Intelligent multi-parameter optimized ultrasonic therapeutic device and optimized control system

Abstract

The present invention relates to the technical field of ultrasonic therapeutic instruments, and in particular to an intelligent multi-parameter optimized ultrasonic therapeutic instrument and an optimized control system, comprising a data collection module for collecting historical ultrasonic therapeutic parameter data of the ultrasonic therapeutic instrument; a model training module for training an ultrasonic therapeutic parameter recommendation model based on the historical ultrasonic therapeutic parameter data, and then obtaining ultrasonic therapeutic parameters corresponding to ultrasonic therapeutic parameter recommendation set labels; and a control module for controlling the ultrasonic frequency, ultrasonic intensity and treatment time of ultrasonic waves emitted by the ultrasonic therapeutic instrument based on the obtained ultrasonic therapeutic parameters. The intelligent multi-parameter optimized ultrasonic therapeutic instrument and the optimized control system provided by the present invention predict the best treatment plan through the ultrasonic therapeutic parameter recommendation model, thereby improving the treatment effect, reducing the need to rely on the operator's experience, and also increasing the usability and popularity of the ultrasonic therapeutic instrument to meet the growing demand for personalized beauty.

Description

Technical Field

[0001] The present invention relates to the technical field of ultrasonic therapeutic instruments, in particular to an intelligent multi-parameter optimized ultrasonic therapeutic instrument and an optimized control system. Background Art

[0002] In the beauty industry, ultrasound technology, due to its high efficiency and non-invasive nature, is increasingly being used in treatments such as skin tightening, anti-aging, and body sculpting. Traditional ultrasound beauty devices, such as "ultrasound cannons," "supersonic cannons," and advanced devices called "beauty sculpting instruments," primarily work by emitting sound waves of specific frequencies and intensities deep within the skin, aiming to stimulate collagen production, promote blood circulation, and achieve slimming and body contouring effects.

[0003] Chinese patent application publication number CN114984469A discloses a control method, controller, system, and therapeutic device for an ultrasound therapy system. The control method for the ultrasound therapy system includes the following steps: step S10, displaying different operation areas divided based on the position of the human skin surface; step S20, displaying a treatment plan corresponding to the operation area selected by the user; step S30, controlling the operation of the ultrasound therapy system according to the treatment plan corresponding to the operation area selected by the user;

[0004] As mentioned in the above application, most existing ultrasound therapeutic devices still face the problems of single parameter settings and insufficient individualized treatment. That is, ultrasound therapeutic devices are set to a single mode for the treatment of all people, which means that it is impossible to achieve personalization and automation of ultrasound therapeutic devices through intelligent multi-parameter optimization systems. For example, the effect of the same device on different individuals may vary greatly because each person's skin type, age, health status and specific needs are different. In addition, the device operator needs to have professional knowledge to correctly set and adjust the treatment parameters, which limits the popularity and efficiency of the device.

[0005] In summary, developing an intelligent, multi-parameter optimized ultrasound therapeutic device and its control system, integrating advanced artificial intelligence technology, can significantly enhance the effectiveness and safety of ultrasound therapeutic devices while also increasing their usability and popularity, thereby meeting the growing demand for personalized beauty treatments. The implementation of such a system will drive the development of ultrasound beauty technology towards greater efficiency, intelligence, and personalization. Summary of the Invention

[0006] In order to solve the above problems, the present invention provides an intelligent multi-parameter optimized ultrasonic therapeutic apparatus and an optimized control system.

[0007] The present invention adopts the following technical solutions to provide an intelligent multi-parameter optimization control system for an ultrasonic therapeutic apparatus, including:

[0008] The data collection module collects historical ultrasound treatment parameter data of the ultrasound treatment device. The historical ultrasound treatment parameter data is collected when the treatment effect meets the standard. The historical ultrasound treatment parameter data includes comprehensive skin parameters, age and gender, and ultrasound treatment parameter sets;

[0009] The comprehensive skin parameters include skin moisture data, skin thickness data, skin oil content data, and skin elasticity data;

[0010] The ultrasonic treatment parameter set includes ultrasonic frequency, ultrasonic intensity and treatment time;

[0011] The model training module trains an ultrasound therapy parameter recommendation model based on historical ultrasound therapy parameter data, collects real-time comprehensive skin parameters, age, and gender, and obtains ultrasound therapy parameter recommendation set labels based on the trained ultrasound therapy parameter recommendation model, and then obtains the ultrasound therapy parameter recommendation set corresponding to the ultrasound therapy parameter recommendation set labels;

[0012] a control module for controlling the ultrasonic frequency, ultrasonic intensity, and treatment time of the ultrasonic waves emitted by the ultrasonic therapeutic apparatus based on the acquired ultrasonic treatment parameters;

[0013] Parameter adjustment module, every preset time T j Acquire skin condition data once, generate a skin condition coefficient based on the skin condition data, generate an ultrasonic treatment time parameter adjustment instruction based on the skin condition coefficient, transmit the parameter adjustment instruction to the control module, and the control module controls the ultrasonic treatment device to adjust the ultrasonic treatment time parameter.

[0014] As a further description of the above technical solution: the recommended set of ultrasound therapy parameters is:

[0015] {(P1, Q1, T1), (P2, Q2, T2), ..., (P n , Q n 、T n )};

[0016] Among them, P n is the ultrasonic frequency corresponding to the set label n, Q n is the ultrasonic intensity corresponding to the set label n, T n is the treatment time corresponding to the set label n, and n is the serial number of the recommended set label of ultrasound treatment parameters.

[0017] As a further description of the above technical solution: the training method of the ultrasound therapy parameter recommendation model includes:

[0018] Pre-set corresponding numbers for ultrasonic treatment parameter sets;

[0019] Converting the skin comprehensive parameters, age, and gender into a corresponding set of feature vectors, using each set of feature vectors as input to the ultrasound therapy parameter recommendation model, the ultrasound therapy parameter recommendation model using a set of ultrasound therapy parameter set numbers corresponding to each set of skin comprehensive parameters, age, and gender as output, using a set of ultrasound therapy parameter set numbers actually corresponding to each set of skin comprehensive parameters, age, and gender as prediction targets, and minimizing the loss function value of the ultrasound therapy parameter recommendation model as a training target; stopping training when the loss function value of the ultrasound therapy parameter recommendation model is less than or equal to a preset target loss value;

[0020] The ultrasound therapy parameter recommendation model may be one of support vector machine regression, random forest regression, or neural network regression models.

[0021] As a further description of the above technical solution: the skin condition data includes skin temperature data, skin humidity data and skin glossiness data;

[0022] The skin moisture data is obtained by measuring with a skin moisture tester, and the skin gloss data is obtained by measuring with a skin gloss meter.

[0023] As a further description of the above technical solution: the method of generating the skin condition coefficient based on the skin condition data is as follows:

[0024]

[0025] Where, Pzt represents the skin condition coefficient, Pw represents the skin temperature data, Ps represents the skin humidity data, and Pg represents the skin gloss data. and represents the weight coefficient, and Both are greater than 0.

[0026] As a further description of the above technical solution: the ultrasonic treatment time parameter adjustment instruction includes a first time adjustment instruction, a second time adjustment instruction and an instruction to stop ultrasonic treatment, wherein the first time adjustment instruction and the second time adjustment instruction are both to shorten the corresponding treatment time, and the time of shortening the treatment by the first time adjustment instruction and the second time adjustment instruction increases successively.

[0027] As a further description of the above technical solution: the method for generating an ultrasound treatment time parameter adjustment instruction based on the skin condition coefficient includes:

[0028] Preset skin condition data gradient thresholds P1, P2 and P3, where P1 < P2 < P3;

[0029] When Pzt<P1, no parameter adjustment instruction is generated;

[0030] When P1≤Pzt<P2, a first time adjustment instruction is generated;

[0031] When P2≤Pzt<P3, a second time adjustment instruction is generated;

[0032] When Pzt>P3, an instruction to stop ultrasonic treatment is generated.

[0033] As a further description of the above technical solution: the skin temperature data collection method includes:

[0034] Obtain the skin area to be treated by the ultrasound therapeutic device and mark it as the area to be tested, aim the thermal imager at the area to be tested, and obtain a thermal imaging image;

[0035] The acquired thermal imaging image is divided into i sub-regions of equal size, each sub-region consists of m pixels;

[0036] Extract the temperature values ​​of m pixels in each sub-region and calculate the sub-region temperature. There is a one-to-one correspondence between pixels and temperature values. The temperature data of the pixels can be automatically obtained through the thermal imager software.

[0037] The temperature values ​​of the i sub-areas are obtained to establish a set, and the maximum temperature value in the set is obtained as the skin temperature data.

[0038] As a further description of the above technical solution: the method of extracting the temperature values ​​of m pixels in each sub-region and calculating the temperature of the sub-region includes:

[0039]

[0040] Where, Ta i represents the temperature value of the ith sub-region, m represents the total number of pixels in the ith sub-region, Ti e Represents the temperature value of the e-th pixel in the i-th sub-region, e≤m.

[0041] An intelligent multi-parameter optimized ultrasonic therapeutic instrument includes an optimization control system of the intelligent multi-parameter optimized ultrasonic therapeutic instrument.

[0042] Beneficial effects:

[0043] The intelligent multi-parameter optimization ultrasonic therapeutic device and optimization control system provided by the present invention obtains ultrasonic therapeutic parameter recommendation set labels based on an ultrasonic therapeutic parameter recommendation model, further obtains ultrasonic therapeutic parameters corresponding to the ultrasonic therapeutic parameter recommendation set labels, and then controls the operation of the ultrasonic therapeutic device based on the ultrasonic therapeutic parameters. Thus, through intelligent multi-parameter acquisition and optimization, personalized and automated control parameter generation of the ultrasonic therapeutic device is achieved. That is, ultrasonic therapeutic parameters are automatically generated according to the user's comprehensive skin parameters, age, and gender, and then the operation of the ultrasonic therapeutic device is controlled based on the ultrasonic therapeutic parameters. That is, the optimal treatment plan is predicted by the ultrasonic therapeutic parameter recommendation model, thereby improving the treatment effect, reducing the need to rely on operator experience, and increasing the ease of use and popularity of the ultrasonic therapeutic device to meet the growing demand for personalized beauty.

[0044] Furthermore, a parameter adjustment module is added, which obtains skin condition data once every preset time, generates a skin condition coefficient based on the skin condition data, and judges the impact of the use of the ultrasonic therapeutic device on the skin condition. Then, based on the degree of the impact, the treatment time of the ultrasonic therapeutic device is reasonably adjusted to achieve dynamic optimization of the ultrasonic treatment parameters, greatly improving the effect and safety of the ultrasonic therapeutic device. This overcomes the existing technology that generally sets the ultrasonic treatment parameters and continues to treat the user until the set parameters are combined or the user feels uncomfortable and issues a request to end, resulting in damage to the user's skin. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The present invention will be further explained below in conjunction with the accompanying drawings and examples:

[0046] Figure 1 A schematic diagram of the module structure of the intelligent multi-parameter optimized ultrasonic therapeutic device and the optimized control system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the technical means, creative features, objectives and effects of the present invention easier to understand, the present invention is further described below with reference to specific diagrams. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other unless they conflict.

[0048] Example 1

[0049] See also Figure 1 The embodiment of the present invention provides a technical solution: an optimization control system for an intelligent multi-parameter optimization ultrasound therapeutic apparatus, comprising:

[0050] The data collection module collects the historical ultrasonic treatment parameter data of the ultrasonic treatment device. The historical ultrasonic treatment parameter data is collected when the treatment effect meets the standard. The historical ultrasonic treatment parameter data includes comprehensive skin parameters, age and gender, and ultrasonic treatment parameter set.

[0051] The comprehensive skin parameters include skin moisture data, skin thickness data, skin oil content data, and skin elasticity data.

[0052] It should be noted that skin moisture data is measured using a skin moisture tester, skin thickness data is obtained through high-frequency ultrasound, MRI, or CT measurements, skin oil content data is obtained through skin oil tester measurements, and skin elasticity data is obtained through skin elasticity measurement instruments (such as Cutometer). Cutometer primarily measures the elastic properties of the skin using negative pressure. Its working principle includes the following steps: using a negative pressure probe, the skin is pulled into the probe opening. Under the action of negative pressure, the skin will deform, and the optical sensor in the probe will record the skin deformation. When the negative pressure is released, the skin will return to its original state. The sensor will continue to record the skin's recovery and then obtain skin elasticity data.

[0053] The ultrasonic treatment parameter set includes ultrasonic frequency, ultrasonic intensity and treatment time.

[0054] The model training module trains an ultrasound therapy parameter recommendation model based on historical ultrasound therapy parameter data, collects real-time comprehensive skin parameters, age and gender, and obtains the ultrasound therapy parameter recommendation set label based on the trained ultrasound therapy parameter recommendation model, and then obtains the ultrasound therapy parameter recommendation set corresponding to the ultrasound therapy parameter recommendation set label.

[0055] The control module controls the ultrasonic frequency, ultrasonic intensity and treatment time of the ultrasonic waves emitted by the ultrasonic therapeutic device based on the acquired ultrasonic treatment parameters.

[0056] The recommended set of ultrasound therapy parameters is:

[0057] {(P1, Q1, T1), (P2, Q2, T2), ..., (P n , Q n 、T n )};

[0058] Among them, P n is the ultrasonic frequency corresponding to the set label n, Q n is the ultrasonic intensity corresponding to the set label n, T n is the treatment time corresponding to the set label n, and n is the serial number of the recommended set label of ultrasound treatment parameters.

[0059] The training method of the ultrasound therapy parameter recommendation model includes:

[0060] The ultrasonic treatment parameter sets are set with corresponding numbers in advance.

[0061] The skin comprehensive parameters, age and gender are converted into a corresponding set of feature vectors, and each set of feature vectors is used as the input of the ultrasound therapy parameter recommendation model. The ultrasound therapy parameter recommendation model uses a set of ultrasound therapy parameter set numbers corresponding to each set of skin comprehensive parameters, age and gender as output, a set of ultrasound therapy parameter set numbers actually corresponding to each set of skin comprehensive parameters, age and gender as prediction targets, and minimizing the loss function value of the ultrasound therapy parameter recommendation model as the training target; training is stopped when the loss function value of the ultrasound therapy parameter recommendation model is less than or equal to the preset target loss value.

[0062] The ultrasound therapy parameter recommendation model may be one of support vector machine regression, random forest regression, or neural network regression models.

[0063] The loss function value of the ultrasound therapy parameter recommendation model is the mean square error.

[0064] Mean square error is one of the commonly used loss functions.

[0065] The model is trained with minimization as the goal, so that the ultrasound therapy parameter recommendation model better fits the data, thereby improving the performance and accuracy of the model.

[0066] In the loss function, MSE is the loss function value of the ultrasound therapy parameter recommendation model, x is the eigenvector group number; p is the number of eigenvector groups; y x is the ultrasonic treatment parameter set number corresponding to the xth group of eigenvectors, is the ultrasonic treatment parameter set number corresponding to the xth group of eigenvectors in real time.

[0067] Other model parameters of the ultrasound therapy parameter recommendation model, target loss value, optimization algorithm, training set test set validation set ratio and loss function optimization are all achieved through actual engineering implementation and continuous experimental tuning.

[0068] Specifically, the optimization control system of the intelligent multi-parameter optimization ultrasonic therapeutic device trains an ultrasonic therapeutic parameter recommendation model by collecting a large amount of historical ultrasonic therapeutic parameter data, and then obtains the skin comprehensive parameters, age and gender of the user with instructions, obtains the ultrasonic therapeutic parameter recommendation set label based on the ultrasonic therapeutic parameter recommendation model, and then obtains the ultrasonic therapeutic parameters corresponding to the ultrasonic therapeutic parameter recommendation set label, and then controls the operation of the ultrasonic therapeutic device based on the ultrasonic therapeutic parameters, thereby realizing personalized and automated control parameter generation of the ultrasonic therapeutic device through intelligent multi-parameter acquisition optimization, that is, automatically generating ultrasonic therapeutic parameters according to the user's skin comprehensive parameters, age and gender, and then controlling the operation of the ultrasonic therapeutic device based on the ultrasonic therapeutic parameters, that is, predicting the best treatment plan through the ultrasonic therapeutic parameter recommendation model, thereby improving the treatment effect, reducing the need to rely on the operator's experience, and increasing the usability and popularity of the ultrasonic therapeutic device to meet the growing personalized beauty needs.

[0069] Example 2

[0070] See also Figure 1 When the ultrasonic therapeutic device is repairing the skin, the thermal and mechanical effects may cause the skin moisture to decrease, and the ultrasonic therapeutic device will usually cause the skin surface temperature to rise when repairing the skin. This is because when the ultrasonic wave is transmitted to the skin and subcutaneous tissue, it will be absorbed by the tissue and converted into heat energy. Secondly, when the ultrasonic therapeutic device is repairing the skin, the mechanical effect may cause damage to the skin surface and reduce the skin gloss. Therefore, when using the ultrasonic therapeutic device to repair the skin, in order to avoid discomfort or damage, it is necessary to regularly collect skin temperature data, skin humidity data, and skin gloss data, and reasonably adjust the treatment time.

[0071] This embodiment adds a parameter adjustment module based on the above embodiment.

[0072] Parameter adjustment module, every preset time T j Acquire skin condition data once, generate a skin condition coefficient based on the skin condition data, generate an ultrasonic treatment time parameter adjustment instruction based on the skin condition coefficient, transmit the parameter adjustment instruction to the control module, and the control module controls the ultrasonic treatment device to adjust the ultrasonic treatment time parameter.

[0073] It should be noted that T j ≤1min, preferably T j 5 seconds.

[0074] The skin condition data includes skin temperature data, skin moisture data, and skin glossiness data.

[0075] The skin moisture data is obtained by measuring with a skin moisture tester, and the skin gloss data is obtained by measuring with a skin gloss meter.

[0076] The skin temperature data collection method comprises:

[0077] Obtain the skin area to be treated by the ultrasound therapy device and mark it as the area to be tested. A thermal imager is aligned with the area to be tested to obtain a thermal imaging image.

[0078] The acquired thermal imaging image is divided into i sub-regions of the same size, and each sub-region consists of m pixels.

[0079] The temperature values ​​of m pixels in each sub-region are extracted to calculate the sub-region temperature. There is a one-to-one correspondence between the pixels and the temperature values. The temperature data of the pixels can be automatically obtained through the thermal imager software.

[0080] The temperature values ​​of the i sub-areas are obtained to establish a set, and the maximum temperature value in the set is obtained as the skin temperature data.

[0081] The method of extracting the temperature values ​​of m pixels in each sub-region and calculating the temperature of the sub-region includes:

[0082]

[0083] Where, Ta i represents the temperature value of the ith sub-region, m represents the total number of pixels in the ith sub-region, Ti e Represents the temperature value of the e-th pixel in the i-th sub-region, e≤m.

[0084] The method of generating the skin condition coefficient based on the skin condition data is as follows:

[0085]

[0086] Where, Pzt represents the skin condition coefficient, Pw represents the skin temperature data, Ps represents the skin humidity data, and Pg represents the skin gloss data. and represents the weight coefficient, and Both are greater than 0.

[0087] The ultrasonic treatment time parameter adjustment instruction includes a first time adjustment instruction, a second time adjustment instruction and an instruction to stop ultrasonic treatment, wherein the first time adjustment instruction and the second time adjustment instruction are both to shorten the corresponding treatment time, wherein the time of shortening the treatment by the first time adjustment instruction and the second time adjustment instruction increases successively.

[0088] The method for generating an ultrasound treatment time parameter adjustment instruction based on a skin condition coefficient includes:

[0089] Preset skin condition data gradient thresholds P1, P2 and P3, where P1 < P2 < P3;

[0090] When Pzt<P1, no parameter adjustment instruction is generated.

[0091] When P1≤Pzt<P2, a first time adjustment instruction is generated.

[0092] When P2≤Pzt<P3, a second time adjustment instruction is generated.

[0093] When Pzt>P3, an instruction to stop ultrasonic treatment is generated.

[0094] Specifically, based on the above embodiments, this embodiment adds a parameter adjustment module, that is, by acquiring skin status data once every preset time, generating a skin status coefficient based on the skin status data, that is, judging the impact of the use of the ultrasonic therapeutic device on the skin status, and then reasonably adjusting the treatment time of the ultrasonic therapeutic device based on the degree of impact, to achieve dynamic optimization of the ultrasonic treatment parameters, greatly improving the effect and safety of the ultrasonic therapeutic device, and overcoming the existing technology that generally sets the ultrasonic treatment parameters and continues to treat the user until the set parameters are ended or the user feels uncomfortable and sends a request to end, resulting in damage to the user's skin.

[0095] Example 3

[0096] The invention discloses an intelligent multi-parameter optimized ultrasonic therapeutic instrument, including an optimization control system of the intelligent multi-parameter optimized ultrasonic therapeutic instrument.

[0097] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above-described embodiments. The above-described embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. Intelligent multi-parameter optimization control system for ultrasonic therapeutic instrument, characterized by: include: The data collection module collects historical ultrasound treatment parameter data of the ultrasound treatment device. The historical ultrasound treatment parameter data is collected when the treatment effect meets the standard. The historical ultrasound treatment parameter data includes comprehensive skin parameters, age and gender, and ultrasound treatment parameter sets; The comprehensive skin parameters include skin moisture data, skin thickness data, skin oil content data, and skin elasticity data; The ultrasonic treatment parameter set includes ultrasonic frequency, ultrasonic intensity and treatment time; The model training module trains an ultrasound therapy parameter recommendation model based on historical ultrasound therapy parameter data, collects real-time comprehensive skin parameters, age, and gender, and obtains ultrasound therapy parameter recommendation set labels based on the trained ultrasound therapy parameter recommendation model, and then obtains the ultrasound therapy parameter recommendation set corresponding to the ultrasound therapy parameter recommendation set labels; a control module for controlling the ultrasonic frequency, ultrasonic intensity, and treatment time of the ultrasonic waves emitted by the ultrasonic therapeutic apparatus based on the acquired ultrasonic treatment parameters; Parameter adjustment module, every preset time T j Acquire skin condition data once, generate a skin condition coefficient based on the skin condition data, generate an ultrasonic treatment time parameter adjustment instruction based on the skin condition coefficient, transmit the parameter adjustment instruction to the control module, and the control module controls the ultrasonic treatment device to adjust the ultrasonic treatment time parameter; The skin condition data includes skin temperature data, skin humidity data and skin glossiness data; The skin temperature data collection method comprises: Obtain the skin area to be treated by the ultrasound therapeutic device and mark it as the area to be tested, aim the thermal imager at the area to be tested, and obtain a thermal imaging image; The acquired thermal imaging image is divided into i sub-regions of equal size, each sub-region consists of m pixels; Extract the temperature values ​​of m pixels in each sub-region and calculate the sub-region temperature. There is a one-to-one correspondence between pixels and temperature values. The temperature data of the pixels can be automatically obtained through the thermal imager software. The temperature values ​​of the i sub-areas are obtained to establish a set, and the maximum temperature value in the set is obtained as the skin temperature data.

2. The optimization control system of the intelligent multi-parameter optimization ultrasonic therapeutic instrument according to claim 1 is characterized in that: The recommended set of ultrasound therapy parameters is: {(P1、Q1、T1),(P2、Q2、T2),……,(P n 、Q n 、T n )}; Among them, P n is the ultrasonic frequency corresponding to the set label n, Q n is the ultrasonic intensity corresponding to the set label n, T n is the treatment time corresponding to the set label n, and n is the serial number of the recommended set label of ultrasound treatment parameters.

3. The optimization control system of the intelligent multi-parameter optimization ultrasonic therapeutic instrument according to claim 1 is characterized in that: The training method of the ultrasound therapy parameter recommendation model includes: Pre-set corresponding numbers for ultrasonic treatment parameter sets; Converting the skin comprehensive parameters, age, and gender into a corresponding set of feature vectors, using each set of feature vectors as input to the ultrasound therapy parameter recommendation model, the ultrasound therapy parameter recommendation model using a set of ultrasound therapy parameter set numbers corresponding to each set of skin comprehensive parameters, age, and gender as output, using a set of ultrasound therapy parameter set numbers actually corresponding to each set of skin comprehensive parameters, age, and gender as prediction targets, and minimizing the loss function value of the ultrasound therapy parameter recommendation model as a training target; stopping training when the loss function value of the ultrasound therapy parameter recommendation model is less than or equal to a preset target loss value; The ultrasound therapy parameter recommendation model is one of a support vector machine regression model, a random forest regression model or a neural network regression model.

4. The optimization control system of the intelligent multi-parameter optimization ultrasonic therapeutic instrument according to claim 1 is characterized in that: The skin moisture data is obtained by measuring with a skin moisture tester, and the skin gloss data is obtained by measuring with a skin gloss meter.

5. The optimization control system of the intelligent multi-parameter optimization ultrasonic therapeutic instrument according to claim 4 is characterized in that: The method of generating the skin condition coefficient based on the skin condition data is as follows: Where, Pzt represents the skin condition coefficient, Pw represents the skin temperature data, Ps represents the skin humidity data, and Pg represents the skin gloss data. and represents the weight coefficient, and Both are greater than 0.

6. The optimization control system of the intelligent multi-parameter optimization ultrasonic therapeutic instrument according to claim 5 is characterized in that: The ultrasonic treatment time parameter adjustment instruction includes a first time adjustment instruction, a second time adjustment instruction and an instruction to stop ultrasonic treatment, wherein the first time adjustment instruction and the second time adjustment instruction both shorten the corresponding treatment time, and the time shortened by the first time adjustment instruction and the second time adjustment instruction increases successively.

7. The optimization control system of the intelligent multi-parameter optimization ultrasonic therapeutic instrument according to claim 6 is characterized in that: The method for generating an ultrasound treatment time parameter adjustment instruction based on a skin condition coefficient includes: Preset skin condition data gradient thresholds P1, P2 and P 3， Where P1<P2<P 3； When Pzt<P1, no parameter adjustment instruction is generated; When P1≤Pzt<P2, a first time adjustment instruction is generated; When P2≤Pzt<P3, a second time adjustment instruction is generated; When Pzt>P3, an instruction to stop ultrasonic treatment is generated.

8. The optimization control system of the intelligent multi-parameter optimization ultrasonic therapeutic instrument according to claim 1 is characterized in that: The method of extracting the temperature values ​​of m pixels in each sub-region and calculating the temperature of the sub-region includes: Where, Ta i represents the temperature value of the ith sub-region, m represents the total number of pixels in the ith sub-region, Ti e Represents the temperature value of the e-th pixel in the i-th sub-region, e≤m.

9. Intelligent multi-parameter optimized ultrasonic therapeutic device, characterized by: The ultrasonic therapeutic apparatus includes an optimization control system of the intelligent multi-parameter optimization ultrasonic therapeutic apparatus as described in any one of claims 1-8.

Images