KR102474888B1 - Method for generating skin care signal and skin care apparatus - Google Patents

Abstract

A skin beauty signal generation method performed in a skin beauty device according to the present invention includes applying a sweep signal by contacting the skin beauty device to a specific skin area of a user; sensing a vibration signal generated in response to the application of the sweep signal; obtaining a resonant frequency by performing a Fast Fourier Transform (FFT) on the sensed vibration signal; inferring a peak frequency corresponding to a vibration signal passing through the specific skin region when the sweep signal is applied using the resonant frequency; and generating a signal corresponding to the peak frequency as the skin beauty signal. According to an embodiment of the present invention, there is an advantage in that the absorption rate of cosmetics or medicines can be increased by using vibration having an optimal beauty effect for each person and skin part.

Description

Method for generating skin care signal and skin care apparatus {Method for generating skin care signal and skin care apparatus}

The present invention relates to a method for generating a beauty signal for the tail and a skin beauty device, and more particularly, to a method for generating a beauty signal for the tail and a skin beauty device for maximizing the absorption of cosmetics or medicines for each user or body part of the user.

Under the stratum corneum of the epidermis of human facial skin, a protective wall is formed with a thick protein protective layer to protect the skin. Since the epidermis and dermis layers of the skin are separated by the protein protective layer, when various nutrients, physiologically active substances, and therapeutic agents are applied to the skin, the substances applied to the skin cannot penetrate deep into the dermis layer, and wastes accumulated in the dermis layer cannot be removed. . Due to this, the effect of skin care and treatment is insufficient.

Nutrients, physiologically active substances, and therapeutic substances applied to the skin are using cosmetic devices that generate vibrations to enhance the effect of skin care and treatment. For example, in the case of using a beauty device that generates vibration, the user applies nutrients to the skin of the face and then massages while vibrating with the beauty device to the skin to which the nutrients are applied, so that the nutrients penetrate deeply into the skin. enhance the effect.

However, since the thickness and density of the skin are different for each person, and the thickness and density are different for each part of the skin even for the same person, if the frequency of vibration generated by the beauty device is the same, the effect may be good or insignificant for each person and for each skin part. this happens

Korea Patent Registration No. 10-1257013 (2013.04.16) Korea Utility Model Registration No. 20-0474471 (2014.09.12) Korean Patent Publication No. 10-2017-0097201 (2017.08.25) Korean Patent Publication No. 10-2019-0141323 (2019.12.24) Korean Patent Publication No. 10-2019-0100258 (2019.08.28)

The present invention has been made to solve the above problems, and the present invention is to provide a skin beauty signal generation method and skin beauty device that maximize absorption of cosmetics or medicines for each user or for each user's body part.

Other objects of the present invention will become clearer through preferred embodiments described below.

According to one aspect of the present invention, a method for generating a skin beauty signal performed by a skin beauty device includes applying a sweep signal by contacting the skin beauty device to a specific skin region of a user; sensing a vibration signal generated in response to the application of the sweep signal; obtaining a resonant frequency by performing a Fast Fourier Transform (FFT) on the sensed vibration signal; inferring a peak frequency corresponding to a vibration signal passing through the specific skin region when the sweep signal is applied using the resonant frequency; and generating a signal corresponding to the peak frequency as the skin beauty signal.

Here, the inferred peak frequency is the resonance frequency obtained by applying a sweep signal by contacting the skin care device to any skin, and fast Fourier transforming the vibration signal generated in response to the application of the sweep signal as input data. And, applying the sweep signal to the arbitrary skin, constructing a plurality of learning data sets having peak frequencies obtained by fast Fourier transforming the vibration signal passing through the arbitrary skin as output data, and the plurality of learning In the AI model created by learning with a data set, it may be output data obtained by using the resonant frequency of the specific skin region as input data.

Here, the peak frequency obtained for the arbitrary skin may be a frequency at which a slope value becomes 0 in a waveform obtained by fast Fourier transform of a vibration signal passing through the arbitrary skin.

Here, the step of sensing the vibration signal generated corresponding to the application of the sweep signal may be performed while the skin care device is in contact with the specific skin area.

The skin beauty signal generation method described above, prior to contacting the skin beauty device to the specific skin region, presetting the amplitude of the sweep signal to be constant in a state where the user holds the skin beauty device It may further include steps to do.

Here, when the inferred peak frequency is one, the signal corresponding to the peak frequency may be a sinusoidal wave signal.

Here, when the inferred peak frequency is plural, the signal corresponding to the peak frequency may be a non-sinusoidal wave obtained by combining a plurality of sinusoidal signals corresponding to each of the plurality of peak frequencies.

Here, the amplitudes of the plurality of peak frequencies may be normalized based on a peak frequency having a maximum amplitude among the plurality of peak frequencies.

According to another aspect of the present invention, a skin care device includes a vibration generator for generating a sweep signal to be applied to a specific skin region of a user; a vibration sensor unit for sensing a vibration signal generated corresponding to a sweep signal applied by contacting the skin care device to the specific skin area; a frequency calculation unit obtaining a resonant frequency by fast Fourier transforming the sensed vibration signal; a frequency inference unit inferring a peak frequency corresponding to a vibration signal passing through the specific skin region when the sweep signal is applied using the resonant frequency; and a beauty signal generator for generating a signal corresponding to the peak frequency as the skin beauty signal.

Here, the inferred peak frequency is the resonance frequency obtained by applying a sweep signal by contacting the skin care device to any skin, and fast Fourier transforming the vibration signal generated in response to the application of the sweep signal as input data. And, applying the sweep signal to the arbitrary skin, constructing a plurality of learning data sets having peak frequencies obtained by fast Fourier transforming the vibration signal passing through the arbitrary skin as output data, and the plurality of learning In the AI model created by learning with a data set, it may be output data obtained by using the resonant frequency of the specific skin region as input data.

Here, the peak frequency obtained for the arbitrary skin may be a frequency at which a slope value becomes 0 in a waveform obtained by fast Fourier transform of a vibration signal passing through the arbitrary skin.

Here, the sensing of the vibration signal generated corresponding to the applied sweep signal may be performed while the skin care device is in contact with the specific skin area.

Before contacting the skin care device to the specific skin area, the skin care device presets a sweep signal so that the amplitude of the sweep signal is constant in a state where the user holds the skin care device. Wealth may be further included.

Here, when the inferred peak frequency is one, the signal corresponding to the peak frequency may be a sinusoidal wave signal.

Here, when the inferred peak frequency is plural, the signal corresponding to the peak frequency may be a non-sinusoidal wave obtained by combining a plurality of sinusoidal signals corresponding to each of the plurality of peak frequencies.

Here, the amplitudes of the plurality of peak frequencies may be normalized based on a peak frequency having a maximum amplitude among the plurality of peak frequencies.

According to another aspect of the present invention, in a recording medium recording a computer program related to a skin beauty signal generation method performed in a skin beauty device, a sweep signal is generated by contacting the skin beauty device to a specific skin area of a user Applying; sensing a vibration signal generated in response to the application of the sweep signal; obtaining a resonant frequency by performing a Fast Fourier Transform (FFT) on the sensed vibration signal; inferring a peak frequency corresponding to a vibration signal passing through the specific skin region when the sweep signal is applied using the resonant frequency; And a recording medium recording a computer program related to a skin beauty signal generation method comprising generating a signal corresponding to the peak frequency as the skin beauty signal may be provided.

According to an embodiment of the present invention, there is an advantage in that the absorption rate of cosmetics or medicines can be increased by using vibration having an optimal beauty effect for each person and skin part.

1 is a flowchart illustrating a method for generating a skin beauty signal according to an embodiment of the present invention.
2 is a diagram showing a sweep signal whose amplitude is constant according to an embodiment of the present invention.
3 is a view showing a process of obtaining a resonant frequency by applying a sweep signal to the skin according to an embodiment of the present invention.
FIG. 4 is a view showing resonant frequencies obtained for each skin part through the process shown in FIG. 3;
5 is a view showing a process of obtaining a peak frequency passing through the skin by applying a sweep signal to the skin according to an embodiment of the present invention.
6 is a diagram showing a process of learning an AI model using a built learning data set according to an embodiment of the present invention.
7 is a diagram showing a peak frequency corresponding to a resonance frequency for each skin part inferred by an AI model according to an embodiment of the present invention.
7 is a diagram showing peak frequencies obtained for each skin part through the process shown in FIG. 5 of the present invention.
8 is a diagram illustrating a method of generating a non-sinusoidal beauty signal by combining a plurality of peak frequencies according to an embodiment of the present invention.
9 is a block diagram showing the configuration of a skin care device according to an embodiment of the present invention.

Advantages and features of the present invention, and methods for achieving them, will become clear with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and will be implemented in various different forms. In this specification, this embodiment is provided to complete the disclosure of the present invention, and to completely inform those skilled in the art of the scope of the invention to which the present invention belongs. And the invention is only defined by the scope of the claims. Thus, in some embodiments, well-known components, well-known operations and well-known techniques have not been described in detail in order to avoid obscuring the interpretation of the present invention.

In addition, like reference numerals designate like elements throughout the specification, and terms used (referred to) in this specification are for describing embodiments and are not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated in the phrase, and components and operations referred to as 'comprising (or including)' do not exclude the presence or addition of one or more other components and operations. . Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used in a meaning commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless they are defined.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

1 is a flowchart showing a method for generating a skin beauty signal according to an embodiment of the present invention, and FIG. 2 is a diagram showing a sweep signal having a constant amplitude according to an embodiment of the present invention. 3 is a diagram showing a process of obtaining a resonant frequency by applying a sweep signal to the skin according to an embodiment of the present invention, and FIG. 4 is a diagram showing a resonant frequency obtained for each skin part through the process shown in FIG. 3. , FIG. 5 is a diagram showing a process of obtaining a peak frequency passing through the skin by applying a sweep signal to the skin according to an embodiment of the present invention, and FIG. 6 is a learning data set constructed according to an embodiment of the present invention 7 is a diagram showing a process of learning an AI model using , and FIG. 7 is a diagram showing a peak frequency corresponding to a resonance frequency for each skin part inferred by an AI model according to an embodiment of the present invention. FIG. 8 is a diagram showing the peak frequency of the present invention. It is a diagram showing a method of generating a non-sinusoidal beauty signal by combining a plurality of peak frequencies according to an embodiment of.

As shown in FIG. 1, in step S10, the skin care device 100 presets the amplitude of a sweep signal (or chirp signal) generated while the user is holding the skin care device to be constant. perform the steps That is, the sweep signal generated while the user is holding the skin care device 100 has a waveform having a constant amplitude as shown in FIG. 2 . The reason for performing the presetting step is that the amplitude of the sweep signal required to perform step S20 is constant, and even if the amplitude of the sweep signal generated by the skin care device 100 is constant in a non-held state, the skin care device 100 ) is gripped, some of the generated vibration is attenuated due to gripping and the amplitude is distorted. Here, the sweep signal generated by the skin care device 100 has a predetermined frequency range (eg, 0 to 8 kHz) and a predetermined time range (eg, 3000 msec).

In step S20, a step of applying a sweep signal in a state in which the skin care device 100 is in contact with a specific skin area of the user is performed. In this case, the user's specific skin area is the forehead, cheek, temple, chin, and the like.

In step S30, the skin care device 100 senses the vibration signal generated according to the application of the sweep signal. At this time, the sensing of the vibration signal is performed in a state in which the skin care device 100 is in contact with the specific skin area. That is, as shown at reference numeral 310 in FIG. 3 , the application of the sweep signal and the sensing of the vibration signal are performed while the head of the skin care device 100 is in contact with the skin. A vibration signal sensed while in contact with the skin may have a form as shown in reference number 320 . That is, the applied vibration signal is a sweep signal having a constant amplitude, and the sensed vibration signal is a signal (eg, 320) whose amplitude is distorted due to some vibration attenuation according to skin contact. Sensing of the vibration signal may be performed simultaneously with or sequentially with the application of the sweep signal or with a minute time difference.

In step S40, the skin care device 100 performs a Fast Fourier Transform (FFT) on the sensed vibration signal (eg, 320) to generate a waveform representing an amplitude value (y-axis) according to a frequency (x-axis). Obtain and analyze it to obtain the resonant frequency. At this time, the resonant frequency is a value at which the slope becomes 0 in the above waveform, and may be one or more (see 330). Here, since the fast Fourier transform used is related to well-known engineering (or mathematical) definitions and algorithms, a detailed description thereof will be omitted.

In step S50, the skin care device 100 infers a peak frequency corresponding to the vibration signal sensed on the opposite side of the skin through the specific skin region when applying the sweep signal to the specific skin region using the resonant frequency. If the processing capability of the skin care device 100 is low, the inference process may be performed in another electronic device (eg, computer, server, etc.) connected to the skin care device 100 by wire or wirelessly. For example, referring to FIG. 5 , a sweep signal is applied to one side of the skin (see 510), and vibration is sensed on the other side of the skin (see 520). At this time, the vibration signal to be sensed may have a form such as reference number 530. Thereafter, the sensed vibration signal (eg, 530) is subjected to Fast Fourier Transform (FFT) to obtain a waveform representing the amplitude value (y-axis) according to the frequency (x-axis), and by analyzing this, the peak frequency is determined. Acquire Here, the peak frequency is a value at which the slope becomes 0 in the above waveform, and may be one or more.

However, since it is impossible to sense a vibration signal by inserting a vibration sensing device into human skin, the peak frequency according to the present invention is obtained through inference using an AI model. Hereinafter, a method for constructing a training data set for generating an AI model and inferring a peak frequency will be described.

The AI model training data set consists of input data and output data. The input data is a set of resonant frequencies obtained by applying a sweep signal to an arbitrary skin surface and fast Fourier transforming a vibration signal generated according to the application of the sweep signal. At this time, the arbitrary skin does not mean the skin of a living person, but skin tissue (eg, pig skin, artificial skin) close to the characteristics of each part of human skin (eg, forehead, cheeks, chin, temple, etc.). say At this time, in order to increase the accuracy of the peak frequency inference of the AI model, it is preferable that the resonant frequency is obtained for skins having various thicknesses and densities. The output data is a set of peak frequencies obtained by applying a sweep signal to an arbitrary skin and fast Fourier transforming the vibration signal passing through the arbitrary skin. Referring to FIG. 5, a sweep signal is applied to one side of the skin (see 510), and vibration is sensed on the other side of the skin (see 520). At this time, the vibration signal to be sensed may have a form such as reference number 530. Thereafter, the sensed vibration signal (eg, 530) is subjected to Fast Fourier Transform (FFT) to obtain a waveform representing the amplitude value (y-axis) according to the frequency (x-axis), and by analyzing this, the peak frequency is determined. Acquire Here, the peak frequency is a value at which the slope becomes 0 in the above waveform, and may be one or more. As described above, a one-to-one correspondence is established between the resonance frequency and the peak frequency obtained for any skin, and the resonance frequency and the peak frequency become input data and output data for AI model learning, respectively. At this time, in order to increase the inference accuracy of the AI model, it is desirable to build a learning data set of resonance frequencies and peak frequencies for skin having as many characteristics as possible (thickness, density, etc.). 6 shows a process of learning an AI model using a built learning data set. For AI modeling, various algorithms such as neural networks, multiple regression, and linear algebra can be applied.

When the resonance frequency of the specific skin region obtained in step S40 is set as input data to the AI model, the AI model infers the peak frequency as output data according to the learning result. Referring to FIG. 7 , when the skin care device 100 acquires a resonant frequency by contacting the forehead, the AI model infers a peak frequency corresponding to the resonant frequency. In this case, the peak frequency is one or more frequencies that are expected to best pass through the skin of the forehead. In the case of using such an AI model, it is possible to solve a problem in which it is impossible to sense a vibration signal by inserting a vibration sensing device into human skin.

In step S60, the skin care device 100 determines whether the number of peak frequencies is plural, and if there are plural peak frequencies, normalizes the peak frequencies based on the peak frequency having the largest amplitude among the plural peak frequencies. For example, when the number of peak frequencies inferred in step S50 is 4, it can be expressed as shown in Table 1. At this time, the normalized values of the values shown in <Table 1> can be shown as in <Table 2>. Here, the decibel (dB) for normalization is in the range of 0.5 to 1.0.

Hz 546 1031 1546 2062 dB 29 30 28 31

Hz 546 1031 1546 2062 Ratio 0.66 0.83 0.5 One

In step S80, the skin care device 100 generates a non-sinusoidal wave obtained by combining a plurality of sinusoidal signals corresponding to each of a plurality of peak frequencies as a skin beauty signal. This process is well shown in FIG. 8 . 8 shows a final vibration waveform to be used when massaging the face, which is measured by combining sinusoidal waves corresponding to four peak frequencies, for example. 8(a) to 8(d) show signals of 546Hz, 1031Hz, 1546Hz, and 2062Hz having different peak frequencies, and FIG. 8(e) shows a non-sinusoidal wave signal combining them.

In step S60, the skin care device 100 determines whether the number of peak frequencies is plural, and if there is one peak frequency, it generates a sine wave signal corresponding to the corresponding peak frequency as a beauty signal (S80).

9 is a block diagram showing the configuration of a skin care device according to an embodiment of the present invention.

As shown in FIG. 9, the skin care device 100 according to the present invention includes a sweep signal setting unit 110, a vibration generating unit 120, a vibration sensing unit 130, a frequency calculating unit 140, and a frequency inference unit. (150), and a cosmetic signal generator (160). Hereinafter, in describing FIG. 9 , content that can be applied in the same manner as the content previously described through FIGS. 1 to 8 will be omitted or briefly described.

The sweep signal setting unit 110 serves to preset the amplitude of a sweep signal (or chirp signal) generated while the user is holding the skin care device to be constant. That is, the sweep signal generated while the user is holding the skin care device 100 has a waveform having a constant amplitude as shown in FIG. 2 .

The vibration generating unit 120 and the vibration sensing unit 130 may be configured together in the head part of the skin care device 100 . The vibration generating unit 120 and the vibration sensing unit 130 may be configured in various forms in the head unit, preferably integrated into one device, or may be integrally formed. Here, if "integration" means separable, integration can be seen to mean that it is difficult to separate, such as being configured together in a semiconductor device. The vibration generator 120 may include a vibrator that generates vibration. The vibrator may be a vibrating speaker, but a small motor may also be used. The vibration generating unit 120 performs a function of generating a sweep signal to be applied to a specific skin area of the user. The vibration generating unit 120 may generate vibration such that the amplitude of the sweep signal generated when the user holds the skin care device 100 is constant according to the setting value of the sweep signal setting unit 110 . In addition, the vibration generator 120 may generate vibration corresponding to the beauty signal generated by the beauty signal generator 160 . The vibration sensing unit 130 performs a function of sensing a vibration signal generated corresponding to a sweep signal applied by contacting the skin care device 100 to a specific skin area. The vibration sensing unit 130 may be a piezo sensor.

The frequency calculator 140 performs a Fast Fourier Transform (FFT) on the sensed vibration signal (eg, 320) to obtain a waveform representing an amplitude value (y-axis) according to a frequency (x-axis), and interprets it. to obtain the resonant frequency. At this time, the resonant frequency is a value at which the slope becomes 0 in the above waveform, and may be one or more (see 330).

When the sweep signal is applied to a specific skin region using the resonant frequency, the frequency inference unit 150 infers a peak frequency corresponding to a vibration signal that passes through the specific skin region and is sensed on the opposite side of the skin. The frequency inference unit 150 may be an AI model for peak frequency inference. At this time, the AI model infers the peak frequency as output data according to the learning result when the acquired resonant frequency of the specific skin region is set as input data.

The beauty signal generation unit 160 performs a function of generating a signal corresponding to the peak frequency as a skin beauty signal. The beauty signal generation unit 160 determines whether the number of peak frequencies is plural, and if there are plural peak frequencies, normalizes the peak frequencies based on the peak frequency having the largest amplitude among the plurality of peak frequencies. Thereafter, the beauty signal generator 160 generates a non-sinusoidal wave obtained by combining a plurality of sinusoidal signals corresponding to each of a plurality of peak frequencies as a skin beauty signal. When the number of peak frequencies is one, the beauty signal generation unit 160 generates a sinusoidal wave signal corresponding to the corresponding peak frequency as a beauty signal.

In addition to the above, the skin care device 100 of FIG. 9 can perform various operations, and since other details have been sufficiently described above with reference to FIGS. 1 to 8, the contents are replaced with those.

On the other hand, even if all the components constituting the embodiment of the present invention are described as being combined or operated as one, the present invention is not necessarily limited to these embodiments. That is, within the scope of the object of the present invention, all of the components may be selectively combined with one or more to operate. In addition, although all of the components may be implemented as a single independent piece of hardware, some or all of the components are selectively combined to perform some or all of the combined functions in one or a plurality of pieces of hardware. It may be implemented as a computer program having. Codes and code segments constituting the computer program may be easily inferred by a person skilled in the art. Such a computer program may implement an embodiment of the present invention by being stored in a computer-readable non-transitory computer readable media, read and executed by a computer.

Here, the non-transitory readable recording medium means a medium that stores data semi-permanently and can be read by a device, not a medium that stores data for a short moment, such as a register, cache, or memory. . Specifically, the above-described programs may be provided by being stored in a non-transitory readable recording medium such as a CD, DVD, hard disk, Blu-ray disk, USB, memory card, or ROM.

Although the preferred embodiments of the present invention have been shown and described above, the present invention is not limited to the specific embodiments described above, and is common in the art to which the present invention pertains without departing from the gist of the present invention claimed in the claims. Of course, various modifications and implementations are possible by those with knowledge of, and these modifications should not be individually understood from the technical spirit or perspective of the present invention.

100: skin care device
110: sweep signal setting unit
120: vibration generating unit
130: vibration sensing unit
140: frequency calculation unit
150: frequency inference unit
160: beauty signal generator

Claims (17)

In the skin beauty signal generation method performed in a skin beauty device including a vibration generator, a vibration sensor unit, a frequency calculator, a frequency inference unit, and a beauty signal generator,
Applying a sweep signal by the vibration generating unit in contact with the skin care device to a specific skin area of the user;
sensing, by the vibration sensor unit, a vibration signal generated in response to the application of the sweep signal;
acquiring a resonant frequency by the frequency operator performing a Fast Fourier Transform (FFT) on the sensed vibration signal;
inferring, by the frequency inference unit, a peak frequency corresponding to a vibration signal passing through the specific skin area when the sweep signal is applied using the resonant frequency; and
Generating, by the beauty signal generation unit, a signal corresponding to the peak frequency as the skin beauty signal,
The inferred peak frequency is,
Applying a sweep signal by contacting the skin care device to any skin, and using the resonance frequency obtained by fast Fourier transforming the vibration signal generated in response to the application of the sweep signal as input data,
Constructing a plurality of training data sets having peak frequencies obtained by applying the sweep signal to the arbitrary skin and fast Fourier transforming the vibration signal passing through the arbitrary skin as output data;
In the AI model created by learning with the plurality of built-in training data sets,
Skin beauty signal generation method, characterized in that the output data obtained by using the resonant frequency of the specific skin area as input data. delete According to claim 1,
The peak frequency obtained for the arbitrary skin is,
Skin beauty signal generation method, characterized in that the frequency at which the slope value is 0 in the waveform obtained by fast Fourier transform of the vibration signal passing through the arbitrary skin. According to claim 1,
Sensing the vibration signal generated in response to the application of the sweep signal,
Skin beauty signal generation method, characterized in that carried out in a state in which the skin care device is in contact with the specific skin area. According to claim 1,
Prior to contacting the skin care device to the specific skin area, presetting the amplitude of the sweep signal to be constant in a state in which the user holds the skin care device A method for generating a beauty signal to do. According to claim 1,
If the inferred peak frequency is one,
The signal corresponding to the peak frequency is a cosmetic signal generation method, characterized in that the sinusoidal wave signal. According to claim 1,
If the inferred peak frequency is plural,
The cosmetic signal generation method, characterized in that the signal corresponding to the peak frequency is a non-sinusoidal wave obtained by combining a plurality of sinusoidal signals corresponding to each of the plurality of peak frequencies. According to claim 1,
If there are a plurality of peak frequencies, the amplitudes of the plurality of peak frequencies are normalized based on a peak frequency having a maximum amplitude among the plurality of peak frequencies. In skin care devices,
a vibration generating unit that generates a sweep signal to be applied to a specific skin area of a user;
a vibration sensor unit for sensing a vibration signal generated corresponding to a sweep signal applied by contacting the skin care device to the specific skin area;
a frequency calculation unit obtaining a resonant frequency by fast Fourier transforming the sensed vibration signal;
a frequency inference unit inferring a peak frequency corresponding to a vibration signal passing through the specific skin region when the sweep signal is applied using the resonant frequency; and
Including a beauty signal generator for generating a signal corresponding to the peak frequency as a skin beauty signal,
The inferred peak frequency is,
Applying a sweep signal by contacting the skin care device to any skin, and using the resonance frequency obtained by fast Fourier transforming the vibration signal generated in response to the application of the sweep signal as input data,
Constructing a plurality of training data sets having peak frequencies obtained by applying the sweep signal to the arbitrary skin and fast Fourier transforming the vibration signal passing through the arbitrary skin as output data;
In the AI model created by learning with the plurality of built-in training data sets,
Skin care device, characterized in that the output data obtained by using the resonant frequency of the specific skin area as input data. delete According to claim 9,
The peak frequency obtained for the arbitrary skin is,
Skin beauty device, characterized in that the frequency at which the slope value is 0 in the waveform obtained by fast Fourier transform of the vibration signal passing through the arbitrary skin According to claim 9,
Sensing of the vibration signal generated corresponding to the applied sweep signal,
Skin beauty device, characterized in that carried out in a state in which the skin beauty device is in contact with the specific skin area According to claim 9,
Before contacting the skin care device to the specific skin area, the skin further comprising a sweep signal setting unit for presetting the amplitude of the sweep signal to be constant in a state in which the user holds the skin care device beauty device. According to claim 9,
If the inferred peak frequency is one,
The skin care device, characterized in that the signal corresponding to the peak frequency is a sinusoidal wave signal. According to claim 9,
If the inferred peak frequency is plural,
The skin care device, characterized in that the signal corresponding to the peak frequency is a non-sinusoidal wave obtained by combining a plurality of sinusoidal wave signals corresponding to each of the plurality of peak frequencies. According to claim 9,
If there are a plurality of peak frequencies, the amplitudes of the plurality of peak frequencies are normalized based on a peak frequency having a maximum amplitude among the plurality of peak frequencies. In a recording medium recording a computer program related to a skin beauty signal generation method performed in a skin beauty device including a vibration generator, a vibration sensor unit, a frequency calculator, a frequency inference unit, and a beauty signal generator,
Applying a sweep signal by the vibration generating unit in contact with the skin care device to a specific skin area of the user;
sensing, by the vibration sensor unit, a vibration signal generated in response to the application of the sweep signal;
acquiring a resonant frequency by the frequency operator performing a Fast Fourier Transform (FFT) on the sensed vibration signal;
inferring, by the frequency inference unit, a peak frequency corresponding to a vibration signal passing through the specific skin area when the sweep signal is applied using the resonant frequency; and
Generating, by the beauty signal generation unit, a signal corresponding to the peak frequency as the skin beauty signal,
The inferred peak frequency is,
A sweep signal is applied by contacting the skin care device to any skin, and a resonance frequency obtained by fast Fourier transform of a vibration signal generated in response to the sweep signal application is used as input data,
Constructing a plurality of learning data sets having peak frequencies obtained by applying the sweep signal to the arbitrary skin and fast Fourier transforming the vibration signal passing through the arbitrary skin as output data;
In the AI model created by learning with the plurality of built-in training data sets,
A recording medium recording a computer program related to a skin beauty signal generation method, characterized in that the output data obtained by using the resonant frequency of the specific skin region as input data.

Images