Remote monitoring system for nervous system based on intelligent wearable device

Abstract

The invention relates to the technical field of medical equipment, in particular to a nervous system remote monitoring system based on intelligent wearable equipment, which comprises a sensor module, a data processing module, a real-time monitoring module, a remote transmission module, a feedback and intervention module, a data storage and analysis module and a user interface module. The sensor module collects nervous system signals of a human body, the data processing module conducts denoising, feature extraction and mode recognition on the nervous system signals and generates warning signals, the remote transmission module transmits data to a remote server or a medical terminal, and the feedback and intervention module provides health suggestions and triggers intervention measures according to monitoring results. The data storage and analysis module performs comprehensive analysis on long-term monitoring data by using a big data analysis technology, and the user interface module provides visual display through a smart phone or wearable equipment. According to the system, real-time monitoring, remote diagnosis and personalized health management of the nervous system are realized, and the system has wide clinical application value.

Description

Technical Field

[0001] The present invention relates to the technical field of medical equipment, and in particular to a remote monitoring system for a nervous system based on an intelligent wearable device. Background Art

[0002] The diagnosis and monitoring of neurological diseases has always been an important research direction in the medical field. Early detection and real-time management of such diseases usually require monitoring of physiological signals such as electroencephalograms and electromyograms. With the rapid development of smart wearable devices and wireless communication technologies, remote monitoring of the nervous system based on wearable devices has gradually become an efficient and convenient solution, providing new possibilities for early diagnosis, treatment evaluation and health management of neurological diseases.

[0003] Although some nervous system monitoring technologies based on smart wearable devices have been launched, the following problems still need to be solved in practical applications: First, existing sensors are susceptible to noise interference and wearing position deviation when collecting neural signals, and the signal acquisition accuracy and stability are insufficient; second, the complexity and dynamic variability of neural signals place high demands on data processing. Existing technologies are inefficient in denoising, feature extraction and pattern recognition, and it is difficult to achieve real-time analysis. Third, in the remote transmission link, existing systems are susceptible to fluctuations in the network environment and lack stability and data security guarantees; finally, existing technologies lack the ability to comprehensively analyze long-term monitoring data, and are unable to track health trends and accurately predict diseases. Summary of the invention

[0004] The present invention provides a remote monitoring system for the nervous system based on an intelligent wearable device.

[0005] A remote monitoring system for the nervous system based on an intelligent wearable device, comprising a sensor module, a data processing module, a real-time monitoring module, a remote transmission module, a feedback and intervention module, a data storage and analysis module and a user interface module, wherein;

[0006] The sensor module is used to collect human nervous system signals, and the nervous system signals include electroencephalogram signals and electromyogram signals;

[0007] The data processing module includes a signal denoising unit, a feature extraction unit and a pattern recognition unit, wherein;

[0008] The signal denoising unit uses a filtering algorithm to remove noise from the nervous system signal;

[0009] The feature extraction unit extracts key features in the nervous system signal based on a preset algorithm, and the key features include average value, root mean square value, frequency peak value and power spectrum density;

[0010] The pattern recognition unit uses machine learning algorithms to analyze collected nervous system signals, identify potential risks of nervous system abnormalities, and provide real-time abnormality detection and early warning;

[0011] The real-time monitoring module is used to monitor the output from the data processing module in real time and evaluate the state changes of the nervous system in real time. The real-time monitoring module adopts a dynamic threshold adjustment mechanism to automatically adjust the threshold according to the individual differences of the patients. If the monitored neural signal exceeds the set threshold, the real-time monitoring module sends a warning signal to prompt the user or medical personnel to handle it;

[0012] The remote transmission module is used to transmit the output of the data processing module and the real-time monitoring module to a remote server or a medical terminal through wireless communication;

[0013] The feedback and intervention module feeds back the monitoring results to the patient or medical staff through the smart wearable device or the mobile phone APP connected to the patient according to the analysis results of the real-time monitoring module, and provides personalized health management suggestions;

[0014] The data storage and analysis module is used to store the collected nervous system signals and the processing results of the data processing module, and to conduct a comprehensive analysis of the long-term monitoring data through big data analysis technology, so as to track the health change trend of the patient and provide a scientific basis for disease prediction and treatment decision-making;

[0015] The user interface module is used to display real-time monitoring data, health trend analysis, early warning information and health advice to patients and doctors.

[0016] Optionally, the sensor module includes:

[0017] The sensor module includes a plurality of microelectrodes and sensor units for respectively collecting electroencephalogram signals and electromyogram signals;

[0018] The microelectrodes are made of flexible conductive materials, which have good skin fit and conductivity, ensuring the accuracy of signal acquisition. The sensor unit is integrated on a flexible substrate through a flexible circuit board;

[0019] Microelectrodes are placed at specific locations on the head to collect EEG signals according to the international 10-20 system, and EMG electrodes are attached to target muscle groups to capture EMG signals generated by muscle activity;

[0020] The flexible conductive material has breathable, waterproof and antibacterial properties;

[0021] The sensor module adopts an adjustable wearing structure, combined with a flexible strap or patch design, and is fixed on different parts of the human body.

[0022] Optionally, the denoising unit specifically includes:

[0023] Data reception and preprocessing: receiving the EEG signals and EMG signals collected by the sensor module, and performing segmented processing on the EEG signals and EMG signals;

[0024] Bandpass filtering: Use a bandpass filter to remove low-frequency baseline drift and high-frequency noise in neural system signals;

[0025] Adaptive noise removal: The filtered neural system signal is refined and denoised through an adaptive filtering algorithm.

[0026] Optionally, the feature extraction unit includes:

[0027] Time domain feature extraction: Extract time domain features from nervous system signals. Time domain features include average value, root mean square value and signal energy.

[0028] Frequency domain feature extraction: Convert the signal to the frequency domain through fast Fourier transform and extract the frequency peak and power spectral density.

[0029] Optionally, the pattern recognition unit of the data processing module classifies and recognizes the neural signal based on the deep learning model, including:

[0030] Input data preparation: receiving the output of the feature extraction unit, including time domain features and frequency domain features, and constructing the extracted time domain features and frequency domain features into feature vectors;

[0031] Classification model selection and training: Based on the constructed feature vector, the support vector machine algorithm is used to build a pattern recognition model;

[0032] Model training process: The labeled historical neural system signal features are used as training data input, and the objective function is optimized using the gradient descent method;

[0033] Online pattern recognition: Input new nervous system signal features into the trained pattern recognition model in real time, and determine whether the signal state is normal or abnormal based on the decision function.

[0034] Optionally, the real-time monitoring module includes:

[0035] Input data reception: receiving the classification results (normal or abnormal) and abnormal pattern labels output by the pattern recognition unit, and receiving the real-time neural system signal feature values ​​output by the data processing module for status assessment;

[0036] Dynamic threshold adjustment: Dynamically adjust the monitoring threshold based on the patient's individual information (including age, medical history, and health status);

[0037] State deviation analysis: compare the real-time nervous system signal characteristic value and dynamic threshold, calculate the state deviation degree, and determine whether the nervous system signal state is normal or abnormal;

[0038] Warning signal generation and prompting: In the event of abnormal status, a warning signal is generated and sent to the patient or medical staff through the user interface module;

[0039] Data recording and transmission: Real-time monitoring results are recorded in the data storage and analysis module for long-term trend analysis, and abnormal warning signals are transmitted to the feedback and intervention module for further health management.

[0040] Optionally, the feedback and intervention module includes:

[0041] Data reception: Real-time reception of status assessment results from the real-time monitoring module, including classification results (normal or abnormal), status deviation degree, dynamic thresholds, and warning signals;

[0042] Feedback information generation: When the status is normal, provide patients with general health advice, such as daily routine adjustments or precautions. When the status is abnormal, generate personalized health feedback information based on the abnormality type.

[0043] Data recording and optimization: All feedback and intervention records are stored in the data storage and analysis module for subsequent analysis and optimization.

[0044] Optionally, the data storage and analysis module includes:

[0045] Data reception and storage: Receive the nervous system signals (including EEG and EMG signals) collected by the sensor module, receive the processing results output by the data processing module, including denoised signals, feature extraction data and pattern recognition results, and classify and store the received data according to timestamps.

[0046] Long-term data accumulation: The results of the real-time monitoring module and the feedback and intervention module are recorded as time series data for long-term monitoring and analysis, integrating the patient's individual information (such as age, medical history) with health monitoring data to form a health record for the entire life cycle;

[0047] Health trend analysis: Predict the health change trend of patients based on the pre-trained ARIMA model, analyze the fluctuation range of patients' health status, and identify potential risk trends;

[0048] Comprehensive analysis of big data: Use cluster analysis algorithms (such as K-means) to group long-term data of different patients and identify groups with similar health patterns.

[0049] Optionally, the user interface module includes:

[0050] The real-time changes of EEG and EMG are displayed through dynamic charts, which can directly reflect the state of the nervous system;

[0051] Display the patient's long-term health status changes and predicted results through health trend charts (such as risk change curves);

[0052] Highlight abnormal conditions and warning signals in the user interface in the form of color markings or pop-up windows, including abnormality type, severity and handling suggestions;

[0053] Display personalized health advice in the form of cards or text prompts, including lifestyle adjustment suggestions, review plans or treatment recommendations;

[0054] The user interface module supports multiple language options, allowing users to switch the interface language according to their needs;

[0055] Support users to adjust data display method (such as selecting line chart or bar chart), set reminder frequency and preferred content.

[0056] Optionally, the remote transmission module includes:

[0057] Data integration and packaging: Receive the processing results of the data processing module, including denoised signals, feature data and pattern recognition results, receive the status assessment results of the real-time monitoring module, including classification results, dynamic thresholds and warning signals, integrate and standardize them, and generate transmission data packets marked with timestamps;

[0058] Wireless communication protocol selection: Select a low-latency, high-bandwidth communication protocol based on transmission requirements;

[0059] Real-time transmission: Use multi-threaded transmission technology to transmit multiple data streams in parallel to ensure the real-time nature of the data;

[0060] Data security: End-to-end encryption of transmitted data;

[0061] Remote server and medical end receiving: The transmitted data packets are sent to the remote server for storage and processing.

[0062] Beneficial effects of the present invention:

[0063] The present invention realizes the accurate acquisition of key nervous system signals (EEG and EMG) by designing a flexible sensor module that fits the human body. It combines the efficient data processing capabilities of signal denoising, feature extraction and pattern recognition units to greatly improve the acquisition and analysis accuracy of neural signals. The real-time monitoring module adopts a dynamic threshold adjustment mechanism, which fully considers the individual differences of patients and ensures the personalization and accuracy of the monitoring results. This precise data acquisition and processing system can identify abnormalities of the nervous system in real time, providing a scientific basis for early warning and personalized intervention of diseases.

[0064] The present invention realizes real-time feedback and secure transmission of monitoring data through the collaborative work of the feedback and intervention module and the remote transmission module. Smart wearable devices and mobile phone APP provide patients with intuitive monitoring results display and personalized health advice. The doctor can obtain patient status information in real time and formulate treatment plans in time. The remote transmission module adopts a variety of communication protocols (such as 5G, Wi-Fi) and encryption technology to ensure the real-time and security of data transmission, and can operate stably even in complex network environments. This design builds an efficient and reliable remote interaction system between patients and medical staff.

[0065] In the present invention, the data storage and analysis module supports the dynamic tracking of patients' health trends through the storage of long-term monitoring data and big data analysis technology. Based on the comprehensive evaluation of time series analysis and clustering algorithms, it can identify potential risks, predict disease development trends, and provide doctors with scientific treatment optimization suggestions. In addition, through the linkage with the real-time monitoring module and the feedback and intervention module, the present invention realizes the organic combination of historical records, real-time status and future predictions at the data level, providing strong technical support for the comprehensive management of neurological diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0067] Figure 1 A schematic diagram of a system flow of an embodiment of the present invention;

[0068] Figure 2 The figure is a flowchart of a data processing module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0069] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0070] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0071] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0072] like Figure 1-Figure 2 As shown, a remote monitoring system of the nervous system based on intelligent wearable devices includes a sensor module, a data processing module, a real-time monitoring module, a remote transmission module, a feedback and intervention module, a data storage and analysis module and a user interface module, wherein;

[0073] The sensor module is used to collect human nervous system signals, including electroencephalogram signals and electromyogram signals;

[0074] The data processing module includes a signal denoising unit, a feature extraction unit and a pattern recognition unit, wherein;

[0075] The signal denoising unit uses a filtering algorithm to remove noise from the nervous system signal;

[0076] The feature extraction unit extracts key features in the nervous system signal based on a preset algorithm, and the key features include average value, root mean square value, frequency peak value and power spectrum density;

[0077] The pattern recognition unit uses machine learning algorithms to analyze collected nervous system signals, identify potential risks of nervous system abnormalities, and provide real-time abnormality detection and early warning;

[0078] The real-time monitoring module is used to monitor the output from the data processing module in real time and evaluate the state changes of the nervous system in real time. The real-time monitoring module adopts a dynamic threshold adjustment mechanism to automatically adjust the threshold according to the individual differences of patients. If the monitored neural signal exceeds the set threshold, the real-time monitoring module will issue a warning signal to prompt the user or medical staff to handle it;

[0079] The remote transmission module is used to transmit the output of the data processing module and the real-time monitoring module to the remote server or medical terminal through wireless communication, ensuring that the doctor can obtain the patient's nervous system status information in a timely manner;

[0080] The feedback and intervention module feeds back the monitoring results to patients or medical staff through smart wearable devices or mobile phone apps connected to patients based on the analysis results of the real-time monitoring module, and provides personalized health management suggestions;

[0081] The data storage and analysis module is used to store the collected nervous system signals and the processing results of the data processing module, and conduct a comprehensive analysis of long-term monitoring data through big data analysis technology, track the health change trend of patients, and provide a scientific basis for disease prediction and treatment decisions;

[0082] The user interface module is used to display real-time monitoring data, health trend analysis, early warning information and health advice to patients and doctors.

[0083] The sensor module includes:

[0084] The sensor module includes a plurality of microelectrodes and sensor units for collecting electroencephalogram signals and electromyogram signals respectively;

[0085] The microelectrodes are made of flexible conductive materials, which have good skin adhesion and conductivity, ensuring the accuracy of signal acquisition. The sensor unit is integrated on a flexible substrate through a flexible circuit board, which can dynamically fit with human body movements and is suitable for long-term wear.

[0086] Microelectrodes are placed at specific locations on the head to collect EEG signals according to the international 10-20 system, and EMG electrodes are attached to target muscle groups to capture EMG signals generated by muscle activity;

[0087] The sensor unit preliminarily amplifies the collected weak electrical signals through a high-sensitivity signal amplifier to enhance the signal quality;

[0088] Flexible conductive materials are breathable, waterproof and antibacterial, which can improve wearing comfort. The materials include polymer substrates (such as PDMS or TPU) and flexible electrodes printed with conductive ink, which take into account durability and flexibility.

[0089] The sensor module adopts an adjustable wearing structure, combined with a flexible strap or patch design, which can be fixed on different parts of the human body and supports multiple removal and re-wearing. It avoids irritation to the skin through non-invasive connection, further improving the wearing experience.

[0090] The sensor module transmits the collected signals to the data processing module via low-power Bluetooth or other wireless protocols.

[0091] The denoising unit specifically includes:

[0092] Data reception and preprocessing: receiving the EEG signals and EMG signals collected by the sensor module, and performing segmented processing on the EEG signals and EMG signals;

[0093] Bandpass filtering: A bandpass filter is used to filter out low-frequency baseline drift and high-frequency noise in the nervous system signal. The filter is designed to meet the following transfer function:

[0094]

[0095] Where H(f) is the frequency response function of the filter, f L is the low frequency cutoff frequency, f H is the high frequency cutoff frequency, and the filtering range of the EEG signal is set to f L =0.5Hz, f H =50Hz, the filter range of the electromyography signal is set to f L =20Hz, f H =500Hz;

[0096] Adaptive noise removal: The filtered neural system signal is refined and denoised by an adaptive filtering algorithm. The target signal is expressed as:

[0097] s(t)=x(t)-αn(t);

[0098] Where x(t) is the input signal, n(t) is the noise signal, and α is the adaptive noise suppression coefficient, which is obtained by minimum mean square error (MSE) optimization.

[0099] The feature extraction unit includes:

[0100] Time domain feature extraction: Extract time domain features from nervous system signals. Time domain features include average value, root mean square value and signal energy, among which;

[0101] The mean is calculated as:

[0102] Among them, x i is the time domain signal value, μ is the signal average value, and N is the number of sampling points;

[0103] The RMS value is calculated as:

[0104] Where RMS is the root mean square value, x i is the time domain signal value, N is the number of sampling points;

[0105] The signal energy is calculated as:

[0106] Where E is the signal energy, x i is the time domain signal value, N is the number of sampling points;

[0107] Frequency domain feature extraction: The signal is converted to the frequency domain through fast Fourier transform, and the frequency peak and power spectrum density are extracted. The fast Fourier transform is calculated as:

[0108]

[0109] Among them, X(f) is the frequency domain signal value, and N is the number of sampling points.

[0110] The pattern recognition unit of the data processing module classifies and recognizes neural signals based on a deep learning model, including:

[0111] Input data preparation: Receive the output of the feature extraction unit, including time domain features and frequency domain features, and construct the extracted time domain features and frequency domain features into feature vectors, expressed as:

[0112] x=[x1,x2,…,x n ], where x n is the nth eigenvalue, n is the number of features;

[0113] Classification model selection and training: Based on the constructed feature vector, the support vector machine algorithm is used to build a pattern recognition model. The model objective function is defined as:

[0114]

[0115] sty i (w·x i +b)≥1-ξ i ,ξ i ≥0

[0116] Among them, w is the weight vector of the pattern recognition model, b is the classification bias term, ξ i is a slack variable, indicating the allowable range of classification error, C is a penalty coefficient, controlling the balance between classification accuracy and model generalization ability, and y i is the label of sample i (+1 or -1), x i is the feature vector of sample i, and m is the total number of training samples;

[0117] Model training process: The labeled historical neural system signal features are used as training data input, and the objective function is optimized using the gradient descent method to solve the optimal model parameters;

[0118] Online pattern recognition: Input new neural signal features into the trained pattern recognition model in real time, and determine whether the signal state is normal or abnormal based on the decision function. The decision function is expressed as:

[0119] f(x)=sign(w·x+b);

[0120] Among them, x is the input feature vector, w is the weight vector, b is the classification bias term, and f(x) is the classification decision function;

[0121] When f(x)>0, it is judged to be in normal state;

[0122] When f(x)≤0, it is judged as an abnormal state;

[0123] Classification result delivery: The classification results (normal or abnormal) and abnormal pattern labels are delivered to the real-time monitoring module for further evaluation and dynamic monitoring.

[0124] The real-time monitoring module includes:

[0125] Input data reception: receiving the classification results (normal or abnormal) and abnormal pattern labels output by the pattern recognition unit, and receiving the real-time neural system signal feature values ​​output by the data processing module for status assessment;

[0126] Dynamic threshold adjustment: Combined with the patient's individual information (including age, medical history, and health status), the monitoring threshold is dynamically adjusted, expressed as:

[0127] T i =T0+β1·P a +β2·P h +β3·P d ;

[0128] Among them, T i is the dynamic threshold, T0 is the initial threshold, β1, β2, β3 are individual feature weight factors, P a is the patient age parameter, P h is the patient health parameter, P d Patient history parameters;

[0129] State deviation analysis: Compare the real-time nervous system signal characteristic value and dynamic threshold, calculate the state deviation degree, and determine whether the nervous system signal state is normal or abnormal, expressed as:

[0130]

[0131] If D≤0, the status is judged to be normal;

[0132] If D>0, the state is determined to be abnormal and a warning signal is triggered;

[0133] Warning signal generation and prompting: In the event of abnormal status, a warning signal is generated and sent to the patient or medical staff through the user interface module;

[0134] Data recording and transmission: Real-time monitoring results are recorded in the data storage and analysis module for long-term trend analysis, and abnormal warning signals are transmitted to the feedback and intervention module for further health management.

[0135] The feedback and intervention modules include:

[0136] Data reception: Real-time reception of status assessment results from the real-time monitoring module, including classification results (normal or abnormal), status deviation degree, dynamic thresholds, and warning signals;

[0137] Feedback information generation: When the status is normal, provide patients with routine health advice, such as daily routine adjustments or precautions. When the status is abnormal, generate personalized health feedback information based on the abnormality type, including:

[0138] The type of abnormality (e.g., abnormal EEG signal or abnormal EMG signal);

[0139] Health risk level (mild, moderate or severe);

[0140] Recommended treatment (such as contacting a doctor immediately, increasing rest time, or adjusting medication).

[0141] Feedback forms and delivery: Feedback information is delivered to patients or medical staff through the following channels:

[0142] Smart wearable devices: remind patients to pay attention to their health status through the display screen or vibration prompts on the device;

[0143] Mobile application (APP): push detailed monitoring reports and suggestions, including real-time data, trend analysis charts and health management tips;

[0144] Telemedicine terminal: Sends patient monitoring data and warning information to doctors to assist them in remote diagnosis.

[0145] When serious abnormalities are detected, health intervention measures are automatically triggered, including:

[0146] Send high-priority alerts to patients, reminding them to seek medical attention immediately;

[0147] Generate a personalized review plan (such as recommending that patients recollect monitoring data within a certain period of time);

[0148] Provide preventive advice (such as adjusting diet, increasing exercise, or reducing stress).

[0149] Data recording and optimization: All feedback and intervention records are stored in the data storage and analysis module for subsequent analysis and optimization.

[0150] Data storage and analysis modules include:

[0151] Data reception and storage: Receive nervous system signals (including EEG and EMG signals) collected by the sensor module, receive the processing results output by the data processing module, including denoised signals, feature extraction data and pattern recognition results, classify and store the received data by timestamp, and use a distributed storage system to improve the reliability and scalability of data storage. Use the Advanced Encryption Standard (AES-256) to encrypt data to ensure data privacy and security.

[0152] Long-term data accumulation: The results of the real-time monitoring module and the feedback and intervention module are recorded as time series data for long-term monitoring and analysis, integrating the patient's individual information (such as age, medical history) with health monitoring data to form a health record for the entire life cycle;

[0153] Health trend analysis: Based on the pre-trained ARIMA model, the patient's health change trend is predicted, the fluctuation range of the patient's health status is analyzed, and potential risk trends are identified, which are expressed as:

[0154] y t =c+φ1y t-1 +φ2y t-2 +…+φ p y t-p +∈ t +θ1∈ t-1 +…+θ q ∈ t-q ;

[0155] Among them, y t is the predicted value of the current health status, c is a constant term, φ1, φ2,…, φ p is the autoregressive coefficient, ∈ t : Random error, θ1, θ2, …, θ q is the moving average coefficient, p,q is the model order;

[0156] Comprehensive analysis of big data: Use cluster analysis algorithms (such as K-means) to group the long-term data of different patients and identify groups with similar health patterns, expressed as:

[0157]

[0158] Among them, J is the clustering objective function, k is the number of clusters, C i is the i-th cluster, x j is the jth data point, μ i is the i-th cluster center;

[0159] Provides a reference for health trends in patient groups and supports early prevention and precision treatment of diseases.

[0160] The user interface module includes:

[0161] The real-time changes of EEG and EMG are displayed through dynamic charts, which can directly reflect the state of the nervous system;

[0162] Display the patient's long-term health status changes and predicted results through health trend charts (such as risk change curves);

[0163] Highlight abnormal status and warning signals in the user interface in the form of color marking or pop-up windows, including abnormal type, severity and handling suggestions;

[0164] Display personalized health advice in the form of cards or text prompts, including lifestyle adjustment suggestions, review plans or treatment recommendations;

[0165] The user interface module supports multiple language options, allowing users to switch the interface language according to their needs;

[0166] It supports users to adjust the data display method (such as selecting a line chart or a bar chart), set reminder frequency and preferred content (such as only receiving specific types of health tips).

[0167] The remote transmission module includes:

[0168] Data integration and packaging: Receive the processing results of the data processing module, including denoising signals, feature data and pattern recognition results, receive the status assessment results of the real-time monitoring module, including classification results, dynamic thresholds and warning signals, integrate and standardize them, and generate a timestamp-marked transmission data packet P(t), expressed as:

[0169] P(t)={T s ,S processed ,F monitoring ,M classification};

[0170] Among them, T s is the timestamp, S processed is the denoised neural signal data, F monitoring To monitor the status results in real time, M classification Classify results for pattern recognition;

[0171] Wireless communication protocol selection: Select low-latency, high-bandwidth communication protocols (such as 5G or Wi-Fi) based on transmission requirements. When the network environment is limited, automatically switch to low-power Bluetooth or narrowband Internet of Things (NB-IoT) protocols to ensure the stability of data transmission;

[0172] Real-time transmission: Use multi-threaded transmission technology to transmit multiple data streams in parallel to ensure the real-time nature of the data;

[0173] Data security: End-to-end encryption of transmitted data, using the Advanced Encryption Standard (AES-256) and Transport Layer Security (TLS) to ensure data security during transmission;

[0174] Remote server and medical end receiving: The transmitted data packets are sent to the remote server for storage and processing. The medical end can obtain the patient's nervous system status information in real time. The data includes real-time monitoring data, abnormal warning signals and health management suggestions.

[0175] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0176] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A remote monitoring system for the nervous system based on smart wearable devices, characterized in that: It includes a sensor module, a data processing module, a real-time monitoring module, a remote transmission module, a feedback and intervention module, a data storage and analysis module and a user interface module, among which; The sensor module is used to collect human nervous system signals, and the nervous system signals include electroencephalogram signals and electromyogram signals; The data processing module includes a signal denoising unit, a feature extraction unit and a pattern recognition unit, wherein; The signal denoising unit uses a filtering algorithm to remove noise from the nervous system signal; The feature extraction unit extracts key features in the nervous system signal based on a preset algorithm, and the key features include average value, root mean square value, frequency peak value and power spectrum density; The pattern recognition unit uses machine learning algorithms to analyze collected nervous system signals, identify potential risks of nervous system abnormalities, and provide real-time abnormality detection and early warning; The real-time monitoring module is used to monitor the output from the data processing module in real time and evaluate the state changes of the nervous system in real time. The real-time monitoring module adopts a dynamic threshold adjustment mechanism to automatically adjust the threshold according to the individual differences of the patients. If the monitored neural signal exceeds the set threshold, the real-time monitoring module sends a warning signal to prompt the user or medical personnel to handle it; The remote transmission module is used to transmit the output of the data processing module and the real-time monitoring module to a remote server or a medical terminal through wireless communication; The feedback and intervention module feeds back the monitoring results to the patient or medical staff through the smart wearable device or the mobile phone APP connected to the patient according to the analysis results of the real-time monitoring module, and provides personalized health management suggestions; The data storage and analysis module is used to store the collected nervous system signals and the processing results of the data processing module, and to conduct a comprehensive analysis of the long-term monitoring data through big data analysis technology, so as to track the health change trend of the patient and provide a scientific basis for disease prediction and treatment decision-making; The user interface module is used to display real-time monitoring data, health trend analysis, early warning information and health advice to patients and doctors.

2. A remote monitoring system for the nervous system based on smart wearable devices according to claim 1, characterized in that: The sensor module comprises: The sensor module includes a plurality of microelectrodes and sensor units for respectively collecting electroencephalogram signals and electromyogram signals; The microelectrodes are made of flexible conductive materials, and the sensor units are integrated on a flexible substrate via a flexible circuit board; Microelectrodes are placed at specific locations on the head to collect EEG signals according to the international 10-20 system, and EMG electrodes are attached to target muscle groups to capture EMG signals generated by muscle activity; The flexible conductive material has breathable, waterproof and antibacterial properties; The sensor module adopts an adjustable wearing structure, combined with a flexible strap or patch design, and is fixed on different parts of the human body.

3. A remote monitoring system for the nervous system based on smart wearable devices according to claim 2, characterized in that: The denoising unit specifically includes: Data reception and preprocessing: receiving the EEG signals and EMG signals collected by the sensor module, and performing segmented processing on the EEG signals and EMG signals; Bandpass filtering: Use a bandpass filter to remove low-frequency baseline drift and high-frequency noise in neural system signals; Adaptive noise removal: The filtered neural system signal is refined and denoised through an adaptive filtering algorithm.

4. A remote monitoring system for the nervous system based on smart wearable devices according to claim 3, characterized in that: The feature extraction unit comprises: Time domain feature extraction: Extract time domain features from nervous system signals. Time domain features include average value, root mean square value and signal energy. Frequency domain feature extraction: Convert the signal to the frequency domain through fast Fourier transform and extract the frequency peak and power spectral density.

5. A remote monitoring system for the nervous system based on smart wearable devices according to claim 4, characterized in that: The pattern recognition unit of the data processing module classifies and recognizes the neural signal based on the deep learning model, including: Input data preparation: receiving the output of the feature extraction unit, including time domain features and frequency domain features, and constructing the extracted time domain features and frequency domain features into feature vectors; Classification model selection and training: Based on the constructed feature vector, the support vector machine algorithm is used to build a pattern recognition model; Model training process: The labeled historical neural system signal features are used as training data input, and the objective function is optimized using the gradient descent method; Online pattern recognition: Input new nervous system signal features into the trained pattern recognition model in real time, and determine whether the signal state is normal or abnormal based on the decision function.

6. A remote monitoring system for the nervous system based on smart wearable devices according to claim 5, characterized in that: The real-time monitoring module includes: Input data reception: receiving the classification results and abnormal pattern labels output by the pattern recognition unit, and receiving the real-time neural system signal feature values ​​output by the data processing module for status assessment; Dynamic threshold adjustment: Dynamically adjust the monitoring threshold based on the patient's individual information; State deviation analysis: compare the real-time nervous system signal characteristic value and dynamic threshold, calculate the state deviation degree, and determine whether the nervous system signal state is normal or abnormal; Warning signal generation and prompting: In the event of abnormal status, a warning signal is generated and sent to the patient or medical staff through the user interface module; Data recording and transmission: Real-time monitoring results are recorded in the data storage and analysis module for long-term trend analysis, and abnormal warning signals are transmitted to the feedback and intervention module.

7. A remote monitoring system for the nervous system based on smart wearable devices according to claim 6, characterized in that: The feedback and intervention module includes: Data reception: Real-time reception of status assessment results from the real-time monitoring module, including classification results (normal or abnormal), status deviation degree, dynamic thresholds, and warning signals; Feedback information generation: Provide patients with routine health advice when the status is normal, and generate personalized health feedback information based on the abnormality type when the status is abnormal; Data recording and optimization: All feedback and intervention records are stored in the data storage and analysis module for subsequent analysis and optimization.

8. A remote monitoring system for the nervous system based on smart wearable devices according to claim 7, characterized in that: The data storage and analysis module includes: Data reception and storage: Receive the nervous system signals collected by the sensor module, receive the processing results output by the data processing module, including denoised signals, feature extraction data and pattern recognition results, and classify and store the received data according to timestamps; Long-term data accumulation: The results of the real-time monitoring module and the feedback and intervention module are recorded as time series data for long-term monitoring and analysis, integrating the patient's individual information and health monitoring data to form a health record for the entire life cycle; Health trend analysis: Predict the health change trend of patients based on the pre-trained ARIMA model, analyze the fluctuation range of patients' health status, and identify potential risk trends; Comprehensive analysis of big data: Use cluster analysis algorithms to group long-term data of different patients and identify groups with similar health patterns.

9. A remote monitoring system for the nervous system based on smart wearable devices according to claim 8, characterized in that: The user interface module comprises: Display the real-time changes of EEG and EMG through dynamic charts; Display the patient's long-term health status changes and predicted results through health trend charts; Highlight abnormal conditions and warning signals in the user interface through color coding or pop-up windows; Display personalized health advice in the form of cards or text prompts, including lifestyle adjustment suggestions, review plans or treatment recommendations; The user interface module supports multiple language options, allowing users to switch the interface language according to their needs; Support users to adjust data display method, set reminder frequency and preferred content.

10. A remote monitoring system for the nervous system based on smart wearable devices according to claim 9, characterized in that: The remote transmission module comprises: Data integration and packaging: Receive the processing results of the data processing module, including denoised signals, feature data and pattern recognition results, receive the status assessment results of the real-time monitoring module, including classification results, dynamic thresholds and warning signals, integrate and standardize them, and generate transmission data packets marked with timestamps; Wireless communication protocol selection: Select the communication protocol based on transmission requirements. The communication protocols include 5G and Wi-Fi. Real-time transmission: Use multi-threaded transmission technology to transmit multiple data streams in parallel; Data security: End-to-end encryption of transmitted data; Remote server and medical end receiving: The transmitted data packets are sent to the remote server for storage and processing.

Images