Wrist signal collecting and processing method and system based on biological tissue analysis

Abstract

The invention relates to the technical field of medical monitoring, in particular to a wrist signal collecting and processing method and system based on biological tissue analysis. The system is used for generating wrist multi-signal acquisition optimization equipment by designing and integrating wrist wearable equipment corresponding to a photoelectric volume pulse wave sensor, an electrocardio sensor and a skin electric response sensor and performing position structure optimization design; the method comprises the following steps: acquiring PPG signals, ECG signals and GSR signals corresponding to wrist biological tissues in real time by using wrist multi-signal acquisition optimization equipment, and performing high-frequency drift preprocessing and biological tissue characteristic analysis to obtain a wrist biological tissue signal characteristic set; and performing feature redundancy and dimension reduction processing on the wrist biological tissue signal feature set, and performing wrist physiological state assessment analysis to obtain a wrist biological tissue state assessment result. According to the invention, accurate acquisition and analysis of wrist signals can be realized, so that reliable data support is provided for personalized analysis.

Description

Technical Field

[0001] The present invention relates to the field of medical monitoring technology, and in particular to a wrist signal acquisition and processing method and system based on biological tissue analysis. Background Art

[0002] Wrist signal acquisition technology has shown great potential in the field of health monitoring due to its convenience and non-invasiveness. Wrist biological tissue contains rich physiological information, such as PPG signals that reflect heart rate and blood oxygen saturation, ECG signals that reflect cardiac electrical activity, GSR signals that reflect skin electrical response, etc., and is susceptible to various interferences during wrist signal acquisition, such as motion artifacts, environmental noise, and crosstalk between signals, which leads to a decrease in signal quality and seriously affects the accuracy of subsequent analysis. However, traditional wrist signal processing systems mostly focus on filtering and noise reduction of single signals, lack consideration of collaborative processing of multi-source signals, and are difficult to effectively solve the problems of interference and drift between signals. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a wrist signal acquisition and processing method and system based on biological tissue analysis to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a wrist signal acquisition and processing system based on biological tissue analysis includes the following modules: Wrist device sensor optimization design module, used to design wrist wearable devices corresponding to integrated photoelectric volumetric pulse wave sensors, electrocardiogram sensors and skin galvanic response sensors; obtain the distribution characteristics of wrist biological tissues, and optimize the position structure of wrist wearable devices based on the distribution characteristics of wrist biological tissues to generate wrist multi-signal acquisition optimization devices; The wrist multi-signal preprocessing module is used to collect PPG signals, ECG signals and GSR signals corresponding to wrist biological tissue in real time by using wrist multi-signal acquisition optimization equipment to generate wrist biological tissue PPG signals, wrist biological tissue ECG signals and wrist biological tissue GSR signals; perform high-frequency drift preprocessing on the wrist biological tissue PPG signals, wrist biological tissue ECG signals and wrist biological tissue GSR signals, so as to generate PPG clear signals, ECG clear signals and GSR clear signals; A biological tissue feature analysis module is used to perform biological tissue feature analysis on a PPG clear signal, an ECG clear signal, and a GSR clear signal, thereby obtaining a wrist biological tissue signal feature set; The wrist biometric state assessment module is used to perform feature redundancy and dimensionality reduction processing on the wrist biological tissue signal feature set to generate a wrist biological tissue signal feature vector; and use a convolutional neural network to perform wrist physiological state assessment and analysis on the wrist biological tissue signal feature vector to obtain a wrist biological tissue state assessment result.

[0005] Furthermore, the wrist device sensor optimization design module includes the following functions: By designing a wrist wearable device that integrates a photoelectric volumetric pulse wave sensor, an electrocardiogram sensor, and a galvanic skin response sensor; Obtain the distribution characteristics of wrist biological tissues, including the distribution location of the radial artery, wrist muscles and wrist nerves; Based on the distribution of the radial artery on the wrist, the PPG sensor in the wrist wearable device is optimized to accurately align the photoplethysmography sensor with the distribution of the radial artery on the wrist, and the flexible bonding technology is used to ensure that the sensor is in close contact with the wrist skin to generate an optimized design scheme for the pulse wave sensor position; Based on the distribution of wrist muscles, the ECG electrode layout of the ECG sensor in the wrist wearable device is optimized to generate an optimized design scheme for the ECG sensor electrode layout; based on the distribution of wrist nerves, the skin interference optimization design of the skin galvanic response sensor in the wrist wearable device is optimized to generate an optimized design scheme for skin galvanic response sensor interference; Based on the pulse wave sensor position optimization design scheme, the ECG sensor electrode layout optimization design scheme and the skin galvanic response sensor interference optimization design scheme, the corresponding positions and layout structures of the photoelectric capacitance pulse wave sensor, ECG sensor and skin galvanic response sensor in the wrist wearable device are optimized to generate a wrist multi-signal acquisition optimization device.

[0006] Furthermore, the optimization of the ECG electrode layout of the electrocardiogram sensor in the wrist wearable device based on the distribution position of the wrist muscles includes: Based on the distribution position of wrist muscles, the muscle electrical interference influence calculation formula is used to calculate the electrical interference influence of the electrode layout corresponding to the ECG sensor in the wrist wearable device to obtain the ECG electrode layout electrical interference influence factor; Based on the ECG electrode layout electrical interference influencing factors, the ECG electrode layout of the ECG sensor in the wrist wearable device is optimized to generate an optimized design scheme for the ECG sensor electrode layout.

[0007] Furthermore, the muscle electrical interference influence calculation formula is specifically: ; In the formula, The electrical interference influencing factor for ECG electrode layout, is the space where the wrist-worn device is located. Layout of the ECG sensing electrodes, is the number of muscle electrical activity distribution points, For the The muscle activity points are located The intensity of muscle electrical activity at is the maximum intensity of muscle electrical activity, For the The weight of the influence of each muscle activity point on electrical interference, is an exponential function, For the The layout position corresponding to the muscle activity point, For the The standard deviation of the layout position corresponding to the muscle activity point, is the maximum frequency of muscle electrical activity, is the interference regulation coefficient of muscle electrical activity, Correction factor for the electrical interference factor of ECG electrode layout.

[0008] Furthermore, the wrist multi-signal preprocessing module includes the following functions: The photoelectric volume pulse wave sensor in the wrist multi-signal acquisition optimization device is used to collect the PPG signal corresponding to the wrist biological tissue in real time to generate the wrist biological tissue PPG signal; The ECG signal corresponding to the wrist biological tissue is collected in real time by using the ECG sensor in the wrist multi-signal acquisition optimization device to generate the wrist biological tissue ECG signal; The skin galvanic response sensor in the wrist multi-signal acquisition optimization device is used to collect the GSR signal corresponding to the wrist biological tissue in real time to generate the wrist biological tissue GSR signal; The wrist biological tissue PPG signal, the wrist biological tissue ECG signal and the wrist biological tissue GSR signal are subjected to high-frequency drift preprocessing to generate a PPG clear signal, an ECG clear signal and a GSR clear signal.

[0009] Further, the high-frequency drift preprocessing of the wrist biological tissue PPG signal, the wrist biological tissue ECG signal and the wrist biological tissue GSR signal includes: Performing timestamp alignment and synchronization processing on wrist biological tissue PPG signals, wrist biological tissue ECG signals and wrist biological tissue GSR signals, so as to compensate for the time deviation corresponding to the signals based on the interpolation algorithm, and ensure that the wrist biological tissue PPG signals, ECG signals and GSR signals are completely aligned on the time axis, so as to obtain a wrist biological tissue multi-source synchronous alignment signal set; Performing wavelet transform decomposition on the wrist biological tissue multi-source synchronous alignment signal set to separate the high-frequency and low-frequency components in the wrist biological tissue signal to obtain the wrist biological tissue multi-source high-frequency signal and the wrist biological tissue multi-source low-frequency signal; Performing high-frequency drift dynamic compensation on multi-source high-frequency signals of wrist biological tissue to obtain high-frequency drift compensation signals of wrist biological tissue; Performing low-frequency noise elimination processing on the multi-source low-frequency signals of the wrist biological tissue to further eliminate the residual noise in the low-frequency components corresponding to the wrist biological tissue signals to obtain the wrist biological tissue low-frequency noise removal signal; Multimodal signal fusion is performed on the high-frequency drift compensation signal of wrist biological tissue and the low-frequency noise removal signal of wrist biological tissue to generate a multimodal clear signal map of wrist biological tissue; based on the multimodal clear signal map of wrist biological tissue and combined with the signal reconstruction method, the wrist biological tissue PPG signal, wrist biological tissue ECG signal and wrist biological tissue GSR signal are reconstructed and output as clear signals to generate PPG clear signal, ECG clear signal and GSR clear signal.

[0010] Furthermore, the high-frequency drift dynamic compensation of multi-source high-frequency signals of wrist biological tissue includes: Performing high-frequency drift component analysis on multi-source high-frequency signals of wrist biological tissue to generate a high-frequency drift component map of wrist biological tissue; Performing high-frequency baseline drift fitting processing on the high-frequency drift component spectrum of wrist biological tissue to obtain the high-frequency baseline drift signal tensor of wrist biological tissue; Based on the high-frequency baseline drift signal tensor of the wrist biological tissue, high-frequency drift dynamic compensation is performed on the multi-source high-frequency signal of the wrist biological tissue to obtain the high-frequency drift compensation signal of the wrist biological tissue.

[0011] Furthermore, the biological tissue feature analysis module includes the following functions: The corresponding pulse wave rise time and pulse wave fall time are obtained through the PPG clear signal, and the peak amplitude and dicrotic fluctuation characteristics of the PPG clear signal are analyzed based on the pulse wave rise time and pulse wave fall time to obtain the pulse wave PPG signal fluctuation characteristics, including the fluctuation amplitude and fluctuation phase corresponding to the pulse wave peak and dicrotic; Perform ECG signal feature analysis on the corresponding P wave group, QRS wave group and T wave group in the ECG clear signal to obtain ECG signal fluctuation features, including the amplitude, width and shape of the P wave, QRS wave and T wave; The skin conductance characteristics of the GSR clear signal are analyzed to obtain the fluctuation characteristics of the skin conductance GSR signal, including the skin conductance change rate and the skin conductance fluctuation mean; The pulse wave PPG signal fluctuation features, electrocardiogram ECG signal fluctuation features and skin conductance GSR signal fluctuation features are merged to obtain the wrist biological tissue signal feature set.

[0012] Furthermore, the wrist biometric status assessment module includes the following functions: Performing feature redundancy removal on a wrist biological tissue signal feature set to obtain a wrist biological tissue signal redundancy removal feature set; Performing principal component feature dimensionality reduction processing on the redundant removal feature set of wrist biological tissue signal, and combining them to form a comprehensive feature vector, so as to generate a wrist biological tissue signal feature vector; Performing feature space topological distribution analysis on wrist biological tissue signal feature vectors to obtain the wrist biological tissue signal feature space distribution density; Based on the spatial distribution density of wrist biological tissue signal features and combined with convolutional neural networks, an adaptive convolution kernel is designed to capture the global features of wrist biological tissue signals using a 5x5 convolution kernel in the signal feature area corresponding to dense features and gentle changes, and to capture the local detail features of wrist biological tissue signals using a 1x1 convolution kernel in the signal feature area corresponding to sparse features and drastic changes, so as to design and generate a wrist feature enhanced adaptive convolution kernel model; The wrist feature enhanced adaptive convolution kernel model is used to perform multi-scale convolution operation on the wrist biological tissue signal feature vector to generate a wrist multi-scale convolution enhanced feature vector; the wrist state is evaluated based on the wrist multi-scale convolution enhanced feature vector and combined with the fuzzy logic reasoning method to obtain the wrist physiological tissue state evaluation index; the physiological assessment calibration is performed based on the wrist physiological tissue state evaluation index and combined with the multi-objective optimization algorithm to obtain the wrist biological tissue state evaluation result.

[0013] Furthermore, the present invention also provides a wrist signal acquisition and processing method based on biological tissue analysis, which is used to execute the wrist signal acquisition and processing system based on biological tissue analysis as described above. The wrist signal acquisition and processing method based on biological tissue analysis includes the following steps: Step S1: designing a wrist wearable device corresponding to an integrated photoelectric volumetric pulse wave sensor, an electrocardiogram sensor, and a galvanic skin response sensor; obtaining the distribution characteristics of wrist biological tissues, and optimizing the position structure of the wrist wearable device based on the distribution characteristics of wrist biological tissues to generate a wrist multi-signal acquisition optimization device; Step S2: using the wrist multi-signal acquisition optimization device to collect the PPG signal, ECG signal and GSR signal corresponding to the wrist biological tissue in real time to generate the wrist biological tissue PPG signal, wrist biological tissue ECG signal and wrist biological tissue GSR signal; performing high-frequency drift preprocessing on the wrist biological tissue PPG signal, wrist biological tissue ECG signal and wrist biological tissue GSR signal to generate PPG clear signal, ECG clear signal and GSR clear signal; Step S3: performing biological tissue feature analysis on the PPG clear signal, the ECG clear signal and the GSR clear signal to obtain a wrist biological tissue signal feature set; Step S4: performing feature redundancy and dimensionality reduction processing on the wrist biological tissue signal feature set to generate a wrist biological tissue signal feature vector; using a convolutional neural network to perform wrist physiological state assessment analysis on the wrist biological tissue signal feature vector to obtain a wrist biological tissue state assessment result.

[0014] Beneficial effects of the present invention: 1. The wrist signal acquisition and processing system based on biological tissue analysis proposed in the present invention has a beneficial effect compared with the prior art. By combining a photoplethysmogram (PPG) sensor, an electrocardiogram (ECG) sensor and a galvanic skin response (GSR) sensor, an integrated wrist wearable device is designed. Different sensors obtain relevant data of wrist biological tissue from different physiological signal angles. The PPG signal reflects changes in blood flow and can be used to monitor cardiovascular health; the ECG signal reflects the electrical activity of the heart and helps to evaluate heart rate and rhythm; the GSR signal provides information on skin response, which can be used to evaluate an individual's emotional response or stress level. The design of the wrist wearable device must be optimized based on the distribution characteristics of the wrist biological tissue to ensure that the sensor can accurately capture various signals. By studying the structure of different levels of biological tissue (such as skin, fat, muscle, etc.) on the wrist, designers can select appropriate positions and structures to optimize the sensor's acquisition effect and maximize the signal strength and accuracy. By integrating and optimizing these sensors, the device has efficient physiological data acquisition capabilities. Secondly, the PPG signal, ECG signal and GSR signal corresponding to the wrist biological tissue are collected in real time by using the wrist multi-signal acquisition optimization device. The main purpose of this step is to obtain multiple biological signals of the human wrist in real time through the wrist multi-signal acquisition device, and capture the PPG signal, ECG signal and GSR signal in real time through high-precision sensors. During the acquisition process, due to the complexity of the signal, there will be certain high-frequency drift noise (such as motion artifacts, ambient light interference, muscle contraction, etc.). Therefore, by performing high-frequency drift preprocessing on these signals, unnecessary noise and artifacts can be removed, thereby enhancing the clarity of the signal, making subsequent analysis more accurate and stable. The preprocessed signal is closer to the real physiological response of the human body, and can provide more accurate data support for the health status assessment of biological tissues. The processed signal can not only effectively reduce interference, but also improve the quality of the data, making the details of the signal clearer and more reliable, but also can fully consider the coordinated processing of multi-source signals, thereby effectively solving the problems of interference and high-frequency drift between signals. Then, by analyzing the biological tissue characteristics of the PPG clear signal, ECG clear signal, and GSR clear signal, the physiological characteristics of cardiovascular health, psychological state, etc. can be obtained through in-depth feature extraction of these signals, thereby providing a basis for subsequent physiological state assessment. Finally, feature redundancy and dimensionality reduction processing are performed on the wrist biological tissue signal feature set to extract representative features, thereby improving the efficiency and accuracy of data processing. Biological signals usually have high dimensions and complexity, which requires dimensionality reduction processing of the feature set for more efficient analysis and modeling. In the process of dimensionality reduction, those features that contribute little to the evaluation results or are redundant will be removed, and only the most recognizable features will be retained, thereby improving the effect of the analysis model.After dimensionality reduction, deep learning models such as convolutional neural networks (CNN) are used to analyze the biological signal feature vectors. These deep learning models can automatically extract useful patterns from the data and identify features related to physiological states such as health status, mood changes, and stress levels. The CNN model can effectively process complex signal data, identify deep features in the signal, and perform state assessment on this basis to obtain the state assessment results of the wrist biological tissue. This result can provide the wearer with real-time health feedback, such as heart health, emotional state, stress level, etc., to help users understand their physical condition in a timely manner and take corresponding measures to adjust it, thereby providing strong support for personalized health management.

[0015] 2. The wrist signal acquisition and processing method based on biological tissue analysis proposed in the present invention realizes any wrist signal acquisition and processing system based on biological tissue analysis described in the present invention, which is used to execute operations between computer programs running on various modules to realize biological tissue analysis, so that the internal structures of the system cooperate with each other and intelligently execute various processes of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings: Figure 1 It is a module schematic diagram of the wrist signal acquisition and processing system based on biological tissue analysis of the present invention; Figure 2 for Figure 1 Schematic diagram of the functional flow of the sensor optimization design module for the mid-wrist device. DETAILED DESCRIPTION

[0017] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0018] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0019] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0020] To achieve this, please refer to Figure 1 to Figure 2 The present invention provides a wrist signal acquisition and processing system based on biological tissue analysis, the system comprising the following modules: Wrist device sensor optimization design module, used to design wrist wearable devices corresponding to integrated photoelectric volumetric pulse wave sensors, electrocardiogram sensors and skin galvanic response sensors; obtain the distribution characteristics of wrist biological tissues, and optimize the position structure of wrist wearable devices based on the distribution characteristics of wrist biological tissues to generate wrist multi-signal acquisition optimization devices; The wrist multi-signal preprocessing module is used to collect PPG signals, ECG signals and GSR signals corresponding to wrist biological tissue in real time by using wrist multi-signal acquisition optimization equipment to generate wrist biological tissue PPG signals, wrist biological tissue ECG signals and wrist biological tissue GSR signals; perform high-frequency drift preprocessing on the wrist biological tissue PPG signals, wrist biological tissue ECG signals and wrist biological tissue GSR signals, so as to generate PPG clear signals, ECG clear signals and GSR clear signals; A biological tissue feature analysis module is used to perform biological tissue feature analysis on a PPG clear signal, an ECG clear signal, and a GSR clear signal, thereby obtaining a wrist biological tissue signal feature set; The wrist biometric state assessment module is used to perform feature redundancy and dimensionality reduction processing on the wrist biological tissue signal feature set to generate a wrist biological tissue signal feature vector; and use a convolutional neural network to perform wrist physiological state assessment and analysis on the wrist biological tissue signal feature vector to obtain a wrist biological tissue state assessment result.

[0021] In the embodiment of the present invention, please refer to Figure 1 FIG. 1 is a schematic diagram of a wrist signal acquisition and processing system based on biological tissue analysis of the present invention. In this example, the wrist signal acquisition and processing system based on biological tissue analysis includes the following modules: S1: Wrist device sensor optimization design module, which is used to design wrist wearable devices corresponding to integrated photoelectric volumetric pulse wave sensors, electrocardiogram sensors and skin galvanic response sensors; obtain the distribution characteristics of wrist biological tissues, and optimize the position structure of wrist wearable devices based on the distribution characteristics of wrist biological tissues to generate wrist multi-signal acquisition optimization devices; In an embodiment of the present invention, a wrist wearable device composed of an integrated photoplethysmogram (PPG) sensor, an electrocardiogram sensor (ECG), and a galvanic skin response sensor (GSR) is designed. First, the distribution characteristics of wrist biological tissues need to be clarified. By modeling the anatomical analysis of the wrist and the thickness of the biological tissues, the influence of wrist tissues on different sensor signals is determined. For example, an optical scanner is used to perform three-dimensional imaging of the blood vessels and muscle layers on the skin surface and below, and the absorption and reflection characteristics of the PPG signal are analyzed. The interference of the ECG signal by the fat layer and muscles of the wrist is further investigated. Based on these analyses, the sensor position and structural layout are optimized to ensure the maximum acquisition efficiency of the PPG, ECG, and GSR signals. During the design process, the comfort and wearing stability of the wrist device must be combined to ensure that the sensor can be accurately fixed on the target biological tissue layer, and finally the wrist multi-signal acquisition optimization device is optimized.

[0022] S2: a wrist multi-signal preprocessing module, which is used to collect PPG signals, ECG signals and GSR signals corresponding to wrist biological tissue in real time using a wrist multi-signal acquisition optimization device to generate wrist biological tissue PPG signals, wrist biological tissue ECG signals and wrist biological tissue GSR signals; perform high-frequency drift preprocessing on the wrist biological tissue PPG signals, wrist biological tissue ECG signals and wrist biological tissue GSR signals, so as to generate PPG clear signals, ECG clear signals and GSR clear signals; In the embodiment of the present invention, the wrist multi-signal acquisition optimization device is used to collect the corresponding PPG signal, ECG signal and GSR signal in the biological tissue in real time. The PPG signal is collected by contacting the integrated photoelectric sensor with the skin surface, and using the light source and the photodiode to measure the reflected light of the blood flow under the skin, so as to obtain the pulse waveform; the ECG signal is collected by detecting the weak electric field changes generated by the electrical activity of the heart through the electrode sensor attached to the skin surface; the GSR signal reflects the changes in emotion or the activity of the sweat glands through the changes in the conductivity of the skin surface. The collected signals are usually interfered by noise, especially high-frequency drift. To this end, in this step, each signal (PPG signal, ECG signal, GSR signal) is pre-processed for high-frequency drift, so that the high-frequency drift in the PPG signal is removed by using a bandpass filter to extract a clear pulse wave signal. For the ECG signal, the adaptive filtering technology is used to remove the high-frequency components introduced by poor electrode contact or environmental noise to ensure the clarity of the ECG signal. The low-frequency part of the GSR signal is amplified by a differential amplifier, and the power supply interference is removed by filtering to obtain a clean GSR signal, and finally a PPG clear signal, an ECG clear signal and a GSR clear signal are generated.

[0023] S3: biological tissue feature analysis module, used to perform biological tissue feature analysis on the PPG clear signal, the ECG clear signal and the GSR clear signal, so as to obtain a wrist biological tissue signal feature set; In an embodiment of the present invention, biological tissue feature analysis is performed after high-frequency drift preprocessing is performed on PPG, ECG and GSR signals. In the PPG signal analysis, features reflecting blood circulation and cardiovascular health, such as heart rate, pulse wave amplitude, etc., are extracted, and the mean, standard deviation and spectral features of the signal are calculated by combining time domain analysis and frequency domain analysis. In the ECG signal feature extraction process, attention is paid to the time and frequency features of key ECG waveforms such as P wave, QRS complex, and T wave, and physiological parameters such as heart rate variability and QT interval are extracted to further analyze the heart health status. For GSR signals, the changing pattern of skin conductance is extracted, and the emotional response or stress state of the individual is inferred by analyzing the changing trend of sweat gland activity. Through the extraction of these features, a feature set of wrist biological tissue signals is constructed, covering multi-dimensional physiological information such as cardiovascular system and emotional state, and finally a feature set of wrist biological tissue signals is obtained.

[0024] S4: Wrist biometric state assessment module, used to perform feature redundancy and dimensionality reduction processing on the wrist biological tissue signal feature set to generate a wrist biological tissue signal feature vector; use a convolutional neural network to perform wrist physiological state assessment and analysis on the wrist biological tissue signal feature vector to obtain a wrist biological tissue state assessment result.

[0025] In an embodiment of the present invention, feature redundancy and dimensionality reduction processing is performed on the feature sets of the extracted PPG clear signal, ECG clear signal, and GSR clear signal. In the feature redundancy processing process, the principal component analysis (PCA) method is used to remove redundant information in the signal to retain effective features that can reflect the physiological state to the greatest extent. For feature dimensionality reduction, independent component analysis (ICA) or linear discriminant analysis (LDA) is used to further reduce the dimension, eliminate noise and interference, and ensure that the extracted features are more concise and effective. The generated wrist biological tissue signal feature vector is then input into a convolutional neural network (CNN) for deep learning processing. Through the multi-layer convolution and pooling operations of CNN, the feature vector is evaluated and analyzed for the wrist physiological state in combination with the trained model. The convolutional neural network can automatically learn key physiological state patterns from the input signal features, and output comprehensive wrist biological tissue state evaluation results such as heart health status, stress level, emotional state, etc. This evaluation result provides a basis for further health monitoring and physiological state warning, and can reflect the wearer's physiological condition in real time, and finally obtain the wrist biological tissue state evaluation result.

[0026] Furthermore, the wrist device sensor optimization design module includes the following functions: By designing a wrist wearable device that integrates a photoelectric volumetric pulse wave sensor, an electrocardiogram sensor, and a galvanic skin response sensor; Obtain the distribution characteristics of wrist biological tissues, including the distribution location of the radial artery, wrist muscles and wrist nerves; Based on the distribution of the radial artery on the wrist, the PPG sensor in the wrist wearable device is optimized to accurately align the photoplethysmography sensor with the distribution of the radial artery on the wrist, and the flexible bonding technology is used to ensure that the sensor is in close contact with the wrist skin to generate an optimized design scheme for the pulse wave sensor position; Based on the distribution of wrist muscles, the ECG electrode layout of the ECG sensor in the wrist wearable device is optimized to generate an optimized design scheme for the ECG sensor electrode layout; based on the distribution of wrist nerves, the skin interference optimization design of the skin galvanic response sensor in the wrist wearable device is optimized to generate an optimized design scheme for skin galvanic response sensor interference; Based on the pulse wave sensor position optimization design scheme, the ECG sensor electrode layout optimization design scheme and the skin galvanic response sensor interference optimization design scheme, the corresponding positions and layout structures of the photoelectric capacitance pulse wave sensor, ECG sensor and skin galvanic response sensor in the wrist wearable device are optimized to generate a wrist multi-signal acquisition optimization device.

[0027] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1The functional flow diagram of the wrist device sensor optimization design module is shown in FIG. 1 . In this embodiment, the wrist device sensor optimization design module includes the following functions: S11: Design a wrist wearable device that integrates a photoelectric plethysmography sensor, an electrocardiogram sensor, and a galvanic skin response sensor; In an embodiment of the present invention, when designing a wrist wearable device integrating a photoelectric volumetric pulse wave sensor (PPG sensor), an electrocardiogram sensor (ECG sensor) and a galvanic skin response sensor (GSR sensor), the performance requirements of each sensor are first determined. The photoelectric volumetric pulse wave sensor needs to have high sensitivity to accurately capture the pulse waveform signal, the electrocardiogram sensor requires high electrode conductivity to obtain clear electrocardiogram signals, and the galvanic skin response sensor needs to have a strong response capability to the skin electrical signal. According to the performance requirements of each sensor, high-performance optical components, conductive electrode materials and high-precision current detection modules are used to ensure that the sensor can work stably. The fit between the wrist skin and the sensor must also be considered during the design, and flexible materials are used in combination with the sensor components. It is also ensured that each sensor has low power consumption, small size and is suitable for wrist wearing, so as to improve the comfort and use effect of the wearable device, and finally a wrist wearable device is designed and generated.

[0028] S12: Obtain the distribution characteristics of wrist biological tissues, including the distribution location of the radial artery, wrist muscles and wrist nerves; In an embodiment of the present invention, by utilizing medical imaging techniques, such as ultrasonic imaging, MRI imaging or CT scanning, detailed tissue structure information of the wrist is obtained, and these imaging data are analyzed by image processing software to accurately calibrate the specific positions and distribution characteristics of the radial artery, muscles and nerves at the wrist. The radial artery at the wrist is usually located on the palm side of the wrist close to the wrist, and is distributed more concentratedly; the wrist muscles are mainly distributed in the forearm area, especially near the radius; the wrist nerves are relatively thin, usually located in the area between the radial artery and the muscles. Based on these biological tissue distribution information, the next step of sensor optimization design is formulated, which can more accurately layout and position the sensors, and finally obtain the distribution characteristics of the wrist biological tissue, including the distribution position of the radial artery at the wrist, the distribution position of the wrist muscles, and the distribution position of the wrist nerves.

[0029] S13: Based on the distribution of the radial artery on the wrist, the PPG sensor in the wrist wearable device is optimized to accurately align the photoplethysmography sensor with the distribution of the radial artery on the wrist, and the flexible bonding technology is used to ensure that the sensor is in close contact with the wrist skin to generate an optimized design scheme for the pulse wave sensor position; In an embodiment of the present invention, when optimizing the design of the photoelectric volumetric pulse wave sensor based on the distribution position of the radial artery at the wrist, simulation software is first used to analyze the relationship between the position of the radial artery at the wrist and the blood flow, and the incident angle and detection angle of the photoelectric volumetric pulse wave sensor are accurately designed using optical principles to ensure that the sensor can be accurately aligned with the surface area of ​​the radial artery. Then, a flexible fitting technology is used to design an adaptable and comfortable fitting structure to ensure that the photoelectric volumetric pulse wave sensor is in close contact with the wrist skin to minimize the gap between the sensor and the skin, thereby ensuring accurate collection of the pulse wave signal. This design scheme also needs to take into account individual differences in wrist circumference, skin type, etc. of different users to ensure that the device has a certain adjustment space when worn to meet the needs of different users, and finally generate an optimized design scheme for the pulse wave sensing position.

[0030] S14: Optimize the ECG electrode layout of the ECG sensor in the wrist wearable device based on the distribution of wrist muscles to generate an optimized design scheme for the ECG sensor electrode layout; optimize the skin interference design of the skin galvanic response sensor in the wrist wearable device based on the distribution of wrist nerves to generate an optimized design scheme for skin galvanic response sensor interference; In an embodiment of the present invention, when optimizing the design of the ECG sensor based on the distribution position of wrist muscles, the relationship between the main position of the wrist area muscles and the ECG signal is first analyzed through the muscle distribution image data. The electrode layout of the ECG sensor must ensure that the electrophysiological activity signal of the wrist area can be captured. The electrode array design is adopted to ensure the accurate transmission of the ECG signal by accurately measuring the distance and angle between the electrodes, so as to design and generate an optimized design scheme for the ECG sensor electrode layout. As for the interference optimization design of the galvanic skin response sensor, considering the relationship between the position of the wrist nerves and the galvanic skin response signal, appropriate interference shielding technology is adopted, and the sensor is designed as a multi-layer structure to reduce the impact of external interference on the signal. In addition, the sensitivity of the galvanic skin response sensor is optimized so that it can capture the skin's electrical response signal more accurately, ensuring the validity and accuracy of the data, and finally generating a galvanic skin response sensor interference optimization design scheme.

[0031] S15: Based on the pulse wave sensor position optimization design scheme, the electrocardiogram sensor electrode layout optimization design scheme and the skin galvanic response sensor interference optimization design scheme, the position and layout structure of the photoelectric capacitance pulse wave sensor, electrocardiogram sensor and skin galvanic response sensor in the wrist wearable device are optimized to generate a wrist multi-signal acquisition optimization device.

[0032] In an embodiment of the present invention, based on the above-mentioned optimization scheme, when designing the specific layout of the photoelectric volumetric pulse wave sensor, the electrocardiogram sensor and the galvanic skin response sensor in the wrist wearable device, firstly, according to the distribution position of the radial artery, muscles and nerves, the optimal position of each sensor is accurately determined, and the layout of the sensor adopts a symmetrical design to ensure the accuracy of signal acquisition during wearing. In specific implementation, the photoelectric volumetric pulse wave sensor is designed to fit the wrist surface and accurately align with the radial artery position. The electrocardiogram sensor electrodes are arranged in an array according to the distribution of wrist muscles to ensure the optimal contact area. The layout of the galvanic skin response sensor is designed to minimize interference according to the nerve distribution. The overall structural design needs to take into account the lightness, comfort and stability of the device, and flexible materials and thin components are used to ensure the comfort of the wearing experience. Through structural optimization, an integrated, multi-signal acquisition, accurate and comfortable wrist wearable device is formed, and finally a wrist multi-signal acquisition optimization device is generated.

[0033] Furthermore, the optimization of the ECG electrode layout of the electrocardiogram sensor in the wrist wearable device based on the distribution position of the wrist muscles includes: Based on the distribution position of wrist muscles, the muscle electrical interference influence calculation formula is used to calculate the electrical interference influence of the electrode layout corresponding to the ECG sensor in the wrist wearable device to obtain the ECG electrode layout electrical interference influence factor; In an embodiment of the present invention, a suitable muscle electrical interference influence calculation formula is formed by combining the spatial area where the wrist wearable device is located, the layout position of the ECG sensor electrodes, the number of muscle electrical activity distribution points, the muscle electrical activity intensity, the maximum muscle electrical activity intensity, the influence weight of the muscle activity point on the electrical interference, the layout position corresponding to the muscle activity point, the standard deviation of the layout position corresponding to the muscle activity point, the maximum frequency of muscle electrical activity, the muscle electrical activity interference adjustment coefficient and related parameters to further accurately adjust the electrode spacing and electrode position, and then derive the electrical interference influence factor under each electrode layout, and finally obtain the ECG electrode layout electrical interference influence factor.

[0034] Preferably, the ECG electrode layout of the electrocardiogram sensor in the wrist wearable device is optimized based on the ECG electrode layout electrical interference influencing factor to generate an optimized design scheme for the electrocardiogram sensor electrode layout.

[0035] In the embodiment of the present invention, by combining the previously obtained ECG electrode layout electrical interference influence factor, the ECG electrode layout of the electrocardiogram sensor in the wrist wearable device is further optimized to generate an optimized electrode layout design scheme. During the implementation process, the previously calculated electrical interference influence factor is firstly used as an input parameter and considered as a key indicator in the optimization algorithm. The electrode position is optimized using a computer-aided design (CAD) tool and a finite element analysis (FEA) model. The optimization process relies on the dynamic simulation of electrical interference and combines the specific anatomical features of the human wrist area (such as bone structure, muscle The electrode position is adjusted according to the optimization process (such as the geometry of the electrode arrangement and the contact resistance between the electrode and the skin). Through the iterative adjustment algorithm, the influence factor of electrical interference is gradually reduced, and the electrode layout is optimized to improve the acquisition accuracy of ECG signals. Specifically, the optimization algorithm (such as genetic algorithm, particle swarm optimization, etc.) is used to automatically adjust the position, spacing and angle of the electrodes to ensure the optimal ECG signal acquisition effect and not be affected by the electrical interference of the wrist muscles. At the same time, the optimization process should also ensure the comfort and operability of the wearable device, and finally generate an optimized design scheme for the ECG sensor electrode layout.

[0036] Furthermore, the muscle electrical interference influence calculation formula is specifically: ; In the formula, The electrical interference influencing factor for ECG electrode layout, is the space where the wrist-worn device is located. Layout of the ECG sensing electrodes, is the number of muscle electrical activity distribution points, For the The muscle activity points are located The intensity of muscle electrical activity at is the maximum intensity of muscle electrical activity, For the The weight of the influence of each muscle activity point on the electrical interference, is an exponential function, For the The layout position corresponding to the muscle activity point, For the The standard deviation of the layout position corresponding to the muscle activity point, is the maximum frequency of muscle electrical activity, is the interference regulation coefficient of muscle electrical activity, Correction factor for the electrical interference factor of ECG electrode layout.

[0037] The present invention obtains a muscle electrical interference influence calculation formula by using a specific mathematical model and after verification, which is used to calculate the electrical interference influence of the electrode layout corresponding to the electrocardiogram sensor in the wrist wearable device. The muscle electrical interference influence calculation formula can accurately calculate the influence of muscle electrical interference on the electrocardiogram signal by considering factors such as muscle activity distribution, interference intensity, and electrode layout position. Through the integral formula, combined with the influence weight and muscle activity intensity of each muscle activity point, the interference degree of different position points on the ECG signal can be quantified, which can help identify which areas have a greater interference influence, thereby guiding the optimization of the electrode layout. The formula involves the integral calculation of the spatial area, which takes into account the relative relationship between the electrode layout position and the muscle activity point, which provides the designer with a basis for how to select the electrode position. By reducing the influence of muscle electrical activity interference, a better electrode layout can be designed to ensure the quality and accuracy of the ECG signal. Multiple parameters in the formula can be adjusted to reflect different environments or individual differences, such as the frequency and adjustment coefficient of muscle electrical activity can be adjusted for different application scenarios, providing flexibility, and by reasonably setting these parameters, the influence degree of electrical interference can be accurately controlled, making the optimization scheme more personalized and efficient. Since wrist-worn devices are often affected by muscle electrical interference, especially noise caused by wrist movement or muscle activity, optimizing the electrode layout through this formula can effectively reduce these interferences, thereby improving the quality of the ECG signal. By optimizing the electrode layout of the ECG sensor based on the electrical interference influencing factor, the wrist-worn device can be more adaptable to the physiological differences and movement states of different users. For example, the optimization algorithm can make the device adapt to differences in body shape, muscle activity intensity, frequency, etc., provide personalized signal acquisition solutions, and further improve the adaptability of the device and user experience. In addition, the correction coefficient in this formula can be used for further adjustment and optimization to reflect the deviations and errors in actual applications, and ensure that the ideal electrical interference impact assessment can be obtained in different application scenarios. This correction makes the calculation more accurate and avoids the error caused by environmental factors or individual differences. In summary, this formula fully considers the electrical interference influencing factor of the ECG electrode layout. , the space where the wrist wearable device is located , ECG sensor electrode layout location , the number of muscle electrical activity distribution points , No. The muscle activity points are located The intensity of muscle electrical activity , the maximum intensity of muscle electrical activity , No. The weight of the influence of muscle activity points on electrical interference , exponential function , No. The layout position corresponding to the muscle activity point , No. The standard deviation of the layout position corresponding to the muscle activity point , the maximum frequency of muscle electrical activity , muscle electrical activity interference regulation coefficient , correction coefficient of the influence factor of electrical interference of ECG electrode layout , according to the ECG electrode layout electrical interference influencing factors The correlation between the above parameters constitutes a functional relationship This formula can realize the calculation process of the electrical interference impact of the electrode layout corresponding to the ECG sensor in the wrist wearable device. At the same time, the correction coefficient of the electrical interference impact factor of the ECG electrode layout is used. The introduction of can be adjusted according to the errors that occur in the calculation process, thereby improving the accuracy and applicability of the calculation formula for the influence of muscle electrical interference.

[0038] Furthermore, the wrist multi-signal preprocessing module includes the following functions: The photoelectric volume pulse wave sensor in the wrist multi-signal acquisition optimization device is used to collect the PPG signal corresponding to the wrist biological tissue in real time to generate the wrist biological tissue PPG signal; In an embodiment of the present invention, in a wrist multi-signal acquisition optimization device, an integrated photoplethysmography (PPG) sensor is used to perform real-time signal acquisition on wrist biological tissue. The PPG sensor is composed of a light source and a photodetector. The light source emits light of a certain wavelength, which penetrates the epidermal tissue of the wrist and is reflected back to the photodetector. The detector obtains signal data related to blood flow according to the intensity change of the reflected light. By analyzing the light signal reflected from the wrist skin surface, the PPG signal of the wrist biological tissue is generated in real time. To ensure signal quality, the light source wavelength of the PPG sensor should be selected to be suitable for the skin permeability and blood absorption characteristics, such as red light or near-infrared light. During the data acquisition process, the processing module in the device performs preliminary filtering on the collected PPG signal to remove ambient light interference, and ensures the reliability of the signal through signal enhancement technology, and finally generates the PPG signal of the wrist biological tissue.

[0039] Preferably, the ECG signal corresponding to the wrist biological tissue is collected in real time by using the ECG sensor in the wrist multi-signal acquisition optimization device to generate the wrist biological tissue ECG signal; In an embodiment of the present invention, in a wrist multi-signal acquisition optimization device, real-time ECG signal acquisition is performed on wrist biological tissue through an integrated ECG sensor. The ECG sensor is attached to the skin surface through a group of electrodes to detect the electrical activity signal generated by the heart. The electrodes sense the heart's electric wave conduction signal through the skin potential difference and convert it into a digital signal. By analyzing the ECG signal, every electrical activity of the heart can be accurately captured, thereby generating an ECG signal of the wrist biological tissue, and finally generating an ECG signal of the wrist biological tissue.

[0040] Preferably, the skin galvanic response sensor in the wrist multi-signal acquisition optimization device is used to collect the GSR signal corresponding to the wrist biological tissue in real time to generate the wrist biological tissue GSR signal; In an embodiment of the present invention, in a wrist multi-signal acquisition optimization device, an integrated galvanic skin response (GSR) sensor is used to collect GSR signals of wrist biological tissue in real time. The GSR signal reflects the physiological and psychological state by measuring changes in skin conductivity. The sensor is usually composed of two electrodes, which contact the wrist skin and obtain the GSR signal by measuring changes in skin resistance. Skin conductance changes are related to sweat gland activity, and sweat secretion will cause changes in skin conductivity. During the signal acquisition process, the GSR sensor in the device monitors the fluctuation of skin conductance values ​​in real time, converts it into an electrical signal and outputs it as a GSR circuit signal, and finally generates a GSR signal of wrist biological tissue.

[0041] Preferably, high-frequency drift preprocessing is performed on the wrist biological tissue PPG signal, the wrist biological tissue ECG signal and the wrist biological tissue GSR signal to generate a PPG clear signal, an ECG clear signal and a GSR clear signal.

[0042] In an embodiment of the present invention, when performing high-frequency drift preprocessing on the PPG signal, ECG signal and GSR signal of the wrist biological tissue, the frequency domain filtering technology is used to process these signals. First, the original signal is converted from the time domain to the frequency domain using the fast Fourier transform (FFT), and the spectrum distribution of each signal is analyzed. In the PPG signal and the ECG signal, there are high-frequency drift components caused by power supply interference or other external factors, which will affect the accuracy of the signal. By setting the filter parameters, a low-pass filter is applied to remove signal components with a frequency higher than a specific threshold, such as interference signals above 50 Hz. For the GSR signal, a similar filtering method is also used to remove noise caused by ambient temperature changes or skin friction. After the frequency domain filtering process, the high-frequency drift components of the PPG signal, the ECG signal and the GSR signal are effectively removed, and clearer and more stable PPG clear signals, ECG clear signals and GSR clear signals are obtained, and finally PPG clear signals, ECG clear signals and GSR clear signals are generated.

[0043] Further, the high-frequency drift preprocessing of the wrist biological tissue PPG signal, the wrist biological tissue ECG signal and the wrist biological tissue GSR signal includes: Performing timestamp alignment and synchronization processing on wrist biological tissue PPG signals, wrist biological tissue ECG signals and wrist biological tissue GSR signals, so as to compensate for the time deviation corresponding to the signals based on the interpolation algorithm, and ensure that the wrist biological tissue PPG signals, ECG signals and GSR signals are completely aligned on the time axis, so as to obtain a wrist biological tissue multi-source synchronous alignment signal set; In an embodiment of the present invention, by ensuring that the timestamps of the PPG (photoplethysmogram) signal, ECG (electrocardiogram) signal and GSR (galvanic skin response) signal of the wrist biological tissue are completely aligned, this process is achieved through an interpolation algorithm. For the three signal sources, their sampling time points and corresponding numerical data are first extracted, and new data points are generated between their timestamps through an interpolation method, such as linear interpolation or cubic interpolation, so that the sampling times of the three signals are completely consistent. The interpolation process should be calculated based on the smallest time unit to ensure that the time intervals of the signals are accurately synchronized, thereby eliminating the time deviation caused by the inconsistent sampling frequencies of different signal sources. For the interpolated data, an error analysis is performed to ensure that the time deviation of all signals is less than a certain threshold to ensure the accuracy of synchronization. If the time deviation exceeds the predetermined threshold, interpolation correction is required again. Through these processes, it is ensured that the PPG signal, ECG signal and GSR signal are accurately aligned on the same time axis, and finally a multi-source synchronous alignment signal set of the wrist biological tissue is obtained.

[0044] Preferably, the multi-source synchronous alignment signal set of wrist biological tissue is decomposed by wavelet transform to separate the high-frequency and low-frequency components in the wrist biological tissue signal to obtain the multi-source high-frequency signal of wrist biological tissue and the multi-source low-frequency signal of wrist biological tissue; In an embodiment of the present invention, the synchronously aligned signal is decomposed by wavelet transform to separate the high-frequency and low-frequency components in the signal for subsequent high-frequency drift compensation and low-frequency noise removal. The wavelet transform uses a time-frequency analysis method based on wavelet function, which can obtain high resolution in time and frequency at the same time. Daubechies wavelet or Coiflet wavelet is selected for signal decomposition. Discrete wavelet transform (DWT) is applied to decompose the multi-source synchronously aligned signal set into sub-signals in different frequency ranges. By selecting appropriate wavelet functions and their scale factors, the signal is decomposed at multiple levels to obtain high-frequency (such as heartbeat signals, skin electrical response mutations, etc.) and low-frequency (such as heart rate fluctuations, slow waves, etc.) components. The decomposed signal can clearly distinguish high-frequency noise and low-frequency background components. In the process of wavelet transform, attention is paid to processing the boundary effect of the signal. Symmetric extension or periodic extension can be used to avoid the influence of edge effects on signal decomposition, to ensure that the decomposition result of each level is accurate, and finally multi-source high-frequency signals of wrist biological tissue and multi-source low-frequency signals of wrist biological tissue are obtained.

[0045] Preferably, high-frequency drift dynamic compensation is performed on the multi-source high-frequency signal of the wrist biological tissue to obtain a high-frequency drift compensation signal of the wrist biological tissue; In an embodiment of the present invention, drift compensation is performed on multi-source high-frequency signals to correct changes in high-frequency components in the signals caused by device drift, noise or other external factors. First, drift detection is performed on the high-frequency signal using a time domain or frequency domain method. A drift detection algorithm based on a differential method can be used to analyze the changing trend of the signal through the differences between consecutive sampling points to identify whether there is drift. The amplitude and frequency of the high-frequency signal are dynamically adjusted by using a high-order filter or adaptive filtering technology to eliminate drift caused by device deviation or environmental factors. Typical methods include Kalman filtering or mean drift correction. These methods ensure that the signal remains stable by dynamically estimating and correcting trend changes in the signal, and ultimately obtain a high-frequency drift compensation signal for wrist biological tissue.

[0046] Preferably, a low-frequency noise elimination process is performed on the multi-source low-frequency signal of the wrist biological tissue to further eliminate the residual noise in the low-frequency component corresponding to the wrist biological tissue signal to obtain a wrist biological tissue low-frequency noise removal signal; In an embodiment of the present invention, a low-pass filter is used to perform preliminary suppression of low-frequency noise. A low-pass filter of the type of Butterworth filter or Chebyshev filter can be used to set an appropriate cutoff frequency to suppress noise components below the frequency. To further eliminate noise, a wavelet denoising method is used. By selecting an appropriate wavelet basis function, a threshold denoising technique is used in the decomposition process of the low-frequency signal to filter out the noise coefficient and retain only the main components in the signal. In the noise removal process, different denoising strategies should be set according to the characteristics of the low-frequency signal. For example, for signals with strong slow wave components, an adaptive threshold denoising method can be used to dynamically adjust the denoising intensity to avoid excessive elimination of useful signals. After the low-frequency noise elimination process, the noise component of the signal is significantly reduced, and more meaningful low-frequency information is retained, which can provide a clearer signal for subsequent analysis, and finally obtain a wrist biological tissue low-frequency noise removal signal.

[0047] Preferably, multimodal signal fusion is performed on the high-frequency drift compensation signal of the wrist biological tissue and the low-frequency noise removal signal of the wrist biological tissue to generate a multimodal clear signal map of the wrist biological tissue; based on the multimodal clear signal map of the wrist biological tissue and combined with the signal reconstruction method, the wrist biological tissue PPG signal, wrist biological tissue ECG signal and wrist biological tissue GSR signal are reconstructed and output as clear signals to generate PPG clear signal, ECG clear signal and GSR clear signal.

[0048] In an embodiment of the present invention, the high-frequency signal and the low-frequency signal after drift compensation and noise elimination are fused to generate a clear multimodal signal spectrum, and the high-frequency drift compensation signal and the low-frequency noise removal signal are combined by using a weighted average method or a signal fusion technology based on the least squares method. During the fusion process, the weights of each signal are optimized to ensure that the fused signal can retain the characteristics of the high-frequency and low-frequency components and reduce interference noise. During signal fusion, the timing relationship between the high-frequency signal and the low-frequency signal is taken into consideration, and a phase synchronization algorithm is used to enable the two to coordinate in both the time domain and the frequency domain to avoid introducing new inconsistencies during the fusion process, thereby generating a clear multimodal signal spectrum of wrist biological tissue. At the same time, the PPG signal, ECG signal and GSR signal of the wrist biological tissue are reconstructed by combining the previously generated multi-modal clear signal map of the wrist biological tissue, and the signal reconstruction algorithm (such as inverse Fourier transform or inverse wavelet transform) is applied to reconstruct the fine PPG, ECG and GSR clear signals to ensure that the information loss is minimized during the signal recovery process, and finally generate PPG clear signals, ECG clear signals and GSR clear signals.

[0049] Furthermore, the high-frequency drift dynamic compensation of multi-source high-frequency signals of wrist biological tissue includes: Performing high-frequency drift component analysis on multi-source high-frequency signals of wrist biological tissue to generate a high-frequency drift component map of wrist biological tissue; In an embodiment of the present invention, a high-frequency signal acquisition device is used to acquire multi-source high-frequency signals of wrist biological tissue. The device needs to have a multi-channel signal receiving function so as to be able to simultaneously collect biological signals from different parts (such as the skin surface, deep tissue, etc.). The high-frequency signal collector can use a sensor array to capture multi-level bioelectric current signals in the wrist tissue by contacting the wrist skin surface. Then, the collected original signal is spectrally analyzed through a high-frequency signal processing algorithm to extract the high-frequency drift component. The high-frequency drift component refers to the change trend of the signal within the high-frequency range, which is related to the bioelectric characteristics of the tissue and changes in the external environment. The signal frequency change is analyzed through frequency domain analysis tools such as Fourier transform to generate a high-frequency drift component spectrum of the wrist biological tissue. This spectrum can present the distribution of different biological signal sources in time and frequency, and finally generate a high-frequency drift component spectrum of the wrist biological tissue.

[0050] Preferably, a high-frequency baseline drift fitting process is performed on the high-frequency drift component spectrum of the wrist biological tissue to obtain a high-frequency baseline drift signal tensor of the wrist biological tissue; In an embodiment of the present invention, after obtaining the high-frequency drift component spectrum of wrist biological tissue, the baseline drift fitting process of the signal is entered. First, polynomial fitting, spline curve fitting or other suitable mathematical models are used to model the baseline drift component in the spectrum. Baseline drift refers to the long-term trend change in the signal, which is caused by environmental interference, equipment noise and other factors. The baseline drift characteristics of the signal are obtained by fitting the drift component. The fitting process uses optimization algorithms such as the least squares method to ensure the accuracy of the fitting results, and the baseline drift components in the signal are removed according to the fitting results. The high-frequency drift signal in the wrist biological tissue can be accurately represented, and finally the high-frequency baseline drift signal tensor of the wrist biological tissue is obtained.

[0051] Preferably, high-frequency drift dynamic compensation is performed on multi-source high-frequency signals of wrist biological tissue based on the high-frequency baseline drift signal tensor of wrist biological tissue to obtain a high-frequency drift compensation signal of wrist biological tissue.

[0052] In an embodiment of the present invention, dynamic compensation is performed on multi-source high-frequency signals by utilizing the previously obtained high-frequency baseline drift signal tensor of wrist biological tissue. Specifically, a time domain compensation algorithm or a frequency domain compensation method is used to apply the baseline drift signal tensor to the original multi-source signal. The time domain compensation method dynamically adjusts the amplitude, frequency and other parameters of the signal by correcting the signal in real time to reduce or eliminate the influence of high-frequency drift on signal quality, while the frequency domain compensation method suppresses or corrects the high-frequency drift components in the spectrum domain to restore the accuracy of the original signal. During the compensation process, the sliding window technology is used to perform local processing on the signal at each moment to ensure the accuracy and real-time performance of the compensation. After dynamic compensation for the high-frequency drift, a high-frequency drift compensation signal of the wrist biological tissue is finally obtained.

[0053] Furthermore, the biological tissue feature analysis module includes the following functions: The corresponding pulse wave rise time and pulse wave fall time are obtained through the PPG clear signal, and the peak amplitude and dicrotic fluctuation characteristics of the PPG clear signal are analyzed based on the pulse wave rise time and pulse wave fall time to obtain the pulse wave PPG signal fluctuation characteristics, including the fluctuation amplitude and fluctuation phase corresponding to the pulse wave peak and dicrotic; In an embodiment of the present invention, a high-quality PPG signal is obtained through a sensor to remove noise from the original PPG signal through an appropriate filter to ensure signal clarity. Then, the pulse wave rise time (i.e., the time from the starting point of the signal to the maximum amplitude) and the pulse wave fall time (i.e., the time from the maximum amplitude to the recovery of the baseline) are extracted through a signal analysis algorithm. These time features can be used through digital signal processing technology, such as waveform detection and edge detection methods, to accurately identify the peaks and troughs of the signal. In the process of extracting pulse wave features, it is also necessary to analyze the amplitude of the peak and determine the change in its amplitude, with special attention paid to whether dicrosis occurs. The feature of the dicrotic wave is usually manifested as an additional small peak with the same rise and fall time as the main pulse wave. By combining time domain and frequency domain analysis, the fluctuation amplitude and fluctuation phase of the pulse wave are identified, thereby comprehensively describing the dynamic characteristics of the pulse wave signal and finally obtaining the fluctuation characteristics of the pulse wave PPG signal.

[0054] Preferably, the P wave group, QRS wave group and T wave group corresponding to the ECG clear signal are subjected to electrocardiographic signal characteristic analysis to obtain electrocardiographic ECG signal fluctuation characteristics, including the amplitude, width and shape corresponding to the P wave, QRS wave and T wave; In an embodiment of the present invention, an ECG sensor is used to collect an ECG signal. After the signal is filtered to remove power frequency interference and myoelectric noise, a QRS detection algorithm (such as a Pan-Tompkins algorithm) is used to identify the starting point and the ending point of the QRS complex, thereby determining the peak position of the R wave of the ECG signal. Based on the position of the R wave, the characteristics of the P wave group, the QRS wave group and the T wave group are further extracted. The P wave reflects the activation of the atrium, the QRS wave group represents the depolarization process of the ventricle, and the T wave represents the repolarization process of the ventricle. During the analysis process, the amplitude, width and morphological characteristics of these wave groups are calculated by a feature extraction method. For example, the amplitude of the P wave is usually small and the duration is short, the amplitude of the QRS wave group is large and the width is wide, and the T wave presents a relatively gentle rise and fall trend. Through these characteristics, the health status of the ECG signal can be judged more accurately, and finally the ECG signal fluctuation characteristics are obtained, including the amplitude, width and morphology corresponding to the P wave, QRS wave and T wave.

[0055] Preferably, skin conductance characteristic analysis is performed on the GSR clear signal to obtain skin conductance GSR signal fluctuation characteristics, including skin conductance change rate and skin conductance fluctuation mean; In an embodiment of the present invention, a skin conductance signal is obtained through a GSR sensor. The signal can reflect the change in moisture on the surface of human skin, and further reflect emotional or physiological changes. First, the collected GSR signal is filtered to remove environmental noise and high-frequency interference to ensure the accuracy of the data. Then, the rate of change of skin conductance is calculated through time domain analysis. The rate of change is the amplitude of change of skin conductance per unit time, which can reveal the physiological response of the body in different situations. Then, the fluctuation mean of skin conductance is calculated to reflect the changing trend of skin conductance over a long period of time. By analyzing the fluctuation characteristics of skin conductance, the stress response or other physiological characteristics of the human body can be evaluated, and the relationship between the physiological state and the environmental stimulus can be further understood. Finally, the fluctuation characteristics of the skin conductance GSR signal are obtained, including the skin conductance change rate and the skin conductance fluctuation mean.

[0056] Preferably, the pulse wave PPG signal fluctuation characteristics, the electrocardiogram ECG signal fluctuation characteristics and the skin conductance GSR signal fluctuation characteristics are combined to obtain a wrist biological tissue signal feature set.

[0057] In an embodiment of the present invention, signal features from different sensors are merged through data fusion technology. First, the pulse wave PPG signal fluctuation features (including pulse wave rise time, fall time, peak amplitude and dicrotic fluctuation features) extracted in step S31, the electrocardiogram ECG signal fluctuation features (including the amplitude, width and morphological features of P wave, QRS wave and T wave) extracted in step S32, and the skin conductance GSR signal fluctuation features (including skin conductance change rate and fluctuation mean) extracted in step S33 are integrated. This integration process can be performed through weighted averaging or machine learning methods to find effective relationships and patterns between different signal features, thereby forming a comprehensive wrist biological tissue signal feature set, which can comprehensively reflect the individual's physiological state and health status, and finally obtain the wrist biological tissue signal feature set.

[0058] Furthermore, the wrist biometric status assessment module includes the following functions: Performing feature redundancy removal on a wrist biological tissue signal feature set to obtain a wrist biological tissue signal redundancy removal feature set; In an embodiment of the present invention, by analyzing the correlation in the feature set of wrist biological tissue signals, the signal features are redundantly removed. Redundant features refer to those features that influence each other in the feature space or repeatedly provide the same information, so as to discard redundant or low-variance features and obtain a feature set after redundancy removal, in which each feature has high independence and information content, avoiding the interference of redundant features in the subsequent analysis process, and finally obtaining the feature set of wrist biological tissue signals with redundant removal.

[0059] Preferably, the wrist biological tissue signal redundancy removal feature set is subjected to principal component feature dimensionality reduction processing, and combined to form a comprehensive feature vector to generate a wrist biological tissue signal feature vector; In an embodiment of the present invention, principal component analysis (PCA) is applied to perform feature dimension reduction processing based on a redundant removal feature set of wrist biological tissue signals. The PCA algorithm projects the original multidimensional data into a lower dimensional space by performing a linear transformation on the feature set, and retains the principal component with the largest variance. In a specific implementation, the covariance matrix of the redundant removal feature set is calculated to extract the first few most representative principal components to reduce the feature dimension and improve the computational efficiency. Then, these principal components are merged according to their importance weights in the data set to form a comprehensive feature vector. The comprehensive feature vector can better capture the essential characteristics of the wrist biological tissue signal while reducing the complexity of the calculation and the risk of overfitting, and is finally combined to generate a wrist biological tissue signal feature vector.

[0060] Preferably, a feature space topological distribution analysis is performed on the wrist biological tissue signal feature vector to obtain the wrist biological tissue signal feature space distribution density; In an embodiment of the present invention, a feature space topological distribution analysis is performed based on the wrist biological tissue signal feature vector. The purpose of this analysis is to reveal the distribution density of signal features in high-dimensional space and the topological relationship between features. Cluster analysis or density estimation methods, such as Gaussian mixture model (GMM) or k-means clustering, are used to group points in the feature space and divide them into multiple dense areas and sparse areas. In specific implementation, t-SNE (t-Distributed Stochastic Neighbor Embedding) or UMAP (Uniform Manifold Approximation and Projection) and other dimensionality reduction methods can be used to map high-dimensional features to two-dimensional or three-dimensional space in order to visualize and analyze the distribution of features in space. This analysis can help identify key areas or patterns in wrist signals and ultimately obtain the spatial distribution density of wrist biological tissue signal features.

[0061] Preferably, an adaptive convolution kernel design is performed based on the spatial distribution density of wrist biological tissue signal features in combination with a convolutional neural network, so that a 5x5 convolution kernel is used in a signal feature area corresponding to dense features and gentle changes to capture the global features of wrist biological tissue signals, and a 1x1 convolution kernel is used in a signal feature area corresponding to sparse features and drastic changes to capture the local detail features of wrist biological tissue signals, so as to design and generate a wrist feature enhanced adaptive convolution kernel model; In an embodiment of the present invention, an adaptive convolution kernel is designed based on the previously obtained feature space distribution density and in combination with a convolutional neural network (CNN). First, based on the signal characteristics of dense areas, a 5x5 convolution kernel is used to capture the global characteristics of the signal, because the signals in these areas change smoothly and are suitable for global perception using a larger convolution kernel. For sparse areas, a 1x1 convolution kernel is used to capture detail features, because the signals in these areas change dramatically and a smaller convolution kernel can effectively capture local rapid changes and detail information. The design of the adaptive convolution kernel is optimized through the training process of the convolutional neural network, and the size and shape of the convolution kernel are dynamically adjusted according to the characteristics of the signal to ensure the best feature extraction effect. Specifically, through the back-propagation algorithm, the convolution kernel weights are adjusted so that the 5x5 convolution kernel adapts to dense areas and the 1x1 convolution kernel adapts to sparse areas, thereby enhancing the network's ability to capture different signal features, and finally a wrist feature enhanced adaptive convolution kernel model is designed and generated.

[0062] Preferably, a wrist feature enhanced adaptive convolution kernel model is used to perform a multi-scale convolution operation on the wrist biological tissue signal feature vector to generate a wrist multi-scale convolution enhanced feature vector; wrist state assessment is performed based on the wrist multi-scale convolution enhanced feature vector in combination with a fuzzy logic reasoning method to obtain a wrist physiological tissue state assessment index; physiological assessment calibration is performed based on the wrist physiological tissue state assessment index in combination with a multi-objective optimization algorithm to obtain a wrist biological tissue state assessment result.

[0063] In an embodiment of the present invention, a multi-scale convolution operation is performed on a wrist biological tissue signal feature vector by using a designed adaptive convolution kernel model, so that the global information and local detail information of the signal are extracted and enhanced by applying convolution kernels of different sizes (for example, 5x5 and 1x1) to the signal feature vector. After the convolution process, the obtained multi-scale convolution enhanced feature vector can more comprehensively reflect the complexity and diversity of the wrist biological tissue signal. Then, the multi-scale convolution enhanced feature vector is evaluated in combination with a fuzzy logic reasoning method to generate a wrist state evaluation index. The fuzzy logic reasoning method can perform state evaluation by setting a rule base and a membership function under high uncertainty and fuzziness, thereby obtaining a quantitative evaluation index. Based on the evaluation index, a physiological evaluation calibration is performed in combination with a multi-objective optimization algorithm to optimize the evaluation result, so as to obtain an accurate wrist biological tissue state evaluation result. This process can provide an objective and accurate evaluation of the health status of the wrist, provide a basis for further health monitoring and intervention, and finally obtain a wrist biological tissue state evaluation result.

[0064] Furthermore, the present invention also provides a wrist signal acquisition and processing method based on biological tissue analysis, which is used to execute the wrist signal acquisition and processing system based on biological tissue analysis as described above. The wrist signal acquisition and processing method based on biological tissue analysis includes the following steps: Step S1: designing a wrist wearable device corresponding to an integrated photoelectric volumetric pulse wave sensor, an electrocardiogram sensor, and a galvanic skin response sensor; obtaining the distribution characteristics of wrist biological tissues, and optimizing the position structure of the wrist wearable device based on the distribution characteristics of wrist biological tissues to generate a wrist multi-signal acquisition optimization device; Step S2: using the wrist multi-signal acquisition optimization device to collect the PPG signal, ECG signal and GSR signal corresponding to the wrist biological tissue in real time to generate the wrist biological tissue PPG signal, wrist biological tissue ECG signal and wrist biological tissue GSR signal; performing high-frequency drift preprocessing on the wrist biological tissue PPG signal, wrist biological tissue ECG signal and wrist biological tissue GSR signal to generate PPG clear signal, ECG clear signal and GSR clear signal; Step S3: performing biological tissue feature analysis on the PPG clear signal, the ECG clear signal and the GSR clear signal to obtain a wrist biological tissue signal feature set; Step S4: performing feature redundancy and dimensionality reduction processing on the wrist biological tissue signal feature set to generate a wrist biological tissue signal feature vector; using a convolutional neural network to perform wrist physiological state assessment analysis on the wrist biological tissue signal feature vector to obtain a wrist biological tissue state assessment result.

[0065] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0066] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A wrist signal acquisition and processing system based on biological tissue analysis, characterized in that: Includes the following modules: Wrist device sensor optimization design module, which is used to design wrist wearable devices corresponding to integrated photoelectric volume pulse wave sensors, electrocardiogram sensors and galvanic skin response sensors; Obtain the distribution characteristics of wrist biological tissues, and optimize the position and structure of the wrist wearable device based on the distribution characteristics of wrist biological tissues to generate wrist multi-signal acquisition optimization equipment; The wrist multi-signal preprocessing module is used to collect PPG signals, ECG signals and GSR signals corresponding to wrist biological tissue in real time by using wrist multi-signal acquisition optimization equipment to generate wrist biological tissue PPG signals, wrist biological tissue ECG signals and wrist biological tissue GSR signals; perform high-frequency drift preprocessing on the wrist biological tissue PPG signals, wrist biological tissue ECG signals and wrist biological tissue GSR signals, so as to generate PPG clear signals, ECG clear signals and GSR clear signals; A biological tissue feature analysis module is used to perform biological tissue feature analysis on a PPG clear signal, an ECG clear signal, and a GSR clear signal, thereby obtaining a wrist biological tissue signal feature set; The wrist biometric state assessment module is used to perform feature redundancy and dimensionality reduction processing on the wrist biological tissue signal feature set to generate a wrist biological tissue signal feature vector; and use a convolutional neural network to perform wrist physiological state assessment and analysis on the wrist biological tissue signal feature vector to obtain a wrist biological tissue state assessment result.

2. The wrist signal acquisition and processing system based on biological tissue analysis according to claim 1, characterized in that: The wrist device sensor optimization design module includes the following functions: By designing a wrist wearable device that integrates a photoelectric volumetric pulse wave sensor, an electrocardiogram sensor, and a galvanic skin response sensor; Obtain the distribution characteristics of wrist biological tissues, including the distribution location of the radial artery, wrist muscles and wrist nerves; Based on the distribution of the radial artery on the wrist, the PPG sensor in the wrist wearable device is optimized to accurately align the photoplethysmography sensor with the distribution of the radial artery on the wrist, and the flexible bonding technology is used to ensure that the sensor is in close contact with the wrist skin to generate an optimized design scheme for the pulse wave sensor position; Optimize the ECG electrode layout of the ECG sensor in the wrist wearable device based on the distribution of wrist muscles to generate an optimized design scheme for the ECG sensor electrode layout; Based on the distribution of wrist nerves, the skin interference optimization design of the skin galvanic response sensor in the wrist wearable device is performed to generate a skin galvanic response sensor interference optimization design scheme; Based on the pulse wave sensor position optimization design scheme, the ECG sensor electrode layout optimization design scheme and the skin galvanic response sensor interference optimization design scheme, the corresponding positions and layout structures of the photoelectric capacitance pulse wave sensor, ECG sensor and skin galvanic response sensor in the wrist wearable device are optimized to generate a wrist multi-signal acquisition optimization device.

3. The wrist signal acquisition and processing system based on biological tissue analysis according to claim 2, characterized in that: The optimization of the ECG electrode layout of the electrocardiogram sensor in the wrist wearable device based on the distribution position of the wrist muscles includes: Based on the distribution position of wrist muscles, the muscle electrical interference influence calculation formula is used to calculate the electrical interference influence of the electrode layout corresponding to the ECG sensor in the wrist wearable device to obtain the ECG electrode layout electrical interference influence factor; Based on the ECG electrode layout electrical interference influencing factors, the ECG electrode layout of the ECG sensor in the wrist wearable device is optimized to generate an optimized design scheme for the ECG sensor electrode layout.

4. The wrist signal acquisition and processing system based on biological tissue analysis according to claim 3 is characterized in that: The muscle electrical interference influence calculation formula is specifically: ； In the formula, The electrical interference influencing factor for ECG electrode layout, is the space where the wrist-worn device is located. Layout of the ECG sensing electrodes, is the number of muscle electrical activity distribution points, For the The muscle activity points are located The intensity of muscle electrical activity at is the maximum intensity of muscle electrical activity, For the The weight of the influence of each muscle activity point on electrical interference, is an exponential function, For the The layout position corresponding to the muscle activity point, For the The standard deviation of the layout position corresponding to the muscle activity point, is the maximum frequency of muscle electrical activity, is the interference regulation coefficient of muscle electrical activity, Correction factor for the electrical interference factor of ECG electrode layout.

5. The wrist signal acquisition and processing system based on biological tissue analysis according to claim 1, characterized in that: The wrist multi-signal preprocessing module includes the following functions: The photoelectric volume pulse wave sensor in the wrist multi-signal acquisition optimization device is used to collect the PPG signal corresponding to the wrist biological tissue in real time to generate the wrist biological tissue PPG signal; The ECG signal corresponding to the wrist biological tissue is collected in real time by using the ECG sensor in the wrist multi-signal acquisition optimization device to generate the wrist biological tissue ECG signal; The skin galvanic response sensor in the wrist multi-signal acquisition optimization device is used to collect the GSR signal corresponding to the wrist biological tissue in real time to generate the wrist biological tissue GSR signal; The wrist biological tissue PPG signal, the wrist biological tissue ECG signal and the wrist biological tissue GSR signal are subjected to high-frequency drift preprocessing to generate a PPG clear signal, an ECG clear signal and a GSR clear signal.

6. The wrist signal acquisition and processing system based on biological tissue analysis according to claim 5, characterized in that: The high-frequency drift preprocessing of the wrist biological tissue PPG signal, the wrist biological tissue ECG signal and the wrist biological tissue GSR signal comprises: Performing timestamp alignment and synchronization processing on wrist biological tissue PPG signals, wrist biological tissue ECG signals and wrist biological tissue GSR signals, so as to compensate for the time deviation corresponding to the signals based on the interpolation algorithm, and ensure that the wrist biological tissue PPG signals, ECG signals and GSR signals are completely aligned on the time axis, so as to obtain a wrist biological tissue multi-source synchronous alignment signal set; Performing wavelet transform decomposition on the wrist biological tissue multi-source synchronous alignment signal set to separate the high-frequency and low-frequency components in the wrist biological tissue signal to obtain the wrist biological tissue multi-source high-frequency signal and the wrist biological tissue multi-source low-frequency signal; Performing high-frequency drift dynamic compensation on multi-source high-frequency signals of wrist biological tissue to obtain high-frequency drift compensation signals of wrist biological tissue; Performing low-frequency noise elimination processing on the multi-source low-frequency signals of the wrist biological tissue to further eliminate the residual noise in the low-frequency components corresponding to the wrist biological tissue signals to obtain the wrist biological tissue low-frequency noise removal signal; Multimodal signal fusion is performed on the high-frequency drift compensation signal of wrist biological tissue and the low-frequency noise removal signal of wrist biological tissue to generate a multimodal clear signal map of wrist biological tissue; based on the multimodal clear signal map of wrist biological tissue and combined with the signal reconstruction method, the wrist biological tissue PPG signal, wrist biological tissue ECG signal and wrist biological tissue GSR signal are reconstructed and output as clear signals to generate PPG clear signal, ECG clear signal and GSR clear signal.

7. The wrist signal acquisition and processing system based on biological tissue analysis according to claim 6, characterized in that: The high-frequency drift dynamic compensation of multi-source high-frequency signals of wrist biological tissue comprises: Performing high-frequency drift component analysis on multi-source high-frequency signals of wrist biological tissue to generate a high-frequency drift component map of wrist biological tissue; Performing high-frequency baseline drift fitting processing on the high-frequency drift component spectrum of wrist biological tissue to obtain the high-frequency baseline drift signal tensor of wrist biological tissue; Based on the high-frequency baseline drift signal tensor of the wrist biological tissue, high-frequency drift dynamic compensation is performed on the multi-source high-frequency signal of the wrist biological tissue to obtain the high-frequency drift compensation signal of the wrist biological tissue.

8. The wrist signal acquisition and processing system based on biological tissue analysis according to claim 1, characterized in that: The biological tissue feature analysis module includes the following functions: The corresponding pulse wave rise time and pulse wave fall time are obtained through the PPG clear signal, and the peak amplitude and dicrotic fluctuation characteristics of the PPG clear signal are analyzed based on the pulse wave rise time and pulse wave fall time to obtain the pulse wave PPG signal fluctuation characteristics, including the fluctuation amplitude and fluctuation phase corresponding to the pulse wave peak and dicrotic; Perform ECG signal feature analysis on the corresponding P wave group, QRS wave group and T wave group in the ECG clear signal to obtain ECG signal fluctuation features, including the amplitude, width and shape of the P wave, QRS wave and T wave; The skin conductance characteristics of the GSR clear signal are analyzed to obtain the fluctuation characteristics of the skin conductance GSR signal, including the skin conductance change rate and the skin conductance fluctuation mean; The pulse wave PPG signal fluctuation features, electrocardiogram ECG signal fluctuation features and skin conductance GSR signal fluctuation features are merged to obtain the wrist biological tissue signal feature set.

9. The wrist signal acquisition and processing system based on biological tissue analysis according to claim 1, characterized in that: The wrist biometric status assessment module includes the following functions: Performing feature redundancy removal on a wrist biological tissue signal feature set to obtain a wrist biological tissue signal redundancy removal feature set; Performing principal component feature dimensionality reduction processing on the redundant removal feature set of wrist biological tissue signal, and combining them to form a comprehensive feature vector, so as to generate a wrist biological tissue signal feature vector; Performing feature space topological distribution analysis on wrist biological tissue signal feature vectors to obtain the wrist biological tissue signal feature space distribution density; Based on the spatial distribution density of wrist biological tissue signal features and combined with convolutional neural networks, an adaptive convolution kernel is designed to capture the global features of wrist biological tissue signals using a 5x5 convolution kernel in the signal feature area corresponding to dense features and gentle changes, and to capture the local detail features of wrist biological tissue signals using a 1x1 convolution kernel in the signal feature area corresponding to sparse features and drastic changes, so as to design and generate a wrist feature enhanced adaptive convolution kernel model; The wrist feature enhanced adaptive convolution kernel model is used to perform multi-scale convolution operation on the wrist biological tissue signal feature vector to generate a wrist multi-scale convolution enhanced feature vector; the wrist state is evaluated based on the wrist multi-scale convolution enhanced feature vector and combined with the fuzzy logic reasoning method to obtain the wrist physiological tissue state evaluation index; the physiological assessment calibration is performed based on the wrist physiological tissue state evaluation index and combined with the multi-objective optimization algorithm to obtain the wrist biological tissue state evaluation result.

10. A wrist signal acquisition and processing method based on biological tissue analysis, characterized in that: The wrist signal acquisition and processing system based on biological tissue analysis according to claim 1 is used to execute the wrist signal acquisition and processing method based on biological tissue analysis, comprising the following steps: Step S1: designing a wrist wearable device corresponding to an integrated photoelectric volumetric pulse wave sensor, an electrocardiogram sensor, and a galvanic skin response sensor; obtaining the distribution characteristics of wrist biological tissues, and optimizing the position structure of the wrist wearable device based on the distribution characteristics of wrist biological tissues to generate a wrist multi-signal acquisition optimization device; Step S2: using the wrist multi-signal acquisition optimization device to collect the PPG signal, ECG signal and GSR signal corresponding to the wrist biological tissue in real time to generate the wrist biological tissue PPG signal, wrist biological tissue ECG signal and wrist biological tissue GSR signal; performing high-frequency drift preprocessing on the wrist biological tissue PPG signal, wrist biological tissue ECG signal and wrist biological tissue GSR signal to generate PPG clear signal, ECG clear signal and GSR clear signal; Step S3: performing biological tissue feature analysis on the PPG clear signal, the ECG clear signal and the GSR clear signal to obtain a wrist biological tissue signal feature set; Step S4: performing feature redundancy and dimensionality reduction processing on the wrist biological tissue signal feature set to generate a wrist biological tissue signal feature vector; using a convolutional neural network to perform wrist physiological state assessment analysis on the wrist biological tissue signal feature vector to obtain a wrist biological tissue state assessment result.

Images