency. Summary of the invention

[0004] In view of this, the present invention provides a method and system for monitoring the effectiveness of universal cardiopulmonary resuscitation training to solve the above problems.

[0005] The present invention provides a method for monitoring the effectiveness of universal cardiopulmonary resuscitation training, comprising: establishing an online learning platform according to the ADDIE education design model, the online learning platform comprising a management end and a student end; the management end generates a cardiopulmonary resuscitation training plan based on the American Heart Association guidelines, a practical experience case library and the Ebbinghaus forgetting curve principle, the cardiopulmonary resuscitation training plan comprising theoretical knowledge training and practical training; obtaining EEG signal data of the student end when the theoretical knowledge training is completed, and an operation video when the practical training is completed; analyzing the student end's concentration on different learning sections during the theoretical knowledge training according to the EEG signal data, and obtaining the concentration Analyze the results; analyze the key points of the operation video through the target recognition algorithm and the target tracking algorithm to obtain the key points analysis results; score the corresponding relationship between the different learning modules and the key points of the operation, the concentration analysis results, and the key points analysis results to obtain a training result score sheet; filter out unqualified items from the training result score sheet according to the preset qualification standards, and re-formulate a consolidation training plan based on the unqualified items and send it to the trainee end for consolidation training, and update the training result score sheet according to the concentration analysis results and the key points analysis results of the consolidation training until all the scores in the training result score sheet are qualified.

[0006] In another implementation of the present invention, the concentration of the trainee on different learning sections in the theoretical knowledge training process is analyzed based on the EEG signal data to obtain a concentration analysis result, including: preprocessing the EEG signal data; calculating the power spectrum density of the preprocessed EEG signal data by a periodogram method or an autocorrelation method; analyzing the power distribution of the EEG signal at the frequency points corresponding to different learning sections according to the power spectrum density; judging the concentration of the trainee on different learning sections in the theoretical knowledge training process based on the power distribution to obtain a concentration analysis result.

[0007] In another implementation of the present invention, the EEG signal data includes α waves, β waves, θ waves and δ waves; increased activity of β waves indicates that the brain is in an active cognitive state; increased activity of α waves and decreased activity of β waves indicate that the brain's attention begins to distract; increased activity of θ waves and δ waves indicates that the brain begins to become fatigued.

[0008] In another implementation of the present invention, it also includes: dividing the concentration level according to the activity state of different frequency waves in the EEG signal data, the concentration levels including high concentration, moderate concentration, mild distraction, and severe distraction; during the theoretical knowledge training process, when it is detected that the attention level reaches severe distraction, the trainee end initiates feedback stimulation.

[0009] In another implementation of the present invention, the power spectral density calculated by the periodogram method is expressed as:

[0010]

[0011] Where x(n) is a random EEG signal sequence of finite length, n = 0, 1, ..., N-1, N is the sequence length; X(k) is the discrete Fourier transform of x(n), k = 0, 1, ..., N-1.

[0012] In another implementation of the present invention, the power spectral density calculated by the autocorrelation method is expressed as:

[0013]

[0014] Among them, Pxx(e jw ) is the autocorrelation function r xx The Fourier transform of (m) and the autocorrelation function are expressed as:

[0015]

[0016] Where x(n) is a random EEG signal sequence of finite length; m represents the time delay.

[0017] In another implementation of the present invention, the operation point analysis is performed on the operation video by a target recognition algorithm and a target tracking algorithm to obtain the operation point analysis result, including: processing multiple frames of video images contained in the operation video by a processing rule preset in the target recognition algorithm to obtain the similarity between two adjacent frames of video images; matchingly superimposing two adjacent frames of video images whose similarity is higher than a preset threshold by the target tracking algorithm, and determining the overlapping image area of ​​the target operation point in the two adjacent frames of video images based on the obtained superposition result; performing area repetition calculation based on the overlapping image area to obtain the motion parameters of the target operation point, wherein the motion parameters of the target operation point are used to generate the operation point analysis result.

[0018] Another aspect of the present invention provides a system for monitoring the effectiveness of cardiopulmonary resuscitation training for all, comprising:

[0019] Platform establishment module: establish an online learning platform according to the ADDIE education design model, the online learning platform includes a management end and a student end;

[0020] Course training module: the management end generates a cardiopulmonary resuscitation training plan based on the American Heart Association guidelines, the practical experience case library and the Ebbinghaus forgetting curve principle, and the cardiopulmonary resuscitation training plan includes theoretical knowledge training and practical training; obtains the EEG signal data of the trainee when completing the theoretical knowledge training and the operation video when completing the practical training;

[0021] Training data analysis module: analyzing the concentration of the trainee on different learning sections during the theoretical knowledge training according to the EEG signal data to obtain the concentration analysis result; analyzing the key points of the operation video through the target recognition algorithm and the target tracking algorithm to obtain the key points analysis result; scoring based on the correspondence between the different learning sections and the key points of the operation, the concentration analysis result, and the key points analysis result to obtain the training result score sheet;

[0022] Training effect tracking module: filter out unqualified items from the training result scoring table according to preset qualification standards, formulate a consolidation training plan based on the unqualified items and send it to the trainees for consolidation training, and update the training result scoring table according to the concentration analysis results and operation point analysis results of the consolidation training until all scores in the training result scoring table are qualified.

[0023] Another aspect of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of a method for monitoring the effectiveness of cardiopulmonary resuscitation training for all people as described in any one of the above items are implemented.

[0024] Another aspect of the present invention provides a computer storage medium, characterized in that a computer program is stored on the computer storage medium, and when the computer program is executed by a processor, the steps in the method for monitoring the effectiveness of universal cardiopulmonary resuscitation training as described in any one of the above items are implemented.

[0025] The effectiveness monitoring method of universal cardiopulmonary resuscitation training of the present invention obtains attention status information during the learning process by collecting EEG signal data of personnel participating in theoretical knowledge training, analyzing the weak electrical signals emitted by brain neurons; and recording operation videos during practical training, analyzing each action of the trainees separately through algorithms, and evaluating whether the body movements of the trainees meet the standards; combining the attention status information of the trainees during training and the action details in the operation videos, analyzing the concentration and mastery of the trainees on different learning modules, and scoring them, and regenerating consolidation training for unqualified items in the scoring results, thereby improving the trainees' mastery of knowledge and skills, and improving the training quality and training efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art description. By reading the detailed description of the following implementation, the advantages and benefits of the solutions become clear to those skilled in the art. The drawings are only used to illustrate the preferred implementation and are not considered to be limitations of the present invention. In the drawings:

[0027] Figure 1 The present invention is a flowchart of a method for monitoring the effectiveness of universal cardiopulmonary resuscitation training according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be described clearly and in detail below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in the field based on the embodiments in the embodiments of the present invention should fall within the scope of protection of the embodiments of the present invention.

[0029] Figure 1 A flow chart of a method for monitoring the effectiveness of universal cardiopulmonary resuscitation training provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, this embodiment mainly includes:

[0030] S101. Establish an online learning platform according to the ADDIE education design model, wherein the online learning platform includes a management end and a student end.

[0031] For example, students complete information registration through the mobile APP or applet, and the management end verifies the information of cardiopulmonary resuscitation trainees and establishes a national cardiopulmonary resuscitation trainee database. When the online registration is successful, the student information will be automatically uploaded to the national cardiopulmonary resuscitation trainee database, and the student information can be viewed by logging into the management end. The student information includes name, gender, age, ID number, contact information, occupation, education level, whether a first aid volunteer certificate has been obtained and the time of obtaining it, etc. Among them, the computer devices used by the mobile end include but are not limited to smart phones, laptops, tablets, desktop computers, physical servers, cloud servers and other devices.

[0032] S102. The management end generates a cardiopulmonary resuscitation training plan based on the American Heart Association guidelines, a practical experience case library, and the Ebbinghaus forgetting curve principle. The cardiopulmonary resuscitation training plan includes theoretical knowledge training and practical training.

[0033] For example, the management end will regularly send the cardiopulmonary resuscitation content that needs to be mastered to each student end at different key time points, and remind the student end to study and complete the test in various forms such as text messages and phone calls. Taking the timeline as the cutoff point, according to the principle of the Ebbinghaus forgetting curve, for example, the corresponding theoretical knowledge learning content can be pushed to the students at key time points such as 20 minutes, 1 hour, 8 hours, 1 day, 2 days, 6 days, and 30 days after the practical training. The learning content is divided into several sections and scattered at different time points to avoid learning too much content at one time, which leads to accelerated forgetting. The learning content is presented in two parts: text and video. According to the feedback of the students on the knowledge mastery of different sections, the system will strengthen the push of the corresponding weak knowledge sections until the students complete all cardiopulmonary resuscitation training plans.

[0034] S103, obtaining the EEG signal data of the trainee when completing the theoretical knowledge training, and the operation video when completing the practical training.

[0035] For example, the EEG signal is obtained by placing electrodes in accordance with the international 10-20 system using a multi-channel electrode cap during training, with a focus on the electrode signals in the frontal lobe (related to attention) and parietal lobe (related to cognitive processing). The operation video is a video of cardiopulmonary resuscitation operation recorded by capturing the body movements of the on-site trainees through an RGB camera during training.

[0036] S104. Analyze the student's concentration on different learning sections during the theoretical knowledge training according to the EEG signal data to obtain a concentration analysis result.

[0037] S105, performing operation key point analysis on the operation video through a target recognition algorithm and a target tracking algorithm to obtain an operation key point analysis result.

[0038] For example, the key points analysis is to analyze the trainee's movements frame by frame based on the trainee's full body movements and interaction with the simulator when the trainee performs CPR on the first aid simulator, including whether the hand position is correct and whether the body posture conforms to the principles of mechanics. This method can capture some details that cannot be reflected by the simulator data, such as whether the trainee keeps his arms straight during the operation.

[0039] S106, scoring is performed based on the correspondence between the different learning modules and the key operation points, the concentration analysis results, and the key operation point analysis results to obtain a training result scoring table.

[0040] S107. Filter out unqualified items from the training result scoring table according to preset qualification standards, formulate a new consolidation training plan based on the unqualified items and send it to the trainees for consolidation training, and update the training result scoring table according to the concentration analysis results and operation key points analysis results of the consolidation training until all scores in the training result scoring table are qualified.

[0041] The effectiveness monitoring method of universal cardiopulmonary resuscitation training of the present invention obtains attention status information during the learning process by collecting EEG signal data of personnel participating in theoretical knowledge training, analyzing the weak electrical signals emitted by brain neurons; and recording operation videos during practical training, analyzing each action of the trainees separately through algorithms, and evaluating whether the body movements of the trainees meet the standards; combining the attention status information of the trainees during training and the action details in the operation videos, analyzing the concentration and mastery of the trainees on different learning modules, and scoring them, and regenerating consolidation training for unqualified items in the scoring results, thereby improving the trainees' mastery of knowledge and skills, and improving the training quality and training efficiency.

[0042] In another implementation of the present invention, the concentration of the trainee on different learning sections in the theoretical knowledge training process is analyzed based on the EEG signal data to obtain a concentration analysis result, including: preprocessing the EEG signal data; calculating the power spectrum density of the preprocessed EEG signal data by a periodogram method or an autocorrelation method; analyzing the power distribution of the EEG signal at the frequency points corresponding to different learning sections according to the power spectrum density; judging the concentration of the trainee on different learning sections in the theoretical knowledge training process based on the power distribution to obtain a concentration analysis result.

[0043] Exemplarily, the EEG signal data is denoised by using a bandpass filter and a wavelet transform of a preset bandpass frequency band in turn, and baseline drift, DC component, myoelectric interference, power frequency interference, etc. in the EEG signal data are filtered out to obtain denoised EEG signal data. The denoised EEG signal data is subjected to data segmentation processing based on a sliding window of a preset size window and a preset step length to obtain segmented EEG signal data, and the segmented EEG signal data is normalized to output preprocessed EEG signal data, which excludes irrelevant information such as electrode interference and environmental noise.

[0044] In another implementation of the present invention, the EEG signal data includes α waves, β waves, θ waves and δ waves; increased activity of β waves indicates that the brain is in an active cognitive state; increased activity of α waves and decreased activity of β waves indicate that the brain's attention begins to distract; increased activity of θ waves and δ waves indicates that the brain begins to become fatigued.

[0045] For example, the collected EEG signal data contains waves of different frequencies, such as alpha waves, beta waves, theta waves, and delta waves, etc. These waves of different frequencies are related to different states of the brain. When a person is in a state of high concentration, the activity of the beta wave will increase, indicating that the brain is in an active cognitive state; if a person begins to be distracted, the activity of the alpha wave may increase, while the activity of the beta wave will decrease, indicating that the brain's attention begins to disperse; when a person is in a state of long-term learning, the activity of the theta wave and the delta wave increases, indicating that the brain begins to become fatigued.

[0046] For example, the common focus-related frequency band is 4-40Hz, and a bandpass filter can be selected, which mainly contains delta (0.5-4Hz), theta (4-8Hz), alpha (8-13Hz), beta (13-30Hz) and gamma (30-40Hz) waves. The following interference can be removed by bandpass filtering:

[0047] Baseline drift, such as low-frequency drift, is usually caused by motion or electrode contact.

[0048] DC component, constant DC signal component.

[0049] Myoelectric interference, usually above 30Hz, is caused by the activity of the head and facial muscles.

[0050] Power frequency interference, power supply noise, usually 50 or 60Hz.

[0051] It should be understood that by eliminating baseline drift, DC components, myoelectric interference and power frequency interference, the signal quality is effectively improved. At the same time, the filtered data can more accurately reflect the effective components related to the state of concentration in the EEG signal, improving the reliability of the data. The use of bandpass filtering effectively removes irrelevant frequency components and interference, making the data purer and more accurate.

[0052] In another implementation of the present invention, it also includes: dividing the concentration level according to the activity state of different frequency waves in the EEG signal data, the concentration levels including high concentration, moderate concentration, mild distraction, and severe distraction; during the theoretical knowledge training process, when it is detected that the attention level reaches severe distraction, the trainee end initiates feedback stimulation.

[0053] For example, the attention state information of the trainees is to obtain the concentration and mastery of different learning modules during the training process based on EEG signal data and operation points analysis. It can be processed by computer and the attention state level of the trainees can be expressed by text descriptions, such as "high concentration", "moderate concentration", "mild distraction", "severe distraction", etc.

[0054] Furthermore, corresponding feedback stimuli are generated according to the concentration level, including visual feedback stimuli, auditory feedback stimuli and tactile feedback stimuli. The feedback stimuli can be in the form of pictures, animations, music, sound prompts, etc. The purpose is to guide and adjust the user's concentration state through these stimuli. Through timely feedback stimulation, users can immediately perceive changes in their concentration, adjust their attention, and improve the quality of training.

[0055] Specifically, the stimulation type and stimulation parameters corresponding to the feedback stimulation are determined according to the concentration level; the modal coding and presentation method corresponding to the stimulation type are determined; and the corresponding feedback stimulation is generated according to the modal coding, presentation method, stimulation type and stimulation parameters; wherein, if the concentration level is greater than or equal to the preset level, the stimulation type is positive stimulation; if the concentration level is lower than the preset level, the feedback stimulation is suggestive stimulation.

[0056] For example, the positive visual stimulation type may be a visual reward (such as color change, a brighter screen, etc.), the suggestive visual stimulation type may be a warning icon or a darkening of color, etc., and the visual stimulation parameters include but are not limited to brightness, color, display time and other parameters, which can refine the presentation of the visual stimulation.

[0057] The type of auditory stimulation is determined according to the user's concentration level. For example, a positive auditory stimulation type can be a positive sound effect (such as pleasant music or prompt sound), and a suggestive auditory stimulation type can be a reminder sound (such as a warning sound, a low prompt sound, etc.). Auditory stimulation parameters include volume, pitch, duration, rhythm and other parameters, which define the specific form of the auditory stimulation.

[0058] Different types of visual and auditory stimuli are concretized through coding. For example, a specific code represents a certain color change or a certain piece of music. Determine the presentation method of visual and auditory stimuli, such as synchronous display, delayed display, gradual change, etc., which determines the presentation time and order of feedback stimuli. According to the aforementioned determined modal coding, presentation method, stimulus type and its parameters, specific visual and auditory feedback stimuli are generated. Visual feedback stimuli may include color changes, brightness adjustments, icon displays, etc., and auditory feedback stimuli may include prompt sounds, music, warning sounds, etc. According to the concentration level, the type and parameters of visual and auditory stimuli are dynamically adjusted: when the concentration level is greater than or equal to the preset level, positive visual stimuli and positive auditory stimuli are generated; when the concentration level is lower than the preset level, suggestive visual stimuli and suggestive auditory stimuli are generated.

[0059] Real-time and personalized visual and auditory feedback stimulation is generated according to the user's concentration level, which effectively promotes the improvement of attention and the development of self-regulation ability of trainees. The above technical content and beneficial effects complement each other and provide trainees with an efficient, intelligent and interactive feedback mechanism.

[0060] In another implementation of the present invention, a feedback adjustment coefficient is determined based on the concentration of the trainees and the historical data of the system, and this coefficient is used to optimize various feedback stimulation parameters to improve user experience and effect. The adjustment coefficient can be pre-set or dynamically generated through the self-learning and adjustment mechanism of the system.

[0061] Specifically, the parameters of the visual feedback stimulation and the auditory feedback stimulation are optimized according to the feedback adjustment coefficient, including: adjusting the font size, font color, animation effect, and transparency of the prompt box of the visual feedback stimulation according to the feedback adjustment coefficient. The visual feedback parameters are adjusted by, for example, increasing or decreasing the font size of the text according to the feedback adjustment coefficient to attract attention or reduce reading pressure, adjusting the text color to improve readability or emphasize important information, for example, using red to highlight warning information, increasing or decreasing the animation effect to make it easier for trainees to notice visual changes, and adjusting the transparency of the prompt box to make it more conspicuous or more integrated into the background.

[0062] The volume, pitch, speaking speed and number of repetitions of auditory feedback stimulation are adjusted according to the feedback adjustment coefficient. The auditory feedback parameters are adjusted by, for example, increasing or decreasing the volume to ensure that users can receive auditory prompts at an appropriate volume, adjusting the high and low pitches of the prompt sounds to make them more in line with the auditory preferences of the trainees or highlighting the urgency of the prompts, adjusting the speed of the voice prompts to suit the understanding and acceptance of the trainees, increasing or decreasing the number of repetitions of the prompt sounds as needed to ensure that the trainees do not miss important prompts or feel irritated by too many repetitions, and increasing or decreasing the vibration intensity to provide appropriate tactile feedback according to the current needs of the trainees. Too high an intensity may interfere with the trainees, while too low an intensity may be ignored.

[0063] In another implementation of the present invention, tactile feedback stimulation can also be generated according to the concentration level through equipment (such as smart watches, bracelets, tactile feedback devices, etc.), and the vibration intensity of the tactile feedback stimulation can be adjusted according to the feedback adjustment coefficient. The tactile feedback can be in the form of vibrations of different intensities and frequencies. The purpose is to attract the attention of the trainees or provide immediate feedback.

[0064] The feedback mechanism is enriched by the comprehensive use of visual, auditory and tactile feedback stimulation. Multimodal feedback can more comprehensively cover the perception channels of trainees, improve the feedback effect and experience of trainees, and tactile feedback is suitable for providing timely and effective feedback in quiet environments or scenarios where users cannot concentrate on browsing the screen. The feedback adjustment coefficient is used to dynamically optimize various feedback parameters, which can quickly respond to changes in the concentration level of trainees and provide timely and accurate feedback.

[0065] By optimizing feedback parameters in real time, the fatigue and boredom of trainees caused by receiving too much or too little feedback information can be avoided, thereby improving the concentration of trainees.

[0066] In another implementation of the present invention, the power spectral density calculated by the periodogram method is expressed as:

[0067]

[0068] Where x(n) is a random EEG signal sequence of finite length, n = 0, 1, ..., N-1, N is the sequence length; X(k) is the discrete Fourier transform of x(n), k = 0, 1, ..., N-1.

[0069] For example, the periodogram method estimates the power spectrum density by dividing the square of the amplitude of the discrete Fourier transform (DFT) of a finite length of sample data of the signal (set as x(n), n=0, 1, ..., N-1) by the sample length N. In the analysis of EEG signals for cardiopulmonary resuscitation training, the power spectrum is calculated by the periodogram method to obtain the power distribution of the EEG signal at different frequency points.

[0070] For example, the power changes of the brain's alpha wave (8-13Hz), beta wave (13-30Hz) and other frequency bands can be observed during the first aid theory training. If the alpha wave power of the EEG signal gradually increases during the first aid theory training, it may indicate that the brain is more relaxed, which means that the trainee's attention is reduced; on the contrary, if the beta wave power increases and lasts for a long time, it may indicate that the brain is in an excited state, which means that the trainee's attention is highly concentrated.

[0071] In another implementation of the present invention, the power spectral density calculated by the autocorrelation method is expressed as:

[0072]

[0073] Among them, Pxx(e jw ) is the autocorrelation function r xx The Fourier transform of (m) and the autocorrelation function are expressed as:

[0074]

[0075] Where x(n) is a random EEG signal sequence of finite length; m represents the time delay.

[0076] Specifically, in actual calculations, the autocorrelation function needs to be properly truncated and normalized because the signal is of finite length. In the analysis of EEG signals in cardiopulmonary resuscitation training, the autocorrelation function can be used to measure the similarity of signals under different time delays. For example, the EEG signals of normal brain activity may have a certain periodicity, and the autocorrelation function can reflect this periodicity. If the brain of the trainee begins to fatigue while learning the theoretical knowledge of first aid, the autocorrelation function of the EEG signal may change and the periodicity may weaken.

[0077] According to the Wiener-Khinchin theorem, the power spectral density is the Fourier transform of the autocorrelation function. After estimating the power spectral density by the autocorrelation method, the power changes of EEG signals at different frequencies can be analyzed in the same way as the periodogram method. For example, the power spectrum changes of EEG signals in the low frequency band (such as delta waves, 0-4Hz) before and after theoretical learning can be compared to evaluate the impact of theoretical learning on the slow wave activity of the brain. If the power of delta waves increases after theoretical learning, it may mean that the metabolic state of the brain is fatigued, because delta waves are related to the inhibitory or pathological state of the brain in some cases.

[0078] It should be understood that by analyzing EEG signal data through algorithm models, the effect of first aid theoretical knowledge training for trainees can be evaluated. For example, by observing the stability and change pattern of the EEG signal power spectrum of different trainees during theoretical learning, if the frequency components and power distribution of the EEG signal of a trainee are relatively stable during the theoretical learning process, and conform to the characteristics of the normal functional state of the brain, it may indicate that the trainee's attention is more focused and the learning effect is better. On the contrary, if there are large fluctuations in the EEG signal or an increase in abnormal frequency components, it may indicate that the trainee's learning attention has decreased and the learning effect is poor. At the same time, it is also possible to evaluate whether the training has improved the trainees' first aid theoretical knowledge and skills by comparing the analysis results of the trainees' EEG signals before and after the training.

[0079] In another implementation of the present invention, the operation point analysis is performed on the operation video by a target recognition algorithm and a target tracking algorithm to obtain the operation point analysis result, including: processing multiple frames of video images contained in the operation video by a processing rule preset in the target recognition algorithm to obtain the similarity between two adjacent frames of video images; matchingly superimposing two adjacent frames of video images whose similarity is higher than a preset threshold by the target tracking algorithm, and determining the overlapping image area of ​​the target operation point in the two adjacent frames of video images based on the obtained superposition result; performing area repetition calculation based on the overlapping image area to obtain the motion parameters of the target operation point, wherein the motion parameters of the target operation point are used to generate the operation point analysis result.

[0080] Exemplarily, by denoising and normalizing the operation video data and using a threshold-based motion segmentation algorithm to analyze each motion of the trainee individually, it is evaluated whether the trainee's body movements meet the standards.

[0081] Through the target recognition algorithm, each video image in the operation video is detected frame by frame to see if it contains body parts, such as the hands or mouth of the trainees; when it is detected that the video image contains body parts, the position information and other related parameters of the body parts in the video image are further identified and determined; and based on the above detection and recognition results, corresponding marking data is added to the video image detected to contain body parts.

[0082] In the video image detected to contain the target body part after being processed by the target recognition algorithm, the position of the target body part in the video image can be first framed by a graphic frame such as a rectangular frame, a circular frame, etc., and the corresponding body part name can be marked at the adjacent position of the image frame.

[0083] The target tracking algorithm is used to obtain the corresponding target tracking result; then, based on the target tracking result, the movement information of the target body part during the operation is obtained. The movement information may include at least one of the following: movement duration, average movement speed, movement trajectory, number of operations, single operation duration, operation sequence, average confidence, and movement information of the center point of the target body part. The training participants are analyzed based on the movement information to determine whether the hand position is correct and whether the pressing posture conforms to the principles of mechanics.

[0084] In another implementation of the present invention, a comprehensive effectiveness score S of the operation video of the training personnel is obtained by a computer processor, as shown in detail below:

[0085] ① Evaluation of the accuracy of the pressing position: The operation video is processed by video analysis software to identify the position of the trainee's hand on the simulator's chest. The standard for defining the correct pressing position is the midpoint of the line connecting the two nipples. In each operation, if the pressing position is correct, it is recorded as 1 correct operation; if the position is slightly deviated (within a circular range with the correct position as the center and a radius of [specific deviation value] cm), it is recorded as 0.5 correct operations; if the position is wrong, it is recorded as 0 correct operations. Let the number of correct pressing position operations be n 正位置 , the total number of operations is N, then the pressing position accuracy score is S 位置 The calculation formula is:

[0086]

[0087] ② Evaluation of compression depth accuracy: According to the cardiopulmonary resuscitation standard, the compression depth standard for adults is 5-6 cm. Use the known information in the video (such as the size of the simulator, the scale marked in the video, etc.) to estimate the depth of each compression of the trainee. Let the number of operations that meet the depth standard (5-6 cm) be n 正深度 , then the compression depth accuracy score S 深度 The calculation formula is:

[0088] ③Compression frequency accuracy assessment: Calculate the number of times the student presses within a specific time interval (such as one minute) in the video to obtain the actual compression frequency f. When the actual compression frequency f satisfies 100≤f≤120 times / minute, the compression frequency accuracy score S 频率 =1; when f<100 or f>120, This formula results in lower scores the further away from the standard frequency.

[0089] ④ Artificial respiration accuracy assessment: Observe the fit between the trainee's mouth and the mannequin's mouth, the duration of the blowing (the standard duration is about 1 second), and the rise and fall of the mannequin's chest during the artificial respiration segment in the video. In each artificial respiration operation, if all three items meet the standards, it will be counted as one correct operation. Let the number of correct artificial respiration operations be n 正呼吸 , then the artificial respiration accuracy score S 呼吸 The calculation formula is:

[0090] ⑤ Step consistency assessment: The standard steps of cardiopulmonary resuscitation include judging the safety of the environment, judging consciousness, calling for emergency treatment, chest compression, opening the airway, and artificial respiration. By analyzing the operation video, determine whether the trainee completes these steps in the correct order each time. Let the number of steps completed correctly and continuously be n 连 , the total number of steps n 总 =6, then the step consistency score is S 连 The calculation formula is

[0091] ⑥ Action transition fluency assessment: Observe the fluency of the trainees in the transition between chest compression and artificial respiration, focusing on the pause time t (unit: seconds) during the transition. Set a reasonable pause time threshold of T = 10 seconds. When t ≤ T, the action transition fluency score is When t>T, S 转换 =0.

[0092] Taking all the above scores into consideration, the training effectiveness score S is obtained by weighted summation. Let the weight of the pressing position accuracy score be w 位置 , the pressing depth accuracy score weight is w 深度, the pressing frequency accuracy score weight is w 频率 , the weight of artificial respiration accuracy score is w 呼吸 , the step coherence score weight is w 连 , the weight of the action transition fluency score is w 转换 , then the training effectiveness score S is calculated as: S = w 位置 S 位置 +w 深度 S 深度 +w 频率 S 频率 +w 呼吸 S 呼吸 +w 连 S 连 +w 转换 S 转换 , weight w 位置 、w 深度 、w 频率 、w 呼吸 、w 连 、w 转换 It can be set according to the focus and objectives of cardiopulmonary resuscitation training. For example, the weight of the score related to the compression operation can be set higher according to the focus of the training.

[0093] Another aspect of the present invention provides a system for monitoring the effectiveness of cardiopulmonary resuscitation training for all, comprising:

[0094] Platform establishment module: establish an online learning platform according to the ADDIE education design model, and the online learning platform includes a management end and a student end.

[0095] Course training module: The management end generates a cardiopulmonary resuscitation training plan based on the American Heart Association guidelines, practical experience case library and the Ebbinghaus forgetting curve principle. The cardiopulmonary resuscitation training plan includes theoretical knowledge training and practical training; the management end obtains the EEG signal data of the trainee when completing the theoretical knowledge training, and the operation video when completing the practical training.

[0096] Training data analysis module: Analyze the concentration of the trainee on different learning modules during the theoretical knowledge training according to the EEG signal data to obtain the concentration analysis result; analyze the operation points of the operation video through the target recognition algorithm and the target tracking algorithm to obtain the operation point analysis result; combine the correspondence between the different learning modules and the operation points, the concentration analysis result, and the operation point analysis result to score and obtain the training result score sheet.

[0097] Training effect tracking module: filter out unqualified items from the training result scoring table according to preset qualification standards, formulate a consolidation training plan based on the unqualified items and send it to the trainees for consolidation training, and update the training result scoring table according to the concentration analysis results and operation point analysis results of the consolidation training until all scores in the training result scoring table are qualified.

[0098] The system for monitoring the effectiveness of cardiopulmonary resuscitation training for all the people of the present invention acquires the EEG signal data of the participants in the theoretical knowledge training, analyzes the weak electrical signals emitted by the brain neurons, and obtains the attention status information in the learning process; and records the operation video during the practical training, and analyzes each action of the trainees separately through the algorithm to evaluate whether the body movements of the trainees meet the standards; and combines the attention status information of the trainees during the training and the action details in the operation video to analyze the concentration and mastery of the trainees on different learning modules, and scores them, and regenerates consolidation training for the unqualified items in the scoring results, thereby improving the trainees' mastery of knowledge and skills, and improving the training quality and training efficiency.

[0099] In another aspect of the present invention, an electronic device includes: a processor, a memory, a communication bus, and a communication interface.

[0100] in:

[0101] The processor, memory and communication interface communicate with each other through a communication bus.

[0102] Communication interface, used to communicate with other electronic devices or servers.

[0103] The processor is used to execute the program, and specifically can execute the steps of any one of the methods for monitoring the effectiveness of cardiopulmonary resuscitation training for all people in the above-mentioned embodiments.

[0104] Specifically, the program may include program codes including computer operation instructions.

[0105] The processor may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0106] The memory is used to store programs. The memory may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.

[0107] The program can be specifically used to enable the processor to execute the steps of any one of the methods for monitoring the effectiveness of cardiopulmonary resuscitation training for all described in the embodiments. The specific implementation of each step in the program can refer to the corresponding descriptions in the steps and units executed by any one of the methods for monitoring the effectiveness of cardiopulmonary resuscitation training for all in the above steps, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the aforementioned method embodiments.

[0108] The above method according to the embodiment of the present invention can be implemented in a server equipped with a central processing unit CPU and an image processing unit COU.

[0109] Thus far, specific embodiments of the present invention have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results.

[0110] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, back, etc.) are only used to explain the relative position relationship between the components in a certain specific order (as shown in the accompanying drawings). If the specific order changes, the directional indication will also change accordingly.

[0111] In the description of the present invention, the terms "first" and "second" are only used to facilitate the description of different components or names, and cannot be understood as indicating or implying a sequential relationship, relative importance, or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features.

[0112] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0113] It should be noted that although the specific embodiments of the present invention are described in detail in conjunction with the accompanying drawings, it should not be understood as limiting the scope of protection of the present invention. Within the scope described in the claims, various modifications and variations that can be made by those skilled in the art without creative work still belong to the scope of protection of the present invention.

[0114] The examples of the embodiments of the present invention are intended to concisely illustrate the technical features of the embodiments of the present invention so that those skilled in the art can intuitively understand the technical features of the embodiments of the present invention, and are not intended to be improper limitations of the embodiments of the present invention.

[0115] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring the effectiveness of universal cardiopulmonary resuscitation training, characterized in that: include: Establish an online learning platform according to the ADDIE education design model, wherein the online learning platform includes a management end and a student end; The management end generates a cardiopulmonary resuscitation training plan based on the American Heart Association guidelines, a practical experience case library, and the Ebbinghaus forgetting curve principle, and the cardiopulmonary resuscitation training plan includes theoretical knowledge training and practical training; Obtaining EEG signal data of the trainee when completing the theoretical knowledge training and operation video when completing the practical training; Analyze the concentration of the trainee on different learning sections during the theoretical knowledge training according to the EEG signal data to obtain a concentration analysis result; Performing an operation point analysis on the operation video by using a target recognition algorithm and a target tracking algorithm to obtain an operation point analysis result; Scoring is performed based on the correspondence between the different learning modules and the key operation points, the concentration analysis results, and the key operation point analysis results to obtain a training result scoring table; According to the preset qualification standards, unqualified items are screened out from the training result scoring table, and a consolidation training plan is re-formulated based on the unqualified items and sent to the trainees for consolidation training. The training result scoring table is updated based on the concentration analysis results and operation point analysis results of the consolidation training until all the scores in the training result scoring table are qualified.

2. The method according to claim 1, characterized in that Analyzing the concentration of the trainee on different learning sections during the theoretical knowledge training according to the EEG signal data to obtain a concentration analysis result includes: Preprocessing the EEG signal data; Calculate the power spectral density of the preprocessed EEG signal data by using the periodogram method or the autocorrelation method; Analyze the power distribution of the EEG signal at the frequency points corresponding to different learning blocks according to the power spectrum density; The concentration of the trainee on different learning sections during the theoretical knowledge training is judged based on the power distribution to obtain a concentration analysis result.

3. The method according to claim 2, characterized in that The EEG signal data includes alpha waves, beta waves, theta waves and delta waves; Increased beta wave activity indicates that the brain is in an active cognitive state; The activity of alpha waves increases and that of beta waves decreases, indicating that the brain's attention begins to disperse; Increased activity in theta and delta waves indicates that the brain is beginning to become fatigued.

4. The method according to claim 3, characterized in that Also includes: Dividing the concentration level according to the activity states of different frequency waves in the EEG signal data, the concentration level including high concentration, moderate concentration, mild distraction, and severe distraction; During the theoretical knowledge training, when it is detected that the attention level reaches severe distraction, the trainee starts feedback stimulation.

5. The method according to claim 2, characterized in that: The power spectral density calculated by the periodogram method is expressed as: Where x(n) is a random EEG signal sequence of finite length, n = 0, 1, ..., N-1, N is the sequence length; X(k) is the discrete Fourier transform of x(n), k = 0, 1, ..., N-1.

6. The method according to claim 2, characterized in that The power spectral density calculated by the autocorrelation method is expressed as: Among them, Pxx(e jw ) is the autocorrelation function r xx The Fourier transform of (m) and the autocorrelation function are expressed as: Where x(n) is a random EEG signal sequence of finite length; m represents the time delay.

7. The method according to claim 1, characterized in that The operation key point analysis of the operation video is performed by using a target recognition algorithm and a target tracking algorithm to obtain an operation key point analysis result, including: Processing the multiple frames of video images contained in the operation video according to the processing rules preset in the target recognition algorithm to obtain the similarity between two adjacent frames of video images; Matching and superimposing the two adjacent frames of video images whose similarity is higher than a preset threshold value is performed by the target tracking algorithm, and determining the overlapping image area of ​​the target operation point in the two adjacent frames of video images according to the obtained superposition result; The area repetition is calculated according to the overlapping image area to obtain the motion parameters of the target operation point, wherein the motion parameters of the target operation point are used to generate the key operation point analysis result.

8. A system for monitoring the effectiveness of cardiopulmonary resuscitation training for all citizens, characterized in that: include: Platform establishment module: establish an online learning platform according to the ADDIE education design model, the online learning platform includes a management end and a student end; Course training module: the management end generates a cardiopulmonary resuscitation training plan based on the American Heart Association guidelines, the practical experience case library and the Ebbinghaus forgetting curve principle, and the cardiopulmonary resuscitation training plan includes theoretical knowledge training and practical training; obtains the EEG signal data of the trainee when completing the theoretical knowledge training and the operation video when completing the practical training; Training data analysis module: analyzing the concentration of the trainee on different learning sections during the theoretical knowledge training according to the EEG signal data to obtain the concentration analysis result; analyzing the key points of the operation video through the target recognition algorithm and the target tracking algorithm to obtain the key points analysis result; scoring based on the correspondence between the different learning sections and the key points of the operation, the concentration analysis result, and the key points analysis result to obtain the training result score sheet; Training effect tracking module: filter out unqualified items from the training result scoring table according to preset qualification standards, formulate a consolidation training plan based on the unqualified items and send it to the trainees for consolidation training, and update the training result scoring table according to the concentration analysis results and operation point analysis results of the consolidation training until all scores in the training result scoring table are qualified.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of a method for monitoring the effectiveness of cardiopulmonary resuscitation training for all citizens as described in any one of claims 1 to 7 are implemented.

10. A computer storage medium, characterized in that: The computer storage medium stores a computer program, which, when executed by a processor, implements the steps in a method for monitoring the effectiveness of cardiopulmonary resuscitation training for all as described in any one of claims 1 to 7.

Images