KR102666450B1 - Method and learning method of providing virtual medical service in a digital twin-based virtual world and computing device using the same - Google Patents

Abstract

The purpose of the present invention is to increase satisfaction with virtual medical services by reconstructing a virtual medical space. A method for providing virtual medical services in a virtual world based on digital twins includes: (a) a step in which a computing device constructs a virtual medical space, which is a virtual hospital for providing virtual medical services, creates medical staff avatars, and performs modeling of the virtual medical space; (b) a step in which the computing device performs a process of calculating a first satisfaction level of the first user corresponding to the first type avatar, and a process of calculating a second satisfaction level of the second type avatar at each time point in time when the interaction with the medical staff avatar occurs; and (c) a step in which the computing device reconstructs the virtual medical space by adjusting at least some of the number of treatment rooms and the number of doctors corresponding to each of the first to n-th treatment departments. According to the present invention, there is an effect of learning the parameters of a learning model included in a learning device, and predicting the waiting time of a specific user by inputting at least a portion of metadata for testing of a specific user, result data of avatar interaction for testing, and the number of treatment rooms and the number of doctors after adjustment.

Description

Method and learning method of providing virtual medical services in a digital twin-based virtual world and computing device using the same {METHOD AND LEARNING METHOD OF PROVIDING VIRTUAL MEDICAL SERVICE IN A DIGITAL TWIN-BASED VIRTUAL WORLD AND COMPUTING DEVICE USING THE SAME}

The present invention relates to a method and learning method for providing virtual medical services in a digital twin-based virtual world, and a computing device using the same.

Recently, as research on technologies related to virtual reality (VR), augmented reality (AR), and mixed reality (MR) has been actively conducted, digital twin technology, which replicates the data of objects existing in reality in the virtual world, has been in the spotlight. there is.

Specifically, digital twin technology combines technologies such as Internet of Things (IoT) sensors and high-speed communication to reflect objects, spaces, and environments that exist in reality in a virtual model and provide feedback on interactions to users in real time. It is a technology that enables two-way communication.

Currently, multiple hospitals at home and abroad are applying digital twin technology to healthcare to provide virtual medical services that enable non-face-to-face treatment and consultation even without visiting the hospital by implementing the internal structure of an actual hospital in a virtual space. Twin-related technologies are being developed.

However, when a real hospital is implemented in a virtual space, when providing virtual medical services, multiple patients may be concentrated on specific departments depending on conditions such as time zone, day of the week, and age group, and as a result, visits to a specific department may occur. There is a problem that satisfaction with virtual medical services may decrease because patients' waiting times may be long.

Therefore, improvement measures to solve the above problems are required.

Patent Registration Publication No. 10-2438836 (2022.08.29)

The purpose of the present invention is to solve the above-mentioned problems.

In addition, the present invention constructs and models a virtual medical space, which is a virtual hospital, and provides a first avatar that appears as a result of at least one first user controlling a first type avatar corresponding to the first user within the virtual medical space. The second user's operation in a state where the user's first satisfaction level and at least the second user has assigned the second user's attribute information to the second type avatar corresponding to the second user as second type avatar metadata By calculating the second level of satisfaction of the type 2 avatar, which appears as a result of allowing the type 2 avatar to work for a certain period of time at will, and adjusting the number of clinics and doctors in each of the multiple medical departments with reference to this, the virtual medical space is reorganized to provide a virtual Another purpose is to increase satisfaction with medical services.

In addition, after constructing and modeling a virtual medical space, the present invention provides at least one of the learning metadata of each specific user and other users, learning avatar interaction result data, user satisfaction information, and the number of clinics and doctors before adjustment for learning. In a state where the virtual medical space is reconfigured by learning to output the number of clinics and doctors after adjustment by inputting some of it to the learning device, avatars corresponding to specific users and other users are active in the reconfigured virtual medical space, so that specific users and each other user's learning metadata, learning avatar interaction result data, and the number of medical rooms and doctors after adjustment for learning are input to the learning device, first waiting time prediction information that predicts the waiting time for each avatar by the learning device, and Learn the parameters of the learning model included in the learning device to output the second dash time prediction information that predicts the waiting time for each medical department, metadata for testing of a specific user, avatar interaction result data for testing, and the number of clinics and doctors after adjustment. Another purpose is to predict the waiting time of a specific user as at least part of the number is input.

The characteristic configuration of the present invention for achieving the purpose of the present invention as described above and realizing the characteristic effects of the present invention described later is as follows.

According to one aspect of the present invention, in a method of providing virtual medical services in a digital twin-based virtual world, (a) a computing device constructs a virtual medical space, which is a virtual hospital for providing virtual medical services, A first type avatar that is a user-controlled avatar corresponding to at least one first user in the virtual medical space, a second type avatar that is a free-moving avatar that corresponds to at least one second user, and a medical staff avatar that corresponds to at least one medical staff. generating a, and performing modeling of the virtual medical space to display a result of interaction of at least some of the first type avatar and the second type avatar with the medical staff avatar; (b) the computing device, at each point in time when the interaction with the medical staff avatar is performed by an operation from the first user within the virtual medical space, 1 Process for calculating satisfaction; and attribute information of the second user including at least some of the gender, age, residential area, workplace information, disease information, and medication information of the second user corresponding to the second type avatar as second type avatar metadata. In the state given to the second type avatar, the second type avatar is active for a predetermined time in the virtual medical space, and the second satisfaction level of the second type avatar at each point in time when the interaction with the medical staff avatar is made. A process of calculating; performing a; and (c) the computing device, for each of the first to nth medical departments in the virtual medical space, determines the 1_1 satisfaction level for the first medical department as the first satisfaction level, and determines the 1_2 satisfaction level as the second satisfaction level. A process of determining the n_1th satisfaction with the nth medical department as the first satisfaction and the n_2th satisfaction with the second satisfaction are performed, wherein the 1_1st satisfaction and the 1_2nd satisfaction to the Calculate the first to nth overall satisfaction for each of the first to nth medical departments with reference to the n_1 satisfaction and the n_2 satisfaction, and calculate at least a portion of the first to nth overall satisfaction. A method including the step of reconfiguring the virtual medical space by adjusting at least a portion of the number of medical rooms and the number of doctors corresponding to each of the first to nth medical departments for reference is disclosed.

As an example, in step (b), the computing device: (i) refers to the number or time of words uttered or input by the first user through the virtual medical space during the interaction of the first user; The calculated first user active data is given to the first type avatar as first type avatar metadata, and (ii) a word uttered or input by the second user through real space during the interaction of the second user. Second user active data calculated with reference to the number or time and second user patience data calculated with reference to the second user's tendency information are additionally given to the second type avatar as the second type avatar metadata. A method characterized by this is disclosed.

As an example, in step (b), in determining the second satisfaction level of a second type specific avatar among the second type avatars, the computing device determines the second satisfaction level of the second type specific avatar at the specific medical department where the second type specific avatar is waiting. If it is determined that the preceding avatar waiting ahead of the second type specific avatar includes at least some of the first type preceding avatar corresponding to the first type avatar and the second type preceding avatar corresponding to the second type avatar, Calculating an expected waiting time or an actual waiting time for a specific avatar of the second type with reference to at least part of the first user aggressiveness data of the first type preceding avatar and the second user aggressiveness data of the second type preceding avatar A method is disclosed, characterized in that determining the second satisfaction level by obtaining .

As an example, in step (b), the computing device: (i) reports the severity of the first user's condition and a doctor for the first user's condition through the virtual medical space upon the interaction of the first user; The first user severity data calculated with reference to the amount of first opinion data is additionally given to the first type avatar as the first type avatar metadata, and (ii) the real space at the time of the interaction of the second user. The second user severity data calculated with reference to the severity of the second user's condition and the amount of the doctor's second opinion data on the second user's condition is additionally stored as the second type avatar metadata. A method characterized by assigning a type to an avatar is disclosed.

As an example, in step (a), the computing device determines the gender, age, visit time, and Obtain at least part of the medical treatment information as existing user metadata, and refer to the existing user metadata to obtain the actual hospital usage information by day of the week, time zone, gender, and age group of the existing user, including the number of visits to each medical department and each The first type avatar, the second type avatar, and the medical staff avatar for mapping the number of doctor visits and modeling the virtual medical space with reference to the mapped information. The number and input avatars for each day of the week and time slot, respectively A method is disclosed, characterized in that it provides gender, age group, and disposition information.

As an example, in step (b), the computing device: (i) receives at least some of the video data and audio data of the first user from at least some of the first user terminal and the photographing device corresponding to the first user; Once obtained, the first type avatar metadata extracted from at least part of the video data and the audio data is given to the first type avatar as first user preference information, and the first user is allowed to use the first type avatar. and (ii) when at least some of the biometric data and digital phenotype data of the second user are obtained from at least some of the wearable device and the second user terminal of the second user, the biometric data of the second user and obtaining second user preference information of the second user by referring to at least part of the digital phenotype data, and additionally assigning the second type avatar metadata to the second type avatar as the second user preference information. In, a method is disclosed, characterized in that the second type avatar is active within the virtual medical space for the predetermined time.

As an example, in step (c), the computing device sets the first satisfaction weight for the first satisfaction to be greater than the second satisfaction weight for the second satisfaction, so that the 1_1th satisfaction to the n_1th satisfaction is By assigning the first satisfaction weight to each, and assigning the second satisfaction weight to each of the 1_2nd to the n_2th satisfaction, the first to the overall satisfaction for each of the first to the nth medical departments is provided. A method characterized by calculating the nth overall satisfaction level is disclosed.

According to another aspect of the present invention, in a learning method for providing virtual medical services in a digital twin-based virtual world, (a) a computing device includes specific user metadata information for learning of a specific user and preset information about the specific user. Other user metadata information for learning of at least one other user with a similarity greater than a threshold, the number of medical rooms before learning adjustment and learning adjustment for each of the first to nth medical departments in a virtual medical space, which is a virtual hospital for providing virtual medical services. Number of doctors, specific user avatar interaction result data for learning of the specific user avatar corresponding to the specific user, other user avatar interaction result data for learning of the other user avatar corresponding to the other user, and specific user satisfaction information for learning and other user satisfaction for learning. Input at least some of the information into a learning device - the learning device included in the computing device - to perform learning to cause the learning device to output the number of medical offices after adjustment and the number of doctors after adjustment, and the number of medical rooms after adjustment and reconfiguring the virtual medical space with reference to at least a portion of the adjusted number of doctors. (b) The computing device acquires additional specific user avatar interaction result data for learning and additional other user avatar interaction result data for learning by causing the specific user avatar and the other user avatar to be active for a predetermined period of time within the reconfigured virtual medical space. and the specific user metadata information for learning, the other user metadata information for learning, the number of medical rooms after the adjustment and the number of doctors after the adjustment for each of the first to the nth medical departments, and the additional specific avatar interaction result data for learning. At least a portion of the additional other user avatar interaction result data for learning is input to the learning device to cause the learning device to provide first waiting time prediction information corresponding to at least some of the specific avatar and the other user avatar and the first outputting at least a portion of second waiting time prediction information corresponding to at least a portion of the medical department or the nth medical department; and (c) the computing device, as at least some of the specific user and the other users visit a real hospital corresponding to the reconfigured virtual medical space and perform face-to-face medical treatment. When at least some of the first waiting time actual information corresponding to and the second waiting time actual information corresponding to at least some of the first to the nth medical departments are obtained, the learning device predicts the first waiting time. A process of learning the parameters of the learning model included in the learning device through backpropagation using loss generated with reference to each of the first waiting time actual information, which is information and the corresponding GT (Ground Truth). ; And a process of learning the parameters of the learning model included in the learning device through backpropagation using a loss generated with reference to each of the second waiting time prediction information and the second waiting time actual information corresponding to GT. ; A method comprising: performing at least some of the steps is disclosed.

According to another aspect of the present invention, a computing device for providing virtual medical services in a digital twin-based virtual world, comprising: at least one memory storing instructions; and at least one processor configured to execute the instructions, wherein the processor: (I) constructs a virtual medical space that is a virtual hospital for providing virtual medical services, and operates at least one medical device within the virtual medical space; Generating a first type avatar that is a user-controlled avatar corresponding to a user, a second type avatar that is a free-moving avatar corresponding to at least one second user, and a medical staff avatar corresponding to at least one medical staff, the first type avatar and a process of performing modeling of the virtual medical space to display results of interaction of at least some of the second type avatars with the medical staff avatar. (II) Calculating the first satisfaction level of the first user corresponding to the first type avatar at each point in time when the interaction with the medical staff avatar is performed by an operation from the first user within the virtual medical space. subprocess; and attribute information of the second user including at least some of the gender, age, residential area, workplace information, disease information, and medication information of the second user corresponding to the second type avatar as second type avatar metadata. In the state given to the second type avatar, the second type avatar is active for a predetermined time in the virtual medical space, and the second satisfaction level of the second type avatar at each point in time when the interaction with the medical staff avatar is made. A subprocess that calculates; A process that performs; and (III) for each of the first to nth medical departments in the virtual medical space, a subprocess of determining the 1_1 satisfaction level for the first medical department as the first satisfaction level and determining the 1_2 satisfaction level as the second satisfaction level. to perform a sub-process of determining the n_1th satisfaction with the nth medical department as the first satisfaction and determining the n_2th satisfaction as the second satisfaction, wherein the 1_1 satisfaction and the 1_2 to the n_1 satisfaction and The first to nth overall satisfaction levels for each of the first to nth medical departments are calculated with reference to the n_2th satisfaction level, and the first to nth overall satisfaction levels are calculated with reference to at least a portion of the first to nth overall satisfaction levels. A computing device that performs a process of reconfiguring the virtual medical space by adjusting at least a portion of the number of medical rooms and the number of doctors corresponding to each of the first to nth medical departments is disclosed.

As an example, in the process (II), the processor: (i) calculates the number or time of words uttered or input by the first user through the virtual medical space during the interaction of the first user; granting the first user active data as first type avatar metadata to the first type avatar, (ii) the words uttered or input by the second user through real space during the interaction of the second user; Second user active data calculated with reference to the number or time and second user patience data calculated with reference to the second user's tendency information are additionally given to the second type avatar as the second type avatar metadata. A computing device featuring features is disclosed.

As an example, in the process (II), the processor, in determining the second satisfaction level of a second type specific avatar among the second type avatars, determines the second satisfaction level of the second type specific avatar in a specific medical department where the second type specific avatar is waiting. Type 2 If it is determined that the preceding avatar waiting ahead of the specific avatar includes at least some of the first type preceding avatar corresponding to the first type avatar and the second type preceding avatar corresponding to the second type avatar, Calculating an expected waiting time or an actual waiting time for a specific avatar of the second type with reference to at least a portion of the first user activeness data of the first type preceding avatar and the second user activeness data of the second type preceding avatar A computing device is disclosed, characterized in that the second satisfaction level is obtained by determining the second level of satisfaction.

As an example, in the process (II), the processor: (i) determines the severity of the first user's condition and a doctor's opinion about the first user's condition via the virtual medical space upon the interaction of the first user; First user severity data calculated with reference to the amount of first opinion data is additionally given to the first type avatar as the first type avatar metadata, and (ii) the real space is provided during the interaction of the second user. The second user severity data calculated with reference to the severity of the second user's condition and the amount of data on the doctor's second opinion regarding the second user's condition is additionally used as the second type avatar metadata. A computing device characterized by assigning an avatar to an avatar is disclosed.

As an example, in the process (I), the processor determines the gender, age, visit time, and medical treatment of a plurality of existing users who visited the actual hospital during a preset past time from the database of the actual hospital corresponding to the virtual medical space. Obtain at least some of the information as existing user metadata, and refer to the existing user metadata to obtain the actual hospital usage information by day of the week, time zone, gender, and age group of the existing user, including the number of visits to each medical department and each doctor. Mapping the number of visits and modeling the virtual medical space with reference to the mapped information; the number of inputs for each day of the week and the time slot for each of the first type avatar, the second type avatar, and the medical staff avatar; and the number of input avatars for each of the input avatars. A computing device characterized by providing gender, age, and orientation information is disclosed.

As an example, in the process (II), the processor: (i) obtains at least some of the video data and audio data of the first user from at least some of the first user terminal and the photographing device corresponding to the first user; Then, in a state where the first type avatar metadata extracted from at least part of the video data and the audio data is given to the first type avatar as first user preference information, the first user is allowed to use the first type avatar. (ii) when at least some of the biometric data and digital phenotype data of the second user are obtained from at least some of the wearable device and the second user terminal of the second user, the biometric data of the second user and Obtaining second user preference information of the second user by referring to at least some of the digital phenotype data, and additionally assigning the second type avatar metadata to the second type avatar as the second user preference information , a computing device characterized in that the second type avatar is active within the virtual medical space for the predetermined time is disclosed.

As an example, in the process (III), the processor sets the first satisfaction weight for the first satisfaction to be greater than the second satisfaction weight for the second satisfaction, respectively, for the 1_1th to the n_1th satisfaction. By assigning the first satisfaction weight to each of the 1_2nd to the n_2th satisfaction, and assigning the second satisfaction weight to each of the first to the nth treatment departments, the first overall satisfaction to the first to the first overall satisfaction for each of the first to the nth medical departments. A computing device characterized by calculating n overall satisfaction is disclosed.

According to another aspect of the present invention, a computing device for providing virtual medical services in a digital twin-based virtual world, comprising: at least one memory storing instructions; and at least one processor configured to execute the instructions, wherein the processor: (I) sets specific user metadata information for learning of a specific user and at least one other user having a similarity of more than a preset threshold to the specific user; Other user metadata information for learning, the number of medical rooms before adjustment for learning and the number of doctors before adjustment for learning in each of the first to nth medical departments in the virtual medical space, which is a virtual hospital for providing virtual medical services, and the specific number corresponding to the specific user. A device for learning at least some of specific user avatar interaction result data for learning of a user avatar, other user avatar interaction result data for learning of another user avatar corresponding to the other user, specific user satisfaction information for learning, and other user satisfaction information for learning - the learning device Is included in the computing device - inputs to and causes the learning device to perform learning to output the number of medical offices after adjustment and the number of doctors after adjustment, and refer to at least a portion of the number of medical rooms after adjustment and the number of doctors after adjustment. A process of reconstructing the virtual medical space; (II) Obtaining additional specific user avatar interaction result data for learning and additional other user avatar interaction result data for learning by causing the specific user avatar and the other user avatar to be active within the reconfigured virtual medical space for a predetermined period of time, and obtaining the specific user avatar interaction result data for learning. User metadata information and other user metadata information for learning, the number of medical rooms after the adjustment and the number of doctors after the adjustment in each of the first to nth medical departments, the additional specific avatar interaction result data for learning, and the additional other users for learning. At least part of the avatar interaction result data is input to the learning device to cause the learning device to provide first waiting time prediction information corresponding to at least some of the specific avatar and the other user's avatar and the first through nth medical departments. A process for outputting at least some of the second waiting time prediction information corresponding to at least some of the medical departments; and (III) as at least some of the specific user and the other users visit a real hospital corresponding to the reconfigured virtual medical space and perform face-to-face medical treatment, a first device corresponding to the specific user and at least some of the other users When at least some of the waiting time actual information and the second waiting time actual information corresponding to at least some of the first to the nth medical departments are obtained, the learning device is configured to obtain the first waiting time prediction information and the corresponding second waiting time information. A subprocess for learning parameters of a learning model included in the learning device through backpropagation using a loss generated with reference to each of the first waiting time actual information, which is GT (Ground Truth); And a sub that learns the parameters of the learning model included in the learning device through backpropagation using a loss generated with reference to each of the second waiting time prediction information and the second waiting time actual information, which is the corresponding GT. process; A computing device that performs a process that performs at least a portion of the process is disclosed.

The present invention constructs and models a virtual medical space, which is a virtual hospital, and provides information about the first user that appears as a result of at least one first user controlling a first type avatar corresponding to the first user within the virtual medical space. The first satisfaction level and at least the second user's attribute information to the second type avatar corresponding to the second user are given to the second type avatar as second type avatar metadata without manipulation by the second user. A virtual medical service is provided by reorganizing the virtual medical space by calculating the second level of satisfaction of the type 2 avatar, which appears as a result of allowing the type 2 avatar to be active for a certain period of time at the will of the avatar, and adjusting the number of clinics and doctors in each department with reference to this. It has the effect of increasing satisfaction.

In addition, after constructing and modeling a virtual medical space, the present invention provides at least some of the learning metadata of each specific user and other users, learning avatar interaction result data, user satisfaction information, and the number of clinics and doctors before adjustment for learning. In a state where the virtual medical space is reconfigured by learning to output the number of clinics and doctors after adjustment by inputting it to a learning device, avatars corresponding to specific users and other users are active in the reconfigured virtual medical space, so that specific users and Each other user's learning metadata, learning avatar interaction result data, and the number of clinics and doctors after adjustment for learning are input to the learning device, and the first waiting time prediction information and medical department that allows the learning device to predict the waiting time for each avatar. Learn the parameters of the learning model included in the learning device to output the second dash time prediction information predicting the waiting time for each star, metadata for testing of a specific user, avatar interaction result data for testing, and the number of clinics and number of doctors after adjustment. As at least part of the input is entered, it has the effect of predicting the waiting time of a specific user.

The following drawings attached for use in explaining embodiments of the present invention are only some of the embodiments of the present invention, and to those skilled in the art (hereinafter “those skilled in the art”), the invention Other drawings can be obtained based on these drawings without further work being done.
1 schematically illustrates a computing device that provides virtual medical services in a digital twin-based virtual world, according to an embodiment of the present invention;
Figure 2 is a flow chart schematically showing a process for providing virtual medical services in a digital twin-based virtual world, according to an embodiment of the present invention;
Figure 3 shows a process for calculating the first satisfaction of at least one first user waiting at a specific medical department or the second satisfaction of a second type avatar corresponding to at least one second user, according to an embodiment of the present invention. It is schematically shown,
Figure 4 schematically shows a state in which avatar metadata to be assigned to avatars corresponding to a plurality of users stored in a database and corresponding satisfaction information are matched and managed according to an embodiment of the present invention;
5A and 5B show, according to another embodiment of the present invention, the number of medical rooms and doctors are predicted after adjustment using a learning device, a virtual medical space is reconstructed with reference to this, and a specific user is identified within the reconstructed virtual medical space. It shows the process of learning a learning model to predict waiting time.

The detailed description of the present invention described below refers to the accompanying drawings, which show by way of example specific embodiments in which the present invention may be practiced to make clear the objectives, technical solutions and advantages of the present invention. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention.

Additionally, throughout the description and claims, the word “comprise” and variations thereof are not intended to exclude other technical features, attachments, components or steps. Other objects, advantages and features of the invention will appear to those skilled in the art, partly from this description and partly from practice of the invention. The examples and drawings below are provided by way of example and are not intended to limit the invention.

Moreover, the present invention encompasses all possible combinations of the embodiments shown herein. It should be understood that the various embodiments of the invention are different from one another but are not necessarily mutually exclusive. For example, specific shapes, structures and characteristics described herein with respect to one embodiment may be implemented in other embodiments without departing from the spirit and scope of the invention. Additionally, it should be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the invention. Accordingly, the detailed description that follows is not intended to be taken in a limiting sense, and the scope of the invention is limited only by the appended claims, together with all equivalents to what those claims assert, if properly described. Similar reference numbers in the drawings refer to identical or similar functions across various aspects.

Hereinafter, in order to enable those skilled in the art to easily practice the present invention, preferred embodiments of the present invention will be described in detail with reference to the attached drawings.

1 is a diagram schematically showing a computing device that provides virtual medical services in a digital twin-based virtual world, according to an embodiment of the present invention.

Referring to FIG. 1, a computing device 100 that provides virtual medical services in a digital twin-based virtual world may include a memory 110 and a processor 120. Additionally, the computing device 100 may additionally include a display 130, but it may also be configured separately rather than included in the computing device 100.

The memory 110 of the computing device 100 that provides virtual medical services in a digital twin-based virtual world may store instructions to be performed by the processor 120. Specifically, the instructions are stored in the digital twin-based virtual world. Code generated for the purpose of enabling the computing device 100 for providing virtual medical services to function in a specific manner, stored in a computer-usable or computer-readable memory that can be directed to a computer or other programmable data processing equipment. It can be saved. Instructions may perform processes to execute functions described in the specification of the present invention.

In addition, the processor 120 of the computing device 100 for providing virtual medical services in a digital twin-based virtual world includes an MPU (Micro Processing Unit) or CPU (Central Processing Unit), a cache memory, and a data bus. It may include hardware configuration such as (Data Bus). Additionally, the computing device 100 may further include an operating system and a software component of an application that performs a specific purpose.

Additionally, the computing device 100 for providing virtual medical services in a digital twin-based virtual world may be linked to the database 200. Here, the database 200 includes a flash memory type, hard disk type, multimedia card micro type, card type memory (for example, SD or XD memory), At least one of RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (ReadOnly Memory), EEPROM (Electrically Erasable Programmable ReadOnly Memory), PROM (Programmable ReadOnly Memory), magnetic memory, magnetic disk, and optical disk. It may include one type of storage medium, but is not limited to this and may include all media capable of storing data. In addition, the database 200 is installed separately from the computing device 100 for providing virtual medical services in a digital twin-based virtual world, or, alternatively, a computing device for providing virtual medical services in a digital twin-based virtual world. It may be installed inside 100 to transmit data or record received data, or, unlike shown, may be implemented separately in two or more pieces, which may vary depending on the implementation conditions of the invention.

Additionally, the display 130 may be separate from the memory 110 and processor 120 in the computing device 100 as a separate device.

Additionally, the computing device 100 may be a user terminal (not shown) such as a smartphone, tablet, or PC, or may be a server for providing virtual medical services in a digital twin-based virtual world. In the latter case, the server may be linked to a separate user terminal (not shown) such as a smartphone, tablet, or PC.

A method using the computing device 100 for providing virtual medical services in a digital twin-based virtual world according to an embodiment of the present invention configured as described above will be described with reference to FIG. 2 as follows.

Figure 2 schematically shows a process for providing virtual medical services in a digital twin-based virtual world, according to an embodiment of the present invention.

Referring to FIG. 2, the computing device 100 constructs a virtual medical space, which is a virtual hospital for providing virtual medical services, and a first user-adjusted avatar corresponding to at least one first user in the virtual medical space. Type avatar, a second type avatar that is a freely active avatar corresponding to at least one second user (i.e., an avatar that automatically moves according to a predetermined algorithm without user control and given the user's metadata), and at least one A medical staff avatar corresponding to the medical staff is created, and modeling of a virtual medical space can be performed to display the results of interaction of at least some of the first type avatar and the second type avatar with the medical staff avatar (S210). .

As an example, the computing device 100 refers to an architectural design drawing including the interior and exterior views of an actual hospital and uses various metaverse platforms such as ZEP, Gather, and ZEPETO to create a virtual medical space identical to an actual hospital in a metaverse environment. can be constructed, and multiple avatars can be created in 2D, 2.5D, and dot design form to perform virtual medical services through interaction within the constructed virtual medical space. At this time, there are a plurality of avatars, a first type avatar that corresponds to at least one first user and allows the first user to interact by operating using the user terminal, and a second user that corresponds to at least one second user. A second type avatar that allows interaction through free activity within the virtual medical space without direct manipulation by the second user by assigning metadata including attribute information, behavior pattern information, etc. to identify the second user. It may include, but is not limited to, a medical staff avatar that corresponds to medical staff such as doctors and nurses and can interact with at least some of the first type avatar and the second type avatar.

In addition, the computing device 100 collects the information of a plurality of existing users who visited the actual hospital during a preset past time (e.g., 1 month, 3 months, 6 months, 1 year, etc.) from the database of the actual hospital corresponding to the virtual medical space. At least some of the gender, age, visit time, and medical treatment information can be obtained as existing user metadata, and by referring to the existing user metadata, actual hospital usage information by day of the week, time zone, gender, and age group of the existing user can be obtained. It can be mapped to the number of visits to the medical department and the number of visits to each doctor. In other words, the computing device 100 refers to the information mapped for existing users through statistical processing and inputs the first type avatar, the second type avatar, and the medical staff avatar by day and time for modeling the virtual medical space, respectively. The optimal number of avatars can be determined, and accordingly, gender, age group, and personality information can be assigned to each input avatar.

Here, the tendency information refers to (i) when the user directly manipulates the avatar using the user terminal, metadata to be assigned to the avatar can be secured by referring to metadata extracted from at least some of the user's video data and audio data; and (ii) when allowing the avatar to freely move within the virtual medical space without manipulating the avatar corresponding to the user (although this does not need to coincide with the avatar's free activity time), the wearable device worn by the user at a certain time and Metadata for assigning to the corresponding avatar may be secured by referring to at least some of the biometric data and digital phenotype data obtained from at least some of the user terminals, but the method is not limited to this.

Next, the computing device 100 calculates the first satisfaction level of the first user corresponding to the first type avatar at each point in time when interaction with the medical staff avatar is performed through an operation by the first user within the virtual medical space. process; And second type attribute information of the second user including at least some of the second user's gender, age, residential area, work information, disease information, and medication information corresponding to the second type avatar as second type avatar metadata. In the state assigned to the avatar, a process of calculating the second satisfaction level of the second type avatar at each time point of interaction with the medical staff avatar by allowing the second type avatar to operate for a predetermined period of time within the virtual medical space can be performed. (S220).

As an example, the computing device 100 allows a specific user to display the behavior of a specific user avatar corresponding to a specific user in a virtual medical space using a specific user terminal, output the voice of a specific user, or input chat content, etc. If it is determined that a virtual medical service is performed through interaction with a medical staff avatar through manipulation, the specific user, as the first user, measures the satisfaction of the first user through the user terminal after each interaction with the first type avatar and the medical staff avatar is completed. It supports responding to an evaluable questionnaire, and the first satisfaction level can be calculated by referring to the contents of the questionnaire surveyed by the first user. Of course, such first satisfaction is not limited to a survey, and can of course be obtained by referring to the real-time facial expression and tone of voice of the user controlling the first type avatar.

At this time, the computing device 100 determines the number or time of words uttered or input by the first user through the virtual medical space when the first user manipulates the first type avatar using the user terminal and interacts with the medical staff avatar. Among the first user severity data calculated with reference to (i) first user activity data and (ii) the severity of the first user's condition and the amount of data on the doctor's first opinion regarding the first user's condition With at least part of the first type avatar metadata assigned to the first type avatar, a specific user who is the first user can manipulate the first type avatar using the user terminal. Here, the first user activeness data can be used as a factor for predicting the time required to interact with the first type avatar and the medical staff avatar, and the first user severity data is the severity of the first user's disease and the first user's condition. It may be calculated by scoring the amount of data on the doctor's first opinion about the condition and calculating the average, or by additionally assigning a predetermined weight and then calculating the average, but it is not limited to this.

Meanwhile, when at least some of the video data and audio data of the first user are obtained from at least some of the first user terminal and the imaging device corresponding to the first user, the computing device 100 collects the acquired video data of the first user. And it is possible to extract first type avatar metadata, such as aggressiveness data and perseverance data, from at least some of the voice data through pre-processing, and convert the extracted first type avatar metadata into first type avatar information as first user tendency information. In a state where , the first user may be allowed to control the first type avatar.

That is, the computing device 100 can calculate the first satisfaction level by additionally reflecting the first type of avatar metadata to the information obtained by the first user through a survey, etc., and the score for the survey content and the first metadata The first satisfaction level may be calculated by calculating the average of the scores, or the first satisfaction level may be calculated by calculating a weighted average by assigning weights to each of the scores for the survey content and the score for the first metadata. It is not limited.

As another example, if the computing device 100 determines that the specific user does not manipulate the specific user avatar corresponding to the specific user using the specific user terminal, the specific user is the second user and determines the second user's gender, age, and residence. Attribute information of the second user, including at least part of region, workplace information, disease information, and medication information, may be given as second type avatar metadata to a second type avatar corresponding to the second user, and the second type avatar By identifying the second type avatar with metadata as the second user, it is possible to freely move within the virtual medical space to perform virtual medical services, and the interaction obtained from each interaction of the second type avatar with the medical staff avatar. The second satisfaction level of the second type avatar can be calculated by referring to the result data.

In addition, when the second type avatar performs an interaction with the medical staff avatar, the computing device 100 calculates the second user proactiveness by referring to the number or time of words uttered or input by the second user through real space. Second user patience data calculated with reference to the data and the second user's preference information may be additionally given to the second type avatar as second type avatar metadata. Here, the second user activity data may be used as an element for predicting the time required for interaction between the second type avatar and the medical staff avatar.

And, in a state where the second type avatar metadata is assigned to the second type Avatar, the computing device 100 is more active than the second type specific avatar in a specific medical department where a second type specific avatar is waiting among the plurality of second type avatars. If it is determined that the preceding avatar waiting ahead includes at least some of the first type preceding avatar corresponding to the first type avatar and the second type preceding avatar corresponding to the second type avatar, the first type preceding avatar of the first type avatar The second satisfaction level may be determined by calculating an expected waiting time or obtaining an actual waiting time for a specific avatar of the second type, with reference to at least some of the user activeness data and the second user activeness data of the second type preceding avatar, FIG. 3 I will explain in more detail with reference to .

Figure 3 shows a process for calculating the first satisfaction of at least one first user waiting at a specific medical department or the second satisfaction of a second type avatar corresponding to at least one second user, according to an embodiment of the present invention. It is schematically shown.

Referring to FIG. 3, inside a specific medical room of a specific medical department located in a virtual medical space where the computing device 100 performed modeling using the metaverse platform, a doctor avatar 311 as a medical staff avatar and a doctor avatar 311 corresponding to the first specific user are displayed. A first specific user avatar 301 is performing non-face-to-face medical treatment through a virtual medical service, and outside the specific medical room, second specific user avatars 302 to 5 corresponding to the 2nd to 5th specific users are present. The avatar 305 is on standby, and the second to fifth specific user avatars 302 to 305 waiting can interact with the nurse avatar 312 as the medical staff avatar. At this time, a receptionist avatar 321 corresponding to a receptionist who can assist with tasks such as reservations and cancellations for virtual medical services may be additionally created, but is not limited to this.

For example, if the computing device 100 determines that the fifth specific user avatar 305 is a first type avatar, the fifth specific user corresponding to the fifth specific user avatar 305 waits and operates the fifth specific user terminal. At the point when the interaction with the nurse avatar 312 is completed using or when it is the turn and the interaction with the doctor avatar 311 is completed inside a specific medical room, the fifth specific user's You can request a survey to calculate the first level of satisfaction.

Thereafter, when the computing device 100 obtains the survey response content from the fifth specific user terminal, it calculates the first satisfaction level with reference to the survey response content, or calculates the fifth specific user meta assigned to the fifth specific user avatar 305. The first satisfaction level may be calculated by additionally reflecting the data, but it is not limited to this. As mentioned above, the first satisfaction level may be calculated using the actual facial expression or tone of voice of the fifth specific user. For reference, even in the case where at least some of the first specific user avatars 301 to 4 fourth specific user avatars 304 are determined to be first type avatars, the first satisfaction level may be calculated through the same process as above.

As another example, if the computing device 100 determines that the fifth specific user avatar 305 is a second type avatar, the computing device 100 selects the second specific user avatar 302 as a preceding avatar waiting before the fifth specific user avatar 305. ) to fourth specific user avatars 304 and a first specific user avatar 301 currently performing non-face-to-face medical treatment through a virtual medical service with the doctor avatar 311, and the first specific user avatar ( It may be determined whether each of 301) to fourth specific user avatars 302 is a first type avatar or a second type avatar.

For example, the computing device 100 may determine that the first specific user avatar 301 and the third specific user avatar 303 are the first type avatar, and the second specific user avatar 302 and the fourth specific user avatar 304 are the first type avatar. If it is determined to be a second type avatar, the first user activity data of the first specific user and the third specific user corresponding to each of the first specific user avatar 301 and the third specific user avatar 303 are referred to. It is possible to calculate or predict the time required for treatment of the specific user avatar 301 and the third specific user avatar 303, and the second specific user avatar 302 and the fourth specific user avatar 304 respectively. The time required for treatment of the second specific user avatar 302 and the fourth specific user avatar 304 can be calculated or predicted by referring to the second user activity data of the second specific user and the fourth specific user.

Accordingly, the computing device 100 adds up the times that the first specific user avatar 301 to the fourth specific user avatar 304 spend to perform non-face-to-face medical treatment through a virtual medical service, thereby creating a fifth specific user avatar 305. ) can determine the waiting time to perform non-face-to-face medical treatment with the doctor avatar 311, so the second satisfaction level of the fifth specific user avatar 305 can be automatically calculated by referring to this.

That is, the computing device 100 calculated the second satisfaction level by assuming that when the specific user avatar waiting in a specific medical department is a second type avatar, the longer the waiting time is based on the waiting time in the specific medical department, the lower the second satisfaction level is. It is not limited to this, and the value of the second satisfaction level may be adjusted by referring to, for example, second user patience data.

Meanwhile, the computing device 100 additionally converts at least some of the second user severity data calculated with reference to the severity of the second user's condition and the amount of the doctor's second opinion data on the second user's condition into a second type avatar. It can be given to a second type avatar as metadata, and when at least some of the second user's biometric data and digital phenotype data are usually obtained from at least some of the second user's wearable device and the second user terminal, the second user's Second user preference information of the second user may be obtained by referring to at least some of the user's biometric data and digital phenotype data, and second type avatar metadata may be additionally assigned to the second type avatar as second user preference information. there is. Here, the second user severity data is obtained by scoring the severity of the second user's condition and the amount of data on the doctor's second opinion about the second user's condition and calculating the average, or by additionally assigning a predetermined weight and then calculating the average. It may be calculated by doing this, but it is not limited to this.

For reference, the computing device 100 matches the first satisfaction corresponding to the first user and the second satisfaction corresponding to the second type avatar with the corresponding first type avatar metadata and second type avatar metadata to store the first satisfaction level corresponding to the first user and the second satisfaction level corresponding to the second type avatar in the database. It can be managed by recording it on (200), and this will be explained with reference to FIG. 4.

Figure 4 schematically illustrates matching and management of avatar metadata to be assigned to avatars corresponding to a plurality of users stored in a database and corresponding satisfaction information, according to an embodiment of the present invention.

Referring to Figure 4, the avatar metadata for User 1 shows that he is a 26-year-old male living in Seoul and working at ○○ Electronics, has been diagnosed with depression and is taking selective serotonin absorbers, and has received treatment a total of 3 times. As can be seen, in the first treatment, on July 4, 2023, the first user used virtual medical services in the virtual medical space by directly manipulating the avatar, and in the second treatment, on July 11, 2023, user 1's schedule was used. Due to the problem, User 1 used the virtual medical service as a second user by not directly manipulating the avatar, and during the third treatment, on July 18, 2023, he again used the virtual medical service by directly manipulating the avatar as the first user. You can confirm that it was done.

In addition, it can be seen that the severity data, aggressiveness data, and patience data for each of User 1's three treatments are managed in the database 200, and this avatar metadata is managed by matching the satisfaction calculated for each treatment. .

At this time, it can be expressed by determining a rating from 1 to 5 for each of the severity data, aggressiveness data, and perseverance data. The severity data can be defined as the worse the user's health status is as it approaches '5', and the aggressiveness data can be defined as The closer it gets to '5', the more active the interaction with the medical staff avatar can be, and the closer patience data gets to '5', the less likely it is to be dissatisfied or irritated by external factors. In addition, severity data, aggressiveness data, and perseverance data may each be calculated and expressed in the form of scores between 0 and 100, but are not limited to this.

Additionally, in the database 200, the avatar metadata and satisfaction level for each medical treatment may be matched and managed for User 2 to User X.

Referring again to FIG. 2, the computing device 100 determines the 1_1 satisfaction level for the first department as the first satisfaction level for each of the first to nth medical departments in the virtual medical space, and determines the 1_2 satisfaction level as the second satisfaction level. A process of determining the n_1th satisfaction with the nth medical department as the first satisfaction and the n_2th satisfaction as the second satisfaction are performed, and the 1_1st satisfaction and the 1_2th satisfaction to the n_1th satisfaction and the n_2th satisfaction are performed. The first to nth overall satisfaction levels for each of the first to nth medical departments are calculated with reference to the first to nth general satisfaction levels, and the first to nth general satisfaction levels are calculated for each of the first to nth medical departments with reference to at least a portion of the first to nth overall satisfaction levels. The virtual medical space can be reconfigured by adjusting at least some of the number of clinics and the number of doctors corresponding to (S230).

As an example, the computing device 100 is a 1_1 satisfaction that is the first satisfaction in the first medical department within the modeled virtual medical space, a 1_2 satisfaction that is a second satisfaction, to a n_1 satisfaction that is the first satisfaction in the n-th medical department, and the In a state where the n_2th satisfaction, which is the second satisfaction, is determined, the first satisfaction weight for the first satisfaction can be set to be greater than the second satisfaction weight for the second satisfaction. In other words, even if metadata about the second user is given to the second type avatar as second type avatar metadata and the second type avatar is identified with the second user, the first user actually uses the first type avatar directly. Since it can be assumed that manipulation may result in a difference from interacting with the medical staff avatar and thus lower accuracy, the first satisfaction weight for the first satisfaction can be set to be greater than the second satisfaction weight for the second satisfaction. .

In addition, the computing device 100 assigns a first satisfaction weight to each of the 1_1st satisfaction to the n_1th satisfaction (i.e., the first satisfaction for each of the first to nth medical departments), and the 1_2th to the n_2th satisfaction. Calculate the first to nth overall satisfaction levels for each of the first to nth medical departments by assigning a second satisfaction weight to each (i.e., the second satisfaction for each of the first to nth medical departments), By referring to the first to nth overall satisfaction levels and reorganizing the virtual medical space so that more clinics and doctors are assigned to departments with low overall satisfaction, the waiting time of users receiving virtual medical services can be minimized and satisfaction can be increased. There is an effect.

Meanwhile, the computing device 100 may support calculating satisfaction by predicting the waiting time of a specific user within a virtual medical space by learning by being equipped with a separate learning device. In this regard, more detailed information is shown in FIGS. 5A and 5B. I will explain it this way.

5A and 5B show, according to another embodiment of the present invention, the number of medical rooms and doctors are predicted after adjustment using a learning device, a virtual medical space is reconstructed with reference to this, and a specific user is identified within the reconstructed virtual medical space. It shows the process of learning a learning model to predict waiting time.

Referring to FIG. 5A, the computing device 100 may further include a learning device, and the learning model 510 included in the learning device includes (i) specific user metadata information for learning, a specific user, and a preset threshold. Other user metadata information for learning about at least one other user with the above similarity, (ii) the number of clinics before adjustment for learning and the number of doctors before adjustment for learning, (iii) specific user avatar interaction result data for learning and other user avatar interaction results for learning. data, and (iv) inputting at least some of the specific user satisfaction information for learning and other user satisfaction information for learning, and performing a process of causing the learning device to output the number of medical rooms after adjustment and the number of doctors after adjustment, and output. The virtual medical space can be reorganized to minimize waiting time when a specific user avatar corresponding to a specific user receives virtual medical services by referring to the adjusted number of medical rooms and the adjusted number of doctors. Of course, it is natural that information about other users with similarity below the threshold to the specific user metadata information for learning can also be entered and learned, so for convenience of explanation, it is explained as above.

For example, when the computing device 100 determines a specific user and other users, age, gender, residential area, workplace information, and disease information included in the user metadata information for each of the plurality of users recorded in the database 200 , it can be determined by referring to at least some of medication information, treatment date, severity data, aggressiveness data, and perseverance data to check whether the user has a similarity of more than a preset threshold to a specific user.

However, since it is difficult to determine that the reconfigured virtual medical space is perfectly optimized by referring to the number of medical rooms after adjustment and the number of doctors after adjustment output using the learning device included in the computing device 100, the reconfigured virtual medical space Interactions can be performed between avatars in space and then optimized through an additional learning process.

As an example, the computing device 100 acquires additional specific user avatar interaction result data for learning and additional other user avatar interaction result data for learning by allowing a specific user avatar and another user's avatar to be active for a predetermined period of time within the reconfigured virtual medical space. , (i) specific user metadata information for learning and other user metadata information for learning, (ii) the number of clinics after adjustment for learning and the number of doctors after adjustment for learning, and (iii) additional specific user avatar interaction result data for learning and additional other users for learning. By inputting at least some of the avatar interaction result data, the learning device generates first waiting time prediction information calculated for a plurality of specific user avatars and a plurality of other avatars in a virtual medical space and a second waiting time prediction calculated for each medical department. A process may be performed to output at least some of the information.

That is, have the learning device output at least some of the first waiting time prediction information that can be influenced by the number of avatars put into the reconfigured virtual medical space and the second waiting time prediction information that can be influenced by the type of medical department. It is done.

In addition, as at least some of the specific user and other users visit a real hospital corresponding to the reconfigured virtual medical space and perform face-to-face treatment, the computing device 100 may provide a first waiting device corresponding to at least some of the specific user and other users. At least some of the time actual information and the second waiting time actual information corresponding to at least some of the first to nth medical departments can be obtained as GT.

Thereafter, the computing device 100 causes the learning device to input each of the first waiting time prediction information and the second waiting time prediction information output from the learning model 510 to the loss layer 520. Waiting time prediction for each avatar by comparing the first waiting time prediction information and the corresponding first waiting time actual information, and/or the second waiting time prediction information and the corresponding second waiting time actual information. At least some of the star waiting time prediction losses can be generated, and the parameters of the learning model 510 can be learned through backpropagation.

In addition, when the computing device 100 completes learning of the parameters of the learning model 510 through the learning device, the learning device provides test subject metadata information, other test subject metadata information, and the number of treatment rooms after adjustment for testing. After adjustment, the number of doctors, and additional specific user avatar interaction result information for testing and at least some of the additional user avatar interaction result data for testing are input to the learning model 510 to provide first waiting time prediction information for testing and testing. By outputting the second waiting time prediction information, it is possible to increase the satisfaction of specific users by minimizing unnecessary waiting time in receiving virtual medical services within the reconfigured virtual medical space.

Additionally, the embodiments according to the present invention described above may be implemented in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc., singly or in combination. The program instructions recorded on the computer-readable recording medium may be specially designed and configured for the present invention or may be known and usable by those skilled in the computer software field. Examples of computer-readable recording media include hard disks, magnetic media such as floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magnetooptical media such as floptical disks. , and hardware devices specifically configured to store and perform program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include not only machine language code such as that created by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform processing according to the invention and vice versa.

In the above, the present invention has been described with specific details such as specific components and limited embodiments and drawings, but this is only provided to facilitate a more general understanding of the present invention, and the present invention is not limited to the above embodiments. , a person skilled in the art to which the present invention pertains can make various modifications and variations from this description.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments, and the scope of the patent claims described below as well as all modifications equivalent to or equivalent to the scope of the claims fall within the scope of the spirit of the present invention. They will say they do it.

Claims (16)

In a method of providing virtual medical services in a digital twin-based virtual world,
(a) the computing device constructs a virtual medical space, which is a virtual hospital for providing virtual medical services, and at least one first type avatar, which is a user-controlled avatar corresponding to at least one first user in the virtual medical space; A second type avatar, which is a freely active avatar corresponding to the second user, and a medical staff avatar corresponding to at least one medical staff are created, and at least some of the first type avatar and the second type avatar interact with the medical staff avatar. performing modeling on the virtual medical space to display the performed results;
(b) the computing device, at each point in time when the interaction with the medical staff avatar is performed by an operation from the first user within the virtual medical space, 1 Process for calculating satisfaction; and attribute information of the second user including at least some of the gender, age, residential area, workplace information, disease information, and medication information of the second user corresponding to the second type avatar as second type avatar metadata. In the state given to the second type avatar, the second type avatar is active for a predetermined time in the virtual medical space, and the second satisfaction level of the second type avatar at each point in time when the interaction with the medical staff avatar is made. A process of calculating; performing a; and
(c) The computing device determines, for each of the first to nth medical departments in the virtual medical space, the 1_1 satisfaction level for the first medical department as the first satisfaction level and the 1_2 satisfaction level as the second satisfaction level. A process of determining or determining the n_1th satisfaction with the nth medical department as the first satisfaction and the n_2th satisfaction with the nth medical department as the second satisfaction are performed, wherein the 1_1th satisfaction and the 1_2nd to the n_1th satisfaction are performed. Calculate the first to nth overall satisfaction levels for each of the first to nth medical departments by referring to the satisfaction level and the n_2th satisfaction level, and refer to at least a portion of the first to nth overall satisfaction levels. Reconfiguring the virtual medical space by adjusting at least a portion of the number of medical rooms and the number of doctors corresponding to each of the first to nth medical departments;
How to include . According to paragraph 1,
In step (b) above,
The computing device, (i) first user active data calculated with reference to the number or time of words uttered or input by the first user through the virtual medical space during the interaction of the first user Type avatar metadata is given to the first type avatar, and (ii) is calculated with reference to the number or time of words uttered or input by the second user through real space during the interaction of the second user. 2. A method characterized in that second user patience data calculated with reference to user activeness data and preference information of the second user is additionally provided to the second type avatar as the second type avatar metadata. According to paragraph 2,
In step (b) above,
In determining the second satisfaction level of a second type specific avatar among the second type avatars, the computing device determines that the second type specific avatar is waiting ahead of the second type specific avatar in a specific medical department where the second type specific avatar is waiting. If it is determined that the preceding avatar includes at least some of a first type preceding avatar corresponding to the first type avatar and a second type preceding avatar corresponding to the second type avatar, the first type preceding avatar of the first type avatar Calculate an expected waiting time or obtain an actual waiting time for a specific avatar of the second type, with reference to at least some of the user activeness data and the second user active data of the second type preceding avatar, and determine the second satisfaction level. A method characterized by: According to paragraph 2,
In step (b) above,
The computing device: (i) refers to the severity of the first user's condition and the amount of data on the doctor's first opinion regarding the first user's condition through the virtual medical space at the time of the interaction of the first user; The calculated first user severity data is additionally assigned to the first type avatar as the first type avatar metadata, and (ii) the severity of the second user's condition is determined through the real space during the interaction of the second user. and additionally providing second user severity data calculated with reference to the amount of data on a doctor's second opinion regarding the second user's condition as the second type avatar metadata to the second type avatar. . According to paragraph 1,
In step (a) above,
The computing device stores at least some of the gender, age, visit time, and medical treatment information of a plurality of existing users who visited the actual hospital during a preset past time from the database of the actual hospital corresponding to the virtual medical space as existing user metadata. Obtained as, and referring to the existing user metadata, the actual hospital usage information by day of the week, time zone, gender, and age group of the existing user is mapped with the number of visits to each medical department and the number of visits to each doctor, and the mapped information With reference to, for modeling the virtual medical space, the number of inputs of the first type avatar, the second type avatar, and the medical staff avatar for each day of the week and the time period, and the gender, age group, and disposition information of each input avatar are given. A method characterized by: According to paragraph 1,
In step (b) above,
When the computing device obtains, (i) at least some of the video data and audio data of the first user from at least some of the first user terminal and the photographing device corresponding to the first user, the video data and the audio data assigning first type avatar metadata extracted from at least part of the first type avatar as first user tendency information to the first type avatar, allowing the first user to control the first type avatar, and (ii) the first type avatar. 2 When at least some of the biometric data and digital phenotypic data of the second user are obtained from at least some of the wearable device of the user and the second user terminal, refer to at least some of the biometric data and digital phenotypic data of the second user In a state in which second user preference information of the second user is obtained, and the second type avatar metadata is additionally given to the second type avatar as the second user preference information, the second type avatar is displayed in the virtual A method characterized in that the activity is performed for the predetermined period of time within a medical space. According to paragraph 1,
In step (c) above,
The computing device sets the first satisfaction weight for the first satisfaction to be greater than the second satisfaction weight for the second satisfaction and assigns the first satisfaction weight to each of the 1_1th satisfaction to the n_1th satisfaction, and , By assigning the second satisfaction weight to each of the 1_2th satisfaction to the n_2th satisfaction, the first to the nth overall satisfaction levels for each of the first to the nth medical departments are calculated. How to. In a learning method for providing virtual medical services in a digital twin-based virtual world,
(a) A computing device includes specific user metadata information for learning of a specific user, other user metadata information for learning of at least one other user having a similarity of more than a preset threshold to the specific user, and virtual data for providing a virtual medical service. The number of medical rooms before adjustment for learning and the number of doctors before adjustment for learning in each of the first to nth medical departments in the virtual medical space, which is a hospital, the specific user avatar interaction result data for learning of the specific user avatar corresponding to the specific user, and the correspondence to the other users. Input at least some of the other user avatar interaction result data for learning, specific user satisfaction information for learning, and other user satisfaction information for learning into a learning device - the learning device included in the computing device - to cause the learning device to , performing learning to output the number of medical rooms after adjustment and the number of doctors after adjustment, and reconstructing the virtual medical space with reference to at least a portion of the number of medical rooms after adjustment and the number of doctors after adjustment;
(b) The computing device acquires additional specific user avatar interaction result data for learning and additional other user avatar interaction result data for learning by causing the specific user avatar and the other user avatar to be active for a predetermined period of time within the reconfigured virtual medical space. and the specific user metadata information for learning, the other user metadata information for learning, the number of medical rooms after the adjustment and the number of doctors after the adjustment for each of the first to the nth medical departments, and the additional specific avatar interaction result data for learning. At least a portion of the additional other user avatar interaction result data for learning is input to the learning device to cause the learning device to provide first waiting time prediction information corresponding to at least some of the specific avatar and the other user avatar and the first outputting at least a portion of second waiting time prediction information corresponding to at least a portion of the medical department or the nth medical department; and
(c) the computing device, as at least some of the specific user and the other users visit a real hospital corresponding to the reconfigured virtual medical space and perform face-to-face medical treatment, When at least part of the corresponding first waiting time actual information and the second waiting time actual information corresponding to at least some of the first to the nth medical departments are obtained, the learning device is configured to provide the first waiting time prediction information. A process of learning the parameters of the learning model included in the learning device through backpropagation using a loss generated with reference to each of the first waiting time actual information, which is the corresponding GT (Ground Truth); And a process of learning the parameters of the learning model included in the learning device through backpropagation using a loss generated with reference to each of the second waiting time prediction information and the second waiting time actual information corresponding to GT. ; performing at least some of the following;
How to include . In a computing device for providing virtual medical services in a digital twin-based virtual world,
at least one memory storing instructions; and
At least one processor configured to execute the instructions,
The processor is configured to: (I) construct a virtual medical space, which is a virtual hospital for providing virtual medical services, and at least one first type avatar, which is a user-controlled avatar corresponding to at least one first user in the virtual medical space; A second type avatar, which is a freely active avatar corresponding to the second user, and a medical staff avatar corresponding to at least one medical staff are created, and at least some of the first type avatar and the second type avatar interact with the medical staff avatar. A process of performing modeling on the virtual medical space to display the performed results; (II) Calculating the first satisfaction level of the first user corresponding to the first type avatar at each point in time when the interaction with the medical staff avatar is performed by an operation from the first user within the virtual medical space. subprocess; and attribute information of the second user including at least some of the gender, age, residential area, workplace information, disease information, and medication information of the second user corresponding to the second type avatar as second type avatar metadata. In the state given to the second type avatar, the second type avatar is active for a predetermined time in the virtual medical space, and the second satisfaction level of the second type avatar at each point in time when the interaction with the medical staff avatar is made. A subprocess that calculates; A process that performs; and (III) for each of the first to nth medical departments in the virtual medical space, a subprocess of determining the 1_1 satisfaction level for the first medical department as the first satisfaction level and determining the 1_2 satisfaction level as the second satisfaction level. to perform a sub-process of determining the n_1th satisfaction with the nth medical department as the first satisfaction and determining the n_2th satisfaction as the second satisfaction, wherein the 1_1 satisfaction and the 1_2 to the n_1 satisfaction and The first to nth overall satisfaction levels for each of the first to nth medical departments are calculated with reference to the n_2th satisfaction level, and the first to nth overall satisfaction levels are calculated with reference to at least a portion of the first to nth overall satisfaction levels. A computing device that performs a process of reconfiguring the virtual medical space by adjusting at least a portion of the number of medical rooms and the number of doctors corresponding to each of the first to nth medical departments. According to clause 9,
In process (II) above,
The processor, (i) converts first user activity data, which is calculated with reference to the number or time of words uttered or input by the first user through the virtual medical space during the interaction of the first user, into a first type given to the first type avatar as avatar metadata, and (ii) second information calculated with reference to the number or time of words uttered or input by the second user through real space during the interaction of the second user. A computing device characterized in that second user patience data calculated with reference to user activeness data and preference information of the second user is additionally provided to the second type avatar as the second type avatar metadata. According to clause 10,
In process (II) above,
In determining the second satisfaction level of a second type specific avatar among the second type avatars, the processor determines whether the second type specific avatar is waiting ahead of the second type specific avatar in a specific medical department where the second type specific avatar is waiting. If it is determined that the avatar includes at least some of a first type preceding avatar corresponding to the first type avatar and a second type preceding avatar corresponding to the second type avatar, the first user of the first type preceding avatar Calculating an expected waiting time or obtaining an actual waiting time for a specific avatar of the second type, with reference to at least some of the activeness data and the second user activeness data of the second type preceding avatar, to determine the second satisfaction level A computing device characterized in that. According to clause 10,
In process (II) above,
The processor calculates (i) with reference to the severity of the first user's condition and the amount of data on the doctor's first opinion regarding the first user's condition through the virtual medical space when the first user interacts with the first user. The first user severity data is additionally given to the first type avatar as the first type avatar metadata, and (ii) the severity of the second user's condition through the real space during the interaction of the second user and A computing device characterized in that second user severity data calculated with reference to the amount of data on the doctor's second opinion regarding the second user's condition is additionally provided to the second type avatar as the second type avatar metadata. . According to clause 9,
In process (I) above,
The processor stores at least some of the gender, age, visit time, and medical treatment information of a plurality of existing users who visited the actual hospital during a preset past time from the database of the actual hospital corresponding to the virtual medical space as existing user metadata. Obtain, refer to the existing user metadata, map the actual hospital usage information by day of the week, time zone, gender, and age group of the existing user with the number of visits to each medical department and the number of visits to each doctor, and map the mapped information For reference, for modeling the virtual medical space, the number of inputs of each of the first type avatar, the second type avatar, and the medical staff avatar for each day of the week and the time period, and the gender, age group, and disposition information of each input avatar are given. A computing device characterized in that. According to clause 9,
In process (II) above,
When the processor (i) obtains at least some of the video data and audio data of the first user from at least some of the first user terminal and the photographing device corresponding to the first user, among the video data and the audio data, With at least part of the extracted first type avatar metadata provided as first user preference information to the first type avatar, allowing the first user to control the first type avatar, (ii) the second user When at least some of the biometric data and digital phenotypic data of the second user are obtained from at least some of the user's wearable device and the second user terminal, referring to at least some of the biometric data and digital phenotypic data of the second user In a state in which second user preference information of the second user is acquired and the second type avatar metadata is additionally provided to the second type avatar as the second user preference information, the second type avatar is used for the virtual medical treatment. A computing device characterized in that it is active in space for the predetermined time. According to clause 9,
In process (III) above,
The processor sets a first satisfaction weight for the first satisfaction to be greater than a second satisfaction weight for the second satisfaction and assigns the first satisfaction weight to each of the 1_1th satisfaction to the n_1th satisfaction, By assigning the second satisfaction weight to each of the 1_2th satisfaction to the n_2th satisfaction, the first to the nth overall satisfaction for each of the first to the nth medical departments is calculated. Computing device. In a computing device for providing virtual medical services in a digital twin-based virtual world,
at least one memory storing instructions; and
At least one processor configured to execute the instructions,
The processor, (I) specific user metadata information for learning of a specific user, other user metadata information for learning of at least one other user having a similarity of more than a preset threshold to the specific user, and a virtual device for providing a virtual medical service. The number of medical rooms before adjustment for learning and the number of doctors before adjustment for learning in each of the first to nth medical departments in the virtual medical space, which is a hospital, the specific user avatar interaction result data for learning of the specific user avatar corresponding to the specific user, and the correspondence to the other users. Input at least some of the other user avatar interaction result data for learning, specific user satisfaction information for learning, and other user satisfaction information for learning into a learning device - the learning device included in the computing device - to cause the learning device to , a process of performing learning to output the number of medical rooms after adjustment and the number of doctors after adjustment, and reconstructing the virtual medical space with reference to at least a portion of the number of medical rooms after adjustment and the number of doctors after adjustment; (II) Obtaining additional specific user avatar interaction result data for learning and additional other user avatar interaction result data for learning by causing the specific user avatar and the other user avatar to be active within the reconfigured virtual medical space for a predetermined period of time, and obtaining the specific user avatar interaction result data for learning. User metadata information and other user metadata information for learning, the number of medical rooms after the adjustment and the number of doctors after the adjustment in each of the first to nth medical departments, the additional specific avatar interaction result data for learning, and the additional other users for learning. At least part of the avatar interaction result data is input to the learning device to cause the learning device to provide first waiting time prediction information corresponding to at least some of the specific avatar and the other user's avatar and the first through nth medical departments. A process for outputting at least some of the second waiting time prediction information corresponding to at least some of the medical departments; and (III) as at least some of the specific user and the other users visit a real hospital corresponding to the reconfigured virtual medical space and perform face-to-face medical treatment, a first device corresponding to the specific user and at least some of the other users When at least some of the waiting time actual information and the second waiting time actual information corresponding to at least some of the first to the nth medical departments are obtained, the learning device is configured to obtain the first waiting time prediction information and the corresponding second waiting time information. A subprocess for learning parameters of a learning model included in the learning device through backpropagation using a loss generated with reference to each of the first waiting time actual information, which is GT (Ground Truth); And a sub that learns the parameters of the learning model included in the learning device through backpropagation using a loss generated with reference to each of the second waiting time prediction information and the second waiting time actual information, which is the corresponding GT. process; A computing device that performs a process that performs at least part of a process.