Home rehabilitation monitoring system for disabled

Abstract

The invention discloses a household rehabilitation monitoring system for the disabled, and relates to the technical field of medical rehabilitation, and the system comprises the following components: a VR training platform, an electroencephalogram acquisition and processing module, a brain wave analysis and feedback module, and a personalized training content generation module. By integrating the VR training platform and the electroencephalogram collection and analysis technology, high personalization and intelligentization of rehabilitation training are achieved, the system can analyze electroencephalogram signals of a user in real time, the attention level, the emotional state and the rehabilitation progress of the user are accurately evaluated, the training difficulty and content are dynamically adjusted accordingly, and the rehabilitation training effect is improved. The real-time feedback and adjustment mechanism ensures that rehabilitation training is always matched with the current state of the user, so that the rehabilitation training effect is remarkably improved, meanwhile, generation of personalized training content meets specific requirements of different users, and the training experience and satisfaction degree of the user are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical rehabilitation, in particular to a home rehabilitation monitoring system for disabled persons. Background Art

[0002] With the rapid development of science and technology, intelligent rehabilitation technology is increasingly used in the medical field, especially in helping the disabled to conduct home rehabilitation. Traditional rehabilitation methods are limited by the lack of venues, equipment and professionals, and it is difficult to meet the growing rehabilitation needs of the disabled. The introduction of virtual reality (VR) technology has provided new possibilities for rehabilitation training. By constructing a realistic virtual environment, patients can conduct rehabilitation training in a safe and risk-free environment, which greatly improves the fun and participation of rehabilitation.

[0003] However, traditional VR rehabilitation training systems still have some significant limitations in practical applications. First, they mostly rely on external devices (such as handles, sensors, etc.) as interactive media. These devices not only increase the complexity of use, but may also restrict the user's natural movement patterns, reducing the realism and effectiveness of rehabilitation training. Secondly, traditional systems lack a real-time and accurate evaluation mechanism for the user's internal state. Usually, they can only judge the progress of rehabilitation based on the user's external performance (such as the completion of movements), and cannot directly monitor the user's internal state, such as attention level, emotional changes, etc. These states are crucial to the effectiveness of rehabilitation training. In addition, traditional systems often lack personalized adjustment mechanisms and cannot dynamically adjust the difficulty and content of training according to the user's real-time state, thereby affecting the pertinence and effectiveness of rehabilitation training.

[0004] In view of the above problems, it is necessary to optimize the existing home rehabilitation monitoring system for the disabled, evaluate the user's internal state by real-time monitoring of the user's brain wave changes, and automatically adjust the training difficulty and content accordingly to achieve home rehabilitation training. Therefore, it is of great significance to develop a home rehabilitation monitoring system for the disabled that can comprehensively realize the above characteristics. Summary of the invention

[0005] The purpose of the present invention is to make up for the deficiencies of the prior art and to provide a home rehabilitation monitoring system for the disabled. It can monitor the user's brain wave changes in real time by combining VR technology with the brain wave feedback mechanism, accurately assess the user's attention level, emotional state and rehabilitation progress, and automatically adjust the training difficulty and content accordingly to achieve personalized and efficient home rehabilitation training. This innovative combination not only improves the pertinence and effectiveness of rehabilitation training, but also greatly enhances the user's experience and satisfaction, bringing new technological breakthroughs and development directions to the field of home rehabilitation for the disabled.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a home rehabilitation monitoring system for the disabled, the system comprising the following components: a VR training platform, an EEG acquisition and processing module, an EEG analysis and feedback module, and a personalized training content generation module;

[0007] The VR training platform uses VR technology to construct rehabilitation training scenarios, allowing users to perform rehabilitation training in a virtual environment;

[0008] The EEG acquisition and processing module includes an EEG acquisition device and a signal processing unit, wherein the EEG acquisition device is placed close to the user's scalp to collect the user's brain wave signals in real time, and the signal processing unit processes the collected brain wave signals to extract key indicators related to attention, emotional state and rehabilitation progress;

[0009] The brainwave analysis and feedback module performs intelligent analysis on the processed brainwave signals based on the algorithm, evaluates the user's attention level, emotional state and rehabilitation progress in real time, and automatically adjusts the training difficulty and content in the VR training platform according to the evaluation results;

[0010] The personalized training content generation module generates personalized training content according to the results of the intelligent analysis and feedback module.

[0011] Furthermore, when the user wears the EEG acquisition device, the EEG acquisition and processing module starts to collect the user's brain wave signals in real time, and pre-processes the collected original signals. It extracts characteristic parameters related to attention, emotional state and rehabilitation progress from the pre-processed signals through algorithms, and stores the processed brain wave data and characteristic parameters in a local or cloud database for subsequent analysis.

[0012] Furthermore, the EEG acquisition and processing module extracts characteristic parameters related to attention, emotional state and rehabilitation progress from the preprocessed signal through an algorithm. Specifically, the collected original EEG signal is preprocessed to obtain the preprocessed EEG signal x(t), and discrete wavelet transform is applied to the preprocessed EEG signal x(t), wherein the wavelet transform formula is: Where W(m,n) is the wavelet coefficient, ψ m,n (t) is the wavelet function after scale expansion and time shift, L is the length of the preprocessed signal, and the characteristic parameters related to attention, emotional state and rehabilitation progress are extracted based on the obtained wavelet coefficients W(m,n).

[0013] Furthermore, the brainwave analysis and feedback module receives the brainwave data from the brainwave acquisition and processing module, uses an algorithm to perform intelligent analysis on the brainwave data, evaluates the user's attention level, emotional state and rehabilitation progress, makes corresponding decisions based on the evaluation results, generates corresponding feedback signals based on the decision results, and sends them to the VR training platform and personalized training content generation module through the control algorithm.

[0014] Furthermore, the brain wave analysis and feedback module uses an algorithm to perform intelligent analysis on brain wave data, and the algorithm formula is: S = w 1 ×A f +w 2 ×E f +w 3 ×P f +w 4 ×C, where S represents the comprehensive evaluation score, A f represents the attention feature evaluation value, E f represents the emotional state feature evaluation value, P f represents the rehabilitation progress feature evaluation value, C represents the signal complexity index, and w 1 、w 2 、w 3 、w 4 is the weight coefficient.

[0015] Furthermore, the brain wave analysis and feedback module formulates corresponding decision-making specific measures according to the evaluation results, including:

[0016] (1) For users with focused attention and stable emotions, the training difficulty is increased; for users with distracted attention or large emotional fluctuations, the training difficulty is reduced;

[0017] (2) Dynamically adjust the training content according to the user's rehabilitation progress and personalized needs. For users with faster progress, provide more high-level training tasks, and for users who need special attention, design targeted training programs;

[0018] (3) When negative emotions such as depression or anxiety are detected in users, psychological support information is automatically generated to help users adjust their emotional state;

[0019] (4) Reasonably arrange training frequency and duration based on the user’s physical condition and training results.

[0020] Furthermore, the brain wave analysis and feedback module generates a corresponding feedback signal according to the decision result, and sends it to the VR training platform and the personalized training content generation module through the control algorithm. The algorithm formula of the control algorithm is: Among them, U(t) is the adjustment amount, K p , Ki , K d They are proportional gain, integral gain and differential gain respectively, e(t) is the error between the set comprehensive training intensity index and the current training intensity, is the integral of the error, is the differential of the error, that is, the rate of change of the error over time.

[0021] Furthermore, the personalized training content generation module receives feedback signals and instructions from the intelligent analysis and feedback module, generates personalized training content based on the feedback results, and pushes the generated training content to the VR training platform. During or after the training, the effectiveness of the personalized training content is evaluated, and subsequent training plans are adjusted based on the evaluation results. By continuously collecting user feedback and training data, the generation algorithm and strategy of personalized training content are continuously optimized.

[0022] Furthermore, the personalized training content generation module continuously optimizes the generation algorithm and strategy of personalized training content by continuously collecting user feedback and training data. The calculation formula for the optimization is: Where: θ t+1 is the updated model parameter, θ t is the current model parameter, η is the learning rate, which controls the step size of parameter update, In the current dataset D t The gradient of the loss function L with respect to the model parameter θ, λ is the weight factor, Δθ hist It is the model parameter adjustment amount calculated based on the feedback results.

[0023] Compared with the existing technology, the home rehabilitation monitoring system for the disabled has the following beneficial effects:

[0024] 1. The present invention realizes highly personalized and intelligent rehabilitation training by integrating VR training platform with EEG acquisition and analysis technology. The system can analyze the user's brain wave signals in real time, accurately evaluate their attention level, emotional state and rehabilitation progress, and dynamically adjust the training difficulty and content accordingly. This instant feedback and adjustment mechanism ensures that the rehabilitation training always matches the user's current state, thereby significantly improving the effect of rehabilitation training. At the same time, the generation of personalized training content meets the specific needs of different users and improves the user's training experience and satisfaction.

[0025] 2. The present invention can automatically generate psychological support information for detected negative emotions such as depression or anxiety by identifying the user's emotional state, helping the user to adjust his or her emotional state. This immediate emotional support and psychological intervention not only helps to relieve the user's psychological pressure, but also enhances the user's confidence and enthusiasm for rehabilitation, thereby promoting the smooth progress of the rehabilitation process.

[0026] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 This is the process operation diagram of the home rehabilitation monitoring system for the disabled;

[0029] Figure 2 Flow chart of radio wave analysis and feedback in the home rehabilitation monitoring system for the disabled. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] Embodiment 1

[0032] This embodiment describes in detail the specific application process of the home rehabilitation monitoring system for the disabled. By integrating the VR training platform, EEG acquisition and processing module, EEG analysis and feedback module and personalized training content generation module, it provides users with rich and diverse VR training scenarios and personalized rehabilitation plans.

[0033] The user should first ensure that all devices (including VR helmets, controllers, EEG acquisition devices, etc.) are correctly connected and in working condition, start the system, and perform initialization settings, including user identity authentication, device calibration, etc., and wear a dry electrode cap or other EEG acquisition device according to the instructions to ensure that the electrodes are in close contact with the scalp to obtain high-quality EEG signals.

[0034] Use a VR helmet to enter preset rehabilitation training scenarios, such as simulated outdoor walking environments, stair climbing, etc. These scenarios are designed to simulate real-life sports scenes to help users conduct targeted rehabilitation training.

[0035] The EEG acquisition device begins to collect the user's brain wave signals in real time and transmits the signals to the signal processing unit. The signal processing unit preprocesses the original signals, including filtering, denoising and other steps, and uses algorithms to extract characteristic parameters related to attention, emotional state and rehabilitation progress from the preprocessed signals. These parameters include brain wave power and coherence in specific frequency bands.

[0036] The EEG analysis and feedback module receives the processed EEG data and uses algorithms for intelligent analysis. The analysis process includes evaluating the user's attention level (such as whether they are focused), emotional state (such as anxiety or depression), and rehabilitation progress (such as the recovery of motor function). According to the evaluation results, the module automatically adjusts the training difficulty and content in the VR training platform. For example, if the user is focused and emotionally stable, the system may increase the training difficulty, such as increasing walking speed or adding obstacles. Otherwise, the difficulty will be reduced to avoid frustration or discomfort for the user. According to the adjustment content, the corresponding feedback signal is generated and sent to the VR training platform and personalized training content generation module through the control algorithm. The algorithm formula of the control algorithm is: Among them, U(t) is the adjustment amount, K p , K i , K d They are proportional gain, integral gain and differential gain respectively, e(t) is the error between the set comprehensive training intensity index and the current training intensity, is the integral of the error, is the differential of the error, that is, the rate of change of the error over time.

[0037] The personalized training content generation module generates personalized training content suitable for the user's current status based on the results of the intelligent analysis and feedback module. These contents may include specific training tasks, scene settings, difficulty adjustments, etc., aiming to maximize the user's rehabilitation progress. The generated content is pushed to the VR training platform for the user to use in the next training.

[0038] During the entire training process, the system continuously monitors the user's brain wave changes and dynamically adjusts the training plan based on real-time feedback results. If the user becomes tired, inattentive or has mood swings, the system may automatically pause training, provide rest suggestions or adjust training content.

[0039] After the training, the system evaluates the effect of the training, including the user's rehabilitation progress, training completion, etc. Based on the evaluation results and user feedback, the system continuously optimizes the generation algorithm and strategy of personalized training content to provide a more accurate and personalized training plan for the next training. The optimization calculation formula is: Where: θ t+1is the updated model parameter, θ t is the current model parameter, η is the learning rate, which controls the step size of parameter update, In the current dataset D t The gradient of the loss function L with respect to the model parameter θ, λ is the weight factor, Δθ hist It is the model parameter adjustment amount calculated based on the feedback results. At the same time, the system records the user's training data, brain wave data and evaluation results in a local or cloud database for subsequent analysis and reference.

[0040] In summary, this embodiment achieves a high degree of personalization and intelligence in rehabilitation training by integrating the VR training platform with EEG acquisition and analysis technology. The system can analyze the user's brain wave signals in real time, accurately evaluate their attention level, emotional state and rehabilitation progress, and dynamically adjust the training difficulty and content accordingly. At the same time, the generation of personalized training content meets the specific needs of different users and improves the user's training experience and satisfaction.

[0041] Embodiment 2

[0042] Based on the first embodiment, this embodiment describes in detail the specific application of brain wave analysis and feedback in the home rehabilitation monitoring system for the disabled.

[0043] The user wears professional EEG acquisition equipment according to the system's instructions, ensuring that the electrodes are in close contact with the scalp to collect high-quality brain wave signals. After the system is started, it immediately begins to collect the user's brain wave data in real time and continuously, providing original material for subsequent analysis.

[0044] The collected original EEG signals first go through the preprocessing stage, using digital filters, denoising algorithms and other technologies to remove noise and artifacts in the signal to ensure the accuracy and reliability of the data. Then, the algorithm is used to conduct in-depth analysis of the preprocessed signals to extract characteristic parameters closely related to attention and emotional state. Specifically, the collected original EEG signals are preprocessed to remove noise and artifacts to obtain the preprocessed EEG signals x(t). Discrete wavelet transform is applied to the preprocessed EEG signals x(t), where the wavelet transform formula is: Where W(m,n) is the wavelet coefficient, ψ m,n (t) is the wavelet function after scale expansion and time shift, L is the length of the preprocessed signal, and the characteristic parameters related to attention, emotional state and rehabilitation progress are extracted based on the obtained wavelet coefficients W(m,n). These parameters may include power spectral density, coherence, asymmetry, etc. in different frequency bands.

[0045] After receiving the extracted characteristic parameters, the EEG analysis and feedback module uses an algorithm for intelligent analysis. The algorithm formula is: S = w 1 ×Af +w 2 ×E f +w 3 ×P f +w 4 ×C, where S represents the comprehensive evaluation score, A f represents the attention feature evaluation value, E f represents the emotional state feature evaluation value, P f represents the rehabilitation progress feature evaluation value, C represents the signal complexity index, and w 1 、w 2 、w 3 、w 4 The system uses the weight coefficient to determine whether the user maintains sufficient concentration to complete the training task based on the comprehensive evaluation score. At the same time, the system also pays special attention to changes in EEG characteristics related to negative emotions such as depression, such as signs of reduced alpha wave activity and increased beta wave activity, to identify the user's emotional state.

[0046] Once the system detects that the user is in a negative emotional state, it immediately activates the psychological support mechanism. Specific measures include:

[0047] (1) Play soothing music or natural sounds to help users relax and relieve tension;

[0048] (2) Provide positive motivational words or stories to enhance users’ self-confidence and positive attitude;

[0049] (3) It is recommended that users perform relaxation exercises such as deep breathing and meditation to calm their emotions and restore their attention.

[0050] At the same time, the system will provide real-time feedback of the user's emotional state to the personalized training content generation module so that corresponding adjustments can be made in subsequent training. According to the evaluation results of the emotional state, the system will dynamically adjust the training difficulty and content in the VR training platform. For emotionally unstable users, the system will take the following measures:

[0051] (1) For users with focused attention and stable emotions, the training difficulty is appropriately increased; for users with distracted attention or large emotional fluctuations, the training difficulty is reduced;

[0052] (2) Dynamically adjust the training content according to the user's rehabilitation progress and personalized needs. For users with faster progress, provide more high-level training tasks, and for users who need special attention, design targeted training programs;

[0053] (3) When negative emotions such as depression or anxiety are detected in users, psychological support information is automatically generated to help users adjust their emotional state;

[0054] (4) Reasonably arrange training frequency and duration based on the user’s physical condition and training results.

[0055] With the continuous accumulation of user feedback and training data, the system continues to optimize the generation algorithm of psychological support information and the generation strategy of personalized training content, and uses big data analysis technology to explore the patterns of user behavior and emotional changes, providing more accurate and personalized support for subsequent rehabilitation training. At the same time, the system also regularly updates and upgrades its algorithms and models to meet the diverse needs of users and the ever-changing rehabilitation environment.

[0056] To sum up, this embodiment can automatically generate psychological support information for detected negative emotions such as depression or anxiety by identifying the user's emotional state, so as to help the user adjust his or her emotional state. This immediate emotional support and psychological intervention not only helps to relieve the user's psychological pressure, but also enhances the user's confidence and enthusiasm for rehabilitation, thereby promoting the smooth progress of the rehabilitation process.

[0057] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. The home rehabilitation monitoring system for the disabled is characterized by: The system includes the following components: VR training platform, EEG acquisition and processing module, EEG analysis and feedback module, and personalized training content generation module; The VR training platform uses VR technology to construct rehabilitation training scenarios, allowing users to perform rehabilitation training in a virtual environment; The EEG acquisition and processing module includes an EEG acquisition device and a signal processing unit, wherein the EEG acquisition device is placed close to the user's scalp to collect the user's brain wave signals in real time, and the signal processing unit processes the collected brain wave signals to extract key indicators related to attention, emotional state and rehabilitation progress; The brainwave analysis and feedback module performs intelligent analysis on the processed brainwave signals based on the algorithm, evaluates the user's attention level, emotional state and rehabilitation progress in real time, and automatically adjusts the training difficulty and content in the VR training platform according to the evaluation results; The personalized training content generation module generates personalized training content according to the results of the intelligent analysis and feedback module.

2. The home rehabilitation monitoring system for the disabled according to claim 1 is characterized in that: When the user wears the EEG acquisition device, the EEG acquisition and processing module starts to collect the user's brain wave signals in real time, and pre-processes the collected original signals. It extracts characteristic parameters related to attention, emotional state and rehabilitation progress from the pre-processed signals through algorithms, and stores the processed brain wave data and characteristic parameters in a local or cloud database for subsequent analysis.

3. The home rehabilitation monitoring system for the disabled according to claim 2 is characterized in that: The EEG acquisition and processing module extracts characteristic parameters related to attention, emotional state and rehabilitation progress from the preprocessed signal through an algorithm. Specifically, the collected original EEG signal is preprocessed to obtain the preprocessed EEG signal x(t), and discrete wavelet transform is applied to the preprocessed EEG signal x(t), wherein the wavelet transform formula is: Among them, W(m,n) is the wavelet coefficient, ψ m,n (t) is the wavelet function after scale expansion and time shift, L is the length of the preprocessed signal, and the characteristic parameters related to attention, emotional state and rehabilitation progress are extracted based on the obtained wavelet coefficients W(m,n).

4. The home rehabilitation monitoring system for the disabled according to claim 1, characterized in that: The brainwave analysis and feedback module receives the brainwave data from the brainwave acquisition and processing module, uses an algorithm to perform intelligent analysis on the brainwave data, evaluates the user's attention level, emotional state and rehabilitation progress, makes corresponding decisions based on the evaluation results, generates corresponding feedback signals based on the decision results, and sends them to the VR training platform and the personalized training content generation module through the control algorithm.

5. The home rehabilitation monitoring system for the disabled according to claim 4 is characterized in that: The EEG analysis and feedback module uses an algorithm to perform intelligent analysis on the EEG data, and the algorithm formula is: S = w1 × A f +w2×E f +w3×P f +w4×C, where S represents the comprehensive evaluation score, A f represents the attention feature evaluation value, E f represents the emotional state feature evaluation value, P f represents the characteristic evaluation value of rehabilitation progress, C represents the signal complexity index, and w1, w2, w3, and w4 are weight coefficients.

6. The home rehabilitation monitoring system for the disabled according to claim 4 is characterized in that ,The brain wave analysis and feedback module formulates corresponding ,decision-making specific measures according to the evaluation results, including: (1) For users with focused attention and stable emotions, the training difficulty is increased; for users with distracted attention or large emotional fluctuations, the training difficulty is reduced; (2) Dynamically adjust the training content according to the user's rehabilitation progress and personalized needs. For users with faster progress, provide more high-level training tasks, and for users who need special attention, design targeted training programs; (3) When negative emotions such as depression or anxiety are detected in users, psychological support information is automatically generated to help users adjust their emotional state; (4) Reasonably arrange training frequency and duration based on the user’s physical condition and training results.

7. The home rehabilitation monitoring system for the disabled according to claim 4 is characterized in that ,The brain wave analysis and feedback module generates the corresponding feedback ,signal according to the decision result, and sends it to the VR training ,platform and personalized training content generation module through the control ,algorithm. The algorithm formula of the control algorithm is: Among them, U(t) is the adjustment amount, K p , K i , K d They are proportional gain, integral gain and differential gain respectively, e(t) is the error between the set comprehensive training intensity index and the current training intensity, is the integral of the error, is the differential of the error, that is, the rate of change of the error over time.

8. The home rehabilitation monitoring system for the disabled according to claim 1 is characterized in that ,The personalized training content generation module receives feedback signals and instructions from the ,intelligent analysis and feedback module, generates personalized ,training content based on the feedback results, and pushes the generated training ,content to the VR training platform. During or after the training process, ,the effect of the personalized training content is evaluated, and ,the subsequent training plan is adjusted according to the evaluation results. ,By continuously collecting user feedback and training data, the generation algorithm and ,strategy of personalized training content is continuously optimized.

9. The home rehabilitation monitoring system for the disabled according to claim 8 is characterized in that The personalized training content generation module continuously collects user feedback and training data to continuously optimize the generation algorithm and strategy of personalized training content. The calculation formula for optimization is: Where: θ t+1 is the updated model parameter, θ t is the current model parameter, η is the learning rate, which controls the step size of parameter update, In the current dataset D t The gradient of the loss function L with respect to the model parameter θ, λ is the weight factor, Δθ hist It is the model parameter adjustment amount calculated based on the feedback results.

Images