System and method for analyzing effect of laser freckle removal

Abstract

The invention relates to the field of data science and analysis, and discloses a laser freckle removing effect analysis system and method.The laser freckle removing effect analysis system comprises a freckle removing requirement label setting module used for obtaining time sequence skin image data and freckle removing requirement description of a target user and setting a freckle removing requirement label of the target user; the collaborative adaptation value calculation module is used for constructing a color spot characteristic matrix of the target user and calculating a collaborative adaptation value of the skin physiological parameter corresponding to the laser parameter configuration; the curative effect threshold determination module is used for analyzing the freckle removing effect prediction trend of the target user, analyzing the freckle evolution situation of the target user and determining curative effect thresholds of the target user in different treatment stages; the freckle removing scheme planning module is used for planning a laser freckle removing scheme of the target user, and the freckle removing effect analysis module is used for executing laser freckle removing processing on the target user and generating a freckle removing effect analysis report of the target user. According to the invention, the analysis accuracy of the laser freckle removing effect can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of beauty skin care, and particularly to a system and method for analyzing the effect of laser freckle removal. Background Art

[0002] In the current beauty skin care field, with the continuous improvement of people's pursuit of skin beauty, the demand for freckle removal is increasing day by day. Laser freckle removal has become a widely used freckle removal method due to its advantages such as high efficiency and convenience.

[0003] At present, the existing analysis of the effect of laser freckle removal mainly adopts subjective judgment methods, that is, by using basic instruments such as skin testers to detect some basic parameters of the skin, such as moisture content, oil secretion, pigment density, etc. According to the personal experience and professional knowledge level of doctors, corresponding treatment plans are formulated, and patients are treated according to the treatment plans. Finally, the effect of laser freckle removal is evaluated based on the skin effect after treatment. However, the instrument can only detect some parameters on the skin surface, and cannot comprehensively reflect the specific characteristics and changes of freckles. Moreover, the cognitive levels of each doctor are different, which leads to a deviation between the formulated treatment plan and the actual situation of the patient, and ultimately results in low accuracy of the effect analysis of laser freckle removal. Summary of the Invention

[0004] The present invention provides a system for analyzing the effect of laser freckle removal, and its main purpose lies in the accuracy of the effect analysis of laser freckle removal.

[0005] To achieve the above object, a system for analyzing the effect of laser freckle removal provided by the present invention includes: a freckle removal requirement label setting module, a collaborative adaptation value calculation module, a curative effect threshold determination module, a freckle removal plan planning module, and a freckle removal effect analysis module;

[0006] The freckle removal requirement label setting module is used to obtain the time-series skin image data and freckle removal requirement description of the target user, extract the freckle distribution characteristics and freckle morphology parameters of the target user from the time-series skin image data, and set the freckle removal requirement label of the target user based on the freckle removal requirement description;

[0007] The collaborative adaptation value calculation module is used to construct a freckle feature matrix of the target user based on the pigment spot distribution characteristics and the freckle removal requirement label, perform an association match between the freckle feature matrix and the historical clinical treatment data in the preset clinical case database to obtain a set of matching cases, extract the laser parameter configuration and curative effect evaluation data in the set of matching cases, collect the skin physiological parameters of the target user, and calculate the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameters;

[0008] The efficacy threshold determination module is used to analyze the prediction trend of the freckle removal effect of the target user by combining the collaborative adaptation value and the efficacy evaluation data, analyze the evolution trend of the freckles of the target user based on the freckle morphology parameters, and determine the efficacy thresholds of the target user at different treatment stages by combining the freckle removal effect prediction trend and the freckle evolution trend;

[0009] The freckle removal plan planning module is used to plan the laser freckle removal plan for the target user based on the efficacy threshold and the freckle feature matrix, and schedule the adverse effect avoidance criteria corresponding to the matching case set;

[0010] The freckle removal effect analysis module is used to perform laser freckle removal treatment on the target user by combining the laser freckle removal plan and the adverse effect avoidance criteria, and collect the stage freckle removal data corresponding to each stage of the freckle removal treatment in real time, and generate a freckle removal effect analysis report for the target user based on the stage freckle removal data.

[0011] Optionally, the extraction of the freckle distribution characteristics and freckle morphology parameters of the target user from the time-series skin image data includes:

[0012] Perform image noise reduction processing on the time-series skin image data to obtain a noise-reduced time-series skin image;

[0013] Extract the skin color characteristics and skin texture characteristics of the noise-reduced time-series skin image respectively;

[0014] Analyze the freckle areas in the noise-reduced time-series skin image based on the skin color characteristics and the skin texture characteristics;

[0015] Perform image segmentation processing on the noise-reduced time-series skin image based on the freckle areas to obtain a freckle segmentation image;

[0016] Extract the freckle distribution characteristics and freckle morphology parameters of the target user from the freckle segmentation image.

[0017] Optionally, the setting of the freckle removal requirement label for the target user based on the freckle removal requirement description includes:

[0018] Perform text cleaning processing on the freckle removal requirement description to obtain a target freckle removal requirement description;

[0019] Perform semantic parsing on the target freckle removal requirement description to obtain the freckle removal requirement semantics;

[0020] Determine the multi-dimensional freckle removal intention corresponding to the target freckle removal requirement description based on the freckle removal requirement semantics;

[0021] Extract the representation of the multi-dimensional freckle removal intention, and set the freckle removal requirement label for the target user based on the representation of the freckle removal intention.

[0022] Optionally, constructing the skin pigmentation feature matrix for the target user based on the pigment spot distribution feature and the freckle removal requirement label includes:

[0023] Perform spatial encoding processing on the pigment spot distribution feature to obtain a pigmentation adjacency matrix;

[0024] Analyze the priority dimension corresponding to the freckle removal requirement label, and calculate the dimension weight corresponding to the priority dimension;

[0025] Perform normalization processing on the dimension weight to obtain the requirement weight vector of the freckle removal requirement label;

[0026] Construct the composite feature matrix of the target user based on the pigmentation adjacency matrix and the requirement weight vector;

[0027] Perform dimensionality reduction and optimization processing on the composite feature matrix to obtain the skin pigmentation feature matrix of the target user.

[0028] Optionally, calculating the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameter includes:

[0029] Extract the laser parameter value in the laser parameter configuration, and determine the physiological parameter value corresponding to the skin physiological parameter;

[0030] Analyze the parametric correlation relationship between the laser parameter configuration and the skin physiological parameter;

[0031] Based on the parametric correlation relationship, perform associative combination on the laser parameter configuration and the skin physiological parameter to obtain a laser-skin parameter combination;

[0032] Combine the laser-skin parameter combination, the laser parameter value, and the physiological parameter value to calculate the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameter.

[0033] Optionally, combining the laser-skin parameter combination, the laser parameter value, and the physiological parameter value to calculate the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameter includes:

[0034] Calculate the combined importance coefficient corresponding to the laser-skin parameter combination;

[0035] Perform normalization processing on the laser parameter value and the physiological parameter value respectively to obtain a first parameter value and a second parameter value;

[0036] Combined with the combined importance coefficient, the first parameter value, and the second parameter value, calculate the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameter through the following formula:

[0037]

[0038] where β represents the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameter, ω k represents the combined importance coefficient corresponding to the k-th combination in the laser-skin parameter combination, l ki represents the i-th first parameter value within the k-th combination in the laser-skin parameter combination, p ki represents the i-th second parameter value within the k-th combination in the laser-skin parameter combination, k represents the starting value of the laser-skin parameter combination, m represents the number of laser-skin parameter combinations, i represents the serial number corresponding to the first parameter value and the second parameter value, and n represents the number corresponding to the first parameter value and the second parameter value.

[0039] Optionally, analyzing the freckle removal effect prediction trend of the target user by combining the collaborative adaptation value and the efficacy evaluation data includes:

[0040] Performing data cleaning on the efficacy evaluation data to obtain pure efficacy evaluation data;

[0041] Analyzing the evaluation labels corresponding to the pure efficacy evaluation data, and screening out the freckle removal effect evaluation data from the pure efficacy evaluation data based on the evaluation labels;

[0042] Extracting the freckle removal effect characteristics from the freckle removal effect evaluation data, and performing feature selection on the freckle removal effect characteristics to obtain key effect characteristics;

[0043] Generating a trend prediction curve for the target user based on the key effect characteristics;

[0044] According to the collaborative adaptation value, performing correction processing on the trend prediction curve to obtain the freckle removal effect prediction trend of the target user.

[0045] Optionally, analyzing the evolution trend of the target user's skin spots based on the skin spot morphology parameters includes:

[0046] Identifying the morphological indicators corresponding to the skin spot morphology parameters, and calculating the index similarity between the morphological indicators;

[0047] Based on the index similarity, performing parameter clustering on the skin spot morphology parameters to obtain clustered skin spot morphology parameters;

[0048] Extracting the time identifier corresponding to the clustered skin spot morphology parameters;

[0049] Combined with the time identifier and the clustered freckle morphological parameters, calculate the index change rate corresponding to the morphological index;

[0050] Based on the index change rate, analyze the index evolution trend corresponding to the morphological index;

[0051] Based on the index evolution trend, analyze the freckle evolution trend of the target user.

[0052] Optionally, the combining the time identifier and the clustered freckle morphological parameters to calculate the index change rate corresponding to the morphological index includes:

[0053] Based on the time identifier, sort the clustered freckle morphological parameters to obtain the sequential freckle morphological parameters;

[0054] Quantify the sequential freckle morphological parameters to obtain the morphological parameter values;

[0055] Based on the morphological parameter values, calculate the index change rate corresponding to the morphological index through the following formula:

[0056]

[0057] where A represents the index change rate corresponding to the morphological index, F a (t b+1 ) represents the morphological parameter value corresponding to the a-th index in the morphological index at time point t b+1 , F a (t b ) represents the morphological parameter value corresponding to the a-th index in the morphological index at time point t b , a represents the serial number corresponding to the morphological index, r represents the number of indexes corresponding to the morphological index, t b+1 and t b respectively represent the (b + 1)-th and b-th time points.

[0058] A method for analyzing the effect of laser freckle removal, characterized in that the method includes:

[0059] Obtain the sequential skin image data and freckle removal requirement description of the target user, extract the freckle distribution characteristics and freckle morphological parameters of the target user from the sequential skin image data, and set the freckle removal requirement label of the target user based on the freckle removal requirement description;

[0060] Based on the pigment spot distribution characteristics and the freckle removal requirement tags, construct the skin pigmentation feature matrix of the target user, associate and match the skin pigmentation feature matrix with the historical clinical treatment data in the preset clinical case database to obtain a set of matching cases, extract the laser parameter configuration and efficacy evaluation data in the set of matching cases, collect the skin physiological parameters of the target user, and calculate the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameters;

[0061] Combined with the collaborative adaptation value and the efficacy evaluation data, analyze the prediction trend of the freckle removal effect of the target user. Based on the skin pigmentation morphology parameters, analyze the evolution trend of the skin pigmentation of the target user. Combining the freckle removal effect prediction trend and the skin pigmentation evolution trend, determine the efficacy threshold of the target user at different treatment stages;

[0062] Based on the efficacy threshold and the skin pigmentation feature matrix, plan the laser freckle removal plan for the target user, and dispatch the adverse effect avoidance criteria corresponding to the set of matching cases;

[0063] Combined with the laser freckle removal plan and the adverse effect avoidance criteria, perform the laser freckle removal treatment on the target user, and collect the stage freckle removal data corresponding to each stage of the freckle removal treatment process in real time. Based on the stage freckle removal data, generate the freckle removal effect analysis report of the target user.

[0064] By extracting the distribution characteristics and morphological parameters of the target user's age spots from the time-series skin image data, the present invention can obtain an accurate quantitative description of the age spot condition of the target user, providing a solid and accurate data foundation for formulating subsequent personalized age spot removal plans and predicting treatment effects. Optionally, by constructing a feature matrix of the target user's age spots based on the distribution characteristics of the pigment spots and the age spot removal requirement tags, the present invention can transform the complex age spot situation and personalized needs of the user into a unified mathematical structure that is convenient for analysis and calculation, providing an important basis for subsequent related processing. By combining the collaborative adaptation value and the treatment effect evaluation data, the present invention analyzes the prediction trend of the age spot removal effect of the target user, integrating the collaborative relationship between laser parameters and skin physiological parameters and past treatment effect data, so as to accurately insight into the trend of the age spot removal effect of the target user in a quantitative and scientific manner, providing a key basis for optimizing and adjusting the personalized age spot removal treatment plan. By planning the laser age spot removal plan for the target user based on the treatment effect threshold and the age spot feature matrix, and further determining the detailed treatment method for the target user's age spots, and scheduling the adverse effect avoidance criteria corresponding to the matching case set, the present invention can ensure the safety and effectiveness of the age spot removal treatment to the greatest extent, and lay an important basis for improving the subsequent age spot removal effect analysis. By combining the laser age spot removal plan and the adverse effect avoidance criteria, the present invention performs laser age spot removal treatment on the target user, improving the treatment accuracy of the age spot removal treatment. Based on the stage age spot removal data, an age spot removal effect analysis report of the target user is generated, and a highly accurate age spot removal effect analysis result can be obtained. Therefore, the accuracy of the age spot removal effect analysis by laser is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 FIG. is a functional module diagram of an age spot removal effect analysis system provided by an embodiment of the present invention;

[0066] Figure 2 FIG. is a flowchart of an age spot removal effect analysis method provided by an embodiment of the present invention;

[0067] The implementation, functional features and advantages of the objectives of the present invention will be further described with reference to the accompanying drawings in conjunction with embodiments. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0068] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0069] In addition, the step timings in the following method embodiments are only examples and not strictly limited.

[0070] In fact, the server device deployed by the laser freckle removal effect analysis system may be composed of one or more devices. The above laser freckle removal effect analysis system can be implemented as: a business instance, a virtual machine, or a hardware device. For example, the laser freckle removal effect analysis system can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, the laser freckle removal effect analysis system can be understood as a software deployed on a cloud node, which is used to provide laser freckle removal effect analysis services for each client. Or, the laser freckle removal effect analysis system can also be implemented as a virtual machine deployed on one or more devices in a cloud node. An application software for managing each client is installed in the virtual machine. Or, the laser freckle removal effect analysis system can also be implemented as a server composed of many identical or different types of hardware devices, and one or more hardware devices are set to provide laser freckle removal effect analysis services for each client.

[0071] In terms of implementation form, the laser freckle removal effect analysis system and the client adapt to each other. That is, if the laser freckle removal effect analysis system is an application installed on a cloud service platform, then the client is a client that establishes a communication connection with this application; or if the laser freckle removal effect analysis system is implemented as a website, then the client is implemented as a web page; or if the laser freckle removal effect analysis system is implemented as a cloud service platform, then the client is implemented as a small program in an instant messaging application.

[0072] Refer to Figure 1 As shown, it is a functional module diagram of a laser freckle removal effect analysis system provided by an embodiment of the present invention.

[0073] The laser freckle removal effect analysis system 100 described in the present invention can be set in a cloud server. In terms of implementation form, it can be used as one or more service devices, or can be installed as an application on the cloud (such as a laser freckle removal effect analysis server, a server cluster, etc.), or can also be developed into a website. According to the functions to be realized, the laser freckle removal effect analysis system 100 includes a freckle removal requirement label setting module 101, a collaborative adaptation value calculation module 102, an efficacy threshold determination module 103, a freckle removal plan planning module 104, and a freckle removal effect analysis module 105.

[0074] In the embodiments of the present invention, in the tracking based on the effect analysis of laser freckle removal, each of the above-mentioned modules can be independently implemented and called with other modules. Here, the call can be understood as that a certain module can be connected to multiple modules of another type and provide corresponding services for the multiple modules it is connected to. In the laser freckle removal effect analysis system provided by the embodiments of the present invention, without modifying the program code, the applicable range of the laser freckle removal effect analysis architecture can be adjusted by adding modules and directly calling them, realizing cluster-level horizontal expansion, so as to achieve the purpose of quickly and flexibly expanding the laser freckle removal effect analysis system. In practical applications, the above-mentioned modules can be set in the same device or different devices, or can be set in virtual devices, such as service instances in a cloud server.

[0075] Next, in combination with specific embodiments, the components and specific working processes of the laser freckle removal effect analysis system will be described respectively.

[0076] The freckle removal requirement label setting module 101 is used to obtain the time-series skin image data and freckle removal requirement description of the target user, extract the freckle distribution characteristics and freckle shape parameters of the target user from the time-series skin image data, and set the freckle removal requirement label of the target user based on the freckle removal requirement description.

[0077] In the present invention, by extracting the freckle distribution characteristics and freckle shape parameters of the target user from the time-series skin image data, an accurate quantitative description of the freckle condition of the target user can be obtained, providing a solid and accurate data foundation for the subsequent formulation of personalized freckle removal plans and effect prediction. Among them, the time-series skin image data is the data composed of skin images taken by the target user at different time points, the freckle removal requirement description is the text expression of the target user's expectations for freckle removal effect, method, cycle, etc., the freckle distribution characteristics are the presentation conditions such as the position and density of freckles on the skin surface of the target user, and the freckle shape parameters are the quantitative values of the target user's freckles in terms of size, shape, color depth, etc.

[0078] As an embodiment of the present invention, the extracting the freckle distribution characteristics and freckle shape parameters of the target user from the time-series skin image data includes:

[0079] Performing image noise reduction processing on the time-series skin image data to obtain noise-reduced time-series skin images;

[0080] Respectively extracting the skin color characteristics and skin texture characteristics of the noise-reduced time-series skin images;

[0081] Based on the skin color characteristics and the skin texture characteristics, analyzing the freckle areas in the noise-reduced time-series skin images;

[0082] Based on the skin pigmentation area, perform image segmentation on the denoised sequential skin image to obtain a skin pigmentation segmentation image;

[0083] Extract the skin pigmentation distribution characteristics and skin pigmentation morphological parameters of the target user from the skin pigmentation segmentation image.

[0084] Among them, the denoised sequential skin image is the image obtained after removing noise interference from the sequential skin image data through noise reduction processing; the skin color feature and the skin texture feature are the characteristics presented by the denoised sequential skin image in terms of color and texture respectively; the skin pigmentation area is the part of the denoised sequential skin image where skin pigmentation exists; the skin pigmentation segmentation image is the image obtained after separating the skin pigmentation area from the normal skin area in the denoised sequential skin image.

[0085] Optionally, the sequential skin image data can be subjected to image noise reduction processing through a mean filter noise reduction algorithm to obtain a denoised sequential skin image; the skin color feature and the skin texture feature of the denoised sequential skin image can be extracted in the HSV color space and the gray-level co-occurrence matrix respectively; the decision tree algorithm can be used to deeply mine the skin color feature and the skin texture feature, and based on the combination rules of the feature parameters, a set of pixel points with skin pigmentation characteristics can be identified, thereby determining the skin pigmentation area in the denoised sequential skin image; based on the skin pigmentation area, the denoised sequential skin image can be subjected to image segmentation processing through a Canny edge detection operator combined with the region growing method to obtain a skin pigmentation segmentation image; the skin pigmentation distribution characteristics and skin pigmentation morphological parameters of the target user can be extracted from the skin pigmentation segmentation image through means such as coordinate positioning and geometric measurement.

[0086] By setting the skin pigmentation removal requirement label of the target user based on the skin pigmentation removal requirement description, the personalized demands of the user can be obtained, laying a solid foundation for formulating a laser skin pigmentation removal plan that highly meets the user's expectations and greatly improving the user experience. Among them, the skin pigmentation removal requirement label is a refined identifier of key information such as the target user's expectation for the skin pigmentation removal effect, the requirement for the treatment cycle, the cost tolerance range, and special preferences.

[0087] As an embodiment of the present invention, setting the skin pigmentation removal requirement label of the target user based on the skin pigmentation removal requirement description includes:

[0088] Perform text cleaning processing on the skin pigmentation removal requirement description to obtain a target skin pigmentation removal requirement description;

[0089] Perform semantic parsing on the target skin pigmentation removal requirement description to obtain the skin pigmentation removal requirement semantics;

[0090] Based on the skin pigmentation removal requirement semantics, determine the multi-dimensional skin pigmentation removal intention corresponding to the target skin pigmentation removal requirement description;

[0091] Extract the representative freckle-removing intention from the multi-dimensional freckle-removing intention, and set the freckle-removing requirement label for the target user based on the representative freckle-removing intention.

[0092] Among them, the target freckle-removing requirement description is a more standardized and accurate text description obtained by cleaning the freckle-removing requirement description to remove noise and redundant information. The freckle-removing requirement semantics is the actual meaning and the specific requirements and expectations of the user for aspects related to freckle-removing contained in the target freckle-removing requirement description through semantic parsing. The multi-dimensional freckle-removing intention is a comprehensive description of the user's freckle-removing intention from multiple dimensions (such as freckle-removing effect, treatment method, time requirement, etc.) corresponding to the target freckle-removing requirement description. The representative freckle-removing intention is the key part or specific indication in the multi-dimensional freckle-removing intention that can represent and reflect the user's core freckle-removing demands and characteristics.

[0093] Optionally, the freckle-removing requirement description can be textually cleaned by means of text preprocessing such as removing stop words, correcting typos, and unifying formats to obtain the target freckle-removing requirement description; the target freckle-removing requirement description can be semantically parsed by semantic analysis to obtain the freckle-removing requirement semantics; based on the freckle-removing requirement semantics, the multi-dimensional freckle-removing intention corresponding to the target freckle-removing requirement description can be determined by means of an intention recognition model or manually formulated semantic rules; the representative freckle-removing intention in the multi-dimensional freckle-removing intention can be extracted by means of screening key semantic elements and focusing on core demand points; based on the representative freckle-removing intention, the freckle-removing requirement label for the target user can be set, such as "quick freckle removal", "gentle treatment", "high-cost-performance freckle removal", etc.

[0094] The collaborative adaptation value calculation module 102 is used to construct a skin spot feature matrix for the target user based on the skin pigment spot distribution feature and the freckle-removing requirement label, associate and match the skin spot feature matrix with the historical clinical treatment data in a preset clinical case database to obtain a set of matching cases, extract the laser parameter configuration and efficacy evaluation data in the set of matching cases, collect the skin physiological parameters of the target user, and calculate the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameters.

[0095] By constructing the skin spot feature matrix for the target user based on the skin pigment spot distribution feature and the freckle-removing requirement label, the present invention can transform the complex skin spot situation and personalized needs of the user into a unified mathematical structure that is convenient for analysis and calculation, providing an important basis for subsequent related processing. Among them, the skin spot feature matrix is a two-dimensional data array constructed for the target user based on the skin pigment spot distribution feature and the freckle-removing requirement label to comprehensively, quantitatively and structurally present the skin spot condition of the target user and the personalized freckle-removing demands.

[0096] As an embodiment of the present invention, constructing the skin pigmentation feature matrix of the target user based on the skin pigmentation spot distribution feature and the skin pigmentation removal requirement label includes:

[0097] Performing spatial encoding processing on the skin pigmentation spot distribution feature to obtain a skin pigmentation spot adjacency matrix;

[0098] Analyzing the priority dimensions corresponding to the skin pigmentation removal requirement label and calculating the dimension weights corresponding to the priority dimensions;

[0099] Performing normalization processing on the dimension weights to obtain a requirement weight vector of the skin pigmentation removal requirement label;

[0100] Constructing the composite feature matrix of the target user based on the skin pigmentation spot adjacency matrix and the requirement weight vector;

[0101] Performing dimensionality reduction and optimization processing on the composite feature matrix to obtain the skin pigmentation feature matrix of the target user.

[0102] Wherein, the skin pigmentation spot adjacency matrix is a matrix that reflects the spatial distribution of skin pigmentation spots through spatial encoding of the skin pigmentation spot distribution feature in terms of node adjacency relationships; the priority dimensions are requirement categories with different importance levels corresponding to the skin pigmentation removal requirement label; the dimension weights represent the relative importance values corresponding to the priority dimensions; the requirement weight vector is a vector obtained by normalizing the dimension weights, with a sum of 1 and reflecting the proportion of requirements in each dimension; the composite feature matrix is a matrix of the target user that combines the skin pigmentation spot distribution feature reflected by the skin pigmentation spot adjacency matrix and the skin pigmentation removal requirement feature reflected by the requirement weight vector.

[0103] Furthermore, the spatial encoding processing of the skin pigmentation spot distribution feature can be performed through a custom spatial position analysis algorithm to obtain a skin pigmentation spot adjacency matrix; the priority dimensions corresponding to the skin pigmentation removal requirement label can be analyzed through a combination of semantic analysis and user requirement research, and the dimension weights corresponding to the priority dimensions can be calculated through the analytic hierarchy process; the dimension weights can be normalized through a standard normalization formula to obtain a requirement weight vector of the skin pigmentation removal requirement label; based on the skin pigmentation spot adjacency matrix and the requirement weight vector, the composite feature matrix of the target user can be constructed through a matrix splicing algorithm; the composite feature matrix can be subjected to dimensionality reduction and optimization processing through a principal component analysis (PCA) dimensionality reduction algorithm to obtain the skin pigmentation feature matrix of the target user.

[0104] By collecting the skin physiological parameters of the target user, the present invention can accurately grasp the individual characteristics of the user's skin, provide a key basis for evaluating the adaptability of laser parameter configuration to skin physiological conditions, calculate the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameters, and understand the degree of fit of the laser treatment plan to the target user's skin through the collaborative adaptation value, so as to scientifically adjust the treatment plan, improve the freckle removal effect and reduce the risk of adverse reactions. Among them, the preset clinical case database is a database storing a large amount of historical clinical treatment data (including freckle characteristics, laser parameter configuration, efficacy evaluation data, etc.), the matching case set is a data set with relevance and matching in the historical clinical treatment data in the preset clinical case database and the freckle feature matrix, the laser parameter configuration and the efficacy evaluation data are respectively the parameter settings for laser treatment and the data for evaluating the treatment effect in the matching case set, the skin physiological parameter is a relevant index reflecting the skin physiological characteristics (such as skin type, skin color, freckle condition, etc.) of the target user, and the collaborative adaptation value represents a quantitative value of the degree of fit of the laser parameter configuration corresponding to the skin physiological parameters. Further, the freckle feature matrix can be associated and matched with the historical clinical treatment data in the preset clinical case database through a matching algorithm to obtain a matching case set, and the matching algorithm includes a cosine similarity algorithm; the laser parameter configuration and the efficacy evaluation data in the matching case set can be extracted through an extraction function, and the extraction function is compiled by a programming language; the skin physiological parameters of the target user can be collected by a professional skin detection instrument.

[0105] As an embodiment of the present invention, calculating the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameters includes:

[0106] Extract the laser parameter values in the laser parameter configuration and determine the physiological parameter values corresponding to the skin physiological parameters;

[0107] Analyze the parameter correlation relationship between the laser parameter configuration and the skin physiological parameters;

[0108] Based on the parameter correlation relationship, perform an associated combination of the laser parameter configuration and the skin physiological parameters to obtain a laser-skin parameter combination;

[0109] Combined with the laser-skin parameter combination, the laser parameter values and the physiological parameter values, calculate the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameters.

[0110] Among them, the laser parameter value is the specific parameter value in the laser parameter configuration (such as the values of specific parameters such as the wavelength, energy density, and pulse width of the laser); the physiological parameter value is the specific measured value corresponding to the skin physiological parameter (such as the measured values of physiological characteristics such as skin water content, pH value, and elasticity); the parameter correlation relationship is the mutual influence and interaction relationship between the laser parameter configuration and the skin physiological parameter (for example, a specific laser wavelength may affect skin pigmentation, which is a parameter correlation relationship).

[0111] Optionally, the laser parameter value in the laser parameter configuration can be extracted through the device data reading module, and the physiological parameter value corresponding to the skin physiological parameter can be determined through a skin detection instrument and supporting analysis software; the parameter correlation relationship between the laser parameter configuration and the skin physiological parameter can be analyzed through a statistical analysis algorithm and a professional knowledge database; based on the parameter correlation relationship, the laser parameter configuration and the skin physiological parameter can be associated and combined through a data fusion algorithm to obtain a laser-skin parameter combination, thereby being able to accurately integrate multi-source data, providing a comprehensive and orderly data basis for in-depth analysis of the synergistic adaptation of lasers and skin physiological characteristics, and effectively improving the scientificity and accuracy of laser treatment plan formulation.

[0112] Furthermore, as an optional embodiment of the present invention, calculating the synergistic adaptation value of the laser parameter configuration corresponding to the skin physiological parameter by combining the laser-skin parameter combination, the laser parameter value, and the physiological parameter value includes:

[0113] Calculating the combined importance coefficient corresponding to the laser-skin parameter combination;

[0114] Normalizing the laser parameter value and the physiological parameter value respectively to obtain a first parameter value and a second parameter value;

[0115] Combining the combined importance coefficient, the first parameter value, and the second parameter value, and calculating the synergistic adaptation value of the laser parameter configuration corresponding to the skin physiological parameter through the following formula:

[0116]

[0117] Among them, β represents the synergistic adaptation value of the laser parameter configuration corresponding to the skin physiological parameter, ω k represents the combined importance coefficient corresponding to the kth combination in the laser-skin parameter combination, l ki represents the ith first parameter value in the kth combination in the laser-skin parameter combination, p kiIt represents the i-th second parameter value within the k-th combination in the laser-skin parameter combination. k represents the starting value of the laser-skin parameter combination, m represents the number of laser-skin parameter combinations, i represents the serial number corresponding to the first parameter value and the second parameter value, and n represents the number corresponding to the first parameter value and the second parameter value.

[0118] Among them, the combination importance coefficient represents the relative importance degree of the corresponding laser-skin parameter combination when evaluating the collaborative adaptation value; the first parameter value and the second parameter value are respectively the actual values adopted by the laser parameter value and the physiological parameter value in the specific calculation process of the collaborative adaptation value.

[0119] Optionally, the combination importance coefficient corresponding to the laser-skin parameter combination can be calculated through the comprehensive analysis of the analytic hierarchy process (AHP) combined with expert experience and a large amount of clinical data; the laser parameter value and the physiological parameter value can be normalized respectively through the z-score normalization formula to obtain the first parameter value and the second parameter value.

[0120] The efficacy threshold determination module 103 is used to analyze the freckle removal effect prediction trend of the target user by combining the collaborative adaptation value and the efficacy evaluation data, analyze the freckle evolution trend of the target user based on the freckle morphology parameters, and determine the efficacy threshold of the target user at different treatment stages by combining the freckle removal effect prediction trend and the freckle evolution trend.

[0121] The present invention combines the collaborative adaptation value and the efficacy evaluation data to analyze the freckle removal effect prediction trend of the target user, and can integrate the collaborative relationship between the laser parameters and the skin physiological parameters as well as the past efficacy data, so as to accurately insight into the trend of the target user's freckle removal effect in a quantitative and scientific manner, providing a key basis for the optimization and adjustment of personalized freckle removal treatment plans. Among them, the freckle removal effect prediction trend is the expected change direction and degree of the improvement of the target user's freckles in the future period after receiving a specific laser freckle removal treatment plan.

[0122] As an embodiment of the present invention, the analysis of the freckle removal effect prediction trend of the target user by combining the collaborative adaptation value and the efficacy evaluation data includes:

[0123] Perform data cleaning processing on the efficacy evaluation data to obtain pure efficacy evaluation data;

[0124] Analyze the evaluation labels corresponding to the pure efficacy evaluation data, and screen out the freckle removal effect evaluation data from the pure efficacy evaluation data based on the evaluation labels;

[0125] Extract the freckle removal effect features from the freckle removal effect evaluation data, perform feature selection processing on the freckle removal effect features to obtain key effect features;

[0126] Generate a trend prediction curve for the target user based on the key effect features;

[0127] According to the collaborative adaptation value, perform correction processing on the trend prediction curve to obtain the freckle removal effect prediction trend of the target user.

[0128] Among them, the pure efficacy evaluation data is clean and accurate data obtained after cleaning operations such as removing noise, errors, duplicates, and filling missing values from the efficacy evaluation data; the evaluation label is an identifier corresponding to the pure efficacy evaluation data for labeling the category, characteristics, or evaluation results of the data; the freckle removal effect evaluation data is a data subset directly related to the freckle removal treatment effect in the pure efficacy evaluation data; the freckle removal effect features are various quantitative indicators (such as changes in freckle area, changes in color depth, etc.) in the freckle removal effect evaluation data that can reflect the freckle removal effect; the key effect features are the features that are retained after screening and removing redundant and irrelevant features from the freckle removal effect features and are the most representative and influential for freckle removal effect evaluation; the trend prediction curve is a curve constructed by the target user based on the key effect features for intuitively presenting the trend of the freckle removal effect changing over time or the treatment process.

[0129] Furthermore, the evaluation labels corresponding to the pure efficacy evaluation data can be analyzed through text classification algorithms (such as Naive Bayes, Support Vector Machine, etc.); based on the evaluation labels, the freckle removal effect evaluation data can be screened from the pure efficacy evaluation data by writing screening rules according to the label content (such as screening out the corresponding data when the label contains words related to "freckle removal effect"); the freckle removal effect features in the freckle removal effect evaluation data can be extracted by combining domain knowledge and data analysis tools (such as based on the evaluation key points of freckle removal effect by dermatologists and data mining algorithms), and the feature selection processing can be performed on the freckle removal effect features by combining statistical tests (such as correlation analysis, chi-square test) and machine learning algorithms (such as recursive feature elimination method) to obtain key effect features; based on the key effect features, the trend prediction curve of the target user can be generated through a time series analysis model (such as ARIMA model) or curve fitting algorithm (such as polynomial fitting); according to the collaborative adaptation value, the trend prediction curve can be corrected by constructing a weighted adjustment function (determining the adjustment amplitude and direction according to the size of the collaborative adaptation value) to obtain the freckle removal effect prediction trend of the target user. This series of methods can systematically and scientifically generate accurate freckle removal effect prediction results from the original data step by step.

[0130] Based on the skin pigmentation morphological parameters, the present invention analyzes the evolution trend of the skin pigmentation of the target user, and can grasp the change trend of the skin pigmentation in terms of size, shape, boundary clarity, etc. over time, providing a key basis for doctors to predict the treatment effect of skin pigmentation removal in advance and adjust the treatment plan in a timely manner. Among them, the evolution trend of the skin pigmentation is the change situation and trend of the skin pigmentation of the target user in terms of size, shape, color, distribution, etc. over time or during the treatment process.

[0131] As an embodiment of the present invention, the analysis of the evolution trend of the skin pigmentation of the target user based on the skin pigmentation morphological parameters includes:

[0132] Identify the morphological indicators corresponding to the skin pigmentation morphological parameters, and calculate the indicator similarity between the morphological indicators;

[0133] Based on the indicator similarity, perform parameter clustering processing on the skin pigmentation morphological parameters to obtain clustered skin pigmentation morphological parameters;

[0134] Extract the time identifier corresponding to the clustered skin pigmentation morphological parameters;

[0135] Combine the time identifier and the clustered skin pigmentation morphological parameters, and calculate the indicator transition rate corresponding to the morphological indicators;

[0136] Based on the indicator transition rate, analyze the indicator evolution trend corresponding to the morphological indicators;

[0137] Based on the indicator evolution trend, analyze the evolution trend of the skin pigmentation of the target user.

[0138] Among them, the morphological indicators are the morphological types corresponding to the skin pigmentation morphological parameters, such as area, perimeter, circularity, etc.; the indicator similarity represents the similarity degree between the morphological indicators; the clustered skin pigmentation morphological parameters are a parameter set obtained by classifying the skin pigmentation morphological parameters based on the indicator similarity; the time identifier is the information of the clustered skin pigmentation morphological parameters in the time dimension, such as the acquisition time point; the indicator transition rate represents the numerical manifestation of the change speed of the morphological indicators per unit time; the indicator evolution trend is the description of the development trend and change situation presented by the morphological indicators over a period of time or under a series of condition changes.

[0139] Further, the morphological indicators corresponding to the morphological parameters of the skin pigmentation can be identified through machine learning-based classification algorithms (such as decision trees, random forests, etc.); the indicator similarity between the morphological indicators can be calculated through the Euclidean distance algorithm; when the indicator similarity is greater than the similarity threshold, the morphological parameters of the skin pigmentation can be subjected to parameter clustering processing through a classification function to obtain the clustered morphological parameters of the skin pigmentation, such as the K-Means clustering function. The similarity threshold is a preset reference value and is set according to the actual application scenario; the time identifier corresponding to the clustered morphological parameters of the skin pigmentation can be extracted from the time field information of the data record or a specific time marking rule; based on the indicator change rate, the time series analysis method (such as the ARIMA model) can be used to analyze the indicator evolution trend corresponding to the morphological indicators; based on the indicator evolution trend, combined with medical professional knowledge, the evolution trend of the skin pigmentation of the target user can be analyzed. For example, according to the continuous reduction of the skin pigmentation area and the gradual lightening of the color in the indicator evolution trend, combined with the medical understanding of the principle of skin pigmentation regression, it can be judged that the skin pigmentation is in a benign improvement trend; or according to the abnormal fluctuation of the clarity of the skin pigmentation boundary in the indicator, combined with medical knowledge, it can be speculated that there may be treatment interference factors leading to unstable evolution of the skin pigmentation.

[0140] Further, as an alternative embodiment of the present invention, the calculation of the indicator change rate corresponding to the morphological indicators by combining the time identifier and the clustered morphological parameters of the skin pigmentation includes:

[0141] Based on the time identifier, the clustered morphological parameters of the skin pigmentation are sorted to obtain the sequential morphological parameters of the skin pigmentation;

[0142] The sequential morphological parameters of the skin pigmentation are quantified to obtain the morphological parameter values;

[0143] Based on the morphological parameter values, the indicator change rate corresponding to the morphological indicators is calculated through the following formula:

[0144]

[0145] where A represents the indicator change rate corresponding to the morphological indicators, F a (t b+1 ) represents the morphological parameter value corresponding to the a-th indicator in the morphological indicators at the t b+1 time point, F a (t b ) represents the morphological parameter value corresponding to the a-th indicator in the morphological indicators at the t b time point, a represents the serial number corresponding to the morphological indicators, r represents the number of indicators corresponding to the morphological indicators, t b+1 and t b respectively represent the (b + 1)-th and b-th time points.

[0146] Among them, the sequence color spot morphology parameters are an ordered parameter set obtained by sorting the clustering color spot morphology parameters according to the time identifier, and the morphology parameter values are the quantization values corresponding to the sequence color spot morphology parameters. Further, the sorting process of the clustering color spot morphology parameters can be implemented by the bubble sort algorithm; the quantization process of the sequence color spot morphology parameters can be achieved by combining edge detection with the moment method. For example, the Canny edge detection algorithm is used to accurately outline the color spot contour, and based on this, the contour coordinate points are obtained, and then substituted into the moment method formula to calculate the zero-order moment to obtain the color spot area, the first-order moment to determine the centroid position, and the moments above the second order to calculate the ellipticity, eccentricity, etc., so as to complete the comprehensive quantization of the sequence color spot morphology parameters.

[0147] By combining the freckle removal effect prediction trend and the color spot evolution trend, the present invention determines the efficacy threshold of the target user at different treatment stages, which can provide a precise treatment reference basis for doctors and provide an important basis for the subsequent planning of the laser freckle removal plan for the target user. Among them, the efficacy threshold is the quantization standard for the improvement degree of the color spots of the target user at different treatment stages, used to judge whether the current treatment stage reaches the expected effective treatment result range. Further, by combining the freckle removal effect prediction trend and the color spot evolution trend, the efficacy threshold of the target user at different treatment stages is determined. For example, by comprehensively analyzing the expected color spot fading degree at different time nodes in the freckle removal effect prediction trend and the changes in actual color spot area, color, shape and other parameters in the color spot evolution trend, through data fitting and medical experience judgment, specific efficacy thresholds such as the area reduction ratio and color lightening value that the color spot improvement needs to reach in each treatment stage are determined.

[0148] The freckle removal plan planning module 104 is used to plan the laser freckle removal plan for the target user based on the efficacy threshold and the color spot feature matrix, and dispatch the adverse effect avoidance criteria corresponding to the matching case set.

[0149] The present invention plans the laser freckle removal plan for the target user based on the efficacy threshold and the freckle feature matrix, and then determines the detailed treatment method for the target user regarding freckles. By scheduling the adverse effect avoidance criteria corresponding to the matching case set, the safety and effectiveness of the freckle removal treatment can be maximally ensured, and an important basis for subsequent improvement of freckle removal effect analysis is laid. Among them, the laser freckle removal plan is a personalized treatment plan for the target user, including contents such as laser type, energy parameters, treatment times, and interval time. The adverse effect avoidance criteria are a series of methods and measures corresponding to the matching case set for preventing and dealing with possible adverse reactions and complications during the laser freckle removal process. Further, based on the efficacy threshold and the freckle feature matrix, the laser freckle removal plan for the target user is planned. The specific planning steps are as follows: First, determine the key features such as the type, area, and depth of the freckles according to the freckle feature matrix. Then, clarify the expected treatment effects at each stage in combination with the efficacy threshold. Next, select appropriate laser devices and parameters based on this information. Then, determine the treatment times, interval time, and treatment course arrangement. At the same time, consider the individual differences of the patient to adjust and optimize the plan. The scheduling of the adverse effect avoidance criteria can be obtained through the precautions in the matching case set.

[0150] The freckle removal effect analysis module 105 is used to perform laser freckle removal processing on the target user in combination with the laser freckle removal plan and the adverse effect avoidance criteria, and collect the stage freckle removal data corresponding to each stage of the freckle removal processing in real time. Based on the stage freckle removal data, a freckle removal effect analysis report for the target user is generated.

[0151] The present invention combines the laser freckle removal scheme and the adverse effect avoidance criterion to perform laser freckle removal treatment on the target user, thereby improving the treatment accuracy of freckle removal treatment. Based on the stage freckle removal data, a freckle removal effect analysis report for the target user is generated, and a highly accurate freckle removal effect analysis result can be obtained, wherein the stage freckle removal data is the data of the freckle removal treatment record corresponding to each stage of the freckle removal treatment process, and the freckle removal effect analysis report is a visualization display result of the freckle removal effect of the target user. Furthermore, the laser freckle removal treatment of the target user can be achieved by corresponding laser treatment equipment; it can be achieved by high-precision Skin imaging equipment, intelligent sensors and professional medical monitoring software collect the stage freckle removal data corresponding to each stage of the freckle removal process in real time; based on the stage freckle removal data, generate the freckle removal effect analysis report of the target user, firstly, classify and organize the stage freckle removal data, arrange the relevant data such as the freckle area, color, texture in order according to the treatment stage, then use statistical analysis methods to calculate the key indicators such as the change trend and improvement degree of the data of each stage, then, combine medical professional knowledge, evaluate the freckle removal effect based on these indicators, and generate a freckle removal effect analysis report in the form of pictures and texts, which includes comparison of each stage, effect summary and subsequent suggestions.

[0152] By extracting the freckle distribution characteristics and freckle morphology parameters of the target user from the time-series skin image data, the present invention can obtain an accurate quantitative description of the freckle condition of the target user, providing a solid and accurate data foundation for the formulation of subsequent personalized freckle removal plans and effect prediction; optionally, by constructing a freckle feature matrix of the target user based on the pigment spot distribution characteristics and the freckle removal requirement tags, the present invention can transform the complex freckle conditions and personalized needs of the user into a unified mathematical structure that is convenient for analysis and calculation, providing an important basis for subsequent related processing; by combining the collaborative adaptation value and the efficacy evaluation data, the present invention analyzes the freckle removal effect prediction trend of the target user, and can integrate the collaborative relationship between the laser parameters and the skin physiological parameters and the past efficacy data, so as to accurately insight into the trend of the freckle removal effect of the target user in a quantitative and scientific manner, providing a key basis for the optimization and adjustment of the personalized freckle removal treatment plan; by planning the laser freckle removal plan of the target user based on the efficacy threshold and the freckle feature matrix, and then the detailed treatment method for the target user's freckles, and scheduling the adverse effect avoidance criteria corresponding to the matching case set, the present invention can ensure the safety and effectiveness of the freckle removal treatment to the greatest extent, and lay an important basis for improving the subsequent freckle removal effect analysis; by combining the laser freckle removal plan and the adverse effect avoidance criteria, the present invention performs the laser freckle removal treatment on the target user, can improve the treatment accuracy of the freckle removal treatment, and generates an analysis report on the freckle removal effect of the target user based on the stage freckle removal data, and can obtain a highly accurate freckle removal effect analysis result. Therefore, the accuracy of the effect analysis of laser freckle removal is improved.

[0153] As Figure 2 shown, it is a schematic flowchart of a method for analyzing the effect of laser freckle removal provided by an embodiment of the present invention. In this embodiment, the method for analyzing the effect of laser freckle removal includes:

[0154] Obtain the time-series skin image data and freckle removal requirement description of the target user, extract the freckle distribution characteristics and freckle morphology parameters of the target user from the time-series skin image data, and set the freckle removal requirement tags of the target user based on the freckle removal requirement description;

[0155] Based on the pigment spot distribution characteristics and the freckle removal requirement tags, construct a freckle feature matrix of the target user, associate and match the freckle feature matrix with the historical clinical treatment data in a preset clinical case database to obtain a matching case set, extract the laser parameter configuration and efficacy evaluation data in the matching case set, collect the skin physiological parameters of the target user, and calculate the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameters;

[0156] Analyze the prediction trend of the freckle removal effect of the target user by combining the collaborative adaptation value and the efficacy evaluation data, analyze the evolution trend of the freckles of the target user based on the freckle morphology parameters, and determine the efficacy threshold of the target user at different treatment stages by combining the freckle removal effect prediction trend and the freckle evolution trend;

[0157] Plan the laser freckle removal plan for the target user based on the efficacy threshold and the freckle feature matrix, and schedule the adverse effect avoidance criteria corresponding to the matching case set;

[0158] Execute the laser freckle removal treatment for the target user by combining the laser freckle removal plan and the adverse effect avoidance criteria, and collect the stage freckle removal data corresponding to each stage of the freckle removal process in real time. Generate the freckle removal effect analysis report of the target user based on the stage freckle removal data.

[0159] In several embodiments provided by the present invention, it should be understood that the provided systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0160] In addition, each functional module in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware, or in the form of a hardware plus software functional module.

[0161] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An effect analysis system for laser freckle removal, characterized in that, The system for analyzing the effect of laser freckle removal includes: a freckle removal requirement label setting module, a collaborative adaptation value calculation module, an efficacy threshold determination module, a freckle removal plan planning module, and a freckle removal effect analysis module; The freckle removal requirement label setting module is used to obtain the sequential skin image data and freckle removal requirement description of the target user, extract the freckle distribution characteristics and freckle morphology parameters of the target user from the sequential skin image data, and set the freckle removal requirement label of the target user based on the freckle removal requirement description; The collaborative adaptation value calculation module is used to construct a freckle feature matrix of the target user based on the pigment spot distribution characteristics and the freckle removal requirement label, perform an association match between the freckle feature matrix and the historical clinical treatment data in the preset clinical case database to obtain a matching case set, extract the laser parameter configuration and efficacy evaluation data in the matching case set, collect the skin physiological parameters of the target user, and calculate the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameters; The efficacy threshold determination module is used to analyze the freckle removal effect prediction trend of the target user by combining the collaborative adaptation value and the efficacy evaluation data, analyze the freckle evolution trend of the target user based on the freckle morphology parameters, and determine the efficacy threshold of the target user at different treatment stages by combining the freckle removal effect prediction trend and the freckle evolution trend; The freckle removal plan planning module is used to plan the laser freckle removal plan of the target user based on the efficacy threshold and the freckle feature matrix, and dispatch the adverse effect avoidance criteria corresponding to the matching case set; The freckle removal effect analysis module is used to perform laser freckle removal treatment on the target user by combining the laser freckle removal plan and the adverse effect avoidance criteria, and collect the stage freckle removal data corresponding to each stage of the freckle removal treatment process in real time, and generate a freckle removal effect analysis report of the target user based on the stage freckle removal data.

2. The effect analysis system for laser freckle removal according to claim 1, wherein, The extracting the freckle distribution characteristics and freckle morphology parameters of the target user from the sequential skin image data includes: Performing image noise reduction processing on the sequential skin image data to obtain a noise-reduced sequential skin image; Respectively extracting the skin color characteristics and skin texture characteristics of the noise-reduced sequential skin image; Analyzing the freckle area in the noise-reduced sequential skin image based on the skin color characteristics and the skin texture characteristics; Performing image segmentation processing on the noise-reduced sequential skin image based on the freckle area to obtain a freckle segmentation image; Extracting the freckle distribution characteristics and freckle morphology parameters of the target user from the freckle segmentation image.

3. The effect analysis system for laser freckle removal according to claim 1, characterized in that, The setting the freckle removal requirement label of the target user based on the freckle removal requirement description includes: Performing text cleaning processing on the freckle removal requirement description to obtain a target freckle removal requirement description; Performing semantic parsing on the target freckle removal requirement description to obtain a freckle removal requirement semantics; Determining the multi-dimensional freckle removal intention corresponding to the target freckle removal requirement description based on the freckle removal requirement semantics; Extract the representative freckle-removing intention in the multi-dimensional freckle-removing intention, and set the freckle-removing requirement label for the target user based on the representative freckle-removing intention.

4. The effect analysis system for laser freckle removal according to claim 1, characterized in that, Based on the pigment spot distribution characteristics and the freckle-removing requirement label, constructing the pigment spot feature matrix of the target user includes: Performing spatial encoding processing on the pigment spot distribution characteristics to obtain a spot adjacency matrix; Analyzing the priority dimension corresponding to the freckle-removing requirement label, and calculating the dimension weight corresponding to the priority dimension; Performing normalization processing on the dimension weight to obtain the requirement weight vector of the freckle-removing requirement label; Based on the spot adjacency matrix and the requirement weight vector, constructing the composite feature matrix of the target user; Performing dimensionality reduction and optimization processing on the composite feature matrix to obtain the pigment spot feature matrix of the target user.

5. The effect analysis system for laser freckle removal according to claim 1, wherein Calculating the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameter includes: Extracting the laser parameter values in the laser parameter configuration, and determining the physiological parameter values corresponding to the skin physiological parameters; Analyzing the parameter correlation relationship between the laser parameter configuration and the skin physiological parameter; Based on the parameter correlation relationship, performing an associative combination of the laser parameter configuration and the skin physiological parameter to obtain a laser-skin parameter combination; Combining the laser-skin parameter combination, the laser parameter values, and the physiological parameter values, and calculating the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameter.

6. The effect analysis system for laser freckle removal according to claim 5, characterized in that Combining the laser-skin parameter combination, the laser parameter values, and the physiological parameter values, and calculating the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameter includes: Calculating the combined importance coefficient corresponding to the laser-skin parameter combination; Performing normalization processing on the laser parameter values and the physiological parameter values respectively to obtain the first parameter value and the second parameter value; Combining the combined importance coefficient, the first parameter value, and the second parameter value, and calculating the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameter through the following formula: Among them, β represents the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameter, ω k represents the combined importance coefficient corresponding to the k-th combination in the laser-skin parameter combination, l ki represents the i-th first parameter value in the k-th combination of the laser-skin parameter combination, p ki represents the i-th second parameter value in the k-th combination of the laser-skin parameter combination, k represents the starting value of the laser-skin parameter combination, m represents the number of laser-skin parameter combinations, i represents the serial number corresponding to the first parameter value and the second parameter value, and n represents the number corresponding to the first parameter value and the second parameter value.

7. The effect analysis system for laser freckle removal according to claim 1, characterized in that, Combining the collaborative adaptation value and the efficacy evaluation data, and analyzing the freckle-removing effect prediction trend of the target user includes: Performing data cleaning processing on the efficacy evaluation data to obtain pure efficacy evaluation data; Analyzing the evaluation labels corresponding to the pure efficacy evaluation data, and screening out the freckle-removing effect evaluation data from the pure efficacy evaluation data based on the evaluation labels; Extracting the freckle-removing effect characteristics in the freckle-removing effect evaluation data, and performing feature selection processing on the freckle-removing effect characteristics to obtain key effect characteristics; Based on the key effect characteristics, generating a trend prediction curve for the target user; According to the collaborative adaptation value, performing correction processing on the trend prediction curve to obtain the freckle-removing effect prediction trend of the target user.

8. The effect analysis system for laser freckle removal according to claim 1, characterized in that, Based on the pigment spot shape parameters, analyzing the evolution trend of the pigment spots of the target user includes: Identifying the shape indicators corresponding to the pigment spot shape parameters, and calculating the indicator similarity between the shape indicators; Based on the indicator similarity, performing parameter clustering processing on the pigment spot shape parameters to obtain clustered pigment spot shape parameters; Extract the time identifier corresponding to the morphological parameters of the clustered color spots; Combine the time identifier and the morphological parameters of the clustered color spots to calculate the index transition rate corresponding to the morphological index; Analyze the index evolution trend corresponding to the morphological index based on the index transition rate; Analyze the evolution trend of the color spots of the target user based on the index evolution trend; 9. The effect analysis system for laser freckle removal according to claim 8, characterized in that, The combining the time identifier and the morphological parameters of the clustered color spots to calculate the index transition rate corresponding to the morphological index includes: Based on the time identifier, sort the morphological parameters of the clustered color spots to obtain the sequential morphological parameters of the color spots; Perform quantization processing on the sequential morphological parameters of the color spots to obtain the morphological parameter values; Based on the morphological parameter values, calculate the index transition rate corresponding to the morphological index through the following formula: Among them, A represents the index transition rate corresponding to the morphological index, F a (t b+1 ) represents the morphological parameter value of the ath index in the morphological index at time point t b+1 , F a (t b ) represents the morphological parameter value of the ath index in the morphological index at time point t b , a represents the serial number corresponding to the morphological index, r represents the number of indicators corresponding to the morphological index, t b+1 and t b represent the (b + 1)th and bth time points respectively.

10. A method for analyzing the effect of laser freckle removal, characterized in that, The method includes: Obtain the time-series skin image data and the description of the freckle removal requirements of the target user, extract the freckle distribution characteristics and the morphological parameters of the color spots of the target user from the time-series skin image data, and set the freckle removal requirement tags of the target user based on the description of the freckle removal requirements; Based on the pigment spot distribution characteristics and the freckle removal requirement tags, construct the freckle feature matrix of the target user, perform correlation matching between the freckle feature matrix and the historical clinical treatment data in the preset clinical case database to obtain a set of matching cases, extract the laser parameter configuration and the efficacy evaluation data in the set of matching cases, collect the skin physiological parameters of the target user, and calculate the collaborative adaptation value of the laser parameter configuration corresponding to the skin physiological parameters; Combine the collaborative adaptation value and the efficacy evaluation data to analyze the freckle removal effect prediction trend of the target user, analyze the evolution trend of the color spots of the target user based on the morphological parameters of the color spots, and combine the freckle removal effect prediction trend and the evolution trend of the color spots to determine the efficacy threshold of the target user at different treatment stages; Based on the efficacy threshold and the freckle feature matrix, plan the laser freckle removal plan for the target user, and schedule the adverse effect avoidance criteria corresponding to the set of matching cases; Combine the laser freckle removal plan and the adverse effect avoidance criteria, perform laser freckle removal treatment on the target user, and collect the stage freckle removal data corresponding to each stage of the freckle removal treatment process in real time. Generate an analysis report on the freckle removal effect of the target user based on the stage freckle removal data.

Images