Treatment control method and system of intelligent self-adaptive wave conduction health care instrument

Abstract

The invention belongs to the technical field of medical health care equipment, and particularly provides a treatment control method of an intelligent self-adaptive wave conduction health care instrument, which comprises the following steps of: acquiring a physiological state signal of a user in real time, and generating an abnormal trigger instruction when the physiological state signal is detected to deviate from a preset health threshold range; inputting physiological index data corresponding to the abnormal trigger instruction into a dynamic adjustment model, wherein the dynamic adjustment model generates a treatment scheme based on a mapping relation between physiological indexes and wave conduction parameters; generating a driving control signal according to the treatment scheme, wherein the driving control signal is used for adjusting a particle resonance wave output device in the wave conduction health care instrument; and outputting a target particle resonance wave through a particle resonance wave output device according to the resonance frequency and the amplitude corresponding to the driving control signal, and continuously driving the action duration corresponding to the control signal. By collecting the physiological state signal of the user in real time and dynamically comparing the physiological state signal with the preset health threshold value, accurate anomaly detection and immediate intervention are achieved, and the limitation of fixed parameter output of traditional equipment is broken through.

Description

Technical Field

[0001] This invention belongs to the field of medical and health care equipment technology, specifically relating to a treatment control method and system for an intelligent adaptive wave conduction health care device. Background Technology

[0002] The wave conduction health and wellness device is an instrument that uses wave-based energy transmission to achieve physiotherapy, rehabilitation, and health improvement. Its core technology is particle resonance. Based on the microparticle properties of quantum physics, particle resonance technology uses high-frequency vibrations of hundreds of millions of times per second to induce resonance between human cells. This resonance can remove impurities from blood vessel walls, release toxins, and correct disordered biomagnetic field frequencies. Therefore, using particle resonance waves as the core technology of the health and wellness device combines quantum physics, traditional Chinese medicine theory, and modern medicine to improve human microcirculation and cell activity through high-frequency vibration energy.

[0003] Existing wave conduction therapy devices typically use fixed treatment parameters, which cannot be adjusted according to the patient's real-time physiological condition. This limitation may lead to poor treatment results and even adverse effects on the patient. Therefore, there is a need for a treatment control method for intelligent adaptive wave conduction therapy devices that can dynamically adjust treatment parameters based on the patient's real-time physiological indicators. Summary of the Invention

[0004] To overcome the shortcomings of the prior art, the present invention provides a treatment control method and system for an intelligent adaptive wave conduction health care device to solve the problems in the prior art.

[0005] One embodiment of the present invention provides a treatment control method for an intelligent adaptive wave conduction health care device, comprising the following steps:

[0006] The system collects user physiological state signals in real time, and generates an abnormality trigger command when the physiological state signals deviate from the preset health threshold range.

[0007] The physiological index data corresponding to the abnormal triggering command is input into the dynamic adjustment model. The dynamic adjustment model generates a treatment plan based on the mapping relationship between the physiological index and the wave conduction parameters. The treatment plan includes at least the parameters of resonance frequency, amplitude and duration of action.

[0008] A drive control signal is generated according to the treatment plan, and the drive control signal is used to adjust the particle resonance wave output device in the wave conduction health care device.

[0009] The particle resonance wave output device is used to drive the target particle resonance wave to output the resonance frequency and amplitude corresponding to the control signal, and to continuously drive the action time corresponding to the control signal.

[0010] In one embodiment, the method for constructing the dynamically adjusted model includes:

[0011] Obtain a historical treatment dataset, which contains multidimensional physiological index data and its corresponding effective treatment parameter sets;

[0012] The dataset is preprocessed to extract the correlation features between the fluctuation characteristics of physiological indicators and the adjustment amount of treatment parameters in the dataset;

[0013] Based on the aforementioned correlation features, a machine learning algorithm is used to perform nonlinear regression modeling to obtain a dynamic adjustment model of physiological indicators and treatment parameters.

[0014] Obtain feedback data on treatment effectiveness, optimize the dynamic adjustment model using gradient descent based on the feedback data, and establish a dynamic association rule base.

[0015] In one embodiment, the step of using a machine learning algorithm to perform nonlinear regression modeling based on the associated features to obtain a dynamic adjustment model of physiological indicators and treatment parameters further includes:

[0016] A time decay factor is added, which is calculated using the following formula:

[0017]

[0018] Where Age is the user's age, BMI is the user's body mass index, t is the cumulative duration of a single treatment, and k1, k2, and α are preset weighting coefficients; the time decay factor is used to dynamically correct the resonant frequency output value of the dynamic adjustment model.

[0019] In one embodiment, the step of real-time acquisition of user physiological state signals and generating an abnormality trigger command when the physiological state signals deviate from a preset health threshold range specifically includes:

[0020] The wearable device uses a multimodal physiological sensor array to collect the user's bioelectrical signals, biomagnetic signals, and thermodynamic signals in real time, and continuously records and generates treatment history data.

[0021] The multimodal signals are subjected to feature fusion processing to generate a comprehensive physiological state assessment value;

[0022] When the evaluation value exceeds the preset health threshold range, the multi-channel anomaly detection algorithm is triggered to generate the anomaly trigger instruction and identify the type of abnormal physiological parameter.

[0023] In one embodiment, the step of real-time acquisition of user physiological state signals and generating an abnormality trigger command when the physiological state signals deviate from a preset health threshold range further includes:

[0024] Synchronize the treatment history data recorded by the wearable device to the dynamic adjustment model;

[0025] The weight allocation strategy for feature fusion processing is optimized based on the incremental learning algorithm.

[0026] In one embodiment, the step of generating a drive control signal according to the treatment plan, wherein the drive control signal is used to adjust the particle resonance wave output device in the wave conduction health care device, specifically includes:

[0027] The waveform parameter set in the treatment plan is analyzed to generate a control signal sequence containing frequency modulation instructions, amplitude control instructions, and timing constraint instructions.

[0028] The control signal sequence is converted into a drive control signal based on a preset impedance matching strategy, the strategy including:

[0029] The amplitude output gradient is pre-compensated based on the user's body surface impedance characteristics;

[0030] Optimize frequency modulation parameters based on the attenuation characteristics of the target frequency band;

[0031] The driving control signal is loaded into the particle resonance wave output device through a multi-channel synchronous transmission protocol to activate the wave field resonance mode of the target frequency band.

[0032] This application also relates to a treatment control system for an intelligent adaptive wave conduction health care device, comprising:

[0033] The acquisition module is used to acquire the user's physiological state signals in real time. When the physiological state signals are detected to deviate from the preset health threshold range, an abnormal trigger command is generated.

[0034] The generation module is used to input the physiological index data corresponding to the abnormal triggering command into the dynamic adjustment model. The dynamic adjustment model generates a treatment plan based on the mapping relationship between physiological indexes and wave conduction parameters. The treatment plan includes at least the parameters of resonance frequency, amplitude and duration of action.

[0035] The driving module is used to generate a driving control signal according to the treatment plan, and the driving control signal is used to adjust the particle resonance wave output device in the wave conduction health care device.

[0036] The output module is used to drive the target particle resonance wave to output the resonance frequency and amplitude corresponding to the control signal through the particle resonance wave output device, and to continuously drive the action time corresponding to the control signal.

[0037] This application also relates to a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described treatment control method for an intelligent adaptive wave conduction health care device.

[0038] This application also relates to a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the treatment control method of the aforementioned intelligent adaptive wave conduction health care device.

[0039] The treatment control method and system of the intelligent adaptive wave conduction health care device provided in the above embodiments have the following beneficial effects:

[0040] 1. By collecting users' physiological state signals in real time and dynamically comparing them with preset health thresholds, accurate anomaly detection and immediate intervention are achieved, overcoming the limitations of fixed parameter output in traditional devices. When physiological indicators deviate from the healthy range, the treatment parameter adjustment mechanism is automatically triggered, ensuring that the frequency, amplitude, and duration of the particle resonance wave precisely match the user's current physiological state, significantly improving treatment safety and targeting, and avoiding problems of overtreatment or insufficient efficacy.

[0041] 2. In one embodiment, a data-driven dynamic decision-making model is constructed based on historical treatment data. Machine learning algorithms are used to uncover the nonlinear mapping relationship between physiological index fluctuations and treatment parameters. Gradient descent is used to optimize the continuously iterative model parameters, forming a self-learning association rule base. This addresses the subjectivity and lag of manual parameter tuning based on experience, enabling the generation of treatment plans to be both scientific and personalized, making it particularly suitable for the long-term health management of patients with chronic diseases.

[0042] 3. In one embodiment, a dynamic correction mechanism using a time decay factor coupled with user age (Age), body mass index (BMI), and treatment duration (t) is introduced to achieve spatiotemporal dual-dimensional optimization of treatment parameters. This factor dynamically adjusts the model output value based on individual metabolic characteristics and treatment progress, effectively balancing changes in human biorhythms and energy accumulation effects during long-term treatment, preventing cellular adaptability decline caused by resonant frequency solidification, and extending the sustainability of treatment efficacy.

[0043] 4. In one embodiment, adaptive pre-compensation and precise parameter optimization of the drive control signal can be achieved based on the user's surface impedance characteristics and the bio-attenuation characteristics of the target treatment frequency band. Amplitude gradient pre-adjustment and frequency modulation parameter adaptation are completed during the signal generation stage, ensuring that after the particle resonance wave output device is activated, the wave field energy distribution of the target frequency band precisely matches the biophysical characteristics of the lesion site. This significantly improves the targeted transmission efficiency of treatment energy and the consistency of tissue absorption, avoiding therapeutic deviations caused by contact impedance fluctuations or frequency band selection mismatch. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0045] Figure 1 A flowchart illustrating a treatment control method for an intelligent adaptive wave conduction health care device provided in an embodiment of the present invention;

[0046] Figure 2 This is a schematic block diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0047] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0048] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative positional relationship and movement of the components in a specific posture. If the specific posture changes, the directional indications will also change accordingly.

[0049] Furthermore, if the embodiments of this invention involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the use of "and / or" or "and / or" throughout the text includes three parallel solutions. For example, "A and / or B" includes solution A, solution B, or a solution where both A and B are satisfied simultaneously. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0050] Reference Figure 1 One embodiment of the present invention provides a treatment control method for an intelligent adaptive wave conduction health care device, comprising the following steps:

[0051] S100. Real-time acquisition of user physiological state signals; when the physiological state signals are detected to deviate from the preset health threshold range, an abnormal trigger command is generated.

[0052] S200. Input the physiological index data corresponding to the abnormal triggering command into the dynamic adjustment model. The dynamic adjustment model generates a treatment plan based on the mapping relationship between physiological indexes and wave conduction parameters. The treatment plan includes at least the parameters of resonance frequency, amplitude and duration of action.

[0053] S300. Generate a drive control signal according to the treatment plan. The drive control signal is used to adjust the particle resonance wave output device in the wave conduction health care device.

[0054] S400. The target particle resonance wave is output through the particle resonance wave output device with the resonance frequency and amplitude corresponding to the drive control signal, and the action time corresponding to the drive control signal is continuously extended.

[0055] In this embodiment, by collecting the user's physiological state signals in real time and dynamically comparing them with preset health thresholds, accurate anomaly detection and immediate intervention are achieved, overcoming the limitations of fixed parameter output in traditional devices. When physiological indicators deviate from the healthy range, a treatment parameter adjustment mechanism is automatically triggered, ensuring that the frequency, amplitude, and duration of the particle resonance wave precisely match the user's current physiological state. This significantly improves treatment safety and targeting, avoiding overtreatment or insufficient efficacy.

[0056] As described in step S100 above, for example, the user's physiological state signals are collected in real time by a monitoring device. The monitoring device can be a biosensor in the user's smartwatch, a peripheral physiological detector, or other devices. The monitoring device collects the user's current physiological index parameters and forms corresponding physiological state signals. The physiological state signals contain various physiological index parameters of the user. Physiological index parameters include physiological data such as blood viscosity, blood oxygen, blood pressure, heart rate, body temperature, and muscle tension. The preset health threshold range is the normal range of various physiological index parameters of the human body. When one or more physiological index parameters in the collected physiological state signals are detected to deviate from the preset health threshold range, it indicates that the user's current physiological state is abnormal, and then an abnormality trigger command is generated to provide a prompt.

[0057] As described in step S200 above, the dynamic adjustment model is a pre-trained machine learning model used to match and determine the physiological health status corresponding to the user's current physiological index parameters, and to match the control parameters of the wave conduction health care device corresponding to that physiological health status. The input of the dynamic adjustment model is the number of physiological indicators corresponding to the abnormal trigger command, and the output is the treatment plan, which consists of the control parameters of the wave conduction health care device, including at least the resonant frequency, amplitude, and duration of action. When one or more physiological index parameters in the user's physiological state signal deviate from the preset health threshold range, an abnormal trigger command is generated and input into the dynamic adjustment model. The dynamic adjustment model then automatically matches the corresponding treatment plan and outputs it. Through the automatic triggering treatment plan matching mechanism, the frequency, amplitude, and duration of the particle resonance wave are accurately matched to the user's current physiological state, significantly improving treatment safety and targeting, and avoiding problems of overtreatment or insufficient efficacy.

[0058] As described in steps S300 and S400 above, the treatment plan output by the dynamic adjustment model is analyzed and transformed. The control parameters of the wave conduction health care device in the treatment plan are converted into drive control signals. The drive control signals are then transmitted to the particle resonance wave output device of the wave conduction health care device through a transmission protocol. This allows the particle resonance wave output device of the wave conduction health care device to output the frequency, amplitude, and duration of the corresponding particle resonance wave according to the treatment plan, so as to accurately match the user's current physiological state.

[0059] In one embodiment, the method for constructing the dynamically adjusted model in step S200 includes:

[0060] S210. Obtain historical treatment dataset, which includes multidimensional physiological index data and its corresponding effective treatment parameter groups;

[0061] S220. Preprocess the dataset to extract the correlation features between the fluctuation characteristics of physiological indicators and the adjustment amount of treatment parameters in the dataset;

[0062] S230. Based on the aforementioned correlation features, a machine learning algorithm is used to perform nonlinear regression modeling to obtain a dynamic adjustment model of physiological indicators and treatment parameters.

[0063] S240. Obtain feedback data on treatment effects, and perform gradient descent optimization on the dynamic adjustment model based on the feedback data to establish a dynamic association rule base.

[0064] In this embodiment, a data-driven dynamic decision-making model is constructed based on historical treatment data. Machine learning algorithms are used to uncover the nonlinear mapping relationship between physiological index fluctuations and treatment parameters. Gradient descent is used to optimize the continuously iterative model parameters, forming a self-learning association rule base. This addresses the subjectivity and lag of manual parameter tuning based on experience, enabling the generation of treatment plans to be both scientific and personalized, making it particularly suitable for the long-term health management of patients with chronic diseases.

[0065] Specifically:

[0066] For step S210: The historical treatment dataset refers to structured data collected from completed treatment cases, containing two core types of information: multidimensional physiological index data and effective treatment parameter sets. Multidimensional physiological index data includes dynamic physiological signals (such as heart rate variability, blood oxygen saturation, etc.) and static indicators (such as age, BMI, basal metabolic rate, etc.), for example, blood glucose fluctuation curves of diabetic patients, 24-hour ambulatory blood pressure monitoring data of hypertensive patients, etc. Effective treatment parameter sets refer to wave conduction control parameter combinations that have been validated in historical treatments, for example, a treatment parameter set example (resonance frequency f = 28.5kHz ± 3%, amplitude A = 15-25Vpp, duration of action 180s ± 5%). The historical treatment dataset is obtained from historical treatment data acquired from medical institutions, users' wearable devices, clinical trial archives, etc.

[0067] For step S220: Preprocessing includes data cleaning (removing outliers), missing value handling (such as interpolation or deletion), and data normalization (such as standardization or normalization). Data cleaning, missing value handling, and data normalization are performed on the acquired historical treatment dataset to ensure data quality and make the data suitable for modeling using machine learning algorithms, ensuring the data meets input requirements. Feature extraction, by identifying and extracting the relationship between physiological index fluctuations and treatment parameter adjustments in the preprocessed historical treatment dataset, simplifies the dataset, improves the interpretability and generalization ability of the model, enhances computational efficiency, and helps discover hidden patterns and knowledge in the data, thus playing an important role in data analysis and machine learning.

[0068] For step S230: Based on the correlation characteristics between the obtained physiological index fluctuation characteristics and the treatment parameter adjustment amount, select an appropriate machine learning algorithm for nonlinear regression modeling, such as the XGBoost algorithm. The XGBoost algorithm has the effects of nonlinear fitting ability, feature importance assessment, and anti-overfitting mechanism. By integrating multiple decision trees, the XGBoost algorithm can capture the complex nonlinear relationship between physiological indexes and treatment parameters (such as the exponential correlation between blood pressure fluctuation and frequency adjustment amount). A dynamic adjustment model of physiological indicators and treatment parameters was obtained by using the XGBoost algorithm for nonlinear regression modeling. The input of the dynamic adjustment model is the preprocessed associated feature vector (such as heart rate variability standard deviation HRV_SD = 12ms, body surface temperature gradient ΔT = 0.3℃ / min), and the output is the treatment parameter set (such as resonance frequency f = 28.5kHz ± 3%, amplitude A = 15-25Vpp). The actual mapping logic is as follows: when HRV_SD > 10ms and ΔT > 0.2℃ / min, the dynamic adjustment model determines that the user is in a state of sympathetic nervous hyperactivity and automatically increases the resonance frequency to enhance the activation efficiency of cell membrane ion channels. The frequency correction amount Δf = 0.05 × HRV_SD (unit kHz).

[0069] For step S240: By collecting real-time feedback data on treatment effects (such as the degree of pain relief and the improvement rate of physiological indicators), the model parameters are dynamically adjusted to gradually reduce the prediction error of the treatment plan. Gradient descent is an iterative optimization algorithm that calculates the error between the model's prediction results and the actual effects, and gradually adjusts the model parameters to reduce the error. Through gradient descent optimization, the model parameters can be automatically corrected based on individual feedback data to generate a personalized treatment plan.

[0070] For the dynamic rule base, key decision logic is extracted from the optimized model and transformed into "condition-action" rules. For example, rule number R2025-001, trigger condition is user age > 65 years old and treatment stage ≥ 3 times, execution action is to adjust the maximum single treatment duration from 180 seconds to 150 seconds, confidence level: 92%. By establishing a dynamic rule base, the system can automatically execute safety rules, such as immediately stopping treatment and issuing an alarm when the detected body surface temperature exceeds 38℃ to prevent tissue overheating damage. For automatic rule execution, for example, when the system detects that the user's age > 65 years old and is entering the 3rd treatment, the rule is automatically invoked to shorten the duration. For updates, the effectiveness of rules is evaluated quarterly, and old rules with a confidence level < 80% are discarded (e.g., a rule is no longer applicable due to equipment upgrades).

[0071] In one embodiment, step S230 further includes:

[0072] A time decay factor is added, which is calculated using the following formula:

[0073]

[0074] Where Age is the user's age, BMI is the user's body mass index, t is the cumulative duration of a single treatment, and k1, k2, and α are preset weighting coefficients; the time decay factor is used to dynamically correct the resonant frequency output value of the dynamic adjustment model.

[0075] In this embodiment, a dynamic correction mechanism using a time decay factor coupled with user age (Age), body mass index (BMI), and treatment duration (t) is introduced to achieve spatiotemporal dual-dimensional optimization of treatment parameters. This factor dynamically adjusts the model output value based on individual metabolic characteristics and treatment progress, effectively balancing changes in human biorhythms and energy accumulation effects during long-term treatment, preventing the decline in cellular adaptability caused by the solidification of resonant frequencies, and extending the sustainability of treatment efficacy.

[0076] Specifically, Age (user age) is obtained through user registration information and used to quantify the effect of metabolic rate decline. Elderly patients (Age ≥ 65) experience a decrease of approximately 30% in cell membrane ion channel activity, requiring compensation through increasing the k1 value. BMI (Body Mass Index) is calculated as weight (kg) / height (m). 2 This reflects the distribution of body fat percentage and muscle mass. In obese patients (BMI ≥ 28), the subcutaneous fat layer reduces wave conduction energy by 15-20%, requiring enhancement of the k2 value to strengthen regulation. t (cumulative duration of a single treatment session), timed from the start of treatment, is measured in minutes. Continuous treatment leads to increased tissue tolerance; the denominator design of t can inhibit excessive energy accumulation. For the weighting coefficients k1, k2, and α, k1 represents the weight of age's influence (default 0.3, adjusted as needed); k2 represents the weight of body fat's influence (default 0.7, adjusted as needed); and α is the metabolic correction coefficient (base value 1.2, adjusted as needed).

[0077] For the resonant frequency output value of the dynamic correction model of the time decay factor, the correction formula is:

[0078] F new =F0·(1+ξ·ΔV);

[0079] Wherein, F0 is the resonant frequency (in kHz) of the initial output of the dynamically adjusted model; ΔV is the real-time acquired cell membrane potential fluctuation value (in mV), which is obtained by a bioelectric sensor at a sampling rate of 200 Hz.

[0080] For example, taking a patient with hypertension and obesity (Age = 58 years, BMI = 29) as an example, k1 = 0.35, k2 = 0.75, and α = 1.1 are set according to the disease type; the duration of a single treatment is t = 25 minutes, and ΔV = 0.42mV is measured in real time. Therefore, the time decay factor is calculated as follows:

[0081]

[0082] If the initial output of the model is F0 = 28.5kHz, then the corrected resonant frequency is:

[0083] F new =28.5×(1+1.53×0.42)≈46.8kHz.

[0084] In one embodiment, step S100 specifically includes:

[0085] S110: Real-time acquisition of the user's bioelectrical signals, biomagnetic signals, and thermodynamic signals through a multimodal physiological sensor array of wearable devices, and continuous recording to generate treatment history data;

[0086] S120. Perform feature fusion processing on the multimodal signals to generate a comprehensive physiological state assessment value;

[0087] S130. When the evaluation value exceeds the preset health threshold range, the multi-channel anomaly detection algorithm is triggered to generate the anomaly trigger instruction and identify the type of abnormal physiological parameter.

[0088] In this embodiment, by adopting this scheme, multimodal physiological sensing data (bioelectric / magnetic / thermodynamic signals) from wearable devices can be integrated to achieve full-dimensional dynamic monitoring and fusion assessment of the user's physiological state, overcoming the limitations of single signal detection. When the comprehensive assessment value generated by the fusion of multi-source signals is abnormal, treatment instructions are precisely triggered and the type of abnormal parameter is identified, significantly improving the timeliness and targeting of treatment intervention and avoiding delays in efficacy caused by misjudgment or missed detection.

[0089] Specifically:

[0090] For step S110, the wearable device's multimodal physiological sensor array collects bioelectrical signals, biomagnetic signals, and thermodynamic signals. For example, a smartwatch worn by the user collects bioelectrical signals (blood oxygen saturation), a chest patch sensor collects biomagnetic signals (cardiac magnetic field disorder), and an infrared thermal imager collects thermodynamic signals (local microcirculation blood flow rate). The multimodal signals cover the three dimensions of electrophysiology, magnetophysiology, and thermodynamics, which can avoid missed detections caused by single signal distortion. At the same time, continuous recording forms an individual health baseline, providing dynamic reference for abnormal detection.

[0091] Furthermore, multimodal signal complementarity verification: the fusion of bioelectrical signals (such as blood oxygen) and thermodynamic signals (such as body surface temperature) can distinguish between pathological abnormalities and environmental interference (such as peripheral blood oxygen reading distortion caused by low temperature); wearable integration advantages: non-invasive continuous monitoring is achieved through flexible sensors such as wristbands / chest patches, ensuring full-cycle tracking of physiological status during treatment.

[0092] In step S120, the multimodal signal integrating the collected bioelectrical, biomagnetic, and thermodynamic signals is preprocessed, feature extracted, and fused to generate a comprehensive physiological state assessment value. Preprocessing includes denoising and alignment; feature extraction includes temporal, frequency, and spatiotemporal feature extraction; and feature fusion uses a weighted entropy method to allocate weights, for example, 60% for bioelectrical signals, 30% for biomagnetic signals, and 10% for thermodynamic signals. Then, principal component analysis is used to reduce the dimensionality to three principal components, generating a comprehensive physiological state assessment value ranging from 0 to 100.

[0093] For step S130, the health threshold range is set by calculating a moving average baseline based on personal historical data (e.g., the average assessment value over the past 7 days, μ = 75 points), and setting the threshold range as μ ± 2σ (σ being the standard deviation). When the comprehensive physiological state assessment value is detected to be outside the set health threshold range, anomaly detection is triggered, a multi-channel detection algorithm is started, and the specific type of signal abnormality is analyzed (e.g., an ECG signal showing a rapid heart rate, or a temperature reading indicating local inflammation). After confirming the abnormality type, a treatment instruction is generated (e.g., "Tachycardia, it is recommended to adjust the frequency to xx kHz"), and the source of the abnormality is marked.

[0094] In one embodiment, step S100 further includes:

[0095] S111. Synchronize the treatment history data recorded by the wearable device to the dynamic adjustment model;

[0096] S112. Optimize the weight allocation strategy for feature fusion processing based on incremental learning algorithm.

[0097] In this embodiment, by adopting this scheme, the treatment history data stream recorded by the wearable device can be synergistically combined with real-time monitoring data, and the weight strategy for multimodal signal fusion can be continuously optimized using an incremental learning algorithm. This mechanism enables the device to dynamically adjust the decision priority of different physiological signals based on the user's long-term treatment feedback, solving the problem of insufficient individual adaptability caused by traditional fixed weight allocation, and achieving adaptive evolutionary capability where the treatment effect increases with the duration of use.

[0098] In one embodiment, step S300 specifically includes:

[0099] S310. Analyze the waveform parameter set in the treatment plan to generate a control signal sequence containing frequency modulation instructions, amplitude control instructions, and timing constraint instructions;

[0100] S320. Based on a preset impedance matching strategy, the control signal sequence is converted into a drive control signal, the strategy including:

[0101] The amplitude output gradient is pre-compensated based on the user's body surface impedance characteristics;

[0102] Optimize frequency modulation parameters based on the attenuation characteristics of the target frequency band;

[0103] S330. The drive control signal is loaded into the particle resonance wave output device through a multi-channel synchronous transmission protocol to activate the wave field resonance mode of the target frequency band.

[0104] In this embodiment, by adopting this scheme, adaptive pre-compensation and precise parameter optimization of the drive control signal can be achieved based on the user's surface impedance characteristics and the bio-attenuation characteristics of the target treatment frequency band. Amplitude gradient pre-adjustment and frequency modulation parameter adaptation are completed during the signal generation stage, ensuring that after the particle resonance wave output device is activated, the wave field energy distribution of the target frequency band precisely matches the biophysical characteristics of the lesion site. This significantly improves the targeted transmission efficiency of treatment energy and the consistency of tissue absorption, avoiding therapeutic deviations caused by contact impedance fluctuations or frequency band selection mismatch.

[0105] Specifically:

[0106] In step S310, the treatment plan generated by the dynamically adjusted model is analyzed, and a set of waveform parameters, including frequency modulation instructions, amplitude control instructions, and timing constraint instructions, is extracted. These parameters are then encoded into a control signal sequence (such as PWM waveforms or DAC digital signals), and an executable digital-to-analog control signal is generated. By converting the abstract parameters output by the model into physical control signals executable by the device, execution deviations caused by signal format mismatches are avoided.

[0107] For step S320, the contact impedance difference is pre-compensated by the body surface impedance (such as the impedance difference between dry skin and sweaty skin) to ensure stable energy transfer efficiency; the frequency is automatically optimized according to the target tissue depth to focus energy on the lesion (such as 28kHz for superficial muscles and 32kHz for deep organs) to ensure the accuracy of energy transfer; based on the impedance matching strategy, the control signal sequence is converted into a drive control signal through signal analysis, digital-to-analog conversion and other processes.

[0108] For step S330, the multi-channel synchronization protocol includes: clock synchronization: using the IEEE 1588PTP protocol, with the clock deviation of each channel calibrated to <100ns; data encapsulation: packaging the drive control signals according to the channel number (e.g., channel 1: frequency command, channel 2: amplitude command); and loading the drive control signals to the particle resonance wave output device based on the multi-channel synchronous transmission protocol to activate the wave field resonance mode of the target frequency band, so that the particle resonance wave output device of the wave conduction health care device outputs the frequency, amplitude, and duration of the corresponding particle resonance wave according to the treatment plan, so as to accurately match the user's current physiological state.

[0109] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0110] In one embodiment, a treatment control system for an intelligent adaptive wave conduction health care device is provided. This treatment control system corresponds to the treatment control method for an intelligent adaptive wave conduction health care device described in the above embodiment. The treatment control system for the intelligent adaptive wave conduction health care device includes:

[0111] The acquisition module is used to acquire the user's physiological state signals in real time. When the physiological state signals are detected to deviate from the preset health threshold range, an abnormal trigger command is generated.

[0112] The generation module is used to input the physiological index data corresponding to the abnormal triggering command into the dynamic adjustment model. The dynamic adjustment model generates a treatment plan based on the mapping relationship between physiological indexes and wave conduction parameters. The treatment plan includes at least the parameters of resonance frequency, amplitude and duration of action.

[0113] The driving module is used to generate a driving control signal according to the treatment plan, and the driving control signal is used to adjust the particle resonance wave output device in the wave conduction health care device.

[0114] The output module is used to drive the target particle resonance wave to output the resonance frequency and amplitude corresponding to the control signal through the particle resonance wave output device, and to continuously drive the action time corresponding to the control signal.

[0115] Specific limitations regarding the treatment control system of an intelligent adaptive wave conduction health care device can be found in the above description of the treatment control method for such a device, and will not be repeated here. Each module in the aforementioned treatment control system of the intelligent adaptive wave conduction health care device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0116] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows. Figure 2 The computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores user data, performs data processing, and performs data analysis. The network interface communicates with external terminals via a network. When the computer program is executed by the processor, it implements a treatment control method for an intelligent adaptive wave conduction health care device.

[0117] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a treatment control method for an intelligent adaptive wave conduction health care device.

[0118] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements a treatment control method for an intelligent adaptive wave conduction health care device.

[0119] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0120] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0121] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A treatment control method for an intelligent adaptive wave conduction health care device, characterized in that, Includes the following steps: The system collects user physiological state signals in real time, and generates an abnormality trigger command when the physiological state signals deviate from the preset health threshold range. The physiological index data corresponding to the abnormal triggering command is input into the dynamic adjustment model. The dynamic adjustment model generates a treatment plan based on the mapping relationship between the physiological index and the wave conduction parameters. The treatment plan includes at least the parameters of resonance frequency, amplitude and duration of action. A drive control signal is generated according to the treatment plan, and the drive control signal is used to adjust the particle resonance wave output device in the wave conduction health care device. The particle resonance wave output device is used to drive the target particle resonance wave to output the resonance frequency and amplitude corresponding to the control signal, and to continuously drive the action time corresponding to the control signal.

2. The treatment control method of the intelligent adaptive wave conduction health care device as described in claim 1, characterized in that, The method for constructing the dynamic adjustment model includes: Obtain a historical treatment dataset, which contains multidimensional physiological index data and its corresponding effective treatment parameter sets; The dataset is preprocessed to extract the correlation features between the fluctuation characteristics of physiological indicators and the adjustment amount of treatment parameters in the dataset; Based on the aforementioned correlation features, a machine learning algorithm is used to perform nonlinear regression modeling to obtain a dynamic adjustment model of physiological indicators and treatment parameters. Obtain feedback data on treatment effectiveness, optimize the dynamic adjustment model using gradient descent based on the feedback data, and establish a dynamic association rule base.

3. The treatment control method of the intelligent adaptive wave conduction health care device as described in claim 2, characterized in that, The step of obtaining a dynamic adjustment model of physiological indicators and treatment parameters by using machine learning algorithms to perform nonlinear regression modeling based on the correlation features further includes: A time decay factor is added, which is calculated using the following formula: Where Age is the user's age, BMI is the user's body mass index, t is the cumulative duration of a single treatment, and k1, k2, and α are preset weighting coefficients; the time decay factor is used to dynamically correct the resonant frequency output value of the dynamic adjustment model.

4. The treatment control method of the intelligent adaptive wave conduction health care device as described in claim 1, characterized in that, The step of real-time acquisition of user physiological state signals and generating an abnormality trigger command when the physiological state signals deviate from a preset health threshold range specifically includes: The wearable device uses a multimodal physiological sensor array to collect the user's bioelectrical signals, biomagnetic signals, and thermodynamic signals in real time, and continuously records and generates treatment history data. The multimodal signals are subjected to feature fusion processing to generate a comprehensive physiological state assessment value; When the evaluation value exceeds the preset health threshold range, the multi-channel anomaly detection algorithm is triggered to generate the anomaly trigger instruction and identify the type of abnormal physiological parameter.

5. The treatment control method of the intelligent adaptive wave conduction health care device as described in claim 4, characterized in that, The step of generating an abnormality trigger command when the real-time acquisition of user physiological state signals is detected to deviate from a preset health threshold range further includes: Synchronize the treatment history data recorded by the wearable device to the dynamic adjustment model; The weight allocation strategy for feature fusion processing is optimized based on the incremental learning algorithm.

6. The treatment control method of the intelligent adaptive wave conduction health care device as described in claim 1, characterized in that, The step of generating a drive control signal according to the treatment plan, wherein the drive control signal is used to adjust the particle resonance wave output device in the wave conduction health care device, specifically includes: The waveform parameter set in the treatment plan is analyzed to generate a control signal sequence containing frequency modulation instructions, amplitude control instructions, and timing constraint instructions. The control signal sequence is converted into a drive control signal based on a preset impedance matching strategy, the strategy including: The amplitude output gradient is pre-compensated based on the user's body surface impedance characteristics; Optimize frequency modulation parameters based on the attenuation characteristics of the target frequency band; The driving control signal is loaded into the particle resonance wave output device through a multi-channel synchronous transmission protocol to activate the wave field resonance mode of the target frequency band.

7. A treatment control system for an intelligent adaptive wave conduction health care device, used to implement the steps of the treatment control method for an intelligent adaptive wave conduction health care device as described in any one of claims 1-6, characterized in that, include: The acquisition module is used to acquire the user's physiological state signals in real time. When the physiological state signals are detected to deviate from the preset health threshold range, an abnormal trigger command is generated. The generation module is used to input the physiological index data corresponding to the abnormal triggering command into the dynamic adjustment model. The dynamic adjustment model generates a treatment plan based on the mapping relationship between physiological indexes and wave conduction parameters. The treatment plan includes at least the parameters of resonance frequency, amplitude and duration of action. The driving module is used to generate a driving control signal according to the treatment plan, and the driving control signal is used to adjust the particle resonance wave output device in the wave conduction health care device. The output module is used to drive the target particle resonance wave to output the resonance frequency and amplitude corresponding to the control signal through the particle resonance wave output device, and to continuously drive the action time corresponding to the control signal.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the treatment control method of the intelligent adaptive wave conduction health care device as described in any one of claims 1-6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the treatment control method of the intelligent adaptive wave conduction health care device as described in any one of claims 1-6.

Images