Facial micro plastic surgery effect simulation method and system based on generative AI

Abstract

The invention discloses a facial micro-plastic surgery effect simulation method and system based on generative AI, and relates to the technical field of facial image processing. According to the facial micro-plastic surgery effect simulation method, facial diagnosis and processing analysis are carried out on facial image data of a patient by combining the generative AI technology; according to the method, the simulation precision of the facial micro-plastic surgery effect is improved, and a personalized and accurate facial plastic scheme is generated in an interactive manner, so that the predictability and safety of the micro-plastic surgery can be remarkably improved, the medical experience of a patient is optimized, the risk of the micro-plastic surgery is reduced, communication with the patient is facilitated, and the medical experience of the patient is improved. And the digital and intelligent development of the micro-shaping industry is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of facial image processing, and in particular to a method and system for simulating facial micro-plastic surgery effects based on generative AI. Background Art

[0002] In medical scenarios, communication between doctors and patients is crucial. As the demand for facial micro-plastic surgery grows, consumers hope to see the results of the surgery in advance when considering it so that they can make more informed decisions. Generative AI simulations can help doctors better explain facial plastic surgery plans and expected results to patients, reducing patients' misunderstandings and concerns.

[0003] With the continuous development of modern plastic surgery technology, the existing prediction effect of facial micro-plastic surgery mainly relies on the experience of professional doctors or some simple visual simulation tools; most of these traditional methods have low accuracy, difficulty in reflecting personalized needs, and complex operations, making it difficult to provide patients with accurate preoperative effect predictions and personalized adjustment suggestions. At the same time, most existing technologies cannot accurately consider factors such as the characteristics of different filling materials, the physical properties of facial skin, and lighting effects, resulting in a large gap between the final postoperative effect and expectations. Due to the different filling materials and the different states of the filling materials in the patient's body, it is difficult for patients to clearly understand the degree to which the selected materials match their own needs;

[0004] In summary, how to combine generative AI to analyze different filling materials and the status of filling materials in the patient's body, simulate and visualize the effects of micro-plastic surgery, promote communication with patients about micro-plastic surgery plans, and reduce surgical risks is an urgent problem to be solved and optimized in the facial micro-plastic surgery effect simulation system. Summary of the invention

[0005] The present invention provides a method and system for simulating the effects of facial micro-plastic surgery based on generative AI, and solves the technical problem of how to combine generative AI to analyze different filling materials and the status of the filling materials in the patient's body to simulate and visualize the effects of micro-plastic surgery.

[0006] In order to solve the above technical problems, the present invention provides a facial micro-plastic surgery effect simulation method and system based on generative AI. The specific technical solution is as follows:

[0007] In a first aspect, a method for simulating facial micro-plastic surgery effects based on generative AI comprises the following steps:

[0008] Collecting a plurality of patient facial three-dimensional image data to obtain a facial three-dimensional image data set; extracting and calibrating facial defect features of each data item in the facial three-dimensional image data set to obtain a defect calibration data set, wherein the defect calibration data represents marking of defect feature data existing on the patient's face;

[0009] Based on the historically collected patient facial 3D image dataset and the defect calibration dataset, the defect feature data existing in the patient's facial 3D image is identified through a generative AI model and an initial micro-plastic surgery plan for the patient's facial defect feature data is simulated;

[0010] Based on the initial micro-plastic surgery plan, the patient can intuitively feel the contrast effect of facial improvement before and after the surgery; based on the comparison results and real-time interactive feedback with the patient, the details of the surgery are adjusted in multiple rounds according to the patient's expected effect, so as to set a real-time adjustment strategy and generate a final facial micro-plastic surgery plan;

[0011] Based on the final facial micro-plastic surgery plan, the facial micro-plastic surgery interaction effect model is constructed to obtain the interaction effect between facial micro-plastic surgery filling or dissolving materials and the human face, and the generative AI model is updated and fed back to obtain the final visual display image of the face after surgery.

[0012] As a further optimization scheme of the present invention, the patient's facial image data is scanned and collected, and three-dimensional modeling is performed on the patient's facial image to generate facial three-dimensional image data; multiple types of facial three-dimensional image data are merged into the facial three-dimensional image data set; and the two-dimensional image data in the four directions of top, bottom, left and right of each facial three-dimensional image are retained to obtain a micro-surgery reference image data set.

[0013] As a further optimization solution of the present invention, the real-time adjustment strategy includes:

[0014] An initial micro-plastic surgery plan based on the facial defect feature data of the patient is used to obtain the degree of facial defect of the patient; a facial flatness threshold range is preset, and the degree of facial defect of the patient is compared with the preset facial flatness threshold range, and based on the comparison result, the degree of facial defect of the patient is obtained as concave or convex;

[0015] pass To obtain the degree of convexity and concavity of facial defects, where R1 and R2 represent the principal curvature radii of the convex and concave areas respectively; when facial concave features appear, the facial concave areas are filled with filling materials so that the concave areas reach the preset facial flatness threshold range; when facial convex features appear, the facial convex areas are dissolved with dissolving materials so that the convex areas reach the preset facial flatness threshold range, so as to obtain the secondary plan for micro-plastic surgery.

[0016] As a further optimization scheme of the present invention, based on the micro-plastic surgery secondary scheme, according to the patient's feedback on the satisfaction with the surgical effect, the description of the facial change requirements and personal preferences, the updated generative AI model is used to output the adjustment simulation results;

[0017] The adjustment simulation results include adjustments to facial contours, skin firmness, fat distribution and filling depth, so as to dynamically optimize and adjust the patient's facial coordination effect in multiple dimensions; based on the adjustment simulation results, a final personalized facial micro-plastic surgery plan with multiple adjustment plans is independently recommended, and iterative optimization is performed in combination with individual differences of patients to obtain a three-level micro-plastic surgery plan.

[0018] As a further optimization scheme of the present invention, facial defect features of each data item in the facial three-dimensional image data set are extracted and calibrated to obtain a defect calibration data set, including:

[0019] The facial three-dimensional image dataset is subjected to centering and scaling processing to normalize the coordinates of each data item in the three-dimensional image dataset to a uniform range, so as to obtain a normalized three-dimensional image dataset; the three-dimensional image models of the normalized three-dimensional image dataset are aligned by an iterative closest point algorithm, so that different facial images are in the same reference coordinate system;

[0020] The defect area is identified by statistical analysis of the three-dimensional shape of the face, and key points are arranged for three-dimensional positioning of image markers on the three-dimensional image data items in the normalized three-dimensional image data set; multiple key points are arranged around the facial defect area; and features of the facial defect area are extracted by three-dimensional point cloud technology to obtain features of the facial defect area;

[0021] Based on the facial defect area features extracted from the three-dimensional image, a sliding window algorithm is used to find the defect area and perform calibration processing to obtain defect calibration data; a variety of defect calibration data are obtained based on a variety of different facial three-dimensional images to form a defect calibration data set.

[0022] As a further optimization scheme of the present invention, the characteristic data of micro-plastic filling or dissolving materials that match human tissue are obtained to obtain a material characteristic data set; the facial three-dimensional image data set and the material characteristic data set collected historically are used to construct a training set to generate a facial micro-plastic surgery interaction effect model; the facial micro-plastic surgery interaction effect model outputs an interaction effect recognition result of the micro-plastic filling or dissolving materials required to represent the facial image;

[0023] The newly acquired three-dimensional facial image of the patient is input into the facial micro-surgery interaction effect model to output facial defect features of the newly acquired three-dimensional facial image of the patient and a prediction result of the interaction effect of the required filling or dissolving materials; based on the interaction effect prediction result, the dynamic change characteristics of the filling or dissolving material in the patient's body are used to obtain the interaction data between the simulation material and the facial tissue.

[0024] As a further optimization scheme of the present invention, simulation is performed based on the recognition result of the facial micro-surgery interaction effect model and combined with the characteristic data of micro-surgery filling or dissolving materials; according to the simulated effect of the filling or dissolving material interaction effect on the patient's face, a visualization image of the postoperative effect is generated to demonstrate the improvement effect of the filling or dissolving material on the facial defect features; based on the demonstrated effect, real-time feedback is provided and the scheme is adjusted in time to generate a personalized facial micro-surgery final scheme.

[0025] As a further optimization scheme of the present invention, according to the characteristic data of different filling or dissolving materials, the deformation effect of the filling or dissolving material is obtained by σ=E·ε; wherein σ represents stress, E represents the elastic modulus of the characteristic data of the material, and ε represents strain;

[0026] Based on the deformation effect of filling or dissolving materials, Obtain the diffusion degree of the filling or dissolving material in the subcutaneous tissue gap to describe the adaptation and distribution of the material on the face; and combine the facial micro-surgery interaction effect model to obtain the effect of the material filling or dissolving on the facial surface morphology;

[0027] In the formula, δ represents the diffusion degree of the filling or dissolving material in the subcutaneous tissue space; F represents the deformation force generated by the filling or dissolving material; k skin Represents the elasticity coefficient of the skin.

[0028] As a further optimization scheme of the present invention, according to the influence of the facial surface morphology after filling or dissolving, the facial lines of the facial micro-surgery 3D image generated by the generative AI model are smoothed by using B-spline deformation;

[0029] by I=I t +I d +I s , to obtain the lighting effect after the real facial display, and map the facial texture to improve the realism of visualization; the facial texture includes skin color uniformity, texture connection and flatness; where I t ,I d and I s They represent the brightness of ambient light, diffuse light, and specular light, respectively, and I represents the brightness of postoperative light actually displayed on the face;

[0030] The micro-plastic surgery effect is checked based on the visualized image to adjust the material filling amount, position, dissolution effect and other parameters; and the generative AI model is updated with feedback to generate a final visualized image of the postoperative effect of facial micro-plastic surgery.

[0031] In a second aspect, the system is provided with an electronic device including a memory, a processor, and a facial micro-plastic surgery effect simulation method program based on generative AI stored in the memory and executable on the processor, wherein the facial micro-plastic surgery effect simulation method program based on generative AI implements the steps of a facial micro-plastic surgery effect simulation method based on generative AI when executed by the processor, and the system includes:

[0032] Data acquisition module: used to acquire a plurality of patient facial three-dimensional image data to obtain a facial three-dimensional image data set; extract and calibrate the facial defect features of each data item in the facial three-dimensional image data set to obtain a defect calibration data set, wherein the defect calibration data represents the marking of defect feature data existing on the patient's face;

[0033] Data recognition module: It is used to identify the defect feature data in the patient's facial 3D image based on the historically collected patient facial 3D image data set and the defect calibration data set, and simulate the initial micro-plastic surgery plan for the patient's facial defect feature data through a generative AI model;

[0034] Real-time adjustment module: It is used to enable the patient to intuitively feel the contrast effect of facial improvement before and after the surgery based on the initial micro-plastic surgery plan; based on the comparison results and real-time interactive feedback with the patient, the surgical details are adjusted multiple times according to the patient's expected effect to set a real-time adjustment strategy and generate the final facial micro-plastic surgery plan;

[0035] Effect display module: It is used to obtain the interactive effect of facial micro-plastic surgery filling or dissolving materials and the human face based on the final facial micro-plastic surgery plan by constructing the facial micro-plastic surgery interactive effect model, and update and feedback the generative AI model to obtain the final visual display image of the face after surgery.

[0036] The present invention has at least the following beneficial effects: by collecting the patient's three-dimensional facial image data, the present invention can obtain information such as the detailed structure, skin texture, and bone features of the face. This data foundation provides accurate and detailed information for subsequent analysis and processing; each patient has a different facial morphology, and three-dimensional data collection can help generate a personalized facial model of the patient, laying a solid foundation for the precise planning of micro-plastic surgery; collecting three-dimensional data from different patients and establishing a diverse data set can improve the generalization ability of the model, enabling AI to adapt to the facial features of different populations and avoid the impact of individual patient data deviations.

[0037] Through feature extraction and calibration, specific facial defects (such as wrinkles, facial asymmetry, sagging, fat accumulation, etc.) of patients can be accurately identified and located. The calibration data set can provide a clear basis for subsequent defect correction and micro-plastic surgery plans; the defect calibration data set can provide consistency standards for different doctors and different AI models, which helps to form a unified diagnosis and treatment reference. It can also be used as "label data" for training generative AI models to improve model accuracy; through quantitative calibration of defects, doctors can more clearly understand the problems with the patient's face, and then formulate micro-plastic surgery plans that better meet actual needs.

[0038] The generative AI model can automatically identify facial defects of patients based on historical data sets and simulate possible correction plans, greatly improving work efficiency and accuracy; the preliminary plan simulated by AI can take into account the unique facial features of each patient, such as facial bone structure, muscle movement, skin tension, etc., and the generated initial plan is more in line with the patient's personalized needs; the application of AI models helps to reduce the subjective errors of doctors in the surgical planning process and provide objective plans based on large amounts of data and model reasoning; the generated initial plan can show the patient's postoperative effects through visualization, so that the patient can intuitively feel the possible changes after the operation and increase his confidence in the surgical plan.

[0039] Through real-time interaction between patients and AI systems, AI can adjust surgical plans based on patient feedback to ensure that the postoperative effect meets the patient's expectations. For example, patients may want a more natural or three-dimensional effect in a certain part, and AI can make dynamic adjustments; interactive feedback with patients increases the patient's participation in the decision-making process, enabling them to make customized adjustments to the surgical plan and increase surgical satisfaction; patient feedback can be used for multiple rounds of adjustments, and the generative AI model can accumulate experience in each round of adjustments, and gradually improve the surgical plan through optimization algorithms to make it more in line with patient needs; by constantly comparing patient expectations with model output, the facial comparison effect before and after surgery can be displayed in real time to help patients make decisions and enhance their confidence in surgery.

[0040] The interactive effect model can accurately simulate the behavior of filling or dissolving materials on the skin, their interactions, and their effects on facial morphology. By simulating the effects of filling, dissolving, or other micro-plastic surgery, the postoperative effect can be better predicted; the model takes into account the interaction between the material and the skin, such as how the filling material forms support under the skin, how the muscles affect the flow of the material, etc., so as to more realistically reflect the postoperative effect; through real-time feedback and adjustments, the AI ​​model continuously optimizes its predictions and effect simulations. This closed-loop mechanism ensures that the final solution generated is highly consistent with the patient's expected effect.

[0041] Visual display images of postoperative effects can help patients clearly understand the possible facial changes after surgery before surgery, and help them better understand the potential benefits of surgery; patients can compare their actual and expected effects through postoperative visual images, which helps them make more informed decisions; precise simulation and visual effect display before surgery can greatly reduce the uncertainty of postoperative effects, help patients better set expectations, and avoid unnecessary psychological pressure after surgery. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flow chart of a facial micro-plastic surgery effect simulation method based on generative AI provided by an embodiment of the present invention;

[0043] Figure 2 It is a schematic diagram of a facial micro-plastic surgery effect simulation system based on generative AI provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The present application is further described in detail below in conjunction with the accompanying drawings. It is necessary to point out here that the following specific implementation methods are only used to further illustrate the present application and cannot be understood as limiting the scope of protection of the present application. Technical personnel in this field can make some non-essential improvements and adjustments to the present application based on the above application content.

[0045] This embodiment provides a method and system for simulating the effect of facial micro-plastic surgery based on generative AI, and the specific implementation methods are as follows:

[0046] like Figure 1 As shown, a facial micro-plastic surgery effect simulation method based on generative AI includes the following steps:

[0047] Step 11, collecting a plurality of patient facial three-dimensional image data to obtain a facial three-dimensional image data set; extracting and calibrating facial defect features of each data item in the facial three-dimensional image data set to obtain a defect calibration data set, wherein the defect calibration data represents marking of defect feature data existing on the patient's face;

[0048] Step 12, based on the historically collected patient facial three-dimensional image dataset and the defect calibration dataset, the defect feature data existing in the patient's facial three-dimensional image is identified by a generative AI model and an initial micro-plastic surgery plan for the patient's facial defect feature data is simulated;

[0049] Step 13, based on the initial micro-plastic surgery plan, the patient is allowed to intuitively experience the contrast effect of facial improvement before and after the surgery; based on the comparison results and real-time interactive feedback with the patient, the details of the surgery are adjusted multiple times according to the patient's expected effect, so as to set a real-time adjustment strategy and generate a final facial micro-plastic surgery plan;

[0050] Step 14, based on the final facial micro-plastic surgery plan, the facial micro-plastic surgery interaction effect model is constructed to obtain the interaction effect between the facial micro-plastic surgery filling or dissolving material and the human face, and the generative AI model is updated and fed back to obtain the final visual display image of the face after surgery.

[0051] In the implementation of the present invention, step 11 establishes a comprehensive facial three-dimensional data set by collecting facial three-dimensional image data of multiple patients. This step is not only for collecting data, but also includes collecting facial images at different angles and different expressions. The purpose of this is to ensure the diversity and representativeness of the data set, so that various possible facial features and defect types can be better covered. By extracting the defect features of each patient's face and calibrating them, a defect calibration data set is formed. This calibration process refers to the clear marking and classification of each facial defect, including but not limited to facial depression, protrusion, wrinkles, collapse and relaxation, so as to provide accurate basic data for subsequent analysis; thereby establishing a large and diverse database containing data on different types of facial defects. The diversity of data provides a more comprehensive foundation for subsequent AI model training, enhancing its generalization ability and accuracy.

[0052] Step 12 uses a generative AI model for training and analysis based on the facial 3D image dataset and defect calibration dataset collected in step 11. The core goal of this step is to use historical data and defect calibration information to accurately identify the defect features of each patient's face and generate an initial plan for micro-plastic surgery. By analyzing and learning these data, the generative AI model can predict and simulate a micro-plastic surgery plan suitable for the patient. The AI ​​model not only simply identifies defects, but also proposes a preliminary plastic surgery plan based on factors such as the patient's overall facial structure and proportions; thereby greatly improving the efficiency and accuracy of plan formulation. The AI's analytical ability can identify details that are not easily perceived by the naked eye, ensuring the rationality and personalization of the initial plan. In addition, the generated plan is more scientific and data-supported, providing a strong basis for subsequent adjustments.

[0053] Step 13: Based on the initial micro-plastic surgery plan generated in step 12, in order to allow patients to more intuitively feel the facial improvement effect before and after the operation, efficient visualization tools (such as three-dimensional model display, virtual reality, etc.) are used for simulation display. In this process, patients can provide feedback on their expectations and requirements for the surgical effect through real-time interaction with doctors. Based on the patient's feedback, the physician can make multiple rounds of adjustments, including modifying the facial proportions, adjusting the filling parts, etc., and finally come up with a final facial micro-plastic surgery plan that satisfies the patient. This process emphasizes interaction with patients to ensure that the final plan meets the patient's needs to the greatest extent; through real-time feedback and multiple rounds of adjustments at this stage, patients can better understand the postoperative effect and enhance their trust and satisfaction with the surgical plan. Through visual simulation, patients can intuitively see their potential changes before surgery, avoiding the anxiety and misunderstanding caused by the inability to accurately foresee the effect in traditional methods.

[0054] Step 14: After the final micro-plastic surgery plan is determined in step 13, a facial micro-plastic surgery interactive effect model is constructed. This model not only considers the interactive effect of facial filling materials or dissolving materials on the human face, but also combines the changes in the postoperative recovery period. By feedback and updating the generative AI model, the final visual display image of the face after surgery can be obtained. Through this model, patients can foresee the effects of surgery, not only morphological changes, but also the long-term effects of factors such as the biocompatibility and durability of postoperative materials on the face; thus ensuring the long-term predictability and accuracy of the surgical effect. By constructing an interactive effect model, some changes and potential problems in the postoperative recovery process can be predicted in advance, helping patients better understand the long-term effects after surgery. At the same time, the update of the AI ​​model can continuously optimize and improve the facial micro-plastic surgery plan to make it more in line with individual differences and biological characteristics.

[0055] The above four steps form a precise and systematic facial micro plastic surgery design process. From data collection to AI model generation, to interactive adjustment with patients, and finally through the optimization of the interactive effect model, each link is closely linked and mutually supportive. This not only greatly improves the accuracy and personalization of micro plastic surgery, but also enhances the patient's experience and trust through visualization and interaction. The beneficial effects of each step complement each other, improving the quality of medical services and patient satisfaction as a whole, while also making the micro plastic surgery process more scientific, transparent and controllable.

[0056] In a preferred embodiment of the present invention, step 11 further comprises:

[0057] Step 111, scan and collect facial image data of the patient, perform three-dimensional modeling on the facial image of the patient to generate facial three-dimensional image data; merge the multiple facial three-dimensional image data into the facial three-dimensional image data set; and retain the two-dimensional image data in the four directions of top, bottom, left and right of each facial three-dimensional image to obtain a micro-surgery reference image data set.

[0058] In the implementation of the present invention, step 111 first performs scanning and acquisition of the patient's facial image data. The patient's facial image data is acquired by using professional three-dimensional scanning equipment (such as an optical scanner or a structured light camera, etc.). This process will capture detailed information of the face from multiple angles and multiple directions to ensure that the scanned data is sufficiently accurate and complete. The acquired data usually includes the geometric morphology, surface details, and texture features of the face; then, advanced image processing technology is used to perform three-dimensional modeling on the acquired facial image data. The modeling process uses computer vision and three-dimensional reconstruction algorithms to integrate image data from different angles to generate a comprehensive and accurate three-dimensional facial model. This three-dimensional model not only reflects the geometric shape of the face, but also contains detailed surface texture information, such as skin texture and tiny details.

[0059] After completing the 3D modeling, the collected data of multiple 3D images are aggregated to form a facial 3D image dataset. This dataset contains 3D facial data from different patients, covering a variety of facial features and structural changes. In order to further improve the diversity and representativeness of the data, the step also requires retaining the 2D image data in the four directions of top, bottom, left and right of each facial 3D image. These 2D images will help to more accurately capture the various angles and local features of the face, thereby supplementing the detailed information in the 3D modeling. After all these data are aggregated, a micro-plastic surgery reference image dataset is formed.

[0060] Facial images from multiple directions are acquired through 3D scanning equipment to ensure that sufficient details are captured. These image data include facial features observed from different perspectives (such as the front, side, top, and bottom) to fully restore the three-dimensional structure of the face; these two-dimensional image data are processed through a three-dimensional reconstruction algorithm to generate a high-precision three-dimensional facial model that retains the detailed geometric shape, curves, and textures of the face. This process relies on computer vision technology and image fusion algorithms to ensure the high fidelity of the facial model; the facial three-dimensional image data of various different patients are aggregated in one data set, and the two-dimensional image data of each three-dimensional model from different angles is saved to further increase the diversity and richness of the data set. By maintaining two-dimensional images in four directions, the data set can provide a more comprehensive reference in subsequent processing.

[0061] Through 3D scanning technology and multi-angle image acquisition, facial details can be accurately captured to generate a highly restored 3D facial model. This makes the subsequent design of facial micro-plastic surgery plans more accurate and avoids the errors caused by traditional 2D images or single-view data; the retained 2D image data in four directions can provide a more comprehensive reference for subsequent facial defect analysis and micro-plastic surgery plan design. These 2D images supplement the details of the 3D model and enhance the multidimensionality and accuracy of the data.

[0062] By aggregating facial 3D image data from a variety of patients, a rich facial dataset was constructed. This dataset not only covers a wide range of facial feature changes, but also provides sufficient sample data for the training of AI models, which helps to generate personalized and accurate micro-plastic surgery plans; the establishment of facial 3D image datasets and their 2D reference images lays the foundation for subsequent facial defect feature extraction, AI model training, and micro-plastic surgery plan design. By using this dataset, doctors and AI systems can more accurately identify the personalized features and defects of patients' faces and develop personalized and expected micro-plastic surgery plans.

[0063] By scanning and collecting facial images of patients and performing 3D modeling, combined with 2D image data in four directions, a detailed and accurate 3D facial dataset was established. This dataset not only provides high-quality basic data for the design of facial micro-plastic surgery programs, but also ensures the comprehensiveness and diversity of the data, which helps to improve the accuracy and personalization of the micro-plastic surgery process. The beneficial effect of this process is that it can provide strong support for subsequent defect calibration, AI model generation, and postoperative effect prediction.

[0064] In a preferred embodiment of the present invention, the real-time adjustment strategy in step 13 includes:

[0065] Step 131, an initial micro-plastic surgery plan based on the facial defect feature data of the patient is used to obtain the degree of facial defect of the patient; a facial flatness threshold range is preset, and the degree of facial defect of the patient is compared with the preset facial flatness threshold range, and based on the comparison result, the degree of facial defect of the patient is obtained as concave or convex;

[0066] Step 132, pass To obtain the degree of convexity and concavity of facial defects, where R1 and R2 represent the principal curvature radii of the convex and concave areas respectively; when facial concave features appear, the facial concave areas are filled with filling materials so that the concave areas reach the preset facial flatness threshold range; when facial convex features appear, the facial convex areas are dissolved with dissolving materials so that the convex areas reach the preset facial flatness threshold range, so as to obtain the secondary plan for micro-plastic surgery.

[0067] In the implementation of the present invention, step 131 formulates an initial micro-plastic surgery plan based on the defect feature data of the patient's face (for example, facial depressions, protrusions, wrinkles, etc.). By analyzing the facial image data, the defective areas of the face are identified, and a preliminary adjustment plan is formulated based on these data. These defect feature data can be obtained through three-dimensional modeling and algorithm analysis to ensure the accuracy of the defect information; then, it will be judged by a preset facial flatness threshold range. The facial flatness threshold is a standard value range used to measure whether each area of ​​the face reaches the expected flatness. The threshold is usually set based on different facial area characteristics, facial aesthetic standards, and individual needs of the patient.

[0068] By comparing the degree of facial defects of the patient with this preset facial flatness threshold range, the system can clearly determine whether the defective area of ​​the face is sunken or convex. This comparison process helps to further analyze the overall condition of the patient's face and provide a basis for subsequent treatment plans; through three-dimensional scanning and image processing technology, the defect data of the patient's face is obtained, which usually includes features such as sunken areas, convex areas, and skin unevenness; the facial flatness threshold is used as a standard to determine whether the facial area meets aesthetic standards or clinical requirements. By comparing the degree of facial defects of the patient with this threshold, it can be clearly determined which areas require further micro-plastic surgery (such as filling or dissolution); based on the comparison with the flatness threshold, facial defects are classified as sunken or convex. In this way, personalized treatment planning can be carried out for different types of facial defects.

[0069] Skin flatness, the overall smoothness of facial skin, wrinkles, and depressions;

[0070] The flatness of facial contours, such as the unevenness of the chin, cheekbones, forehead, etc.

[0071] Skin smoothness is usually expressed as the roughness of the subcutaneous tissue gap. Common measurement methods include the collection and analysis of skin texture by a subcutaneous tissue gap roughness analyzer (such as a dermatoscope or 3D scanner).

[0072] Good flatness, skin roughness is within the range of 0.5μm-1.0μm;

[0073] Medium smoothness, skin roughness is in the range of 1.0μm-1.5μm;

[0074] Poor flatness, skin roughness is above 1.5μm.

[0075] Contour flatness can be analyzed through facial scanning and 3D reconstruction techniques, and is usually quantified by the degree of change in facial curvature;

[0076] Good flatness, facial curvature variation ≤1.0mm.

[0077] Moderate flatness, facial curvature variation between 1.0mm-2.0mm.

[0078] Poor flatness, facial curvature variation **>2.0mm**.

[0079] The degree of depression / protrusion of the face, especially the deficiencies or protrusions of the nose bridge, cheekbones, forehead, etc.

[0080] Signs of skin aging, such as wrinkles and sagging;

[0081] Spots or acne scars, pigmentation or scars on the skin.

[0082] The height difference of each area of ​​the face is measured by 3D facial scanning equipment.

[0083] Low defectivity, height difference in facial area does not exceed 1.0mm.

[0084] Moderate defect, the height difference of the facial area is between 1.0mm-2.0mm.

[0085] High defectivity, with the height difference in the facial area exceeding 2.0mm.

[0086] The manifestations of skin aging can be judged by skin elasticity, fine lines and sagging. Commonly used parameters include skin elasticity index (Elasticity Index) and the number of fine lines.

[0087] Low defect level: skin elasticity index is greater than 70, with no obvious fine lines;

[0088] Moderate defects: skin elasticity index 50-70, a few fine lines;

[0089] High defect level: Skin elasticity index is less than 50, with obvious fine lines and sagging.

[0090] The need to adjust the micro plastic surgery plan can be determined by comparing the values ​​of flatness and defects. For example, a patient's facial skin roughness is 1.2μm (medium flatness), the facial curvature variation is 1.8mm (medium flatness), and the main facial defects are the depression in the eye bag area (2.5mm depression depth) and the fine lines on the forehead (skin elasticity index 55); the skin and contour flatness are both in the medium range, and the skin smoothness and contour symmetry need to be improved; the depression of the eye bags and the fine lines on the forehead indicate that the face has medium defects, and local filling and tightening treatment are needed in the micro plastic surgery plan.

[0091] As another example, another patient had skin roughness of 0.8μm (good smoothness) and facial curvature variation of 0.5mm (good smoothness), but had obvious zygomatic protrusion (height difference 2.2mm) and neck sagging (skin elasticity index 45); the smoothness of the skin and contour was good, but local areas (zygomatic bones and neck) required special attention; the height difference of the zygomatic bones was large, and the neck was obviously sagging, which needed to be adjusted through filling and firming measures.

[0092] Step 132 determines the specific type of facial defect (depression or protrusion) based on the analysis results in step 131. Next, the degree of convexity and concavity of the defective area is further calculated using a mathematical formula or an algorithm model. In this process, the principal curvature radii (R1 and R2) are used to describe the degree of curvature of the facial depression or protrusion area; R1 and R2 represent the principal curvature radii of the convex and concave areas, respectively, and are used to quantify the curvature of the defective area. By calculating these principal curvature values, the severity of the facial depression or protrusion area can be accurately assessed. The purpose of this step is to provide a more accurate micro-plastic surgery plan to ensure the best treatment effect.

[0093] Based on this analysis result, if there are sunken features on the face, they are usually filled with filling materials to make the sunken areas reach the preset facial flatness threshold range. The filling materials can be hyaluronic acid, collagen, etc., which can effectively restore the flatness of the sunken areas and have good biocompatibility; when there are protruding features on the face, they are treated with dissolving materials. Dissolving materials (such as soluble fillers) can help dissolve or reduce the volume of the protruding areas, smoothing them and restoring them to the appropriate facial contour. The ultimate goal is to carry out targeted repairs on the patient's facial depression or protrusion problems based on the facial flatness threshold range, and develop a secondary micro-plastic surgery plan that conforms to facial aesthetics.

[0094] By obtaining the principal radius of curvature (R1 and R2) of the defective area, the curvature change of the facial area is quantified, thereby accurately assessing the severity of the defect. This calculation helps determine which part needs to be filled or dissolved; for sunken areas, these areas are filled by selecting appropriate filling materials, such as hyaluronic acid or collagen, to restore flatness; for protruding areas, the facial contour is restored to its ideal state by using soluble materials for dissolution. Dissolving materials help reduce excessive protrusions and restore natural facial lines; by calculating the degree of convexity and concavity of facial defects and selecting appropriate materials for filling or dissolving, the facial contour can be accurately adjusted to achieve the desired aesthetic effect; through specific analysis of facial depressions and protrusions, the treatment process is made more targeted and controllable, reducing uncertainty in the treatment process; according to the specific defect characteristics of the patient's face, a personalized micro-plastic surgery plan is customized to ensure that each patient can obtain the best treatment effect. Through the precise calculation of convexity and concavity, the treatment plan is more accurate, avoiding excessive or insufficient treatment; through the precise application of filling and dissolving materials, it is possible to restore facial flatness while maintaining the natural beauty of the face, avoiding unnatural or artificial effects, and improving the naturalness and durability of the postoperative effect.

[0095] In a preferred embodiment of the present invention, step 13 further comprises:

[0096] Step 133, based on the micro plastic surgery secondary plan, according to the patient's feedback on the satisfaction with the surgical effect, the description of the facial change requirements and personal preferences, based on the updated generative AI model, to output the adjustment simulation results;

[0097] Step 134, the adjustment simulation results include adjustments to facial contours, skin firmness, fat distribution, and filling depth, so as to dynamically optimize and adjust the patient's facial coordination effect in multiple dimensions; based on the adjustment simulation results, a plurality of adjustment plans for the final personalized facial micro-plastic surgery plan are autonomously recommended, and iterative optimization is performed in combination with individual differences of patients to obtain a three-level micro-plastic surgery plan.

[0098] In the implementation of the present invention, the core of step 133 is to use the patient's feedback (including satisfaction with the surgical effect, facial change requirements, personal preferences, etc.) as input data, combined with the existing micro-plastic surgery secondary plan, and use the updated generative AI model for analysis and adjustment. The generative AI model can simulate and foresee the specific effects of different adjustment plans on the patient's face, and then output the adjusted simulation results; obtain the patient's evaluation and expectations of the existing surgical effects through questionnaires, dialog boxes or direct communication methods, including facial contours, skin texture, fat distribution and other aspects; the AI ​​model is based on these feedbacks and existing secondary plan data. Perform calculations and simulations to infer which adjustment measures can most effectively meet the patient's needs; through the simulation results, it can provide doctors with optimized facial plans and assist patients in understanding the effects of the adjustments; by collecting and analyzing the patient's specific feedback, ensure that the adjusted plan is more in line with the patient's personal needs and expectations; the AI ​​model can more accurately predict the impact of different adjustments on the patient's facial effects, reducing surgical risks and uncertainties.

[0099] Step 134 further optimizes multiple dimensions such as facial contour, skin firmness, fat distribution and filling depth by adjusting the simulation results according to step 133. The system optimizes the coordination effect of the patient's face according to the changes in multiple dimensions, and finally generates multiple micro-plastic surgery plans and recommends them to the patient for selection; the adjustment of the simulation results does not only focus on a single facial feature, but starts from the overall coordination of the face, comprehensively considers multiple factors such as facial contour, skin firmness, fat distribution and filling depth, and performs dynamic optimization and adjustment. Based on the individual differences of patients (such as facial bone structure, skin type, facial muscle state, etc.), the AI ​​system can continuously iterate and optimize the micro-plastic surgery plan, and propose a series of different adjustment plans for patients to choose; by continuously optimizing the adjustment plan, it can automatically provide patients with the final personalized micro-plastic surgery plan that best suits their needs.

[0100] Through multi-dimensional optimization, the patient's facial effect is more natural and coordinated, avoiding abrupt local adjustments; accurate recommendations are made based on the individual differences of the patient to ensure that the final micro-plastic surgery plan meets the patient's unique facial structure and aesthetic needs; it can be continuously optimized based on feedback, avoiding repeated adjustments or dissatisfaction caused by improper plan selection in traditional surgery.

[0101] In a preferred embodiment of the present invention, in step 11, facial defect features of each data item in the facial three-dimensional image data set are extracted and calibrated to obtain a defect calibration data set, including:

[0102] Step 112, normalizing the coordinates of each data item in the facial three-dimensional image dataset to a uniform range by centering and scaling the facial three-dimensional image dataset to obtain a normalized three-dimensional image dataset; aligning the three-dimensional image models of the normalized three-dimensional image dataset by an iterative closest point algorithm to make different facial images in the same reference coordinate system;

[0103] Step 113, identifying defect areas by statistical analysis of the three-dimensional shape of the face, performing three-dimensional positioning of image markers and arranging key points for the three-dimensional image data items in the normalized three-dimensional image data set; arranging multiple key points around the facial defect area; and extracting features of the facial defect area by three-dimensional point cloud technology to obtain features of the facial defect area;

[0104] Step 114, based on the facial defect area features extracted from the three-dimensional image, a sliding window algorithm is used to find the defect area and perform calibration processing to obtain defect calibration data; a variety of defect calibration data are obtained based on a variety of different facial three-dimensional images to form a defect calibration data set.

[0105] In the implementation of the present invention, the three-dimensional image data set of the face is centered and scaled in step 112 to achieve data standardization. The centering process is to translate all the coordinates of the three-dimensional data set so that the center of the data set is aligned with the origin of the coordinate system. Then, the scaling operation adjusts all the coordinates proportionally so that the coordinates of the data items fall within a uniform range, unified to the range of [-1,1]; this standardization process helps to eliminate the scale differences and position differences between different facial data sets; after standardization, different facial images can be mapped to the same reference coordinate system, eliminating geometric differences caused by factors such as shooting angle and distance; after standardization, facial images can be further compared and analyzed in the same coordinate system to avoid errors caused by inconsistent data; it provides a good foundation for the subsequent iterative closest point algorithm (ICP), so that different facial images can be accurately aligned to ensure the accuracy of subsequent analysis.

[0106] Step 113 identifies potential defect areas by statistically analyzing the three-dimensional shape of the face. First, the normalized three-dimensional image data is subjected to three-dimensional positioning of image markers to arrange key points. The three-dimensional positioning of image markers means positioning facial defect feature markers on the three-dimensional facial image, and distributing these key points on the three-dimensional facial data set. These key points are usually distributed around areas where defects may exist (such as eye bags, nasolabial folds, etc.). These key points are used to mark the geometric features of different facial areas, especially in possible defect areas; next, the facial data around the key points are further analyzed using three-dimensional point cloud technology to extract defect area features. Through detailed analysis of facial 3D data, point cloud technology can capture tiny geometric differences, such as depressions, swellings or other defective features of the skin; by locating key points in 3D using image markers and arranging them around defective areas, the location of facial defects can be accurately calibrated to ensure that subsequent analysis is focused on the problem area; point cloud technology can capture tiny deformations of the face, helping to identify and quantify facial defects such as wrinkles, depressions or asymmetrical parts, thereby providing data support for defect repair; by extracting features of defective areas, it can provide precise input for subsequent repair algorithms to ensure that the repair effect is natural and accurate.

[0107] Step 114 further calibrates the defective area in the facial image through a sliding window algorithm. The sliding window algorithm is an algorithm that moves step by step on the facial image. It can automatically locate and calibrate the defective area. By scanning multiple windows, the specific position and shape of each facial defect can be accurately located. Each window will be used to calibrate the defect and generate a set of defect calibration data, that is, the specific position, shape and size of each defective area; by processing multiple different facial three-dimensional images, multiple defect calibration data can be obtained, and these data can be collected into a defect calibration data set. This data set contains the defect characteristics of different individuals and can be used for subsequent personalized facial repair and model training; the sliding window algorithm can automatically identify and calibrate the defective area without manual intervention, which improves the efficiency and accuracy of calibration; it can capture the slight differences in facial defects and generate accurate defect data to ensure the efficiency and effect of subsequent repair; by processing different facial images, a variety of defect calibration data are collected to provide data support for subsequent personalized repair solutions, and can be used for training and optimization of machine learning models to improve the intelligence level of facial repair technology.

[0108] In a preferred embodiment of the present invention, step 14 comprises:

[0109] Step 141, obtaining micro-plastic surgery filling or dissolving material property data that matches human tissue to obtain a material property data set; constructing a training set with the facial three-dimensional image data set and the material property data set collected historically to generate a facial micro-plastic surgery interaction effect model; the facial micro-plastic surgery interaction effect model outputs an interaction effect recognition result of the micro-plastic surgery filling or dissolving material required to represent the facial image;

[0110] Step 142, input the newly acquired three-dimensional facial image of the patient into the facial micro-surgery interaction effect model to output facial defect features of the newly acquired three-dimensional facial image of the patient and a prediction result of the interaction effect of the required filling or dissolving materials; based on the prediction result of the interaction effect, the dynamic change characteristics of the filling or dissolving material in the patient's body are used to obtain the interaction data between the simulation material and the facial tissue.

[0111] In the implementation of the present invention, step 141 collects data on the characteristics of micro-plastic filling or dissolving materials that are compatible with human tissue. These data include information on the physicochemical properties of different filling or dissolving materials, compatibility with skin tissue, absorption rate of materials in the body, elastic changes, etc. The establishment of these data sets is based on historically collected samples, covering the characteristics of various commonly used micro-plastic materials (such as hyaluronic acid, botulinum toxin, etc.); then, the facial three-dimensional image data set is combined with the material property data set to construct a training set. This training set is used to generate a facial micro-plastic interaction effect model. The model can predict the effect of the required micro-plastic filling or dissolving material based on the input three-dimensional facial image, that is, predict the interactive effect of facial defect repair through the effect of different materials on the face.

[0112] By combining facial three-dimensional data and material property data, the model can more accurately predict the effect of micro-plastic surgery and reduce side effects or repair failures caused by improper material selection; the accumulation and training of historical data enables the model to be personalized and can generate appropriate micro-plastic surgery filling plans based on the specific facial features and defects of each patient; the model can provide doctors or plastic surgeons with a data-based prediction tool to help them better understand the impact of different materials on facial morphology and optimize treatment plans.

[0113] The input in step 142 is a newly acquired three-dimensional image of the patient's face. By inputting the image into the previously generated facial micro-plastic surgery interaction effect model, the model will output the facial defect characteristics of the patient and the interaction effect prediction results of the required filling or dissolving materials. The prediction results can not only identify the defects on the face, but also calculate the appropriate type of micro-plastic surgery material and its specific application amount according to the model; then, based on these prediction results, the dynamic change characteristics of the filling or dissolving materials in the patient's body are further analyzed. This step simulates the interaction between these materials and facial tissues, taking into account factors such as material absorption, metabolism and biocompatibility, and obtains detailed data on the changes of materials in the body.

[0114] By inputting the patient's 3D facial image, the model can provide a micro plastic surgery filling or dissolving solution that is unique to the patient. It can not only accurately identify facial defects, but also tailor the most suitable treatment plan. It simulates the interaction between materials and facial tissues to help doctors predict the actual effects of different materials in patients, such as how to integrate with skin tissue, how long it takes to absorb, possible side effects, etc. This provides more comprehensive theoretical support for micro plastic surgery treatment. By simulating the dynamic change process of materials, it can predict possible adverse reactions or poor results in advance, reduce surgical risks, and increase patients' trust in the treatment effect.

[0115] In a preferred embodiment of the present invention, step 14 further comprises:

[0116] Step 143, based on the recognition result of the facial micro-surgery interaction effect model, and in combination with the micro-surgery filling or dissolving material characteristic data, simulation is performed; according to the simulated effect of the filling or dissolving material interaction effect on the patient's face, a postoperative effect visualization image is generated to demonstrate the improvement effect of the filling or dissolving material on the facial defect characteristics; based on the demonstrated effect, real-time feedback is provided and the plan is adjusted in time to generate a personalized facial micro-surgery final plan.

[0117] In the implementation of the present invention, simulation is performed based on the recognition results of the micro-plastic surgery interaction effect model. First, the patient's facial three-dimensional image and historical data are input. Through the previously established facial micro-plastic surgery interaction effect model, the model has identified the defective features of the patient's face and the required filling or dissolving materials. Next, the model combines the characteristic data of micro-plastic surgery filling or dissolving materials (such as the material's density, elasticity, absorption rate, degree of integration with the skin, etc.) to simulate the interactive effects of these materials on facial tissues; by simulating the interaction between materials and tissues, the system can predict the specific effects of different materials on the patient's face. For example, the simulation can show how filling materials change facial contours, how to improve wrinkles or sunken areas, or how dissolving materials reduce facial puffiness or improve asymmetry problems.

[0118] Through in-depth simulation of material properties and interaction effects, doctors can be provided with an accurate understanding of the role of each material, avoiding poor results caused by material mismatch in actual treatment; simulation based on the patient's specific facial condition can tailor a suitable micro-plastic surgery plan for each patient, reducing unnecessary adjustments and incorrect treatment choices; by simulating the effects of filling or dissolving materials on the face, doctors can quickly select the most appropriate material and usage, thereby improving treatment outcomes.

[0119] After the simulation is completed, the system will generate a visualization image of the postoperative effect based on the interactive effects of the materials. This image shows the expected facial effect of the patient after treatment, showing how the filling or dissolving materials can improve facial defect features, such as making the facial contour smoother, restoring firmness, or improving wrinkles, depressions and other problems. These effects are presented in a three-dimensional reconstruction manner, which can intuitively reflect the actual effect of the material on the face; the visualization image of the postoperative effect provides patients with an intuitive preview of the effect, helping them to more clearly understand the expected changes after treatment, thereby increasing their confidence in treatment; patients and doctors can communicate better through visualization images to ensure that patients have clear expectations of the postoperative effect and avoid misunderstandings or dissatisfaction with the results; through the simulated postoperative effect, doctors can evaluate the degree of match between the actual effect of the material and the patient's expectations, providing an important reference for subsequent treatment decisions.

[0120] After the visualization images are generated, patients or doctors can provide real-time feedback based on the displayed results. If the patient is not satisfied with the simulated postoperative results, or the doctor thinks that the effects of certain materials or filling areas are not ideal, the plan can be adjusted in time based on the feedback information. This means that the type of material, the amount of filling, or the treatment area can be redefined to achieve a more ideal effect;

[0121] When a certain area is filled too full or has an unnatural appearance, the doctor can adjust the amount of filling material or choose a different material for re-optimization; real-time feedback and adjustment functions can be optimized according to the patient's actual needs, ensuring that the treatment plan is more personalized and accurate, thereby improving patient satisfaction.

[0122] Through simulation and timely adjustment of the plan, the need for postoperative repair can be reduced, because multiple optimizations and adjustments have been made based on the results before the actual operation; each patient has different facial features and needs, and real-time adjustments enable the treatment plan to flexibly adapt to the changes of different patients and ensure personalized treatment effects.

[0123] After simulation, visual image display and plan adjustment, the final treatment plan was confirmed and generated. This is a personalized final facial micro-plastic surgery plan after multiple optimizations. The plan takes into account the patient's facial features, defect characteristics, required filling or dissolving materials, and the best treatment effect to ensure that the ideal cosmetic effect can be obtained during the treatment process; through the previous simulation and feedback adjustment, the final plan generated is more in line with the patient's needs and the doctor's professional advice, ensuring the treatment effect and patient safety; personalized micro-plastic surgery plans can meet the patient's aesthetic needs and expectations to the greatest extent, avoiding the inconsistent or unsatisfactory results that may be caused by standardized treatment plans; the final plan is based on a large amount of simulation data, feedback and adjustments, with higher accuracy, ensuring that micro-plastic surgery can achieve the best results.

[0124] In a preferred embodiment of the present invention, step 143 further includes:

[0125] Step 1431, according to the characteristic data of different filling or dissolving materials, the deformation effect of the filling or dissolving material is obtained by σ=E·ε; wherein σ represents stress, E represents the elastic modulus of the characteristic data of the material, and ε represents strain;

[0126] Step 1432, based on the deformation effect of the filling or dissolving material, Obtain the diffusion degree of the filling or dissolving material in the subcutaneous tissue gap to describe the adaptation and distribution of the material on the face; and combine the facial micro-surgery interaction effect model to obtain the effect of the material filling or dissolving on the facial surface morphology;

[0127] In the formula, δ represents the diffusion degree of the filling or dissolving material in the subcutaneous tissue space; F represents the deformation force generated by the filling or dissolving material; k skin Represents the elasticity coefficient of the skin.

[0128] In the implementation of the present invention, step 1431 focuses on the deformation effect of the material by analyzing the characteristic data of different filling or dissolving materials. Parameters such as stress (σ), elastic modulus (E) and strain (ε) are used to simulate the behavior of the material on the face based on these physical quantities. Stress describes the influence of external forces on the material, the elastic modulus represents the elastic properties of the material, that is, the deformation ability of the material when subjected to external forces, and the strain represents the degree of deformation of the material under the action of stress;

[0129] Through this analysis, it is possible to predict the deformation effect of each filling or dissolving material when applied to the face, for example, how the material adjusts its shape with the movement of facial muscles, or how it produces different effects in different areas. This simulation can reflect the adaptability of the material on the facial skin and its shaping effect on the facial contour; by modeling the physical properties of the material, it can accurately predict the deformation of the material in different facial areas, helping doctors understand the actual effect of the material after use; by calculating stress, elastic modulus and strain, it can effectively avoid unnatural changes in the appearance of the material on the face, such as asymmetric or abrupt filling effects; based on the deformation characteristics of different materials, doctors can choose the most suitable material for the patient to ensure the best treatment effect.

[0130] Step 1432 further calculates the diffusion of the material in the subcutaneous tissue gap based on the deformation effect of the filling or dissolving material in step 1431. The diffusion reflects the distribution characteristics of the material in the subcutaneous tissue gap, mainly describing how the material expands, adapts, and distributes in different areas in the subcutaneous tissue gap. This process takes into account factors such as skin elasticity, texture, and thickness, and evaluates the distribution of materials on the face and their interactions;

[0131] Combined with the previous interactive effect model of facial micro-surgery, the system predicts the specific impact of material filling or dissolution on the facial surface morphology based on the diffusion of the material. For example, filling materials may form obvious bulges in certain areas, while dissolving materials may adjust the smoothness of the face by slowly dispersing. Through this comprehensive analysis, the system can provide each patient with a more accurate facial morphology improvement plan.

[0132] The calculation of diffusion degree can help doctors better understand how materials are evenly distributed in the gaps of subcutaneous tissue on the face, avoid uneven effects, and ensure the balance and naturalness of facial shape; by analyzing the diffusion and distribution of filling or dissolving materials on the face, doctors can more finely control the use of each material to ensure the personalization and efficiency of the treatment plan; combining the diffusion degree and micro-surgery interaction effect model can predict the impact of each material on facial morphology, thereby providing patients with the most suitable treatment plan.

[0133] The combined use of step 1431 and step 1432 can provide a detailed prediction of the effect of the material after application on the face by analyzing the deformation effect and diffusion of the filling or dissolving material. First, the deformation of the material is evaluated through a physical model to ensure that the selection and application of the material can naturally adapt to the facial structure; then, by calculating the diffusion, the distribution of the material on the face is optimized, and the specific impact of the treatment effect on the facial morphology is predicted. The core purpose of this process is to accurately simulate the actual effect of the material before treatment, to ensure that each patient's personalized treatment plan is accurate and effective, and to avoid unnatural or asymmetric problems that may occur during surgery.

[0134] In a preferred embodiment of the present invention, step 143 further includes:

[0135] Step 1433, based on the impact of the facial surface morphology after filling or dissolving, use B-spline deformation to smooth the facial lines of the facial micro-surgery 3D image generated by the generative AI model;

[0136] Step 1434, by I=I t +I d +I s , to obtain the lighting effect after the real facial display, and map the facial texture to improve the realism of visualization; the facial texture includes skin color uniformity, texture connection and flatness; where I t ,I d and I s They represent the brightness of ambient light, diffuse light, and specular light, respectively, and I represents the brightness of postoperative light actually displayed on the face;

[0137] Step 1435, based on the visualization image, check the micro-plastic surgery effect to adjust the material filling amount, position, dissolution effect and other parameters; and feedback to update the generative AI model to generate a visualization image of the final facial micro-plastic surgery effect.

[0138] In the implementation of the present invention, step 1433 uses B-spline deformation technology to smooth the facial three-dimensional image generated by the generative AI model based on the facial surface morphology effect result generated in step 1432. B-spline deformation can effectively smooth facial lines, optimize facial contours, and ensure that the effect after micro-plastic surgery is softer and more natural; through the processing of B-spline deformation, the lines and contours of the face will be smoother and more natural, avoiding the stiff and unnatural effects caused by micro-plastic surgery. This process ensures that the facial micro-plastic surgery effect is more ergonomic and visually more comfortable.

[0139] Step 1434 is intended to add realistic lighting effects to the generated facial 3D image, simulating how light affects the face in the actual postoperative environment. In addition, facial texture is mapped, including skin color uniformity, texture connection, and flatness, to enhance the realism of the image. By considering ambient light (I t ), diffuse reflection (I d ) and specular reflection (I s ) brightness, can more accurately present the visual effects of the face under different lighting conditions; the mapping of lighting effects and facial textures can greatly enhance the realism and visualization of the image, making the virtual image closer to the postoperative effect. This process can help doctors and patients understand the effects of micro plastic surgery more intuitively, ensuring that the expected postoperative effect is close to reality.

[0140] Step 1435 Through the visualization image, the user can view the micro-plastic surgery effect and make adjustments, including various parameters such as filling amount, position, and dissolution effect. This step provides an interactive platform that allows users to make real-time adjustments on the image until the most ideal effect is found. At the same time, the system will feedback and update the generative AI model to generate the final facial micro-plastic surgery effect map; the advantage of this step is interactivity and real-time, making the micro-plastic surgery process more personalized and flexible. Through continuous adjustment and feedback, users can accurately control the micro-plastic surgery effect and avoid unsatisfactory results due to errors or imperfect predictions. Ultimately, the generated visualization image can accurately show the postoperative effect and help patients make more informed decisions.

[0141] like Figure 2 As shown, a facial micro-plastic surgery effect simulation system based on generative AI includes:

[0142] Data acquisition module: used to acquire a plurality of patient facial three-dimensional image data to obtain a facial three-dimensional image data set; extract and calibrate the facial defect features of each data item in the facial three-dimensional image data set to obtain a defect calibration data set, wherein the defect calibration data represents the marking of defect feature data existing on the patient's face;

[0143] Data recognition module: It is used to identify the defect feature data in the patient's facial 3D image based on the historically collected patient facial 3D image data set and the defect calibration data set, and simulate the initial micro-plastic surgery plan for the patient's facial defect feature data through a generative AI model;

[0144] Real-time adjustment module: It is used to enable the patient to intuitively feel the contrast effect of facial improvement before and after the surgery based on the initial micro-plastic surgery plan; based on the comparison results and real-time interactive feedback with the patient, the surgical details are adjusted multiple times according to the patient's expected effect to set a real-time adjustment strategy and generate the final facial micro-plastic surgery plan;

[0145] Effect display module: It is used to obtain the interactive effect of facial micro-plastic surgery filling or dissolving materials and the human face based on the final facial micro-plastic surgery plan by constructing the facial micro-plastic surgery interactive effect model, and update and feedback the generative AI model to obtain the final visual display image of the face after surgery.

[0146] When the functions of the above modules are implemented in the form of software functional units and used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks or optical disks.

[0147] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general intelligent device. Therefore, the purpose of the present invention can also be achieved by simply providing a program product containing a program code that implements the method or system. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order. Some steps can be performed in parallel or independently of each other.

Claims

1. A facial micro-plastic surgery effect simulation method based on generative AI, characterized in that: include: Collecting a plurality of patient facial three-dimensional image data to obtain a facial three-dimensional image data set; extracting and calibrating facial defect features of each data item in the facial three-dimensional image data set to obtain a defect calibration data set, wherein the defect calibration data represents marking of defect feature data existing on the patient's face; Based on the historically collected patient facial 3D image dataset and the defect calibration dataset, the defect feature data existing in the patient's facial 3D image is identified through a generative AI model and an initial micro-plastic surgery plan for the patient's facial defect feature data is simulated; Based on the initial micro-plastic surgery plan, the patient can intuitively feel the contrast effect of facial improvement before and after the surgery; based on the comparison results and real-time interactive feedback with the patient, the details of the surgery are adjusted in multiple rounds according to the patient's expected effect, so as to set a real-time adjustment strategy and generate a final facial micro-plastic surgery plan; Based on the final facial micro-plastic surgery plan, the facial micro-plastic surgery interaction effect model is constructed to obtain the interaction effect between facial micro-plastic surgery filling or dissolving materials and the human face, and the generative AI model is updated and fed back to obtain the final visual display image of the face after surgery.

2. According to claim 1, a facial micro-plastic surgery effect simulation method based on generative AI is characterized in that: Scan and collect facial image data of a patient, perform three-dimensional modeling on the facial image of the patient to generate facial three-dimensional image data; merge a plurality of the facial three-dimensional image data into the facial three-dimensional image data set; The two-dimensional image data in the four directions of top, bottom, left and right of each of the three-dimensional facial images are retained to obtain a micro-surgery reference image data set.

3. The method for simulating facial micro-plastic surgery effects based on generative AI according to claim 2, characterized in that: The real-time adjustment strategy includes: An initial micro-plastic surgery plan based on the patient's facial defect feature data to obtain the degree of the patient's facial defect; Preset a facial flatness threshold range, compare the patient's facial defect with the preset facial flatness threshold range, and determine whether the patient's facial defect is concave or convex based on the comparison result; pass To obtain the degree of convexity and concavity of facial defects, where R1 and R2 represent the main curvature radii of the convex and concave areas respectively; when facial concave features appear, the facial concave area is filled with filling materials so that the concave area reaches the preset facial flatness threshold range; When protruding facial features appear, the protruding facial area is dissolved by dissolving materials so that the protruding area reaches the preset facial flatness threshold range to obtain a secondary micro-plastic surgery plan.

4. The method for simulating facial micro-plastic surgery effects based on generative AI according to claim 3, characterized in that: Based on the micro-plastic surgery secondary plan, according to the patient's feedback on the satisfaction with the surgical effect, the description of the facial change requirements and personal preferences, the updated generative AI model is used to output the adjustment simulation results; The adjustment simulation results include adjustments to facial contours, skin firmness, fat distribution and filling depth, so as to dynamically optimize and adjust the patient's facial coordination effect in multiple dimensions; based on the adjustment simulation results, a final personalized facial micro-plastic surgery plan with multiple adjustment plans is independently recommended, and iterative optimization is performed in combination with individual differences of patients to obtain a three-level micro-plastic surgery plan.

5. The method for simulating facial micro-plastic surgery effects based on generative AI according to claim 1, characterized in that: Extracting and calibrating facial defect features of each data item in the facial three-dimensional image dataset to obtain a defect calibration dataset, including: The facial three-dimensional image dataset is subjected to centering and scaling processing to normalize the coordinates of each data item in the three-dimensional image dataset to a uniform range, so as to obtain a normalized three-dimensional image dataset; the three-dimensional image models of the normalized three-dimensional image dataset are aligned by an iterative closest point algorithm, so that different facial images are in the same reference coordinate system; The defect area is identified by statistical analysis of the three-dimensional shape of the face, and key points are arranged for three-dimensional positioning of image markers on the three-dimensional image data items in the normalized three-dimensional image data set; multiple key points are arranged around the facial defect area; and features of the facial defect area are extracted by three-dimensional point cloud technology to obtain features of the facial defect area; Based on the facial defect area features extracted from the three-dimensional image, a sliding window algorithm is used to find the defect area and perform calibration processing to obtain defect calibration data; a variety of defect calibration data are obtained based on a variety of different facial three-dimensional images to form a defect calibration data set.

6. The method for simulating facial micro-plastic surgery effects based on generative AI according to claim 5, characterized in that: Acquire the micro-plastic filling or dissolving material property data that matches the human body tissue to obtain a material property data set; construct a training set with the historically collected facial three-dimensional image data set and the material property data set to generate a facial micro-plastic surgery interaction effect model; the facial micro-plastic surgery interaction effect model outputs an interaction effect recognition result of the micro-plastic filling or dissolving material required to represent the facial image; The newly acquired three-dimensional facial image of the patient is input into the facial micro-surgery interaction effect model to output facial defect features of the newly acquired three-dimensional facial image of the patient and a prediction result of the interaction effect of the required filling or dissolving materials; based on the interaction effect prediction result, the dynamic change characteristics of the filling or dissolving material in the patient's body are used to obtain the interaction data between the simulation material and the facial tissue.

7. The method for simulating facial micro-plastic surgery effects based on generative AI according to claim 6, characterized in that: Based on the recognition result of the facial micro-plastic surgery interaction effect model, simulation is performed in combination with the micro-plastic surgery filling or dissolving material characteristic data; according to the simulated effect of the filling or dissolving material interaction effect on the patient's face, a postoperative effect visualization image is generated to demonstrate the improvement effect of the filling or dissolving material on the facial defect characteristics; Based on the display effect, real-time feedback and timely adjustment of the plan are provided to generate a personalized final plan for facial micro-surgery.

8. The method for simulating facial micro-plastic surgery effects based on generative AI according to claim 7, characterized in that: According to the characteristic data of different filling or dissolving materials, the deformation effect of the filling or dissolving material is obtained by σ=E·ε; wherein σ represents stress, E represents the elastic modulus of the characteristic data of the material, and ε represents strain; Based on the deformation effect of filling or dissolving materials, Obtain the diffusion degree of the filling or dissolving material in the subcutaneous tissue gap to describe the adaptation and distribution of the material on the face; and combine the facial micro-surgery interaction effect model to obtain the effect of the material filling or dissolving on the facial surface morphology; In the formula, δ represents the diffusion degree of the filling or dissolving material in the subcutaneous tissue gap; F represents the deformation force generated by the filling or dissolving material; k skin Represents the elasticity coefficient of the skin.

9. The method for simulating facial micro-plastic surgery effects based on generative AI according to claim 8, characterized in that: According to the impact of the facial surface morphology after filling or dissolving, the facial lines of the facial micro-surgery 3D image generated by the generative AI model are smoothed using B-spline deformation; by I=I t +I d +I s , to obtain the lighting effect after the face real display surgery, and map the facial texture to improve the realism of visualization; the facial texture includes skin color uniformity, texture connection and flatness; where I t ,I d and I s They represent the brightness of ambient light, diffuse light, and specular light, respectively, and I represents the brightness of postoperative light actually displayed on the face; View the micro-plastic surgery effect based on the visualized image to adjust the material filling amount, position, dissolution effect and other parameters; And feedback is provided to update the generative AI model to generate a final visualization image of the postoperative effect of facial micro-plastic surgery.

10. A facial micro-plastic surgery effect simulation system based on generative AI, characterized in that: The system is provided with an electronic device including a memory, a processor, and a facial micro-plastic surgery effect simulation method program based on generative AI stored in the memory and executable on the processor. When the facial micro-plastic surgery effect simulation method program based on generative AI is executed by the processor, the steps of the facial micro-plastic surgery effect simulation method based on generative AI as claimed in any one of claims 1 to 9 are implemented. The system includes: Data acquisition module: used to acquire a plurality of patient facial three-dimensional image data to obtain a facial three-dimensional image data set; extract and calibrate the facial defect features of each data item in the facial three-dimensional image data set to obtain a defect calibration data set, wherein the defect calibration data represents the marking of defect feature data existing on the patient's face; Data recognition module: It is used to identify the defect feature data in the patient's facial 3D image based on the historically collected patient facial 3D image data set and the defect calibration data set, and simulate the initial micro-plastic surgery plan for the patient's facial defect feature data through a generative AI model; Real-time adjustment module: It is used to enable the patient to intuitively feel the contrast effect of facial improvement before and after the surgery based on the initial micro-plastic surgery plan; based on the comparison results and real-time interactive feedback with the patient, the surgical details are adjusted multiple times according to the patient's expected effect to set a real-time adjustment strategy and generate the final facial micro-plastic surgery plan; Effect display module: It is used to obtain the interactive effect of facial micro-plastic surgery filling or dissolving materials and the human face based on the final facial micro-plastic surgery plan by constructing the facial micro-plastic surgery interactive effect model, and update and feedback the generative AI model to obtain the final visual display image of the face after surgery.

Images