A microwave irradiation area matching method and system

Abstract

The application discloses a microwave irradiation area matching method and system, relates to the technical field of intelligent energy regulation and control, and establishes a controllable microwave radiation field in an intelligent resonant cavity, combines a multi-modal acquisition device to acquire target area reflection and transmission power, three-dimensional temperature distribution, blood flow change, tissue water content and thickness key parameters in real time, and constructs a comprehensive physiological response parameter set through multi-source signal fusion and inversion processing; calculates a tissue resonance response coefficient, judges a microwave resonance absorption state, and implements an energy regulation strategy; calculates a thermal response coupling coefficient, evaluates a thermal effect response, and gives a regulation strategy; calculates a microcirculation improvement index and implements corresponding regulation; finally, an AI dynamic energy adjustment model is constructed by using a convolutional neural network, and adaptive optimization of energy output is realized. The method can realize multi-parameter real-time closed-loop regulation and control, improve energy transmission efficiency and microcirculation improvement effect, and has the advantages of high precision, safety and personalized adaptation.

Description

Technical Field

[0001] This invention relates to the field of intelligent energy regulation technology, specifically to a microwave irradiation area matching method and system. Background Technology

[0002] With the development of modern rehabilitation medicine technology, microwave therapy, due to its high penetration, non-contact nature, and safety, has become an important means of physical therapy, pain relief, inflammation repair, and circulation improvement. Microwaves propagate in the form of electromagnetic waves within tissues, directly acting on deep tissues of the human body, causing molecules in the tissues to rotate and oscillate at high speed, thereby generating a thermal effect, promoting local blood circulation, accelerating metabolic processes, and improving tissue microcirculation, resulting in significant therapeutic and conditioning effects.

[0003] Microwave therapy systems typically rely on fixed power, frequency, and irradiation methods, making it impossible to achieve precise matching for different individuals, tissue types, and pathological conditions. Limited by energy transfer efficiency, uniformity of thermal effects, and differences in tissue response, existing technologies have the following main shortcomings:

[0004] Lacking personalized matching capabilities, most existing microwave therapy devices use uniform power output and fixed frequency, which cannot be dynamically adjusted according to the physiological differences, lesion characteristics and temperature response of the patient's local tissues, making it difficult to optimize the treatment effect.

[0005] The thermal effect and energy distribution are difficult to monitor in real time. In the existing technology, there is a lack of real-time and high-precision detection methods for temperature distribution, tissue thermal response and microcirculation improvement after microwave irradiation, making it difficult to achieve dynamic feedback and closed-loop control.

[0006] Lacking an intelligent optimization mechanism, existing microwave therapy systems fail to combine tissue physiological parameters, reflection / transmission power characteristics, and temperature field characteristics to optimize energy regulation through intelligent models, thus failing to fully realize the potential of microwave therapy.

[0007] Insufficient safety controls and the lack of early warning mechanisms for risks such as local overheating or insufficient microcirculation in some systems prevent multi-dimensional safety control and pose treatment risks. Summary of the Invention

[0008] To address the shortcomings of existing technologies, this invention provides a microwave irradiation area matching method and system to solve the problems mentioned in the background art.

[0009] To achieve the above objectives, the present invention provides the following technical solution: a microwave irradiation area matching method, comprising the following steps:

[0010] Step 1: By establishing a controllable microwave radiation field within the intelligent resonant cavity and combining it with a multi-modal acquisition device, key parameters such as reflection and transmission power, surface and deep temperature distribution, blood flow changes, tissue water content, and thickness of the target area are acquired in real time. After multi-source signal synchronization, filtering, and fusion processing, the three-dimensional temperature field and tissue dielectric properties are reconstructed using thermal conduction inversion and electromagnetic inversion algorithms to construct a comprehensive physiological response parameter set for the target area. A reference dataset is also measured.

[0011] Step 2: Extract the real and imaginary parts of the complex permittivity of the target region using a complex permittivity spectroscopy fitting algorithm. Combine this with the electromagnetic response curve and use a stress-electromagnetic coupling inversion algorithm to obtain the stress distribution characteristics inside the tissue. Calculate the tissue resonance response coefficient ORC and compare it with the tissue resonance response threshold Oth to determine whether the target region has reached the microwave resonance absorption state. If it has, proceed to the thermal effect analysis process; otherwise, provide appropriate strategies.

[0012] Step 3: By performing time series smoothing and Gaussian spatial filtering on the three-dimensional temperature field data, extract the temperature change rate and temperature spatial gradient, and construct the temperature dynamic characteristic curve of the target area; calculate the thermal response coupling coefficient HRC, and compare it with the thermal response threshold Hth to determine whether the thermal response of the current target area is qualified. If it is not qualified, an appropriate strategy is given.

[0013] Step 4: By obtaining the target area tissue resonance response coefficient ORC and the target area thermal response coupling coefficient HRC, combined with the blood flow rate change rate and reference data, calculate the target area microcirculation improvement index MCI, and compare it with the microcirculation improvement threshold Mth to determine whether the current microcirculation improvement effect in the area is qualified. If it is not qualified, give corresponding strategies.

[0014] Step 5: Construct an AI dynamic energy adjustment model using a convolutional neural network. With tissue resonance response, thermal response, and microcirculation improvement parameters as training inputs, extract energy absorption and physiological response features. Through multiple rounds of training and online optimization, achieve adaptive updating and dynamic optimization of the energy regulation model, thereby achieving the optimal match between energy transfer efficiency and microcirculation improvement effect under different individual and tissue conditions.

[0015] Preferably, step one includes:

[0016] S11. Real-time monitoring of microwave irradiation scenarios for rehabilitation therapy, pain theory, inflammation repair, and circulation improvement; setting an intelligent resonant cavity in the main cavity of the treatment machine to form a controllable microwave radiation field; deploying an embedded microwave detection array on the outer edge of the irradiation head to detect changes in reflected and transmitted power in real time; deploying multimodal temperature sensing components on the surface and surrounding area of ​​the irradiation target area to monitor local temperature distribution and dynamic changes.

[0017] S12. A frequency-tunable microwave signal is output through the resonant cavity driving device to scan and irradiate the target area; the microwave detection array synchronously acquires the signals of reflected power Pr and transmitted power Pt; the acquired raw signals are processed by time synchronization and noise filtering, normalization correction and spectrum decomposition, and the electromagnetic response curves and preliminary reflected and transmitted power spectrum data of each position are obtained after processing.

[0018] S13. By deploying infrared thermal imaging modules, embedded miniature thermocouple arrays, and fiber Bragg grating temperature sensors around the resonant cavity outlet, above the irradiation area, and at the lateral boundaries, the real-time temperature T of the target area's surface and at different depths is acquired. The multi-source temperature signals are then processed through time synchronization, noise filtering, and spatial interpolation fusion. A three-dimensional temperature field distribution of the target area is established using a finite-difference heat conduction inversion algorithm or Kriging interpolation reconstruction technique. ;

[0019] S14. Deploy photoplethysmography (PPG) sensors and infrared thermal imaging equipment in the target irradiation area to simultaneously collect dynamic blood flow parameters and obtain the blood flow rate of change Qss. Acquire the surface temperature distribution map of the target area using the infrared thermal imaging module. Combine this with an infrared reflectivity and absorptivity model to invert and obtain the local tissue water content hsl. Simultaneously, utilize a low-intensity microwave dielectric parameter testing module to emit probe waves at different measuring points and measure the reflection coefficient and phase difference. Calculate the tissue dielectric constant based on an electromagnetic inversion algorithm to obtain the tissue thickness zzh. Combine the blood flow rate of change, tissue thickness, and water content to form a local physiological response parameter set. Determine the baseline temperature Tbase, reference physiological temperature Tref, baseline blood flow Qref, and reference standard stress based on the measurement data under steady-state conditions. Establish a reference dataset.

[0020] Preferably, step two includes:

[0021] S21. Based on the reflection and transmission power spectrum data, a complex dielectric spectrum fitting algorithm is used to obtain the dielectric property parameters of the target region at different frequency bands, and the real part dcs and imaginary part dcx of the complex dielectric constant are extracted; based on the electromagnetic response curve, a stress-electromagnetic coupling inversion algorithm is used to fit the power distribution gradient to obtain the standard deviation of the stress distribution inside the target region. .

[0022] Preferably, step two further includes:

[0023] S22. By combining the reflected power Pr and the transmitted power Pt, the real part dcs and the imaginary part dcx of the complex permittivity, and the standard deviation of the stress distribution within the target region. and reference standard stress After dimensionless processing, the resonance response coefficient (ORC) of the target region tissue is calculated and obtained.

[0024] S23. By setting a preset tissue resonance response threshold Oth, and comparing the target region tissue resonance response coefficient ORC with the tissue resonance response threshold Oth, the first evaluation results are obtained, including:

[0025] When the target region tissue resonance response coefficient ORC ≥ tissue resonance response threshold Oth, it indicates that the target region has reached the microwave resonance absorption state and enters the thermal effect analysis process.

[0026] When the target region's tissue resonance response coefficient ORC is less than the tissue resonance response threshold Oth, it indicates that the target region has not reached the microwave resonance absorption state, triggering the first warning command and generating the first strategy: Adaptively fine-tuning the center frequency of the current frequency band using a resonant cavity frequency tuning device to improve local matching; adjusting the microwave waveform envelope and pulse width parameters to optimize energy distribution uniformity; real-time correction of the output power amplitude based on the reflection power Pr change trend of the previous cycle; rescanning once after correction and recalculating the target region's tissue resonance response coefficient ORC; if it still has not reached the tissue resonance response threshold Oth, then recording the current region as an energy coupling difficulty zone, the system automatically switches to low-power monitoring, extending the integration time to accumulate data and prevent local overheating.

[0027] Preferably, step three includes:

[0028] S31. Three-dimensional temperature field distribution based on the target region By employing time series smoothing and Gaussian spatial filtering algorithms, spatiotemporal denoising and local anomaly suppression processing are performed on the raw temperature of the three-dimensional temperature field distribution data of the target region, and the temperature change rate is extracted. and temperature spatial gradient The average temperature rise rate and thermal diffusion trend were calculated to establish the temperature dynamic characteristic curve of the target area.

[0029] Preferably, step three further includes:

[0030] S32, by acquiring the real-time temperature T and the rate of temperature change and temperature spatial gradient By combining the baseline temperature Tbase and the reference physiological temperature Tref, and after dimensionless processing, the thermal response coupling coefficient HRC of the target region is calculated and obtained.

[0031] S33. By setting a preset thermal response threshold Hth, and comparing and analyzing the thermal response coupling coefficient HRC of the target area with the thermal response threshold Hth, the second evaluation results are obtained, including:

[0032] When the thermal response coupling coefficient HRC of the target area is greater than or equal to the thermal response threshold Hth, it indicates that the thermal response of the current target area is qualified. Maintain the current energy output and beam control status and continue to monitor.

[0033] When the thermal response coupling coefficient HRC of the target area is less than the thermal response threshold Hth, it indicates that the thermal response of the current target area is unqualified, and there is a risk of insufficient local temperature rise or insufficient thermal coupling. This triggers a second warning instruction and generates a second strategy: automatically extend the microwave irradiation time by 30% and increase the microwave output power ratio by 15%; adjust the beam pointing angle and irradiation frequency to improve the uniformity of energy distribution; recalculate HRC after the correction. If the result is still less than Hth after two consecutive corrections, it is recorded as a "continuously insufficient response area". The system performs pulse energy compensation to enhance local heat accumulation and prevent overheating.

[0034] Preferably, step four includes:

[0035] S41. The target area tissue resonance response coefficient ORC and the target area thermal response coupling coefficient HRC are obtained by calculation. Combined with the blood flow rate change rate Qss and the baseline blood flow rate Qref, after dimensionless processing, the microcirculation improvement index MCI of the target area is calculated.

[0036] Preferably, step four further includes:

[0037] S42. By setting a microcirculation improvement threshold Mth, and comparing the microcirculation improvement index MCI of the target area with the microcirculation improvement threshold Mth, the third evaluation results are obtained, including:

[0038] When the microcirculation improvement index MCI of the target area is greater than or equal to the microcirculation improvement threshold Mth, it indicates that the current microcirculation improvement effect in the area is qualified. The system maintains the current energy output parameters and beam control strategy and continues to monitor.

[0039] When the Microcirculation Improvement Index (MCI) of the target area is less than the Microcirculation Improvement Threshold (Mth), it indicates that the current microcirculation improvement effect in the area is unqualified, and there is a risk of insufficient local blood perfusion or uneven energy distribution. This triggers the third warning instruction and generates the third strategy: automatically extending the energy application time by 20% and increasing the output power by 10%; adjusting the resonant frequency micro-shift to optimize tissue energy coupling; and initiating a local energy dynamic rematching process, which feeds back to step two to perform resonance optimization and recalculate the MCI. If the results are still lower than Mth after two consecutive attempts, it is marked as a "microcirculation response insufficiency area," and the system performs periodic pulse intervention to enhance the local blood flow improvement effect.

[0040] Preferably, step five includes:

[0041] S51. Construct an initial energy control convolutional neural network model using a convolutional neural network (CNN). Train and test the initial convolutional neural network model using the target region tissue resonance response coefficient (ORC), the target region thermal response coupling coefficient (HRC), and the target region microcirculation improvement index (MCI), combined with the local tissue water content (hsl) and tissue thickness (zzh), to obtain the trained convolutional neural network model, which serves as the AI ​​dynamic energy adjustment model.

[0042] S52. The input data is processed through the intermediate layer of the convolutional neural network to extract feature vectors, which are used to identify the energy absorption characteristics and physiological response characteristics under different tissue types. Through the obtained feature information, the AI ​​dynamic energy adjustment model is trained and validated to optimize the model's ability to identify nonlinear coupling characteristics and its prediction accuracy, thereby forming a stable dynamic energy mapping relationship.

[0043] S53. Based on the predicted output of the AI ​​model and the accumulation of historical data, the feature weights and inter-layer connection parameters of the convolutional neural network are continuously updated to realize online learning and dynamic optimization of the energy regulation model. This enables the system to achieve the overall optimal match of energy transfer efficiency, temperature uniformity and microcirculation improvement effect for different individuals, different tissue characteristics and environmental conditions.

[0044] Preferably, a microwave irradiation area matching system includes:

[0045] The multimodal physiological parameter acquisition and reconstruction module is used to establish a controllable microwave radiation field within the intelligent resonant cavity. Combined with a multimodal acquisition device, it acquires key parameters in real time, including reflection and transmission power, surface and deep temperature distribution, blood flow changes, tissue water content, and thickness of the target area. After multi-source signal synchronization, filtering, and fusion processing, the module reconstructs the three-dimensional temperature field and tissue dielectric properties using thermal conduction inversion and electromagnetic inversion algorithms, constructing a comprehensive physiological response parameter set for the target area. It also measures a reference dataset.

[0046] The electromagnetic response resonance feature analysis module is used to extract the real and imaginary parts of the complex permittivity of the target region using a complex permittivity spectrum fitting algorithm, and combined with the electromagnetic response curve, to obtain the stress distribution characteristics inside the tissue using a stress-electromagnetic coupling inversion algorithm; the tissue resonance response coefficient ORC is calculated and compared with the tissue resonance response threshold Oth to determine whether the target region has reached the microwave resonance absorption state. If it has, the thermal effect analysis process is initiated; if it has not, an appropriate strategy is provided.

[0047] The thermal effect feature coupling judgment module is used to perform time series smoothing and Gaussian spatial filtering on three-dimensional temperature field data, extract the temperature change rate and temperature spatial gradient, construct the temperature dynamic feature curve of the target area, calculate the thermal response coupling coefficient HRC, and compare it with the thermal response threshold Hth to determine whether the thermal response of the current target area is qualified. If it is not qualified, an appropriate strategy is given.

[0048] The microcirculation improvement assessment module is used to calculate the microcirculation improvement index (MCI) of the target area by acquiring the target area tissue resonance response coefficient (ORC) and the target area thermal response coupling coefficient (HRC), combined with the blood flow rate change rate and reference data, and compare it with the microcirculation improvement threshold (Mth) to determine whether the current microcirculation improvement effect in the area is qualified. If it is not qualified, corresponding strategies are given.

[0049] The adaptive energy regulation optimization module is used to construct an AI dynamic energy adjustment model using a convolutional neural network. It takes tissue resonance response, thermal response and microcirculation improvement parameters as training inputs, extracts energy absorption and physiological response features, and achieves adaptive updating and dynamic optimization of the energy regulation model through multiple rounds of training and online optimization. This enables the optimal matching of energy transfer efficiency and microcirculation improvement effect under different individual and tissue conditions.

[0050] This invention provides a method and system for matching microwave irradiation areas. It has the following beneficial effects:

[0051] (1) The microwave irradiation area matching method and system integrates multi-source signals such as reflected power, transmitted power, temperature distribution, blood flow changes, tissue water content and thickness by setting up a multi-modal physiological parameter acquisition and reconstruction module. Combined with thermal conduction inversion and electromagnetic inversion algorithms, it can realize high-precision reconstruction of the three-dimensional temperature field and tissue dielectric properties of the target area, greatly improve the matching accuracy and individualized analysis capability of the microwave irradiation area, and avoid energy distribution deviation caused by single sensor information.

[0052] (2) The microwave irradiation area matching method and system, through the collaborative calculation of the electromagnetic response resonance feature analysis module and the thermal effect feature coupling judgment module, can calculate the tissue resonance response coefficient ORC and the thermal response coupling coefficient HRC respectively, and adaptively adjust the output power, frequency and beam direction based on the threshold to achieve accurate matching of dielectric properties and thermal conductivity of different tissues, effectively prevent the problem of excessive local energy accumulation and insufficient heating, and improve energy utilization efficiency and tissue safety.

[0053] (3) This microwave irradiation area matching method and system, through the introduction of a microcirculation improvement assessment module, couples and analyzes tissue resonance response, thermal response, and blood flow rate change to calculate the microcirculation improvement index (MCI) and form a closed-loop control judgment mechanism. This design can assess local blood perfusion and energy absorption status in real time, trigger strategy adjustment and dynamic rematching in a timely manner, significantly improve the controllability and stability of microcirculation improvement effect, and enhance the physiological recovery efficiency of the treatment area.

[0054] (4) The microwave irradiation area matching method and system constructs a convolutional neural network AI model through an adaptive energy regulation optimization module. The system can realize online learning and dynamic optimization of energy regulation parameters based on historical training data and real-time feature information, so that energy transfer efficiency, temperature uniformity and microcirculation improvement effect automatically tend to the optimal state under different individual and tissue conditions, significantly improving the system's adaptability and intelligence level, and reducing the need for manual intervention. Attached Figure Description

[0055] Figure 1 This is a schematic diagram of the steps of a microwave irradiation area matching method according to the present invention;

[0056] Figure 2 This is a block diagram flowchart of a microwave irradiation area matching system according to the present invention. Detailed Implementation

[0057] 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 some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0058] Example 1

[0059] Please see Figure 1 This invention provides a microwave irradiation area matching method, comprising the following steps:

[0060] Step 1: By establishing a controllable microwave radiation field within the intelligent resonant cavity and combining it with a multi-modal acquisition device, key parameters such as reflection and transmission power, surface and deep temperature distribution, blood flow changes, tissue water content, and thickness of the target area are acquired in real time. After multi-source signal synchronization, filtering, and fusion processing, the three-dimensional temperature field and tissue dielectric properties are reconstructed using thermal conduction inversion and electromagnetic inversion algorithms to construct a comprehensive physiological response parameter set for the target area. A reference dataset is also measured.

[0061] Step 2: Extract the real and imaginary parts of the complex permittivity of the target region using a complex permittivity spectroscopy fitting algorithm. Combine this with the electromagnetic response curve and use a stress-electromagnetic coupling inversion algorithm to obtain the stress distribution characteristics inside the tissue. Calculate the tissue resonance response coefficient ORC and compare it with the tissue resonance response threshold Oth to determine whether the target region has reached the microwave resonance absorption state. If it has, proceed to the thermal effect analysis process; otherwise, provide appropriate strategies.

[0062] Step 3: By performing time series smoothing and Gaussian spatial filtering on the three-dimensional temperature field data, extract the temperature change rate and temperature spatial gradient, and construct the temperature dynamic characteristic curve of the target area; calculate the thermal response coupling coefficient HRC, and compare it with the thermal response threshold Hth to determine whether the thermal response of the current target area is qualified. If it is not qualified, an appropriate strategy is given.

[0063] Step 4: By obtaining the target area tissue resonance response coefficient ORC and the target area thermal response coupling coefficient HRC, combined with the blood flow rate change rate and reference data, calculate the target area microcirculation improvement index MCI, and compare it with the microcirculation improvement threshold Mth to determine whether the current microcirculation improvement effect in the area is qualified. If it is not qualified, give corresponding strategies.

[0064] Step 5: Construct an AI dynamic energy adjustment model using a convolutional neural network. With tissue resonance response, thermal response, and microcirculation improvement parameters as training inputs, extract energy absorption and physiological response features. Through multiple rounds of training and online optimization, achieve adaptive updating and dynamic optimization of the energy regulation model, thereby achieving the optimal match between energy transfer efficiency and microcirculation improvement effect under different individual and tissue conditions.

[0065] In this embodiment, by constructing an AI dynamic energy adjustment model based on a convolutional neural network, the parameters of tissue resonance response, thermal response, and microcirculation improvement are jointly modeled and adaptively optimized to achieve dynamic matching and real-time control of microwave irradiation energy under different individual and tissue conditions. This enables the energy transfer efficiency, temperature distribution uniformity, and microcirculation improvement effect to reach the optimal simultaneously, significantly improving the safety, individualized adaptability, and therapeutic effectiveness of the microwave irradiation process.

[0066] Example 2

[0067] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1 Specifically, step one includes:

[0068] S11. Real-time monitoring of microwave irradiation scenarios for rehabilitation therapy, pain theory, inflammation repair, and circulation improvement; setting an intelligent resonant cavity in the main cavity of the treatment machine to form a controllable microwave radiation field; deploying an embedded microwave detection array on the outer edge of the irradiation head to detect changes in reflected and transmitted power in real time; deploying multimodal temperature sensing components on the surface and surrounding area of ​​the irradiation target area to monitor local temperature distribution and dynamic changes.

[0069] S12. A frequency-tunable microwave signal is output through the resonant cavity driving device to scan and irradiate the target area; the microwave detection array synchronously acquires the signals of reflected power Pr and transmitted power Pt; the acquired raw signals are processed by time synchronization and noise filtering, normalization correction and spectrum decomposition, and the electromagnetic response curves and preliminary reflected and transmitted power spectrum data of each position are obtained after processing.

[0070] S13. By deploying infrared thermal imaging modules, embedded miniature thermocouple arrays, and fiber Bragg grating temperature sensors around the resonant cavity outlet, above the irradiation area, and at the lateral boundaries, the real-time temperature T of the target area's surface and at different depths is acquired. The multi-source temperature signals are then processed through time synchronization, noise filtering, and spatial interpolation fusion. A three-dimensional temperature field distribution of the target area is established using a finite-difference heat conduction inversion algorithm or Kriging interpolation reconstruction technique. ;

[0071] S14. Deploy photoplethysmography (PPG) sensors and infrared thermal imaging equipment in the target irradiation area to simultaneously collect dynamic blood flow parameters and obtain the blood flow rate of change Qss. Acquire the surface temperature distribution map of the target area using the infrared thermal imaging module. Combine this with an infrared reflectivity and absorptivity model to invert and obtain the local tissue water content hsl. Simultaneously, utilize a low-intensity microwave dielectric parameter testing module to emit probe waves at different measuring points and measure the reflection coefficient and phase difference. Calculate the tissue dielectric constant based on an electromagnetic inversion algorithm to obtain the tissue thickness zzh. Combine the blood flow rate of change, tissue thickness, and water content to form a local physiological response parameter set. Determine the baseline temperature Tbase, reference physiological temperature Tref, baseline blood flow Qref, and reference standard stress based on the measurement data under steady-state conditions. Establish a reference dataset.

[0072] In this embodiment, by constructing a multimodal physiological parameter acquisition system within the irradiation area and integrating multi-source data from microwave reflection and transmission signals, infrared thermal imaging, thermocouple arrays, and fiber Bragg sensors, the system can simultaneously acquire temperature distribution, blood flow changes, and water content characteristics of the target tissue in both space and time. This enables high-precision reconstruction of the electromagnetic response and thermodynamic behavior of local tissues. This design effectively improves the real-time monitoring accuracy and spatial resolution during microwave irradiation, providing a complete and reliable input data foundation for subsequent energy regulation models, thereby significantly enhancing the system's adaptability and individualized energy regulation capabilities.

[0073] Example 3

[0074] This embodiment is an explanation based on Embodiment 2. Please refer to it. Figure 1 Specifically, step two includes:

[0075] S21. Based on the reflection and transmission power spectrum data, a complex dielectric spectrum fitting algorithm is used to obtain the dielectric property parameters of the target region at different frequency bands, and the real part dcs and imaginary part dcx of the complex dielectric constant are extracted; based on the electromagnetic response curve, a stress-electromagnetic coupling inversion algorithm is used to fit the power distribution gradient to obtain the standard deviation of the stress distribution inside the target region. .

[0076] In this embodiment, by introducing a complex dielectric spectrum fitting algorithm and a stress-electromagnetic coupling inversion model, the real and imaginary parts of the complex dielectric constant of the target tissue can be accurately extracted at different frequency bands, and the internal stress distribution characteristics can be obtained simultaneously through inversion, realizing a joint quantitative analysis of the tissue's dielectric properties and mechanical state. This method can effectively reveal the energy absorption characteristics and stress response laws of tissues under microwave irradiation, providing highly reliable physical parameter support for subsequent energy control and tissue safety assessment.

[0077] Example 4

[0078] This embodiment is an explanation based on Embodiment 3. Please refer to it. Figure 1 Specifically, step two also includes:

[0079] S22. By combining the reflected power Pr and the transmitted power Pt, the real part dcs and the imaginary part dcx of the complex permittivity, and the standard deviation of the stress distribution within the target region. and reference standard stress After dimensionless processing, the resonance response coefficient (ORC) of the target region tissue is calculated using the following formula:

[0080]

[0081] In the formula, w1, w2, and w3 represent weighting coefficients;

[0082] Formula principle: Ratio of reflected power to transmitted power This item describes the energy distribution and loss characteristics of microwaves during propagation in tissues. When the tissue is in a resonant absorption state, the transmitted power Pt decreases significantly, while the reflected power Pr shows a peak change in a specific frequency band. Therefore, this ratio can sensitively reflect the degree of absorption and matching of incident energy by the tissue.

[0083] Complex permittivity ratio The real part of the complex permittivity, dcs, represents the energy storage capacity of the medium, while the imaginary part, dcx, represents the energy loss capacity of the medium. The ratio of the two reflects the absorption and dissipation characteristics of electromagnetic energy by the tissue. When the tissue approaches the resonant frequency band, the imaginary part increases and the ratio decreases, indicating that the energy absorption is significantly enhanced. Therefore, this term is used to characterize the electromagnetic resonance characteristics of the tissue.

[0084] Stress ratio This item reflects the relative change between the internal stress state and structural stability of the tissue; microwave irradiation may cause thermal stress changes in the microstructure of the tissue, and the standard deviation of stress distribution. Relative to reference stress An increase in ...

[0085] The ratio of reflected power to transmitted power characterizes the influence of tissue resonance response and has a major weight. It is used to reflect the absorption efficiency and energy matching degree of tissue to incident microwave energy and is a key indicator for judging the resonance absorption state.

[0086] The ratio of the real to imaginary part of the complex permittivity represents the influence of the tissue's resonant response. It has a moderate weight and is used to reflect the dielectric polarization and energy loss characteristics of the tissue at different frequencies. It has a decisive influence on the electromagnetic absorption capacity.

[0087] : Characterizes the influence of the ratio of the standard deviation of internal stress distribution to the reference stress on the tissue resonance response, and has an auxiliary weight. It is used to reflect the coupling effect of stress changes in the tissue structure on dielectric properties and energy absorption uniformity, and is an important supplementary indicator of microstructure stability.

[0088] This formula is based on a triple mechanism of energy transfer, dielectric properties, and stress coupling. It can calculate the comprehensive response level of a tissue to microwave energy by characterizing parameters without directly measuring the field strength inside the tissue, providing a quantitative basis for subsequent thermal effect analysis and energy regulation.

[0089] S23. By setting a preset tissue resonance response threshold Oth, and comparing the target region tissue resonance response coefficient ORC with the tissue resonance response threshold Oth, the first evaluation results are obtained, including:

[0090] When the target region tissue resonance response coefficient ORC ≥ tissue resonance response threshold Oth, it indicates that the target region has reached the microwave resonance absorption state and enters the thermal effect analysis process.

[0091] When the target region's tissue resonance response coefficient ORC is less than the tissue resonance response threshold Oth, it indicates that the target region has not reached the microwave resonance absorption state, triggering the first warning command and generating the first strategy: Adaptively fine-tuning the center frequency of the current frequency band using a resonant cavity frequency tuning device to improve local matching; adjusting the microwave waveform envelope and pulse width parameters to optimize energy distribution uniformity; real-time correction of the output power amplitude based on the reflection power Pr change trend of the previous cycle; rescanning once after correction and recalculating the target region's tissue resonance response coefficient ORC; if it still has not reached the tissue resonance response threshold Oth, then recording the current region as an energy coupling difficulty zone, the system automatically switches to low-power monitoring, extending the integration time to accumulate data and prevent local overheating.

[0092] The tissue resonance response threshold Oth was obtained by statistically analyzing the electromagnetic response characteristics of different tissue types under multi-band microwave irradiation. By collecting a large amount of data on reflected power, transmitted power, and complex permittivity parameters from surface and deep tissues in both non-resonant absorption and critical resonant absorption states, the distribution range of the resonance response coefficient ORC was extracted. Combined with bioelectromagnetic compatibility experimental data and expert judgment, a reasonable critical threshold was determined. Referring to medical electromagnetic radiation safety standards and tissue energy absorption ratio (SAR) specifications, a tissue resonance response threshold Oth was ultimately established to distinguish between non-resonant and resonant absorption states, ensuring the safety and effectiveness of energy regulation processes.

[0093] In this embodiment, by constructing the tissue resonance response coefficient ORC and dynamically comparing it with the preset threshold Oth, it is possible to accurately determine whether the target tissue has entered the microwave resonance absorption state. Combined with feedback control mechanisms such as adaptive frequency fine-tuning, waveform envelope optimization and power amplitude correction, the system can achieve adaptive improvement of energy matching degree under different tissue dielectric properties and stress states, significantly improve the efficiency and uniformity of microwave irradiation, avoid the risk of local energy overload or thermal damage, and enhance the safety and stability of the system.

[0094] Example 5

[0095] This embodiment is an explanation based on Embodiment 4. Please refer to it. Figure 1 Specifically, step three includes:

[0096] S31. Three-dimensional temperature field distribution based on the target region By employing time series smoothing and Gaussian spatial filtering algorithms, spatiotemporal denoising and local anomaly suppression processing are performed on the raw temperature of the three-dimensional temperature field distribution data of the target region, and the temperature change rate is extracted. and temperature spatial gradient The average temperature rise rate and thermal diffusion trend were calculated to establish the temperature dynamic characteristic curve of the target area.

[0097] In this embodiment, by introducing a time series smoothing algorithm and a Gaussian spatial filtering algorithm into the three-dimensional temperature field distribution of the target area, spatiotemporal denoising and local anomaly suppression of temperature data are achieved. This effectively eliminates the influence of environmental disturbances and measurement noise on the heat distribution results, ensuring that the extraction of temperature change rate and spatial gradient is more accurate and stable. This results in obtaining a temperature dynamic characteristic curve that reflects the real heat conduction process, providing a highly reliable data foundation for subsequent thermal response analysis and energy control.

[0098] Example 6

[0099] This embodiment is an explanation based on Embodiment 5. Please refer to it. Figure 1 Specifically, step three also includes:

[0100] S32, by acquiring the real-time temperature T and the rate of temperature change and temperature spatial gradient By combining the baseline temperature Tbase and the reference physiological temperature Tref, and after dimensionless processing, the thermal response coupling coefficient HRC of the target region is calculated as follows:

[0101]

[0102] In the formula, w4, w5, and w6 represent weighting coefficients;

[0103] Formula principle: Temperature change rate term This value is used to characterize the rate at which a tissue heats up during irradiation, reflecting the energy absorption rate and the tissue's thermal sensitivity. When energy coupling is sufficient, this value is larger, indicating that the heat conduction process is efficient.

[0104] Temperature space gradient term It is used to reflect the uniformity of temperature distribution and heat diffusion capacity within a tissue; when the tissue has good thermal conductivity, the gradient is smoother, indicating fewer local hot spots and more uniform heat conduction.

[0105] Temperature difference item This describes the relative increase in the current temperature of an organism compared to the baseline and reference temperature, and is an important indicator for measuring the heat accumulation effect.

[0106] Characterizing the rate of temperature change The influence on the degree of thermal response coupling has a high weight and is the main indicator, reflecting the tissue's sensitivity to instantaneous temperature rise from microwave irradiation.

[0107] Characterizing the spatial temperature gradient The influence on the degree of thermal response coupling has the second highest weight, reflecting the uniformity of thermal diffusion and thermal conduction efficiency within the tissue;

[0108] : Characterizes the difference between actual temperature and baseline / reference temperature The influence on the degree of coupling of thermal response accounts for an auxiliary weight, reflecting the contribution of the overall temperature rise of the tissue to the thermal equilibrium state;

[0109] This formula is based on the theory of thermal conduction dynamics and energy diffusion. By weighted integration of three temperature characteristic quantities, it achieves a comprehensive quantification of the tissue thermal response state, which is used to judge the sufficiency and safety of local thermal effects and provide a basis for subsequent energy control strategies.

[0110] S33. By setting a preset thermal response threshold Hth, and comparing and analyzing the thermal response coupling coefficient HRC of the target area with the thermal response threshold Hth, the second evaluation results are obtained, including:

[0111] When the thermal response coupling coefficient HRC of the target area is greater than or equal to the thermal response threshold Hth, it indicates that the thermal response of the current target area is qualified. Maintain the current energy output and beam control status and continue to monitor.

[0112] When the thermal response coupling coefficient HRC of the target area is less than the thermal response threshold Hth, it indicates that the thermal response of the current target area is unqualified, and there is a risk of insufficient local temperature rise or insufficient thermal coupling. This triggers a second warning instruction and generates a second strategy: automatically extend the microwave irradiation time by 30% and increase the microwave output power ratio by 15%; adjust the beam pointing angle and irradiation frequency to improve the uniformity of energy distribution; recalculate HRC after the correction. If the result is still less than Hth after two consecutive corrections, it is recorded as a "continuously insufficient response area". The system performs pulse energy compensation to enhance local heat accumulation and prevent overheating.

[0113] The thermal response threshold Hth is obtained through experimental and simulation analysis of temperature field distribution in various physiological tissues under different microwave power densities and irradiation times. By collecting the rate of temperature change and spatial temperature gradient under thermal equilibrium and critical heat accumulation states, the variation range of the thermal response coupling coefficient HRC is statistically analyzed. Combined with tissue heat conduction models and physiological heat tolerance limits, a reasonable critical threshold is determined. Referring to human thermal safety standards (IEC 60601 series) and tissue thermal damage criteria (Arrhenius model), a thermal response threshold Hth that effectively distinguishes between normal heating and overheating risk is formed, serving as a safety limit for controlling the thermal effect process.

[0114] In this embodiment, by introducing a calculation model for the thermal response coupling coefficient HRC and combining it with multidimensional thermal parameters such as real-time temperature, temperature change rate, and spatial gradient for dimensionless processing, a comprehensive quantitative evaluation of the thermal conduction characteristics and temperature rise efficiency of the target area is achieved. At the same time, based on the dynamic comparison between HRC and the thermal response threshold Hth, areas with insufficient local thermal response or uneven thermal coupling can be accurately identified, thereby enabling intelligent correction of microwave output power, irradiation time, and beam distribution, effectively improving energy utilization and tissue temperature rise uniformity, and ensuring the safety and stability of the heating process.

[0115] Example 7

[0116] This embodiment is an explanation based on Embodiment 6. Please refer to it. Figure 1 Specifically, step four includes:

[0117] S41. By calculating the target area tissue resonance response coefficient ORC and the target area thermal response coupling coefficient HRC, and combining the blood flow rate change rate Qss and baseline blood flow Qref, after dimensionless processing, the microcirculation improvement index MCI of the target area is calculated as follows:

[0118]

[0119] In the formula, a1, a2 and a3 represent weighting coefficients.

[0120] Formula principle: Tissue resonance response term ORC: reflects the degree of matching between microwave and tissue dielectric properties; when the tissue is in a good resonance state, energy absorption is more sufficient, promoting the increase of local tissue temperature and metabolic level;

[0121] Thermal response coupling term HRC: characterizes the tissue's thermal diffusion efficiency and temperature uniformity; moderate thermal response contributes to capillary dilation and improved blood flow;

[0122] Blood flow ratio It is used to quantify the increase in current blood flow relative to the baseline state and is a direct indicator reflecting the degree of microcirculation activation.

[0123] The ORC (Organic Resonance Response Coefficient) characterizes the influence of tissue resonance response coefficient on the microcirculation improvement index. It has a high weight and is a key factor, reflecting the dominant contribution of tissue energy absorption and structural matching degree to blood flow regulation under electromagnetic influence.

[0124] The coefficient HRC, which characterizes the effect of thermal response coupling coefficient on the microcirculation improvement index, has a medium to high weight, reflecting the promoting effect of local temperature change rate and thermal diffusion effect on improving microcirculation activity.

[0125] : Ratio representing the rate of change of blood flow The impact on the microcirculation improvement index has a relatively low weight, reflecting the combined effect of hemodynamic changes on local tissue nutrient exchange and circulatory efficiency improvement.

[0126] This formula is based on a triple physiological linkage mechanism of energy coupling, heat conduction, and blood flow regulation. By integrating electromagnetic, thermal, and fluid physiological parameters, it achieves quantitative characterization of the microcirculation improvement effect, providing a precise basis for individualized energy output and dynamic feedback control.

[0127] In this embodiment, the target region tissue resonance response coefficient (ORC), thermal response coupling coefficient (HRC), and blood flow rate change ratio are introduced. The Microcirculation Improvement Index (MCI) was constructed to achieve a comprehensive quantitative assessment of the electromagnetic resonance absorption, thermal diffusion, and hemodynamic coupling effects in local tissues. This index can reflect the degree of microcirculation improvement and energy regulation effects without relying on invasive measurements, providing a scientific basis for optimizing the multi-field coupling of heat, flow, and physiology in the tissue repair process, and significantly improving the accuracy and physiological relevance of the assessment.

[0128] Example 8

[0129] This embodiment is an explanation based on Embodiment 7. Please refer to it. Figure 1 Specifically, step four also includes:

[0130] S42. By setting a microcirculation improvement threshold Mth, and comparing the microcirculation improvement index MCI of the target area with the microcirculation improvement threshold Mth, the third evaluation results are obtained, including:

[0131] When the microcirculation improvement index MCI of the target area is greater than or equal to the microcirculation improvement threshold Mth, it indicates that the current microcirculation improvement effect in the area is qualified. The system maintains the current energy output parameters and beam control strategy and continues to monitor.

[0132] When the Microcirculation Improvement Index (MCI) of the target area is less than the Microcirculation Improvement Threshold (Mth), it indicates that the current microcirculation improvement effect in the area is unqualified, and there is a risk of insufficient local blood perfusion or uneven energy distribution. This triggers the third warning instruction and generates the third strategy: automatically extending the energy application time by 20% and increasing the output power by 10%; adjusting the resonant frequency micro-shift to optimize tissue energy coupling; and initiating a local energy dynamic rematching process, which feeds back to step two to perform resonance optimization and recalculate the MCI. If the results are still lower than Mth after two consecutive attempts, it is marked as a "microcirculation response insufficiency area," and the system performs periodic pulse intervention to enhance the local blood flow improvement effect.

[0133] The microcirculation improvement threshold Mth was obtained by analyzing long-term monitoring data on changes in local blood flow, blood oxygen saturation, and tissue temperature under different individuals and irradiation intensities. By comparing the statistical distribution of the microcirculation improvement index (MCI) before and after treatment, the critical threshold between significant improvement and no significant change was extracted. Combined with tissue perfusion kinetics models and clinical rehabilitation experimental results, a reasonable microcirculation improvement threshold Mth was determined. Referring to relevant industry standards in rehabilitation physiotherapy and bio-thermal therapy, a criterion was established to distinguish between effective microcirculation promotion and insufficient response states, guiding adaptive optimization and individualized control of energy parameters.

[0134] In this embodiment, by setting a microcirculation improvement threshold Mth and dynamically comparing and analyzing the microcirculation improvement index MCI, the present invention can achieve real-time determination and adaptive control of the local blood perfusion status of the target tissue: when the detection result is lower than the threshold, the system can automatically extend the energy application time, increase the output power, and perform resonant frequency micro-shift and energy rematching, thereby accurately compensating for the problem of uneven local energy distribution; this mechanism significantly improves the targeting of energy application and the sustainability of tissue microcirculation improvement, avoids overheating or underheating, and ensures the safety and physiological benefits of the treatment process.

[0135] Example 9

[0136] This embodiment is an explanation based on Embodiment 8. Please refer to it. Figure 1 Specifically, step five includes:

[0137] S51. Construct an initial energy control convolutional neural network model using a convolutional neural network (CNN). Train and test the initial convolutional neural network model using the target region tissue resonance response coefficient (ORC), the target region thermal response coupling coefficient (HRC), and the target region microcirculation improvement index (MCI), combined with the local tissue water content (hsl) and tissue thickness (zzh), to obtain the trained convolutional neural network model, which serves as the AI ​​dynamic energy adjustment model.

[0138] S52. The input data is processed through the intermediate layer of the convolutional neural network to extract feature vectors, which are used to identify the energy absorption characteristics and physiological response characteristics under different tissue types. Through the obtained feature information, the AI ​​dynamic energy adjustment model is trained and validated to optimize the model's ability to identify nonlinear coupling characteristics and its prediction accuracy, thereby forming a stable dynamic energy mapping relationship.

[0139] S53. Based on the predicted output of the AI ​​model and the accumulation of historical data, the feature weights and inter-layer connection parameters of the convolutional neural network are continuously updated to realize online learning and dynamic optimization of the energy regulation model. This enables the system to achieve the overall optimal match of energy transfer efficiency, temperature uniformity and microcirculation improvement effect for different individuals, different tissue characteristics and environmental conditions.

[0140] In this embodiment, by introducing an AI dynamic energy adjustment model based on convolutional neural networks, the present invention can achieve adaptive learning and optimization of the energy transfer process in the target area: the model combines multiple physiological characteristics such as tissue resonance response, thermal response coupling and microcirculation improvement, automatically extracts energy absorption and physiological response characteristics and continuously updates weight parameters, thereby achieving dynamic energy regulation under different individual and tissue conditions; this mechanism effectively improves energy transfer efficiency, temperature uniformity and microcirculation improvement effect, and significantly enhances the accuracy, personalization and safety of treatment.

[0141] Example 10

[0142] A microwave irradiation area matching system, please refer to Figure 2 Specifically, including:

[0143] The multimodal physiological parameter acquisition and reconstruction module is used to establish a controllable microwave radiation field within the intelligent resonant cavity. Combined with a multimodal acquisition device, it acquires key parameters in real time, including reflection and transmission power, surface and deep temperature distribution, blood flow changes, tissue water content, and thickness of the target area. After multi-source signal synchronization, filtering, and fusion processing, the module reconstructs the three-dimensional temperature field and tissue dielectric properties using thermal conduction inversion and electromagnetic inversion algorithms, constructing a comprehensive physiological response parameter set for the target area. It also measures a reference dataset.

[0144] The electromagnetic response resonance feature analysis module is used to extract the real and imaginary parts of the complex permittivity of the target region using a complex permittivity spectrum fitting algorithm, and combined with the electromagnetic response curve, to obtain the stress distribution characteristics inside the tissue using a stress-electromagnetic coupling inversion algorithm; the tissue resonance response coefficient ORC is calculated and compared with the tissue resonance response threshold Oth to determine whether the target region has reached the microwave resonance absorption state. If it has, the thermal effect analysis process is initiated; if it has not, an appropriate strategy is provided.

[0145] The thermal effect feature coupling judgment module is used to perform time series smoothing and Gaussian spatial filtering on three-dimensional temperature field data, extract the temperature change rate and temperature spatial gradient, construct the temperature dynamic feature curve of the target area, calculate the thermal response coupling coefficient HRC, and compare it with the thermal response threshold Hth to determine whether the thermal response of the current target area is qualified. If it is not qualified, an appropriate strategy is given.

[0146] The microcirculation improvement assessment module is used to calculate the microcirculation improvement index (MCI) of the target area by acquiring the target area tissue resonance response coefficient (ORC) and the target area thermal response coupling coefficient (HRC), combined with the blood flow rate change rate and reference data, and compare it with the microcirculation improvement threshold (Mth) to determine whether the current microcirculation improvement effect in the area is qualified. If it is not qualified, corresponding strategies are given.

[0147] The adaptive energy regulation optimization module is used to construct an AI dynamic energy adjustment model using a convolutional neural network. It takes tissue resonance response, thermal response and microcirculation improvement parameters as training inputs, extracts energy absorption and physiological response features, and achieves adaptive updating and dynamic optimization of the energy regulation model through multiple rounds of training and online optimization. This enables the optimal matching of energy transfer efficiency and microcirculation improvement effect under different individual and tissue conditions.

[0148] In this embodiment, a closed-loop adaptive energy regulation system is formed by constructing five functional modules: multimodal physiological parameter acquisition and reconstruction, electromagnetic response resonance feature analysis, thermal effect feature coupling determination, microcirculation improvement assessment, and adaptive energy regulation optimization. This system can acquire and fuse multi-source physiological parameters in real time, accurately determine tissue resonance and thermal response characteristics, evaluate the microcirculation improvement effect, and optimize energy output based on an AI dynamic regulation model to achieve precise delivery and dynamic matching of microwave energy, thereby significantly improving treatment efficiency, safety, and personalized adaptability.

[0149] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by those skilled in the art for each set of sample data; as long as it does not affect the ratio between the parameter and the quantized value, it is acceptable.

[0150] The above formulas are all derived from software simulation using a large amount of data, and are selected to be close to the actual values. The coefficients in the formulas are set by those skilled in the art based on the actual situation. The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or changes made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A microwave irradiation area matching system, characterized in that, include: The multimodal physiological parameter acquisition and reconstruction module is used to establish a controllable microwave radiation field in the intelligent resonant cavity. Combined with the multimodal acquisition device, it can acquire key parameters such as reflection and transmission power, surface and deep temperature distribution, blood flow changes, tissue water content and thickness in the target area in real time. After multi-source signal synchronization, filtering and fusion processing, the three-dimensional temperature field and tissue dielectric properties are reconstructed using thermal conduction inversion and electromagnetic inversion algorithms to build a comprehensive physiological response parameter set for the target region; and a reference dataset is measured. The electromagnetic response resonance feature analysis module is used to extract the real and imaginary parts of the complex permittivity of the target region using a complex permittivity spectrum fitting algorithm, and combined with the electromagnetic response curve, to obtain the stress distribution characteristics inside the tissue using a stress-electromagnetic coupling inversion algorithm. The tissue resonance response coefficient ORC was calculated and compared with the tissue resonance response threshold Oth to determine whether the target area has reached the microwave resonance absorption state. If it has, the thermal effect analysis process begins; otherwise, an appropriate strategy is adopted. The analysis also considers the reflected power Pr and transmitted power Pt, the real part dcs and imaginary part dcx of the complex permittivity, and the standard deviation of the stress distribution within the target area. and reference standard stress After dimensionless processing, the resonance response coefficient (ORC) of the target region tissue is calculated using the following formula: In the formula, w1, w2, and w3 represent weighting coefficients; The thermal effect feature coupling judgment module is used to perform time series smoothing and Gaussian spatial filtering on three-dimensional temperature field data, extract the temperature change rate and temperature spatial gradient, construct the temperature dynamic feature curve of the target area, calculate the thermal response coupling coefficient HRC, and compare it with the thermal response threshold Hth to determine whether the thermal response of the current target area is qualified. If it is not qualified, an appropriate strategy is given. By obtaining real-time temperature T and temperature change rate and temperature spatial gradient By combining the baseline temperature Tbase and the reference physiological temperature Tref, and after dimensionless processing, the thermal response coupling coefficient HRC of the target region is calculated as follows: In the formula, w4, w5, and w6 represent weighting coefficients; The microcirculation improvement assessment module is used to calculate the microcirculation improvement index (MCI) of the target area by acquiring the target area tissue resonance response coefficient (ORC) and the target area thermal response coupling coefficient (HRC), combined with the blood flow rate change rate and reference data, and compare it with the microcirculation improvement threshold (Mth) to determine whether the current microcirculation improvement effect in the area is qualified. If it is not qualified, corresponding strategies are given. By calculating the target area tissue resonance response coefficient (ORC) and the target area thermal response coupling coefficient (HRC), and combining the blood flow rate change rate (Qss) and baseline blood flow rate (Qref), after dimensionless processing, the microcirculation improvement index (MCI) of the target area is calculated as follows: In the formula, a1, a2, and a3 represent weighting coefficients; The adaptive energy regulation optimization module is used to construct an AI dynamic energy adjustment model using a convolutional neural network. It uses the tissue resonance response coefficient ORC, thermal response coupling coefficient HRC, and thermal response coupling coefficient HRC as training inputs to extract energy absorption and physiological response features. Through multiple rounds of training and online optimization, it realizes the adaptive updating and dynamic optimization of the energy regulation model, thereby achieving the optimal match between energy transfer efficiency and microcirculation improvement effect under different individual and tissue conditions.

2. The microwave irradiation area matching system according to claim 1, characterized in that, The multimodal physiological parameter acquisition and reconstruction module is used to perform the following steps: Real-time monitoring of microwave irradiation scenarios for rehabilitation therapy, pain theory, inflammation repair, and circulation improvement; and the formation of a controllable microwave radiation field by setting an intelligent resonant cavity in the main cavity of the treatment machine. An embedded microwave detection array is deployed on the outer edge of the irradiation head to detect changes in reflected and transmitted power in real time; multimodal temperature sensing components are deployed on the surface and surrounding area of ​​the irradiated target region to monitor local temperature distribution and dynamic changes. A frequency-tunable microwave signal is output through a resonant cavity driving device to scan and irradiate the target area; the microwave detection array synchronously acquires the signals of reflected power Pr and transmitted power Pt; the acquired raw signals are processed by time synchronization and noise filtering, normalization correction and spectrum decomposition, and the electromagnetic response curves and preliminary reflected and transmitted power spectrum data of each position are obtained after processing. Infrared thermal imaging modules, embedded miniature thermocouple arrays, and fiber Bragg grating temperature sensors are deployed around the resonant cavity outlet, above the irradiation area, and at the lateral boundaries to collect real-time temperatures T at the surface and different depths of the target area. The multi-source temperature signals are then processed through time synchronization, noise filtering, and spatial interpolation fusion. A three-dimensional temperature field distribution of the target area is then established using a finite-difference heat conduction inversion algorithm or Kriging interpolation reconstruction technique. ; A photoplethysmography (PPG) sensor and an infrared thermal imaging device were deployed in the target irradiation area to simultaneously collect dynamic blood flow parameters, obtaining the blood flow rate change (Qss). The infrared thermal imaging module acquired a surface temperature distribution map of the target area, and combined with an infrared reflectivity and absorptivity model, the local tissue water content (hsl) was retrieved. Simultaneously, a low-intensity microwave dielectric parameter testing module was used to emit probe waves at different measuring points and measure the reflection coefficient and phase difference. Based on an electromagnetic inversion algorithm, the tissue dielectric constant was calculated, and the tissue thickness (zzh) was obtained. The blood flow rate change, tissue thickness, and water content were combined to form a local physiological response parameter set. Based on the measurement data under steady-state conditions, the baseline temperature (Tbase), reference physiological temperature (Tref), baseline blood flow (Qref), and reference standard stress were determined. Establish a reference dataset.

3. The microwave irradiation area matching system according to claim 2, characterized in that, The electromagnetic response resonance characteristic analysis module is used to perform the following steps: Based on reflection and transmission power spectrum data, a complex dielectric spectrum fitting algorithm is used to obtain the dielectric property parameters of the target region at different frequency bands, and the real part dcs and imaginary part dcx of the complex dielectric constant are extracted. Based on the electromagnetic response curve, a stress-electromagnetic coupling inversion algorithm is used to fit the power distribution gradient to obtain the standard deviation of the stress distribution within the target region. .

4. The microwave irradiation area matching system according to claim 3, characterized in that, The electromagnetic response resonance feature analysis module further includes performing the following steps: by setting a preset tissue resonance response threshold Oth, and comparing the target region tissue resonance response coefficient ORC with the tissue resonance response threshold Oth to obtain a first evaluation result, including: When the target region tissue resonance response coefficient ORC ≥ tissue resonance response threshold Oth, it indicates that the target region has reached the microwave resonance absorption state and enters the thermal effect analysis process. When the target region's tissue resonance response coefficient ORC is less than the tissue resonance response threshold Oth, it indicates that the target region has not reached the microwave resonance absorption state, triggering the first warning command and generating the first strategy: Adaptively fine-tuning the center frequency of the current frequency band using a resonant cavity frequency tuning device to improve local matching; adjusting the microwave waveform envelope and pulse width parameters to optimize energy distribution uniformity; real-time correction of the output power amplitude based on the reflection power Pr change trend of the previous cycle; rescanning once after correction and recalculating the target region's tissue resonance response coefficient ORC; if it still has not reached the tissue resonance response threshold Oth, then recording the current region as an energy coupling difficulty zone, the system automatically switches to low-power monitoring, extending the integration time to accumulate data and prevent local overheating.

5. A microwave irradiation area matching system according to claim 4, characterized in that, The thermal effect characteristic coupling determination module is used to perform the following steps: Three-dimensional temperature field distribution of the target region By employing time series smoothing and Gaussian spatial filtering algorithms, spatiotemporal denoising and local anomaly suppression processing are performed on the raw temperature of the three-dimensional temperature field distribution data of the target region, and the temperature change rate is extracted. and temperature spatial gradient The average temperature rise rate and thermal diffusion trend were calculated to establish the temperature dynamic characteristic curve of the target area.

6. A microwave irradiation area matching system according to claim 5, characterized in that, The thermal effect characteristic coupling determination module also includes the following steps: By setting a preset thermal response threshold Hth and comparing the thermal response coupling coefficient HRC of the target area with the thermal response threshold Hth, the second evaluation results are obtained, including: When the thermal response coupling coefficient HRC of the target area is greater than or equal to the thermal response threshold Hth, it indicates that the thermal response of the current target area is qualified. Maintain the current energy output and beam control status and continue to monitor. When the thermal response coupling coefficient HRC of the target area is less than the thermal response threshold Hth, it indicates that the thermal response of the current target area is unqualified, and there is a risk of insufficient local temperature rise or insufficient thermal coupling. This triggers a second warning instruction and generates a second strategy: automatically extend the microwave irradiation time by 30% and increase the microwave output power ratio by 15%; adjust the beam pointing angle and irradiation frequency to improve the uniformity of energy distribution; recalculate HRC after the correction. If the result is still less than Hth after two consecutive corrections, it is recorded as a "continuously insufficient response area". The system performs pulse energy compensation to enhance local heat accumulation and prevent overheating.

7. A microwave irradiation area matching system according to claim 1, characterized in that, The microcirculation improvement assessment module is used to perform the following steps: By setting a preset microcirculation improvement threshold Mth, and comparing the microcirculation improvement index (MCI) of the target area with the microcirculation improvement threshold Mth, the third evaluation results are obtained, including: When the microcirculation improvement index MCI of the target area is greater than or equal to the microcirculation improvement threshold Mth, it indicates that the current microcirculation improvement effect in the area is qualified. The system maintains the current energy output parameters and beam control strategy and continues to monitor. When the Microcirculation Improvement Index (MCI) of the target area is less than the Microcirculation Improvement Threshold (Mth), it indicates that the current microcirculation improvement effect in the area is unqualified, and there is a risk of insufficient local blood perfusion or uneven energy distribution. This triggers the third warning instruction and generates the third strategy: automatically extending the energy application time by 20% and increasing the output power by 10%; adjusting the resonant frequency micro-shift to optimize tissue energy coupling; and initiating a local energy dynamic rematching process, which feeds back to step two to perform resonance optimization and recalculate the MCI. If the results are still lower than Mth after two consecutive attempts, it is marked as a "microcirculation response insufficient area," and the system performs periodic pulse intervention to enhance the local blood flow improvement effect.

8. A microwave irradiation area matching system according to claim 1, characterized in that, The adaptive energy regulation and optimization module is used to perform the following steps: An initial energy-controlled convolutional neural network model was constructed using a convolutional neural network (CNN). The initial model was trained and tested using the target region's tissue resonance response coefficient (ORC), thermal response coupling coefficient (HRC), and microcirculation improvement index (MCI), combined with the local tissue water content (hsl) and tissue thickness (zzh), to obtain the trained convolutional neural network model, which serves as the AI ​​dynamic energy adjustment model. The input data is processed through the intermediate layer of a convolutional neural network to extract feature vectors, which are used to identify energy absorption characteristics and physiological response characteristics under different tissue types. The acquired feature information is used to perform secondary training and validation on the AI ​​dynamic energy adjustment model to optimize the model's ability to identify nonlinear coupling characteristics and its prediction accuracy, thereby forming a stable dynamic energy mapping relationship. Based on the predicted output of the AI ​​model and the accumulation of historical data, the feature weights and interlayer connection parameters of the convolutional neural network are continuously updated to achieve online learning and dynamic optimization of the energy regulation model. This enables the system to achieve the overall optimal match of energy transfer efficiency, temperature uniformity, and microcirculation improvement for different individuals, tissue characteristics, and environmental conditions.

Images