A modeling device for evaluating skin repair efficacy based on machine learning model

Abstract

The present invention provides a skin repair efficacy evaluation modeling device based on a machine learning model, which relates to the technical field of skin repair. The method comprises: a friction module, which is used to apply uniform friction force on the skin surface; a scratch module, which is used to make scratches on the surface of a three-dimensional skin model of a human body; a friction number counting module, which is used to record the number of frictions; a force control module, which is used to control the friction force applied to the skin; a speed control module, which is used to control the friction speed on the skin; a scratch control module, which is used to control the length of the scratch generated by friction on the skin; an angle control module, which is used to adjust the scratch angle on the skin; a feedback module, which is used to measure the erythema index and hemoglobin content of the skin through a multi-spectral imaging device; a central control module, which is used to control a force control module, a speed control module, a scratch control module and a position control module; and a safety protection module, which is used to provide safety protection through an emergency stop button and a safety guardrail.

Description

Technical Field

[0001] The present invention relates to the technical field of skin repair, and in particular to a skin repair efficacy evaluation modeling device based on a machine learning model. Background Art

[0002] Skin injury modeling is an important method in skin pathology research, helping scientists understand the physiological and biochemical reactions of the skin during injury and repair. By simulating different types and degrees of skin damage, the skin's healing mechanism, inflammatory response, and regeneration process can be studied.

[0003] Existing skin injury modeling mostly relies on manual operation, which is not only inefficient but also prone to errors. It is difficult to ensure the uniformity and consistency of the number of frictions, strength, speed, scratch length, depth, angle and distribution, which affects the accuracy and repeatability of the test results. Summary of the invention

[0004] In order to solve the technical problems that skin injury modeling in the prior art mostly relies on manual operation, which is not only inefficient but also prone to errors, and it is difficult to ensure the uniformity and consistency of the number of frictions, strength, speed, scratch length, depth, angle and distribution, thus affecting the accuracy and repeatability of the test results, the present invention provides a skin repair efficacy evaluation modeling device based on a machine learning model.

[0005] The technical solution provided by the embodiment of the present invention is as follows:

[0006] An embodiment of the present invention provides a skin repair efficacy evaluation modeling device based on a machine learning model, comprising:

[0007] The friction module is used to simulate friction damage and apply uniform friction force on the skin surface;

[0008] A scratch module, used to create scratches on the surface of a normal human 3D skin model;

[0009] A friction times counting module is used to record the friction times;

[0010] A force control module is used to control the friction force applied to the skin through a robotic arm, and to provide real-time feedback of the friction force on the skin through a force sensor;

[0011] A speed control module, used to control the friction speed on the skin by controlling the motor speed, and to provide real-time feedback of the friction speed on the skin through a speed sensor;

[0012] A scratch control module, used to control the length of the scratch caused by friction on the skin through the slide rail system, control the depth of the scratch caused by friction on the skin through the depth adjustment device, and provide real-time feedback of the depth of the scratch caused by friction on the skin through the depth sensor;

[0013] An angle control module, used to adjust the scratch angle on the skin through an angle fine-tuning device, and to control the scratch angle on the skin to remain constant through a fixed angle mechanism;

[0014] A position control module, used to control the uniform distribution of multiple scratches on the skin through a multi-point scratching system, and to provide real-time feedback of the positions of the multiple scratches on the skin through a position sensor;

[0015] A feedback module for measuring the erythema index and hemoglobin content of the skin by a multispectral imaging device;

[0016] A central control module, used to control the force control module, the speed control module, the scratch control module and the position control module according to the data fed back in real time by the force sensor, the speed sensor, the depth sensor and the position sensor and the erythema index and hemoglobin content fed back in real time by the feedback module;

[0017] Safety protection module for safety protection via emergency stop button and safety fence.

[0018] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0019] In the present invention, the force control module, speed control module, scratch control module and position control module can be controlled according to the data fed back in real time by the force sensor, speed sensor, depth sensor and position sensor, as well as the erythema index and hemoglobin content fed back in real time by the feedback module, so as to automatically realize skin injury modeling and improve the efficiency of skin injury modeling. The uniformity and consistency of the number of frictions, force, speed, scratch length, depth, angle and distribution can be ensured, so as to improve the standardization and consistency of skin injury modeling in skin human efficacy testing and soothing repair projects, and improve the accuracy and repeatability of the test results. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1A schematic diagram of the structure of a skin repair efficacy evaluation modeling device based on a machine learning model provided in an embodiment of the present invention.

[0022] [Reference Signs]

[0023] 1-Friction module; 2-Scratch module; 3-Friction times counting module; 4-Force control module; 5-Speed ​​control module; 6-Scratch control module; 7-Angle control module; 8-Position control module; 9-Feedback module; 10-Central control module; 11-Safety protection module. DETAILED DESCRIPTION

[0024] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0025] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0026] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0027] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0028] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0029] Reference Manual Attached Figure 1 , showing a structural schematic diagram of a skin repair efficacy evaluation modeling device based on a machine learning model provided in an embodiment of the present invention.

[0030] An embodiment of the present invention provides a skin repair efficacy evaluation modeling device based on a machine learning model, which can cause a short-term and recoverable erythema phenomenon on healthy skin within a safe range, causing only slight and temporary skin redness, and this reaction is expected and controllable and does not violate medical ethics.

[0031] The skin repair efficacy evaluation modeling equipment based on the machine learning model includes: a friction module 1, a scratch module 2, a friction times counting module 3, a force control module 4, a speed control module 5, a scratch control module 6, an angle control module 7, a position control module 8, a feedback module 9, a central control module 10 and a safety protection module 11.

[0032] Friction module 1 is used to simulate friction damage and apply uniform friction force on the skin surface.

[0033] Specifically, the friction module 1 is usually a device with a friction pad or a friction surface. The friction pad may be made of various materials (such as sandpaper, cloth), and its surface has different roughness, which is used to create different degrees of friction damage. The friction module 1 is fixed to the end of the robot arm to ensure that the friction force can be evenly applied to the target surface.

[0034] The scratch module 2 is used to create scratches on the surface of a normal human three-dimensional skin model.

[0035] Specifically, the scratching module 2 is a scratching needle or a custom scratching device, which can produce clear scratches on the target surface. The scratching module 2 is installed on the robot arm through a clamp or a fixture, and can accurately control the parameters (such as length, depth and angle) of the scratch on the target surface.

[0036] The friction times counting module 3 is used to record the friction times.

[0037] Specifically, the friction times counting module 3 is implemented by an electronic counter, which automatically records once each friction is completed.

[0038] Optionally, the electronic counter is mounted on the control panel of the robot arm or the friction device.

[0039] Furthermore, the friction times counting module 3 further comprises a friction sensor which is installed near the friction surface, detects each friction action and sends a signal to the electronic counter.

[0040] In the present invention, the friction times counting module 3 implemented by the electronic counter not only improves the accuracy and efficiency of the experiment, but also significantly improves the consistency and repeatability of the experimental operation, providing a reliable data basis for the evaluation of skin repair efficacy.

[0041] The force control module 4 is used to control the friction force applied to the skin through the mechanical arm, and can accurately control the force or intensity applied to the skin. The friction force on the skin is fed back in real time by the force sensor, so that the friction force can be consistent each time.

[0042] Specifically, the mechanical arm is installed on the device body, and a force sensor is provided at the end thereof. The force sensor is installed at the contact point at the end of the mechanical arm, monitors the applied force in real time and feeds back to the central control module 10.

[0043] In the present invention, through the combination of the robotic arm and the force sensor, the force control module 4 can accurately control the friction force applied to the skin, ensuring that the force is consistent in each experiment, thereby significantly improving the accuracy, efficiency and repeatability of the experiment, reducing human errors and sample damage, and providing a reliable experimental basis for the evaluation of skin repair efficacy.

[0044] The speed control module 5 is used to control the friction speed on the skin by controlling the motor speed, so as to achieve uniformity of the friction speed. The friction speed on the skin is fed back in real time by the speed sensor, so as to ensure a constant friction speed.

[0045] Specifically, the motor is used to drive the friction device and is installed in the driving system of the friction device. The speed sensor is installed on the motor shaft to monitor the speed in real time and feed it back to the central control module 10.

[0046] In the present invention, by controlling the combination of motor speed and speed sensor, the speed control module 5 can accurately control the friction speed on the skin, ensuring that the speed of each experiment is constant, thereby significantly improving the accuracy, efficiency and repeatability of the experiment, reducing human errors and sample damage, and providing a reliable experimental basis for the evaluation of skin repair efficacy.

[0047] The scratch control module 6 is used to control the length of the scratch caused by friction on the skin through the slide rail system, and can accurately set the length and depth of the scratch. The depth of the scratch caused by friction on the skin is controlled by the depth adjustment device, and the depth of the scratch caused by friction on the skin is fed back in real time by the depth sensor, so that the scratch depth can be ensured to be consistent.

[0048] Specifically, the slide rail system is installed in the operating area of ​​the equipment and is equipped with a high-precision electric slide rail with adjustable length and precision scale. An electric lifting platform is installed on the slide rail system to adjust the scratch depth. A depth sensor is installed on the electric lifting platform to monitor the scratch depth in real time and feed it back to the central control module 10.

[0049] In a possible implementation, the slide rail system is configured with a high-precision electric slide rail, the length of the electric slide rail is adjustable, and a precision scale is provided on the electric slide rail to ensure accurate control of the scratch length.

[0050] In a possible implementation, the depth adjustment device includes an electric lifting platform. The depth of the scratches produced by friction on the skin is controlled by controlling the height of the electric lifting platform, thereby ensuring that the depth of each scratch is consistent.

[0051] In the present invention, through the combination of high-precision electric slide rails, electric lifting platforms and depth sensors, the scratch control module 6 can accurately control the length and depth of friction scratches on the skin, ensuring that the length and depth of the scratches are consistent in each experiment, thereby significantly improving the accuracy, efficiency and repeatability of the experiment, reducing human errors and sample damage, and providing a reliable experimental basis for the evaluation of skin repair efficacy.

[0052] The angle control module 7 is used to adjust the scratch angle on the skin through the angle fine-tuning device, and to control the scratch angle on the skin to remain constant through the fixed angle mechanism. The angle fine-tuning device allows the scratch angle to be fine-tuned within a preset range, which can ensure the flexibility and accuracy of the experiment.

[0053] Specifically, a fixed angle mechanism is installed at the end of the robot arm to ensure a constant scratching angle, and an angle fine-tuning device is installed on the fixed angle mechanism to allow fine-tuning of the scratching angle within a preset range.

[0054] In a possible implementation, a fixed angle mechanism is disposed at the end of the robot arm to ensure that the scratching angle is constant.

[0055] In the present invention, through the combination of the angle fine-tuning device and the fixed angle mechanism, the angle control module 7 can accurately adjust and maintain the angle of the scratch on the skin, ensuring the angle consistency and flexibility in the experiment, thereby significantly improving the accuracy, efficiency and repeatability of the experiment, reducing human errors, and providing a reliable experimental basis for the evaluation of skin repair efficacy.

[0056] The position control module 8 is used to control the uniform distribution of the multi-point scratches on the skin through the multi-point scratch system, and to provide real-time feedback of the positions of the multi-point scratches on the skin through the position sensor.

[0057] Specifically, the position control module 8 presets multiple scratching positions by a computer program, and the robot arm performs scratching operations in sequence according to the preset positions. At the same time, the position control module 8 also includes a position calibration device. The position calibration device includes a laser positioning and a camera, which is installed above or around the operation area to monitor the scratching position in real time to ensure the position accuracy.

[0058] In a possible implementation, the multi-point scratching system presets a plurality of scratching positions through a computer program, and the robot arm performs friction operations sequentially according to the preset plurality of scratching positions.

[0059] In a possible implementation, the position sensor specifically includes a laser positioning sensor and a camera. The laser positioning sensor and the camera can provide real-time feedback of the positions of multiple scratches on the skin, thereby ensuring accurate scratch positions and avoiding error accumulation.

[0060] In the present invention, through the combination of a multi-point scratch system and a position sensor, the position control module 8 can accurately control the distribution of multi-point scratches on the skin, ensuring the accuracy and consistency of the scratch position in each experiment, thereby significantly improving the accuracy, efficiency and repeatability of the experiment, reducing human errors, and providing a reliable experimental basis for the evaluation of skin repair efficacy.

[0061] The feedback module 9 is used to measure the erythema index and hemoglobin content of the skin by means of a multi-spectral imaging device.

[0062] Among them, the multispectral imaging equipment collects reflected light information at different depths of the skin through multiple spectral channels to analyze changes in skin erythema and hemoglobin content.

[0063] Among them, the erythema index (EI) is an indicator used to quantify the degree of skin erythema (skin redness usually caused by inflammation, irritation or trauma).

[0064] Among them, hemoglobin content is an indicator to measure the concentration of hemoglobin (heme) in the skin, which is used to evaluate skin blood flow and blood supply.

[0065] In a possible implementation manner, the feedback module 9 is specifically used for:

[0066] The erythema index and hemoglobin content of the skin were measured by multispectral imaging equipment.

[0067] Using data fusion technology, skin condition is predicted based on erythema index and hemoglobin content.

[0068] Optionally, data from different sensors can be processed comprehensively through data fusion techniques such as weighted averaging and Bayesian inference to improve data accuracy and reliability.

[0069] Specifically, data fusion technology includes:

[0070] The erythema index (RI) and hemoglobin content (Hb) data of the skin surface are collected in real time through multispectral imaging equipment.

[0071] The collected erythema index and hemoglobin data are preprocessed to remove noise and outliers. Common methods include median filtering and standardization.

[0072] Perform weighted averaging on the preprocessed data to obtain more stable and reliable results:

[0073]

[0074] Among them, RI avg represents the weighted mean erythema index, Hbavg Represents the weighted average hemoglobin content, RI i and Hb i are the erythema index and hemoglobin content collected at the i-th time, ω i is the weight at the i-th collection.

[0075] Combining the data collected multiple times with prior knowledge, a more accurate estimate can be obtained using the Bayesian inference method. The Bayesian formula is as follows:

[0076]

[0077] Among them, P(θ|data) is the posterior probability, P(data|θ) is the likelihood function, P(θ) is the prior probability, and P(data) is the normalization constant.

[0078] According to the erythema index and hemoglobin content after fusion, calculate the appropriate adjustment of operating parameters:

[0079] F adjust =F current +k1(RI target -RI avg )+k2(Hb target -Hb avg )

[0080] V adjust =V current +k3(RI target -RI avg )+k4(Hb target -Hb avg )

[0081] D adjust =D current +k5(RI target -RI avg )+k6(Hb target -Hb avg )

[0082] Among them, F adjust 、V adjust and D adjust are the adjustment values ​​of friction intensity, speed and depth respectively, F current 、V current and D current They are the current friction force, speed and depth respectively, k1 to k6 are adjustment coefficients, RI target Indicates the target erythema index, Hb arget Indicates the target hemoglobin content.

[0083] In the present invention, by using multispectral imaging equipment and data fusion technology, the feedback module 9 can provide accurate and reliable skin condition assessment data, support a variety of application scenarios, and improve the efficiency and quality of experiments and research.

[0084] The central control module 10 is used to control the force control module 4, the speed control module 5, the scratch control module 6 and the position control module 8 by using a machine learning algorithm according to the data fed back in real time by the force sensor, the speed sensor, the depth sensor and the position sensor and the erythema index and the hemoglobin content fed back in real time by the feedback module 9, so as to ensure the accuracy and consistency of the operation process.

[0085] Optionally, Force sensor: installed at the contact point at the end of the robot arm to monitor the applied force. Depth sensor: installed on the electric lifting platform to monitor the scratch depth. Speed ​​sensor: installed on the motor shaft to monitor the friction speed. Laser positioning and camera: installed above or around the operating area to monitor the scratch position in real time and ensure accurate positioning.

[0086] Specifically, the central control module 10 is composed of a high-performance processor and embedded control software, and monitors and controls the operation of each module in real time.

[0087] In a possible implementation, the central control module 10 is specifically used for:

[0088] Using machine learning algorithms, a relationship model between skin conditions and operating parameters is established.

[0089] Specifically, the machine learning algorithm can input erythema index RI, hemoglobin content Hb, friction force F, speed V, depth D. Output: friction force F adjust , speed V adjust and depth D adjust The amount of adjustment.

[0090] Collect a large amount of experimental data, record the erythema index, hemoglobin content and corresponding operating parameters (force, speed, depth, etc.).

[0091] Important features were selected as model inputs, such as erythema index, hemoglobin content, force, speed, and depth.

[0092] Use regression analysis or neural network models for training. For example, using a multivariate linear regression model:

[0093] RI=β0+β1F+β2V+β3D+ε

[0094] Hb=γ0+γ1F+γ2V+γ3D+η

[0095] Among them, RI and Hb are erythema index and hemoglobin content, respectively; F, V, and D are force, speed, and depth, respectively; β0, β1, β2, β3, γ0, γ1, γ2, and γ3 are model coefficients; and ε and η are error terms.

[0096] Use methods such as cross-validation to evaluate the accuracy and stability of the model and select the best model.

[0097] The safety protection module 11 is used for providing safety protection through an emergency stop button and a safety guardrail.

[0098] During operation, the model makes predictions based on real-time monitoring data and adjusts operating parameters. The specific steps are as follows:

[0099] (1) Real-time data collection: The sensor collects erythema index, hemoglobin content and current operating parameters in real time.

[0100] (2) Data input model: Input the data collected in real time into the machine learning model.

[0101] (3) Predicted Adjustment: The model predicts the operating parameters that need to be adjusted based on the input data.

[0102] (4) Adjust operating parameters: adjust friction force, speed and depth according to the model prediction results.

[0103] Optionally, the machine learning model is trained with a large amount of experimental data to continuously optimize the relational model parameters and improve the accuracy and stability of the prediction.

[0104] Acquire the skin status fed back in real time by the feedback module 9.

[0105] According to the skin condition fed back in real time by the feedback module 9, the operating parameters are determined using the relationship model between the skin condition and the operating parameters.

[0106] Optionally, the operating parameters include: friction force, friction speed, scratch depth, and scratch angle.

[0107] According to the operating parameters, the force control module 4, the speed control module 5, the scratch control module 6 and the position control module 8 are controlled.

[0108] In the present invention, through real-time monitoring and intelligent adjustment of the central control module 10, the accuracy and consistency of the operation process can be ensured, human errors can be reduced, experimental efficiency and data quality can be improved, a reliable experimental basis can be provided for the evaluation of skin repair efficacy, and the improvement of scientific research level can be promoted.

[0109] In one possible implementation, the operation process of the skin repair efficacy evaluation modeling device based on the machine learning model specifically includes:

[0110] S1: Set operating parameters.

[0111] Optionally, the operating parameters include a preset number of frictions.

[0112] S2: Fix the skin sample on the workbench.

[0113] S3: Start the equipment, and the robot arm performs friction operation according to the operating parameters.

[0114] S4: Record the number of frictions in real time, monitor and adjust the friction force, friction speed, scratch depth and scratch angle.

[0115] S5: When the preset friction times are reached, the operation will automatically stop and the parameter data will be recorded.

[0116] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0117] In the present invention, the force control module 4, the speed control module 5, the scratch control module 6 and the position control module 8 can be controlled according to the data fed back in real time by the force sensor, the speed sensor, the depth sensor and the position sensor, as well as the erythema index and the hemoglobin content fed back in real time by the feedback module 9, so as to automatically realize the skin injury modeling and improve the efficiency of the skin injury modeling. The uniformity and consistency of the number of frictions, the force, the speed, the scratch length, the depth, the angle and the distribution can be ensured, so as to improve the standardization and consistency of the skin injury modeling in the skin human efficacy test and the soothing and repairing projects, and improve the accuracy and repeatability of the test results.

[0118] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0119] There are a few points to note:

[0120] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.

[0121] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0122] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0123] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A skin repair efficacy evaluation modeling device based on a machine learning model, characterized in that: include: The friction module is used to simulate friction damage and apply uniform friction force on the skin surface; A scratch module, used to create scratches on the surface of a normal human 3D skin model; A friction times counting module is used to record the friction times; A force control module is used to control the friction force applied to the skin through a robotic arm, and to provide real-time feedback of the friction force on the skin through a force sensor; A speed control module, used to control the friction speed on the skin by controlling the motor speed, and to provide real-time feedback of the friction speed on the skin through a speed sensor; A scratch control module, used to control the length of the scratch caused by friction on the skin through the slide rail system, control the depth of the scratch caused by friction on the skin through the depth adjustment device, and provide real-time feedback of the depth of the scratch caused by friction on the skin through the depth sensor; An angle control module, used to adjust the scratch angle on the skin through an angle fine-tuning device, and to control the scratch angle on the skin to remain constant through a fixed angle mechanism; A position control module, used to control the uniform distribution of multiple scratches on the skin through a multi-point scratching system, and to provide real-time feedback of the positions of the multiple scratches on the skin through a position sensor; A feedback module for measuring the erythema index and hemoglobin content of the skin by a multispectral imaging device; A central control module, configured to control the force control module, the speed control module, the scratch control module and the position control module by using a machine learning algorithm according to the data fed back in real time by the force sensor, the speed sensor, the depth sensor and the position sensor and the erythema index and hemoglobin content fed back in real time by the feedback module; Safety protection module for safety protection via emergency stop button and safety fence.

2. The skin repair efficacy evaluation modeling device based on the machine learning model according to claim 1 is characterized in that: The slide rail system is equipped with a high-precision electric slide rail, the length of the electric slide rail is adjustable, and a precision scale is provided on the electric slide rail.

3. The skin repair efficacy evaluation modeling device based on the machine learning model according to claim 1 is characterized in that: The depth adjustment device comprises an electric lifting platform, and the depth of the scratches produced by friction on the skin is controlled by controlling the height of the electric lifting platform.

4. The skin repair efficacy evaluation modeling device based on a machine learning model according to claim 1, characterized in that: The fixed angle mechanism is arranged at the end of the mechanical arm.

5. The skin repair efficacy evaluation modeling device based on machine learning model according to claim 1, characterized in that: The multi-point scratching system presets a plurality of scratching positions through a computer program, and the mechanical arm performs friction operations in sequence according to the preset plurality of scratching positions.

6. The skin repair efficacy evaluation modeling device based on a machine learning model according to claim 1, characterized in that: The position sensor specifically includes a laser positioning sensor and a camera, and the laser positioning sensor and the camera are used to provide real-time feedback of the positions of multiple scratches on the skin.

7. The skin repair efficacy evaluation modeling device based on a machine learning model according to claim 1, characterized in that: The feedback module is specifically used for: The erythema index and hemoglobin content of the skin were measured by multispectral imaging equipment; The skin condition is predicted according to the erythema index and the hemoglobin content by using data fusion technology.

8. The skin repair efficacy evaluation modeling device based on a machine learning model according to claim 1, characterized in that: The central control module is specifically used for: Using machine learning algorithms, a relationship model between skin conditions and operating parameters is established; Acquire the skin condition fed back in real time by the feedback module; According to the skin state fed back in real time by the feedback module, the operating parameters are determined using a relationship model between the skin state and the operating parameters; The force control module, the speed control module, the scratch control module and the position control module are controlled according to the operating parameters.

9. The skin repair efficacy evaluation modeling device based on the machine learning model according to claim 8, characterized in that: The operating parameters include: friction force, friction speed, scratch depth, and scratch angle.

10. The skin repair efficacy evaluation modeling device based on machine learning model according to claim 9, characterized in that: The operation process of the skin repair efficacy evaluation modeling device based on the machine learning model specifically includes: S1: Set operating parameters; S2: Fix the skin sample on the workbench; S3: starting the device, and the robot arm performs friction operation according to the operating parameters; S4: Real-time recording of friction times, monitoring and adjusting friction intensity, friction speed, scratch depth and scratch angle; S5: When the preset friction times are reached, the operation will automatically stop and the parameter data will be recorded.

Images