Preprocessing data construction device for training rehabilitation exercise guide artificial intelligence model, and control method therefor

Abstract

The present disclosure relates to a preprocessing data construction device and method for training a rehabilitation exercise guide artificial intelligence model, which comprise: acquiring chart data of a patient through an input unit; scanning the chart data; extracting specific data from the scanned chart data; and storing the extracted specific data in a memory on the basis of a predetermined rule, wherein the specific data is used for training the rehabilitation exercise guide artificial intelligence model.

Description

A device for constructing preprocessing data for training an artificial intelligence model for a rehabilitation exercise guide and its control method.

[0001] The present disclosure relates to the construction of preprocessing data. More specifically, it relates to a device for constructing preprocessing data for training an artificial intelligence model for a rehabilitation exercise guide, and a control method thereof.

[0002] The field of rehabilitation therapy is rapidly expanding its scope and market due to the growing elderly population. Recently, new rehabilitation treatments and training methods utilizing robots have been trialed. However, in practice, manual therapy and various rehabilitation tools with different skill levels and training methods are being used interchangeably, and data standards for electronic medical records (EMRs) are unclear. IBM Watson, an AI technology, was introduced to a domestic university hospital in 2017 and is being used as a device for cancer diagnosis and is already being utilized in various medical fields. To effectively utilize AI in rehabilitation, personalized rehabilitation plans must be developed based on clinical data obtained from treatment, taking into account individual overlapping conditions and physical characteristics. Personalized rehabilitation aims to shorten the duration of painful rehabilitation training and treatment while enhancing the effectiveness of rehabilitation.

[0003] However, in the case of conventional technology, data is required to learn the artificial intelligence model for rehabilitation exercise guidance. However, this data exists as unstructured data recorded in a chart, so it has the limitation that it can only be used in a limited way. In addition, there is a disadvantage that medical staff have to manually input unstructured data one by one, which causes inconvenience to users.

[0004] The purpose of the embodiment disclosed in the present disclosure is to provide a preprocessing construction device for learning a rehabilitation exercise guide artificial intelligence model that facilitates artificial intelligence learning by constructing unstructured data recorded in a chart into structured data.

[0005] The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

[0006] A device for constructing preprocessing data for learning a rehabilitation exercise guide artificial intelligence model according to the present disclosure comprises: an input unit for receiving chart data of a patient; a memory for storing the chart data; and a control unit for acquiring the chart data through the input unit, storing the chart data in the memory, scanning the chart data, extracting specific data from the scanned chart data, and storing the extracted specific data in the memory based on a predetermined rule, wherein the stored specific data is used for learning the rehabilitation exercise guide artificial intelligence model.

[0007] In addition, a method for constructing preprocessing data for learning a rehabilitation exercise guide artificial intelligence model according to the present disclosure includes the steps of: acquiring a patient's chart data through the input unit; scanning the chart data; extracting specific data from the scanned chart data; and storing the extracted specific data in a memory (150) based on a predetermined rule, wherein the specific data is used for learning a rehabilitation exercise guide artificial intelligence model.

[0008] In addition, a computer program stored in a computer-readable recording medium may be further provided to execute a method for implementing the present disclosure.

[0009] In addition, a computer-readable recording medium recording a computer program for executing a method for implementing the present disclosure may be further provided.

[0010] According to the aforementioned problem solving means of the present disclosure, it is possible to facilitate artificial intelligence learning by constructing unstructured data recorded in a chart into structured data, thereby improving user convenience.

[0011] According to the aforementioned problem solving means of the present disclosure, meaningful information about a patient's condition can be obtained based on chart data, and the information can be preprocessed to help in learning an artificial intelligence model, thereby improving user convenience.

[0012] The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

[0013] Figure 1 is a configuration diagram of a preprocessing data construction device for learning an artificial intelligence model for a rehabilitation exercise guide according to the present disclosure.

[0014] FIG. 2 is a diagram illustrating a flowchart of a method for constructing preprocessing data for learning an artificial intelligence model for a rehabilitation exercise guide according to the present disclosure.

[0015] FIG. 3 is a diagram illustrating an example of extracting a ROM (Range of motion or (joint) range of motion) string from chart data according to the present disclosure.

[0016] FIG. 4 is a diagram illustrating that numbers following a ROM (Range of motion or (joint) range of motion) string according to the present disclosure sequentially correspond to predetermined values ​​related to shoulder angle information.

[0017] FIG. 5 is a diagram illustrating extraction of an MMT (Manual muscle test or muscle strength) string from chart data according to the present disclosure.

[0018] Figure 6 is a drawing showing a case where suturing of shoulder surgery according to the present disclosure is successful.

[0019] Figure 7 is a drawing illustrating a case in which suturing of shoulder surgery according to the present disclosure is incorrect.

[0020] FIG. 8 is a diagram illustrating an example of a data format according to the present disclosure.

[0021] FIG. 9 is a diagram illustrating a configuration of a preprocessing data construction device for learning an artificial intelligence model for a rehabilitation exercise guide according to the present disclosure.

[0022] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and any content that is common in the technical field to which this disclosure pertains or that overlaps between embodiments is omitted. The terms "part, module, element, block" used in the specification may be implemented in software or hardware, and depending on the embodiments, multiple "parts, modules, elements, blocks" may be implemented as a single component, or a single "part, module, element, block" may include multiple components.

[0023] Throughout the specification, when a part is said to be "connected" to another part, this includes not only direct connection but also indirect connection, and indirect connection includes connection via a wireless communication network.

[0024] Additionally, when a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise specifically stated.

[0025] Throughout the specification, when we say that an element is "on" another element, this includes not only cases where the element is in contact with the other element, but also cases where another element exists between the two elements.

[0026] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0027] Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0028] The identification codes for each step are used for convenience of explanation and do not describe the order of each step. Each step may be performed in a different order than specified unless the context clearly indicates a specific order.

[0029] The operating principle and embodiments of the present invention will be described with reference to the attached drawings below.

[0030] The present invention can be implemented not only in a server system but also in various devices capable of performing computational processing and providing results to a user. For example, the present invention according to the present disclosure may include a computer, a server device, and a mobile terminal, or may be implemented in any one of the following forms.

[0031] Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.

[0032] The above server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

[0033] The above portable terminal may include, for example, a wireless communication device that ensures portability and mobility, and may include all kinds of handheld-based wireless communication devices such as a PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminal, a smart phone, and a wearable device such as a watch, a ring, a bracelet, an anklet, a necklace, glasses, contact lenses, or a head-mounted device (HMD).

[0034] The related functions according to the present disclosure are operated through a processor and memory. The processor may be composed of one or more processors. In this case, one or more processors may be a general-purpose processor such as a CPU, an AP, a DSP (Digital Signal Processor), a graphics-only processor such as a GPU or a VPU (Vision Processing Unit), or an artificial intelligence-only processor such as an NPU. One or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in memory. Alternatively, if one or more processors are artificial intelligence-only processors, the artificial intelligence-only processor may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0035] The predefined operation rules or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that the basic artificial intelligence model is learned by a learning algorithm using a plurality of learning data, thereby creating a predefined operation rules or artificial intelligence model set to perform a desired characteristic (or purpose). This learning may be performed in the device itself on which the artificial intelligence according to the present disclosure is performed, or may be performed through a separate server and / or system. Examples of the learning algorithm include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0036] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values, and performs neural network operations through operations between the operation results of the previous layer and the multiple weights. The multiple weights of the multiple neural network layers may be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model is reduced or minimized during the learning process. The artificial neural network may include a deep neural network (DNN), and examples thereof include, but are not limited to, a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or deep Q-networks.

[0037] The processor can create a neural network, train (or learn) a neural network, perform computations based on received input data, and generate information signals based on the results of the computations, or retrain the neural network.

[0038] Neural networks include CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), perceptron, multilayer perceptron, FF (Feed Forward), RBF (Radial Basis Network), DFF (Deep Feed Forward), LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), AE (Auto Encoder), VAE (Variational Auto) Encoder), DAE (Denoising Auto Encoder), SAE (Sparse Auto Encoder), MC (Markov Chain), HN (Hopfield Network), BM (Boltzmann Machine), RBM (Restricted Boltzmann Machine), DBN (Depp Belief Network), DCN (Deep Convolutional Network), DN (Deconvolutional Network), DCIGN (Deep Convolutional Inverse Graphics Network), Generative Adversarial Network (GAN), Liquid State Machine (LSM), Extreme Learning Machine (ELM), It will be understood by those skilled in the art that any neural network may be included, including but not limited to ESN (Echo State Network), DRN (Deep Residual Network), DNC (Differentiable Neural Computer), NTM (Neural Turning Machine), CN (Capsule Network), KN (Kohonen Network), and AN (Attention Network).

[0039] According to an exemplary embodiment of the present disclosure, the processor may be configured to perform a process for generating a CNN (Convolution Neural Network) such as GoogleNet, AlexNet, VGG Network, Region with Convolution Neural Network (R-CNN), Region Proposal Network (RPN), Recurrent Neural Network (RNN), Stacking-based deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restrcted Boltzman Machine (RBM), Fully Convolutional Network, Long Short-Term Memory (LSTM) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT, SP-BERT, MRC / QA for natural language processing, Text Analysis, Dialog System, GPT-3, GPT-4, Visual Analytics for vision processing, Visual Understanding, Video Synthesis, ResNet for data intelligence, Anomaly Detection, Prediction, Time-Series Forecasting, Various artificial intelligence structures and algorithms, including optimization, recommendation, and data creation, can be utilized, but are not limited thereto. Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings.

[0040] Figure 1 is a configuration diagram of a preprocessing data construction device for learning an artificial intelligence model for a rehabilitation exercise guide according to the present disclosure.

[0041] Referring to FIG. 1, a preprocessing data construction device (100) for learning a rehabilitation exercise guide artificial intelligence model includes an input unit (110), a sensor unit (120), a control unit (130), a display (140), a memory (150), a communication unit (160), and a camera (170).

[0042] The input unit (110) receives chart data.

[0043] The sensor unit (120) senses chart data by attaching a sensor.

[0044] The control unit (130) obtains the chart data through the input unit (110), stores the chart data in the memory (150), scans the chart data, extracts specific data from the scanned chart data, and stores the extracted specific data in the memory (150) based on a predetermined rule.

[0045] Here, specific data is used to train an artificial intelligence model for rehabilitation exercise guidance.

[0046] The display (140) displays a graphic image according to a control command from the control unit (130).

[0047] Memory (150) stores chart data.

[0048] The communication unit (160) transmits and receives data with an external device (200).

[0049] Here, the external device (200) includes an external device such as a smartphone, PC, laptop, tablet PC, etc.

[0050] The camera (170) photographs a subject in front according to a control command from the control unit (130).

[0051] The control unit (130) performs labeling and preprocessing based on the acquired chart data.

[0052] The control unit (130) extracts a ROM (Range Of Motion) string containing shoulder angle information from the above chart data. A detailed description thereof is provided in Fig. 3.

[0053] The control unit (130) sequentially corresponds the numbers following the ROM string to predetermined values ​​related to shoulder angle information. A detailed description thereof is provided in Fig. 4.

[0054] The control unit (130) extracts an MMT (Manual Muscle Test) string containing a muscle strength-related degree from the above chart data. A detailed description thereof is provided in Fig. 5.

[0055] The control unit (130) separates the extracted MMT string into two pieces of information.

[0056] The control unit (130) acquires an MRI image through the input unit (110), determines a predetermined shape from the acquired MRI image as a region of interest (ROI), and controls the display (140) to display the determined region of interest. A detailed description thereof is provided in FIGS. 6 and 7.

[0057] The control unit (130) scans the first area (peripheral area) which is the area of ​​interest and an area spaced a predetermined distance from the area of ​​interest.

[0058] If there is a point of separation between the area of ​​interest and the first area, the control unit (130) determines the surgical site as a ruptured case.

[0059] If there is no separation point between the area of ​​interest and the first area, the control unit (130) determines the surgical site as a case where suturing is well done.

[0060] The control unit (130) controls the display to display the above-mentioned separation point so as to be distinguished from other areas.

[0061] However, the components illustrated in FIG. 1 are not essential for implementing the present invention, and thus the present invention described in this specification may have more or fewer components than the components listed above.

[0062] The communication unit (160) may include one or more components that enable communication with an external device, and may include, for example, at least one of a broadcast reception module, a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0063] The input unit (110) is for inputting video information (or signal), audio information (or signal), data, or information input from a user, and may include at least one camera, at least one microphone, and at least one user input unit. Voice data or image data collected by the input unit (110) may be analyzed and processed into a user control command.

[0064] The display (140) displays (outputs) information processed by the artificial intelligence-based user behavior pattern analysis device (100). For example, the artificial intelligence-based user behavior pattern analysis device (100) can display execution screen information of a running application program (e.g., an application), or UI (User Interface) or GUI (Graphical User Interface) information according to such execution screen information.

[0065] The memory (150) can store data supporting various functions of the present invention, programs for the operation of the control unit, input / output data (e.g., music files, still images, moving images, etc.), and can store a plurality of application programs (or applications) driven by the present invention, data for the operation of the device, and commands. At least some of these application programs can be downloaded from an external server via wireless communication.

[0066] The memory (150) may include at least one type of storage medium among a flash memory type, a hard disk type, an SSD (Solid State Disk type), an SDD (Silicon Disk Drive type), a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. In addition, the memory (150) may be a database connected by wire or wirelessly, although separate from the present invention, and may be implemented as a database system.

[0067] The control unit (130) may be implemented as at least one core, a memory storing data on an algorithm for controlling the operation of components within the artificial intelligence-based user behavior pattern analysis device (100) or a program reproducing the algorithm, and at least one processor (not shown) that performs the aforementioned operation using the data stored in the memory. In this case, the memory and the processor may be implemented as separate chips. Alternatively, the memory and the processor may be implemented as a single chip.

[0068] In addition, the control unit (130) can control any one or a combination of the components discussed above in order to implement various embodiments according to the present disclosure described in FIGS. 2 to 9 below in the present invention.

[0069] At least one component may be added or deleted to correspond to the performance of the components illustrated in Figure 1. Furthermore, it will be readily apparent to those skilled in the art that the relative positions of the components may be altered to correspond to the performance or structure of the system.

[0070] Meanwhile, each component illustrated in FIG. 1 refers to software and / or hardware components such as a Field Programmable Gate Array (FPGA) and an Application Specific Integrated Circuit (ASIC).

[0071] Figure 2 is a flowchart illustrating a method for constructing preprocessing data for learning an artificial intelligence model for a rehabilitation exercise guide according to the present disclosure. The present invention is performed by a preprocessing data construction device (100) or a control unit (130) for learning an artificial intelligence model for a rehabilitation exercise guide.

[0072] Referring to Fig. 2, the patient's chart data is acquired through the input unit (110) (S210).

[0073] Scan the above chart data (S220).

[0074] Specific data is extracted from the scanned chart data (S230).

[0075] The extracted specific data is stored in the memory (150) based on a predetermined rule (S240).

[0076] Here, specific data is used to train an artificial intelligence model for rehabilitation exercise guidance.

[0077] FIG. 3 is a diagram illustrating an example of extracting a ROM string from chart data according to the present disclosure.

[0078] Referring to FIG. 3, the control unit (130) extracts a ROM string (320) containing shoulder angle information from chart data (310).

[0079] The extracted ROM string (320) becomes 130 - 60 - 70 - 10 - L4.

[0080] FIG. 4 is a diagram illustrating that numbers following a ROM string according to the present disclosure sequentially correspond to predetermined values ​​related to shoulder angle information.

[0081] Referring to FIG. 4, the control unit (130) sequentially corresponds the numbers following the ROM string to predetermined values ​​related to shoulder angle information.

[0082] The ROM string is 130 - 60 - 70 - 10 - L4.

[0083] For example, 130 corresponds to forward flexion, 60 corresponds to external rotation at side, 70 corresponds to external rotation at abduction, 10 corresponds to adduction, and L4 corresponds to internal rotation.

[0084] Here, forward flexion refers to how far the shoulder moves forward.

[0085] External rotation at side refers to how much the shoulder moves sideways.

[0086] External rotation at abduction refers to how much the shoulder moves outward toward the body.

[0087] Adduction refers to how much the shoulder moves inward toward the body.

[0088] Internal rotation refers to how much the shoulder moves downward.

[0089] FIG. 5 is a diagram illustrating extraction of an MMT string from chart data according to the present disclosure.

[0090] Referring to FIG. 5, the control unit (130) extracts an MMT string (330) including a muscle strength-related degree from the chart data (310).

[0091] The MMT string (330) becomes 5-10.

[0092] The control unit (130) separates the extracted MMT string into two pieces of information.

[0093] For example, if the MMT string (330) is 5-10, it is separated into 5 and 10.

[0094] Here, the first 5 represents the power grade, and 10 represents 10 seconds. Therefore, NW stands for No Weakness, meaning that the strength is normal and not weak, meaning that you can last 10 seconds with a power of grade 5.

[0095] For example, it could be 4-9. You can last 9 seconds with a power grade of 4.

[0096] For 4-9, you can last 8 seconds with a power grade of 4.

[0097] Figure 6 is a drawing showing a case where suturing of shoulder surgery according to the present disclosure is successful.

[0098] Referring to FIG. 6, the control unit (130) acquires an MRI image through the input unit (110), determines a predetermined shape in the acquired MRI image as a region of interest (ROI), and controls the display (140) to display the determined region of interest (610).

[0099] Here, the region of interest (610) is called Region of Interest, ROI, and refers to the area that the user is interested in and carefully examines.

[0100] The shape of the area of ​​interest (610) can be adjusted to a circular, box-shaped, or user-defined shape.

[0101] The control unit (130) scans the area of ​​interest (610) and the first area (peripheral area, 620), which is an area spaced a predetermined distance from the area of ​​interest (610).

[0102] The area of ​​interest (610) and the first area (620) can have different shapes and can be displayed in different colors.

[0103] If there is no separation point between the area of ​​interest (610) and the first area (620), the control unit (130) determines the surgical site as a case where suturing is well done.

[0104] In conventional techniques, doctors look at MRI images to determine whether suturing the surgical site was successful.

[0105] According to the present invention, an artificial intelligence model determines whether suturing of a surgical site is successful based on an MRI image of the surgical site.

[0106] The control unit (130) determines whether the shoulder surgical suture portion is ruptured based on the presence or absence of a separation point in the area of ​​interest (610).

[0107] The control unit (130) learns the surgical site image and, based on the learned image, determines whether the surgical site suture portion included in the newly input MRI image is ruptured.

[0108] Additionally, the control unit (130) labels an image determined to be a rupture of the surgical site suture portion by the presence of a gap point in the region of interest (610).

[0109] The control unit (130) inputs MRI images on which labeling has been performed into the artificial intelligence model to perform artificial intelligence learning for rehabilitation exercise guidance.

[0110] Figure 7 is a drawing illustrating a case in which suturing of shoulder surgery according to the present disclosure is incorrect.

[0111] Referring to FIG. 7, the control unit (130) acquires an MRI image through the input unit (110), determines a predetermined shape in the acquired MRI image as a region of interest (ROI), and controls the display (140) to display the determined region of interest (710).

[0112] Here, the region of interest (710) is called Region of Interest, ROI, and refers to the area that the user is interested in and carefully examines.

[0113] The control unit (130) scans the area of ​​interest (710) and the first area (peripheral area, 720), which is an area spaced a predetermined distance from the area of ​​interest (710).

[0114] The control unit (130) determines the surgical site as a ruptured case if there is a separation point (730) between the area of ​​interest (710) and the first area (720).

[0115] The control unit (130) controls the display (140) to display the separation point (730) so as to be distinguished from other areas.

[0116] For example, the separation point (730) may be displayed differently in at least one of color and shape from the area of ​​interest (710) and the first area (720).

[0117] The separation point (730) can be displayed in the form of a flashing light.

[0118] FIG. 8 is a diagram illustrating an example of a data format according to the present disclosure.

[0119] Referring to Figure 8, the numbers can be listed vertically in the order of 1, 2, 3…

[0120] Angular information includes forward flexion, external rotation at side, external rotation at abduction, adduction, and internal rotation.

[0121] Strength content includes power grade and number of seconds held.

[0122] Regarding whether there is a rupture, if it is 0, it means normal. If it is 1, it means a rupture.

[0123] According to the present invention, meaningful information about a patient's condition can be obtained based on chart data, and the information can be preprocessed to help in learning an artificial intelligence model, thereby improving user convenience.

[0124] FIG. 9 is a diagram illustrating a configuration of a preprocessing data construction device for learning an artificial intelligence model for a rehabilitation exercise guide according to the present disclosure.

[0125] Referring to FIG. 9, a device for constructing preprocessing data for training an artificial intelligence model for a rehabilitation exercise guide includes a device (1600). The device (1600) may include a memory (1602), a processor (1603), a transceiver (1604), and a peripheral device (1601). Furthermore, as an example, the device (1600) may further include other configurations and is not limited to the above-described embodiment.

[0126] More specifically, the device (1600) of FIG. 9 may be an exemplary hardware / software architecture, such as an NDN device, an NDN server, or a content router. As an example, the memory (1602) may be non-removable memory or removable memory. Furthermore, as an example, the peripheral device (1601) may include a display, GPS, or other peripheral devices, and is not limited to the above-described embodiment.

[0127] In addition, as an example, the above-described device (1600) may include a communication circuit such as the transceiver (1604), and may perform communication with an external device based thereon.

[0128] Additionally, as an example, the processor (1603) may be at least one of a general-purpose processor, a digital signal processor (DSP), a DSP core, a controller, a microcontroller, ASICs (Application Specific Integrated Circuits), FPGA (Field Programmable Gate Array) circuits, any other type of integrated circuit (IC), and one or more microprocessors associated with a state machine. In other words, it may be a hardware / software configuration that performs a control role for controlling the above-described device (1600).

[0129] At this time, the processor (1603) may execute computer-executable instructions stored in the memory (1602) to perform various essential functions of the present invention. For example, the processor (1603) may control at least one of signal coding, data processing, power control, input / output processing, and communication operations. In addition, the processor (1603) may control the physical layer, the MAC layer, and the application layers. In addition, for example, the processor (1603) may perform authentication and security procedures in the access layer and / or the application layer, and is not limited to the above-described embodiment.

[0130] For example, the processor (1603) can communicate with other devices via the transceiver (1604). For example, the processor (1603) can control a node to communicate with other nodes via a network through the execution of computer-executable instructions. That is, the communication performed in the present invention can be controlled. For example, the other nodes can be NDN servers, content routers, and other devices. For example, the transceiver (1604) can transmit RF signals via an antenna and transmit signals based on various communication networks.

[0131] In addition, as an example, MIMO technology, beamforming, etc. can be applied as antenna technology, and are not limited to the above-described embodiment. In addition, the signal transmitted and received through the transceiver (1604) can be modulated and demodulated and controlled by the processor (1603), and are not limited to the above-described embodiment.

[0132] The various embodiments of the present disclosure are not intended to list all possible combinations but rather to illustrate representative aspects of the present disclosure, and the matters described in the various embodiments may be applied independently or in combinations of two or more.

Claims

1. In a device for building preprocessing data for learning an artificial intelligence model for a rehabilitation exercise guide, Input section for entering patient chart data; Memory for storing the above chart data; and Obtain the above chart data through the above input section, Store the above chart data in the above memory, Scan the above chart data, Extract specific data from the scanned chart data, Including a control unit that stores the extracted specific data in a memory based on a predetermined rule, The above specific data is saved and used to learn the artificial intelligence model for the rehabilitation exercise guide. A device for building preprocessing data for learning an artificial intelligence model for a rehabilitation exercise guide.

2. In paragraph 1, the control unit, Extracting a ROM string containing shoulder angle information from the above chart data, A device for building preprocessing data for learning an artificial intelligence model for a rehabilitation exercise guide.

3. In the second paragraph, the control unit, The numbers following the above ROM string correspond sequentially to predetermined values ​​related to shoulder angle information. A device for building preprocessing data for learning an artificial intelligence model for a rehabilitation exercise guide.

4. In paragraph 1, the control unit, Extracting the MMT string containing the strength-related degree from the above chart data, A device for building preprocessing data for learning an artificial intelligence model for a rehabilitation exercise guide.

5. In paragraph 4, the control unit, Separating the above extracted MMT string into two pieces of information, A device for building preprocessing data for learning an artificial intelligence model for a rehabilitation exercise guide.

6. In paragraph 1, Further comprising a display for displaying a graphic image, The above control unit MRI images are acquired through the above input unit, In the acquired MRI image, a predetermined shape is determined as a region of interest (ROI), Controlling the above display to display the determined area of ​​interest, A device for building preprocessing data for learning an artificial intelligence model for a rehabilitation exercise guide.

7. In paragraph 1, the control unit, Scanning the first region, which is an region of interest and a region spaced a predetermined distance from the region of interest, A device for building preprocessing data for learning an artificial intelligence model for a rehabilitation exercise guide.

8. In paragraph 7, the control unit, If there is no gap point between the above area of ​​interest and the first area, the surgical site is determined as a case with good suture. A device for building preprocessing data for learning an artificial intelligence model for a rehabilitation exercise guide.

9. In paragraph 7, the control unit, If there is a point of separation between the above area of ​​interest and the first area, the surgical site is determined as a ruptured case. A device for building preprocessing data for learning an artificial intelligence model for a rehabilitation exercise guide.

10. In paragraph 9, the control unit, Controlling the display so that the above-mentioned separation point is displayed so as to be separated from other areas; A device for building preprocessing data for learning an artificial intelligence model for a rehabilitation exercise guide.

11. In the method of constructing preprocessing data for learning the artificial intelligence model of the rehabilitation exercise guide, A step of obtaining patient chart data through the input unit; A step of scanning the above chart data; A step of extracting specific data from the scanned chart data; and A step of storing the extracted specific data in memory based on a predetermined rule, The above specific data is used to learn the artificial intelligence model for rehabilitation exercise guide. A method for constructing preprocessing data for training an artificial intelligence model for rehabilitation exercise guidance.

12. In paragraph 11, A step of extracting a ROM string containing shoulder angle information from the above chart data; and Further comprising a step of sequentially corresponding the numbers after the above ROM string to predetermined values ​​related to shoulder angle information. A method for constructing preprocessing data for training an artificial intelligence model for rehabilitation exercise guidance.

13. In paragraph 11, A step of extracting an MMT string including a strength-related degree from the above chart data; and Further comprising a step of separating the extracted MMT string into two pieces of information. A method for constructing preprocessing data for training an artificial intelligence model for rehabilitation exercise guidance.

14. In paragraph 11, A step of acquiring an MRI image through the input unit; A step of determining a predetermined shape as a region of interest (ROI) in the acquired MRI image; and Further comprising a step of controlling the display to display the determined region of interest. A method for constructing preprocessing data for training an artificial intelligence model for rehabilitation exercise guidance.

15. In paragraph 11, A step of scanning a first region which is a region of interest and a region spaced apart from the region of interest by a predetermined distance; A step of determining the surgical site as a well-sutured case if there is no gap point between the above region of interest and the first region; If there is a gap point between the above region of interest and the first region, a step of determining the surgical site as a ruptured case; and Further comprising a step of controlling the display to display the separation point so as to be distinguished from other areas. A method for constructing preprocessing data for training an artificial intelligence model for rehabilitation exercise guidance.

Images