KR20230040912A - Apparent age prediction device - Google Patents

Abstract

The present disclosure is to provide a cognitive age predicting device which calculates a cognitive age indicating a degree of aging. The cognitive age predicting device includes: a memory for acquiring the assessed cognitive age and subject data and storing a cognitive age prediction model generated based on the assessed cognitive age and subject data; an input unit for receiving information of a measurement subject including facial images, skin measurement values, genetic information, environmental information, or lifestyle information; and a cognitive age prediction calculation unit for acquiring the predicted cognitive age of the measurement subject by applying the information of the measurement subject to the cognitive age prediction model.

Description

Cognitive age prediction device {Apparent age prediction device}

The present disclosure relates to a device for predicting cognitive age.

As people become more interested in appearance, skin care, etc., devices for calculating skin age by measuring skin conditions have appeared. However, since this skin age is limited only to the skin itself, even if the skin age is calculated high, it is somewhat difficult to know that the skin is in a poor state unless the skin is observed closely, so that the calculated skin age is not trusted, or efforts for subsequent management are made. There is a limit that cannot be reached.

Accordingly, there is a demand for a new guide that is highly reliable and can arouse awareness in relation to people's appearance or skin.

An object of the present disclosure is to provide an apparatus for predicting a perceived age that calculates a perceived age representing a degree of aging.

A cognitive age prediction system according to an embodiment of the present disclosure includes a data providing server that obtains an evaluated cognitive age and subject data, a server that obtains a cognitive age prediction model based on the evaluated cognitive age and subject data received from the data providing server, and The mobile terminal receives the cognitive age prediction model from the server, and obtains the predicted cognitive age by applying the information of the measurement subject including face image, skin measurement value, genetic information, environment information, or lifestyle information to the cognitive age prediction model. can

The mobile terminal may receive the information of the measurement target directly or receive it from the measurement target information storage server that stores the measurement target information.

A cognitive age prediction system according to an embodiment of the present disclosure includes a data providing server that obtains an evaluated cognitive age and subject data, a server that obtains a cognitive age prediction model based on the evaluated cognitive age and subject data received from the data providing server, and Includes a mobile terminal displaying the predicted cognitive age of the measurement target obtained based on the cognitive age prediction model, and the server includes a facial image, skin measurement value, genetic information, environmental information, or lifestyle information from the mobile terminal. It is possible to receive the information of the subject to be measured, apply the received information of the subject to be measured to a cognitive age prediction model to obtain a predicted cognitive age, and transmit the obtained predicted cognitive age to the mobile terminal.

The server may receive measurement target information directly input into the mobile terminal from the mobile terminal, or may receive measurement target information from a measurement target information storage server that stores the measurement target information according to a transmission command from the mobile terminal. .

The server may detect an outlier in the information of the subject to be measured.

The server may obtain an average value of the estimated cognitive age or predicted cognitive age of people of the same age as the measurement subject, and may obtain a residual between the predicted cognitive age and the average value of the measurement subject.

The mobile terminal may display a diagram showing predicted cognitive ages and average values.

The mobile terminal may display the predicted cognitive age and average value for each aging factor.

*The mobile terminal can display the predicted cognitive age and average value for each aging factor in a radial chart.

The server may create and store a table in which average values of estimated cognitive ages or predicted cognitive ages are mapped by age.

Aging factors may include at least one of wrinkles, melasma/skin color, sebum/porphyrin, genes, and environment/lifestyle.

The server or the mobile terminal may obtain a predicted cognitive age of the measurement subject by using a cognitive age prediction model, and obtain a predicted cognitive age through the predicted cognitive age value.

The server or the mobile terminal may obtain a predicted age value through a random forest or a linear regression model.

A cognitive age prediction system according to an embodiment of the present disclosure includes a data providing server that obtains an evaluated cognitive age and subject data, a server that obtains a cognitive age prediction model based on the evaluated cognitive age and subject data received from the data providing server, and Measurement target information that directly receives and stores the measurement target’s information including facial image, skin measurement, genetic information, environmental information, or lifestyle information, transmits the measurement target’s information to a server, or stores the measurement target’s information Includes a mobile terminal receiving a transmission from a storage server to store information of a subject to be measured, or providing a transmission command to transmit information of a subject to be measured from a server for storing subject information to a server, and the server stores the acquired cognitive age prediction model, or The predicted cognitive age of the measurement target obtained by applying the measurement target information transmitted from the mobile terminal or from the measurement target information storage server through the mobile terminal's transmission command to the cognitive age prediction model. Received and displayed from the server, or applied directly to the mobile terminal and stored measurement target information or measurement target information stored in the mobile terminal received through a transmission command from the measurement target information storage server and applied to the cognitive age prediction model transmitted from the server The obtained predicted cognitive age of the measurement subject may be displayed.

According to an embodiment of the present disclosure, by outputting the perceived age, there is an advantage in providing highly reliable evaluation results in relation to appearance or skin to users.

According to an embodiment of the present disclosure, since the average value of the perceived ages of people of the same age is provided together with the perceived age, there is an advantage in securing objectivity in calculating the perceived age regardless of the propensity of evaluators.

According to an embodiment of the present disclosure, since the predicted cognitive age and average value are output for each aging factor, it is possible to identify problems for each aging factor, and since prescriptions/products are recommended accordingly, there is an advantage of enabling intensive improvement for each problematic factor. .

1 is a control block diagram of an apparatus for predicting a perceived age according to an embodiment of the present disclosure.
FIG. 2 is a diagram illustrating an example of a regression tree constructed through a random forest model of wrinkle prediction age according to an embodiment of the present disclosure.
3 is a diagram illustrating an example of an evaluation result diagram output by the apparatus for predicting a cognitive age according to an embodiment of the present disclosure.
4 is a block diagram of a system for predicting a perceived age according to an embodiment of the present disclosure.
5 is a flowchart illustrating a method of operating a system for predicting a perceived age according to an embodiment of the present disclosure.

Hereinafter, the embodiments disclosed in this specification will be described in detail with reference to the accompanying drawings, but the same or similar elements are given the same reference numerals regardless of reference numerals, and redundant description thereof will be omitted. The suffix "part" for components used in the following description is given or used interchangeably in consideration of ease of writing the specification, and does not itself have a meaning or role distinct from each other. In addition, in describing the embodiments disclosed in this specification, if it is determined that a detailed description of a related known technology may obscure the gist of the embodiment disclosed in this specification, the detailed description thereof will be omitted. In addition, the accompanying drawings are only for easy understanding of the embodiments disclosed in this specification, the technical idea disclosed in this specification is not limited by the accompanying drawings, and all changes included in the spirit and technical scope of the present invention , it should be understood to include equivalents or substitutes.

Terms including ordinal numbers, such as first and second, may be used to describe various components, but the components are not limited by the terms. These terms are only used for the purpose of distinguishing one component from another.

Singular expressions include plural expressions unless the context clearly dictates otherwise.

In this application, terms such as "comprise" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

1 is a control block diagram of an apparatus for predicting a perceived age according to an embodiment of the present disclosure.

The cognitive age prediction device 1 includes an input unit 10, a cognitive age prediction calculation unit 20, a memory 30, an update unit 40, a predicted cognitive age analysis unit 50, and a cognitive age analysis result output unit 60. ) may include at least some or all of them.

The input unit 10 may receive information necessary for predicting a recognized age.

The input unit 10 may receive at least one of a face image, skin measurement values, genetic information, environment information, lifestyle information, and actual age. The input unit 10 necessarily receives a face image and may additionally receive one or more of genetic information, environment information, lifestyle information, and actual age.

The input unit 10 may include a face photographing device for receiving a face image. For example, the face photographing device may be a camera.

The input unit 10 may include a skin photographing device or a skin measuring device for receiving a skin measurement value. The input unit 10 may receive a skin measurement value from at least one of a skin photographing device and a skin measuring device.

The input unit 10 may receive genetic information from an external certification authority. Specifically, when each user receives individual information, the input unit 10 may receive genetic information of each user corresponding to the individual information from the authentication authority by transmitting the individual information to the authentication authority.

The input unit 10 may receive environmental information and lifestyle information through a questionnaire. Specifically, the input unit 10 may display at least one question related to environment information and lifestyle information, receive a user input for the displayed question, and acquire environment information and lifestyle information. The environmental information and lifestyle information may include height, weight, exposure to sunlight, use of UV blocker, eating habits, whether to smoke and whether to drink alcohol, but since this information is only exemplary, it is appropriate that it is not limited thereto.

The input unit 10 may receive a user input and receive an actual age.

On the other hand, in this specification, the actual age means the number of years the user has lived since he was born. That is, the actual age may mean the body age.

The perceived age may refer to an age recognized by the outside (others). The perceived age may be an apparent age.

The cognitive age prediction calculator 20 may estimate a cognitive age prediction value by using at least one cognitive age prediction model. For example, the cognitive age prediction calculation unit 20 may estimate a cognitive age prediction value using five cognitive age prediction models, but the number of cognitive age prediction models is only exemplary and is not limited thereto.

The cognitive age prediction calculation unit 20 may include a cognitive age prediction model management unit 21 and a predicted cognitive age derivation unit 23 .

The cognitive age prediction model management unit 21 may perform at least one of storing, using, or managing the cognitive age prediction model. The cognitive age prediction model management unit 21 applies at least one of the face image, skin measurement value, genetic information, environmental information, or lifestyle information received by the input unit 10 to the cognitive age prediction model, A cognitive age prediction value may be obtained.

), 기미/피부색에 따른 예측 인지 나이 수치(

), 피지/포피린에 따른 예측 인지 나이 수치(

), 유전자에 따른 예측 인지 나이 수치(

) 및/또는 환경/생활습관에 따른 예측 인지 나이 수치(

)를 포함할 수 있다.The cognitive age prediction value is the predicted cognitive age value according to wrinkles (

), predictive cognitive age values according to melasma/skin color (

), predicted cognitive age according to sebum/porphyrin (

), predictive cognitive age according to genes (

) and/or predicted cognitive age values according to environment/lifestyle (

) may be included.

)는 주름 예측 나이 선형 회귀 모델인

을 통해 산출될 수 있고,

은 아래와 같은 수학식을 통해 도출될 수 있다.Instead of the predicted perceived age value according to the wrinkles, the age derived by analyzing the input face image in any way may be used as the predicted perceived age value according to the wrinkles. Predicted cognitive age values according to wrinkles (

) is a wrinkle prediction age linear regression model

can be calculated through

can be derived through the following equation.

~

는 각각 이마, 눈 옆, 눈 밑, 눈 안쪽 위, 팔자, 입술 주위 등 부위별 주름을 추출한 수치이고,

~

는 선형 회귀 계수로 y 절편 및 가중치일 수 있다.In Equation 1 above,

~

is a value obtained by extracting wrinkles for each part, such as the forehead, side of the eyes, under the eyes, inside the eyes, nasolabial folds, and around the lips, respectively,

~

is a linear regression coefficient and may be a y-intercept and a weight.

은 랜덤 포레스트(random forest)로 구성 가능하나, 이는 예시적인 것에 불과하며, 다른 기계학습 방법이 적용될 수도 있다.According to one embodiment,

can be configured as a random forest, but this is only an example, and other machine learning methods may be applied.

A random forest may be composed of a plurality of regression trees, and an example of a regression tree is shown in FIG. 2 .

FIG. 2 is a diagram illustrating an example of a regression tree constructed through a random forest model of wrinkle prediction age according to an embodiment of the present disclosure.

~

에 의해 결정될 수 있다.As shown in FIG. 2, it is a value obtained by extracting wrinkles by region such as the forehead, the side of the eye, under the eye, the inside of the eye, the nasolabial fold, and around the lip, respectively.

~

can be determined by

)를 산출하기 위한 주름 예측 나이 선형 회귀 모델인

만을 설명하였으나, 이는 설명의 편의를 위한 예시에 불과하다.On the other hand, the predicted cognitive age according to wrinkles so far (

), which is a wrinkle predictive age linear regression model for calculating

Although only has been described, this is only an example for convenience of description.

)를 산출하기 위한 기미/피부색 예측 나이 선형 회귀 모델인

, 피지/포피린에 따른 예측 인지 나이 수치(

)를 산출하기 위한 피지/포피린 예측 나이 선형 회귀 모델인

, 유전자에 따른 예측 인지 나이 수치(

)를 산출하기 위한 유전자 예측 나이 선형 회귀 모델인

, 환경/생활습관에 따른 예측 인지 나이 수치(

)를 산출하기 위한 환경/생활습관 예측 나이 선형 회귀 모델인

또한

과 유사한 방식으로 산출될 수 있다.That is, the predicted cognitive age value according to melasma/skin color (

), a predictive age linear regression model for melasma/skin color

, Predicted cognitive age values according to sebum/porphyrin (

), a sebum/porphyrin predictive age linear regression model to calculate

, Predicted cognitive age values according to genes (

), which is a gene-predicted age linear regression model to calculate

, Predicted cognitive age values according to environment/lifestyle (

), which is an environmental/lifestyle predictive age linear regression model to calculate

also

can be calculated in a similar way.

,

,

,

,

각각을 이용하여, 주름에 따른 예측 인지 나이 수치(

), 기미/피부색에 따른 예측 인지 나이 수치(

), 피지/포피린에 따른 예측 인지 나이 수치(

), 유전자에 따른 예측 인지 나이 수치(

), 환경/생활습관에 따른 예측 인지 나이 수치(

)를 산출할 수 있다.In summary, the cognitive age prediction model management unit 21 is a cognitive age prediction model.

,

,

,

,

Using each, the predicted cognitive age value according to wrinkles (

), predictive cognitive age values according to melasma/skin color (

), predicted cognitive age according to sebum/porphyrin (

), predictive cognitive age according to genes (

), predicted cognitive age according to environment/lifestyle (

) can be calculated.

~

를 종합한 통합 인지 나이

일 수 있다.The predicted cognitive age derivation unit 23 may obtain the predicted cognitive age using the predicted cognitive age values obtained by the cognitive age prediction model management unit 21 . The predicted cognitive age is a plurality of predicted cognitive age values

~

integrated cognitive age

can be

를 산출할 수 있다.The predicted cognitive age derivation unit 23 uses the cognitive age prediction values obtained by the cognitive age prediction model management unit 21 to integrate the cognitive age.

can be calculated.

는 통합 인지 나이 함수

를 통해 산출될 수 있고,

는 아래 수학식 2와 같을 수 있다.integrated cognitive age

is the integrated cognitive age function

can be calculated through

May be the same as Equation 2 below.

~

는 예측 인지 나이 수치들로 산출 방법은 위에서 검토한 바와 같다.

~

는 개별 예측 인지 나이의 가중치로, 개별 예측 모델의 인지 나이 예측 정확도의 역수를 사용할 수 있으나, 이 또한 조정될 수 있다.In Equation 2 above

~

are predicted cognitive age values, and the calculation method is the same as reviewed above.

~

As a weight of individual predicted cognitive age, the reciprocal of the cognitive age prediction accuracy of the individual predictive model can be used, but this can also be adjusted.

는 상기한 산출방법에 국한되지 않고, 입력된 얼굴이미지를 이미지 분석하여 도출된 나이일 수도 있다.integrated cognitive age

is not limited to the above calculation method, and may be an age derived by image analysis of an input face image.

Meanwhile, the cognitive age prediction models may be transferred from the memory 30 . That is, the memory 30 may collect data, generate a cognitive age prediction model using the collected data, and transmit the model to the cognitive age prediction calculation unit 20 .

The memory 30 may include at least one of databases 31 and 33 , a prediction model generator 35 and an average model generator 37 . Meanwhile, in the present disclosure, the memory 30 has been described as a component of the apparatus 1 for predicting a perceived age, but the memory 30 may be implemented in the form of a server separately from the apparatus 1 for predicting a perceived age.

The databases 31 and 33 may include an integrated subject database 31 and a material and prescription database 33 .

The subject integrated database 31 may receive and store subject data for generating a cognitive age prediction model from the update unit 40 .

The update unit 40 may receive test subject data and perform at least one of conversion and management.

The update unit 40 receives the face image input and measured by the input unit 10, skin measurement values, genetic information, environment information, lifestyle information, and actual age from the input unit 10, and evaluates separately evaluated by the evaluator. Age can be entered.

Specifically, the update unit 40 may include a data processing unit 41 and an outlier detection unit 42 . The data processing unit 41 may convert the test subject data transmitted from the input unit 10 to match the data format of the databases 31 and 33 . For example, the data processing unit 41 may encode, anonymize, or assign a control number to the test subject data transmitted from the input unit 10 . In addition, the data processing unit 41 may perform a numerical unification operation for each measuring device in the test subject data transmitted from the input unit 10 . For example, the data processing unit 41 may perform an operation of dividing a value obtained by subtracting the average from the measured values of each measuring device by the standard deviation.

The outlier detection unit 42 may detect an outlier in the subject data transmitted from the input unit 10 . For example, the outlier detection unit 42 may detect outliers such as height divided by weight, whether there is a difference of more than 3*standard deviation from the average, menopause responses, and the like.

The subject data may include at least one of the subject's actual age, estimated age, measured skin value, genetic information, environmental information, and lifestyle information.

The evaluated cognitive age may refer to the cognitive age of the subject evaluated by at least one evaluator. When there are several evaluators, the evaluated cognitive age may refer to an average age of the subject's perceived ages evaluated by the evaluators.

The material and prescription database 33 may store customized prescription information for at least one aging factor. Aging factors may include five types of wrinkles, melasma/skin color, sebum/porphyrin, genes, and environment/lifestyle.

The material and prescription database 33 may include efficacious materials, genetically tailored materials, material-applied formulations, and the like.

The predictive model generation unit 31 may generate a cognitive age prediction model for each aging factor by utilizing the subject's integrated information.

Specifically, the model generation unit 31 uses the subject data, that is, the subject's actual age, the evaluated perceived age, the age derived by analyzing the facial image, the measured skin value, genetic information, environmental information, and lifestyle information, to determine the perceived age. A predictive model can be created. For example, the predictive model generation unit 31 recognizes an actual age, an age derived by analyzing a face image, a skin measurement value, genetic information, environment information, or lifestyle information by using a relationship between one or more of the evaluation and cognitive age. An age prediction model can be created.

The predictive model generation unit 31 may transfer the generated cognitive age prediction model to the cognitive age prediction calculator 20 .

In addition, as the subject data stored in the subject integrated database 31 is updated, the cognitive age prediction model may also be updated.

The average model generating unit 27 may generate an average model for calculating an average value of the estimated cognitive age or predicted cognitive age for each age or a table in which the average value of the estimated cognitive age or predicted cognitive age for each age is mapped.

Specifically, the average model generating unit 27 may generate an average model for calculating an average value of the estimated cognitive age or predicted cognitive age.

According to an embodiment, the average model generation unit 27 may be a linear regression model of the estimated cognitive age or predicted cognitive age and the actual age, which may be expressed as Equation 3 below.

In particular, the average model generating unit 27 may generate an average model through a linear regression model of the estimated cognitive age or the predicted cognitive age and the actual age when the subject data is smaller than the reference size.

Meanwhile, according to another embodiment, the average model generating unit 27 may generate an average model using an average of estimated cognitive ages or predicted cognitive ages for each age. That is, the average model generating unit 27 may generate an average model for calculating an average value of the predicted cognitive age for each age.

In particular, the average model generation unit 27 may generate an average model using an average of estimated cognitive ages or predicted cognitive ages for each age when subject data is larger than the standard size. Also, the average model generation unit 27 may generate an average model using the average of the predicted cognitive ages only for the age of 30 or more.

According to another embodiment, the average model generation unit 27 may generate average models for each of wrinkles, melasma/skin color, sebum/porphyrin, genes, and environment/lifestyle.

Each of the above-described embodiments may be implemented separately, or a plurality may be integrated and implemented.

Meanwhile, the average model generation unit 27 may generate and store the average of the estimated cognitive age or predicted cognitive age through the average model in the form of a table, examples of which are shown in Table 1 below.

real age Mean predicted cognitive age 21 22.8 22 23.6 23 24.4 ... ... 78 73.4 79 74.3 80 75.9

The average model generation unit 37 may transmit the generated average model to the predicted cognitive age analysis unit 50. When the predicted cognitive age analysis unit 50 receives the predicted cognitive age and the actual age, the predicted cognitive age and the predicted cognitive age Residuals of the mean value of cognitive age can be calculated. More specifically, the predicted cognitive age analysis unit 50 may include an average model management unit 51 and a cognitive age residual derivation unit 53 . The average model management unit 51 may perform at least one of storing, using, and managing the average model transmitted from the average model generation unit 37 . The average model management unit 51 may receive the predicted cognitive age from the predicted cognitive age derivation unit 23 and the actual age from the input unit 10 . The average model management unit 51 may obtain an average value of the predicted cognitive age corresponding to the actual age by using the average model.

The cognitive age residual deriving unit 53 may calculate a residual that is a difference between the predicted cognitive age and the average value.

For example, the average model management unit 51 receives data indicating that the actual age of the measurement target user is 23 years old and the predicted cognitive age is 25 years old. The average model management unit 51 calculated the average value of the predicted cognitive age of the actual age of 23 as 24.4 years. That is, the average model management unit 51 may calculate an average value of predicted cognitive age, which is a degree of looking older than people of the same age. Further, the cognitive age residual derivation unit 53 may obtain, as a residual, 0.6 years old, which is a difference between the predicted cognitive age of 25 years and the average value of 24.4 years.

As described above, when the cognitive age residual deriving unit 53 uses the difference between the predicted cognitive age and the average value of the predicted cognitive age, there is an advantage in that objectivity of the evaluation can be improved. Specifically, since people tend to rate people younger than themselves as more than their actual age, and people who are older than themselves as younger than their actual age, if we assume that we use the difference between actual age and perceived age, , the objectivity of the cognitive age may be lowered by the age or tendency of the person who evaluates it. For example, people in their 30s and 40s tend to evaluate those in their 20s as older and those in their 60s as younger, which causes a deviation, which can be compensated for by using the average value of predicted cognitive ages. In addition, since the cognitive age prediction model tends to predict closer to the average of the learning data, the cognitive age residual derivation unit 53 may play a role of correcting this pattern.

The residual obtained by the perceived age residual derivation unit 53 may be transmitted to the perceived age analysis result output unit 60 .

The perceived age analysis result output unit 60 may have a display and display the perceived age analysis result through the display.

The cognitive age analysis result output unit 60 may include at least some or all of the evaluation result diagram derivation unit 61 and the recommended product/prescription derivation unit 63 .

The evaluation result diagram derivation unit 61 may receive residuals and average values from the predicted cognitive age analysis unit 50, and generate and output an evaluation result diagram using the received residuals and average values.

3 is a diagram illustrating an example of an evaluation result diagram output by the apparatus for predicting a cognitive age according to an embodiment of the present disclosure.

As shown in FIG. 3 , the evaluation result diagram derivation unit 61 may generate and display the prediction of the cognitive age, that is, the evaluation result as a diagram.

For example, the evaluation result diagram derivation unit 61 may include a first line (average) indicating an average value of predicted cognitive age, which is a degree of looking aged of people of the same age as the measurement target user, and a measurement target user's aged appearance. A radial chart in which a second line (yours) representing predicted cognitive age, which is a degree, is shown may be generated as a diagram. In particular, the evaluation result diagram derivation unit 61 has a first line connecting average values for each of wrinkles, melasma/skin color, sebum/porphyrin, genes, and environment/lifestyle, and a second line connecting the predicted cognitive age of the user to be measured. You can create a radial chart with In this case, it may mean that the second line is located inside the first line, it means that the line looks younger, and it may mean that it looks older as it is located outside the line.

As such, since the average value and the predicted cognitive age of the user to be measured are displayed on the first line and the second line, the user to be measured has the advantage of being able to more intuitively determine whether he/she looks older or younger than the average through the diagram.

In addition, wrinkles, melasma/skin color, sebum/porphyrin, genes, and environment/lifestyle are displayed, so the measurement target user has the advantage of being able to determine whether he/she looks older or younger than the average for each factor.

Meanwhile, the recommended product/prescription derivation unit 63 may derive and output a product or prescription based on the residual and the average value. The recommended product/prescription derivation unit 63 may derive and output a product or prescription for each user to be measured based on the material of the memory 30 and the information of the prescription database 33 .

For example, the recommended product/prescription derivation unit 63 provides a product or prescription in relation to the melasma/skin color analyzed as looking older than the average value and the environment/lifestyle for the measured user analyzed as in the example of FIG. 3 can do. For example, the recommendation product/prescription derivation unit 63 may prescribe vitamin C in relation to melasma/skin color and recommend a sunscreen in relation to environment/lifestyle.

Meanwhile, the above-described cognitive age prediction device 1 may be a device manufactured separately to obtain and output the perceived age, or may be a mobile terminal such as a smart phone. That is, it may be a device for predicting a perceived age in which a mobile terminal acquires and outputs a perceived age.

In addition, the present disclosure may be implemented as a perceived age prediction system that predicts and outputs a perceived age through communication between a plurality of devices.

4 is a block diagram of a system for predicting a perceived age according to an embodiment of the present disclosure.

The cognitive age prediction system may include a mobile terminal 110 , a server 120 and a data providing server 130 . In the system for predicting a perceived age according to the present invention, the mobile terminal 110 or the server 120 may be the aforementioned cognitive age predicting device, may include some or all of the features of the aforementioned cognitive age predicting device, and the mobile terminal 110 and the server 120 may perform each function by dividing the function of the above-described cognitive age prediction device. In the following, the functions of the cognitive age predicting device are divided and the execution of each function in the system will be exemplarily described.

The mobile terminal 110 may be a user terminal such as a smart phone, a tablet PC, or a laptop computer.

The server 120 may obtain a cognitive age prediction model. The server 120 may obtain a cognitive age prediction model based on data received from the data providing server 130 .

The server 120 may directly obtain the perceived age based on the perceived age prediction model, or may transmit the perceived age prediction model to the mobile terminal 110 to acquire the perceived age in the mobile terminal 110 .

The data providing server 130 may store and update data necessary for calculating a cognitive age prediction model. The data providing server 130 may store and update algorithms and user information necessary for calculating a cognitive age prediction model.

The data providing server 130 may store the evaluation cognitive age and subject data. The data providing server 130 may transmit the evaluated cognitive age and subject data to the server 120 . The data providing server 130 may perform an authentication operation before transmitting the evaluation recognition age and test subject data to the server 120, and through this, the personal information of the subjects may be protected.

The data providing server 130 may directly obtain a perceived age prediction model based on data necessary to calculate the perceived age prediction model. Alternatively, the data providing server 130 may transmit data necessary for calculating the perceived age prediction model to the server 20 so that the server 20 may acquire the perceived age prediction model.

Next, referring to FIG. 5 , a method for the cognitive age prediction system to acquire a cognitive age prediction model, obtain a predicted cognitive age based on the cognitive age prediction model, and provide recommendation information accordingly will be described in detail.

5 is a flowchart illustrating a method of operating a system for predicting a perceived age according to an embodiment of the present disclosure.

The data providing server 130 may store the evaluated cognitive age and subject data (S111).

That is, the data providing server 130 may store and manage data necessary for generating a cognitive age prediction model including the evaluated cognitive age and subject data.

The subject data may include the actual age of the subject, the perceived age of evaluation, the age derived by analyzing the face image, the measured skin value, genetic information, environmental information, lifestyle information, and the like.

The data providing server 130 may transmit data necessary for acquiring the cognitive age prediction model to the server 120 (S113).

The server 120 may receive data necessary for obtaining a cognitive age prediction model from the data providing server 130 .

The server 120 may obtain a cognitive age prediction model based on data necessary for acquiring the cognitive age prediction model (S115).

On the other hand, the mobile terminal 110 may acquire the information of the measurement target (S117).

The mobile terminal 110 may transmit the information of the subject to be measured to the server 120 (S119). The server 120 may receive information on a subject to be measured from the mobile terminal 110 .

The server 120 may receive information of a measurement target directly input to the mobile terminal 110 from the mobile terminal 110 . Alternatively, the server 120 may receive measurement target information from a separate measurement target information storage server (not shown) storing measurement target information according to a transmission command from the mobile terminal 110 . To this end, the mobile terminal 110 may provide a transmission command for transmitting measurement target information from a measurement target information storage server (not shown) to the server 120 .

Here, the measurement subject information storage server (not shown) may be the data providing server 130 . Alternatively, a measurement subject information storage server (not shown) is an institution that measures and evaluates the subject's skin condition, an institution that analyzes and evaluates the subject's gene, or collects or evaluates environmental information or lifestyle information of the subject. It may be a storage server owned by an institution or a storage server owned by an institution that receives and stores data from the above institutions.

When the server 120 receives the measurement target's information from the mobile terminal 110, it may acquire the predicted cognitive age by applying the measurement target's information to a cognitive age prediction model (S121).

The server 120 may obtain the predicted cognitive age and transmit a diagram showing the predicted cognitive age and average age to the mobile terminal 110 (S123).

The server 120 may transmit a diagram showing the predicted cognitive age and average age to the mobile terminal 110 to be displayed on the mobile terminal 110 . The average age may be an average value of an estimated or predicted age of people of the same age as the measurement subject.

In addition, the server 120 may transmit recommendation and prescription information to the mobile terminal 110 to be displayed on the mobile terminal 110 .

In the above, it has been described that the server 120 generates and stores a cognitive age prediction model and an average model through a cognitive age prediction model generator and an average model generator, and calculates a predicted cognitive age and an age residual through the models. The system according to the present invention is not limited thereto, and each prediction model generated by the server 120 may be transmitted to the mobile terminal 110 and the mobile terminal itself may directly calculate the predicted cognitive age and the age residual.

Specifically, the server 120 may transmit the perceived age prediction model to the mobile terminal 110 , and the mobile terminal 110 may store the perceived age prediction model received from the server 120 . The mobile terminal 110 may acquire the predicted cognitive age by applying the information of the subject to be measured to the cognitive age prediction model received from the server 120 . The mobile terminal 110 may receive the information of the measurement target directly or receive it from a separate measurement target information storage server (not shown) that stores the measurement target information.

According to one embodiment of the present invention, the mobile terminal 110 receives the actual age together with the input data to calculate the predicted cognitive age and the age residual, transmits the data to the data providing server 130, and transmits the data to the data providing server 130. ) can update the prediction models by storing the data set for updating the model with the input data.

The above-described present disclosure can be implemented as computer readable codes in a medium on which a program is recorded. The computer-readable medium includes all types of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable media include Hard Disk Drive (HDD), Solid State Disk (SSD), Silicon Disk Drive (SDD), ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. there is

The above detailed description should not be construed as limiting in all respects and should be considered illustrative. The scope of this specification should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent scope of this specification are included in the scope of this specification.

The above description is merely an example of the technical idea of the present invention, and various modifications and variations can be made to those skilled in the art without departing from the essential characteristics of the present invention.

Therefore, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but to explain, and the scope of the technical idea of the present invention is not limited by these embodiments.

The protection scope of the present invention should be construed according to the following claims, and all technical ideas within the equivalent range should be construed as being included in the scope of the present invention.

Claims (14)

a data providing server that acquires the assessed cognitive age and subject data;
a server that obtains a cognitive age prediction model based on the evaluated cognitive age and subject data received from the data providing server; and
The mobile terminal
The predicted cognitive age is obtained by receiving the cognitive age prediction model from the server and applying the information of the measurement target including face image, skin measurement value, genetic information, environmental information, or lifestyle information to the cognitive age prediction model. doing
A cognitive age prediction system.
The method of claim 1,
The mobile terminal
Directly input the information of the subject to be measured,
Received from the measurement target information storage server that stores the measurement target information
A cognitive age prediction system.
a data providing server that acquires the assessed cognitive age and subject data;
a server that obtains a cognitive age prediction model based on the evaluated cognitive age and subject data received from the data providing server; and
And a mobile terminal displaying the predicted cognitive age of the measurement subject obtained based on the cognitive age prediction model,
The server
The predicted cognitive age is received from the mobile terminal by receiving information of the measurement target including facial image, skin measurement value, genetic information, environment information, or lifestyle information, and applying the received information of the measurement target to the cognitive age prediction model. Obtaining and transmitting the obtained predicted cognitive age to the mobile terminal
A cognitive age prediction system.
The method of claim 3,
The server
Receiving information of the measurement target directly input to the mobile terminal from the mobile terminal;
Receiving the information of the measurement target from the measurement target information storage server storing the measurement target information according to a transmission command from the mobile terminal
A cognitive age prediction system.
The method according to any one of claims 1 to 4,
The server
Detecting anomalies in the information of the measurement subject
A cognitive age prediction system.
The method according to any one of claims 1 to 4,
The server or mobile terminal
Obtaining an average value of the estimated cognitive age or predicted cognitive age of people of the same age as the measurement subject, and obtaining a residual between the predicted cognitive age and the average value of the measurement subject
A cognitive age prediction system.
The method of claim 6,
The mobile terminal
Displaying a diagram showing the predicted cognitive age and the average value
A cognitive age prediction system.
The method of claim 7,
The mobile terminal
Displaying the predicted cognitive age and the average value for each aging factor
A cognitive age prediction system.
The method of claim 8,
The mobile terminal
Displaying the predicted cognitive age and the average value for each aging factor in a radial chart
A cognitive age prediction system.
The method of claim 6,
The server
Creating and storing a table mapping the average value of the estimated cognitive age or predicted cognitive age by age
A cognitive age prediction system.
The method of claim 8,
The aging factor is
wrinkles, melasma/skin color, sebum/porphyrin, genes, and environment/lifestyle
A cognitive age prediction system.
The method according to any one of claims 1 to 4,
The server or the mobile terminal
Obtaining a cognitive age prediction value of the measurement subject using the cognitive age prediction model, and obtaining a predicted cognitive age through the cognitive age prediction value
A cognitive age prediction system.
The method of claim 12,
The server or the mobile terminal
Obtaining the cognitive age prediction value through a random forest or linear regression model
A cognitive age prediction system.
a data providing server that acquires the assessed cognitive age and subject data;
a server that obtains a cognitive age prediction model based on the evaluated cognitive age and subject data received from the data providing server; and
Directly receiving and storing the information of the measurement target, including facial image, skin measurement value, genetic information, environmental information, or lifestyle information, transmitting the measurement target's information to the server, or storing the measurement target's information Including a mobile terminal receiving a measurement target information storage server to store the measurement target information or providing a transmission command to transmit the measurement target information from the measurement target information storage server to the server;
The server stores the acquired cognitive age prediction model or transmits it to a mobile terminal,
The mobile terminal
The predicted cognitive age of the measurement target obtained by applying the measurement target information transmitted from the mobile terminal or from the measurement target information storage server through a transmission command of the mobile terminal to the cognitive age prediction model is received from the server. Applied to the cognitive age prediction model transmitted from the server, displaying, or directly input and stored measurement target information in the mobile terminal or measurement target information received and stored in the mobile terminal through a transmission command from the measurement target information storage server Displaying the predicted cognitive age of the measurement subject obtained by
A cognitive age prediction system.

Images