KR102068587B1 - Computing device for providing bone density information - Google Patents

Abstract

According to one embodiment of the present disclosure, provided is a computer program stored in a computer readable storage medium including encoded commands, which enables at least one processor of a computing apparatus to perform the following operations when executed by the at least one processor, wherein the operations are: receiving a body composition data set of a user; extracting a biometric data set and an impedance data set based on the body composition data set of the user to generate an input data set including the biometric data set and the impedance data set; and generating bone density change information of the user by calculating the input data set related to the user by using a bone density measurement model.

Description

COMPUTING DEVICE FOR PROVIDING BONE DENSITY INFORMATION}

The present disclosure relates to a computing device for providing bone density information, and more particularly, to a computing device for calculating bone density change information based on body composition data.

As the number of elderly people around the world increases and their income levels rise, so does their concern for health. In general, the balance of the production of bone in humans is balanced, but in older people, the secretion of estrogen is lowered, thereby lowering the bone absorption function, especially in postmenopausal women, the incidence of osteoporosis increases. This osteoporosis rarely exhibits any apparent external symptoms, and once lost bone mass can be very difficult to recover. Accordingly, there is an increasing demand for bone condition analysis. X-ray absorptiometry, ultrasound, clove computed tomography, etc. exist to analyze various bone conditions. Currently, X-ray absorption measurement is the most used to analyze the condition of bone.

However, in the case of X-ray absorption measurement method, there is a problem in that it is necessary to equip the equipment according to the inconvenience of the large size of the equipment and radioactivity. In other words, since it is necessary to measure by a professional operator who has a license to handle radiation, there is a limit to being able to receive medical care only at a large hospital at a general hospital level. This can lead to an economic burden on the measurement.

Thus, there may be a need in the art for computer programs that more easily calculate bone conditions, such as osteoporosis, and provide information related to the calculated bone conditions.

KR 10-1567502

TECHNICAL FIELD The present disclosure is directed to the background art described above and relates to a computing device for providing information about bone density.

In one embodiment of the present disclosure for solving the above problems, a computer program stored in a computer readable storage medium comprising encoded instructions, the computer program being executed by one or more processors of a computing device, Allow one or more processors to perform the following operations, the operations comprising: receiving a user's body composition data set, extracting a biometric data set and an impedance data set based on the user's body composition data set And generating an input data set including an impedance data set and calculating an input data set related to the user by using a bone density measurement model to generate bone density change information of the user.

Alternatively, extracting the biometric data set and the impedance data set based on the user's body composition data set to generate an input data set may include at least one of impedance data and biometric data in the body composition data included in the body composition data set. Determining whether data is matched, extracting impedance data and biometric data based on the determination, and generating a biometric data set including the biometric data and an impedance data set including the impedance data. can do.

Alternatively, the extracting of the biometric data and the impedance data based on the determination may include, if the biometric data and the impedance data match the body component data, extracting the impedance data and the biometric data matched to the body component data. If the biometric data does not match with the extracting operation and the body composition data, health examination data corresponding to the body composition data is received, and the biometric data corresponding to the viewpoint data included in the body composition data is extracted from the health examination data. It may include at least one of the operation.

Alternatively, the bone density measurement model may be generated through at least one of machine learning and regression analysis.

Alternatively, the machine learning receives the user's bone density data set and matches each input data included in the input data set to bone density data included in the bone density data set to generate a labeled learning data set. And by using the labeled training data set, the bone density measurement model can be generated.

Alternatively, the bone density measurement model includes one or more network functions, each of the one or more network functions including at least one of an input layer, one or more hidden layers, and an output layer, wherein the input layer is one or more input nodes. Wherein each of the one or more hidden layers includes one or more hidden nodes, the output layer comprises one or more output nodes, and each node included in each layer links with one or more nodes of another layer. Each of the links may be connected to each other, and each link may have a weight.

Alternatively, the regression analysis may receive the user's bone density data set, determine at least one of impedance data and biometric data included in the input data set as an independent variable for regression analysis, and determine the bone density data set. Determine as a dependent variable for regression analysis, generate a regression equation for correlation analysis between the independent variable and the dependent variable, matching the learning bone density data set of the user to the input data set as a dependent variable learning data set Generating the coefficients of the regression equation using the training data set, and generating the bone density measurement model.

Alternatively, the independent variable may include at least one of height, weight, age and multi impedance of the user.

Alternatively, the multi-impedance is a multi-path impedance, which is an impedance associated with a path through which current flows from one of the two or more electrodes to the other, and the impedance of at least a portion of the user's body for measuring the impedance of the user. It may include a multi-frequency impedance that is one or more frequency-specific impedance of the voltage applied to at least a portion of the body.

Alternatively, the bone density change information may be generated based on viewpoint data included in each of one or more input data of the user as data on the amount of change in bone density of the user.

Alternatively, the method may further include generating bone density guide data based on the bone density change information, and wherein the bone density guide data includes: when the bone density change amount included in the bone density change information deviates from a predetermined threshold change amount, the bone density value; The data may be determined based on a time point at which the change amount deviates from a predetermined threshold change amount, receive health check data corresponding to the time point, and be generated based on the received health check data.

Alternatively, the method may further include generating bone density prediction information based on the bone density change information, wherein the bone density prediction information may be generated by matching a time point corresponding to future prediction bone density.

In another embodiment of the present disclosure, a method for providing bone density change information, the method comprising: receiving a body composition data set of a user, extracting a bio data set and an impedance data set based on the body composition data set of the user, and extracting the bio data; Generating an input data set including the set and the impedance data set, and generating the bone density change information of the user by calculating an input data set related to the user using a bone density measurement model.

In another embodiment of the present disclosure, a computing device for providing bone density change information is disclosed. The computing device includes a processor including one or more cores, a memory for storing program codes executable in the processor, and a network unit for transmitting and receiving data to and from a user terminal and an external server, wherein the processor is configured to store a user's body component data set. Receiving, extracting a biometric data set and an impedance data set based on the user's body composition data set to generate an input data set including the biometric data set and the impedance data set, and using a bone density measurement model to The input data set may be calculated to generate bone density change information of the user.

The present disclosure can provide a computer program for calculating information about bone density.

Various aspects are now described with reference to the drawings, wherein like reference numerals are used to refer to like components throughout. In the following examples, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of one or more aspects. However, it will be apparent that such aspect (s) may be practiced without these specific details.
1 is a conceptual diagram illustrating a system of a computing device for calculating bone density associated with one embodiment of the present disclosure.
2 illustrates a block diagram of a computing device providing information about a user's bone density associated with one embodiment of the present disclosure.
3 is a schematic diagram illustrating a network function associated with one embodiment of the present disclosure.
Figure 4 is an exemplary view showing a bone density measurement model associated with an embodiment of the present disclosure.
5 is an exemplary graph applying a bone density measurement model associated with an embodiment of the present disclosure.
6 is an exemplary graph applying a bone density measurement model associated with an embodiment of the present disclosure.
FIG. 7 is a diagram for comparing data values of bone mineral density measurement models and other bone mineral density measurement devices according to another embodiment of the present disclosure.
8 is an exemplary graph for explaining a threshold change amount related to bone density guide information generation based on bone density change information associated with an embodiment of the present disclosure.
9 illustrates a flow chart for providing bone density change information associated with one embodiment of the present disclosure.
10 illustrates a flow chart for extracting biometric data and impedance data associated with one embodiment of the present disclosure.
11 shows a brief general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

Various embodiments are now described with reference to the drawings. In this specification, various descriptions are presented to provide an understanding of the present disclosure. However, it will be apparent that such embodiments may be practiced without these specific details.

As used herein, the terms “component”, “module”, “system” and the like refer to computer-related entities, hardware, firmware, software, a combination of software and hardware, or the execution of software. For example, a component may be, but is not limited to being, a process running on a processor, a processor, an object, a thread of execution, a program, and / or a computer. For example, both an application running on a computing device and the computing device can be a component. One or more components can reside within a processor and / or thread of execution. One component can be localized within one computer. One component may be distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures stored thereon. The components may be connected via a network such as the Internet and other systems via, for example, signals with one or more data packets (e.g., data and / or signals from one component interacting with other components in a local system, distributed system). Data may be communicated via local and / or remote processes.

In addition, the term “or” is intended to mean an implicit “or” rather than an exclusive “or”. In other words, unless specified otherwise or unambiguously in context, "X uses A or B" is intended to mean one of the natural implicit substitutions. That is, X uses A; X uses B; Or where X uses both A and B, "X uses A or B" may apply in either of these cases. Also, it is to be understood that the term "and / or" as used herein refers to and includes all possible combinations of one or more of the listed related items.

In addition, the terms "comprises" and / or "comprising" should be understood to mean that the corresponding features and / or components are present. It is to be understood, however, that the terms "comprises" and / or "comprising" do not exclude the presence or addition of one or more other features, components, and / or groups thereof. Also, unless otherwise specified or in the context of indicating a singular form, the singular in the specification and claims should generally be interpreted as meaning "one or more."

Those skilled in the art will further appreciate that the various illustrative logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be electronic hardware, computer software, or a combination of both. It should be appreciated that it can be implemented with To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented in hardware or as software depends on the particular application and design constraints imposed on the overall system. Skilled artisans can implement the described functionality in a variety of ways for each particular application. However, such implementation decisions should not be construed as causing a departure from the scope of the present disclosure.

In one embodiment of the present disclosure, the server may include other configurations for performing the server environment of the server. The server may include all types of devices. The server is a digital device, and may be a digital device having a computing power with a processor and a memory such as a laptop computer, a notebook computer, a desktop computer, a web pad, a mobile phone, and the like. The server may be a web server that handles services. The type of server described above is merely an example and the present disclosure is not limited thereto.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be apparent to those of ordinary skill in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present invention is not limited to the embodiments presented herein. The invention should be construed in the broadest scope consistent with the principles and novel features set forth herein.

1 is a conceptual diagram illustrating a system of a computing device for calculating bone density associated with one embodiment of the present disclosure.

According to one embodiment of the present disclosure, computing device 100 and external server 200 may transmit and receive information via interconnections via wireless and / or wired.

According to an embodiment of the present disclosure, the computing device 100 may generate bone density change information. More specifically, the computing device 100 may generate the bone density change information of the user by calculating an input data set related to the user by using the bone density measurement model. In this case, the input data set may be a measurement history of biometric data and impedance of a specific user. In detail, the input data set may include a biometric data set which is a set of biometric data including a height, a gender, a weight, and an age of a user, and an impedance data set which is a set of impedance data including a multi-impedance of a user. That is, the computing device 100 may generate the bone density change information of the user by calculating the height, sex, weight, age, and impedance information of the user as a bone density measurement model. Here, the bone density change information is information about the bone density change amount of the user, and may be generated based on the viewpoint data included in each of the one or more input data of the user. For example, when the biometric data included in the input data set is measured in February 2018 and April 2018, the corresponding biometric data is measured in February 2028 and April 2018 based on the measured biometric data. Bone density change information can be generated. The description of the specific time point of the above-described input data is only an example, and a measurement time point of the impedance data included in the input data may also be based on generating bone density change information, and the measurement time point may be any time point at which the input data is measured. It can include both.

Therefore, the user can easily be provided with information about his / her bone density through the computing device 100 without equipment for measuring bone density and a professional operator who can handle the equipment.

According to an embodiment of the present disclosure, the computing device 100 may generate an input data set by extracting biometric data and impedance data based on body composition data of a user. More specifically, the computing device 100 extracts the biometric data set and the impedance data set based on the body composition data set by determining whether at least one of the impedance data and the biometric data is matched with the body composition data included in the body composition data set. can do. That is, in order to measure body composition, biometric data of the user (eg, age, gender, height, weight, etc.) and multi-impedance are required, and the user's body composition data, biometric data, and multi-impedance data may be matched and stored. have.

In detail, when the biometric data and the impedance data match the body component data, the computing device 100 may extract the impedance data and the biometric data matched to the body component data. In addition, when the biometric data does not match the body composition data of the user, the computing device 100 may receive health examination data corresponding to the body composition data from the external server 200, and may calculate the body composition data from the received health examination data. The biometric data corresponding to the measurement time point may be extracted. When the impedance data does not match the body composition data of the user, the computing device 100 may invert the impedance data using the body composition data and the biometric data matched with the body composition data, and extract the inverted impedance data. Can be. That is, the computing device 100 may generate input data for calculating bone density change information by extracting biometric data and impedance data through body composition data of the user.

In addition, the computing device 100 may generate and provide bone density guide information to the user based on the bone density change information. More specifically, the computing device 100 determines when the bone density change amount deviates from the predetermined threshold change amount when the bone density change information of the user outputted using the input data as the input of the bone density measurement model deviates from the predetermined threshold change amount, Health check data corresponding to the time point may be received from the external server 200. In this case, the computing device 100 may generate bone density guide information based on the received medical examination data. Accordingly, the user may determine a specific event according to the change amount of his / her bone density through the bone density change information provided by the computing device 100, thereby more easily identifying an event affecting his / her bone density.

2 illustrates a block diagram of a computing device providing information about a user's bone density associated with one embodiment of the present disclosure.

The components of computing device 100 shown in FIG. 2 are exemplary. Only some of the components shown in FIG. 2 may configure the computing device 100. In addition to the components shown in FIG. 2, additional component (s) may be included in the computing device 100. In addition, computing device 100 may include any type of device, including, for example, computing power with a processor and memory, such as a laptop computer, notebook computer, desktop computer, web pad, mobile phone, etc. It may be a digital device equipped with. In addition, the computing device 100 may be a web server that calculates bone density change information.

In an embodiment of the present disclosure, the computing device 100 may distribute and process the model by using at least one of the CPU, the GPGPU, and the TPU. In addition, in an embodiment of the present disclosure, the computing device 100 may distribute and process the model along with other computing devices.

In the present specification, the network function may be used interchangeably with an artificial neural network and a neural network. In this specification, the network function may include one or more neural networks, in which case the output of the network function may be an ensemble of the outputs of the one or more neural networks.

In this specification, the model may include a network function. The model may include one or more network functions, in which case the output of the model may be an ensemble of outputs of one or more network functions.

As shown in FIG. 2, the computing device 100 may include a processor 110, a memory 120, and a network unit 130.

According to an embodiment of the present disclosure, the processor 110 may include one or more cores, and may include a central processing unit (CPU) and a general purpose graphics unit (GPGPU) of the computing device 100. and a processor for data analysis and deep learning such as a processing unit (TPU) and a tensor processing unit (TPU). The processor 110 may read the computer program stored in the memory 120 to calculate bone density change information according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, the processor 110 may perform calculation for learning a neural network. The processor 110 may be configured to process neural networks such as processing input data for learning in deep learning (DN), feature extraction from input data, error calculation, weight update of neural networks using backpropagation, and the like. You can perform calculations for learning.

In addition, at least one of the CPU, GPGPU, and TPU of the processor 110 may process the training of the model. For example, the CPU and GPGPU can work together to train the model and compute bone density data using the model. In addition, in an embodiment of the present disclosure, a processor of a plurality of computing devices may be used together to process training of a model and calculation of bone density data through a bone density measurement model. In addition, the computer program executed in the computing device according to an embodiment of the present disclosure may be a CPU, a GPGPU, or a TPU executable program.

Hereinafter, a method of calculating bone density change information according to an embodiment of the present disclosure will be described.

According to an embodiment of the present disclosure, the processor 110 may obtain a body composition data set of a user. In this case, the body composition data set of the user acquired by the processor 110 is information analyzing the components constituting the human body of the user, for example, the user's weight, lean body mass, muscle mass, body water volume, intracellular water content, body It may include information about the lactate index and body fat percentage. As described above, the specific description of the body composition data of the user is only an example, and the present disclosure is not limited thereto.

According to one embodiment of the present disclosure, the processor 110 may generate an input data set. More specifically, the processor 110 may extract the biometric data set and the impedance data set based on the body composition data set of the user to generate an input data set including the biometric data set and the impedance data set. In this case, the biometric data set may be a set of biometric data including height, gender, weight, and age of the user, and the impedance data set may be a set of impedance data including multi-impedance of the user. In addition, multi-impedance may be applied to at least a portion of the user's body for measurement of multipath impedance and impedance of at least a portion of the user's body, which is an impedance associated with a path through which current flows from one electrode to the other of two or more electrodes. It may include a multi-frequency impedance which is one or more frequency-specific impedance of the applied voltage. In detail, the multipath impedance may include a path connecting two electrodes of the body composition measuring device to the left and right hands of the user, or a path connecting the two electrodes to the left and right feet of the user, respectively. That is, the multipath impedance may be impedance data measured through a change in a region where two electrodes are connected to the user's body, and may include impedance data measured through at least one path. In addition, the multi-frequency impedance may be an impedance value measured by changing a frequency on the same path. For example, when two electrodes provided in the body composition measuring device are connected to a user's left hand and right hand, when the frequency of the voltage applied to the user's body is applied at 50 KHz, the measured impedance data and the 250 KHz are applied. Information on the multi-frequency impedance may be generated based on the measured impedance data. That is, the impedance data used to calculate the bone density in the present disclosure includes multipath impedance and multi-frequency impedance, rather than simply measured impedance information, so that more accurate bone density can be calculated.

일 수 있다. 전술한 관계 정보에 대한 기재는 예시일 뿐이며, 본 개시는 이에 제한되지 않는다. In addition, the processor 110 may generate relationship information that is information about a relationship between at least two factors of the input data set. For example, the relationship information may be information about a relationship between weight and multi-impedance among factors of the learning biometric data. For example, relationship information

Can be. The above description of the relationship information is only an example, and the present disclosure is not limited thereto.

In addition, the processor 110 may generate an input data set including the biometric data set and the impedance data set based on the body composition data set of the user. In detail, the processor 110 may determine whether at least one of the impedance data and the biometric data is matched with the body component data included in the body composition data set, and extract the impedance data and the biometric data based on the determination. have. In more detail, when the biometric data and the impedance data match the body composition data of the user, the processor 110 may extract the impedance data and the biometric data matched with the body composition data. In addition, when the biometric data does not match the body composition data, the processor 110 receives health examination data corresponding to the body composition data from the external server 200 and corresponds to a measurement time point of the body composition data in the received health examination data. Biometric data can be extracted. When the impedance data does not match the body composition data of the user, the processor 110 may invert the impedance data using the body composition data and the biometric data matched with the body composition data, and extract the inverted impedance data.

According to an embodiment of the present disclosure, the processor 110 may invert impedance data using body composition data and biometric data corresponding to the body composition data. For example, since the measurement of the body composition requires impedance and biometric data, if two data of the body component, the impedance and the biometric data are known, the other data can be obtained. More specifically, the method in which the processor 110 inverts the impedance may include at least one of a method using a regression equation, a method through learning an artificial neural network, and a method using a formula (system equation) for correlation of each data. It may include. The foregoing description of the method of inverting impedance is merely an example, and the present disclosure is not limited thereto.

According to one embodiment of the present disclosure, the processor 110 may obtain a bone density data set. In this case, the bone density data included in the bone density data set may be data related to the strength of the bone of the user. For example, the bone density data may include a bone density value of a user, an index comparing with a bone density of a predetermined user group, an index comparing with a bone density of a user group of the same age group as the user of the bone density data, and a gender equal to the user of the bone density data. It may include at least one of the index compared with the bone density of the user group, the index compared with the bone density of the same ethnic group as the user of the bone density data, T-value and Z-value. T-values can include values expressed as standard deviations as compared to the average BMD of a young adult population at the same gender. T-values can include values expressed as standard deviations based on (measured bone density values in patients-average bone density values in younger populations). The T-value may be a value that represents an absolute risk for fracture. The Z-value may include a value expressed as a standard deviation by comparing bone density and mean bone density of the same age group. Z-values can include values expressed as standard deviations based on (measured bone density values of patients-average bone density values of the same age group). For example, the learning bone density data may be a T-value when measured for postmenopausal women or men 50 years or older, and may be a Z-value when measured for children, adolescents, premenopausal women, or men 50 years of age or older. . The description of the above-described learning biometric data and learning bone density data is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the processor 110 may generate a bone density measurement model. In this case, the bone density measurement model generated by the processor 110 may be generated through at least one of machine learning and regression analysis. Hereinafter, the process of generating a bone density measurement model through machine learning will be described.

)를 학습 데이터의 입력으로 하고, 상기 사용자 A의 학습 골밀도 데이터(본 예시에서, T-값 -0.1)를 학습 데이터의 라벨로 하여 학습 데이터를 생성할 수 있다. 전술한 학습 데이터의 생성에 대한 기재는 예시일 뿐이며 본 개시는 이에 제한되지 않는다.According to an embodiment of the present disclosure, the processor 110 may generate the learning data by labeling the learning bone density data of the user on the learning input data of the user included in the learning data set. The processor 110 may generate the learning data using the learning input data of the user as the input of the learning data and the learning bone density data of the user as the label of the learning data. For example, user A's learning input data (in this example, 60 years old, 164 cm, female, 53 kg, 700 Ω,

) Can be used as input of the training data, and the training data can be generated using the training bone density data of the user A (T-value -0.1 in this example) as the label of the training data. The description of the generation of the above-described learning data is only an example and the present disclosure is not limited thereto.

In addition, when there is a missing item among one or more items of the user's learning input data, the processor 110 may set the item value of the missing item as an intermediate value or an average value of the learning data set. In detail, the processor 110 may delete the column for the corresponding item when data about one item among the biometric data and the impedance of the users of the learning input data set is insufficient. For example, if there is no data of an item for a key among the items of user B's learning biometric data, for a missing item for a user B's key, for a user's height of all users of the same gender and age, The item value for the missing item can be supplemented with an average value of 173 cm. For example, when the data on the weight of the items of the learning biometric data is present in the learning biometric data of the user more than a predetermined ratio among all the users, the column for the corresponding item (weight in this example) may be deleted. The description of the item value supplement of the above-described missing item is only an example, and the present disclosure is not limited thereto.

In addition, the processor 110 may generate a bone density measurement model including one or more network functions 300. The processor 110 may generate a bone density measurement model including one or more network functions 300 including at least one of an input layer, one or more hidden layers, and an output layer. The processor 110 may generate a network function 300 composed of input layers including one or more input nodes. The processor 110 may generate a network function such that the hidden layer included in the network function includes one or more hidden nodes. The processor 110 may generate the network function 300 such that the output layer included in the network function includes one or more output nodes. The processor 110 may generate each node included in the layer of the network function to be connected to one or more nodes of another layer through a link. Each weight may be set to each link.

In addition, the processor 110 may input training input data of training data as an input of a bone density measurement model. In detail, the processor 110 may input input data into one or more input nodes included in the input layer of the bone density measurement model. In this case, the learning input data may include one or more items, and the items may mean each of data related to the health of the user. The processor 110 may respectively input items of training input data to each of one or more input nodes included in the input layer of the bone density measurement model. For example, when five nodes are included in the input layer of the bone density measurement model, the processor 110 may determine five items of the five input items of height, weight, age, gender, and multi-impedance of the training input data. You can type in For example, the processor 110 may include a first item (in this example, item height 156 cm) in the first node included in the input layer of the bone density measurement model, and a second item (in this example, item weight 43 kg in the second node). ), The third node has a third item (in this example, item age 17), the fourth node has a fourth item (in this example, item gender female) and the fifth node has a fifth item (in this example, item Multi impedance 800 Ω) can be input. In another example, the input layer of the bone density measurement model may further receive a plurality of bio multi-impedances. The specific description of the input of the bone density measurement model described above is merely an example, and the present disclosure is not limited thereto.

In addition, the processor 110 may generate a bone density measurement model including an input layer, one or more hidden layers, and an output layer. In this case, the layer may include one or more nodes. Nodes can be connected via links with other nodes. The processor 110 may calculate an item input to an input node of an input layer of the bone density measurement model through a link connected to the input node and propagate it to the hidden layer. The operation can include any mathematical operation. For example, the operation may be a product or a compound product, but the foregoing description is merely an example and the present disclosure is not limited thereto. The processor 110 may calculate an item input to an input node of the bone density measurement model through a link connected to the input node and propagate it to the output layer through one or more hidden layers. The processor 110 may generate bone density data based on the value propagated to the output layer of the bone density measurement model.

The processor 110 may determine the first node value of the first node of the bone density measurement model, the second node value of the second node included in the previous layer connected to the first node, the second node included in the previous layer, and the It can be derived by calculating the first link weight of the link set in the link connecting the first node. The processor 110 computes the first node value of the first node of the bone density measurement model by using the second link weight set in the link connecting the third node included in the next layer connected with the first node and propagates to the third node. can do.

The processor 110 inputs each item value of an item included in the training input data set of the training data into one or more input nodes included in the input layer of the bone density measurement model to generate a bone density measurement model, and outputs the bone density measurement model. The error can be calculated by comparing the bone density data (ie, output) calculated in the layer with the learning bone density data (ie, correct answer). The processor 110 may adjust the weight of the bone density measurement model based on the error. The processor 110 may update a weight set for each link by propagating from an output layer included in one or more network functions of the bone density measurement model to an input layer through one or more hidden layers based on the error.

In addition, in generating the bone density measurement model, the processor 110 may set a dropout so that a part of the output of the hidden node is not transmitted to the next hidden node in order to prevent overfitting.

The training epoch inputs the training input data to each of the one or more input nodes included in the input layer of one or more network functions of the bone density measurement model for all the training data included in the training data set, and labels the training input data. The derived learning bone density data (i.e., the correct answer) and the bone density data (i.e., the output) of the bone density measurement model to derive an error, and the derived error from the output layer of one or more network functions of the bone density measurement model. By propagating through the input layer, the weights set in the respective links may be updated. That is, when the operation using the bone density measurement model and the weight update process for the bone density measurement model are performed on all the training data included in the training data set, the training data may be 1 epoch.

When generating the bone density measurement model, the processor 110 may set the learning rate of the bone density measurement model to a predetermined value or more when the learning epoch for learning the bone density measurement model is less than or equal to a predetermined epoch. When generating the bone density measurement model, the processor 110 may set the learning rate of the bone density measurement model to be equal to or less than a predetermined value when the learning epoch for learning the bone density measurement model is greater than or equal to a predetermined epoch. The learning rate may mean an update degree of weights. For example, in the early stage of learning, the learning rate can be set high (ie, the weighting degree of the update is large), so that the output of the learning data can quickly access the label of the learning data. For example, later in the training, you can set the learning rate low (that is, by making the weight update smaller) to reduce the error between the output of the training data and the label of the training data (that is, to improve accuracy). can do. The above disclosure about the learning rate is only an example, and the disclosure is not limited thereto.

The processor 110 may perform the learning of the bone density measurement model more than a predetermined epoch, and then determine whether to stop learning using the verification data set. The predetermined epoch may be part of the overall learning goal epoch. The processor 110 may make a part of the training data set a verification data set. The verification data is data corresponding to the learning data, and may be data for determining whether to stop learning. After the learning of the bone density measurement model is repeated over a predetermined epoch, the processor 110 may determine whether the learning effect of the bone density measurement model is greater than or equal to a predetermined level using the verification data. For example, the processor 110 uses 100 million pieces of learning data to perform 10000 times of target repetition learning, and then uses 1000 pieces of verification data after performing 10000 times of repetitive learning, which is a predetermined epoch. 10 repetitive learning (ie, 10 epochs), and when the change of neural network output is less than or equal to a predetermined level during the 10 repetitive learning, it may be determined that further learning is meaningless and the learning may be terminated. That is, the verification data may be used to determine the completion of the learning based on whether the effect of the epoch-specific learning in the repetitive learning of the neural network is above or below a certain level. The above-described learning data, the number of verification data, and the number of repetitions are only examples, and the present disclosure is not limited thereto.

The processor 110 may set at least one of the training data sets as a test data set. The test data is data corresponding to the training data, and may be data used to verify performance after the training of the model is completed. The processor 110 may use one or more input data and bone density data labeled in the biometric data as a test data set. The processor 110 inputs the input data included in the test data set into the bone density measurement model, compares the output from the bone density measurement model with the labeled bone density data, and calculates a correct answer rate of the bone density measurement model for the test data set. You can judge. The processor 110 inputs the training input data of the user included in the test data into the bone density measurement model, and the bone density data (ie, output) output from the bone density measurement model and the learning bone density of the user included in the test data. By comparing the data (ie, the correct answer), the activation of the bone density measurement model can be determined if the error is less than or equal to a predetermined value. The processor 110 compares the bone density data (ie, output) output from the bone density measurement model with the learning bone density data of the user included in the test data (ie, the correct answer), and when the error is greater than or equal to a predetermined value, the bone density Training of the measurement model can be performed further above a predetermined epoch or deactivated the bone density measurement model. When the processor 110 deactivates the bone density measurement model, the processor 110 may discard the bone density measurement model. The processor 110 may determine the performance of the generated bone density measurement model based on factors such as accuracy, precision, recall, and the like. The foregoing performance evaluation criteria are only examples and the present disclosure is not limited thereto. According to an exemplary embodiment of the present disclosure, the processor 110 may independently generate one or more bone density measurement models by independently learning one or more network functions included in each bone density measurement model, and evaluate the performance of only the neural network having a certain performance or more. It can be used for measuring bone density.

That is, the processor 110 processes the training data set as an input of a network function, compares the output value of the network function with the result value of the labeled training data (ie, bone density data), and reverses the error according to the comparison. By propagating and learning the network function, a bone density measurement model can be generated.

According to another embodiment of the present disclosure, the processor 110 may generate a bone density measurement model through regression analysis.

The processor 110 may obtain learning data through the network unit 130. At this time. The training data may include training input data and training bone density data including training biometric data and training impedance data of all customers. The training data set may include the training input data of the customer as an independent variable for regression analysis, and include the training bone density data of the customer matching the training input data of the customer as a dependent variable for the independent variable. have. The training input data may include one or more items having respective item values as described above. As described above, the learning bone density data may include a bone density value of a user, an index comparing with a bone density of a predetermined user group, an index comparing with a bone density of a user group of the same age as the user of the bone density data, and a gender equal to the user of the bone density data. It may include at least one of the index compared to the bone density of the user group of, the index compared to the bone density of the same ethnic group as the user of the bone density data, T-value and Z-value. To improve the predictability of the regression equation, you can include only customers who meet one or more constraints on the customers of your training data set. For example, a constraint might be a condition such that the proportion of males and females in the training data set is equal to or greater than 20, or that a customer with a T-score value of zero or less in bone density is more than a customer with a T-score value of 0 or more. It may include. The description of the foregoing constraints is merely an example, and the present disclosure is not limited thereto.

When two variables are given, the processor 110 may predict the other variable by using one variable as an input of a regression equation, or may analyze the relationship between the two variables by calculating through the regression equation. According to another embodiment of the present disclosure, the processor 110 uses a multiple linear regression equation (ie, at least one of input data as an independent variable for regression analysis and a bone density data of the user as a dependent variable for regression analysis) , Regression). The regression equation may be an expression for correlation analysis between the independent variable and the dependent variable. For example, regression

일 수 있다. 전술한 회귀식의 독립 변수는 다른 독립 변수 항목이 더 포함될 수 있다. 전술한 회귀식은 상수를 더 포함할 수 있다. 예를 들어, 회귀식의 독립 변수는

일 수 있다. 회귀식의 a 내지 e는 각 독립 변수에 대한 계수일 수 있다. 회귀식의 a 내지 e는 각 독립 변수와 골밀도 데이터의 상관성을 나타내는 계수일 수 있다. 종속 변수(즉, 골밀도 데이터)와 상관 관계가 높은 독립 변수들의 계수 값은 상관 관계가 낮은 독립 변수들의 계수 값보다 큰 값을 가질 수 있다. 종속 변수(즉, 골밀도 데이터)와 상관 관계가 사전 결정된 값 이하인 경우(즉, 상관 관계가 낮은 경우) 회귀식의 독립 변수에서 제외될 수 있다. 전술한 회귀식의 멀티 임피던스 항목 값은, 다중 경로 임피던스에 관한 값 또는 다중 주파수 임피던스에 관한 값일 수 있다. 전술한 회귀식의 관계 정보는 다른 둘 이상의 독립 변수에 기초한 관계 정보를 포함할 수 있다. 회귀식은 전체 사용자에 대해 적용되는 식일 수도 있고, 연령대 별, 성별 별, 또는 골밀도 관련 질병 내력 유무에 기초하여 적용되는 식일 수도 있다. 전술한 회귀식에 대한 기재는 예시일 뿐이며, 본 개시는 이에 제한되지 않는다.

Can be. The independent variable of the aforementioned regression expression may further include other independent variable items. The above regression equation may further comprise a constant. For example, a regression independent variable

Can be. A to e of the regression equation may be coefficients for each independent variable. A to e of the regression equation may be coefficients representing correlation of each independent variable with bone density data. The coefficient value of the independent variables having a high correlation with the dependent variable (ie, bone density data) may have a value larger than that of the independent variables having a low correlation. If the correlation with the dependent variable (ie, bone density data) is below a predetermined value (ie, the correlation is low), it may be excluded from the independent variable of the regression equation. The above-described regression multi-impedance item value may be a value regarding multipath impedance or a value regarding multi-frequency impedance. The relationship information of the aforementioned regression equation may include relationship information based on two or more independent variables. The regression equation may be an expression applied to the entire user, or may be an expression applied based on age group, gender, or the presence of disease history related to bone density. The description of the above regression equation is merely an example, and the present disclosure is not limited thereto.

인 경우, 프로세서(110)는 실제 골밀도 값인

와 근사적으로 구한 골밀도 값인

의 오차(즉,

)의 제곱의 합(즉,

)이 최소가 되는 모델을 생성할 수 있다. 프로세서(110)는 복수의 학습 데이터(

)에 대하여 최소 제곱법을 만족하는 골밀도 측정 모델을 생성할 수 있다. 전술한 골밀도 측정 모델의 회귀식에 관한 기재는 예시일 뿐이며, 본 개시는 이에 제한되지 않는다.The processor 110 uses the learning input data of the customer included in the training data as the independent variable of the regression equation, and the learning bone density data of the customer included in the training data as the dependent variable of the regression equation, and depends on the independent variable of the regression equation. Coefficients representing the correlation of variables can be extracted. The processor 110 may generate a bone density measurement model based on the least squares method. The least square method may be a method of obtaining a model in which the sum of squares of the error of the value of the dependent variable and the value corresponding to the actual dependent variable is minimized. Regression Diet of Bone Mineral Density Model

If the processor 110 is a real bone density value

The approximate bone density value

Of error (i.e.

Sum of squares of squares (i.e.

You can create a model with)). The processor 110 includes a plurality of training data (

We can create a model for measuring bone density that satisfies the least square method. The description regarding the regression equation of the above-described bone density measurement model is only an example, and the present disclosure is not limited thereto.

(

))를 연산하여 골밀도 측정 모델의 회귀식에 대한 성능을 검증할 수 있다. 전술한 결정 계수 식에서, n은 테스트 데이터의 수일 수 있고,

는 테스트 데이터의 학습 생체 데이터를 회귀식의 독립 변수로 하여 도출된 종속 변수의 값일 수 있고,

는 테스트 데이터의 학습 골밀도 데이터 값일 수 있고,

는 테스트 데이터 세트에 포함된 하나 이상의 테스트 데이터의 학습 생체 데이터를 회귀식의 독립 변수로 하여 도출된 종속 변수의 값의 평균 값일 수 있다. 프로세서(110)는 학습된 골밀도 측정 모델의 결정 계수가 사전 결정된 값 이상인 경우(즉, 1에 가까운 값인 경우) 골밀도 측정 모델의 활성화를 결정할 수 있다. 전술한 성능 검증에 대한 기재는 예시일 뿐이며, 본 개시는 이에 제한되지 않는다.The processor 110 may use at least one learning data of the learning data set as test data. The test data is data corresponding to the training data, and may be data used to verify performance after the training of the model is completed. According to one embodiment of the performance verification of the bone density measurement model of the present disclosure, the processor 110 may verify the performance of the regression equation of the bone density measurement model using residual analysis. The residual is the difference between the value derived by the regression equation (that is, the value of the dependent variable derived from the test biometric data of the test data as an independent variable of the regression equation) and the actual value (ie, the learning bone density data of the test data). It can mean a car. The processor 110 may determine activation of the bone density measurement model when the residual of the learned bone density measurement model is equal to or less than a predetermined value (that is, a value that converges to zero). The processor 110 may determine deactivation of the bone density measurement model when the residual of the learned bone density measurement model is equal to or greater than a predetermined value (ie, a value far from zero). According to another embodiment of the performance verification of a bone density measurement model of the present disclosure, the processor 110 may determine a coefficient of determination (

(

) Can be used to verify the performance of the regression equation of the BMD model. In the above determination coefficient formula, n may be the number of test data,

May be the value of the dependent variable derived from the learning biometric data of the test data as an independent variable of the regression equation,

May be a learning bone density data value of the test data,

May be an average value of values of the dependent variable derived by using the learning biometric data of one or more test data included in the test data set as an independent variable of the regression equation. The processor 110 may determine the activation of the bone density measurement model when the determined coefficient of the learned bone density measurement model is greater than or equal to a predetermined value (ie, a value close to 1). The above description of the performance verification is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the processor 110 may generate bone density change information of a user using a bone density measurement model. More specifically, the processor 110 may output the bone density change information of the user by processing the input data set related to the user as an input of the bone density measurement model. In this case, the bone density change information may be generated based on the viewpoint data included in each of the one or more input data of the user as information on the bone density change amount of the user. For example, when the biometric data included in the input data set is measured in February 2018 and April 2018, the corresponding biometric data is measured in February 2028 and April 2018 based on the measured biometric data. Bone density change information can be generated. The description of the specific time point of the above-described input data is only an example, and the present disclosure is not limited thereto.

In addition, the processor 110 may generate bone density guide information based on the bone density change information. More specifically, when the bone density change amount included in the bone density change information is out of a predetermined threshold change amount, the processor 110 determines a time point at which the bone density change amount is out of a predetermined threshold change amount, and provides health-health data corresponding to the time point. It can be received from the external server 200. Referring to FIG. 8, the computing device 100 may generate bone density guide information based on bone density change information. More specifically, the computing device 100 may determine a time point at which the bone density change amount included in the bone density change information deviates from the predetermined threshold change amount. In this case, the predetermined threshold change amount may be generated based on the biometric information of the user. In more detail, the threshold change amount may be generated based on at least one of a user's gender, age, height, and weight. Accordingly, each user may have a different threshold change amount. For example, when the threshold change amount 510 of a specific user has a range as shown in FIG. 8, the computing device 100 determines when the bone density change amount of the specific user deviates from the threshold change amount 510 (520). ) Is September. In addition, the computing device 100 may receive health examination data corresponding to the time point from the external server 200. In this case, the external server 200 may be at least one of a government server and a medical server. In addition, the computing device 100 may generate the bone density guide information based on the received health examination data of the user when the amount of change in bone density of the user deviates from the predetermined threshold change amount. In detail, referring to FIG. 8, when the amount of change in bone density of the user deviates from the predetermined threshold change amount 510 (520), the medical examination data of the user at the corresponding time may be analyzed. That is, the computing device 100 may determine the factors that influenced the bone density of the user by analyzing the user's health examination data for the corresponding time (time point outside the predetermined threshold change amount). For example, when the health examination data includes information about the pregnancy of the user in September (a time point outside the predetermined threshold change amount) of the user, the computing device 100 may influence the factor of the bone density of the user. Determining that the pregnancy is to generate and provide the bone density guide information based on the determination to the user. As described above, the detailed description of the factors affecting the bone density is only an example, and the present disclosure is not limited thereto.

That is, the computing device 100 generates and provides bone density guide information for a factor in which the user's past bone density has changed, so that the user can determine a factor that affects his / her bone density, so that future management of bone density can be further managed. Can be facilitated.

In addition, the processor 110 may generate bone density prediction information based on the bone density change information. In this case, the bone density prediction information may be generated by matching a time point corresponding to the future bone density of the user. Accordingly, the user may be provided with BMD prediction information about a future time point through the computing device 100, so that the user may more realistically recognize the current state of his / her BMD and more systematically manage the BMD in the future. Can be.

According to an embodiment of the present disclosure, the network unit 130 may include a transmitter and a receiver. The network unit 130 may include a wired / wireless internet module for network connection. Wireless Internet technologies may include Wireless LAN (Wi-Fi), Wireless Broadband (Wibro), World Interoperability for Microwave Access (Wimax), High Speed Downlink Packet Access (HSDPA), and the like. As a wired Internet technology, a digital subscriber line (XDSL), fibers to the home (FTTH), power line communication (PLC), and the like may be used.

In addition, the network unit 130 may include a short range communication module, and may transmit / receive data to and from an electronic device including a short range communication module and located at a relatively short distance with the service processing apparatus. As a short range communication technology, Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, and the like may be used. In one embodiment of the present disclosure, the network unit 130 may detect the connection state of the network and the transmission and reception speed of the network. The data received through the network unit 130 may be stored through the memory 120 or transmitted to other electronic devices in a short distance through a short range communication module.

In addition, the network unit 130 may transmit / receive data to another computing device, a server, and the like for outputting the bone density change information according to an embodiment of the present disclosure. The network unit 130 may transmit / receive data necessary for an embodiment of the present disclosure, such as body composition data, biometric data, impedance data, and bone density data, to another computing device, a server, or the like. In addition, the network unit 130 may enable communication between a plurality of computing devices so that learning of the bone density measurement model may be distributed in each of the plurality of computing devices. The network unit 130 may enable communication between a plurality of computing devices to perform distributed processing of bone density data calculation using a bone density measurement model.

The memory 120 may store a computer program for performing a method for measuring bone density according to an embodiment of the present disclosure, and the stored computer program may be read and driven by the processor 110.

The memory 120 according to embodiments of the present disclosure may store a program for the operation of the processor 110, and temporarily or permanently store input / output data (eg, bone density data, biometric data, etc.). It may be. The memory 120 may store data regarding a display and sound. The memory 120 includes a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (for example, SD or XD memory), RAM (Random Access Memory, RAM), Static Random Access Memory (SRAM), Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Programmable Read-Only Memory (PROM), Magnetic Memory, Magnetic At least one type of storage medium may be included. The description of the above-described memory is only an example, and the present disclosure is not limited thereto.

3 is a schematic diagram illustrating a network function associated with one embodiment of the present disclosure.

Throughout this specification, computational models, neural networks, network functions, neural networks may be used in the same sense. A neural network may consist of a set of interconnected computing units, which may generally be referred to as "nodes." Such "nodes" may be referred to as "neurons". The neural network comprises at least one node. The nodes (or neurons) that make up the neural networks may be interconnected by one or more "links".

Within a neural network, one or more nodes connected via a link may form a relationship of input node and output node relatively. The concept of an input node and an output node is relative; any node in an output node relationship for one node may be in an input node relationship in relation to another node, and vice versa. As mentioned above, the input node to output node relationship can be created around the link. More than one output node can be connected to a single input node via a link, and vice versa.

In an input node and output node relationship connected via one link, the output node may be determined based on data input to the input node. Here, the node interconnecting the input node and the output node may have a weight. The weight may be variable, and may be varied by the user or algorithm in order for the neural network to perform the desired function. For example, when one or more input nodes are interconnected by each link to one output node, the output node is set to values input to input nodes connected to the output node and to a link corresponding to each input node. The output node value may be determined based on the weight.

As described above, a neural network is formed by interconnecting one or more nodes through one or more links to form an input node and an output node relationship within the neural network. The characteristics of the neural network may be determined according to the number of nodes and links in the neural network, the relationship between the nodes and the links, and the value of the weight assigned to each of the links. For example, if there are the same number of nodes and links, and there are two neural networks with different weight values between the links, the two neural networks may be recognized as different from each other.

The neural network may comprise one or more nodes. Some of the nodes that make up the neural network may construct one layer based on distances from the original input node, for example, a set of nodes with a distance n from the original input node, You can configure n layers. The distance from the original input node may be defined by the minimum number of links that must pass to reach the node from the original input node. However, the definition of such a layer is arbitrary for explanation, and the order of the layer in the neural network may be defined in a manner different from that described above. For example, a layer of nodes may be defined by distance from the final output node.

The initial input node may refer to one or more nodes to which data is directly input without going through a link in relation to other nodes among the nodes in the neural network. Alternatively, in a neural network network, in a relationship between nodes based on a link, it may mean nodes having no other input nodes connected by a link. Similarly, the final output node may refer to one or more nodes that do not have an output node in relation to other nodes of the nodes in the neural network. Also, the hidden node may refer to nodes constituting a neural network other than the first input node and the last output node. The neural network according to an embodiment of the present disclosure may have the same number of nodes in the input layer as the number of nodes in the output layer, and the number of nodes decreases and then increases again as the number of nodes goes from the input layer to the hidden layer. Can be. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer is smaller than the number of nodes in the output layer, and the number of nodes decreases as the node progresses from the input layer to the hidden layer. have. In addition, the neural network according to another embodiment of the present disclosure may have a larger number of nodes in the input layer than the number of nodes in the output layer, and the number of nodes increases as the number of nodes increases from the input layer to the hidden layer. Can be. The neural network according to another embodiment of the present disclosure may be a neural network in a combined form of the neural networks described above.

A deep neural network (DNN) may refer to a neural network including a plurality of hidden layers in addition to an input layer and an output layer. Deep neural networks can be used to identify latent structures of data. In other words, you can identify the potential structures of photos, texts, videos, voices, and music (e.g., what objects are in the photos, what the content and emotions of the text are, and what the content and emotions of the voice are). . Deep neural networks include convolutional neural networks (CNNs), recurrentneural networks (RNNs), auto encoders, Generic Adversarial Networks (GAN), restricted boltzmann (RBM) machine), deep belief network (DBN), Q network, U network, Siamese network and the like. The description of the deep neural network described above is merely an example and the present disclosure is not limited thereto.

The neural network may be trained in at least one of supervised learning, unsupervised learning, and semi supervised learning. Training of neural networks is intended to minimize errors in the output. In the neural network learning, the neural network errors are inputted from the output layer of the neural network in order to repeatedly input the training data into the neural network, calculate the neural network output and target errors for the training data, and reduce the errors. The process of updating the weight of each node of the neural network by backpropagation in the direction. In the case of teacher learning, the learning data using the correct answer is labeled in each learning data (ie, the labeled learning data), and in the case of the comparative learning, the correct answer may not be labeled in each learning data. That is, for example, the learning data in the case of teacher learning regarding data classification may be data in which a category is labeled in each of the learning data. The labeled training data is input to the neural network, and an error can be calculated by comparing the label of the training data with the output (category) of the neural network. As another example, in the case of non-comparative learning on data classification, an error may be calculated by comparing learning data as an input with a neural network output. The calculated error is propagated backward in the neural network (ie, the direction from the output layer to the input layer), and the connection weight of each node of each layer of the neural network may be updated according to the reverse propagation. The connection weight of each node to be updated may be changed according to a learning rate. The computation of the neural network for the input data and the backpropagation of the errors can constitute a learning cycle. The learning rate may be applied differently according to the number of repetitions of the learning cycle of the neural network. For example, in the early stages of neural network learning, high learning rates can be used to allow the neural network to quickly achieve a certain level of performance, increasing efficiency, and lower learning rates for later learning.

In the learning of neural networks, in general, the training data may be a subset of the actual data (i.e., the data to be processed using the trained neural network), thus reducing the error for the training data but not the error for the actual data. There may be an increasing learning cycle. Overfitting is a phenomenon in which an error about the actual data is increased by excessively learning the training data. For example, a neural network that learns a cat by showing a yellow cat may not recognize that the cat is a cat other than a yellow cat. Overfitting can act as a cause of increased errors in machine learning algorithms. Various optimization methods can be used to prevent such overfitting. In order to prevent overfitting, a method of increasing learning data, regulating, or dropping out of a node of a network in the course of learning may be applied.

Figure 4 is an exemplary view showing a bone density measurement model associated with an embodiment of the present disclosure.

A learning method in a bone density measurement model according to an embodiment of the present disclosure will be described. In this example, one or more hidden layers may be included between the hidden layer 1 440 and the hidden layer 2 450, and the one or more hidden layers may be omitted.

The computing device 100 may generate a bone density measurement model that includes one or more network functions 400. The network function 400 may include one input layer 430, one or more hidden layers, and one output layer 460.

The computing device 100 may input training biometric data to the network function 400 of the bone density measurement model. Each item of training biometric data may be input to each input node included in the input layer 430 of the network function 400 of the bone density measurement model. For example, the item value for height 179 cm is the first input node 401, the item value for weight 78 kg is the second input node 402, the item value for age 32 is the third input node 403, The item value for the gender male may be input to the fourth input node 404 and the item value for the multi impedance 600 Ω to the fifth input node 405. The description of the above-described item value is only an example, and the present disclosure is not limited thereto.

The computing device 100 may calculate each of the item values input to the input node included in the input layer 430 of the network function 400 with the weights set in the link connected to the input node and propagate them to the hidden layer. . For example, the first hidden node 420 included in the hidden layer 1 440 is a value obtained by calculating a value transmitted to the first input node 401 and a first weight 411, and a second input node 402. ), The value passed to the third input node 403 and the value passed to the third input node 403, the value passed to the fourth input node 404, and the fourth weight The calculated value, the value transmitted to the fifth input node 405, and the value calculated by the fifth weight may be received. For example, the first hidden node 420 included in the hidden layer 1 440 is a value obtained by multiplying the value transmitted to the first input node 401 by the first weight 411, and the second input node 402. A value multiplied by a second weighted value, a value multiplied by a third weighted value and a value passed to a third input node 403, a value multiplied by a fourth weighted value, and a value passed to a fourth input node 404, The sum of the value multiplied by the fifth weighted value and the value transmitted to the fifth input node 405 may be received. The description of the above operation is merely an example, and the present disclosure is not limited thereto.

The training biometric data of the network function 400 may be propagated from the input layer 430 to the output layer 460 through the hidden layer 1 440 and the hidden layer 2 450. The weight of the network function 400 may be adjusted based on an error between bone density data (ie, output) and learning bone density data (ie, correct answer), which are output values at the output node 462 included in the output layer 460. . Processor 110 passes from output layer 460 of network function 300 to input layer 430 via one or more hidden layers (e.g., in order of hidden layer2 450, then hidden layer1 440). While propagating the error, the weights set for each link may be updated (for example, after adjusting the weight of W2 (1,1) 431), the weight of W1 (1,1) 411 may be adjusted.

A method for generating bone density data using a trained bone density measurement model according to an embodiment of the present disclosure will be described.

The computing device 100 may input each item value of items included in the biometric data of the user to each input node included in the input layer 430 of the network function 400. For example, the computing device 100 may input a value corresponding to 176 cm, which is an item value of a key, of biometric data to the first input node 401 of the input layer 430. The processor 110 weights the value input to the input layer 430 of the network function 400 (in this example, the first weight W1 (1,1) 411) and the second weight W2 (1,1 Output node 462 included in output layer 460 via one or more hidden nodes (in this example, including hidden layer 1 440 and hidden layer 2 450). Can propagate. The computing device 100 may send bone density data, which is an output value of the output node 462, through the network unit 130, store in the memory 120, or transmit the bone density data to display means (eg, a display). The above description of the method for generating bone density data is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, bone density data may be generated by using biometric data of a user as an input of a trained bone density measurement model.

5 is an exemplary graph applying a bone density measurement model associated with an embodiment of the present disclosure.

FIG. 5 is an exemplary graph showing a graph comparing bone density data using a bone density measurement model including a regression equation and a bone density measurement method DEXA (Dual Energy X-ray Absorptiometry) according to another embodiment of the present disclosure. . The x-axis of the graph is a user's bone density measured using DEXA, a bone density measurement method, and the y-axis of the graph is a user's bone density measured using a bone density measurement model including the above regression equation. The user's bone density values measured using DEXA and the user's bone density values calculated using a bone density measurement model including a regression equation are plotted on a graph. A graph in the form of a scatter plot can visually show the relationship between the two values. In a graph showing the correlation in the form of a scatter plot, the graph may be drawn in the upward direction. In the graph showing the correlation in the form of scatter plot, the graph may be drawn in the downward direction when the correlation is negative. The correlation obtained through the graph is 0.523, and the output of bone density data using a DEXA and the output of bone density data using a bone density measurement model including a regression equation are highly correlated. Accordingly, it can be seen that the bone density measurement model including the regression equation according to another embodiment of the present disclosure has similar performance to the bone density data output when compared to DEXA which is commonly used in hospitals and the like. Bone density measurement model including a regression equation according to another embodiment of the present disclosure, it is possible to measure the bone density of the whole body within a shorter time than DEXA, less error due to the user's skill or posture changes, periodic equipment management Can be more economical because is not needed.

6 is an exemplary graph applying a bone density measurement model associated with an embodiment of the present disclosure.

FIG. 6 is an exemplary graph illustrating a Receiver Operating Characteristic (ROC) curve using a bone density measurement model including a regression equation according to another embodiment of the present disclosure. In this graph showing the ROC curve, the x-axis is 1-specificity, and the bone density measurement model is determined to be free of disease (in this embodiment, the T-score is determined to be a disease from a user with osteopenia having -1.0 or less. The y-axis is the sensitivity, and the bone density measurement model indicates the percentage of users who actually have a disease. In this example, a high sensitivity of 80% and specificity of 70% were obtained. The area under the graph in the ROC curve is called AUC (Area Under the Curve). The larger the AUC, the more accurate the model. In this embodiment, the AUC value for the ROC curve is 0.847, indicating that the bone density measurement model is a very accurate model.

FIG. 7 is a diagram for comparing data values of bone mineral density measurement models and other bone mineral density measurement devices according to another embodiment of the present disclosure.

FIG. 7 is a table illustrating values comparing bone density data using DEXA, which is a method of measuring bone density with bone density measuring apparatuses of the ultrasound method. When compared with DEXA, which is a method for measuring bone density of ultrasound-type bone density measuring apparatus, the highest correlation is 0.526, when compared with bone density measurement model including a regression equation and bone density measurement method DEXA according to another embodiment of the present invention. It has a value similar to that of 0.523. That is, it can be seen that the bone density measurement model including the regression equation according to another embodiment of the present disclosure has higher or similar performance than the bone density measurement apparatus using ultrasound. The maximum value of AUC of the ROC curve of the ultrasonic bone density measuring apparatus is 0.75. Therefore, it can be seen that the bone density measurement model of the present invention is a model capable of measuring more accurate bone density data when compared with the AUC value of 0.847 of the bone density measurement model including the regression equation according to another embodiment of the present invention.

9 illustrates a flow chart for providing bone density change information associated with one embodiment of the present disclosure.

According to an embodiment of the present disclosure, the computing device 100 may receive a user's body composition data set from the external server 200 (610). In this case, the body composition data set of the user acquired by the computing device 100 is information analyzing the components constituting the human body of the user, for example, the user's weight, lean body mass, muscle mass, body water volume, intracellular water content, body It may include information about the lactate index and body fat percentage. As described above, the specific description of the body composition data of the user is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the computing device 100 may generate an input data set including the biometric data set and the impedance data set by extracting the biometric data set and the impedance set based on the usage body composition data set. (620). In this case, the biometric data set may be a set of biometric data including height, gender, weight, and age of the user, and the impedance data set may be a set of impedance data including multi-impedance of the user. In addition, multi-impedance may be applied to at least a portion of the user's body for measurement of multipath impedance and impedance of at least a portion of the user's body, which is an impedance associated with a path through which current flows from one electrode to the other of two or more electrodes. It may include a multi-frequency impedance which is one or more frequency-specific impedance of the applied voltage. In detail, the multipath impedance may include a path connecting two electrodes provided in the body composition measuring device to the user's left hand and right hand, respectively, or a path connecting the two electrodes to the user's left and right foot, respectively. That is, the multipath impedance may be impedance data measured through a change in a region where two electrodes are connected to a user's body, and may include impedance data measured through at least one path. In addition, the multi-frequency impedance may be an impedance value measured by changing a frequency on the same path. For example, when two electrodes provided in the body composition measuring device are connected to a user's left hand and right hand, when the frequency of the voltage applied to the user's body is applied at 50 KHz, the measured impedance data and the 250 KHz are applied. Information on the multi-frequency impedance may be generated based on the measured impedance data. That is, the impedance data used to calculate the bone density in the present disclosure includes multipath impedance and multi-frequency impedance, rather than simply measured impedance information, so that more accurate bone density can be calculated.

According to an embodiment of the present disclosure, the computing device 100 may generate the bone density change information of the user by calculating an input data set related to the user by using the bone density measurement model (630). In this case, the bone density change information may be generated based on the viewpoint data included in each of the one or more input data of the user as information on the bone density change amount of the user. For example, when the biometric data included in the input data set is measured in February 2018 and April 2018, the corresponding biometric data is measured in February 2028 and April 2018 based on the measured biometric data. Bone density change information can be generated. The description of the specific time point of the above-described input data is only an example, and the present disclosure is not limited thereto.

In addition, the computing device 100 may generate bone density guide information based on the bone density change information. More specifically, when the bone density change amount included in the bone density change information is out of a predetermined threshold change amount, the computing device 100 determines a time point at which the bone density change amount is out of a predetermined threshold change amount, and health-health data corresponding to the time point. Can be received from the external server 200. Referring to FIG. 8, the computing device 100 may generate bone density guide information based on bone density change information. More specifically, it may be determined that the bone density change amount included in the bone density change information deviates from the predetermined threshold change amount. In this case, the predetermined threshold change amount may be generated based on the biometric information of the user. In more detail, the threshold change amount may be generated based on at least one of a user's gender, age, height, and weight. Accordingly, each user may have a different threshold change amount. That is, the computing device 100 generates and provides bone density guide information on a factor in which the user's past bone density has changed, so that the user can determine a factor influencing his / her bone density, so that future management of the bone density can be further performed. Can be facilitated.

In addition, the computing device 100 may generate bone density prediction information based on the bone density change information. In this case, the bone density prediction information may be generated by matching a time point corresponding to the future bone density of the user. Accordingly, the user may be provided with BMD prediction information about a future time point through the computing device 100, so that the user may more realistically recognize the current state of his / her BMD and more systematically manage the BMD in the future. Can be.

10 illustrates a flow chart for extracting biometric data and impedance data associated with one embodiment of the present disclosure.

According to an embodiment of the present disclosure, the computing device 100 may perform at least one of the following steps to extract the biometric data and the impedance data based on the body composition data.

According to an embodiment of the present disclosure, when the biometric data and the impedance data match the body component data, the computing device 100 may extract the impedance data and the biometric data matched to the body component data (710).

In addition, when the biometric data does not match the body composition data, the computing device 100 may receive health check data corresponding to the body composition data, and extract the bio data corresponding to the measurement point of the body composition from the health check data. 720.

In addition, when the impedance data does not match the body composition data, the computing device 100 may invert the impedance data using the body composition data and the biometric data matched to the body composition data, and extract the inverted impedance data ( 730).

11 shows a brief general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

Although the present disclosure has been described above generally with respect to computer executable instructions that may be executed on one or more computers, those skilled in the art will appreciate that the present disclosure may be implemented in combination with other program modules and / or as a combination of hardware and software. will be.

Generally, program modules include routines, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. In addition, those skilled in the art will appreciate that the methods of the present disclosure may include uniprocessor or multiprocessor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, and the like (each of which And other computer system configurations, including one or more associated devices.

The described embodiments of the present disclosure can also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

Computers typically include a variety of computer readable media. Any medium that can be accessed by a computer can be a computer readable medium, which can be volatile and nonvolatile media, transitory and non-transitory media, removable and non-transitory media. Removable media. By way of example, and not limitation, computer readable media may comprise computer readable storage media and computer readable transmission media. Computer-readable storage media are volatile and nonvolatile media, temporary and non-transitory media, removable and non-removable implemented in any method or technology for storing information such as computer readable instructions, data structures, program modules or other data. Media. Computer storage media may include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROMs, digital video disks or other optical disk storage devices, magnetic cassettes, magnetic tapes, magnetic disk storage devices or other magnetic storage devices, Or any other medium that can be accessed by a computer and used to store desired information.

Computer-readable transmission media typically embody computer readable instructions, data structures, program modules or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and the like. Includes all information delivery media. The term modulated data signal refers to a signal that has one or more of its characteristics set or changed to encode information in the signal. By way of example, and not limitation, computer readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, or other wireless media. Combinations of any of the above should also be included within the scope of computer readable transmission media.

An exemplary environment 1100 is illustrated that implements various aspects of the present disclosure, including a computer 1102, which includes a processing unit 1104, a system memory 1106, and a system bus 1108. do. System bus 1108 connects system components, including but not limited to system memory 1106, to processing unit 1104. Processing unit 1104 may be any of a variety of commercially available processors. Dual processor and other multiprocessor architectures may also be used as the processing unit 1104.

The system bus 1108 may be any of several types of bus structures that may be further interconnected to a memory bus, a peripheral bus, and a local bus using any of a variety of commercial bus architectures. System memory 1106 includes read only memory (ROM) 2110 and random access memory (RAM) 2112. The basic input / output system (BIOS) is stored in nonvolatile memory 2110, such as ROM, EPROM, EEPROM, etc., and the BIOS provides a basic aid for transferring information between components in the computer 1102, such as during startup. Contains routines. RAM 2112 may also include high speed RAM, such as static RAM for caching data.

Computer 1102 also includes an internal hard disk drive (HDD) 2114 (eg, EIDE, SATA). The internal hard disk drive 2114 may also be configured for external use within a suitable chassis (not shown). ), Magnetic floppy disk drive (FDD) 2116 (eg, for reading from or writing to removable diskette 2118), and optical disk drive 1120 (eg, CD-ROM disk) 1122 or for reading from or writing to other high capacity optical media such as DVD). The hard disk drive 2114, the magnetic disk drive 2116, and the optical disk drive 1120 are connected to the system bus 1108 by the hard disk drive interface 1124, the magnetic disk drive interface 1126, and the optical drive interface 1128, respectively. ) Can be connected. Interface 1124 for external drive implementation includes at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

These drives and their associated computer readable media provide nonvolatile storage of data, data structures, computer executable instructions, and the like. In the case of computer 1102, drives and media correspond to storing any data in a suitable digital format. Although the description of computer readable media above refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those skilled in the art will appreciate zip drives, magnetic cassettes, flash memory cards, cartridges, and the like. Other types of media readable by the computer, etc. may also be used in the exemplary operating environment and it will be appreciated that any such media may include computer executable instructions for performing the methods of the present disclosure.

Multiple program modules may be stored in the drive and RAM 2112, including operating system 2130, one or more application programs 2132, other program modules 2134, and program data 2136. All or a portion of the operating system, applications, modules and / or data may also be cached in RAM 2112. It will be appreciated that the present disclosure may be implemented in various commercially available operating systems or combinations of operating systems.

A user may enter commands and information into the computer 1102 via one or more wired / wireless input devices, such as a keyboard 2138 and a mouse 1140. Other input devices (not shown) may include a microphone, IR remote control, joystick, game pad, stylus pen, touch screen, and the like. These and other input devices are often connected to the processing unit 1104 through an input device interface 1142 that is connected to the system bus 1108, but the parallel port, IEEE 1394 serial port, game port, USB port, IR interface, Etc. can be connected by other interfaces.

A monitor 1144 or other type of display device is also connected to the system bus 1108 via an interface such as a video adapter 1146. In addition to the monitor 1144, the computer generally includes other peripheral output devices (not shown) such as speakers, printers, and the like.

Computer 1102 may operate in a networked environment using logical connections to one or more remote computers, such as remote computer (s) 1148, via wired and / or wireless communications. Remote computer (s) 1148 can be a workstation, computing device computer, router, personal computer, portable computer, microprocessor-based entertainment device, peer device, or other conventional network node, and typically is associated with computer 1102. Although many or all of the components described above are included, for simplicity, only memory storage 1150 is shown. The logical connections shown include wired / wireless connections to a local area network (LAN) 1152 and / or a larger network, such as a telecommunications network (WAN) 1154. Such LAN and WAN networking environments are commonplace in offices and businesses, facilitating enterprise-wide computer networks such as intranets, all of which may be connected to worldwide computer networks, such as the Internet.

When used in a LAN networking environment, the computer 1102 is connected to the local network 1152 via a wired and / or wireless communication network interface or adapter 1156. Adapter 1156 may facilitate wired or wireless communication to LAN 1152, which also includes a wireless access point installed therein for communicating with wireless adapter 1156. When used in a WAN networking environment, the computer 1102 may include a modem 1158, connect to a communications computing device on the WAN 1154, or establish communications over the WAN 1154, such as over the Internet. Other means. The modem 1158, which may be an internal or external and wired or wireless device, is connected to the system bus 1108 via the serial port interface 1142. In a networked environment, program modules or portions thereof described with respect to computer 1102 may be stored in remote memory / storage device 1150. It will be appreciated that the network connections shown are exemplary and other means of establishing a communications link between the computers can be used.

Computer 1102 is associated with any wireless device or entity disposed and operating in wireless communication, such as a printer, scanner, desktop and / or portable computer, portable data assistant, communications satellite, wireless detectable tag. Communicate with any equipment or location and telephone. This includes at least Wi-Fi and Bluetooth wireless technology. Thus, the communication can be a predefined structure as in a conventional network or simply an ad hoc communication between at least two devices.

Wireless Fidelity (Wi-Fi) allows you to connect to the Internet without wires. Wi-Fi is a wireless technology such as a cell phone that allows a device, for example, a computer, to transmit and receive data indoors and outdoors, ie anywhere within the coverage area of a base station. Wi-Fi networks use a wireless technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, high-speed wireless connections. Wi-Fi may be used to connect computers to each other, to the Internet, and to a wired network (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in unlicensed 2.4 and 5 GHz wireless bands, for example, at 11 Mbps (802.11a) or 54 Mbps (802.11b) data rates, or in products that include both bands (dual band). have.

Those skilled in the art will appreciate that information and signals may be represented using any of a variety of different technologies and techniques. For example, data, instructions, instructions, information, signals, bits, symbols, and chips that may be referenced in the above description may include voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields. Or particles, or any combination thereof.

One of ordinary skill in the art of the disclosure will appreciate that the various illustrative logical blocks, modules, processors, means, circuits and algorithm steps described in connection with the embodiments disclosed herein may be implemented in electronic hardware, It will be appreciated that for purposes of the present invention, various forms of program or design code, or combinations thereof, may be implemented. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and design constraints imposed on the overall system. One skilled in the art of the present disclosure may implement the described functionality in various ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

The various embodiments presented herein may be embodied in a method, apparatus, or article of manufacture using standard programming and / or engineering techniques. The term "article of manufacture" includes a computer program, carrier, or media accessible from any computer-readable device. For example, computer-readable media may include magnetic storage devices (eg, hard disks, floppy disks, magnetic strips, etc.), optical discs (eg, CDs, DVDs, etc.), smart cards, and flash memory. Devices, such as, but not limited to, EEPROM, cards, sticks, key drives, and the like. In addition, various storage media presented herein include one or more devices and / or other machine-readable media for storing information.

It is to be understood that the specific order or hierarchy of steps in the processes presented is an example of exemplary approaches. Based upon design priorities, it is understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of the present disclosure. The accompanying method claims present elements of the various steps in a sample order, but are not meant to be limited to the specific order or hierarchy presented.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure should not be limited to the embodiments set forth herein but should be construed in the broadest scope consistent with the principles and novel features set forth herein.

Claims (14)

A computer program stored in a computer readable storage medium containing encoded instructions, wherein the computer program, when executed by one or more processors of a computer system, causes the one or more processors to perform the following operations: The actions are:
Receiving a body composition data set of a user;
Extracting a biometric data set and an impedance data set based on the body composition data set of the user to generate an input data set including the biometric data set and the impedance data set; And
Generating bone density change information of the user by calculating an input data set related to the user using a bone density measurement model;
Including,
Computer program stored on a computer readable storage medium.
The method of claim 1,
The operation of extracting the biometric data set and the impedance data set based on the body composition data set of the user and generating an input data set includes:
Determining whether at least one of impedance data and biometric data is matched with body component data included in the body component data set;
Extracting impedance data and biometric data based on the determination; And
Generating a biometric data set including the biometric data and an impedance data set including the impedance data;
Including,
Computer program stored on a computer readable storage medium.
The method of claim 2,
Extracting the biometric data and the impedance data based on the determination,
Extracting the impedance data and the biometric data matched with the body component data when the biometric data and the impedance data match the body component data; And
Receiving the medical examination data corresponding to the body component data when the biometric data does not match the body component data, and extracting the biological data corresponding to the measurement time point of the body component data from the medical examination data;
Including at least one operation of,
Computer program stored on a computer readable storage medium.
The method of claim 1,
The bone density measurement model,
Generated through at least one of machine learning and regression analysis,
Computer program stored on a computer readable storage medium.
The method of claim 4, wherein
The machine learning,
Receive the bone density data set of the user, match each input data included in the input data set with bone density data included in the bone density data set to generate a labeled learning data set, and generate the labeled learning data set By generating the bone density measurement model,
Computer program stored on a computer readable storage medium.
The method of claim 5, wherein
The bone density measurement model,
One or more network functions, each of the one or more network functions including at least one of an input layer, one or more hidden layers, and an output layer, the input layer comprising one or more input nodes, and the one or more hidden layers Each comprising one or more hidden nodes, and the output layer comprises one or more output nodes, and each node included in each layer is each connected via a link with one or more nodes of another layer, the respective links Is weighted,
Computer program stored on a computer readable storage medium.
The method of claim 4, wherein
The regression analysis,
Receiving the bone density data set of the user, determining at least one of impedance data and biometric data included in the input data set as an independent variable for regression analysis, determining the bone density data set as a dependent variable for regression analysis, and Generate a regression equation for correlation analysis between the independent variable and the dependent variable, generate a training data set by matching the learning bone density data set of the user to the input data set as a dependent variable, and generate the training data set. By using the derivation coefficient of the regression equation, to generate the bone density measurement model,
Computer program stored on a computer readable storage medium.
The method of claim 7, wherein
The independent variable,
At least one of the user's height, weight, age and multi-impedance,
Computer program stored on a computer readable storage medium.
The method of claim 8,
The multi impedance is,
The multipath impedance, which is the impedance associated with the path of current flow from one electrode to the other of the two or more electrodes, and the voltage applied to at least a portion of the user's body for measuring impedance to at least a portion of the user's body. Including a multi-frequency impedance, which is one or more frequency-specific impedance,
Computer program stored on a computer readable storage medium.
The method of claim 1,
The bone density change information,
Data about the change in bone density of the user, which is generated based on the viewpoint data included in each of the one or more input data of the user,
Computer program stored on a computer readable storage medium.
The method of claim 1,
Generating bone density guide data based on the bone density change information;
More, and
The bone density guide data,
When the bone density change amount included in the bone density change information is out of a predetermined threshold change amount, it is determined that the bone density change amount is out of a predetermined threshold change amount, the health examination data corresponding to the time point is received, and the received health Which is data generated based on examination data,
Computer program stored on a computer readable storage medium.
The method of claim 1,
Generating bone density prediction information based on the bone density change information;
More,
The bone density prediction information,
The time point corresponding to the future prediction bone density is generated by matching,
Computer program stored on a computer readable storage medium.
A method for providing bone density change information performed in one or more processors of a computing device, the method comprising:
Receiving a set of body composition data of a user at the processor;
Extracting, by the processor, a biometric data set and an impedance data set based on the body composition data set of the user to generate an input data set including the biometric data set and the impedance data set; And
Generating, by the processor, a bone density change information of the user by calculating an input data set related to the user using a bone density measurement model;
Containing,
A method for providing bone density change information performed in one or more processors of a computing device.
A computing device that provides bone density change information,
A processor including one or more cores;
A memory storing program codes executable in the processor; And
A network unit for transmitting and receiving data to and from a user terminal and an external server;
Including, and
The processor,
Receiving a body composition data set of a user, extracting a biometric data set and an impedance data set based on the body composition data set of the user, generating an input data set including the biometric data set and the impedance data set, and generating a bone density measurement model. To calculate the input data set related to the user to generate bone density change information of the user,
Computing device providing bone density change information.

Images