KR20230076349A - System for trading medical data using non-fungible token - Google Patents

Abstract

Disclosed is a system for trading medical data using a non-fungible token. The present invention may comprise: a first terminal which generates medical data of a first user; a second terminal which generates selection data for a second user; and a server which provides the selection data to the first terminal, receives consent data corresponding to the selection data from the first terminal, and provides the second terminal with rights to access the medical data based on the consent data. The server may generate a first metahuman corresponding to the first user, generate virtual view image data according to the field of view of the first metahuman, and transmit the generated virtual view image data to the first terminal. The selection data may include the second user's purchase intention information and payment information for the medical data, and the information may correspond to purchase proposal information provided by the first metahuman. According to the present invention, users who are subject to medical data can directly trade their medical data.

Description

Medical data trading system using non-fungible token {SYSTEM FOR TRADING MEDICAL DATA USING NON-FUNGIBLE TOKEN}

The present invention relates to a medical data transaction system using a non-fungible token. More specifically, it relates to a medical data transaction system in which a user participates in a medical data block chain as one NFT and directly sells medical data about his or her medical records to other institutions and receives compensation.

Currently, with the development of artificial intelligence technology, big data technology that extracts useful information by processing a lot of data is attracting attention.

In the case of face recognition, artificial intelligence technology has already reached the level of finding wanted criminals in real time among various people, and in the case of voice recognition, it has reached the level of controlling home appliances through words, and in the case of the pharmaceutical industry Artificial intelligence is being applied for efficient drug development, and in the case of the military field, artificial intelligence is being applied to robots that perform dangerous missions instead of humans.

Big data technology is also being applied in various forms to maximize sales and increase advertising effects by analyzing products that are popular by time and season thanks to the development of artificial intelligence technology.

Meanwhile, in the medical field, the aforementioned artificial intelligence technology and big data technology are attracting attention as technologies for medical diagnosis and prediction.

Specifically, when a sufficient amount of medical data and related biometric data such as respiration, heart rate, blood pressure, and body temperature are sufficiently secured, and big data technology and artificial intelligence technology that are already being used are applied, diagnosis and It is considered that not only treatment but also prediction and prevention of diseases that may occur in the future are possible.

However, in the current medical field, it is difficult to realize the aforementioned paradigm shift due to the difficulty in securing reliable medical data.

Specifically, the current medical data is stored in the hospital or clinic where the individual received treatment. The only cases in which an individual has medical data are a request for medical treatment, a medical certificate, image data, or examination records that are delivered when moving a medical institution. That is, in the past, medical information was managed mainly by individual medical institutions that treated patients, and it was not permitted in principle to extract and share medical information outside of medical institutions except when a patient requested his/her medical records.

After all, there is a problem in that it is practically impossible to collect medical data in the current medical system and develop algorithms for predicting and preventing diseases.

In addition, the current development of artificial intelligence technology is causing enormous changes not only in engineering and medicine, but also in the data industry.

Two important directions of the recent blockchain industry are decentralization and commercialization of non-fungible tokens (NFTs). Decentralization is the first thing in finance that decentralized finance (DE-fi) has begun to eat into the market in earnest, and numerous independent ecosystem-based coins or tokens have been released, and some have been commercially successful. The part where decentralization is rapidly taking place next to finance is medical care. In addition to the enhancement of patients' rights in the medical treatment environment, the claim of patients' rights is getting stronger in areas other than medical treatment.

In particular, with the recent implementation of the My Data project, the proportion of patients, who are data subjects, in determining the scope and target of utilization of health data has increased absolutely. However, until now, health data has been exclusively managed by the medical institution where the individual patient received treatment and can be used in extremely limited cases such as research. The cases in which an individual has medical data are only medical treatment requests, medical certificates, copied charts, image data, or examination records that are delivered when moving medical institutions. The reason why the use of health data is limited despite the relaxation of legal regulations is because of the limitations of standardization and anonymization of health data.

Therefore, the need for a blockchain that can trade personal health data using NFT technology is increasing.

KR101261042B1 (Title of invention: method for providing personalized medical information sales service)

An object of the present invention is to provide a transaction system in which an owner of medical data, such as a medical record, can directly transact his or her own data.

In addition, an object of the present invention is to provide a trading system in which a user can use various functions by providing various tool data in a server.

In addition, an object of the present invention is to provide a trading system in which the owner of medical data such as medical records can directly trade his or her own data NFTs by participating in a block chain as one data NFT complex composed of countless data NFTs. .

In order to solve the above problems, the present invention provides the selection data to a first terminal generating medical data of a first user, a second terminal generating selection data of a second user, and the first terminal, A server receiving consent data corresponding to the selection data from a first terminal and providing access to the medical data to the second terminal based on the consent data, wherein the server is configured to provide access to the medical data to the first user. A corresponding first meta-human is generated, virtual view image data according to the field of view of the first meta-human is generated and transmitted to the first terminal, and the selection data is used by the second user to generate the medical data. It may include purchase intention information and payment information for , and may correspond to purchase proposal information provided from the first meta-human.

Also, the server may generate diagnostic data for the first user based on the medical data and transmit the diagnostic data to the first terminal.

Also, the server may receive a user input from the first terminal, and generate first processed medical data by processing the medical data based on the user input and tool data previously stored in the server.

In addition, when the first terminal generates usage right information of the medical data based on a Non Fungible Token (NFT) and receives matching information between the selection data and the consent data from the server, the generated based on the NFT The usage right information may be transmitted to the second terminal.

In addition, the server may receive and store the medical data from the first terminal, and provide the access authority to the second terminal that provides the usage right information generated based on the NFT.

In addition, the server may remove the access right to the second terminal after a certain period of time based on the usage right information.

In addition, the server receives and stores the blockchain-based cryptocurrency from the second terminal based on the usage right information, and transmits the cryptocurrency to the wallet address received from the first terminal after providing the access authority. can

According to the present invention, a user who is a target of medical data can directly transact his or her own medical data.

In addition, the present invention uploads one's own medical data to the server, and through various tool data provided by the server, directly processes one's own medical data according to the type, amount, and intention of the user's data, thereby increasing the effect of converting each into one NFT. have

In addition, the present invention has the effect of allowing the server to receive medical treatment services based on the learned data by uploading its own medical data composite NFT to the server.

The effects obtainable according to the present invention are not limited to the effects mentioned above, and other effects not mentioned are clearly understood by those skilled in the art from the outer surface of the protection unit below. It could be.

1 shows a medical data transaction system using a non-fungible token according to the present invention.
2 shows a server according to the present invention.
Figure 3 shows the functional components of a memory according to the present invention.
4 is a diagram showing an example of an image correction filter according to the present invention.
5 is a diagram showing CIE 1931 color coordinates according to the present invention.
6 shows a graph in which the K-center clustering process according to the present invention is performed.
The accompanying drawings, which are included as part of the detailed description to aid understanding of the present specification, provide examples of the present specification and describe technical features of the present specification together with the detailed description.

Hereinafter, the embodiments disclosed in this specification will be described in detail with reference to the accompanying drawings, but the same or similar elements are given the same reference numerals regardless of reference numerals, and redundant description thereof will be omitted.

In addition, in describing the embodiments disclosed in this specification, if it is determined that a detailed description of a related known technology may obscure the gist of the embodiment disclosed in this specification, the detailed description thereof will be omitted.

In addition, the accompanying drawings are only for easy understanding of the embodiments disclosed in this specification, the technical idea disclosed in this specification is not limited by the accompanying drawings, and all changes included in the spirit and technical scope of the present invention , it should be understood to include equivalents or substitutes.

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

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

In this application, terms such as "comprise" or "having" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof external to the protection unit in the specification, but one or It should be understood that it does not preclude the possibility of the presence or addition of other features, numbers, steps, operations, components, parts, or combinations thereof beyond that.

Hereinafter, based on the above description, a medical data transaction system using a non-fungible token according to a preferred embodiment of the present specification will be described in detail as follows.

1 shows a medical data transaction system using a non-fungible token according to the present invention.

The medical data trading system according to the present invention may mean a trading platform for trading medical data using a metaverse or a block chain for trading. In addition, the medical data transaction system according to the present invention may mean a transaction platform using non-fungible tokens, NFT, or a block chain for transaction.

According to FIG. 1 , a medical data transaction system using a non-fungible token according to the present invention may include a first terminal 100, a second terminal 200, and a server 300. A terminal according to the present invention may mean a computing device including a smart phone, tablet, notebook, desktop, personal computer, PDA, and the like. Also, a terminal according to the present invention may mean a terminal device for VR or AR.

The first terminal 100 may be a device that generates medical data of a first user. The first user is a medical data provider and may generate medical data through the first terminal 100 . Medical data is data including a first user's medical record, health condition information, body information, and the like, and may refer to all information related to medical services provided by the first user. The first user may be a person who provides medical data and may be a subject who sells or rents medical data.

Also, the medical data according to the present invention may include not only the user's medical data generated by medical treatment, but also the user's medical data reprocessed through various means implemented in the server 300 . Accordingly, in the present invention, the concept of trading medical data may include a concept of not only trading raw data of a user, but also mostly medical data reprocessed by a learning module, a processing module, and the like.

The second terminal 200 may be a device that generates selection data of the second user. The second user may be a subject who wants to purchase or rent the first data of the first user. The selection data may include information about selecting desired medical data from among a plurality of medical data stored in the DB 400 from the second user. The selection data may include purchase intention information of the second user for the selected medical data. That is, the second terminal 200 may transmit a message about the purchase intention of the second user by transmitting the selection data to the server 300 . A message regarding purchase intention may be input to the second terminal 200 by the second user. Also, the selection data may further include payment information generated by the second user. The payment information may be payment information of a type of cryptocurrency or money desired by the first user. The second user may be a subject who purchases or uses medical data, and may be a hospital, research institute, research institute, or individual.

The server 300 may be a component that communicates with and relays the first terminal 100 and the second terminal 200 . The server 300 may provide the selection data received from the second terminal 200 to the first terminal 100 . The server 300 may receive consent data corresponding to the selection data from the first terminal 100 . The consent data includes the consent message of the first user, and as the consent data is transmitted to the second terminal 200 , a transaction for medical data of the first user may be established.

The server 300 may provide a metaverse platform or block chain through which the first user and the second user can trade through the first terminal 100 and the second terminal 200 . The server 300 may generate a meta-human that encrypts the user's personal information for blockchain. A meta-human according to the present invention may be a kind of character representing a user on a blockchain. The metahuman according to the present invention is anonymized user's personal information, and may have standardized specifications according to the blockchain specifications provided by the server 300.

The server 300 may generate a first metahuman corresponding to the first user. Also, the server 300 may generate a second metahuman corresponding to the second user. Hereinafter, the description of the first metahuman according to the present invention can be equally applied to the second metahuman.

In addition, the server 300 may generate virtual view image data according to the field of view of the first metahuman and transmit it to the first terminal 100 . Through this, the first user can be provided with a view according to the movement of the first metahuman on the metaverse platform or blockchain as a screen, and the system according to the present invention allows the first user to directly enter the metaverse platform or blockchain. It is possible to provide the first user with sensory information to feel that he or she enters and transacts.

The server 300 may provide the purchase proposal information provided from the first metahuman of the first user to the second terminal 200 of the second user. The selection data generated from the second terminal 200 may be data corresponding to purchase proposal information provided from the first metahuman.

For example, the first user may access the metaverse trading platform or blockchain provided by the server 300 using the first terminal 100 such as a VR or AR terminal in order to sell his or her medical data. The server 300 may provide a virtual view image for the first terminal 100 . The server 300 may receive purchase proposal information from the first terminal 100 or the first metahuman, and may receive selection data corresponding to the purchase proposal information from the second terminal 200 or the second metahuman. The server 300 may receive consent data corresponding to the selection data from the first terminal 100 or the first meta-human. The server 300 may generate matching information when the selection data and the acceptance data match each other. The server 300 may generate matching information and transmit it to the first terminal 100 .

The first terminal 100 may generate usage right information of medical data based on a Non Fungible Token (NFT). That is, the terminal having the NFT generated by the first terminal 100 may have the right to use the medical data of the first user. That is, it can be determined whether or not there is a right to use medical data through the NFT. At this time, the NFT may be formed based on Ethereum.

The server 300 may generate matching information between selection data received from the second terminal 200 and acceptance data received from the first terminal 100 . The matching information may be information for verifying whether the medical data that the second user wants to purchase or rent is the first user's medical data. The server 300 may transmit the generated matching information to the first terminal 100 . Upon receiving the matching information, the first terminal 100 may transmit license information generated based on the NFT to the second terminal 200 . The server 300 may provide access to medical data of the first user to the second terminal 200 having license information generated based on the NFT.

The server 300 may receive and store medical data from the first terminal 100 . At this time, the medical data may be encrypted and stored. The server 300 may provide access to encrypted and stored medical data to the second terminal 200 that provides usage right information generated based on the NFT. Based on the usage right information, the server 300 may remove access rights to the second terminal 200 after a certain period of time. That is, the first terminal 100 generates usage right information of the medical data based on the NFT, and upon receiving matching information between selection data and consent data from the server 300, the first terminal 100 generates the usage right information generated based on the NFT. 2 can be transmitted to the terminal 200.

For example, the first user may store blood pressure-related numerical data for 10 years as medical data in the first terminal 100 . The first terminal 100 may generate an NFT corresponding to medical data. Medical data may be transmitted from the first terminal 100 to the server 300 and stored. The second terminal 200 may receive an NFT from the first terminal 100 in order to use the medical data of the first user. The server 300 may grant permission to view medical data to the second terminal 200 having the NFT. At this time, NFTs may be of several types. The first NFT may even allow permission to download medical data. The second NFT may even allow the right to process and utilize medical data on the server 300. In this case, the first NFT or the second NFT may include information about a period of downloading or processing and utilizing. When the first user generates an NFT to include a period of one month in NFT information, the second terminal 200 having the corresponding NFT may be authorized from the server 300 only for the period. The server 300 may grant authority to the second terminal 200 only for a period according to the NFT. The usage right information in the present invention may include information on the type of NFT and information on the duration of the right. At this time, the NFT may be directly transmitted from the first terminal 100 to the second terminal 200 .

Authorization according to the present invention may include contents about data reading, downloading, reading range and reading period.

In addition, the server 300 receives and stores the blockchain-based cryptocurrency from the second terminal 200 based on the usage right information, provides access rights, and then encrypts the wallet address received from the first terminal 100. currency can be transferred.

2 shows a server according to the present invention.

According to Figure 2, the server 300 according to the present invention may include a processor, memory and communication module.

The processor 310 may execute commands stored in the memory 320 to control other components. The processor 310 may execute instructions stored in the memory 320 .

The processor 310 is a component capable of performing calculations and controlling other devices. Mainly, it may mean a central processing unit (CPU), an application processor (AP), a graphics processing unit (GPU), and the like. Also, the CPU, AP, or GPU may include one or more cores therein, and the CPU, AP, or GPU may operate using an operating voltage and a clock signal. However, while a CPU or AP consists of a few cores optimized for serial processing, a GPU may consist of thousands of smaller and more efficient cores designed for parallel processing.

The processor 310 may provide or process appropriate information or functions to a user by processing signals, data, information, etc. input or output through the components described above or by running an application program stored in the memory 320.

The memory 320 stores data supporting various functions of the server 300 . The memory 320 may store a plurality of application programs (application programs or applications) running in the server 300, data for operation of the server 300, and commands. At least some of these application programs may be downloaded from an external server through wireless communication. Also, the application program may be stored in the memory 320, installed in the server 300, and driven by the processor 310 to perform the operation (or function) of the server 300.

The memory 320 may be a flash memory type, a hard disk type, a solid state disk type, a silicon disk drive type, or a multimedia card micro type. ), card-type memory (eg SD or XD memory, etc.), RAM (random access memory; RAM), SRAM (static random access memory), ROM (read-only memory; ROM), EEPROM (electrically erasable programmable read -only memory), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. Also, the memory 320 may include a web storage performing a storage function on the Internet.

The communication module 330 transmits and receives information with a base station or a camera having a communication function through an antenna. The communication module 330 may include a modulation unit, a demodulation unit, a signal processing unit, and the like. Also, the communication module 330 may perform a wired communication function.

Wireless communication may refer to communication using a wireless communication network using a communication facility previously installed by telecommunication companies and a frequency of the communication facility. At this time, the communication module 330 is CDMA (code division multiple access), FDMA (frequency division multiple access), TDMA (time division multiple access), OFDMA (orthogonal frequency division multiple access), SC-FDMA (single carrier frequency division multiple access), etc., as well as the communication module 330 can also be used for 3rd generation partnership project (3GPP) long term evolution (LTE). In addition, not only 5G communication, which is currently being commercialized, but also 6G, which is scheduled to be commercialized later, can be used. However, the present specification may utilize a pre-installed communication network without being bound by such a wireless communication method.

In addition, as a short range communication technology, Bluetooth, BLE (Bluetooth Low Energy), Beacon, RFID (Radio Frequency Identification), NFC (Near Field Communication), infrared communication (Infrared Data Association; IrDA) ), UWB (Ultra Wideband), ZigBee, etc. may be used.

Figure 3 shows the functional components of a memory according to the present invention.

According to FIG. 3 , the memory according to the present invention may include a learning module 321 , a data processing module 322 , an authorization module 323 , a transaction module 324 and a diagnosis module 325 .

The learning module 321 according to the present invention may learn the first user's medical data as an input value of the deep learning algorithm. At this time, the learning algorithm used may be divided according to the type of medical data.

When the medical data is image data such as X-ray images or MRI images (first type), a learning algorithm used for learning may be a CNN algorithm. That is, the CNN algorithm may be a learning algorithm using a plurality of layers. In addition, the CNN algorithm can automatically learn a filter that maximizes image classification accuracy, and by adding a new layer called a convolutional layer and a polling layer before the fully connected layer, after applying the filtering technique to the original image, the filtered image A classification operation can be performed on . The CNN algorithm is configured to apply a filtering technique to the original image by adding a new layer, called a convolutional layer and a pooling layer, before the fully-connected layer, and then perform a classification operation on the filtered image. can

If the medical data is numerical data measured at regular intervals, such as blood pressure values, BMI values, and heart rate-related numerical information (type 2), the learning algorithm used for learning may be a clustering algorithm, especially a K-center clustering algorithm. can

The K-center clustering process refers to clustering given data into K clusters. In this K-center clustering process, after randomly selecting a sample value from a given data sample, the distance from the sample value to other sample data is measured. At this time, the nearest centroid is selected from each data sample, and the distance from the corresponding sample to another data sample value is calculated again. By repeating this process, clustering is achieved. That is, a plurality of clusters are created. This clustering technique can be mainly implemented in Python. Clustering is being used as one of the algorithms that can be used in signal analysis.

The data processing model according to the present invention receives user input from the first terminal (100 in FIG. 1, hereinafter the same), and based on the user input and tool data previously stored in the server (300 in FIGS. 1 and 2, hereinafter the same) First processed medical data may be generated by processing the medical data. Tool data may refer to all tools that a user can use to process medical data. Tool data according to the present invention may include various learning algorithm functions.

The data processing module 322 according to the present invention may be configured to process medical data of a first user and provide the processed medical data to a second user. The second user may directly download and use the medical data, but may process and use the medical data on the server 300 for security reasons. To this end, the data processing module 322 according to the present invention may provide various learning algorithm functions. That is, the second user may process medical data of the first user by utilizing the data processing module 322 .

Also, the data processing model according to the present invention may be configured to process medical data of the first user according to a request through the first terminal 100 of the first user. To this end, the data processing module 322 according to the present invention may provide various learning algorithm functions. That is, the first user may process his own medical data by utilizing the data processing module 322 .

For example, the first user may input a command to the data processing module 322 of the server 300 through the first terminal 100 and utilize tool data. The first user may learn or replicate his or her own blood pressure values for 10 years according to tool data, and compress only the period during which the characteristic points appear.

The authorization module 323 according to the present invention may recognize NFT information and grant permission to view or download medical data to a terminal holding the NFT. The terminal granted the right to use by the authorization module 323 can access the server 300 or DB 400 according to the present invention and process or download the medical data of the first user on the data processing module 322. there is.

The transaction module 324 according to the present invention may be configured for NFT transactions between the first terminal 100 and the second terminal (200 in FIG. 1, hereinafter the same). The transaction module 324 may receive information on the amount of money to be provided according to the transaction information (eg, 50 USD or 0.01 Bitcoin). The transaction module 324 may receive a confirmation message by retransmitting the received money amount information to the first terminal 100 and the second terminal 200 . When receiving payment information from the second terminal 200 , the transaction module 324 may receive cryptocurrency from the second terminal 200 as much as the amount of money according to the payment information. The transaction module 324 may transmit the received cryptocurrency to the first terminal 100 after confirming that the NFT has been transmitted to the second terminal 200 .

Also, the transaction module 324 may provide a function of trading medical data without a price. Through this, the first user may donate his or her medical data to the second user.

The diagnosis module 325 according to the present invention may receive a learning value from the learning module 321 and diagnose a health problem of the first user based on the learning value. That is, the diagnostic module 325 may generate diagnostic data for the first user based on the medical data and transmit the generated diagnostic data to the first terminal 100 .

Specifically, the diagnostic module 325 learns data such as diagnostic records of a plurality of users who have obtained prior consent, derives a tendency based on the diagnostic records of a plurality of users, and based on the derived tendency, the first user of medical data can be analyzed. As an analysis means, a CNN algorithm or an algorithm of a K-center clustering process may be used. Specific examples will be described later.

The advertisement module 326 according to the present invention may provide an advertisement image to the first terminal 100 based on the advertisement request data received from the second terminal 200 . For example, the advertisement module 326 may receive advertisement request data indicating that medical data of a hypertensive patient is obtained from the second terminal 200 . The advertisement module 326 may display a corresponding advertisement on the first terminal 200 based on the advertisement request data.

Therefore, according to the present invention, the first user can have an effect of determining which research or project he or she will participate in based on the information displayed in the advertisement image.

The service providing module 327 according to the present invention may provide a user with a service according to a reservation of another hospital or a claim in a form (diagnosis letter, opinion letter, insurance claim, etc.). In addition, the service providing module 327 may provide sharing of medical information, a discussion service, or a survey service on an individual-to-individual or individual-to-institution basis.

4 is a diagram showing an example of an image correction filter according to the present invention, and FIG. 5 is a diagram showing CIE 1931 color coordinates according to the present invention.

According to FIG. 4 , the CNN algorithm according to the present invention may be applied to image data among medical data. Specifically, the learning module (321 in FIG. 3, hereinafter the same) according to the present invention can learn by distinguishing pre-labeled image data.

For example, the learning module 321 may learn X-ray image data of a lung of a lung cancer patient and X-ray image data of a normal person's lung, respectively. Based on this, the diagnosis module 325 may learn X-ray image data obtained by photographing the lungs among medical data of the first user, and diagnose whether the first user has lung cancer. As such, the learning module 321 and the diagnosis module 325 according to the present invention learn image data to extract feature points for a disease such as lung cancer, and diagnose the disease based thereon. At this time, in order to extract feature points, the CNN algorithm may use an image filter.

The operation equation for the image filter using the CNN algorithm according to the present invention is shown in Equation 1 below.

[Equation 1]

(step,

: 행렬로 표현된 필터링된 이미지의 i번째 행, j번째 열의 픽셀,

: pixels in the i-th row and j-th column of the filtered image expressed as a matrix,

: 필터,

: filter,

: 이미지,

: image,

: 필터의 높이 (행의 수),

: height of the filter (number of rows),

: 필터의 너비 (열의 수)이다.)

: The width of the filter (number of columns).)

Preferably, the operation expression for the image filter using the CNN algorithm is as shown in Equation 2 below.

[Equation 2]

(step,

: 행렬로 표현된 필터링된 이미지의 i번째 행, j번째 열의 픽셀,

: pixels in the i-th row and j-th column of the filtered image expressed as a matrix,

: 응용 필터

: Application filter

: 이미지,

: image,

: 응용 필터의 높이 (행의 수),

: height of application filter (number of rows),

: 응용 필터의 너비 (열의 수)이다.)

: The width (number of columns) of the application filter.)

는 응용 필터로서 제1 사용자 또는 환자의 병변 부위에 대한 이미지를 포함하는 이미지 데이터에 적용되는 필터일 수 있다. 특히, X-ray 이미지나 MRI 이미지는 일반 사진 등의 이미지와는 다른 취급이 필요할 수 있다. 이러한 필요성을 충족하기 위하여, 응용 필터

는 아래의 수학식 3에 의하여 연산될 수 있다. Preferably,

may be an application filter applied to image data including an image of a lesion site of the first user or patient. In particular, X-ray images or MRI images may require different handling from images such as general photographs. To meet these needs, application filters

Can be calculated by Equation 3 below.

[Equation 3]

: 필터,

: 계수,

: 응용 필터)(step,

: filter,

: Coefficient,

: application filter)

에 따른 필터는 도 4에 따른 엣지 인식 필터(Edge detection), 샤픈 필터(sharpen) 및 박스 블러 필터(Box blur) 중 어느 하나의 행렬일 수 있다. At this time, each

The filter according to may be any one matrix of an edge detection filter according to FIG. 4, a sharpen filter, and a box blur filter.

를 구하는 연산식은 아래의 수학식 4와 같다. 이때,

는 필터의 효율을 높이기 위하여 사용되는 하나의 변수로서 해석될 수 있으며, 그 단위는 무시될 수 있다. Preferably,

The operation expression for obtaining is as shown in Equation 4 below. At this time,

can be interpreted as a variable used to increase the efficiency of the filter, and its unit can be ignored.

[Equation 4]

를 활용한 응용 필터 F'를 통하여, 보다 정확한 인식이 가능하다. However, the diameter (diameter) of the lens of the camera used for image capture is in mm, and the f-value of the lens may mean an F number. In addition, the RGB coordinate distance may mean a distance between the substituted coordinate and the origin (0, 0) by substituting color information of a unit dot appearing in the image data into the RGB coordinate. In this case, the RGB coordinates may be CIE 1931 color coordinates according to FIG. 5 . Therefore, the maximum RGB coordinate distance in Equation 4 may mean the maximum distance between the unit dot and the origin in the image data, and the minimum distance in RGB coordinates means the minimum distance between the unit dot and the origin in the image data. can do. That is, Equation 4 according to the present invention is

More accurate recognition is possible through the application filter F' using .

[Experimental example]

With respect to the image data according to the present invention, it was examined whether the difference between the lesion area of the patient and the body part of the normal person displayed by the image data generated when the application filter F' of the present invention is applied is accurately determined. The table below shows the accuracy of the recognition result as a numerical value, depending on whether a filter is applied or not, requested by a person in the relevant technical field.

no filter applied

적용filter

apply filter

apply accuracy (score) 75 90 99

Table 5 shows the scores for accuracy evaluated by experts for each case. This experimental example is an experiment based on image data of 50 lung cancer patients and 50 normal people for a module that has been learned through the CNN algorithm according to the present invention, and the accuracy of whether or not lung cancer is actually invented is measured out of 100 points.

As can be seen in Table 5, when the filter is not applied, there is a probability of error in image recognition, and the evaluation is relatively low accuracy. In contrast, the accuracy was slightly higher when the general CNN filter F was applied, but it was confirmed that the accuracy was remarkably improved when the applied filter F' was applied.

6 shows a graph in which the K-center clustering process according to the present invention is performed.

According to FIG. 6, as a result of performing the K-center clustering process, two clusters are finally generated. As a result of performing the K-center clustering process according to the present invention, measurement values can be classified into clustering 1 and clustering 2.

In this case, the data to be clustered may be information of numerical data of a patient group and numerical data of a normal group for a specific body figure.

The diagnosis module 325 according to the present invention may finally generate two clusters based on the K-center clustering process and derive similarity based on the Euclidean distance between the two clusters.

In addition, the diagnosis module 325 according to the present invention extracts an average value of each of the two clusters, extracts a final distance value between each average value, and detects whether the first user has invented an invention based on the final distance value. . A specific method for detecting whether or not an invention has occurred will be described later.

The diagnostic module 325 according to the present invention may calculate the first central value of clustering 1 through an average calculation method, and calculate the second central value of clustering 2 through an average calculation method. The diagnostic module 325 calculates final distance values between the first central value and the second central value, and when the size of the final distance value is greater than a predetermined value, it is determined that the similarity of each cluster is lower than the predetermined value. can Conversely, when the magnitude of the final distance value is smaller than the predetermined value, it may be determined that the similarity of each cluster is higher than the predetermined value.

For example, clustering 1 may be a cluster based on numerical data of patients, and clustering 2 may be a cluster based on numerical data among medical data of the first user. Clusterings 1 and 2 are just numbering for randomly dividing clusters, and numbering can be changed in some cases.

That is, the diagnosis module 325 calculates a final distance value between the first central value of clustering 1 and the second central value of clustering 2, and when the magnitude of the final distance value is greater than a predetermined value, the numerical data of the first user As a result of the diagnosis based on, it can be determined that the patient is in a normal state because there is a difference from the numerical data of the patients.

The diagnosis module 325 according to the present invention may perform a K-center clustering process by using feature 1 as the x-axis coordinate and feature 2 as the y-axis coordinate. The diagnosis module 325 may calculate a first central value of cluster 1 and a second central value of cluster 2, and calculate a Euclidean distance between the first central value and the second central value. The Euclidean distance may be defined by Equation 5 below.

[Equation 5]

(However, d is the distance value, (x, y) is the coordinate value, and x and y are the patient's numerical data)

For example, in order to determine whether the first user corresponds to a high-risk hypertension group, systolic blood pressure or diastolic blood pressure may be required from numerical data among medical data. In this case, x may be systolic blood pressure (mmHg) and y may be diastolic blood pressure (mmHg).

At this time, the final distance value according to the present invention can be extracted in the following order.

(1) Extracting the first average value (x1, y1) of cluster 1 and the second average value (x2, y2) of cluster 2

(2) The first average value and the second average value are coordinate values, respectively, and the final distance value (L) between the first average value and the second average value is extracted based on Equation 6 below.

[Equation 6]

(However, (x1, y1) is a coordinate value generated based on the average value of cluster 1 (= first central value), and (x2, y2) is generated based on the average value of cluster 2 (= second central value) coordinates)

In the present invention, when the final extracted distance value (L) is greater than the preset distance value, the numerical data of the first user is different from the numerical data of the patients, so the diagnosis module 325 diagnoses the first user as a normal state. can do.

In general, in the case of learning using statistics of patients and statistics of normal people and diagnosing based on the learning result, it may be more accurate to use the corrected Euclidean distance described below rather than using only the simple Euclidean distance. The corrected Euclidean distance is referred to as the corrected final distance value (L') and can be extracted based on Equations 7 and 8 below.

[Equation 7]

(However, (x1, y1) is a coordinate value generated based on the average value of cluster 1, and (x2, y2) is a coordinate value generated based on the average value of cluster 2)

[Equation 8]

At this time, α is a correction constant for more accurate determination of the abnormal state, and the unit of α can be ignored.

As such, when the second information is generated by determining the degree of similarity based on the corrected final distance value L' using Equation 7 and Equation 8, there is an effect that the diagnosis result of the diagnosis module 325 appears more accurately. .

The above-described present invention can be modeled as a computer readable code on a medium on which a program is recorded. The computer-readable medium includes all types of recording devices in which data readable by a computer system is stored. Examples of computer-readable media include Hard Disk Drive (HDD), Solid State Disk (SSD), Silicon Disk Drive (SDD), ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. , and also includes those modeled in the form of carrier waves (eg, transmission over the Internet). Accordingly, the above detailed description should not be construed as limiting in all respects and should be considered illustrative. The scope of this specification should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent scope of this specification are included in the scope of this specification.

Any or other embodiments of the present invention described above are not mutually exclusive or distinct. Certain or other embodiments of the present invention described above may be used in combination or combination of respective configurations or functions.

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

100: first terminal
200: second terminal
300: server

Claims (7)

a first terminal generating medical data of a first user;
a second terminal generating selection data of a second user; and
Providing the selection data to the first terminal, receiving consent data corresponding to the selection data from the first terminal, and providing access to the medical data to the second terminal based on the consent data including a server;
The server,
generating a first metahuman corresponding to the first user, generating virtual view image data according to the field of view of the first metahuman, and transmitting the generated data to the first terminal;
The selection data,
The second user includes purchase intention information and payment information for the medical data and corresponds to purchase proposal information provided from the first metahuman.
Medical data trading system using non-fungible tokens.
According to claim 1,
The server,
generating diagnostic data for the first user based on the medical data and transmitting the diagnostic data to the first terminal;
Medical data trading system using non-fungible tokens.
According to claim 1,
The server,
Receiving a user input from the first terminal and processing the medical data based on the user input and tool data previously stored in the server to generate first processed medical data;
Medical data trading system using non-fungible tokens.
According to claim 1,
The first terminal,
When usage right information of the medical data is generated based on a Non Fungible Token (NFT) and matching information between the selection data and the consent data is received from the server, the usage right information generated based on the NFT is converted to the second which is transmitted to the terminal,
Medical data trading system using non-fungible tokens.
According to claim 4,
The server,
Providing the access right to the second terminal that receives and stores the medical data from the first terminal and provides the usage right information generated based on the NFT,
Medical data trading system using non-fungible tokens.
According to claim 5,
The server,
Based on the usage right information, removing the access right to the second terminal after a certain period of time,
Medical data trading system using non-fungible tokens.
According to claim 5,
The server,
Receiving and storing blockchain-based cryptocurrency from the second terminal based on the usage right information, and transmitting the cryptocurrency to the wallet address received from the first terminal after providing the access right,
Medical data trading system using non-fungible tokens.

Images