Laser therapeutic instrument, laser therapeutic instrument operation control device and storage medium

Abstract

The invention relates to a laser therapeutic instrument, a laser therapeutic instrument operation control device and a storage medium. The laser therapeutic instrument comprises a processor and a memory. Wherein the memory is used for storing computer programs; the processor executes the following steps when running a computer program: acquiring static characteristics and dynamic characteristics of a target object; based on the static features and the dynamic features, combining a tissue characteristic map and a prediction model to obtain a change trend prediction result of the target object; the tissue characteristic map comprises static characteristic reference values of different tissue types / skin types and a historical change rule curve of dynamic characteristics along with time; the prediction model is obtained based on constitutive equation training of the target object; on the basis of the variation trend prediction result, working parameters during operation on each region of the target object are determined in combination with an energy gradient distribution algorithm; and on the basis of the working parameters, real-time parameters of corresponding components in the laser therapeutic instrument are adjusted, and treatment of the target object is completed. Therefore, the accuracy and the stability of treatment are improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a laser therapy device, a laser therapy device operation control device, and a storage medium. Background Technology

[0002] Carbon dioxide laser therapy devices, with their wavelength and strong absorption characteristics of water in biological tissues, achieve tissue burning, cutting, carbonization, and physiotherapy through photothermal effects. They have been widely used in clinical fields such as dermatology, plastic surgery, and ophthalmology, becoming core equipment for treatments such as freckle removal, scar removal, and tissue repair.

[0003] However, existing carbon dioxide laser therapy devices still have many technical defects in clinical applications, which restrict the further improvement of treatment accuracy, safety and efficacy stability. For example, the precise control of the treatment process is difficult. Key operational factors such as the time, position and angle of laser irradiation directly affect the accuracy and efficacy of energy action. Existing equipment lacks the ability to dynamically adapt to these factors. In clinical operation, human operation errors or equipment positioning deviations can easily cause the laser energy to deviate from the target area, resulting in problems such as insufficient treatment or excessive damage. Summary of the Invention

[0004] Therefore, it is necessary to provide a laser therapy device, a laser therapy device operation control device, and a storage medium to address the above-mentioned technical problems.

[0005] In a first aspect, this application provides a laser therapy device, including a processor and a memory; wherein the memory is used to store a computer program; and the processor performs the following steps when running the computer program: Acquire static and dynamic features of the target object; wherein the static features characterize the optical properties parameters of the target object; and the dynamic features characterize the dynamic changes of the target object during the treatment process. Based on the static and dynamic features, combined with the tissue characteristic map and the prediction model, the predicted trend of the target object is obtained; wherein, the tissue characteristic map includes the static feature baseline values ​​of different tissue types / skin textures and the historical change curves of the dynamic features over time; the prediction model is trained based on the constitutive equation of the target object; Based on the predicted trend, and combined with the energy gradient allocation algorithm, the working parameters for operating on each region of the target object are determined. Based on the operating parameters, the real-time parameters of the corresponding components in the laser therapy device are adjusted to complete the treatment of the target object.

[0006] In one embodiment, obtaining the predicted trend of the target object based on the static features and the dynamic features, combined with the tissue characteristic map and the prediction model, includes: The static features are matched with the tissue characteristic map to obtain the target tissue category and the corresponding dynamic change benchmark trend; The static features and the dynamic features are input into the prediction model to obtain candidate change trend prediction results; The change trend prediction result is obtained based on the candidate change trend prediction result and the dynamic change benchmark trend.

[0007] In one embodiment, matching the static features with the tissue characteristic map to obtain the target tissue category and the corresponding dynamic change baseline trend includes: From the static features, key and non-core indicators are selected to match, and the similarity between the key matching indicators and the benchmark values ​​of static features in the tissue characteristic map is calculated. Candidate units are selected from the tissue characteristic map based on the similarity. When there are multiple candidate units, the fit of the non-core indicators is compared. Based on the fit, the target organization category is selected from the candidate units and the corresponding dynamic change benchmark trend is determined.

[0008] In one embodiment, the prediction model is a physical information neural network; the training method of the prediction model includes: Acquire sample data and extract sample features; wherein, the sample features include static sample features and dynamic sample features; Based on the deformation and strain, mechanical properties and stress relaxation of the tissue under laser irradiation, the constitutive equation of the target object is constructed. The initial network is trained based on the sample features, and the constitutive equation is embedded as a constraint in the network loss function. The initial network is iterated until the loss value converges to obtain the prediction model.

[0009] In one embodiment, determining the operating parameters for operating on each region of the target object based on the predicted trend and in conjunction with an energy gradient allocation algorithm includes: The laser spot is divided into multiple independent micro-regions using a spot segmentation algorithm; Based on the predicted value of the tissue absorption coefficient in the predicted trend, determine the static feature weight and the dynamic trend weight. Based on the predicted temperature value in the trend prediction results, a safety correction factor is determined; The target power density in the operating parameters is determined based on the base power density of each independent micro-region, the static feature weight, the dynamic trend weight, and the safety correction coefficient. Based on the predicted value of the tissue absorption coefficient in the predicted trend, the target laser wavelength in the working parameters is determined.

[0010] In one embodiment, determining the target laser wavelength in the working parameters based on the predicted tissue absorption coefficient value in the predicted trend results includes: Based on the predicted value of the tissue absorption coefficient, the current static absorption coefficient, and the static thickness of the micro-region, the penetration depth prediction result is determined; Based on the penetration depth prediction results, the target laser wavelength is obtained by substituting the tissue characteristic spectrum into the data.

[0011] In one embodiment, adjusting the real-time parameters of the corresponding components in the laser therapy device based on the operating parameters includes: The target power density is mapped to a power control signal using a linear mapping formula; The penetration depth prediction result is mapped to a focusing lens control signal using a mapping formula between penetration depth and focusing lens; wherein the focusing lens control signal includes a position control signal and / or an angle control signal.

[0012] In one embodiment, the expression for the network loss function is as follows: ; ; ; in, Indicates data loss; The physical loss is indicated and determined based on the constitutive equation; Indicates the balance coefficient; N indicates the number of training samples; Indicates the measured tissue characteristic values; Indicates predicted tissue characteristic values; Indicates the L2 norm; M indicates the number of physical constraint sampling points; Indicates the mechanical stress of the tissue; Indicates relaxation time; Indicates the dynamic elastic modulus; Instructions for organizational response.

[0013] Secondly, this application also provides a laser therapy device operation control device, applied to a laser therapy device, the device comprising: An acquisition module is used to acquire the static and dynamic features of a target object; wherein the static features characterize the optical properties parameters of the target object; and the dynamic features characterize the dynamic changes of the target object during the treatment process. The prediction module is used to obtain the predicted trend of the target object based on the static features and the dynamic features, combined with the tissue characteristic map and the prediction model; wherein, the tissue characteristic map includes the static feature baseline values ​​of different tissue types / skin textures and the historical change curves of the dynamic features over time; the prediction model is trained based on the constitutive equation of the target object; The analysis module is used to determine the working parameters for operating on each region of the target object based on the predicted trend and the energy gradient allocation algorithm. The adjustment module is used to adjust the real-time parameters of the corresponding components in the laser therapy device based on the operating parameters, so as to complete the treatment of the target object.

[0014] Thirdly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps performed by the laser therapy device described in any embodiment of this application.

[0015] The aforementioned laser therapy device simultaneously acquires the static optical properties of the target object and its dynamic changes during treatment. This not only fully covers the individual differences in tissue complexity and disease variability among different patients, but also captures the dynamic drift of indicators such as tissue temperature, moisture, and elastic modulus under laser irradiation in real time. Combined with tissue characteristic maps containing static characteristic benchmarks and historical dynamic characteristic changes for different tissue types / skin textures, and the prediction results derived from a prediction model trained on the constitutive equation of the target object, this device achieves precise adaptation to individual differences in different tissue types and skin textures based on massive amounts of historical clinical data. Furthermore, the physical constraints of the constitutive equation ensure that the prediction results strictly conform to objective laws such as biomechanics, reducing the impact of purely data-driven approaches. The model overcomes physical paradoxes and prediction biases, enabling scientific and forward-looking prediction of tissue characteristic changes. Furthermore, compared to the passive parameter adjustment mode of traditional equipment, forward-looking prediction can effectively offset the delay error from laser energy emission to its effect on the tissue. Based on this, an energy gradient allocation algorithm precisely matches differentiated working parameters to different micro-regions within the target area, solving the problem of local energy excess or deficiency caused by traditional uniform energy output. Finally, by mapping the optimized working parameters to the real-time control parameters of the corresponding components of the laser therapy device, the accuracy and stability of treatment are significantly improved, clinical risks are significantly reduced, and the inconsistent efficacy among different patients is effectively addressed, ensuring the consistency and reliability of treatment results. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the steps of a laser therapy device performing an operation control method according to an exemplary embodiment;

[0017] Figure 2 This is a flowchart illustrating the steps of a laser therapy device performing an operation control method according to an exemplary embodiment;

[0018] Figure 3 This is a structural block diagram of a laser therapy device operation control device according to an exemplary embodiment;

[0019] Figure 4 This is an internal structural diagram of a laser therapy device according to an exemplary embodiment. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0021] The terms "first," "second," and "third" used in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such processes, methods, products, or apparatus.

[0022] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0023] In this embodiment, the laser therapy device is a type of medical device that utilizes the interaction effects between lasers and biological tissues (photothermal effect, photochemical effect, photobiostimulation effect, photomechanical effect, etc.) to achieve disease treatment, tissue repair, deformity correction, or cosmetic shaping by adjusting parameters such as laser wavelength, power, pulse width, and irradiation mode. The laser therapy device may include, but is not limited to, at least one of carbon dioxide laser therapy devices, semiconductor (diode) laser therapy devices, and erbium laser therapy devices.

[0024] In some embodiments, such as Figure 1 As shown, a laser therapy device is provided, including a processor and a memory; wherein the memory is used to store a computer program; the processor performs the following steps when running the computer program:

[0025] S101, Obtain the static and dynamic features of the target object; wherein, the static features characterize the optical properties parameters of the target object; and the dynamic features characterize the dynamic changes of the target object during the treatment process.

[0026] In this embodiment, the target object can be human tissue. The target object may include, but is not limited to, at least one of epithelial tissue, connective tissue, nerve tissue, and muscle tissue.

[0027] In the embodiments of this application, the optical characteristic parameters may include, but are not limited to, at least one of the absorption coefficient, scattering coefficient, incident laser light flux, and reflected light flux.

[0028] In the embodiments of this application, the dynamic change may include, but is not limited to, at least one of tissue temperature, tissue elastic modulus, and tissue moisture.

[0029] In some embodiments, obtaining the static and dynamic features of the target object includes: Acquire raw sensor data; Based on the incident and reflected light flux of the laser in the original data of the sensor, and combined with the inverse Monte Carlo algorithm, the static features are determined; wherein, the static features include at least one of the tissue absorption coefficient, tissue reduced scattering coefficient, tissue refractive index, and tissue thickness; The dynamic characteristics are determined based on the tissue temperature, tissue elastic modulus, absorption coefficient, and / or tissue moisture content in the raw data from the sensor; wherein the dynamic characteristics include the amount of temperature change, the amount of elastic modulus change, the moisture loss rate, and / or the amount of absorption coefficient change.

[0030] In this embodiment, the tissue absorption coefficient characterizes the tissue's ability to absorb laser energy.

[0031] In this embodiment, the tissue reduced scattering coefficient characterizes the tissue's ability to scatter laser light.

[0032] For example, one way to compute static features using the inverse Monte Carlo algorithm is as follows: ; in, Indicator tissue absorption coefficient; The reduced scattering coefficient of the tissue is indicated by d; d indicates the tissue thickness. Indicates the incident light flux of the laser; The indicator is the reflected light flux; k1 and k2 are calibration coefficients, which can be determined by matching with pre-stored tissue characteristic maps. For example, k1 can be 0.85 for oily skin and 1.1 for dry skin.

[0033] In some embodiments, the laser therapy device can denoise the raw sensor data using a sliding window filtering algorithm to obtain target data, ensuring data smoothness; the temperature change can be determined by the difference between the tissue temperature at the next moment and the tissue temperature at the previous moment in the target data; the change in absorption coefficient can be determined by the difference between the absorption coefficient at the next moment and the absorption coefficient at the previous moment in the target data; the tissue moisture loss rate can be inverted by the change in scattering coefficient in the target data; and the change in elastic modulus can be derived from the pressure sensor data in the target data.

[0034] In this embodiment, by relying on the inverse Monte Carlo algorithm to invert and calculate the incident and reflected light flux of the laser, core static optical features such as tissue absorption coefficient and reduced scattering coefficient can be accurately extracted. This ensures that the initial parameters are highly matched with the inherent tissue characteristics of the target object, effectively solving the problem of insufficient adaptation to individual differences caused by traditional equipment relying on experience-based preset static parameters. Furthermore, by calculating dynamic features such as temperature change and moisture loss rate based on indicators such as tissue temperature and elastic modulus in the original sensor data, the tissue characteristic drift caused by laser energy during treatment can be captured in real time. This fills the gap that static features cannot reflect the real-time state of the tissue. Ultimately, this provides comprehensive, accurate, and real-time data support for subsequent trend prediction based on tissue characteristic maps and determination of differentiated working parameters based on energy gradient allocation algorithms, ensuring the accuracy and stability of the entire treatment process from the source.

[0035] S102, based on the static features and the dynamic features, combined with the tissue characteristic map and the prediction model, the prediction result of the change trend of the target object is obtained; wherein, the tissue characteristic map includes the static feature benchmark values ​​of different tissue types / skin textures and the historical change curve of the dynamic features over time; the prediction model is trained based on the constitutive equation of the target object.

[0036] In this embodiment of the application, the organizational characteristic map is a pre-stored database of multi-dimensional features and trend mappings.

[0037] In some embodiments, such as Figure 2 As shown, the step of obtaining the predicted trend of the target object based on the static features and the dynamic features, combined with the organizational characteristic map and the prediction model, includes: S1021, Match the static features with the tissue characteristic map to obtain the target tissue category and the corresponding dynamic change benchmark trend; S1022, Input the static features and the dynamic features into the prediction model to obtain the candidate change trend prediction results; S1023, Based on the candidate change trend prediction results and the dynamic change benchmark trend, the change trend prediction results are obtained.

[0038] In some embodiments, the laser therapy device can input normalized static features into a tissue characteristic map, match the most similar tissue category as the target tissue category, and extract the dynamic change benchmark trend corresponding to the target tissue category.

[0039] In some embodiments, matching the static features with the tissue characteristic map to obtain the target tissue category and the corresponding dynamic change baseline trend includes: From the static features, key and non-core indicators are selected to match, and the similarity between the key matching indicators and the benchmark values ​​of static features in the tissue characteristic map is calculated. Candidate units are selected from the tissue characteristic map based on the similarity. When there are multiple candidate units, the fit of the non-core indicators is compared. Based on the fit, the target organization category is selected from the candidate units and the corresponding dynamic change benchmark trend is determined.

[0040] In some embodiments, multi-source data can be collected, including static feature data and dynamic change data. The multi-source data is preprocessed and standardized to obtain target data. The target data is then classified and labeled, including major categories based on tissue type, such as skin tissue, mucous membrane tissue, and scar tissue. Each major category of tissue type is further subdivided according to tissue characteristics. For example, the skin tissue category can be classified by skin type into oily, dry, combination-dry, and sensitive skin, or the scar tissue category can be classified by scar type into hypertrophic scars, atrophic scars, and old scars. Each classification unit is assigned a unique label (e.g., "skin tissue - oily skin" is labeled T01-F01) to facilitate rapid retrieval and matching in the future.

[0041] In some embodiments, for each classification unit (e.g., "scar tissue - dry skin"), the mean, standard deviation, and confidence interval (e.g., 95%) of the static characteristics of all its samples are statistically analyzed. The mean is used as the static characteristic benchmark value of the classification unit (e.g., the average absorption coefficient of this category is 0.8 mm⁻¹, and the average thickness is 2.2 mm). At the same time, the standard deviation and confidence interval are stored for similarity determination during subsequent matching. For the dynamic time series data of each classification unit, the mean of dynamic characteristics at each time point is calculated according to the time axis (e.g., 0-30s) (e.g., the average temperature change at 500ms and the average moisture loss rate at 10s). With time as the horizontal axis and the mean of dynamic characteristics as the vertical axis, a smooth dynamic change benchmark trend curve is fitted to generate. The dynamic change benchmark trend curve includes the temperature change trend curve, the absorption coefficient change trend curve, the elastic modulus change trend curve, etc., which intuitively reflects the typical dynamic response law of this type of tissue under laser treatment.

[0042] In some embodiments, a storage structure of "classification index + feature matrix" is adopted: the first-level index is the organization type, and the second-level index is the organization characteristics, resulting in an organization characteristic map; the static feature benchmark value table and dynamic trend curve library of the corresponding classification unit can be directly retrieved by clicking the index; or, matching classification units can be filtered by a single static feature (such as absorption coefficient) or a combination of features (absorption coefficient + thickness).

[0043] In some embodiments, the laser therapy device can select the static features that have the greatest impact on the laser therapy response as key matching indicators and assign weights accordingly. For example, based on clinical data statistics, it can be determined that the tissue absorption coefficient and thickness directly determine the laser penetration depth and energy absorption efficiency, and therefore have the highest weight; the initial elastic modulus reflects the mechanical properties of the tissue and has the second highest weight; the refractive index has a relatively small impact on laser propagation and has the lowest weight. Therefore, the key matching indicators can be determined as tissue absorption coefficient (weight 40%), tissue thickness (weight 30%), initial elastic modulus (weight 20%), and refractive index (weight 10%). For each core matching dimension, the target is calculated. The relative deviation between the target value and the benchmark value (e.g., relative deviation of absorption coefficient = |target absorption coefficient - benchmark absorption coefficient| / benchmark absorption coefficient) is combined with weights to calculate a weighted comprehensive similarity. A similarity threshold (e.g., ≥85%) is set, and classification units with a comprehensive similarity higher than the threshold are selected as candidate units. If there is only one candidate unit, it is directly determined as the target tissue category and the corresponding dynamic change benchmark trend is determined. If there are multiple candidate units, the fit of non-core indicators (e.g., reduced scattering coefficient) can be further compared, and candidate units with excessive deviation of non-core features are eliminated to obtain the target tissue category and determine the corresponding dynamic change benchmark trend.

[0044] In this embodiment, key and non-core indicators are first selected from static features in a hierarchical manner to accurately grasp the core feature dimensions that have the most significant impact on tissue type, skin texture determination, and laser treatment response. This makes the similarity calculation with the static feature benchmark value of the tissue characteristic map more targeted, reduces the matching deviation caused by irrelevant interference from non-core features, and improves the efficiency and accuracy of the initial candidate unit selection. Based on the similarity of core indicators, candidate units are selected from the map, which can quickly lock the matching range that highly matches the core static features of the target object from a massive number of tissue type-skin texture classification units, reducing the workload of subsequent fine comparison, while ensuring the matching fit of candidate units. When there are multiple candidate units, the fit of non-core indicators is further compared to achieve a second fine verification and identification of candidate units. This can effectively eliminate mismatched units that are similar in core indicators but have large deviations in non-core indicators, reduce misjudgment of tissue type caused by accidental similarity of core indicators, and make the matching results of tissue type and skin texture more consistent with the actual tissue characteristics of the target object.

[0045] In this embodiment of the application, the prediction model refers to an algorithm model used to predict the trend of changes in the characteristics of the target tissue during laser treatment. For example, the prediction model can be a weighted fusion Long Short-Term Memory (LSTM) network, a Convolutional Neural Network (CNN), a CNN-LSTM hybrid deep learning model, a Physics-Informed Neural Network (PINN), etc.

[0046] In some embodiments, the prediction model is a physical information neural network; the training method of the prediction model includes: Acquire sample data and extract sample features; wherein, the sample features include static sample features and dynamic sample features; Based on the deformation and strain, mechanical properties and stress relaxation of the tissue under laser irradiation, the constitutive equation of the target object is constructed. The initial network is trained based on the sample features, and the constitutive equation is embedded as a constraint in the network loss function. The initial network is iterated until the loss value converges to obtain the prediction model.

[0047] In this embodiment of the application, sample features refer to the core quantitative indicators extracted from sample data that can characterize the tissue properties under laser irradiation.

[0048] In this embodiment, the deformation of the tissue indicates the physical changes in shape and size of the tissue caused by the photothermal effect of the laser after it acts on the tissue due to thermal softening, thermal expansion or structural changes, such as local contraction and thinning of skin tissue after laser irradiation. These are the macroscopic mechanical responses of the tissue.

[0049] In this embodiment, the strain generated by the tissue is a quantitative characterization of the tissue deformation under laser irradiation. The calculation formula can be the ratio of the tissue deformation increment to the original size (e.g., thickness direction strain = tissue thickness change / initial tissue thickness), reflecting the degree and proportion of tissue deformation.

[0050] In this embodiment of the application, mechanical properties refer to the inherent mechanical properties of tissues under laser irradiation that resist deformation or damage caused by external forces. They are the core indicators characterizing the mechanical state of tissues, such as the elastic modulus, viscosity coefficient, hardness, and ductility of tissues.

[0051] In this embodiment, stress relaxation refers to the mechanical phenomenon that the stress generated inside the tissue gradually decreases over time under constant strain conditions. For example, after laser irradiation causes the tissue to undergo fixed deformation, the stress inside the tissue will gradually decrease over time. This is the core mechanical basis for constructing the tissue constitutive equation.

[0052] In the embodiments of this application, the constitutive equation is a physical equation that characterizes the quantitative relationship between the mechanical response (such as stress and strain) of the target tissue under laser irradiation and its own mechanical properties and external conditions. It is a mathematical expression of the biomechanical laws of tissue.

[0053] For example, the constitutive equation can be determined based on the tissue mechanical stress, relaxation time, dynamic elastic modulus, and tissue strain.

[0054] In some embodiments, the expression for the network loss function is as follows: ; ; ; in, Indicates data loss; The physical loss is indicated and determined based on the constitutive equation; Indicates the balance coefficient; N indicates the number of training samples; Indicates the measured tissue characteristic values; Indicates predicted tissue characteristic values; Indicates the L2 norm; M indicates the number of physical constraint sampling points; Indicates the mechanical stress of the tissue; Indicates relaxation time; Indicates the dynamic elastic modulus; Instructions for organizational response.

[0055] In this embodiment, the constitutive equation of the target object is constructed based on the actual mechanical responses of tissue under laser irradiation, such as deformation, strain, mechanical properties, and stress relaxation. This allows the equation to accurately and clinically represent the true biomechanical laws of tissue under laser treatment, providing a physical constraint basis that conforms to objective reality for subsequent model training. Training the initial network based on sample features and embedding the constitutive equation as a constraint condition into the network loss function for iteration until the loss value converges allows the model to fully learn the individual differences in different tissue types and skin textures based on sample features, achieving data-driven personalized adaptation. Furthermore, the physical constraints force the model output results to strictly follow the objective mechanical and photothermal coupling laws of the tissue, reducing the physical paradoxes, overfitting, and prediction biases that are prone to occur in purely data-driven models. Simultaneously, the training process until the loss value converges allows the network parameters to reach their optimal state, ensuring that the final prediction model has a stable and accurate ability to predict tissue characteristic changes. From the algorithm model level, this provides scientific and reliable core support for subsequent trend prediction and parameter allocation in laser treatment, solidifying the foundation for the accuracy, rationality, and feasibility of the entire laser treatment plan.

[0056] In some embodiments, the laser therapy device can extract spatial features of tissue characteristic maps (such as the optical difference distribution between the T and U zones of mixed skin) through CNN, and then learn time series patterns through LSTM network. Based on static and dynamic features, it can accurately predict the trend of tissue characteristics after a predetermined time (such as 30ms, 2s, etc.) to obtain candidate trend prediction results. For example, it can predict that the scattering coefficient of dry skin will increase at a rate of 0.02 / s under continuous laser action, and the epidermal moisture loss rate will reach 1.5% / s. The candidate trend prediction results and the dynamic baseline trend are weighted and fused to obtain the trend prediction result.

[0057] In this embodiment, the target tissue category and dynamic change baseline trend are first obtained by matching static features with tissue characteristic maps, providing a general reference based on a large amount of historical clinical data for trend prediction and reducing the limitation of the prediction model being detached from clinical reality. Then, the static features and real-time dynamic features are input into the prediction model to generate candidate trend prediction results, ensuring that the prediction results can accurately match the individual tissue dynamic change state of the current treatment subject. Finally, the candidate prediction results are fused with the dynamic change baseline trend to obtain the final trend prediction result. This not only effectively corrects the prediction bias caused by noise interference that may exist in real-time data, but also prioritizes the adaptation to the individual's real-time state when there are differences between individual tissue characteristics and the general baseline, significantly improving the accuracy, stability and robustness of trend prediction, and laying a reliable data foundation for subsequent energy gradient allocation and precise adjustment of treatment device parameters based on the prediction results.

[0058] S103, Based on the predicted trend of change and combined with the energy gradient allocation algorithm, determine the working parameters for operating on each region of the target object.

[0059] In one embodiment, the laser spot can be divided into multiple independent micro-regions using a spot segmentation algorithm. Each micro-region is independently matched with working parameters through an AI model. For example, the T-zone of combination skin has high sebum secretion and a low absorption coefficient, so the power density of the corresponding micro-region can be automatically increased to 80W / cm², and the wavelength can be adjusted to 10750nm. On the other hand, the U-zone of skin is drier and has a higher scattering coefficient, so the power density of the corresponding micro-region is reduced to 30W / cm², and the wavelength is switched to 10650nm.

[0060] In some embodiments, determining the operating parameters for operating on each region of the target object based on the trend prediction results and in conjunction with an energy gradient allocation algorithm includes: The laser spot is divided into multiple independent micro-regions using a spot segmentation algorithm; Based on the predicted value of the tissue absorption coefficient in the predicted trend, determine the static feature weight and the dynamic trend weight. Based on the predicted temperature value in the trend prediction results, a safety correction factor is determined; The target power density in the operating parameters is determined based on the base power density of each independent micro-region, the static feature weight, the dynamic trend weight, and the safety correction coefficient. Based on the predicted value of the tissue absorption coefficient in the predicted trend, the target laser wavelength in the working parameters is determined.

[0061] In one embodiment, the tissue thermal damage threshold of micro-region i is compared with the predicted temperature. When the predicted temperature is close to the tissue thermal damage threshold, the safety correction coefficient decays rapidly using an exponential decay model. For example, one way to determine the safety correction coefficient is as follows: ; Where, [x] + =max(x,0); K indicates the threshold of thermal damage to tissue; K indicates the safe attenuation coefficient. Indicates the predicted temperature value.

[0062] In one embodiment, the static feature weight is determined based on the ratio of the absorption coefficient of micro-region i to the average absorption coefficient of the target object; for example, one way to determine the static feature weight is as follows: .

[0063] For example, a method for determining dynamic trend weights can be as follows: ; in, The predicted value of the tissue absorption coefficient of microregion i; Indicates the current absorption coefficient of microregion i.

[0064] For example, a target power density can be determined as follows: ; in, Indicates base power density; Indicates the static feature weights; Indicates dynamic trend weights; Indicates the safety correction factor.

[0065] In this embodiment, the laser spot is divided into multiple independent micro-regions using a spot segmentation algorithm, breaking the limitations of uniform energy output in traditional laser therapy devices. This allows for differentiated parameter configuration based on the tissue characteristics of different parts within the target area, reducing the problem of thermal damage caused by excessive energy in local areas or poor therapeutic effects due to insufficient energy. Static feature weights and dynamic trend weights are determined based on the predicted tissue absorption coefficient from the trend prediction results, ensuring that the target power density both conforms to the inherent static optical characteristics of the tissue and accurately adapts to the real-time dynamic changes in the tissue during treatment. This effectively offsets parameter mismatch issues caused by the delay in laser energy application. A safety correction coefficient is determined based on the temperature prediction value, enabling early prediction of tissue thermal damage risks. Dynamic adjustment of the power density avoids local temperature exceeding limits, significantly improving treatment safety. Simultaneously, the target laser wavelength is also determined based on the predicted tissue absorption coefficient, ensuring precise matching between the laser penetration depth and the real-time tissue state, further enhancing the accuracy and effectiveness of treatment. Ultimately, this provides a scientific and personalized basis for real-time parameter adjustment of the corresponding components of the laser therapy device.

[0066] In some embodiments, determining the target laser wavelength in the working parameters based on the predicted tissue absorption coefficient value in the trend prediction result includes: Based on the predicted value of the tissue absorption coefficient, the current static absorption coefficient, and the static thickness of the micro-region, the penetration depth prediction result is determined; Based on the penetration depth prediction results, the target laser wavelength is obtained by substituting the tissue characteristic spectrum into the data.

[0067] In some embodiments, the laser therapy device can determine the target penetration depth based on the static thickness of micro-region i, the current absorption coefficient, and the predicted value of the tissue absorption coefficient, thus characterizing the predicted penetration depth requirement; and substitute the target penetration depth into the wavelength-absorption coefficient-penetration depth correlation model of the tissue characteristic spectrum to obtain the target laser wavelength.

[0068] For example, one method for determining the penetration depth of a target can be: ; where d i Indicates the static thickness of micro-region i; Indicates the current absorption coefficient of micro-region i; The predicted value of the tissue absorption coefficient for microregion i.

[0069] In this embodiment, by combining the predicted value of tissue absorption coefficient, the current static absorption coefficient, and the static thickness of the micro-area, the dynamic drift of tissue characteristics during treatment can be proactively adapted. This reduces the risk of laser penetration being too deep and damaging normal subcutaneous tissue due to changes in tissue absorption capacity, or too shallow and failing to reach the core area of ​​the lesion. Simultaneously, by substituting the predicted penetration depth into the tissue characteristic map to match the target laser wavelength, rather than directly calculating the wavelength using theoretical formulas, the theoretical deviation caused by differences in individual tissue composition (such as water content and collagen content) can be corrected based on the large amount of clinical measurement data accumulated in the map. This ensures that the actual penetration effect corresponding to the selected wavelength accurately matches the predicted requirements. Furthermore, the optimal solution can be selected from the actual output wavelength range of the laser therapy device, taking into account both the scientific nature of wavelength selection and the feasibility of equipment execution. Ultimately, this significantly improves the accuracy of laser action and ensures treatment effectiveness and safety.

[0070] S104, Based on the operating parameters, adjust the real-time parameters of the corresponding components in the laser therapy device to complete the treatment of the target object.

[0071] In some embodiments, adjusting the real-time parameters of the corresponding components in the laser therapy device based on the operating parameters includes: The target power density is mapped to a power control signal using a linear mapping formula; The penetration depth prediction result is mapped to a focusing lens control signal using a mapping formula between penetration depth and focusing lens; wherein, the focusing lens control signal includes a position control signal and / or an angle control signal.

[0072] In some embodiments, the calculated target power density of the micro-area is substituted into a pre-calibrated linear correlation benchmark between power and control signal to directly obtain the corresponding benchmark power control signal. Simultaneously, the benchmark power control signal is slightly linearly corrected by combining real-time acquired tissue dynamic characteristics and environmental parameters. The correction magnitude is linearly correlated with the degree of parameter deviation, ensuring the stability of the mapping relationship while offsetting the influence of interference factors. During this process, the actual output power of the laser and the target power density can also be compared in real time, and linear compensation is performed based on the deviation between the two to ensure that the final output power control signal and the target power density always maintain a precise linear correspondence.

[0073] In some embodiments, pre-stored linear correlations are acquired. These linear correlations include: first, a linear ratio between penetration depth and focusing lens position displacement, where for every preset increase in penetration depth, the focusing lens moves linearly a corresponding distance away from the tissue; and second, a linear correlation between penetration depth uniformity requirements and focusing lens angle adjustment amplitude, where the greater the deviation in spot uniformity, the higher the amplitude of linear fine-tuning of the focusing lens angle. Based on these linear correlations, the initial position control signal and angle control signal of the focusing lens are directly calculated. Then, combined with the curved contour features of the treatment area and dynamic tissue deformation data, the initial control signal is linearly optimized, with the optimization amount linearly correlated with contour deviation and deformation degree. In addition, the optical path monitoring sensor captures the deviation between the actual focusing state and the target penetration depth in real time. The system performs linear feedback adjustment based on this deviation value, ensuring that the position and angle control signals of the focusing lens always maintain a precise linear mapping with the penetration depth prediction result, ensuring that the laser penetration depth fully meets the treatment requirements.

[0074] Thus, by converting the target power density into a power control signal through a linear mapping formula, a precise, stable, and traceable correspondence can be established between the target treatment parameters and the laser hardware execution signals. This reduces the complex errors caused by nonlinear conversion and facilitates rapid linear compensation based on the deviation between the actual power output and the target value monitored in real time. Furthermore, converting the penetration depth prediction result into a focusing lens position and / or angle control signal through linear mapping ensures that the adjustment range of the focusing lens is directly proportional to the penetration depth requirement. This allows for precise control of the focusing position and range of the laser spot, adapting to the differences in penetration depth in different micro-regions. These two types of linear mapping not only simplify the calculation logic of parameter conversion and reduce the system's computational load but also provide a clear correction path for subsequent real-time closed-loop feedback adjustments. This ensures that the actions of each component of the laser therapy device are highly compatible with personalized treatment needs, ultimately improving the accuracy and stability of the laser therapy device.

[0075] The aforementioned laser therapy device simultaneously acquires the static optical properties of the target object and its dynamic changes during treatment. This not only fully covers the individual differences in tissue complexity and disease variability among different patients, but also captures the dynamic drift of indicators such as tissue temperature, moisture, and elastic modulus under laser irradiation in real time. Combined with tissue characteristic maps containing static characteristic benchmarks and historical dynamic characteristic changes for different tissue types / skin textures, and the prediction results derived from a prediction model trained on the constitutive equation of the target object, this device achieves precise adaptation to individual differences in different tissue types and skin textures based on massive amounts of historical clinical data. Furthermore, the physical constraints of the constitutive equation ensure that the prediction results strictly conform to objective laws such as biomechanics, reducing the impact of purely data-driven approaches. The model overcomes physical paradoxes and prediction biases, enabling scientific and forward-looking prediction of tissue characteristic changes. Furthermore, compared to the passive parameter adjustment mode of traditional equipment, forward-looking prediction can effectively offset the delay error from laser energy emission to its effect on the tissue. Based on this, an energy gradient allocation algorithm precisely matches differentiated working parameters to different micro-regions within the target area, solving the problem of local energy excess or deficiency caused by traditional uniform energy output. Finally, by mapping the optimized working parameters to the real-time control parameters of the corresponding components of the laser therapy device, the accuracy and stability of treatment are significantly improved, clinical risks are significantly reduced, and the inconsistent efficacy among different patients is effectively addressed, ensuring the consistency and reliability of treatment results.

[0076] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0077] Based on the same inventive concept, this application also provides a laser therapy device operation control apparatus for implementing the above-described laser therapy device operation control method steps. The solution provided by this apparatus is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the laser therapy device operation control apparatus provided below can be found in the above-described limitations on the laser therapy device operation control method steps, and will not be repeated here.

[0078] In one embodiment, such as Figure 3 As shown, a laser therapy device operation control device is provided, applied to a laser therapy device, the device comprising: The acquisition module 10 is used to acquire the static and dynamic features of the target object; wherein the static features characterize the optical property parameters of the target object; and the dynamic features characterize the dynamic changes of the target object during the treatment process. Prediction module 20 is used to obtain the predicted trend of the target object based on the static features and the dynamic features, combined with the tissue characteristic map and the prediction model; wherein, the tissue characteristic map includes the static feature baseline values ​​of different tissue types / skin textures and the historical change curve of the dynamic features over time; the prediction model is trained based on the constitutive equation of the target object; Analysis module 30 is used to determine the working parameters when operating on each region of the target object based on the predicted trend and in combination with the energy gradient allocation algorithm. The adjustment module 40 is used to adjust the real-time parameters of the corresponding components in the laser therapy device based on the operating parameters, so as to complete the treatment of the target object.

[0079] In one embodiment, the prediction module 20 includes: A matching unit is used to match the static features with the tissue characteristic map to obtain the target tissue category and the corresponding dynamic change benchmark trend; The first prediction unit is used to input the static features and the dynamic features into the prediction model to obtain the candidate change trend prediction result; The second prediction unit is used to obtain the trend prediction result based on the candidate trend prediction result and the dynamic trend benchmark.

[0080] In one embodiment, the first prediction unit is configured to perform the following steps: From the static features, key and non-core indicators are selected to match, and the similarity between the key matching indicators and the benchmark values ​​of static features in the tissue characteristic map is calculated. Candidate units are selected from the tissue characteristic map based on the similarity. When there are multiple candidate units, the fit of the non-core indicators is compared. Based on the fit, the target organization category is selected from the candidate units and the corresponding dynamic change benchmark trend is determined.

[0081] In one embodiment, the prediction model is a physical information neural network; the training method of the prediction model includes: Acquire sample data and extract sample features; wherein, the sample features include static sample features and dynamic sample features; Based on the deformation and strain, mechanical properties and stress relaxation of the tissue under laser irradiation, the constitutive equation of the target object is constructed. The initial network is trained based on the sample features, and the constitutive equation is embedded as a constraint in the network loss function. The initial network is iterated until the loss value converges to obtain the prediction model.

[0082] In one embodiment, the analysis module 30 includes: The segmentation unit is used to divide the laser spot into multiple independent micro-regions using a spot segmentation algorithm; The first determining unit is used to determine the static feature weight and the dynamic trend weight based on the predicted value of the tissue absorption coefficient in the predicted trend of change. The second determining unit is used to determine a safety correction coefficient based on the temperature prediction value in the trend prediction result; The third determining unit is used to determine the target power density in the operating parameters based on the base power density of each independent micro-region, the static feature weight, the dynamic trend weight, and the safety correction coefficient. The fourth determining unit is used to determine the target laser wavelength in the working parameters based on the predicted value of the tissue absorption coefficient in the predicted trend of change.

[0083] In one embodiment, the fourth determining unit is configured to perform the following steps: Based on the predicted value of the tissue absorption coefficient, the current static absorption coefficient, and the static thickness of the micro-region, the penetration depth prediction result is determined; Based on the penetration depth prediction results, the target laser wavelength is obtained by substituting the tissue characteristic spectrum into the data.

[0084] In one embodiment, the adjustment module 40 is configured to perform the following steps: The target power density is mapped to a power control signal using a linear mapping formula; The penetration depth prediction result is mapped to a focusing lens control signal using a mapping formula between penetration depth and focusing lens; wherein, the focusing lens control signal includes a position control signal and / or an angle control signal.

[0085] In one embodiment, the expression for the network loss function is as follows: ; ; ; in, Indicates data loss; The physical loss is indicated and determined based on the constitutive equation; Indicates the balance coefficient; N indicates the number of training samples; Indicates the measured tissue characteristic values; Indicates predicted tissue characteristic values; Indicates the L2 norm; M indicates the number of physical constraint sampling points; Indicates the mechanical stress of the tissue; Indicates relaxation time; Indicates the dynamic elastic modulus; Instructions for organizational response.

[0086] Each module in the aforementioned laser therapy device operation control unit can be implemented entirely or partially through software, hardware, or a combination thereof. Each module can be embedded in the processor of the laser therapy device in hardware form or independent of it, or it can be stored in the memory of the laser therapy device in software form, so that the processor can call and execute the corresponding operations of each module.

[0087] In one embodiment, a laser therapy device is provided, the internal structure of which can be shown in the following diagram. Figure 4 As shown, the laser therapy device includes a processor, memory, communication interface, display unit, and input device connected via a method bus. The processor provides computational and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores operating methods and computer programs. The internal memory provides an environment for the operation of the operating methods and computer programs stored in the non-volatile storage medium. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a laser therapy device operation control method. The display screen can be an LCD screen or an e-ink screen. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the device's casing, or an external keyboard, touchpad, or mouse.

[0088] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the laser therapy device to which the present application is applied. A specific laser therapy device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0089] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps performed by the laser therapy device in the above embodiments.

[0090] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps performed by the processor of any of the above-described laser therapy devices.

[0091] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0092] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, compilable logic units, quantum computing-based data processing logic units, etc., and are not limited to these.

[0093] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0094] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A laser therapy device, characterized in that, It includes a processor and a memory; wherein the memory is used to store a computer program; and the processor performs the following steps when running the computer program: Acquire static and dynamic features of the target object; wherein the static features characterize the optical properties parameters of the target object; and the dynamic features characterize the dynamic changes of the target object during the treatment process. Based on the static and dynamic features, combined with the tissue characteristic map and the prediction model, the predicted trend of the target object is obtained; wherein, the tissue characteristic map includes the static feature baseline values ​​of different tissue types / skin textures and the historical change curves of the dynamic features over time; the prediction model is trained based on the constitutive equation of the target object; Based on the predicted trend, and combined with the energy gradient allocation algorithm, the working parameters for operating on each region of the target object are determined. Based on the operating parameters, the real-time parameters of the corresponding components in the laser therapy device are adjusted to complete the treatment of the target object.

2. The laser therapy device according to claim 1, characterized in that, The process of obtaining the predicted trend of the target object based on the static and dynamic features, combined with the tissue characteristic map and prediction model, includes: The static features are matched with the tissue characteristic map to obtain the target tissue category and the corresponding dynamic change benchmark trend; The static features and the dynamic features are input into the prediction model to obtain candidate change trend prediction results; The change trend prediction result is obtained based on the candidate change trend prediction result and the dynamic change benchmark trend.

3. The laser therapy device according to claim 1, characterized in that, The step of matching the static features with the tissue characteristic map to obtain the target tissue category and the corresponding dynamic change baseline trend includes: From the static features, key and non-core indicators are selected to match, and the similarity between the key matching indicators and the benchmark values ​​of static features in the tissue characteristic map is calculated. Candidate units are selected from the tissue characteristic map based on the similarity. When there are multiple candidate units, the fit of the non-core indicators is compared. Based on the fit, the target organization category is selected from the candidate units and the corresponding dynamic change benchmark trend is determined.

4. The laser therapy device according to claim 1, characterized in that, The prediction model is a physical information neural network; the training method of the prediction model includes: Acquire sample data and extract sample features; wherein, the sample features include static sample features and dynamic sample features; Based on the deformation and strain, mechanical properties and stress relaxation of the tissue under laser irradiation, the constitutive equation of the target object is constructed. The initial network is trained based on the sample features, and the constitutive equation is embedded as a constraint in the network loss function. The initial network is iterated until the loss value converges to obtain the prediction model.

5. The laser therapy device according to claim 1, characterized in that, Based on the predicted trend, and combined with the energy gradient allocation algorithm, the operating parameters for operating on each region of the target object are determined, including: The laser spot is divided into multiple independent micro-regions using a spot segmentation algorithm; Based on the predicted value of the tissue absorption coefficient in the predicted trend, determine the static feature weight and the dynamic trend weight. Based on the predicted temperature value in the trend prediction results, a safety correction factor is determined; The target power density in the operating parameters is determined based on the base power density of each independent micro-region, the static feature weight, the dynamic trend weight, and the safety correction coefficient. Based on the predicted value of the tissue absorption coefficient in the predicted trend, the target laser wavelength in the working parameters is determined.

6. The laser therapy device according to claim 4, characterized in that, The determination of the target laser wavelength in the working parameters based on the predicted tissue absorption coefficient value in the predicted trend results includes: Based on the predicted value of the tissue absorption coefficient, the current static absorption coefficient, and the static thickness of the micro-region, the penetration depth prediction result is determined; Based on the penetration depth prediction results, the target laser wavelength is obtained by substituting the tissue characteristic spectrum into the data.

7. The laser therapy device according to claim 4, characterized in that, The step of adjusting the real-time parameters of the corresponding components in the laser therapy device based on the operating parameters includes: The target power density is mapped to a power control signal using a linear mapping formula; The penetration depth prediction result is mapped to a focusing lens control signal using a mapping formula between penetration depth and focusing lens; wherein, the focusing lens control signal includes a position control signal and / or an angle control signal.

8. The laser therapy device according to claim 4, characterized in that, The expression for the network loss function is as follows: ； ； ； in, Indicates data loss; The physical loss is indicated and determined based on the constitutive equation; Indicates the balance coefficient; N indicates the number of training samples; Indicates the measured tissue characteristic values; Indicates predicted tissue characteristic values; Indicates the L2 norm; M indicates the number of physical constraint sampling points; Indicates the mechanical stress of the tissue; Indicates relaxation time; Indicates the dynamic elastic modulus; Instructions for organizational response.

9. A laser therapy instrument operation control device, characterized in that, Applied to a laser therapy device, the device includes: An acquisition module is used to acquire the static and dynamic features of a target object; wherein the static features characterize the optical properties parameters of the target object; and the dynamic features characterize the dynamic changes of the target object during the treatment process. The prediction module is used to obtain the predicted trend of the target object based on the static features and the dynamic features, combined with the tissue characteristic map and the prediction model; wherein, the tissue characteristic map includes the static feature baseline values ​​of different tissue types / skin textures and the historical change curves of the dynamic features over time; the prediction model is trained based on the constitutive equation of the target object; The analysis module is used to determine the working parameters for operating on each region of the target object based on the predicted trend and the energy gradient allocation algorithm. The adjustment module is used to adjust the real-time parameters of the corresponding components in the laser therapy device based on the operating parameters, so as to complete the treatment of the target object.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it performs the steps of the laser therapy device as described in any one of claims 1 to 8.

Images