Thermal Margari operation comfort method and system based on skin parameters

Abstract

The invention relates to the technical field of medical cosmetology and skin health management, in particular to a thermal margari operation comfort method and system based on skin parameters, and the method comprises the steps: collecting various types of medication data of an operated person, constructing a historical behavior analysis scheme containing risk identification logic based on high-risk population data, and on this basis, establishing a risk identification logic analysis scheme based on the historical behavior analysis scheme; on the basis of the scheme, associated historical behavior data of low-risk crowds and other users are collected and analyzed, and multiple groups of multi-dimensional user historical behavior data are formed through integration. And finally, processing the data by using a preset comprehensive evaluation scheme, and calculating the skin side effect risk level of each operated person, so that personalized risk screening and feature checking are completed before an operation, and an objective basis is provided for clinically formulating a safer and more comfortable treatment scheme, and the treatment safety and the user experience are improved.

Description

Technical Field

[0001] This invention relates to the field of medical aesthetics and skin health management technology, and in particular to a method and system for improving the comfort of Thermage procedures based on skin parameters. Background Technology

[0002] Thermage, a common high-frequency monopolar radiofrequency skin tightening technology, stimulates collagen regeneration by applying heat energy to the dermis and subcutaneous tissue. Although the technology is generally considered safe, in practice, due to differences in individual skin characteristics, physiological conditions, and medication history, it can still cause varying degrees of skin side effects such as redness, swelling, blisters, pigmentation, or burns. These side effects not only affect the treatment outcome and recovery period but also directly impact the comfort and treatment experience of the patient, becoming one of the key issues hindering the widespread and comfortable application of this technology.

[0003] Currently, the assessment of skin side effects risks in pre-Thermage treatment evaluation mainly relies on the operating physician's clinical experience and simple questioning. The standard procedure focuses on inquiring about current medication history, especially photosensitizing or anticoagulant drugs, but the assessment method is rather fragmented and subjective. For drug categories that are not directly contraindicated but can indirectly increase risk by affecting skin barrier function, microcirculation, or inflammatory potential, there is a lack of systematic classification and risk quantification. Furthermore, existing methods fail to fully utilize multi-dimensional information such as the patient's past skin imaging history and behavioral preference data for correlation analysis, resulting in a single-dimensional risk assessment, insufficient predictability, and difficulty in achieving refined individual risk stratification.

[0004] The shortcomings of existing technologies are mainly reflected in the following aspects: First, risk identification is passive and delayed, relying heavily on typical contraindication signals that have already occurred, and failing to delve deeply into potential risks; second, data utilization is fragmented, with skin parameters, medication history, and historical behavior data existing in isolation, failing to form an effective comprehensive analysis model; third, judgment criteria are subjective and inconsistent, lacking an objective, systematic, and repeatable risk assessment logical framework. Therefore, there is an urgent need for a standardized method that can integrate multi-source heterogeneous data, automatically identify complex risk patterns, and provide personalized skin side effect risk predictions for each user, in order to guide clinicians in developing more accurate, safe, and comfortable operating procedures. Summary of the Invention

[0005] To achieve the above objectives, this application provides the following technical solution:

[0006] A method for improving the comfort of Thermage procedures based on skin parameters, characterized by comprising:

[0007] Collect the attribute characteristics of the person undergoing Thermage treatment, including multiple types of medication data;

[0008] Based on the aforementioned multiple types of medication data, the historical behavior data of the Thermage treatment recipients were collected sequentially to obtain multiple sets of historical behavior data of Thermage treatment recipients.

[0009] Based on the pre-set plan and the historical behavioral data of the multiple groups of Thermage patients, the risk of skin side effects of the attribute characteristics of the Thermage patients is judged to verify the attribute characteristics of the Thermage patients.

[0010] Furthermore, the method also includes:

[0011] The multiple types of medication data include a first type of medication data and a second type of medication data. The first type of medication data consists of data from Thermage patients with low risk of skin side effects, while the second type of medication data consists of data from Thermage patients with high risk of skin side effects.

[0012] Based on the aforementioned multiple types of medication data, the historical behavioral data of the individuals who underwent Thermage treatments are collected sequentially, specifically including:

[0013] Collect historical behavioral data of operators who underwent Thermage treatments;

[0014] Based on the historical behavior plan of the Thermage user, the first group of historical behavior data of Thermage user is associated with the first type of drug use data.

[0015] The aforementioned plan for collecting the historical behavior data of the operator performing Thermage treatments specifically includes:

[0016] Based on the second type of medication data, the risk coefficient of Thermage image attributes to the characteristic data of Thermage users is determined, and the historical behavior plan of Thermage users includes the risk coefficient.

[0017] Furthermore, the method of determining the first set of historical behavior data of Thermage users associated with the first type of medication data based on the historical behavior plan of Thermage users specifically includes:

[0018] Based on the Thermage image attributes of each person undergoing Thermage treatment in the first type of medication data, and the risk coefficient of the Thermage image attributes to the characteristic data of the person undergoing Thermage treatment, the characteristic data of each person undergoing Thermage treatment is determined.

[0019] The step of determining the risk coefficient of Thermage image attributes to the characteristic data of Thermage users based on the second type of medication data specifically includes:

[0020] If the Thermage image attribute is a certain accident image, the risk coefficient of the Thermage image attribute to the characteristic data of the person undergoing Thermage includes: the probability value that the person undergoing Thermage has a certain characteristic.

[0021] Furthermore, the method specifically includes:

[0022] Based on the second type of medication data, at least one Thermage user identification strategy is used, wherein different Thermage user identification strategies have different structures; the Thermage user historical behavior scheme includes the operation logic of the at least one Thermage user identification strategy.

[0023] The step of determining the first group of historical behavior data of Thermage users associated with the first type of medication data based on the historical behavior scheme of Thermage users specifically includes: processing the Thermage user attribute features of each Thermage user in the first type of medication data sequentially through the at least one Thermage user identification strategy to obtain the Thermage user classification data of each Thermage user.

[0024] The first group of historical behavior data of Thermage patients includes the classification data of Thermage patients for each individual.

[0025] Furthermore, the method specifically includes:

[0026] Based on the second type of medication data, the correlation data between the characteristic data of the person undergoing Thermage treatment and the operation data of the person undergoing Thermage treatment on the application terminal is determined; the historical behavior plan of the person undergoing Thermage treatment includes the correlation data.

[0027] The step of determining the first group of historical behavior data of Thermage users associated with the first type of medication data based on the historical behavior scheme of Thermage users specifically includes: comparing the operation data of Thermage users operating application terminals in the first type of medication data with the operation data of Thermage users in the association relationship to obtain the Thermage user feature data of each Thermage user, and the first group of historical behavior data of Thermage users includes the Thermage user feature data of each Thermage user.

[0028] Furthermore, before determining the risk of skin side effects based on the pre-set plan and the historical behavioral data of the multiple groups of Thermage patients, the method further includes:

[0029] The index uses the identifiers of the individuals who received Thermage treatments to index multiple sets of historical behavioral data for each individual.

[0030] Furthermore, the method, which determines the risk of skin side effects based on the pre-set plan and the historical behavioral data of the multiple groups of Thermage recipients, specifically includes:

[0031] Determine the importance value of sequentially associating the multiple sets of historical behavior data of the operators of Thermage treatments;

[0032] Based on the historical behavioral data of each group of Thermage patients and their associated importance values, as well as the preset function calculation formula, the risk of skin side effects of each Thermage patient's attribute characteristics is calculated.

[0033] Furthermore, the method calculates the skin side effect risk of a particular Thermage patient based on their historical behavioral data and associated importance values, as well as a pre-defined function, specifically including:

[0034] The historical behavior data of a specific Thermage patient in each group of Thermage patients' historical behavior data is standardized sequentially to obtain standardized data for each group.

[0035] The sum of the products of each set of standardized data and the associated importance value is taken as the skin side effect risk of a certain Thermage patient's attribute characteristics.

[0036] Furthermore, the method, which determines the risk of skin side effects based on the pre-set plan and the historical behavioral data of the multiple groups of Thermage recipients, specifically includes:

[0037] Based on historical behavioral data of multiple Thermage users and a pre-built machine learning model, the risk of skin side effects for each Thermage user is determined by their individual attributes.

[0038] The machine learning model is used to calculate the risk of skin side effects based on historical behavioral data of multiple groups of Thermage patients.

[0039] According to a second aspect of the present invention, the present invention claims protection for a Thermage procedure comfort system based on skin parameters, and a Thermage procedure comfort method based on skin parameters, comprising:

[0040] The data acquisition unit for Thermage users is used to collect the attribute characteristics of Thermage users, which include multiple types of medication data. The multiple types of medication data include a first type of medication data and a second type of medication data. The first type of medication data is data of Thermage users with low risk of skin side effects, and the second type of medication data is data of Thermage users with high risk of skin side effects.

[0041] The classification and collection unit is used to sequentially collect the associated historical behavior data of the Thermage users based on the multiple types of medication data, and obtain multiple sets of historical behavior data of Thermage users.

[0042] The skin side effect risk unit is used to determine the skin side effect risk of the Thermage patient based on the preset plan and the historical behavioral data of the multiple groups of Thermage patients, so as to verify the attribute characteristics of the Thermage patients.

[0043] The classification and collection unit is specifically used to collect the historical behavior patterns of the Thermage users; and to determine the first group of historical behavior data of Thermage users associated with the first type of medication data based on the historical behavior patterns of the Thermage users.

[0044] The aforementioned scheme for collecting historical behavior data of Thermage users specifically includes: based on the second type of medication data, determining the risk coefficient of Thermage image attributes to the characteristic data of Thermage users, wherein the historical behavior scheme of Thermage users includes the risk coefficient.

[0045] The first set of historical behavior data of Thermage users, which is used to determine the association between the first type of medication data and the historical behavior data of Thermage users based on the historical behavior plan of Thermage users, specifically includes:

[0046] Based on the Thermage image attributes of each person undergoing Thermage treatment in the first type of medication data, and the risk coefficient of the Thermage image attributes to the characteristic data of the person undergoing Thermage treatment, the characteristic data of each person undergoing Thermage treatment is determined.

[0047] The step of determining the risk coefficient of Thermage image attributes to the characteristic data of Thermage users based on the second type of medication data specifically includes:

[0048] If the Thermage image attribute is a certain accident image, the risk coefficient of the Thermage image attribute to the characteristic data of the person undergoing Thermage includes: the probability value that the person undergoing Thermage has a certain characteristic.

[0049] This invention relates to the field of medical aesthetics and skin health management technology, and particularly to a method and system for improving the comfort of Thermage procedures based on skin parameters. It involves collecting various medication data from the patients and constructing a historical behavior analysis scheme incorporating risk identification logic based on high-risk population data. Building upon this scheme, it collects and analyzes related historical behavior data from low-risk individuals and other users, integrating them into multi-dimensional user historical behavior data sets. Finally, a pre-set comprehensive assessment scheme is used to process this data, calculating the skin side effect risk level for each patient. This allows for personalized risk screening and feature verification before the procedure, aiming to provide objective evidence for developing safer and more comfortable treatment plans in clinical settings, thereby improving treatment safety and user experience. Attached Figure Description

[0050] Figure 1 A flowchart illustrating a method for improving the comfort of Thermage procedures based on skin parameters, as claimed in an embodiment of the present invention.

[0051] Figure 2 This is a structural diagram of a Thermage operation comfort system based on skin parameters, which is claimed in an embodiment of the present invention. Detailed Implementation

[0052] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0053] The terms "first," "second," and "third" in this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of those features. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. All directional indications in the embodiments of this application, such as up, down, left, right, front, back, etc., are only used to explain the relative positional relationships and movements between components in a specific orientation as shown in the accompanying drawings. If the specific orientation changes, the directional indications will change accordingly. Furthermore, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0054] References to embodiments herein mean that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0055] According to a first embodiment of the present invention, the present invention claims protection for a method for improving the comfort of Thermage procedures based on skin parameters, referring to... Figure 1 ,include:

[0056] Collect the attribute characteristics of the person undergoing Thermage treatment, including multiple types of medication data;

[0057] Based on the aforementioned multiple types of medication data, the historical behavior data of the Thermage treatment recipients were collected sequentially to obtain multiple sets of historical behavior data of Thermage treatment recipients.

[0058] Based on the pre-set plan and the historical behavioral data of the multiple groups of Thermage patients, the risk of skin side effects of the attribute characteristics of the Thermage patients is judged to verify the attribute characteristics of the Thermage patients.

[0059] In this embodiment, the aim is to pre-assess the risk of side effects that individual skin may experience from Thermage energy stimulation before treatment by collecting and analyzing data, thereby providing a basis for developing personalized and comfortable operating parameters.

[0060] The method comprises three logically interconnected core phases.

[0061] Phase 1: Collecting Attribute Characteristics of Thermage Subjects; This phase is the step in establishing initial user profiles. Operators comprehensively collect static characteristic information of individuals about to receive Thermage treatment, either through standardized electronic questionnaires, face-to-face interviews, and review of medical records. The attribute characteristics of Thermage subject recipients constitute a comprehensive dataset, containing not only basic demographic information such as age, gender, and skin type (e.g., Fitzpatrick classification), but also, at its core, multi-category medication data. Here, "multi-category" is not a simple quantitative concept, but rather a collection of classifications based on medical knowledge of the potential impact of drugs on skin physiological state, healing ability, and photothermal response.

[0062] For example, this collection may include, but is not limited to, the history of use of oral medications such as retinoids, antibiotics, immunosuppressants, topical medications such as retinoic acid creams, high-concentration fruit acid products, and certain supplements such as photosensitive herbal supplements. The focus of the collection is on recording the type of medication, dosage, duration of use, and time of discontinuation; these are fundamental data for assessing the current condition of the skin and potential risks.

[0063] The second stage involves sequentially collecting related historical behavioral data based on multiple types of medication data. This stage is a dynamic analysis and data expansion phase of the methodology. It does not view medication data in isolation, but rather uses it as clues or triggering conditions to actively trace and mine dynamic historical information that is related to the characteristics of this type of medication and can more deeply reflect the true condition of the skin or user behavior patterns. Sequential collection means that there is a sequential or logical dependency in the processing, and the depth and breadth of subsequent data collection may be determined based on the risk level of the medication data. The related historical behavioral data of Thermage users refers to data that can indirectly or directly reflect skin tolerance, repair ability, or user response patterns to treatment.

[0064] For example, for users who have used specific medications, further searches will be conducted to determine if they have received similar phototherapy in the past, their skin reaction records before and after treatment (such as the duration and severity of erythema and edema), or changes in long-term skin monitoring data. Through this correlation mining, isolated current medication characteristics are connected with rich, multi-dimensional chains of historical behavioral evidence, ultimately forming multiple sets of historical behavioral data of Thermage users. These sets may represent data sets from different sources such as clinical records, historical reports from skin analyzers, post-operative follow-up feedback, or different types such as imaging data, time-series data of physiological parameters, and subjective feedback data.

[0065] The third stage: Based on the pre-set plan and multiple sets of historical behavioral data, assess the risk of skin side effects and verify attribute characteristics. This stage is the comprehensive assessment and decision-making stage. The pre-set plan is a pre-defined risk assessment logic framework or model that defines how to interpret and integrate all the heterogeneous data collected in the previous steps. This plan may integrate the reasoning path of dermatology clinical guidelines, statistical model rules, or machine learning models. Input multiple sets of historical behavioral data of Thermage users into this pre-set plan, and perform calculations, matching, and reasoning through the built-in logic of the plan. The output result is a comprehensive judgment of the risk of skin side effects of the attribute characteristics of the Thermage user. This judgment can be a risk level such as high, medium, low, risk score, or a specific risk description such as a significant risk of delayed epidermal healing. Finally, verifying the attribute characteristics of the Thermage user means that this risk assessment process also verifies and labels the initially collected attribute characteristics, especially the medication data.

[0066] For example, based on the analysis of historical behavioral data, it may be found that although a user has not reported the use of high-risk drugs, their historical skin reaction pattern is highly consistent with high-risk characteristics. This may suggest that the medication history needs to be re-verified or that the user should be classified into a group that requires careful handling. The whole process constitutes a complete closed loop from feature collection to in-depth behavioral analysis and then to comprehensive risk assessment.

[0067] Furthermore, the method also includes:

[0068] The multiple types of medication data include a first type of medication data and a second type of medication data. The first type of medication data consists of data from Thermage patients with low risk of skin side effects, while the second type of medication data consists of data from Thermage patients with high risk of skin side effects.

[0069] Based on the aforementioned multiple types of medication data, the historical behavioral data of the individuals who underwent Thermage treatments are collected sequentially, specifically including:

[0070] Collect historical behavioral data of operators who underwent Thermage treatments;

[0071] Based on the historical behavior plan of the Thermage user, the first group of historical behavior data of Thermage user is associated with the first type of drug use data.

[0072] The aforementioned plan for collecting the historical behavior data of the operator performing Thermage treatments specifically includes:

[0073] Based on the second type of medication data, the risk coefficient of Thermage image attributes to the characteristic data of Thermage users is determined, and the historical behavior plan of Thermage users includes the risk coefficient.

[0074] In this embodiment, the specific composition of multiple types of medication data is clarified to include at least two categories with clear risk indications; the first type of medication data is defined as medication records that characterize a low risk of skin side effects. This usually refers to drugs that have not been found to produce significant adverse interactions with Thermage treatment in a large number of clinical practices, or have little effect on skin barrier function, inflammatory response and healing ability.

[0075] For example, conventional antihypertensive drugs, statins, and most vitamin supplements, except for those with photosensitivity, can be categorized into this type, provided that standard discontinuation guidelines are strictly followed. The second category of medication data is the opposite, specifically referring to medication histories with a high risk of skin side effects. These drugs usually directly or indirectly affect skin integrity, immune response, or sensitivity to heat damage. Typical examples include: retinoids such as isotretinoin, which may still affect sebaceous gland function and skin repair for several months after discontinuation; certain antibiotics that can cause photosensitivity reactions, such as doxycycline and tetracycline; and topical or applied corticosteroids and chemotherapy drugs. This dichotomy of medication data is a prerequisite for the differentiated and refined analysis of the entire method.

[0076] Secondly, the specific implementation logic of the step of collecting historical behavioral data of Thermage users based on multiple types of medication data was refined; this logic is divided into two sub-steps: the first step is to collect historical behavioral data of Thermage users.

[0077] The solution here does not refer to the historical data of a single user, but rather a set of universally applicable analytical rules, feature association knowledge, or risk identification patterns extracted from the historical data of the population corresponding to the second category of medication data in high-risk groups. Specifically, a core action in constructing this solution is to determine the risk coefficient of Thermage image attributes to the characteristic data of Thermage users based on the second category of medication data. This means that by utilizing a large amount of Thermage image attributes accumulated by the known high-risk population in the second category of medication groups—that is, skin image feature data obtained before treatment through skin detectors, hyperspectral imaging, and other equipment, such as quantitative or morphological indicators like capillary density, pigment distribution, and texture roughness—data mining and statistical analysis are conducted to identify which specific image attribute patterns, such as a certain red area distribution pattern or epidermal translucency value range, have a stable and significant correlation with certain adverse clinical judgment characteristics of Thermage users, such as thin and delicate skin, easy capillary dilation, and active melanocytes. The strength of this correlation is quantified as a risk coefficient, which can be a correlation coefficient, an odds ratio, or a conditional probability value. All these sets of knowledge related to image attributes, features, and risk coefficients constitute an important part of the historical behavior plan of the person undergoing Thermage treatment.

[0078] The second step is to determine the first set of historical behavior data of Thermage users based on the historical behavior scheme of Thermage users. This describes how to apply the experience learned from high-risk groups, namely the historical behavior scheme, to examine the population corresponding to the first type of medication data of low-risk groups. The current skin image attributes of the first type of medication users are input into the scheme. Using the risk coefficient association rules in the scheme, it is used to infer what potential skin features these low-risk users may have that have not yet been directly revealed by their medication history, thereby generating the first set of historical behavior data of Thermage users. This set of data is essentially feature inference data derived from image analysis.

[0079] Furthermore, the method of determining the first set of historical behavior data of Thermage users associated with the first type of medication data based on the historical behavior plan of Thermage users specifically includes:

[0080] Based on the Thermage image attributes of each person undergoing Thermage treatment in the first type of medication data, and the risk coefficient of the Thermage image attributes to the characteristic data of the person undergoing Thermage treatment, the characteristic data of each person undergoing Thermage treatment is determined.

[0081] The step of determining the risk coefficient of Thermage image attributes to the characteristic data of Thermage users based on the second type of medication data specifically includes:

[0082] If the Thermage image attribute is a certain accident image, the risk coefficient of the Thermage image attribute to the characteristic data of the person undergoing Thermage includes: the probability value that the person undergoing Thermage has a certain characteristic.

[0083] In this embodiment, a specific execution path is given for the process of determining the first group of historical behavior data of the first type of medication data associated with the historical behavior of the Thermage user based on the historical behavior plan of the user. Each user in the first type of medication data needs to be processed one by one.

[0084] For any given user, the operation steps are as follows: First, obtain the user's current Thermage image attributes, which may be the results of skin image analysis taken before this treatment. Then, access the pre-constructed historical behavior plan for Thermage users. This plan stores the risk coefficient correspondence between various Thermage image attributes derived from the analysis of the second group of drug users and the characteristic data of Thermage users. Compare or match the user's image attributes with the image attribute patterns in the plan. If the user's image attributes match a certain pattern defined in the plan, then based on the risk coefficient (association rule) bound to that pattern in the plan, logically determine that the user has corresponding skin characteristic data.

[0085] For example, the scheme defines: image attribute A, such as a specific morphology of capillary plexus, → associated feature B, such as a high risk coefficient for skin barrier dysfunction. When an image of a first-class user is identified as having attribute A, it is determined that the user has feature B, and this feature B is recorded as a historical behavioral data of the user. The set of feature data obtained by all first-class users through this process constitutes the first set of historical behavioral data.

[0086] The process of constructing a scheme to determine the risk coefficient of Thermage image attributes to the characteristic data of Thermage users based on the second type of medication data is illustrated through a specific scenario. Here, a concept is introduced: an "accident image"; the accident here does not refer to an actual medical accident, but to a specific image pattern that is marked as abnormal, high-risk, or strongly correlated with adverse outcomes in medical image analysis.

[0087] For example, in the pre-treatment evaluation of Thermage, an atypical, poorly defined patchy erythema image may be marked as an accident image by an experienced physician or through historical data analysis because it may be associated with an excessive postoperative inflammatory response. When the analyzed Thermage image attribute is identified as such an accident image, the risk coefficient determined from it is specifically expressed as the probability value of Thermage being performed by a certain operator. This means that the risk coefficient is quantified as a probability estimate in this context.

[0088] For example, analysis of historical data revealed that among the second group of patients, a high percentage of individuals exhibiting image pattern X (accident image) had a high probability value and were later clinically diagnosed or assessed as having characteristic Y, such as delayed superficial dermal repair ability. This percentage, the probability value, is used as a quantitative indicator of the strength of the association between the image attribute and the characteristic and is stored in the historical behavior record.

[0089] Furthermore, the method specifically includes:

[0090] Based on the second type of medication data, at least one Thermage user identification strategy is used, wherein different Thermage user identification strategies have different structures; the Thermage user historical behavior scheme includes the operation logic of the at least one Thermage user identification strategy.

[0091] The step of determining the first group of historical behavior data of Thermage users associated with the first type of medication data based on the historical behavior scheme of Thermage users specifically includes: processing the Thermage user attribute features of each Thermage user in the first type of medication data sequentially through the at least one Thermage user identification strategy to obtain the Thermage user classification data of each Thermage user.

[0092] The first group of historical behavior data of Thermage patients includes the classification data of Thermage patients for each individual.

[0093] In this embodiment, the specific implementation method of collecting the historical behavior plan of the person undergoing Thermage treatment is as follows: at least one identification strategy for the person undergoing Thermage treatment is used based on the second type of medication data, wherein the structure of different identification strategies for the person undergoing Thermage treatment is different.

[0094] This means that when analyzing data on high-risk second-category drug users, a single analysis model or rule set is not used; instead, multiple identification strategies are deployed in parallel or sequentially. The key is the difference in structure, which emphasizes that these strategies have fundamental differences in algorithm principles, data processing methods, or logical architecture.

[0095] For example, Strategy 1 might be a decision tree rule set based on solidified expert experience, which classifies user data through a series of if-then conditional branches; Strategy 2 might be a clustering analysis model, which unsupervisedly divides users into different clusters based on the similarity of skin physiological parameters; Strategy 3 might be a deep learning convolutional neural network, which automatically learns and extracts deep features directly from the pixels of the original skin image for classification. Each strategy, from a different perspective and methodology, provides its own logical solution to the problem of how to identify user risk characteristics. These different operational logics—that is, the specific process framework of feature selection, calculation, and decision-making within each strategy—are themselves integrated as valuable knowledge into the historical behavior plan of Thermage users.

[0096] Therefore, this scheme not only includes the final output rules of the strategy, but may also include meta-information such as the strategy's configuration parameters and feature importance ranking.

[0097] When applying this scheme to determine the historical behavioral data associated with the first type of medication data, the specific operation is as follows: The attribute characteristics of each Thermage user in the first type of medication data are processed sequentially through at least one Thermage user identification strategy. The attribute characteristics of the first type of medication users may include basic information, some skin parameters, etc., as input, and are sequentially fed to the identification strategies with different structures defined in the scheme. Each strategy independently processes the user's input data according to its own operating logic and generates an intermediate result or classification insight. This is the Thermage user classification data.

[0098] For example, a rule-based strategy might output type A; a clustering strategy might output the cluster it belongs to: the third cluster; a neural network strategy might output feature vectors: [v1, v2, v3…] and a classification label. All these strategies generate a collection of multi-perspective classification data for the same user, collectively forming a rich, multi-dimensional profile of that user. This collection of profiles for all users in the first category constitutes the first set of historical behavioral data for Thermage treatment recipients. This method, by integrating heterogeneous analytical perspectives, aims to obtain a more robust and comprehensive user profile than a single strategy.

[0099] Furthermore, the method specifically includes:

[0100] Based on the second type of medication data, the correlation data between the characteristic data of the person undergoing Thermage treatment and the operation data of the person undergoing Thermage treatment on the application terminal is determined; the historical behavior plan of the person undergoing Thermage treatment includes the correlation data.

[0101] The step of determining the first group of historical behavior data of Thermage users associated with the first type of medication data based on the historical behavior scheme of Thermage users specifically includes: comparing the operation data of Thermage users operating application terminals in the first type of medication data with the operation data of Thermage users in the association relationship to obtain the Thermage user feature data of each Thermage user, and the first group of historical behavior data of Thermage users includes the Thermage user feature data of each Thermage user.

[0102] In this embodiment, the specific method of this claim in the step of collecting the historical behavior records of Thermage users is as follows: based on the second type of medication data, determine the correlation data between the characteristic data of Thermage users and the operation data of Thermage users on the application terminal; here a new data type is introduced: Thermage user operation data on the application terminal; this refers to the interactive behavior logs generated by users before and after receiving Thermage treatment through related mobile applications, tablet consultations, online assessment questionnaires and other terminal interfaces.

[0103] For example, the time users spend on each item in the pre-operative questionnaire, the adjustment trajectory of the pain sensitivity slider, the repeatedly viewed post-operative care instructions, and frequently appearing symptom keywords in historical consultation records; taking the high-risk group of the second medication user as the research subject, the correlation analysis was performed between their clinical assessment of Thermage user characteristics data, such as high skin sensitivity and significant anxiety as determined by doctors, and their terminal operation data. Data mining techniques such as frequent pattern mining, sequence analysis, and correlation analysis were used to identify the correspondence between stable behavioral patterns and clinical characteristics.

[0104] For example, analysis revealed that users clinically assessed as having high anxiety and high skin sensitivity generally exhibited a complex sequence of behaviors, including excessive time spent in the 'pain management' section, frequent returns to modify 'expected results' options, and logging into the application to read 'side effects' articles more than a certain number of times within a week prior to surgery. These findings were extracted into structured relational data, which may take the form of a set of rules representing behavioral pattern X → relational feature Y with confidence level Z%. This relational data became a core component of the historical behavioral plan.

[0105] When applying this scheme to analyze the historical behavioral data of Category I medication users, the specific steps are as follows: The operation data of each Thermage user operating the application terminal in the Category I medication data is compared with the operation data of Thermage users in the associated relationships. For each new user using only Category I low-risk medications, complex image analysis or multiple clinical assessments are no longer required. Instead, their real-time or recent operation data on the terminal application is directly collected. Then, this behavioral data is compared with the associated relationship data stored in the historical behavior scheme using pattern matching or similarity calculation. By comparison, the new user's behavioral pattern is identified as most closely similar to which behavioral pattern(s) defined in the historical scheme. Based on the matching results and the clinical feature data associated with that historical behavioral pattern, an inference about the new user's skin characteristics can be obtained.

[0106] For example, user A's terminal operation data shows that they quickly completed all questionnaires and rarely viewed post-operative content, matching their historical behavioral pattern M: high efficiency and low attention. This pattern has historically been strongly correlated with good skin tolerance and low anxiety, thus inferring that user A possesses this characteristic. This inferred characteristic data is then included as the operator's characteristic data for user A's Thermage treatment and incorporated into the first set of historical behavioral data. This method utilizes easily accessible, non-invasive behavioral data to indirectly assess user status, expanding data dimensions while also improving the convenience of assessment.

[0107] Furthermore, before determining the risk of skin side effects based on the pre-set plan and the historical behavioral data of the multiple groups of Thermage patients, the method further includes:

[0108] The index uses the identifiers of the individuals who received Thermage treatments to index multiple sets of historical behavioral data for each individual.

[0109] In this embodiment, after generating multiple sets of historical behavior data for Thermage users, this data may be distributed across different database tables, output files of analysis modules, or temporary storage areas. For example, one set of data may come from the image analysis module, another set from the multi-strategy recognition module, and yet another set from the behavior correlation analysis module. Each set of data contains analysis results for multiple users.

[0110] Before making a final comprehensive risk assessment, it is essential to ensure that all scattered data fragments belonging to the same user are accurately aggregated to form a complete personal data view. To this end, this claim introduces and implements a key step: indexing multiple sets of historical behavior data of each Thermage user through the identifier of the Thermage user.

[0111] Thermage is identified by operators using a unique identifier assigned to each user, such as an encrypted patient ID or medical record number. This identifier is linked to all records of that user at the source of all data collection and processing. Using this unique identifier as a retrieval key, it acts like a central scheduler to perform global scanning and indexing across multiple sets of historical behavioral data.

[0112] The specific operation is as follows: based on this identifier, find the user's record in the first set of data, find another record belonging to the same user in the second set of data, and so on, until all data entries of the user are extracted from all available data sets. This process links and integrates all historical behavior analysis results of different dimensions generated around the user through its unique identifier.

[0113] This step forms the basis for any subsequent personalized analysis, whether it is weighted calculation or model prediction. It ensures that when calculating the risk of a user's skin side effects, it is based on the user's complete and multi-dimensional data profile, rather than data mixed with other users' information or incomplete fragmented data, thus fundamentally guaranteeing the individual accuracy and reliability of risk assessment.

[0114] Furthermore, the method, which determines the risk of skin side effects based on the pre-set plan and the historical behavioral data of the multiple groups of Thermage recipients, specifically includes:

[0115] Determine the importance value of sequentially associating the multiple sets of historical behavior data of the operators of Thermage treatments;

[0116] Based on the historical behavioral data of each group of Thermage patients and their associated importance values, as well as the preset function calculation formula, the risk of skin side effects of each Thermage patient's attribute characteristics is calculated.

[0117] In this embodiment, the first layer is weight allocation: determining the importance value of sequentially associating multiple groups of historical behavioral data of Thermage users. In the preset scheme, an importance value has been preset for each group of historical behavioral data of Thermage users of different types or from different sources; the determination of this value is based on medical prior knowledge and analysis of the validity of historical data.

[0118] For example, skin parameter data sets that directly reflect the physiological state of the skin and are measured by high-precision instruments, such as barrier function and moisture content, may have higher objectivity and direct correlation with side effects, and therefore are assigned higher importance values. On the other hand, feature data sets indirectly inferred through user behavior, although valuable, may be assigned relatively lower importance values ​​due to their indirectness and subjectivity. Importance values ​​can be specific weighting coefficients such as 0.8, 0.5, and 0.3, or they can be high, medium, and low levels corresponding to specific numerical values. This judgment process is static and built into the design of the preset scheme.

[0119] The second layer is a comprehensive calculation: based on the historical behavioral data of each group of Thermage users and their associated importance values, and a pre-defined function, the risk of skin side effects for each Thermage user's attributes is calculated. This is a dynamic calculation process tailored to each user. For each user to be evaluated, the specific numerical values ​​or scores of that user in each group of historical behavioral data are first obtained through indexing. These data may already be processed standardized values ​​or risk scores. Then, the calculation is performed according to the pre-defined function. The core logic of this function is: multiply the user's score in each group of data by the corresponding importance value of that group (i.e., perform weighted calculation), and then, according to the calculation formula, usually sum or possibly a more complex combination, combine all weighted results to generate a single, comprehensive risk value. This final calculated value represents the quantitative judgment of the user's risk of skin side effects. This method makes the risk assessment process transparent and interpretable by explicitly defining the contribution weights of different data sources.

[0120] Furthermore, the method calculates the skin side effect risk of a particular Thermage patient based on their historical behavioral data and associated importance values, as well as a pre-defined function, specifically including:

[0121] The historical behavior data of a specific Thermage patient in each group of Thermage patients' historical behavior data is standardized sequentially to obtain standardized data for each group.

[0122] The sum of the products of each set of standardized data and the associated importance value is taken as the skin side effect risk of a certain Thermage patient's attribute characteristics.

[0123] In this embodiment, when calculating the risk of skin side effects for a specific user, denoted as user Z, the following operations are performed:

[0124] Step 1: Data Standardization; Since the historical behavioral data of the operators of Thermage treatments in different groups may have completely different dimensions, numerical ranges and distribution characteristics, for example, one group of data is a percentage score of 0-100, another group is a level score of 1-5, and another group is continuous temperature measurement values, directly performing weighted summation will lead to the data with larger dimensions dominating the results.

[0125] Therefore, standardization must be performed first. The historical behavioral data of a specific Thermage user from each group of users' historical behavior data must be standardized sequentially. This means that for user Z, the values ​​V1 in the first group, V2 in the second group, V3 in the third group, and so on, are extracted. Then, according to the standardization method defined for each group of data in the pre-defined scheme, such as min-max scaling or Z-score standardization, V1, V2, V3, etc., are independently transformed to a uniform, dimensionless scale. For example, they are all transformed to a distribution between 0 and 1, or with a mean of 0 and a standard deviation of 1. After this step, we obtain a new set of values ​​for user Z corresponding to each group of data: S1V1 after standardization, S2V2 after standardization, S3V3 after standardization, etc. These standardized data sets are comparable.

[0126] Step 2: Weighted summation to obtain the final risk value; retrieve the importance values ​​associated with each group of data from the preset plan, denoted as W1, W2, W3, ..., and then perform the calculation: multiply the first group of standardized data S1 by the first group of importance value W1 to obtain the weighted value P1 = S1 × W1; similarly, obtain P2 = S2 × W2, P3 = S3 × W3, ... Finally, add the products of each group of standardized data and the associated importance values ​​to obtain the final risk value R = P1 + P2 + P3 + ... This sum R is used as the skin side effect risk of a certain Thermage treatment recipient's attribute characteristics. This R value integrates the performance of user Z across all dimensions.

[0127] Furthermore, the method, which determines the risk of skin side effects based on the pre-set plan and the historical behavioral data of the multiple groups of Thermage recipients, specifically includes:

[0128] Based on historical behavioral data of multiple Thermage users and a pre-built machine learning model, the risk of skin side effects for each Thermage user is determined by their individual attributes.

[0129] The machine learning model is used to calculate the risk of skin side effects based on historical behavioral data of multiple groups of Thermage patients.

[0130] In this embodiment, the core of the pre-configured solution is one or a set of pre-configured machine learning models. These models are not based on fixed weighted rules, but rather learn automatically from a large number of historical cases how to predict risk based on multi-dimensional inputs using a data-driven approach.

[0131] First, model construction and pre-deployment: Before deployment, the machine learning model needs to be trained using a dataset containing a large number of historical cases. This training set must include multiple sets of historical behavioral data from Thermage users for each case as input features (the reason the model learns) and the actual skin side effects (none, mild, moderate, severe) for each case as labels or target values ​​(the result the model predicts). During training, the model automatically explores and discovers the hidden, non-linear correlation patterns and decision boundaries between these complex, high-dimensional input features and the final risk outcome through its internal algorithms, such as backpropagation in neural networks and node splitting in decision trees. After training, the model's internal parameters, such as the weights of the neural network and the structure of the decision tree, are fixed, forming a prediction function that encapsulates this complex mapping relationship. This trained model is completely saved and deployed, becoming the pre-deployed machine learning model, which itself is an intelligent embodiment of the pre-deployed solution; its function is clearly defined as calculating the risk of skin side effects based on multiple sets of historical behavioral data from Thermage users.

[0132] Secondly, the application of the model and risk assessment: When evaluating new users, following all the aforementioned steps, multiple sets of historical behavioral data of the users who underwent Thermage treatment are collected and generated. These data are then organized into a fixed-format input feature vector required by the model through indexing. This feature vector is then input into a pre-set machine learning model. The model performs a series of complex mathematical transformations and logical judgments internally. This process is a black box, but it follows the trained parameters and ultimately outputs a risk assessment of skin side effects for the user. This output can be a direct classification of risk category or a continuous numerical regression prediction representing the probability of risk.

[0133] For example, the model might output a high risk, or a percentage probability of moderate or higher side effects. The core advantage of this approach lies in its ability to handle highly complex and high-dimensional feature interactions, potentially uncovering predictive patterns that surpass human empirical rules, thereby enabling more accurate and automated risk assessment.

[0134] According to a second embodiment of the present invention, referring to Figure 2 This invention claims protection for a Thermage procedure comfort system based on skin parameters, and a Thermage procedure comfort method based on skin parameters, comprising:

[0135] The data acquisition unit for Thermage users is used to collect the attribute characteristics of Thermage users, which include multiple types of medication data. The multiple types of medication data include a first type of medication data and a second type of medication data. The first type of medication data is data of Thermage users with low risk of skin side effects, and the second type of medication data is data of Thermage users with high risk of skin side effects.

[0136] The classification and collection unit is used to sequentially collect the associated historical behavior data of the Thermage users based on the multiple types of medication data, and obtain multiple sets of historical behavior data of Thermage users.

[0137] The skin side effect risk unit is used to determine the skin side effect risk of the Thermage patient based on the preset plan and the historical behavioral data of the multiple groups of Thermage patients, so as to verify the attribute characteristics of the Thermage patients.

[0138] The classification and collection unit is specifically used to collect the historical behavior patterns of the Thermage users; and to determine the first group of historical behavior data of Thermage users associated with the first type of medication data based on the historical behavior patterns of the Thermage users.

[0139] The aforementioned scheme for collecting historical behavior data of Thermage users specifically includes: based on the second type of medication data, determining the risk coefficient of Thermage image attributes to the characteristic data of Thermage users, wherein the historical behavior scheme of Thermage users includes the risk coefficient.

[0140] The first set of historical behavior data of Thermage users, which is used to determine the association between the first type of medication data and the historical behavior data of Thermage users based on the historical behavior plan of Thermage users, specifically includes:

[0141] Based on the Thermage image attributes of each person undergoing Thermage treatment in the first type of medication data, and the risk coefficient of the Thermage image attributes to the characteristic data of the person undergoing Thermage treatment, the characteristic data of each person undergoing Thermage treatment is determined.

[0142] The step of determining the risk coefficient of Thermage image attributes to the characteristic data of Thermage users based on the second type of medication data specifically includes:

[0143] If the Thermage image attribute is a certain accident image, the risk coefficient of the Thermage image attribute to the characteristic data of the person undergoing Thermage includes: the probability value that the person undergoing Thermage has a certain characteristic.

[0144] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0145] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units. The above are merely embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made based on the description and drawings of this application, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

[0146] The specific embodiments of the invention have been described in detail above, but they are only examples, and this application is not limited to the specific embodiments described above. For those skilled in the art, any equivalent modifications or substitutions to the invention are also within the scope of this application. Therefore, all equivalent changes, modifications, and improvements made without departing from the spirit and principles of this application should be covered within the scope of this application.

Claims

1. A method for improving the comfort of Thermage procedures based on skin parameters, characterized in that, include: Collect the attribute characteristics of the person undergoing Thermage treatment, including multiple types of medication data; Based on the aforementioned multiple types of medication data, the historical behavior data of the Thermage treatment recipients were collected sequentially to obtain multiple sets of historical behavior data of Thermage treatment recipients. Based on the pre-set plan and the historical behavioral data of the multiple groups of Thermage patients, the risk of skin side effects of the attribute characteristics of the Thermage patients is judged to verify the attribute characteristics of the Thermage patients.

2. The method for improving the comfort of Thermage procedures based on skin parameters according to claim 1, characterized in that, Also includes: The multiple types of medication data include a first type of medication data and a second type of medication data. The first type of medication data consists of data from Thermage patients with low risk of skin side effects, while the second type of medication data consists of data from Thermage patients with high risk of skin side effects. Based on the aforementioned multiple types of medication data, the historical behavioral data of the individuals who underwent Thermage treatments are collected sequentially, specifically including: Collect historical behavioral data of operators who underwent Thermage treatments; Based on the historical behavior plan of the Thermage user, the first group of historical behavior data of Thermage user is associated with the first type of drug use data. The aforementioned plan for collecting the historical behavior data of the operator performing Thermage treatments specifically includes: Based on the second type of medication data, the risk coefficient of Thermage image attributes to the characteristic data of Thermage users is determined, and the historical behavior plan of Thermage users includes the risk coefficient.

3. The method for improving the comfort of Thermage procedures based on skin parameters according to claim 2, characterized in that, The first set of historical behavior data of Thermage users, which is associated with the first type of medication data, based on the historical behavior plan of Thermage users, specifically includes: Based on the Thermage image attributes of each person undergoing Thermage treatment in the first type of medication data, and the risk coefficient of the Thermage image attributes to the characteristic data of the person undergoing Thermage treatment, the characteristic data of each person undergoing Thermage treatment is determined. The step of determining the risk coefficient of Thermage image attributes to the characteristic data of Thermage users based on the second type of medication data specifically includes: If the Thermage image attribute is a certain accident image, the risk coefficient of the Thermage image attribute to the characteristic data of the person undergoing Thermage includes: the probability value that the person undergoing Thermage has a certain characteristic.

4. The method as described in claim 3, characterized in that, The aforementioned plan for collecting the historical behavior data of the operator performing Thermage treatments specifically includes: Based on the second type of medication data, at least one Thermage user identification strategy is used, wherein different Thermage user identification strategies have different structures; the Thermage user historical behavior scheme includes the operation logic of the at least one Thermage user identification strategy. The step of determining the first group of historical behavior data of Thermage users associated with the first type of medication data based on the historical behavior scheme of Thermage users specifically includes: processing the Thermage user attribute features of each Thermage user in the first type of medication data sequentially through the at least one Thermage user identification strategy to obtain the Thermage user classification data of each Thermage user. The first group of historical behavior data of Thermage patients includes the classification data of Thermage patients for each individual.

5. The method as described in claim 3, characterized in that, The aforementioned plan for collecting the historical behavior data of the operator performing Thermage treatments specifically includes: Based on the second type of medication data, the correlation data between the characteristic data of the person undergoing Thermage treatment and the operation data of the person undergoing Thermage treatment on the application terminal is determined; the historical behavior plan of the person undergoing Thermage treatment includes the correlation data. The step of determining the first group of historical behavior data of Thermage users associated with the first type of medication data based on the historical behavior scheme of Thermage users specifically includes: comparing the operation data of Thermage users operating application terminals in the first type of medication data with the operation data of Thermage users in the association relationship to obtain the Thermage user feature data of each Thermage user, and the first group of historical behavior data of Thermage users includes the Thermage user feature data of each Thermage user.

6. The method as described in claim 3, characterized in that, Before determining the risk of skin side effects based on the pre-set plan and the historical behavioral data of the multiple groups of Thermage patients, the method further includes: The index uses the identifiers of the individuals who received Thermage treatments to index multiple sets of historical behavioral data for each individual.

7. The method as described in claim 3, characterized in that, The method of determining the risk of skin side effects based on the preset plan and the historical behavioral data of the multiple groups of Thermage recipients specifically includes: Determine the importance value of sequentially associating the multiple sets of Thermage treatment data with the operator's historical behavior data; Based on the historical behavioral data of each group of Thermage patients and their associated importance values, as well as the preset function calculation formula, the risk of skin side effects of each Thermage patient's attribute characteristics is calculated.

8. The method as described in claim 5, characterized in that, The method calculates the skin side effect risk of a particular Thermage patient based on their historical behavioral data and associated importance values, as well as a pre-defined function, using their Thermage patient attribute characteristics. Specifically, this includes: The historical behavior data of a specific Thermage patient in each group of Thermage patients' historical behavior data is standardized sequentially to obtain standardized data for each group. The sum of the products of each set of standardized data and the associated importance value is used as the skin side effect risk of a certain Thermage patient's attribute characteristics.

9. The method as described in claim 3, characterized in that, The method of determining the risk of skin side effects based on the preset plan and the historical behavioral data of the multiple groups of Thermage recipients specifically includes: Based on historical behavioral data of multiple Thermage users and a pre-built machine learning model, the risk of skin side effects for each Thermage user is determined by their individual attributes. The machine learning model is used to calculate the risk of skin side effects based on historical behavioral data of multiple groups of Thermage patients.

10. A Thermage procedure comfort system based on skin parameters, performing a Thermage procedure comfort method based on skin parameters as described in any one of claims 1-9, characterized in that, include: The data acquisition unit for Thermage users is used to collect the attribute characteristics of Thermage users, which include multiple types of medication data. The multiple types of medication data include a first type of medication data and a second type of medication data. The first type of medication data is data of Thermage users with low risk of skin side effects, and the second type of medication data is data of Thermage users with high risk of skin side effects. The classification and collection unit is used to sequentially collect the associated historical behavior data of the Thermage users based on the multiple types of medication data, and obtain multiple sets of historical behavior data of Thermage users. The skin side effect risk unit is used to determine the skin side effect risk of the Thermage patient based on the preset plan and the historical behavioral data of the multiple groups of Thermage patients, so as to verify the attribute characteristics of the Thermage patients. The classification and collection unit is specifically used to collect the historical behavior patterns of the Thermage users; and to determine the first group of historical behavior data of Thermage users associated with the first type of medication data based on the historical behavior patterns of the Thermage users. The aforementioned scheme for collecting historical behavior data of Thermage users specifically includes: based on the second type of medication data, determining the risk coefficient of Thermage image attributes to the characteristic data of Thermage users, wherein the historical behavior scheme of Thermage users includes the risk coefficient. The first set of historical behavior data of Thermage users, which is associated with the first type of medication data, based on the historical behavior plan of Thermage users, specifically includes: Based on the Thermage image attributes of each person undergoing Thermage treatment in the first type of medication data, and the risk coefficient of the Thermage image attributes to the characteristic data of the person undergoing Thermage treatment, the characteristic data of each person undergoing Thermage treatment is determined. The step of determining the risk coefficient of Thermage image attributes to the characteristic data of Thermage users based on the second type of medication data specifically includes: If the Thermage image attribute is a certain accident image, the risk coefficient of the Thermage image attribute to the characteristic data of the person undergoing Thermage includes: the probability value that the person undergoing Thermage has a certain characteristic.

Images