Cupping therapy real-time monitoring and closed-loop regulation and control system based on multi-modal data fusion

Abstract

The invention relates to a multi-modal data fusion cupping therapy real-time monitoring and closed-loop regulation and control system, which belongs to the technical field of medical instruments and comprises a data acquisition module, a data processing module, a man-machine interaction platform and a control module. The negative pressure, subcutaneous tissue blood oxygen parameters and body surface morphological changes in the cupping process are monitored in a non-invasive mode in real time, the data processing module calculates the hemoglobin concentration, the blood oxygen saturation degree and the hyperemia index in real time and conducts multi-modal data fusion analysis in combination with fuzzy logic, and the control module dynamically adjusts the power of an air pump through an incremental digital PID algorithm. According to the system, the safety, consistency and reliability of treatment can be improved, the dependence on the experience of an operator is reduced, and data support is provided for curative effect evaluation and personalized treatment.

Description

Technical Field

[0001] This invention belongs to the field of medical device technology and relates to a multimodal data dynamic non-invasive monitoring system and control system, especially a multimodal data fusion cupping therapy real-time monitoring and closed-loop control system. Background Technology

[0002] Cupping therapy is a traditional Chinese medicine therapy that creates negative pressure at specific points on the body surface, causing local tissue congestion or slight rupture of subcutaneous capillaries to achieve the purpose of promoting blood circulation, removing blood stasis, and relaxing muscles and tendons. Modern research shows that it may work by affecting blood circulation, immune and pain regulation pathways. It is often used as an adjunct treatment for musculoskeletal pain and soft tissue injuries. However, traditional cupping therapy lacks means to quantify parameters, relies heavily on the operator's experience, and cannot monitor the effects of cupping in real time, thus making it impossible to make real-time adjustments.

[0003] Patent CN120242202A discloses a cupping machine. The cupping device of this invention patent is equipped with a real-time pressure detection module, a negative pressure generating device and a calculation module. By monitoring the negative pressure inside the cup in real time and making feedback adjustments, the stability of parameters during the cupping process is maintained. It also has a visual detection module for detecting the location of the acupoints being cupped.

[0004] Patent CN109276234A discloses a hemodynamic parameter monitoring system for cupping therapy. This invention patent monitors tissue hemodynamic data using an optical probe during cupping, thereby effectively providing information on the physiological effects of cupping.

[0005] Patent CN116327187A discloses a cupping monitoring system with an adaptive flexible probe. This invention integrates an optical monitoring system into the cupping device to achieve real-time monitoring of deep tissue hemodynamics during the cupping process, and enhances the practicality and comfort of the device by using a flexible probe.

[0006] However, the data collected in the above-mentioned methods are all of a single type, which cannot monitor and adjust multiple physiological parameters in real time during cupping using various devices, nor can it provide real-time feedback and adjustment for the cupping process, or use specific and scientific methods for parameter control. Furthermore, there is currently no research on the acquisition and analysis of image data of the cupping site during cupping. Summary of the Invention

[0007] The purpose of this invention is to overcome the shortcomings of the prior art and propose a real-time parameter monitoring and closed-loop control system for cupping therapy based on multimodal data fusion. This system can monitor the changes in physiological parameters during the cupping process in real time in a dynamic and non-invasive manner and feed them back to the cupping device for real-time closed-loop stable control.

[0008] In view of the above background analysis, the present invention provides a multimodal data fusion cupping therapy real-time monitoring and closed-loop control system, including a data acquisition module, a data processing module, a human-computer interaction platform and a control module.

[0009] The data acquisition module includes an optical signal acquisition device, an image signal acquisition device, and a pressure signal acquisition device, which are used to acquire optical, visual, and pressure multimodal signals, respectively.

[0010] The data processing module includes optical signal processing, image signal processing, and multimodal data fusion analysis and decision-making units, which are used to process pressure information, optical information and visual image information, respectively, and fuse the processed data to obtain control information.

[0011] The human-computer interaction platform includes a data visualization unit and an operation control unit, which are used to visualize the results obtained by the data processing module and provide users with an operation control input interface.

[0012] The control module is used to receive signals from the human-machine interaction platform and the data processing module, and to control the power of the air pump.

[0013] The control module is also connected to a vacuum pump, which regulates the negative pressure inside the tank by controlling the power of the vacuum pump.

[0014] Specifically, the optical signal acquisition device includes a light source and a detector embedded in the base, which measures the scattering and absorption of near-infrared light by tissue through a transmitter-receiver probe and transmits the relevant data to the data processing module.

[0015] The data processing module first calculates the change in light absorption at each wavelength. The relationship between the change in light absorption and the change in hemoglobin concentration is expressed by the following formula:

[0016]

[0017] Where λ1 and λ2 are the wavelengths of the two corresponding light waves, and ΔA(λ1) and ΔA(λ2) are the relationships between the light absorption changes of the two corresponding light waves and the changes in hemoglobin concentration. These are the molar extinction coefficients of oxyhemoglobin and deoxyhemoglobin at their respective wavelengths. Δc Hb The concentrations of oxyhemoglobin and deoxyhemoglobin are to be determined; L is the distance between the light source and the detector; DPL is the differential path factor, a dimensionless correction parameter related to tissue optical properties; G(λ1) is the attenuation caused by changes in the photon scattering path, usually assumed to be consistent at both wavelengths. By eliminating the need to solve the above system of two linear equations through differential calculation, the concentrations can be calculated in real time. Δc HbSubsequently, tissue oxygen saturation can be calculated using the following formula:

[0018]

[0019] Tissue oxygen saturation reflects changes in local tissue blood perfusion and total hemoglobin concentration. It reflects changes in blood perfusion in local tissues.

[0020] Specifically, the image signal acquisition device and the data processing module are connected via a data transmission bus.

[0021] The data processing module processes the image data acquired by the image signal acquisition device, including color space conversion and congestion index calculation. Specifically, it first locates the circular area within the can opening and eliminates edge shadow interference. Then, it uses color space conversion to transform the ROI area from the RGB color space to the HSV color space to better separate color information. Next, it calculates the congestion index: congestion is mainly manifested as an enhancement of red, which in the HSV space is reflected as a decrease in hue value and an increase in saturation value. Therefore, the congestion index I can be expressed as:

[0022]

[0023] Where: N is the total number of pixels within the ROI. and These are the normalized H and S values ​​(range 0 to 1) of the i-th pixel. α and β are weighting coefficients used to adjust the contribution of the H and S components. The index range is [0,1], with larger values ​​indicating more severe congestion. The Sobel operator is used to calculate the gradient magnitude of the image, followed by binarization and morphological opening to eliminate minor noise. If the area of ​​a continuous region exceeds a set threshold, it is judged as an abnormal bulge or blister, triggering a safety alarm. For example, a continuous region area exceeding 50 pixels is judged as an abnormal bulge or blister.

[0024] Specifically, the data processing module also includes a multimodal data fusion analysis and decision-making unit, which performs time alignment, feature extraction and fusion analysis on asynchronously acquired pressure signals, optical signals and image data, and finally outputs signals for closed-loop control and safety warning.

[0025] In the data acquisition module, the pressure signal acquisition device obtains the pressure signal in a high-frequency acquisition mode of f1, the optical signal acquisition device 4 obtains the optical signal in a medium-frequency acquisition mode of f2, and the visual image signal acquisition device 3 obtains the image signal in a low-frequency acquisition mode of f3, wherein f1 > f2 > f3.

[0026] The hardware timestamp-based interpolation alignment method unifies all data streams onto the same time axis with a preset fusion period. For low-frequency image data, the extracted feature values, such as the congestion index, remain constant between two acquisition frames until the next frame is updated.

[0027] Features were extracted from pressure signals, optical signals, and image signals, including real-time negative pressure value P, negative pressure change rate dP / dt, and the percentage of time the negative pressure was maintained within the target range; real-time blood oxygen saturation StO2(t) and blood oxygen decrease rate d(StO2) / dt; total hemoglobin concentration tHb(t), real-time congestion index I(t), and congestion index change rate dI / dt.

[0028] A fuzzy logic system is introduced, taking the above features as input to comprehensively evaluate the current efficacy and safety situation. The continuous and precise input values ​​are transformed into discrete variables, each of which corresponds to a membership function. Through a fuzzy rule base based on expert knowledge, the results of multi-dimensional discrete variables are combined and reasoned. The results of fuzzy reasoning are then transformed into a precise output value, namely the Comprehensive Safety Index (CSI) and the Therapeutic Effect Index (TEI), both with a value range of [0,1]. The output of the fusion analysis module is used to dynamically optimize the control loop.

[0029] The control module employs an incremental digital PID control algorithm to dynamically adjust the PWM duty cycle of the vacuum pump at a fixed frequency, thereby precisely controlling the negative pressure inside the tank. The control algorithm calculates the output increment Δu(k) at the k-th sampling time:

[0030]

[0031] Where: e(k) = P t arget-P m easure(k) is the deviation between the current negative pressure setpoint and the measured value, K. p ,K i ,K d These are the proportional, integral, and derivative coefficients, which need to be tuned based on the system response. T s Given the sampling period, the actual control output at the current moment is u(k) = u(k-1) + Δu(k). This output value u(k) is converted into the duty cycle of the PWM signal to drive the air pump motor. Anti-saturation processing of the integral term and feedforward filtering of the derivative term are also introduced into the algorithm to enhance the stability and response speed of the control.

[0032] The parameters Kp, Ki, and Kd of the PID controller are functions of CSI, as detailed below:

[0033]

[0034] in, The baseline PID parameters are tuned based on the system's initial response. The higher the CSI, the more conservative the system tends to be. When the CSI increases, the system automatically reduces the proportional coefficient Kp and increases the derivative coefficient Kd, making the control action gentler and more cautious, avoiding the risk of exacerbating negative pressure fluctuations. The system can adjust the treatment strategy in real time based on the TEI. If the TEI rises rapidly to a high level in the early stages of treatment, it indicates that the patient is sensitive, and the system can suggest shortening the treatment time or reducing the target negative pressure. If the TEI remains low, the system can prompt the operator whether to appropriately increase the stimulation. This fusion architecture has an inherent fault tolerance mechanism.

[0035] This invention proposes a real-time monitoring and closed-loop control system for cupping therapy based on multimodal data fusion. It solves the problem that traditional cupping therapy relies heavily on the operator's personal experience for negative pressure control and lacks objective quantitative standards. By integrating signals from three modalities—pressure, optical signals, and visual images—it achieves for the first time multi-dimensional, real-time, and non-invasive synchronous monitoring of negative pressure intensity, deep tissue blood oxygenation status, and changes in body surface morphology during cupping, providing an objective data foundation for efficacy evaluation and mechanism of action research.

[0036] This invention introduces a closed-loop control logic based on real-time data. After the data processing module analyzes the collected information, the control module can adjust the power of the suction pump accordingly, thereby dynamically maintaining or adjusting the negative pressure inside the tank to a preset safe and effective range. This avoids the risks of soft tissue damage, blisters, etc. caused by excessive negative pressure or prolonged duration, while ensuring the consistency, repeatability, and optimization of treatment parameters, thus improving the safety and reliability of treatment. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention, 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 these drawings without creative effort.

[0038] Figure 1 This is a schematic diagram of the structure of the present invention;

[0039] Figure 2 This is a block diagram of the multimodal data non-invasive monitoring system of the present invention;

[0040] Among them, 1. tank body, 2. air outlet and air pump, 3. image signal acquisition device and pressure signal acquisition device, 4. optical signal acquisition device. Detailed Implementation

[0041] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0042] like Figure 1-2 As shown, the present invention provides a real-time monitoring and closed-loop control system for cupping therapy based on multimodal data fusion, including a data acquisition module, a data processing module, a human-computer interaction platform, and a control module.

[0043] The data acquisition module includes an optical signal acquisition device 4, an image signal acquisition device, and a pressure signal acquisition device 3, which are used to acquire optical, visual, and pressure multimodal signals, respectively.

[0044] The data processing module includes optical signal processing, image signal processing, and multimodal data fusion analysis and decision-making units, which are used to process pressure information, optical information and visual image information, respectively, and fuse the processed data to obtain control information.

[0045] The human-computer interaction platform includes a data visualization unit and an operation control unit, which are used to visualize the results obtained by the data processing module and provide users with an operation control input interface.

[0046] The control module is used to receive signals from the human-machine interaction platform and the data processing module, and to control the power of the air pump.

[0047] The control module is also connected to a vacuum pump, which regulates the negative pressure inside the tank by controlling the power of the vacuum pump.

[0048] Specifically, the pressure signal acquisition device is embedded in the tank wall of tank 1 1-2 cm from the top, and is connected to the data processing module via a bus. The bus and the tank wall are sealed together.

[0049] Specifically, the optical signal acquisition device includes a light source and a detector embedded in the base, wherein the light source and the detector protrude slightly from the surface of the base by 2-3 mm to ensure good contact between the detector and the skin.

[0050] In one specific implementation, the light source and detector are a 700nm-900nm dual-wavelength integrated LED near-infrared light source and near-infrared optical detector. The scattering and absorption of near-infrared light by tissue is measured by a transmitter-receiver probe, and the relevant data is transmitted to the data processing module.

[0051] The data processing module first calculates the change in light absorption at each wavelength. The relationship between the change in light absorption and the change in hemoglobin concentration is expressed by the following formula:

[0052]

[0053] Where λ1 and λ2 are the wavelengths of the two corresponding light waves, and ΔA(λ1) and ΔA(λ2) are the relationships between the light absorption changes of the two corresponding light waves and the changes in hemoglobin concentration. These are the molar extinction coefficients of oxyhemoglobin and deoxyhemoglobin at their respective wavelengths. Δc Hb The concentrations of oxyhemoglobin and deoxyhemoglobin are to be determined; L is the distance between the light source and the detector; DPL is the differential path factor, a dimensionless correction parameter related to tissue optical properties; G(λ1) is the attenuation caused by changes in the photon scattering path, usually assumed to be consistent at both wavelengths. By eliminating the need to solve the above system of two linear equations through differential calculation, the concentrations can be calculated in real time. Δc Hb Subsequently, tissue oxygen saturation can be calculated using the following formula:

[0054]

[0055] Tissue oxygen saturation reflects changes in local tissue blood perfusion and total hemoglobin concentration. It reflects changes in blood perfusion in local tissues.

[0056] Specifically, the image signal acquisition device and the data processing module are connected via a data transmission bus. In one specific embodiment, the image signal acquisition device uses a miniature camera with a resolution of 1080p, which acquires 3 frames of images per second.

[0057] The data processing module processes the image data acquired by the image signal acquisition device, including color space conversion and congestion index calculation. Specifically, it first locates the circular area within the can opening and eliminates edge shadow interference. Then, it uses color space conversion to transform the ROI area from the RGB color space to the HSV color space to better separate color information. Next, it calculates the congestion index: congestion is mainly manifested as an enhancement of red, which in the HSV space is reflected as a decrease in hue value and an increase in saturation value. Therefore, the congestion index I can be expressed as:

[0058]

[0059] Where: N is the total number of pixels within the ROI. and These are the normalized H and S values ​​(range 0 to 1) of the i-th pixel. α and β are weighting coefficients used to adjust the contribution of the H and S components. The index range is [0,1], with larger values ​​indicating more severe congestion. The Sobel operator is used to calculate the gradient magnitude of the image, followed by binarization and morphological opening to eliminate minor noise. If the area of ​​a continuous region exceeds a set threshold, it is judged as an abnormal bulge or blister, triggering a safety alarm. For example, a continuous region area exceeding 50 pixels is judged as an abnormal bulge or blister.

[0060] Specifically, the data processing module also includes a multimodal data fusion analysis and decision-making unit, which performs time alignment, feature extraction and fusion analysis on asynchronously acquired pressure, optical and image data, and finally outputs signals for closed-loop control and safety warning.

[0061] In the data acquisition module, the pressure signal acquisition device obtains the pressure signal in a high-frequency acquisition mode of f1, the optical signal acquisition device 4 obtains the optical signal in a medium-frequency acquisition mode of f2, and the visual image signal acquisition device 3 obtains the image signal in a low-frequency acquisition mode of f3, wherein f1 > f2 > f3.

[0062] The hardware timestamp-based interpolation alignment method unifies all data streams onto the same time axis with a preset fusion period. For low-frequency image data, the feature values ​​(such as the congestion index) extracted between two acquisition frames remain constant until the next frame is updated. In one specific implementation, the preset fusion period is 100ms.

[0063] Features were extracted from pressure signals, optical signals, and image signals, including real-time negative pressure value P, negative pressure change rate dP / dt, and the percentage of time the negative pressure was maintained within the target range; real-time blood oxygen saturation StO2(t) and blood oxygen decrease rate d(StO2) / dt; total hemoglobin concentration tHb(t), real-time congestion index I(t), and congestion index change rate dI / dt.

[0064] A fuzzy logic system is introduced, taking the aforementioned features as input to comprehensively evaluate the current efficacy and safety status. Precise values ​​such as negative pressure change rate, blood oxygen saturation rate, and congestion index are converted into low, medium, and high fuzzy linguistic variables through preset membership functions. Each discrete variable corresponds to a membership function. Based on expert experience, a series of "IF-THEN" rules are set, such as: "IF high negative pressure change rate AND high blood oxygen saturation rate THEN high safety index." The results of the multi-dimensional discrete variables are combined for inference, and the fuzzy inference output is then converted into a precise output value using the centroid method, namely the Comprehensive Safety Index (CSI) and the Therapeutic Effect Index (TEI), expressed as:

[0065]

[0066] Where, μ i x i This relates to the membership degree of the corresponding parameter and the value of the output variable.

[0067] Both CSI and TEI have a value range of [0,1]. The output of the fusion analysis module is used to dynamically optimize the fuzzy rule base of the control loop.

[0068] The control module employs an incremental digital PID control algorithm to dynamically adjust the PWM duty cycle of the vacuum pump at a fixed frequency, thereby precisely controlling the negative pressure inside the tank. The control algorithm calculates the output increment Δu(k) at the k-th sampling time:

[0069]

[0070] Where: e(k) = P target -P measure (k) represents the deviation between the current negative pressure setpoint and the measured value, K p ,K i ,K d These are the proportional, integral, and derivative coefficients, which need to be tuned according to the system response. Ts is the sampling period. The actual control output at the current moment is u(k) = u(k-1) + Δu(k). This output value u(k) is converted into the duty cycle of the PWM signal to drive the air pump motor. Anti-saturation processing of the integral term and feedforward filtering of the derivative term are also introduced into the algorithm to enhance the stability and response speed of the control.

[0071] The parameters Kp, Ki, and Kd of the PID controller are functions of CSI, expressed as:

[0072]

[0073] in, The baseline PID parameters are tuned based on the system's initial response. A higher CSI indicates a more conservative control approach. When CSI increases, the system automatically reduces the proportional gain Kp and increases the derivative gain Kd, making the control action gentler and more cautious, avoiding the risk of exacerbated negative pressure fluctuations. The system can adjust the treatment strategy in real time based on TEI. If TEI rises rapidly to a high level in the early stages of treatment, it indicates a sensitive patient response, and the system can suggest shortening the treatment time or lowering the target negative pressure. If TEI remains low, the system can prompt the operator to appropriately increase the stimulation. This fusion architecture has an inherent fault-tolerance mechanism. For example, optical probes may generate signal noise due to hair or vigorous movement. In this case, the system can cross-validate using image information and pressure stability. If the optical signal is abnormal while the pressure and image signals are stable, the optical abnormality is temporarily ignored, and the data segment is marked as unreliable, rather than immediately triggering an error alarm, thereby reducing the false alarm rate and improving system robustness.

[0074] The human-computer interaction platform includes a data visualization module and an operation control module. The data visualization module is connected to the data processing module and displays the data obtained from the data processing device to the user in a visual manner. The operation control module is connected to the control module and is used to transmit user commands to the control module. In a specific embodiment, the human-computer interaction platform receives commands from the operator to set the duration of the cupping process, the negative pressure, and to control the start and stop of the cupping process in real time. The data processing module can compare the collected negative pressure with the set negative pressure, calculate the valve opening or suction pump power using the gradient descent method, and send the commands to the control module. Simultaneously, when the negative pressure rises excessively due to external factors or malfunctions, it can urgently open the valve to ensure user safety. The human-computer interaction platform can also directly send user commands to the control module for direct regulation.

[0075] The human-computer interaction platform can be selected from PC or mobile phone. Through software and APP platforms developed based on Windows / Android systems, it can realize data visualization and real-time control. The human-computer interaction platform can connect to the device through a wireless transmission device to help users operate the device remotely, or it can connect to a PC / mobile phone through a wired connection to help users perform low-latency real-time close-range operation.

[0076] The working process of this invention is as follows:

[0077] The cupping jar is placed on the desired acupoint. The user sets the time through the human-computer interaction platform. After the air pump of the jar is activated, it adheres tightly to the skin surface through negative pressure. Then, the dual-wavelength LED light source, miniature camera, and optical probe are automatically activated to collect and transmit data. The entire cupping and detection process is non-invasive and will not cause any damage to the user's body. The data processing module analyzes and transmits the obtained data, and uses the data to provide real-time feedback and closed-loop control of the cupping process to maintain its stability and ensure safety. After receiving the data, the human-computer interaction platform displays it in a graphical format and accepts user commands for real-time adjustments, thus achieving closed-loop control of the cupping process.

[0078] 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 the present invention.

[0079] 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 merely 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. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0080] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0081] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0082] In the embodiments provided by this invention, it should be understood that the disclosed apparatus / terminal devices and methods can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0083] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0084] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0085] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0086] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention 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 the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A multi-modal data fusion cupping therapy real-time monitoring and closed-loop regulation system, characterized in that: The system comprises a data acquisition module, a data processing module, a man-machine interaction platform and a control module; The data acquisition module comprises optical signal acquisition devices (4), image signal acquisition devices and pressure signal acquisition devices (3) for acquiring optical, image and pressure multi-modal signals respectively; The data processing module aligns the optical, image and pressure multi-modal signals to the same time axis with a preset fusion period based on the interpolation alignment method of hardware time stamp, and extracts features from the optical, image and pressure signals, including real-time negative pressure value P, negative pressure change rate dP / dt, and time percentage of negative pressure maintained in the target interval, real-time blood oxygen saturation StO2(t), blood oxygen drop rate d(StO2) / dt, total hemoglobin concentration tHb(t), real-time congestion index I(t), and congestion index change rate dI / dt; The control module adopts a fuzzy logic control system, takes the above features as the input of the fuzzy logic system, and converts the output result of the fuzzy reasoning into a comprehensive safety index (CSI) and a therapeutic effect index (TEI); The control module adopts an incremental digital PID control algorithm to dynamically adjust the PWM duty cycle of the air suction pump at a fixed frequency, so as to accurately control the negative pressure in the tank. The parameters Kp, Ki and Kd of the PID controller are functions of the CSI, and are specifically as follows: wherein, Kp is a reference PID parameter; K p Kp i Kp d are proportional, integral, and derivative coefficients, respectively. The control module is also connected with the air suction pump to adjust the negative pressure in the tank by controlling the power of the air suction pump.

2. The real-time monitoring and closed-loop control system according to claim 1, wherein the PID control algorithm calculates the output increment Δu(k) at the kth sampling time: wherein: e(k) = P t arget-P m easure(k) is the deviation of the current time negative pressure set value and the measured value, K p ,K i ,K d respectively proportional, integral, differential coefficient, T s is the sampling period, the actual control output of the current time is u(k) = u(k-1) + Δu(k), the output value u(k) is converted to the duty ratio of the PWM signal, drive the air pump motor.

3. The real-time monitoring and closed-loop control system according to claim 1, wherein the pressure signal acquisition devices are embedded in the tank wall of the tank body 1 at a distance of 1-2 cm from the top.

4. The real-time monitoring and closed-loop control system according to claim 1, wherein the optical signal acquisition devices comprise light sources and probes embedded in the base, which measure the scattering and absorption of near-infrared light by tissues through the emission-reception probes, and transmit the related data to the data processing module.

5. The real-time monitoring and closed-loop control system according to claim 2, wherein the data processing module calculates the light absorption change at each wavelength, and the relationship between the light absorption change and the change in hemoglobin concentration is represented by the following formula: where λ1, λ2 are the wavelengths of the two corresponding light waves, ΔA(λ1), ΔA(λ2) are the relationships between the light absorption changes and the hemoglobin concentration changes of the two corresponding light waves; are the molar extinction coefficients of oxyhemoglobin and deoxyhemoglobin at the corresponding wavelengths, respectively, Δc Hb is the concentration of oxyhemoglobin and deoxyhemoglobin to be solved, L is the distance between the light source and the detector, DPL is the differential path factor, which is a dimensionless correction parameter related to the optical properties of the tissue, G(λ1) is the attenuation caused by the change of the photon scattering path, which is calculated in real time by difference calculation Δc Hb , and then the tissue oxygen saturation can be calculated by the following formula:

6. The real-time monitoring and closed-loop control system according to claim 1, wherein the data processing module processes the image data collected by the image signal acquisition devices, including color space conversion and congestion index calculation.

7. The real-time monitoring and closed-loop control system of claim 6, the color space conversion and congestion index calculation comprising: First, the circular area in the tank opening is located and the edge shadow interference is excluded, and then the ROI region is converted from the RGB color space to the HSV color space through color space conversion to better separate the color information; then, the congestion index calculation is performed: congestion mainly manifests as the enhancement of red color, which is reflected as the decrease of hue value and the increase of saturation value in the HSV space, therefore, the congestion index I can be expressed as: where: N is the total number of pixels within the ROI, and are the normalized H and S values of the ith pixel, ranging from 0 to 1, and a and β are weighting factors.

8. The real-time monitoring and closed-loop control system according to claim 1, wherein the comprehensive safety index (CSI) and the therapeutic effect index (TEI) are expressed as: wherein, μ i 、x i is the membership of the corresponding parameter to the value of the output variable. 9.The real-time monitoring and closed-loop regulation system of claim 1, wherein in the data acquisition module, the pressure signal acquisition device acquires pressure signals in a high frequency f1, the optical signal acquisition device 4 acquires optical signals in a medium frequency f2, and the visual image signal acquisition device 3 acquires image signals in a low frequency f3. f1>f2>f3.

10. The real-time monitoring and closed-loop regulation system of claim 1, wherein the human-machine interface platform comprises a data visualization unit and an operation control unit for visualizing the results obtained by the data processing module and providing an operation control input interface for the user.

Images