Real-time analysis method and system for tunable 1200nm fiber laser irradiation therapy data

Abstract

The present invention provides a method and system for real-time analysis of tunable 1200nm fiber laser irradiation treatment data, which relates to the field of data processing technology. The method comprises: using a tunable 1200nm fiber laser to perform laser irradiation on a preset target area; obtaining the light intensity, temperature and response data of the target area during the laser irradiation in real time through a light sensor, a temperature sensor and a biological tissue response monitor; preprocessing the light intensity, temperature and response data of the biological tissue in the target area during the laser irradiation, including noise filtering, signal amplification and data calibration, to obtain processed data. The present invention realizes precise control of 1200nm fiber laser irradiation treatment and early warning of potential side effects by real-time analysis of laser irradiation data, thereby improving the treatment effect and safety.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a real-time analysis method and system for tunable 1200nm optical fiber laser irradiation treatment data. Background Art

[0002] In traditional fiber laser systems, data collection relies on independent sensor modules, which may have problems with the accuracy and synchronization of the collected data due to different specifications and response time differences. Especially in application scenarios that require high-speed operation or precise control, data inconsistency may directly affect the accuracy of subsequent analysis and limit the system's ability to respond quickly to dynamic changes. With the increase in fiber laser output power and the complexity of application scenarios, the amount of data generated has also increased dramatically. Traditional data processing methods, such as simple threshold judgment or offline analysis, can no longer meet the needs of real-time processing. This not only prolongs the time from data collection to decision making, but may also miss key information due to processing delays, affecting the overall performance of the system.

[0003] The operating parameters of fiber lasers need to be adjusted dynamically according to real-time conditions. However, traditional systems lack an effective intelligent feedback mechanism and cannot achieve automatic optimization of parameters. This requires operators to continuously monitor and adjust manually, which not only increases the workload, but may also lead to operational errors due to human factors, reducing the stability and reliability of the system. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a real-time analysis method and system for tunable 1200nm fiber laser irradiation treatment data, thereby improving the monitoring accuracy and dynamic adjustment capability of the operation process.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0006] In a first aspect, a method for real-time analysis of tunable 1200 nm fiber laser irradiation treatment data, the method comprising:

[0007] Using a tunable 1200nm fiber laser, the preset target area is laser irradiated;

[0008] The light intensity, temperature and biological tissue response data of the target area during laser irradiation are obtained in real time through light sensors, temperature sensors and biological tissue response monitors;

[0009] Preprocessing the light intensity, temperature and response data of biological tissues in the target area during laser irradiation, including noise filtering, signal amplification and data calibration, to obtain processed data;

[0010] Based on the processed data, an analysis model is constructed to extract key indicators during laser irradiation, including the absorption efficiency of laser by biological tissue, the temperature change rate, and potential side effect warning information;

[0011] Initialize the differential evolution parameters, including population size, mutation factor, and crossover probability, to generate an initial solution set, and evaluate the fitness of each individual in the initial solution set through an analytical model to obtain the fitness value of each individual;

[0012] According to the fitness value of each individual, determine the individuals in the current population for differential mutation and crossover to generate test individuals, and compare the fitness values ​​of the test individuals with the corresponding original individuals to determine the new generation of population;

[0013] The differential mutation and crossover operations and the new generation population determination are repeatedly performed until a preset number of iterations is reached to obtain an optimized solution. According to the optimized solution, the operating parameters of the fiber laser, including output power, wavelength or irradiation mode, are automatically and in real time adjusted.

[0014] Furthermore, the light intensity, temperature and response data of the biological tissue in the target area during the laser irradiation process are preprocessed, including noise filtering, signal amplification and data calibration, to obtain processed data, including:

[0015] Analyze the characteristics and noise types of light intensity, temperature, and biological tissue response data, and identify the noise types in the data, including Gaussian noise and salt and pepper noise;

[0016] According to the noise type, use mean filtering to remove the noise in the data, and set the parameters of the mean filtering, including the window size and threshold, to obtain the filtered data;

[0017] Analyze the amplitude of the filtered data to determine the signal amplification factor, and use the amplification factor to linearly amplify the filtered data to obtain amplified data;

[0018] The amplified data are calibrated using linear regression, and the processed data are obtained by comparing them with standard values ​​to eliminate systematic errors and offsets.

[0019] Furthermore, based on the processed data, an analysis model is constructed to extract key indicators during laser irradiation, including the absorption efficiency of laser by biological tissue, the temperature change rate, and potential side effect warning information, including:

[0020] From the processed data, characteristic data related to the laser irradiation process are determined, including the average and peak values ​​of the light intensity, the temperature variation trend, and the specific pattern of biological tissue response;

[0021] According to the determined characteristic data and analysis target related to the laser irradiation process, an analysis model is determined, and the characteristic data related to the laser irradiation process is divided into a training set and a verification set;

[0022] The analysis model is trained using the training set, and the analysis model parameters are adjusted until the preset training effect is achieved to obtain the trained analysis model; the trained analysis model is verified and evaluated using the validation set to obtain the evaluation results;

[0023] According to the evaluation results, the light intensity and biological tissue response data are analyzed using a verified analysis model, the regression coefficient between light intensity and biological tissue response is calculated, and the time series of temperature data is trended. During the analysis process, abnormal changes in the biological tissue response data, including tissue damage and inflammatory response, are continuously monitored to extract the biological tissue's absorption efficiency of the laser, the temperature change rate, and potential side effect warning information.

[0024] Furthermore, the regression coefficient calculation formula between light intensity and biological tissue response is: ;

[0025] in, Represents the regression coefficient between light intensity and biological tissue response; Indicates the number of data points; Indicates The light intensity value of each data point; Indicates The light intensity value of each data point; Indicates The biological tissue response value of data points; Indicates The biological tissue response value of data points; , , Represents an index variable.

[0026] Furthermore, the differential evolution parameters, including population size, mutation factor, and crossover probability, are initialized to generate an initial solution set, and the fitness of each individual in the initial solution set is evaluated through an analytical model to obtain the fitness value of each individual, including:

[0027] Determine the parameters contained in each individual in the initial solution set, including the output power, wavelength, and irradiation mode of the laser;

[0028] For each parameter, a value is randomly generated within the value range to form a solution vector. The random generation process is repeated until a preset number of solutions are obtained to obtain an initial solution set.

[0029] Each individual in the initial solution set is used as an input parameter and input into the analysis model;

[0030] The analysis model simulates the laser irradiation process according to the input parameters and outputs relevant data, including the absorption efficiency of the laser by the biological tissue and the temperature change;

[0031] According to the output related data, a fitness function is defined to calculate the fitness value of each individual in the initial solution set.

[0032] Furthermore, the fitness value calculation formula for each individual in the initial solution set is: ;

[0033] in, Represents the fitness value of each individual; , , , represents the weight coefficient; It indicates the absorption efficiency of laser by biological tissue; Indicates the rate of temperature change; Represents the first input parameters; Represents the first The weight coefficients of the input parameters; Indicates warning information about potential side effects.

[0034] Furthermore, according to the fitness value of each individual, the individuals in the current population are determined to perform differential mutation and crossover to generate test individuals, and the fitness values ​​of the test individuals are compared with the corresponding original individuals to determine the new generation population, including:

[0035] Randomly select two different individuals from the current population as basis vectors, calculate the difference between the two basis vectors, obtain the difference vector, adjust the difference vector, and combine it with the individuals in the current population to obtain the mutation vector;

[0036] Perform a crossover operation on the mutation vector and the individuals in the previous population to generate test individuals;

[0037] The fitness function is used to calculate the fitness value of the test individual, and the fitness value of the test individual is compared with the fitness value of the corresponding original individual to obtain a comparison result;

[0038] Based on the comparison results, the population is updated to form a new generation of population.

[0039] Second, the real-time analysis system for tunable 1200nm fiber laser irradiation treatment data includes:

[0040] The acquisition module is used to use a tunable 1200nm fiber laser to perform laser irradiation on a preset target area; obtain the light intensity, temperature and response data of the target area during the laser irradiation in real time through a light sensor, a temperature sensor and a biological tissue response monitor; pre-process the light intensity, temperature and response data of the biological tissue in the target area during the laser irradiation, including noise filtering, signal amplification and data calibration, to obtain processed data; construct an analysis model based on the processed data, and extract key indicators during the laser irradiation process, including the absorption efficiency of the biological tissue to the laser, the temperature change rate and potential side effect warning information;

[0041] The processing module is used to initialize the differential evolution parameters, including the population size, mutation factor, and crossover probability, to generate an initial solution set, and evaluate the fitness of each individual in the initial solution set through an analytical model to obtain the fitness value of each individual; according to the fitness value of each individual, determine the individuals in the current population to perform differential mutation and crossover, generate test individuals, and compare the fitness values ​​of the test individuals with those of the corresponding original individuals to determine a new generation of population; repeatedly perform differential mutation and crossover operations, and determine a new generation of population until a preset number of iterations is reached to obtain an optimized solution, and according to the optimized solution, automatically and in real time adjust the operating parameters of the fiber laser, including output power, wavelength or irradiation mode.

[0042] According to a third aspect, a computing device includes:

[0043] one or more processors;

[0044] The storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method described.

[0045] In a fourth aspect, a computer-readable storage medium stores a program, and when the program is executed by a processor, the method described is implemented.

[0046] The above solution of the present invention includes at least the following beneficial effects:

[0047] By acquiring the light intensity, temperature and response data of biological tissues in the target area during laser irradiation in real time, and performing refined preprocessing and analysis, the effect of laser treatment can be accurately evaluated. This helps doctors or therapists adjust treatment parameters based on real-time feedback, thereby improving the accuracy and effectiveness of treatment. This method can monitor the absorption efficiency of lasers by biological tissues, the rate of temperature change, and potential side effect warning information in real time. This helps to promptly detect and deal with possible safety issues, such as overheating and tissue damage, thereby ensuring the safety of laser treatment.

[0048] By iteratively optimizing the initial solution set through the differential evolution algorithm, the operating parameters of the fiber laser, including output power, wavelength or irradiation mode, can be adjusted automatically and in real time. This helps to find the optimal parameter combination suitable for the current treatment situation, thereby further improving the treatment effect. Real-time data analysis and parameter optimization can reduce the trial and error and adjustment time during the treatment process, thereby speeding up the treatment process and improving the overall treatment efficiency. Through real-time data analysis and parameter adjustment, a personalized treatment plan can be provided for each patient. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a flow chart of a method for real-time analysis of tunable 1200nm fiber laser irradiation therapy data provided by an embodiment of the present invention.

[0050] Figure 2 It is a schematic diagram of a real-time analysis system for tunable 1200nm fiber laser irradiation therapy data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0052] like Figure 1 As shown, an embodiment of the present invention provides a method for real-time analysis of tunable 1200nm fiber laser irradiation treatment data, the method comprising the following steps:

[0053] Step 11, using a tunable 1200nm fiber laser to irradiate a preset target area;

[0054] Step 12, obtaining the light intensity, temperature and response data of the biological tissue in the target area during the laser irradiation process in real time through the light sensor, temperature sensor and biological tissue response monitor;

[0055] Step 13, preprocessing the light intensity, temperature and response data of the biological tissue in the target area during the laser irradiation process, including noise filtering, signal amplification and data calibration, to obtain processed data;

[0056] Step 14, constructing an analysis model based on the processed data, and extracting key indicators during the laser irradiation process, including the absorption efficiency of the biological tissue to the laser, the temperature change rate, and potential side effect warning information;

[0057] Step 15, initializing differential evolution parameters, including population size, mutation factor, and crossover probability, to generate an initial solution set, and evaluating the fitness of each individual in the initial solution set through an analytical model to obtain a fitness value of each individual;

[0058] Step 16, according to the fitness value of each individual, determine the individuals in the current population to perform differential mutation and crossover, generate test individuals, and compare the fitness values ​​of the test individuals with the corresponding original individuals to determine the new generation population;

[0059] Step 17, repeatedly performing differential mutation and crossover operations, and determining a new generation population, until a preset number of iterations is reached to obtain an optimized solution, and automatically and in real time adjust the operating parameters of the fiber laser, including output power, wavelength or irradiation mode, according to the optimized solution.

[0060] In an embodiment of the present invention, the light intensity, temperature and response data of biological tissues in the target area during laser irradiation can be obtained in real time and accurately through optical sensors, temperature sensors and biological tissue response monitors. This allows the treatment process to be accurately monitored to ensure the accuracy and effectiveness of laser irradiation. The data obtained in real time is preprocessed and analyzed, an analysis model is constructed, and key indicators are extracted. These key indicators provide data-driven decision support for doctors or therapists, helping them to adjust treatment strategies according to real-time conditions. By real-time monitoring of the absorption efficiency of biological tissues for lasers, the rate of temperature change and potential side effect warning information, safety issues can be discovered and handled in a timely manner, which helps to reduce side effects such as tissue damage and overheating, and improve the safety and effectiveness of treatment.

[0061] The initial solution set is iteratively optimized using a differential evolution algorithm to automatically and in real time adjust the operating parameters of the fiber laser. This intelligent parameter optimization method can find the optimal parameter combination that best suits the current treatment situation, further improving the treatment effect. Real-time data analysis and parameter optimization allow the treatment process to be adjusted according to the specific situation of each patient. This helps to achieve personalized treatment and meet the treatment needs of different patients. Real-time data monitoring and parameter optimization can reduce trial and error and adjustment time during treatment and improve treatment efficiency. At the same time, by precisely controlling the parameters of laser irradiation, energy consumption and costs can be reduced.

[0062] In a preferred embodiment of the present invention, the above step 11, using a tunable 1200nm fiber laser to perform laser irradiation on a preset target area; the above step 12, using a light sensor, a temperature sensor and a biological tissue response monitor to obtain in real time the light intensity, temperature and biological tissue response data of the target area during the laser irradiation process, may include:

[0063] Use a tunable 1200nm fiber laser to set the initial laser parameters (such as output power, wavelength, irradiation mode, etc.) according to the treatment needs. Aim the output end of the laser at the preset target area, such as skin lesions, tumor tissue, etc., for precise laser irradiation. Place it near the target area or on the laser irradiation path to monitor the changes in light intensity during laser irradiation in real time. This helps to ensure the stability and accuracy of laser irradiation. Attach it to the target area or embed it in biological tissue (such as through minimally invasive means) to monitor the temperature changes caused by laser irradiation in real time. This helps to evaluate the effect of laser treatment and prevent tissue damage caused by overheating. Biological tissue response monitors include spectrometers, imaging equipment, etc., which are used to monitor the response of biological tissues to laser irradiation, such as spectral changes, morphological changes, etc. This helps to evaluate the efficacy of laser treatment and detect potential side effects in a timely manner.

[0064] Taking the treatment of skin lesions as an example, suppose a patient has a skin hemangioma and needs to be treated with a tunable 1200nm fiber laser. According to the size, location, and depth of the hemangioma, the laser parameters are set, such as lower output power to avoid excessive damage to surrounding tissues, specific wavelengths to match the absorption characteristics of the hemangioma, and continuous irradiation mode to ensure uniformity of treatment. The output end of the laser is aimed at the hemangioma area for precise laser irradiation. The optical sensor monitors the light intensity changes during laser irradiation in real time to ensure the stability and accuracy of the laser beam and avoid the influence of light intensity fluctuations on the treatment effect. The temperature sensor is attached to the skin near the hemangioma area to monitor the temperature changes caused by laser irradiation in real time. The doctor adjusts the laser parameters according to the temperature changes to ensure the effectiveness and safety of the treatment. The biological tissue response monitor (such as a spectrometer) is used to monitor the spectral changes in the hemangioma area to evaluate the efficacy of laser treatment. If the spectrum changes significantly, it may indicate that the hemangioma is being effectively destroyed.

[0065] In a preferred embodiment of the present invention, the above step 13, pre-processing the light intensity, temperature and response data of the biological tissue in the target area during the laser irradiation process, including noise filtering, signal amplification and data calibration to obtain processed data, may include:

[0066] Step 133, analyzing the characteristics and noise types of the light intensity, temperature, and biological tissue response data, and identifying the noise types in the data, including Gaussian noise and salt and pepper noise;

[0067] Step 134, according to the noise type, use mean filtering to remove the noise in the data, and set the parameters of the mean filtering, including the window size and threshold, to obtain filtered data;

[0068] Step 135, analyzing the amplitude of the filtered data, determining the signal amplification factor, and using the amplification factor to linearly amplify the filtered data to obtain amplified data;

[0069] Step 136, using linear regression, calibrates the amplified data, and eliminates system errors and offsets by comparing with standard values ​​to obtain processed data.

[0070] In the embodiment of the present invention, the light intensity data is analyzed for its changing trend over time to identify whether there are periodic fluctuations or sudden changes. For the temperature data, its rising and falling rates and stable state are observed to determine the effect of laser irradiation on temperature. For the biological tissue response data (such as spectrum, image, etc.), the response characteristics and their association with laser irradiation are analyzed according to their specific forms. By calculating the standard deviation of the data and mean , observe whether the data distribution is close to the normal distribution , identify the existence of Gaussian noise. The calculation formula of the standard deviation is: ;in, Indicates the number of values ​​in the data; Represents an index variable; Indicates the first numerical values; represents the mean of the data. Calculate the mean and standard deviation After that, we can draw a histogram of the data and compare it with the theoretical normal distribution. If the data points are roughly distributed around the mean Centered, standard deviation If the data is on a bell-shaped curve with a width of , then it can be considered that the data is close to a normal distribution, thus identifying the presence of Gaussian noise. Check whether there are extreme outliers in the data, which are much higher or much lower than other data points, by setting a threshold To identify, that is The data points are considered as salt and pepper noise. For Gaussian noise, select mean filtering. The formula for mean filtering is: ;in, It means the signal after mean filtering at time The smoothing value of Indicates the window size of the mean filter; Represents the original signal at time For salt and pepper noise, select median filtering. The formula for median filtering is: ;in, It means the signal after median filtering at time The smoothing value of Represents the index of the sample point; Represents the original signal at time The value of Represents the set of all sample points in the window. Adaptive filtering adjusts the filter parameters according to the local characteristics of the data. Select the appropriate window size according to the fluctuation of the data and the noise intensity. Set the threshold to control the identification of noise points in the filter, and obtain the filtered data, light intensity, temperature, and biological tissue response data.

[0071] Analyze the amplitude of the filtered data to determine the dynamic range of the data . Choose the appropriate magnification based on the dynamic range and subsequent processing requirements The selection of the magnification factor should ensure that the amplified data does not exceed the range of the processing system and can fully display the detailed characteristics of the data. The filtered data is linearly amplified using the determined magnification factor, and the formula is: ;in, It means that the signal after linear amplification is at time The value of Indicates the amplification factor, which is used to control the degree of signal amplification. >1, the signal is amplified; when 0< <1, the signal is attenuated; when =1, the signal remains unchanged; It means the signal after filtering at time The value of is the smoothed signal obtained by any filtering method (such as mean filtering, median filtering, etc.). The amplified data is calibrated using methods such as linear regression. The formula for linear regression is: ;in, Indicates the calibrated data; , represents the linear regression coefficient; Indicates the signal after linear amplification. During the calibration process, the known standard value is used as a reference. If it is found that there are still large errors or inconsistencies in the calibrated data, it is necessary to readjust the filter parameters, amplification factor or calibration method, and repeat the above steps until a satisfactory result is obtained.

[0072] Taking laser treatment of skin lesions as an example, assume that during the laser irradiation process, data on light intensity, temperature, and skin tissue response (such as spectral changes) are obtained. Analysis of the light intensity data shows that there is slight Gaussian noise, which may be caused by the instability of the laser source or the measurement error of the light sensor. Analysis of the temperature data shows that there is salt and pepper noise, which may be caused by external interference or data transmission errors in the temperature sensor during the measurement process. Analysis of the skin tissue response data shows that the data is relatively stable, but there is a slight offset, which may be caused by system errors. Mean filtering is applied to the light intensity data, with a window size of 5 and a threshold of 0.1 to smooth the data and remove Gaussian noise. Median filtering is applied to the temperature data, with a window size of 3 to remove salt and pepper noise and retain the authenticity of the data. The filtered light intensity data and temperature data are analyzed to determine that the signal amplification factor is 2 to enhance the useful signal and facilitate subsequent processing. The amplification factor is used to linearly amplify the filtered data to obtain the amplified data. The amplified light intensity data and temperature data are calibrated using the linear regression method. By comparing with known standard light intensity and temperature values, systematic errors and offsets can be eliminated. The calibrated data should more accurately reflect the changes in light intensity and temperature during laser irradiation, providing a reliable basis for subsequent treatment evaluation and parameter adjustment.

[0073] By analyzing the characteristics and noise types, Gaussian noise and salt and pepper noise in the data can be accurately identified. The mean filtering method can be used to remove noise in the data according to the noise type, effectively improving the signal-to-noise ratio of the data. A detailed analysis of the amplitude of the filtered data can determine the appropriate signal amplification factor. Linear amplification can enhance the strength of useful signals and also help extract more useful information. The amplified data is calibrated using the linear regression method, and by comparing it with the standard value, the system error and offset can be accurately eliminated. The optimization of the preprocessing process, including noise filtering, signal amplification, and data calibration, can improve the efficiency of data processing.

[0074] In a preferred embodiment of the present invention, the above step 14, based on the processed data, constructs an analysis model and extracts key indicators in the laser irradiation process, including the absorption efficiency of the laser by the biological tissue, the temperature change rate and potential side effect warning information, which may include:

[0075] Step 141, determining characteristic data related to the laser irradiation process from the processed data, including the average value and peak value of the light intensity, the temperature variation trend, and the specific pattern of biological tissue response;

[0076] Step 142, determining an analysis model according to the determined characteristic data related to the laser irradiation process and the analysis target, and dividing the characteristic data related to the laser irradiation process into a training set and a validation set;

[0077] Step 143, using the training set to train the analysis model and adjusting the analysis model parameters until a preset training effect is achieved to obtain a trained analysis model; using the validation set to validate and evaluate the trained analysis model to obtain an evaluation result;

[0078] Step 144, based on the evaluation results, the light intensity and biological tissue response data are analyzed using a verified analysis model, the regression coefficient between the light intensity and the biological tissue response is calculated, and a trend analysis is performed on the time series of the temperature data. During the analysis process, abnormal changes in the biological tissue response data, including tissue damage and inflammatory response, are continuously monitored to extract the biological tissue's absorption efficiency of the laser, the temperature change rate, and potential side effect warning information.

[0079] In an embodiment of the present invention, characteristic data related to the laser irradiation process are determined from the processed data. These characteristic data include the average and peak values ​​of light intensity, which help to understand the intensity distribution of the laser; the temperature change trend, which reflects the thermal effect of laser irradiation on the tissue; and the specific mode of biological tissue response, such as spectral changes, which provides direct information on the tissue's response to the laser. According to the determined characteristic data and the analysis target (i.e., extracting the absorption efficiency of biological tissue to the laser, the temperature change rate, and potential side effect warning information), an analysis model is selected. For example, a multivariate linear regression model is used to analyze the relationship between light intensity and biological tissue response, and a time series analysis model is used to study the temperature change trend. The characteristic data is divided into a training set and a validation set. The training set is used to train the model, and the validation set is used to evaluate the performance of the model. The analysis model is trained using the training set, and the model parameters are adjusted until the preset training effect is achieved. For example, the parameters of the regression model can be optimized by minimizing the prediction error. The trained analysis model is verified and evaluated using the validation set to obtain an evaluation result. The evaluation result includes indicators such as the accuracy and recall rate of the model, which are used to determine whether the performance of the model meets the requirements. Based on the evaluation results, the light intensity and biological tissue response data are analyzed using a validated analysis model. The regression coefficient between light intensity and biological tissue response is calculated, which helps to understand the mechanism of laser action on tissue.

[0080] Trend analysis is performed on the time series of temperature data to extract key information such as the temperature change rate. During the analysis, abnormal changes in biological tissue response data, such as tissue damage and inflammatory response, are continuously monitored. These abnormal changes may indicate potential side effects, so timely warnings are required.

[0081] Suppose a study on laser treatment of skin lesions is underway, and the goal is to determine the laser parameters to maximize the treatment effect and minimize side effects. Data on light intensity, temperature, and skin tissue response during laser irradiation are collected and preprocessed to remove noise and errors. The average and peak values ​​of light intensity, the trend of temperature changes, and specific patterns of skin tissue response (such as spectral changes) are extracted from the preprocessed data as feature data. A multivariate linear regression model and a time series analysis model are constructed, and the models are trained using the training set. The prediction performance of the model is optimized by adjusting the model parameters, and the model is verified and evaluated using the validation set. The light intensity and skin tissue response data are analyzed using the trained analysis model, and the regression coefficients are calculated to understand the intensity of the laser effect on the skin. Trend analysis is performed on the time series of temperature data to extract key information such as the temperature change rate to evaluate the thermal effect of laser irradiation on the skin. During the analysis process, abnormal changes in the skin tissue response data, such as inflammatory reactions such as redness, swelling, and pain, and potential side effects such as tissue damage, are continuously monitored. Based on the extracted key indicators and monitoring results, the laser parameters and treatment plan are determined to maximize the treatment effect and minimize side effects.

[0082] Through the analysis model, the absorption efficiency of laser by biological tissue can be accurately calculated, which helps to adjust the laser parameters to ensure that the laser energy is effectively absorbed by the tissue, thereby improving the treatment effect. The accurate extraction of the temperature change rate can better control the thermal effect generated during laser irradiation, avoid damage to the tissue due to overheating, and ensure that the treatment temperature achieves the best effect. The analysis model can continuously monitor abnormal changes in biological tissue response data, such as tissue damage and inflammatory response. This helps to detect potential side effects in a timely manner and take appropriate measures to intervene, thereby reducing the risk during treatment. By analyzing the regression coefficient between light intensity and biological tissue response, the effect of different light intensities on tissues can be understood. This helps to achieve personalized treatment and improve the pertinence and accuracy of treatment effects. The constructed analysis model can automatically process and analyze a large amount of laser irradiation process data and quickly extract key indicators. This improves the efficiency of data analysis and processing.

[0083] In a preferred embodiment of the present invention, the regression coefficient calculation formula between light intensity and biological tissue response is: ;

[0084] in, Represents the regression coefficient between light intensity and biological tissue response; Indicates the number of data points; Indicates The light intensity value of each data point; Indicates The light intensity value of each data point; Indicates The biological tissue response value of data points; Indicates The biological tissue response value of data points; , , Represents an index variable.

[0085] In an embodiment of the present invention, data on light intensity and biological tissue response during laser irradiation are collected. Ensure that the number of data points is known, and each data point has a corresponding light intensity value and biological tissue response value . Calculate the mean of the light intensity data: . Calculate the mean of biological tissue response data: For each data point, calculate , and sum to get the numerator: For each data point, calculate , and sum to get the denominator: Using the calculated numerator and denominator, calculate the regression coefficient according to the formula .

[0086] Assume there are the following 4 data points:

[0087]

[0088] Calculate the mean:

[0089] Light intensity average ;

[0090] Mean biological tissue response ;

[0091] Calculate the numerator part: ;

[0092] ;

[0093] ;

[0094] ;

[0095] Numerator = 56.25 + 6.25 + 6.25 + 56.25 = 125.

[0096] Calculate the denominator: ;

[0097] ;

[0098] Denominator = 56.25 + 6.25 + 6.25 + 56.25 = 125.

[0099] Calculate the regression coefficient: That is, the regression coefficient between light intensity and biological tissue response is 1, indicating that light intensity and biological tissue response.

[0100] Regression coefficient Provides a quantitative indicator to describe the strength and direction of the relationship between light intensity and biological tissue response. This helps researchers understand more accurately how lasers affect biological tissues and how this effect changes at different light intensities. Through the regression coefficient, a predictive model can be established to predict the response of biological tissues at a given light intensity. The regression coefficient can help determine the optimal range of light intensity to achieve the desired biological tissue response. This helps reduce unnecessary tissue damage while ensuring the effectiveness of the treatment. By optimizing the light intensity, the safety and efficiency of laser treatment can be improved. By analyzing the regression coefficients of different patients, more personalized laser treatment can be achieved. Because biological tissues of different patients may have different responses to lasers, adjusting treatment parameters according to individual regression coefficients can improve the targeting and effectiveness of treatment. In the research and development and production of laser medical equipment, regression coefficients can be used for quality control and effect evaluation. By measuring and comparing the regression coefficients of different devices or under different conditions, the consistency of device performance and treatment effects can be ensured.

[0101] In a preferred embodiment of the present invention, the above step 15, initializing the differential evolution parameters, including population size, mutation factor, and crossover probability, to generate an initial solution set, and evaluating the fitness of each individual in the initial solution set through an analytical model to obtain the fitness value of each individual, may include:

[0102] Step 155, determining the parameters contained in each individual in the initial solution set, including the output power, wavelength, and irradiation mode of the laser;

[0103] Step 156, for each parameter, randomly generate a value within the value range to form a solution vector, and repeat the random generation process until a preset number of solutions are obtained to obtain an initial solution set;

[0104] Step 157, input each individual in the initial solution set as an input parameter into the analysis model;

[0105] Step 158, the analysis model simulates the laser irradiation process according to the input parameters, and outputs relevant data, including the absorption efficiency of the biological tissue to the laser and the temperature change;

[0106] Step 159, defining a fitness function according to the output related data to calculate the fitness value of each individual in the initial solution set.

[0107] In an embodiment of the present invention, the population size refers to the number of individuals in the initial solution set. An appropriate population size is selected. For example, it can be set to 50 or 100. The mutation factor is used to control the degree of mutation in the differential evolution process. It is a real number between 0 and 1. For example, it can be set to 0.5 or 0.8. The crossover probability is used to determine whether to accept the mutated individual in the crossover operation. It is also a real number between 0 and 1. For example, it can be set to 0.7 or 0.9. The parameters contained in each individual include the output power, wavelength and irradiation mode of the laser. These parameters together define a laser irradiation scheme. For each parameter, a value is randomly generated within its value range. For example, the output power may range from 0 to 100 watts, the wavelength may range from 400 to 800 nanometers, and the irradiation mode may be continuous irradiation or pulsed irradiation (which can be represented by 0 and 1). The randomly generated values ​​are combined into a solution vector to represent an individual. Repeat this process until a preset number of solutions are obtained to obtain an initial solution set. Each individual in the initial solution set is used as an input parameter and input into the analysis model. The analytical model simulates the laser irradiation process according to the input parameters and outputs relevant data, including the absorption efficiency of the laser by the biological tissue and the temperature change. Based on the output relevant data, the fitness function is defined. The fitness function should be able to reflect the effect of the laser irradiation scheme. For example, it can be defined as the weighted sum of the absorption efficiency and the temperature change. The fitness function is used to calculate the fitness value of each individual in the initial solution set.

[0108] Suppose there is a differential evolution algorithm for optimizing laser irradiation scheme. Initialization parameters, population size 50; mutation factor 0.6; crossover probability 0.8; generate initial solution set, individual 1: [50 watts, 600 nanometers, continuous irradiation]; individual 2: [80 watts, 750 nanometers, pulsed irradiation]... individual 50: [30 watts, 550 nanometers, continuous irradiation] Input individual 1 into the analysis model, and get an absorption efficiency of 0.8 and a temperature change of 10 degrees. Suppose the fitness of individual 1 is calculated to be 0.66. Repeat this process to calculate the fitness value of each individual in the initial solution set.

[0109] By randomly generating an initial solution set, the differential evolution algorithm can conduct an extensive search throughout the solution space, making it more likely to find the final solution. Each individual in the initial solution set contains different parameter combinations, which increases the diversity of solutions. A highly diverse solution set helps the algorithm produce more diverse offspring in subsequent iterations, thereby increasing the chances of finding a high-quality solution. By simulating the laser irradiation process through an analytical model and outputting key data such as the absorption efficiency of the laser by biological tissues and temperature changes, the fitness of each individual can be accurately evaluated. This ensures that the algorithm can perform selection, crossover and mutation operations based on accurate information, thereby optimizing the solution more effectively. With the initial solution set and fitness evaluation, the differential evolution algorithm can converge to a high-quality solution more quickly. Because the algorithm can sort and select individuals based on fitness values, it can prioritize retaining excellent individuals and eliminate inferior individuals, thereby accelerating the optimization process. As a quantitative indicator, the fitness value can intuitively reflect the quality of each individual. This helps researchers sort, compare and select solutions, making it easier to find the optimal solution or satisfactory solution. By optimizing the output power, wavelength, and irradiation mode of the laser using the differential evolution algorithm, a more efficient laser irradiation scheme can be obtained. This helps to improve the effect and safety of laser treatment and reduce unnecessary tissue damage. The generation of the initial solution set and the fitness evaluation process can provide useful information for the improvement of the differential evolution algorithm. For example, by analyzing the characteristics of high-quality solutions and low-quality solutions in the initial solution set, the algorithm parameters can be adjusted or the operation strategy can be improved, thereby improving the performance and efficiency of the algorithm.

[0110] In a preferred embodiment of the present invention, the fitness value calculation formula of each individual in the initial solution set is: ;

[0111] in, Represents the fitness value of each individual; , , , represents the weight coefficient; It indicates the absorption efficiency of laser by biological tissue; Indicates the rate of temperature change; Represents the first input parameters; Represents the first The weight coefficients of the input parameters; Indicates warning information about potential side effects.

[0112] In the embodiment of the present invention, the weight coefficient is determined , , and These coefficients are used to balance the importance of absorption efficiency, temperature change rate, input parameters and potential side effects in the calculation of fitness value. For each individual in the initial solution set, it is input as an input parameter to the analysis model. The analysis model outputs the absorption efficiency of the biological tissue for the laser and temperature change rate For each individual, there are three input parameters , and (corresponding to the output power, wavelength and irradiation mode of the laser, respectively). Each input parameter has a corresponding weight coefficient , and . Calculates the weighted sum of the input parameters ,in From 1 to 3. The analysis model also outputs a potential side effect warning message , which is used to reflect the risk of side effects that may occur during laser irradiation. According to the formula, the fitness value of each individual is calculated.

[0113] Assume that there are the following individuals and their parameters in the initial solution set:

[0114] Instance 1: (Indicates output power 50 watts, wavelength 600 nanometers, continuous irradiation).

[0115] Instance 2: represents an output power of 80 W, a wavelength of 750 nm, and pulsed irradiation). Also, the following weighting coefficients and model outputs have been determined:

[0116] Weight coefficient: .

[0117] Model output (assumed values):

[0118] Instance 1: .

[0119] Instance 2: .

[0120] Input parameter weight coefficients (assumed values): . Now, the fitness value of each individual can be calculated:

[0121] The fitness value of individual 1 is: (Round to three decimal places).

[0122] The fitness value of individual 2 is: Round to three decimal places).

[0123] By setting different weight coefficients and input parameter weights , the fitness of individuals can be personalized for different application scenarios and needs. This improves the flexibility and pertinence of the evaluation. A quantitative evaluation standard allows the fitness value of each individual to be specifically calculated and compared. This helps researchers to more intuitively understand the pros and cons of each individual and make more accurate decisions. By calculating the fitness value of each individual, the differential evolution algorithm can be guided to perform selection, crossover and mutation operations, thereby accelerating the optimization process and finding the final solution. By optimizing parameters such as the output power, wavelength and irradiation mode of the laser, the absorption efficiency and temperature change rate of biological tissues to the laser can be improved, while reducing potential side effects. Various parameters (such as absorption efficiency, temperature change rate, etc.) can be measured and verified through experiments. This makes the evaluation process more reliable and accurate.

[0124] In a preferred embodiment of the present invention, the above step 16, according to the fitness value of each individual, determines the individuals in the current population to perform differential mutation and crossover, generates test individuals, and compares the fitness values ​​of the test individuals with the corresponding original individuals to determine the new generation population, which may include:

[0125] Step 166, randomly select two different individuals from the current population as basis vectors, calculate the difference between the two basis vectors to obtain a differential vector, and adjust the differential vector and combine it with the individuals in the current population to obtain a mutation vector;

[0126] Step 167, performing a crossover operation on the mutation vector and the individuals in the previous population to generate a test individual;

[0127] Step 168, using the fitness function to calculate the fitness value of the test individual, and comparing the fitness value of the test individual with the fitness value of the corresponding original individual to obtain a comparison result;

[0128] Step 169, based on the comparison result, update the population to form a new generation population.

[0129] In this embodiment of the present invention, two different individuals are randomly selected from the current population as basis vectors, denoted as and . Calculate the difference between the two basis vectors and get the difference vector The difference vector is adjusted by multiplying it by a scaling factor , to control the degree of variation. Select another individual in the current population (and or The adjusted difference vector is compared with Combined, we get the mutation vector . For the mutation vector and individuals in the previous population Perform crossover operation to generate experimental individuals The crossover operation is performed by a crossover probability To determine, for each dimension of the vector, The probability of selecting a mutation vector The corresponding dimension value of The corresponding dimension value of . Use the fitness function to calculate the test individual The fitness value of the test individual The fitness value of the corresponding original individual The fitness value of for , otherwise keep .

[0130] Repeat the above process until all individuals in the current population are traversed to form a new generation of population.

[0131] Assume that there are three individuals in the current population, and their parameter vectors (corresponding to the output power, wavelength, and irradiation mode of the laser) and fitness values ​​are as follows:

[0132] Individual 1 , fitness value: 0.8.

[0133] Individual 2 , fitness value: 0.75.

[0134] Instance 3 , fitness value: 0.7. Perform differential mutation and crossover operations:

[0135] Randomly select individual 1 and individual 2 as basis vectors. Calculate the difference vector . Adjust the difference vector, assuming the scaling factor F = 0.5 , then the adjusted difference vector . Select individual 3 as the combination object. Mutation vector Assuming the crossover probability . For the mutation vector Crossover with individual 3, assuming that the generated experimental individual (Here we assume that the first two dimensions are The probability selects the value of the mutation vector, while the last dimension retains the value of the original individual).

[0136] Use the fitness function to calculate the test individuals The fitness value of is assumed to be 0.85. The fitness value (0.85) and the original individual The fitness value of is (0.7). The fitness value of is better, so replace for . Therefore, the individuals in the new generation population are:

[0137] Instance 1: , fitness value: 0.8.

[0138] Instance 2: , fitness value: 0.75.

[0139] By randomly selecting a basis vector and calculating a differential vector, and then combining it with individuals in the current population to generate a mutation vector, this process introduces new gene combinations and enhances the diversity of the population. The differential mutation operation utilizes the difference information between the two basis vectors, which helps the algorithm approach the final solution faster. By adjusting the differential vector and combining it with individuals in the current population, a mutation vector that is closer to the optimal solution can be generated, thereby accelerating the convergence process of the algorithm. The crossover operation generates new trial individuals by combining the mutation vector with individuals in the previous population. These trial individuals may have a better gene combination, thereby improving the quality of the solution. By comparing the fitness values ​​of the trial individuals and the original individuals, better individuals can be selected to enter the new generation population to further improve the quality of the solution. Due to the randomness of the differential mutation and crossover operations, the algorithm can continuously introduce new gene combinations during the search process, which helps to avoid the algorithm from converging to the local optimal solution too early. By continuously updating the population, the algorithm can continue to explore the search space. Through differential mutation and crossover operations, the algorithm can more effectively utilize the fitness information of individuals to guide the search process. This helps to reduce invalid searches and improve the efficiency of the algorithm. At the same time, by comparing the fitness values ​​of the test individuals and the original individuals, better individuals can be quickly screened out, further accelerating the convergence of the algorithm. Differential mutation and crossover operations are basic operations in optimization algorithms such as differential evolution algorithms, which are easy to implement and expand. By adjusting parameters (such as scaling factors, crossover probability, etc.), the search behavior and performance of the algorithm can be flexibly controlled.

[0140] In a preferred embodiment of the present invention, the above step 17, repeatedly performing the differential mutation and crossover operations, and determining the new generation population, until a preset number of iterations is reached to obtain an optimized solution, and automatically and in real time adjusting the operating parameters of the fiber laser, including the output power, wavelength or irradiation mode, according to the optimized solution, may include:

[0141] Determine the search range of the fiber laser operating parameters, such as the possible value range of output power, wavelength and irradiation mode. Randomly generate an initial population, in which each individual represents a specific set of operating parameter combinations. Define a fitness function that calculates the fitness value of each individual based on the performance indicators of the fiber laser (such as cutting efficiency, heat affected zone size, processing accuracy, etc.). Evaluate each individual in the initial population to obtain its fitness value. Randomly select two different individuals in the current population as basis vectors. Calculate the difference between the two basis vectors to obtain the difference vector, and scale the difference vector. Select another individual in the current population and combine the adjusted difference vector with it to generate a mutation vector. Perform a crossover operation on the mutation vector and the original individual, and determine which dimensions come from the mutation vector and which dimensions come from the original individual based on the crossover probability, thereby generating a test individual.

[0142] Use the fitness function to evaluate the fitness value of the test individual. Compare the fitness value of the test individual with the fitness value of the corresponding original individual. If the fitness value of the test individual is better, replace the original individual with the test individual; otherwise, retain the original individual. Repeat the above process until all individuals in the current population are traversed to form a new generation of population. Repeat the steps of differential mutation and crossover operation and determination of the new generation of population until the preset number of iterations is reached. After reaching the preset number of iterations, determine the optimized solution, that is, the combination of operating parameters, based on the fitness value of the individual. According to the optimized solution, the operating parameters of the fiber laser are automatically and real-time adjusted through the control system.

[0143] Suppose you need to optimize the operating parameters of a fiber laser for metal cutting. The steps are as follows:

[0144] Determine the search range, the output power is 100-500W, the wavelength is 900-1100nm, and the irradiation mode is continuous or pulsed. Randomly generate 100 individuals as the initial population, each of which represents a specific set of operating parameter combinations. Calculate the fitness value based on the cutting efficiency, cutting surface roughness, and heat affected zone size. Perform cutting experiments on each individual in the initial population to evaluate its fitness value. Select two basis vectors, such as [200W, 1000nm, continuous] and [400W, 950nm, pulsed]. Calculate the difference vector and scale it, such as [200-400, 1000-950, (continuous-pulsed) numerical representation], and make appropriate adjustments. Select another individual, such as [300W, 980nm, continuous], and combine it with the adjusted difference vector to generate a mutation vector.

[0145] Perform crossover operations on the mutation vector and the original individual to generate a test individual. Perform a cutting experiment on the test individual to evaluate its fitness value. If the test individual is better than the original individual, replace the original individual; otherwise, keep the original individual. Repeat this process until all individuals are traversed to form a new generation of population. Repeat the above steps until the preset number of iterations (such as 1000 times) is reached. Select the individual with the highest fitness value from the final population as the optimal operating parameter combination, such as [350W, 970nm, pulse]. Send the optimized parameters to the control system of the fiber laser to automatically adjust its operating parameters for efficient cutting.

[0146] like Figure 2 As shown, the embodiment of the present invention also provides a tunable 1200nm fiber laser irradiation treatment data real-time analysis system 20, comprising:

[0147] The acquisition module 21 is used to use a tunable 1200nm fiber laser to perform laser irradiation on a preset target area; obtain the light intensity, temperature and response data of the target area in the laser irradiation process in real time through a light sensor, a temperature sensor and a biological tissue response monitor; pre-process the light intensity, temperature and response data of the biological tissue in the target area in the laser irradiation process, including noise filtering, signal amplification and data calibration, to obtain processed data; construct an analysis model based on the processed data, and extract key indicators in the laser irradiation process, including the absorption efficiency of the biological tissue to the laser, the temperature change rate and potential side effect warning information;

[0148] The processing module 22 is used to initialize the differential evolution parameters, including the population size, the mutation factor, and the crossover probability, to generate an initial solution set, and evaluate the fitness of each individual in the initial solution set through an analytical model to obtain the fitness value of each individual; according to the fitness value of each individual, determine the individuals in the current population to perform differential mutation and crossover, generate test individuals, and compare the fitness values ​​of the test individuals with those of the corresponding original individuals to determine a new generation of population; repeat the differential mutation and crossover operations and determine the new generation of population until a preset number of iterations is reached to obtain an optimized solution, and according to the optimized solution, automatically and in real time adjust the operating parameters of the fiber laser, including the output power, wavelength or irradiation mode.

[0149] It should be noted that the system is a system corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0150] The embodiment of the present invention further provides a computing device, comprising: a processor, a memory storing a computer program, wherein when the computer program is executed by the processor, the method described above is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0151] The embodiment of the present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the method described above. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0152] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A real-time analysis method for tunable 1200nm fiber laser irradiation treatment data, characterized in that: The method comprises: Using a tunable 1200nm fiber laser, the preset target area is laser irradiated; Through light sensors, temperature sensors and biological tissue response monitors, the light intensity, temperature and biological tissue response data of the target area during laser irradiation are obtained in real time; Preprocessing the light intensity, temperature and response data of biological tissue in the target area during laser irradiation, including noise filtering, signal amplification and data calibration, to obtain processed data; Based on the processed data, an analysis model is constructed to extract key indicators during laser irradiation, including the absorption efficiency of laser by biological tissue, the temperature change rate, and potential side effect warning information; Initialize the differential evolution parameters, including population size, mutation factor, and crossover probability, to generate an initial solution set, and evaluate the fitness of each individual in the initial solution set through an analytical model to obtain the fitness value of each individual; According to the fitness value of each individual, determine the individuals in the current population for differential mutation and crossover to generate test individuals, and compare the fitness values ​​of the test individuals with the corresponding original individuals to determine the new generation of population; The differential mutation and crossover operations and the new generation population determination are repeatedly performed until a preset number of iterations is reached to obtain an optimized solution. According to the optimized solution, the operating parameters of the fiber laser, including output power, wavelength or irradiation mode, are automatically and in real time adjusted.

2. The method for real-time analysis of tunable 1200 nm fiber laser irradiation therapy data according to claim 1, characterized in that: Preprocess the light intensity, temperature and biological tissue response data of the target area during laser irradiation, including noise filtering, signal amplification and data calibration, to obtain processed data, including: Analyze the characteristics and noise types of light intensity, temperature, and biological tissue response data, and identify the noise types in the data, including Gaussian noise and salt and pepper noise; According to the noise type, use mean filtering to remove the noise in the data, and set the parameters of the mean filtering, including the window size and threshold, to obtain the filtered data; Analyze the amplitude of the filtered data to determine the signal amplification factor, and use the amplification factor to linearly amplify the filtered data to obtain amplified data; The amplified data are calibrated using linear regression, and the processed data are obtained by comparing them with standard values ​​to eliminate systematic errors and offsets.

3. The method for real-time analysis of tunable 1200 nm fiber laser irradiation therapy data according to claim 2, characterized in that: Based on the processed data, an analysis model is constructed to extract key indicators during laser irradiation, including the absorption efficiency of laser by biological tissue, the temperature change rate, and potential side effect warning information, including: From the processed data, characteristic data related to the laser irradiation process are determined, including the average and peak values ​​of the light intensity, the temperature variation trend, and the specific pattern of biological tissue response; According to the determined characteristic data and analysis target related to the laser irradiation process, an analysis model is determined, and the characteristic data related to the laser irradiation process is divided into a training set and a verification set; The analysis model is trained using the training set, and the analysis model parameters are adjusted until the preset training effect is achieved to obtain the trained analysis model; the trained analysis model is verified and evaluated using the validation set to obtain the evaluation results; According to the evaluation results, the light intensity and biological tissue response data are analyzed using a verified analysis model, the regression coefficient between light intensity and biological tissue response is calculated, and the time series of temperature data is trended. During the analysis process, abnormal changes in the biological tissue response data, including tissue damage and inflammatory response, are continuously monitored to extract the biological tissue's absorption efficiency of the laser, the temperature change rate, and potential side effect warning information.

4. The method for real-time analysis of tunable 1200 nm fiber laser irradiation therapy data according to claim 3, characterized in that: The regression coefficient calculation formula between light intensity and biological tissue response is: ; in, Represents the regression coefficient between light intensity and biological tissue response; Indicates the number of data points; Indicates The light intensity value of each data point; Indicates The light intensity value of each data point; Indicates The biological tissue response value of data points; Indicates The biological tissue response value of data points; , , Represents an index variable.

5. The method for real-time analysis of tunable 1200 nm fiber laser irradiation therapy data according to claim 4, characterized in that: Initialize the differential evolution parameters, including population size, mutation factor, and crossover probability, to generate an initial solution set, and evaluate the fitness of each individual in the initial solution set through the analytical model to obtain the fitness value of each individual, including: Determine the parameters contained in each individual in the initial solution set, including the output power, wavelength, and irradiation mode of the laser; For each parameter, a value is randomly generated within the value range to form a solution vector. The random generation process is repeated until a preset number of solutions are obtained to obtain an initial solution set. Each individual in the initial solution set is used as an input parameter and input into the analysis model; The analysis model simulates the laser irradiation process according to the input parameters and outputs relevant data, including the absorption efficiency of the laser by the biological tissue and the temperature change; According to the output related data, a fitness function is defined to calculate the fitness value of each individual in the initial solution set.

6. The method for real-time analysis of tunable 1200 nm fiber laser irradiation therapy data according to claim 5, characterized in that: The fitness value calculation formula for each individual in the initial solution set is: ; in, Represents the fitness value of each individual; , , , represents the weight coefficient; It indicates the absorption efficiency of laser by biological tissue; Indicates the rate of temperature change; Represents the first input parameters; Represents the first The weight coefficients of the input parameters; Indicates warning information about potential side effects.

7. The method for real-time analysis of tunable 1200 nm fiber laser irradiation therapy data according to claim 6, characterized in that: According to the fitness value of each individual, determine the individuals in the current population for differential mutation and crossover, generate test individuals, and compare the fitness values ​​of the test individuals with the corresponding original individuals to determine the new generation of population, including: Randomly select two different individuals from the current population as basis vectors, calculate the difference between the two basis vectors, obtain the difference vector, adjust the difference vector, and combine it with the individuals in the current population to obtain the mutation vector; Perform a crossover operation on the mutation vector and the individuals in the previous population to generate test individuals; The fitness function is used to calculate the fitness value of the test individual, and the fitness value of the test individual is compared with the fitness value of the corresponding original individual to obtain a comparison result; Based on the comparison results, the population is updated to form a new generation of population.

8. A real-time analysis system for tunable 1200 nm fiber laser irradiation therapy data, the system implementing the method as claimed in any one of claims 1 to 7, characterized in that: include: The acquisition module is used to use a tunable 1200nm fiber laser to perform laser irradiation on a preset target area; through a light sensor, a temperature sensor and a biological tissue response monitor, the light intensity, temperature and response data of the target area during the laser irradiation process are obtained in real time; Preprocessing the light intensity, temperature and response data of biological tissue in the target area during laser irradiation, including noise filtering, signal amplification and data calibration, to obtain processed data; Based on the processed data, an analysis model is constructed to extract key indicators during laser irradiation, including the absorption efficiency of laser by biological tissue, the temperature change rate, and potential side effect warning information; The processing module is used to initialize the differential evolution parameters, including the population size, mutation factor, and crossover probability, to generate an initial solution set, and evaluate the fitness of each individual in the initial solution set through an analytical model to obtain the fitness value of each individual; according to the fitness value of each individual, determine the individuals in the current population to perform differential mutation and crossover, generate test individuals, and compare the fitness values ​​of the test individuals with those of the corresponding original individuals to determine a new generation of population; repeatedly perform differential mutation and crossover operations, and determine a new generation of population until a preset number of iterations is reached to obtain an optimized solution, and according to the optimized solution, automatically and in real time adjust the operating parameters of the fiber laser, including output power, wavelength or irradiation mode.

9. A computing device, characterized in that include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images